summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-03-31 20:05:01 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2020-03-31 20:05:01 +0300
commit3cd86a58f7734bf9cef38f6f899608ebcaa3da13 (patch)
tree6ae5b8109011ee40deef645a9701e2d8dc4e4fce /arch
parenta8222fd5b80c7ec83f257060670becbeea9b50b9 (diff)
parentb2a84de2a2deb76a6a51609845341f508c518c03 (diff)
downloadlinux-3cd86a58f7734bf9cef38f6f899608ebcaa3da13.tar.xz
Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux
Pull arm64 updates from Catalin Marinas: "The bulk is in-kernel pointer authentication, activity monitors and lots of asm symbol annotations. I also queued the sys_mremap() patch commenting the asymmetry in the address untagging. Summary: - In-kernel Pointer Authentication support (previously only offered to user space). - ARM Activity Monitors (AMU) extension support allowing better CPU utilisation numbers for the scheduler (frequency invariance). - Memory hot-remove support for arm64. - Lots of asm annotations (SYM_*) in preparation for the in-kernel Branch Target Identification (BTI) support. - arm64 perf updates: ARMv8.5-PMU 64-bit counters, refactoring the PMU init callbacks, support for new DT compatibles. - IPv6 header checksum optimisation. - Fixes: SDEI (software delegated exception interface) double-lock on hibernate with shared events. - Minor clean-ups and refactoring: cpu_ops accessor, cpu_do_switch_mm() converted to C, cpufeature finalisation helper. - sys_mremap() comment explaining the asymmetric address untagging behaviour" * tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (81 commits) mm/mremap: Add comment explaining the untagging behaviour of mremap() arm64: head: Convert install_el2_stub to SYM_INNER_LABEL arm64: Introduce get_cpu_ops() helper function arm64: Rename cpu_read_ops() to init_cpu_ops() arm64: Declare ACPI parking protocol CPU operation if needed arm64: move kimage_vaddr to .rodata arm64: use mov_q instead of literal ldr arm64: Kconfig: verify binutils support for ARM64_PTR_AUTH lkdtm: arm64: test kernel pointer authentication arm64: compile the kernel with ptrauth return address signing kconfig: Add support for 'as-option' arm64: suspend: restore the kernel ptrauth keys arm64: __show_regs: strip PAC from lr in printk arm64: unwind: strip PAC from kernel addresses arm64: mask PAC bits of __builtin_return_address arm64: initialize ptrauth keys for kernel booting task arm64: initialize and switch ptrauth kernel keys arm64: enable ptrauth earlier arm64: cpufeature: handle conflicts based on capability arm64: cpufeature: Move cpu capability helpers inside C file ...
Diffstat (limited to 'arch')
-rw-r--r--arch/arm64/Kconfig69
-rw-r--r--arch/arm64/Makefile11
-rw-r--r--arch/arm64/crypto/aes-ce.S4
-rw-r--r--arch/arm64/crypto/aes-modes.S48
-rw-r--r--arch/arm64/crypto/aes-neon.S4
-rw-r--r--arch/arm64/crypto/ghash-ce-core.S16
-rw-r--r--arch/arm64/include/asm/asm_pointer_auth.h65
-rw-r--r--arch/arm64/include/asm/assembler.h16
-rw-r--r--arch/arm64/include/asm/checksum.h7
-rw-r--r--arch/arm64/include/asm/compiler.h24
-rw-r--r--arch/arm64/include/asm/cpu_ops.h8
-rw-r--r--arch/arm64/include/asm/cpucaps.h5
-rw-r--r--arch/arm64/include/asm/cpufeature.h125
-rw-r--r--arch/arm64/include/asm/esr.h2
-rw-r--r--arch/arm64/include/asm/kvm_arm.h1
-rw-r--r--arch/arm64/include/asm/kvm_asm.h4
-rw-r--r--arch/arm64/include/asm/kvm_mmu.h9
-rw-r--r--arch/arm64/include/asm/memory.h1
-rw-r--r--arch/arm64/include/asm/mmu.h10
-rw-r--r--arch/arm64/include/asm/mmu_context.h2
-rw-r--r--arch/arm64/include/asm/page.h4
-rw-r--r--arch/arm64/include/asm/perf_event.h3
-rw-r--r--arch/arm64/include/asm/pointer_auth.h50
-rw-r--r--arch/arm64/include/asm/proc-fns.h2
-rw-r--r--arch/arm64/include/asm/processor.h3
-rw-r--r--arch/arm64/include/asm/smp.h12
-rw-r--r--arch/arm64/include/asm/stackprotector.h5
-rw-r--r--arch/arm64/include/asm/sysreg.h48
-rw-r--r--arch/arm64/include/asm/topology.h9
-rw-r--r--arch/arm64/kernel/Makefile2
-rw-r--r--arch/arm64/kernel/armv8_deprecated.c2
-rw-r--r--arch/arm64/kernel/asm-offsets.c16
-rw-r--r--arch/arm64/kernel/cpu-reset.S2
-rw-r--r--arch/arm64/kernel/cpu_errata.c18
-rw-r--r--arch/arm64/kernel/cpu_ops.c11
-rw-r--r--arch/arm64/kernel/cpufeature.c165
-rw-r--r--arch/arm64/kernel/cpuidle.c9
-rw-r--r--arch/arm64/kernel/entry-common.c2
-rw-r--r--arch/arm64/kernel/entry-ftrace.S48
-rw-r--r--arch/arm64/kernel/entry.S121
-rw-r--r--arch/arm64/kernel/head.S86
-rw-r--r--arch/arm64/kernel/hibernate-asm.S2
-rw-r--r--arch/arm64/kernel/hyp-stub.S2
-rw-r--r--arch/arm64/kernel/machine_kexec_file.c2
-rw-r--r--arch/arm64/kernel/perf_event.c338
-rw-r--r--arch/arm64/kernel/pointer_auth.c7
-rw-r--r--arch/arm64/kernel/process.c5
-rw-r--r--arch/arm64/kernel/ptrace.c16
-rw-r--r--arch/arm64/kernel/relocate_kernel.S4
-rw-r--r--arch/arm64/kernel/setup.c8
-rw-r--r--arch/arm64/kernel/sleep.S2
-rw-r--r--arch/arm64/kernel/smp.c159
-rw-r--r--arch/arm64/kernel/stacktrace.c5
-rw-r--r--arch/arm64/kernel/topology.c180
-rw-r--r--arch/arm64/kernel/vdso/sigreturn.S4
-rw-r--r--arch/arm64/kernel/vdso32/sigreturn.S23
-rw-r--r--arch/arm64/kvm/hyp-init.S18
-rw-r--r--arch/arm64/kvm/hyp.S4
-rw-r--r--arch/arm64/kvm/hyp/fpsimd.S8
-rw-r--r--arch/arm64/kvm/hyp/hyp-entry.S27
-rw-r--r--arch/arm64/kvm/hyp/switch.c28
-rw-r--r--arch/arm64/kvm/hyp/sysreg-sr.c8
-rw-r--r--arch/arm64/kvm/hyp/tlb.c8
-rw-r--r--arch/arm64/kvm/sys_regs.c103
-rw-r--r--arch/arm64/lib/csum.c27
-rw-r--r--arch/arm64/lib/strcmp.S2
-rw-r--r--arch/arm64/mm/context.c32
-rw-r--r--arch/arm64/mm/mmu.c379
-rw-r--r--arch/arm64/mm/proc.S104
-rw-r--r--arch/arm64/mm/ptdump_debugfs.c4
70 files changed, 1908 insertions, 650 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index c6c32fb7f546..6e41c4b62607 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -117,6 +117,7 @@ config ARM64
select HAVE_ALIGNED_STRUCT_PAGE if SLUB
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_BITREVERSE
+ select HAVE_ARCH_COMPILER_H
select HAVE_ARCH_HUGE_VMAP
select HAVE_ARCH_JUMP_LABEL
select HAVE_ARCH_JUMP_LABEL_RELATIVE
@@ -280,6 +281,9 @@ config ZONE_DMA32
config ARCH_ENABLE_MEMORY_HOTPLUG
def_bool y
+config ARCH_ENABLE_MEMORY_HOTREMOVE
+ def_bool y
+
config SMP
def_bool y
@@ -951,11 +955,11 @@ config HOTPLUG_CPU
# Common NUMA Features
config NUMA
- bool "Numa Memory Allocation and Scheduler Support"
+ bool "NUMA Memory Allocation and Scheduler Support"
select ACPI_NUMA if ACPI
select OF_NUMA
help
- Enable NUMA (Non Uniform Memory Access) support.
+ Enable NUMA (Non-Uniform Memory Access) support.
The kernel will try to allocate memory used by a CPU on the
local memory of the CPU and add some more
@@ -1497,6 +1501,9 @@ config ARM64_PTR_AUTH
bool "Enable support for pointer authentication"
default y
depends on !KVM || ARM64_VHE
+ depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_PAC
+ depends on CC_IS_GCC || (CC_IS_CLANG && AS_HAS_CFI_NEGATE_RA_STATE)
+ depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS)
help
Pointer authentication (part of the ARMv8.3 Extensions) provides
instructions for signing and authenticating pointers against secret
@@ -1504,16 +1511,72 @@ config ARM64_PTR_AUTH
and other attacks.
This option enables these instructions at EL0 (i.e. for userspace).
-
Choosing this option will cause the kernel to initialise secret keys
for each process at exec() time, with these keys being
context-switched along with the process.
+ If the compiler supports the -mbranch-protection or
+ -msign-return-address flag (e.g. GCC 7 or later), then this option
+ will also cause the kernel itself to be compiled with return address
+ protection. In this case, and if the target hardware is known to
+ support pointer authentication, then CONFIG_STACKPROTECTOR can be
+ disabled with minimal loss of protection.
+
The feature is detected at runtime. If the feature is not present in
hardware it will not be advertised to userspace/KVM guest nor will it
be enabled. However, KVM guest also require VHE mode and hence
CONFIG_ARM64_VHE=y option to use this feature.
+ If the feature is present on the boot CPU but not on a late CPU, then
+ the late CPU will be parked. Also, if the boot CPU does not have
+ address auth and the late CPU has then the late CPU will still boot
+ but with the feature disabled. On such a system, this option should
+ not be selected.
+
+ This feature works with FUNCTION_GRAPH_TRACER option only if
+ DYNAMIC_FTRACE_WITH_REGS is enabled.
+
+config CC_HAS_BRANCH_PROT_PAC_RET
+ # GCC 9 or later, clang 8 or later
+ def_bool $(cc-option,-mbranch-protection=pac-ret+leaf)
+
+config CC_HAS_SIGN_RETURN_ADDRESS
+ # GCC 7, 8
+ def_bool $(cc-option,-msign-return-address=all)
+
+config AS_HAS_PAC
+ def_bool $(as-option,-Wa$(comma)-march=armv8.3-a)
+
+config AS_HAS_CFI_NEGATE_RA_STATE
+ def_bool $(as-instr,.cfi_startproc\n.cfi_negate_ra_state\n.cfi_endproc\n)
+
+endmenu
+
+menu "ARMv8.4 architectural features"
+
+config ARM64_AMU_EXTN
+ bool "Enable support for the Activity Monitors Unit CPU extension"
+ default y
+ help
+ The activity monitors extension is an optional extension introduced
+ by the ARMv8.4 CPU architecture. This enables support for version 1
+ of the activity monitors architecture, AMUv1.
+
+ To enable the use of this extension on CPUs that implement it, say Y.
+
+ Note that for architectural reasons, firmware _must_ implement AMU
+ support when running on CPUs that present the activity monitors
+ extension. The required support is present in:
+ * Version 1.5 and later of the ARM Trusted Firmware
+
+ For kernels that have this configuration enabled but boot with broken
+ firmware, you may need to say N here until the firmware is fixed.
+ Otherwise you may experience firmware panics or lockups when
+ accessing the counter registers. Even if you are not observing these
+ symptoms, the values returned by the register reads might not
+ correctly reflect reality. Most commonly, the value read will be 0,
+ indicating that the counter is not enabled.
+
endmenu
menu "ARMv8.5 architectural features"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index dca1a97751ab..f15f92ba53e6 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -65,6 +65,17 @@ stack_protector_prepare: prepare0
include/generated/asm-offsets.h))
endif
+ifeq ($(CONFIG_ARM64_PTR_AUTH),y)
+branch-prot-flags-$(CONFIG_CC_HAS_SIGN_RETURN_ADDRESS) := -msign-return-address=all
+branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET) := -mbranch-protection=pac-ret+leaf
+# -march=armv8.3-a enables the non-nops instructions for PAC, to avoid the
+# compiler to generate them and consequently to break the single image contract
+# we pass it only to the assembler. This option is utilized only in case of non
+# integrated assemblers.
+branch-prot-flags-$(CONFIG_AS_HAS_PAC) += -Wa,-march=armv8.3-a
+KBUILD_CFLAGS += $(branch-prot-flags-y)
+endif
+
ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
KBUILD_CPPFLAGS += -mbig-endian
CHECKFLAGS += -D__AARCH64EB__
diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S
index 45062553467f..1dc5bbbfeed2 100644
--- a/arch/arm64/crypto/aes-ce.S
+++ b/arch/arm64/crypto/aes-ce.S
@@ -9,8 +9,8 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
-#define AES_ENTRY(func) SYM_FUNC_START(ce_ ## func)
-#define AES_ENDPROC(func) SYM_FUNC_END(ce_ ## func)
+#define AES_FUNC_START(func) SYM_FUNC_START(ce_ ## func)
+#define AES_FUNC_END(func) SYM_FUNC_END(ce_ ## func)
.arch armv8-a+crypto
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
index 8a2faa42b57e..cf618d8f6cec 100644
--- a/arch/arm64/crypto/aes-modes.S
+++ b/arch/arm64/crypto/aes-modes.S
@@ -51,7 +51,7 @@ SYM_FUNC_END(aes_decrypt_block5x)
* int blocks)
*/
-AES_ENTRY(aes_ecb_encrypt)
+AES_FUNC_START(aes_ecb_encrypt)
stp x29, x30, [sp, #-16]!
mov x29, sp
@@ -79,10 +79,10 @@ ST5( st1 {v4.16b}, [x0], #16 )
.Lecbencout:
ldp x29, x30, [sp], #16
ret
-AES_ENDPROC(aes_ecb_encrypt)
+AES_FUNC_END(aes_ecb_encrypt)
-AES_ENTRY(aes_ecb_decrypt)
+AES_FUNC_START(aes_ecb_decrypt)
stp x29, x30, [sp, #-16]!
mov x29, sp
@@ -110,7 +110,7 @@ ST5( st1 {v4.16b}, [x0], #16 )
.Lecbdecout:
ldp x29, x30, [sp], #16
ret
-AES_ENDPROC(aes_ecb_decrypt)
+AES_FUNC_END(aes_ecb_decrypt)
/*
@@ -126,7 +126,7 @@ AES_ENDPROC(aes_ecb_decrypt)
* u32 const rk2[]);
*/
-AES_ENTRY(aes_essiv_cbc_encrypt)
+AES_FUNC_START(aes_essiv_cbc_encrypt)
ld1 {v4.16b}, [x5] /* get iv */
mov w8, #14 /* AES-256: 14 rounds */
@@ -135,7 +135,7 @@ AES_ENTRY(aes_essiv_cbc_encrypt)
enc_switch_key w3, x2, x6
b .Lcbcencloop4x
-AES_ENTRY(aes_cbc_encrypt)
+AES_FUNC_START(aes_cbc_encrypt)
ld1 {v4.16b}, [x5] /* get iv */
enc_prepare w3, x2, x6
@@ -167,10 +167,10 @@ AES_ENTRY(aes_cbc_encrypt)
.Lcbcencout:
st1 {v4.16b}, [x5] /* return iv */
ret
-AES_ENDPROC(aes_cbc_encrypt)
-AES_ENDPROC(aes_essiv_cbc_encrypt)
+AES_FUNC_END(aes_cbc_encrypt)
+AES_FUNC_END(aes_essiv_cbc_encrypt)
-AES_ENTRY(aes_essiv_cbc_decrypt)
+AES_FUNC_START(aes_essiv_cbc_decrypt)
stp x29, x30, [sp, #-16]!
mov x29, sp
@@ -181,7 +181,7 @@ AES_ENTRY(aes_essiv_cbc_decrypt)
encrypt_block cbciv, w8, x6, x7, w9
b .Lessivcbcdecstart
-AES_ENTRY(aes_cbc_decrypt)
+AES_FUNC_START(aes_cbc_decrypt)
stp x29, x30, [sp, #-16]!
mov x29, sp
@@ -238,8 +238,8 @@ ST5( st1 {v4.16b}, [x0], #16 )
st1 {cbciv.16b}, [x5] /* return iv */
ldp x29, x30, [sp], #16
ret
-AES_ENDPROC(aes_cbc_decrypt)
-AES_ENDPROC(aes_essiv_cbc_decrypt)
+AES_FUNC_END(aes_cbc_decrypt)
+AES_FUNC_END(aes_essiv_cbc_decrypt)
/*
@@ -249,7 +249,7 @@ AES_ENDPROC(aes_essiv_cbc_decrypt)
* int rounds, int bytes, u8 const iv[])
*/
-AES_ENTRY(aes_cbc_cts_encrypt)
+AES_FUNC_START(aes_cbc_cts_encrypt)
adr_l x8, .Lcts_permute_table
sub x4, x4, #16
add x9, x8, #32
@@ -276,9 +276,9 @@ AES_ENTRY(aes_cbc_cts_encrypt)
st1 {v0.16b}, [x4] /* overlapping stores */
st1 {v1.16b}, [x0]
ret
-AES_ENDPROC(aes_cbc_cts_encrypt)
+AES_FUNC_END(aes_cbc_cts_encrypt)
-AES_ENTRY(aes_cbc_cts_decrypt)
+AES_FUNC_START(aes_cbc_cts_decrypt)
adr_l x8, .Lcts_permute_table
sub x4, x4, #16
add x9, x8, #32
@@ -305,7 +305,7 @@ AES_ENTRY(aes_cbc_cts_decrypt)
st1 {v2.16b}, [x4] /* overlapping stores */
st1 {v0.16b}, [x0]
ret
-AES_ENDPROC(aes_cbc_cts_decrypt)
+AES_FUNC_END(aes_cbc_cts_decrypt)
.section ".rodata", "a"
.align 6
@@ -324,7 +324,7 @@ AES_ENDPROC(aes_cbc_cts_decrypt)
* int blocks, u8 ctr[])
*/
-AES_ENTRY(aes_ctr_encrypt)
+AES_FUNC_START(aes_ctr_encrypt)
stp x29, x30, [sp, #-16]!
mov x29, sp
@@ -409,7 +409,7 @@ ST5( st1 {v4.16b}, [x0], #16 )
rev x7, x7
ins vctr.d[0], x7
b .Lctrcarrydone
-AES_ENDPROC(aes_ctr_encrypt)
+AES_FUNC_END(aes_ctr_encrypt)
/*
@@ -433,7 +433,7 @@ AES_ENDPROC(aes_ctr_encrypt)
uzp1 xtsmask.4s, xtsmask.4s, \tmp\().4s
.endm
-AES_ENTRY(aes_xts_encrypt)
+AES_FUNC_START(aes_xts_encrypt)
stp x29, x30, [sp, #-16]!
mov x29, sp
@@ -518,9 +518,9 @@ AES_ENTRY(aes_xts_encrypt)
st1 {v2.16b}, [x4] /* overlapping stores */
mov w4, wzr
b .Lxtsencctsout
-AES_ENDPROC(aes_xts_encrypt)
+AES_FUNC_END(aes_xts_encrypt)
-AES_ENTRY(aes_xts_decrypt)
+AES_FUNC_START(aes_xts_decrypt)
stp x29, x30, [sp, #-16]!
mov x29, sp
@@ -612,13 +612,13 @@ AES_ENTRY(aes_xts_decrypt)
st1 {v2.16b}, [x4] /* overlapping stores */
mov w4, wzr
b .Lxtsdecctsout
-AES_ENDPROC(aes_xts_decrypt)
+AES_FUNC_END(aes_xts_decrypt)
/*
* aes_mac_update(u8 const in[], u32 const rk[], int rounds,
* int blocks, u8 dg[], int enc_before, int enc_after)
*/
-AES_ENTRY(aes_mac_update)
+AES_FUNC_START(aes_mac_update)
frame_push 6
mov x19, x0
@@ -676,4 +676,4 @@ AES_ENTRY(aes_mac_update)
ld1 {v0.16b}, [x23] /* get dg */
enc_prepare w21, x20, x0
b .Lmacloop4x
-AES_ENDPROC(aes_mac_update)
+AES_FUNC_END(aes_mac_update)
diff --git a/arch/arm64/crypto/aes-neon.S b/arch/arm64/crypto/aes-neon.S
index 247d34ddaab0..e47d3ec2cfb4 100644
--- a/arch/arm64/crypto/aes-neon.S
+++ b/arch/arm64/crypto/aes-neon.S
@@ -8,8 +8,8 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
-#define AES_ENTRY(func) SYM_FUNC_START(neon_ ## func)
-#define AES_ENDPROC(func) SYM_FUNC_END(neon_ ## func)
+#define AES_FUNC_START(func) SYM_FUNC_START(neon_ ## func)
+#define AES_FUNC_END(func) SYM_FUNC_END(neon_ ## func)
xtsmask .req v7
cbciv .req v7
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index 084c6a30b03a..6b958dcdf136 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -587,20 +587,20 @@ CPU_LE( rev w8, w8 )
* struct ghash_key const *k, u64 dg[], u8 ctr[],
* int rounds, u8 tag)
*/
-ENTRY(pmull_gcm_encrypt)
+SYM_FUNC_START(pmull_gcm_encrypt)
pmull_gcm_do_crypt 1
-ENDPROC(pmull_gcm_encrypt)
+SYM_FUNC_END(pmull_gcm_encrypt)
/*
* void pmull_gcm_decrypt(int blocks, u8 dst[], const u8 src[],
* struct ghash_key const *k, u64 dg[], u8 ctr[],
* int rounds, u8 tag)
*/
-ENTRY(pmull_gcm_decrypt)
+SYM_FUNC_START(pmull_gcm_decrypt)
pmull_gcm_do_crypt 0
-ENDPROC(pmull_gcm_decrypt)
+SYM_FUNC_END(pmull_gcm_decrypt)
-pmull_gcm_ghash_4x:
+SYM_FUNC_START_LOCAL(pmull_gcm_ghash_4x)
movi MASK.16b, #0xe1
shl MASK.2d, MASK.2d, #57
@@ -681,9 +681,9 @@ pmull_gcm_ghash_4x:
eor XL.16b, XL.16b, T2.16b
ret
-ENDPROC(pmull_gcm_ghash_4x)
+SYM_FUNC_END(pmull_gcm_ghash_4x)
-pmull_gcm_enc_4x:
+SYM_FUNC_START_LOCAL(pmull_gcm_enc_4x)
ld1 {KS0.16b}, [x5] // load upper counter
sub w10, w8, #4
sub w11, w8, #3
@@ -746,7 +746,7 @@ pmull_gcm_enc_4x:
eor INP3.16b, INP3.16b, KS3.16b
ret
-ENDPROC(pmull_gcm_enc_4x)
+SYM_FUNC_END(pmull_gcm_enc_4x)
.section ".rodata", "a"
.align 6
diff --git a/arch/arm64/include/asm/asm_pointer_auth.h b/arch/arm64/include/asm/asm_pointer_auth.h
new file mode 100644
index 000000000000..ce2a8486992b
--- /dev/null
+++ b/arch/arm64/include/asm/asm_pointer_auth.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_ASM_POINTER_AUTH_H
+#define __ASM_ASM_POINTER_AUTH_H
+
+#include <asm/alternative.h>
+#include <asm/asm-offsets.h>
+#include <asm/cpufeature.h>
+#include <asm/sysreg.h>
+
+#ifdef CONFIG_ARM64_PTR_AUTH
+/*
+ * thread.keys_user.ap* as offset exceeds the #imm offset range
+ * so use the base value of ldp as thread.keys_user and offset as
+ * thread.keys_user.ap*.
+ */
+ .macro ptrauth_keys_install_user tsk, tmp1, tmp2, tmp3
+ mov \tmp1, #THREAD_KEYS_USER
+ add \tmp1, \tsk, \tmp1
+alternative_if_not ARM64_HAS_ADDRESS_AUTH
+ b .Laddr_auth_skip_\@
+alternative_else_nop_endif
+ ldp \tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APIA]
+ msr_s SYS_APIAKEYLO_EL1, \tmp2
+ msr_s SYS_APIAKEYHI_EL1, \tmp3
+ ldp \tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APIB]
+ msr_s SYS_APIBKEYLO_EL1, \tmp2
+ msr_s SYS_APIBKEYHI_EL1, \tmp3
+ ldp \tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APDA]
+ msr_s SYS_APDAKEYLO_EL1, \tmp2
+ msr_s SYS_APDAKEYHI_EL1, \tmp3
+ ldp \tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APDB]
+ msr_s SYS_APDBKEYLO_EL1, \tmp2
+ msr_s SYS_APDBKEYHI_EL1, \tmp3
+.Laddr_auth_skip_\@:
+alternative_if ARM64_HAS_GENERIC_AUTH
+ ldp \tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APGA]
+ msr_s SYS_APGAKEYLO_EL1, \tmp2
+ msr_s SYS_APGAKEYHI_EL1, \tmp3
+alternative_else_nop_endif
+ .endm
+
+ .macro ptrauth_keys_install_kernel tsk, sync, tmp1, tmp2, tmp3
+alternative_if ARM64_HAS_ADDRESS_AUTH
+ mov \tmp1, #THREAD_KEYS_KERNEL
+ add \tmp1, \tsk, \tmp1
+ ldp \tmp2, \tmp3, [\tmp1, #PTRAUTH_KERNEL_KEY_APIA]
+ msr_s SYS_APIAKEYLO_EL1, \tmp2
+ msr_s SYS_APIAKEYHI_EL1, \tmp3
+ .if \sync == 1
+ isb
+ .endif
+alternative_else_nop_endif
+ .endm
+
+#else /* CONFIG_ARM64_PTR_AUTH */
+
+ .macro ptrauth_keys_install_user tsk, tmp1, tmp2, tmp3
+ .endm
+
+ .macro ptrauth_keys_install_kernel tsk, sync, tmp1, tmp2, tmp3
+ .endm
+
+#endif /* CONFIG_ARM64_PTR_AUTH */
+
+#endif /* __ASM_ASM_POINTER_AUTH_H */
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index aca337d79d12..0bff325117b4 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -257,12 +257,6 @@ alternative_endif
.endm
/*
- * mmid - get context id from mm pointer (mm->context.id)
- */
- .macro mmid, rd, rn
- ldr \rd, [\rn, #MM_CONTEXT_ID]
- .endm
-/*
* 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
*/
@@ -431,6 +425,16 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU
.endm
/*
+ * reset_amuserenr_el0 - reset AMUSERENR_EL0 if AMUv1 present
+ */
+ .macro reset_amuserenr_el0, tmpreg
+ mrs \tmpreg, id_aa64pfr0_el1 // Check ID_AA64PFR0_EL1
+ ubfx \tmpreg, \tmpreg, #ID_AA64PFR0_AMU_SHIFT, #4
+ cbz \tmpreg, .Lskip_\@ // Skip if no AMU present
+ msr_s SYS_AMUSERENR_EL0, xzr // Disable AMU access from EL0
+.Lskip_\@:
+ .endm
+/*
* copy_page - copy src to dest using temp registers t1-t8
*/
.macro copy_page dest:req src:req t1:req t2:req t3:req t4:req t5:req t6:req t7:req t8:req
diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h
index 8d2a7de39744..b6f7bc6da5fb 100644
--- a/arch/arm64/include/asm/checksum.h
+++ b/arch/arm64/include/asm/checksum.h
@@ -5,7 +5,12 @@
#ifndef __ASM_CHECKSUM_H
#define __ASM_CHECKSUM_H
-#include <linux/types.h>
+#include <linux/in6.h>
+
+#define _HAVE_ARCH_IPV6_CSUM
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+ const struct in6_addr *daddr,
+ __u32 len, __u8 proto, __wsum sum);
static inline __sum16 csum_fold(__wsum csum)
{
diff --git a/arch/arm64/include/asm/compiler.h b/arch/arm64/include/asm/compiler.h
new file mode 100644
index 000000000000..eece20d2c55f
--- /dev/null
+++ b/arch/arm64/include/asm/compiler.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_COMPILER_H
+#define __ASM_COMPILER_H
+
+#if defined(CONFIG_ARM64_PTR_AUTH)
+
+/*
+ * The EL0/EL1 pointer bits used by a pointer authentication code.
+ * This is dependent on TBI0/TBI1 being enabled, or bits 63:56 would also apply.
+ */
+#define ptrauth_user_pac_mask() GENMASK_ULL(54, vabits_actual)
+#define ptrauth_kernel_pac_mask() GENMASK_ULL(63, vabits_actual)
+
+/* Valid for EL0 TTBR0 and EL1 TTBR1 instruction pointers */
+#define ptrauth_clear_pac(ptr) \
+ ((ptr & BIT_ULL(55)) ? (ptr | ptrauth_kernel_pac_mask()) : \
+ (ptr & ~ptrauth_user_pac_mask()))
+
+#define __builtin_return_address(val) \
+ (void *)(ptrauth_clear_pac((unsigned long)__builtin_return_address(val)))
+
+#endif /* CONFIG_ARM64_PTR_AUTH */
+
+#endif /* __ASM_COMPILER_H */
diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h
index 86aabf1e0199..d28e8f37d3b4 100644
--- a/arch/arm64/include/asm/cpu_ops.h
+++ b/arch/arm64/include/asm/cpu_ops.h
@@ -55,12 +55,12 @@ struct cpu_operations {
#endif
};
-extern const struct cpu_operations *cpu_ops[NR_CPUS];
-int __init cpu_read_ops(int cpu);
+int __init init_cpu_ops(int cpu);
+extern const struct cpu_operations *get_cpu_ops(int cpu);
-static inline void __init cpu_read_bootcpu_ops(void)
+static inline void __init init_bootcpu_ops(void)
{
- cpu_read_ops(0);
+ init_cpu_ops(0);
}
#endif /* ifndef __ASM_CPU_OPS_H */
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 865e0253fc1e..8eb5a088ae65 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -58,7 +58,10 @@
#define ARM64_WORKAROUND_SPECULATIVE_AT_NVHE 48
#define ARM64_HAS_E0PD 49
#define ARM64_HAS_RNG 50
+#define ARM64_HAS_AMU_EXTN 51
+#define ARM64_HAS_ADDRESS_AUTH 52
+#define ARM64_HAS_GENERIC_AUTH 53
-#define ARM64_NCAPS 51
+#define ARM64_NCAPS 54
#endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 2a746b99e937..afe08251ff95 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -208,6 +208,10 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
* In some non-typical cases either both (a) and (b), or neither,
* should be permitted. This can be described by including neither
* or both flags in the capability's type field.
+ *
+ * In case of a conflict, the CPU is prevented from booting. If the
+ * ARM64_CPUCAP_PANIC_ON_CONFLICT flag is specified for the capability,
+ * then a kernel panic is triggered.
*/
@@ -240,6 +244,8 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
#define ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU ((u16)BIT(4))
/* Is it safe for a late CPU to miss this capability when system has it */
#define ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU ((u16)BIT(5))
+/* Panic when a conflict is detected */
+#define ARM64_CPUCAP_PANIC_ON_CONFLICT ((u16)BIT(6))
/*
* CPU errata workarounds that need to be enabled at boot time if one or
@@ -279,9 +285,20 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
/*
* CPU feature used early in the boot based on the boot CPU. All secondary
- * CPUs must match the state of the capability as detected by the boot CPU.
+ * CPUs must match the state of the capability as detected by the boot CPU. In
+ * case of a conflict, a kernel panic is triggered.
+ */
+#define ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE \
+ (ARM64_CPUCAP_SCOPE_BOOT_CPU | ARM64_CPUCAP_PANIC_ON_CONFLICT)
+
+/*
+ * CPU feature used early in the boot based on the boot CPU. It is safe for a
+ * late CPU to have this feature even though the boot CPU hasn't enabled it,
+ * although the feature will not be used by Linux in this case. If the boot CPU
+ * has enabled this feature already, then every late CPU must have it.
*/
-#define ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE ARM64_CPUCAP_SCOPE_BOOT_CPU
+#define ARM64_CPUCAP_BOOT_CPU_FEATURE \
+ (ARM64_CPUCAP_SCOPE_BOOT_CPU | ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU)
struct arm64_cpu_capabilities {
const char *desc;
@@ -340,18 +357,6 @@ static inline int cpucap_default_scope(const struct arm64_cpu_capabilities *cap)
return cap->type & ARM64_CPUCAP_SCOPE_MASK;
}
-static inline bool
-cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap)
-{
- return !!(cap->type & ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU);
-}
-
-static inline bool
-cpucap_late_cpu_permitted(const struct arm64_cpu_capabilities *cap)
-{
- return !!(cap->type & ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU);
-}
-
/*
* Generic helper for handling capabilties with multiple (match,enable) pairs
* of call backs, sharing the same capability bit.
@@ -390,14 +395,16 @@ unsigned long cpu_get_elf_hwcap2(void);
#define cpu_set_named_feature(name) cpu_set_feature(cpu_feature(name))
#define cpu_have_named_feature(name) cpu_have_feature(cpu_feature(name))
-/* System capability check for constant caps */
-static __always_inline bool __cpus_have_const_cap(int num)
+static __always_inline bool system_capabilities_finalized(void)
{
- if (num >= ARM64_NCAPS)
- return false;
- return static_branch_unlikely(&cpu_hwcap_keys[num]);
+ return static_branch_likely(&arm64_const_caps_ready);
}
+/*
+ * Test for a capability with a runtime check.
+ *
+ * Before the capability is detected, this returns false.
+ */
static inline bool cpus_have_cap(unsigned int num)
{
if (num >= ARM64_NCAPS)
@@ -405,14 +412,53 @@ static inline bool cpus_have_cap(unsigned int num)
return test_bit(num, cpu_hwcaps);
}
+/*
+ * Test for a capability without a runtime check.
+ *
+ * Before capabilities are finalized, this returns false.
+ * After capabilities are finalized, this is patched to avoid a runtime check.
+ *
+ * @num must be a compile-time constant.
+ */
+static __always_inline bool __cpus_have_const_cap(int num)
+{
+ if (num >= ARM64_NCAPS)
+ return false;
+ return static_branch_unlikely(&cpu_hwcap_keys[num]);
+}
+
+/*
+ * Test for a capability, possibly with a runtime check.
+ *
+ * Before capabilities are finalized, this behaves as cpus_have_cap().
+ * After capabilities are finalized, this is patched to avoid a runtime check.
+ *
+ * @num must be a compile-time constant.
+ */
static __always_inline bool cpus_have_const_cap(int num)
{
- if (static_branch_likely(&arm64_const_caps_ready))
+ if (system_capabilities_finalized())
return __cpus_have_const_cap(num);
else
return cpus_have_cap(num);
}
+/*
+ * Test for a capability without a runtime check.
+ *
+ * Before capabilities are finalized, this will BUG().
+ * After capabilities are finalized, this is patched to avoid a runtime check.
+ *
+ * @num must be a compile-time constant.
+ */
+static __always_inline bool cpus_have_final_cap(int num)
+{
+ if (system_capabilities_finalized())
+ return __cpus_have_const_cap(num);
+ else
+ BUG();
+}
+
static inline void cpus_set_cap(unsigned int num)
{
if (num >= ARM64_NCAPS) {
@@ -447,6 +493,29 @@ cpuid_feature_extract_unsigned_field(u64 features, int field)
return cpuid_feature_extract_unsigned_field_width(features, field, 4);
}
+/*
+ * Fields that identify the version of the Performance Monitors Extension do
+ * not follow the standard ID scheme. See ARM DDI 0487E.a page D13-2825,
+ * "Alternative ID scheme used for the Performance Monitors Extension version".
+ */
+static inline u64 __attribute_const__
+cpuid_feature_cap_perfmon_field(u64 features, int field, u64 cap)
+{
+ u64 val = cpuid_feature_extract_unsigned_field(features, field);
+ u64 mask = GENMASK_ULL(field + 3, field);
+
+ /* Treat IMPLEMENTATION DEFINED functionality as unimplemented */
+ if (val == 0xf)
+ val = 0;
+
+ if (val > cap) {
+ features &= ~mask;
+ features |= (cap << field) & mask;
+ }
+
+ return features;
+}
+
static inline u64 arm64_ftr_mask(const struct arm64_ftr_bits *ftrp)
{
return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift);
@@ -590,15 +659,13 @@ static __always_inline bool system_supports_cnp(void)
static inline bool system_supports_address_auth(void)
{
return IS_ENABLED(CONFIG_ARM64_PTR_AUTH) &&
- (cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH_ARCH) ||
- cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH_IMP_DEF));
+ cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH);
}
static inline bool system_supports_generic_auth(void)
{
return IS_ENABLED(CONFIG_ARM64_PTR_AUTH) &&
- (cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH_ARCH) ||
- cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH_IMP_DEF));
+ cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH);
}
static inline bool system_uses_irq_prio_masking(void)
@@ -613,11 +680,6 @@ static inline bool system_has_prio_mask_debugging(void)
system_uses_irq_prio_masking();
}
-static inline bool system_capabilities_finalized(void)
-{
- return static_branch_likely(&arm64_const_caps_ready);
-}
-
#define ARM64_BP_HARDEN_UNKNOWN -1
#define ARM64_BP_HARDEN_WA_NEEDED 0
#define ARM64_BP_HARDEN_NOT_REQUIRED 1
@@ -678,6 +740,11 @@ static inline bool cpu_has_hw_af(void)
ID_AA64MMFR1_HADBS_SHIFT);
}
+#ifdef CONFIG_ARM64_AMU_EXTN
+/* Check whether the cpu supports the Activity Monitors Unit (AMU) */
+extern bool cpu_has_amu_feat(int cpu);
+#endif
+
#endif /* __ASSEMBLY__ */
#endif
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index cb29253ae86b..6a395a7e6707 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -60,7 +60,7 @@
#define ESR_ELx_EC_BKPT32 (0x38)
/* Unallocated EC: 0x39 */
#define ESR_ELx_EC_VECTOR32 (0x3A) /* EL2 only */
-/* Unallocted EC: 0x3B */
+/* Unallocated EC: 0x3B */
#define ESR_ELx_EC_BRK64 (0x3C)
/* Unallocated EC: 0x3D - 0x3F */
#define ESR_ELx_EC_MAX (0x3F)
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 6e5d839f42b5..51c1d9918999 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -267,6 +267,7 @@
/* Hyp Coprocessor Trap Register */
#define CPTR_EL2_TCPAC (1 << 31)
+#define CPTR_EL2_TAM (1 << 30)
#define CPTR_EL2_TTA (1 << 20)
#define CPTR_EL2_TFP (1 << CPTR_EL2_TFP_SHIFT)
#define CPTR_EL2_TZ (1 << 8)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 44a243754c1b..7c7eeeaab9fa 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -36,6 +36,8 @@
*/
#define KVM_VECTOR_PREAMBLE (2 * AARCH64_INSN_SIZE)
+#define __SMCCC_WORKAROUND_1_SMC_SZ 36
+
#ifndef __ASSEMBLY__
#include <linux/mm.h>
@@ -75,6 +77,8 @@ extern void __vgic_v3_init_lrs(void);
extern u32 __kvm_get_mdcr_el2(void);
+extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ];
+
/* Home-grown __this_cpu_{ptr,read} variants that always work at HYP */
#define __hyp_this_cpu_ptr(sym) \
({ \
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 785762860c63..30b0e8d6b895 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -481,7 +481,7 @@ static inline void *kvm_get_hyp_vector(void)
int slot = -1;
if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR) && data->fn) {
- vect = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs_start));
+ vect = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs));
slot = data->hyp_vectors_slot;
}
@@ -510,14 +510,13 @@ static inline int kvm_map_vectors(void)
* HBP + HEL2 -> use hardened vertors and use exec mapping
*/
if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR)) {
- __kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs_start);
+ __kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs);
__kvm_bp_vect_base = kern_hyp_va(__kvm_bp_vect_base);
}
if (cpus_have_const_cap(ARM64_HARDEN_EL2_VECTORS)) {
- phys_addr_t vect_pa = __pa_symbol(__bp_harden_hyp_vecs_start);
- unsigned long size = (__bp_harden_hyp_vecs_end -
- __bp_harden_hyp_vecs_start);
+ phys_addr_t vect_pa = __pa_symbol(__bp_harden_hyp_vecs);
+ unsigned long size = __BP_HARDEN_HYP_VECS_SZ;
/*
* Always allocate a spare vector slot, as we don't
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 4d94676e5a8b..2be67b232499 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -54,6 +54,7 @@
#define MODULES_VADDR (BPF_JIT_REGION_END)
#define MODULES_VSIZE (SZ_128M)
#define VMEMMAP_START (-VMEMMAP_SIZE - SZ_2M)
+#define VMEMMAP_END (VMEMMAP_START + VMEMMAP_SIZE)
#define PCI_IO_END (VMEMMAP_START - SZ_2M)
#define PCI_IO_START (PCI_IO_END - PCI_IO_SIZE)
#define FIXADDR_TOP (PCI_IO_START - SZ_2M)
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index d79ce6df9e12..68140fdd89d6 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -13,6 +13,7 @@
#define TTBR_ASID_MASK (UL(0xffff) << 48)
#define BP_HARDEN_EL2_SLOTS 4
+#define __BP_HARDEN_HYP_VECS_SZ (BP_HARDEN_EL2_SLOTS * SZ_2K)
#ifndef __ASSEMBLY__
@@ -23,9 +24,9 @@ typedef struct {
} mm_context_t;
/*
- * This macro is only used by the TLBI code, which cannot race with an
- * ASID change and therefore doesn't need to reload the counter using
- * atomic64_read.
+ * This macro is only used by the TLBI and low-level switch_mm() code,
+ * neither of which can race with an ASID change. We therefore don't
+ * need to reload the counter using atomic64_read().
*/
#define ASID(mm) ((mm)->context.id.counter & 0xffff)
@@ -43,7 +44,8 @@ struct bp_hardening_data {
#if (defined(CONFIG_HARDEN_BRANCH_PREDICTOR) || \
defined(CONFIG_HARDEN_EL2_VECTORS))
-extern char __bp_harden_hyp_vecs_start[], __bp_harden_hyp_vecs_end[];
+
+extern char __bp_harden_hyp_vecs[];
extern atomic_t arm64_el2_vector_last_slot;
#endif /* CONFIG_HARDEN_BRANCH_PREDICTOR || CONFIG_HARDEN_EL2_VECTORS */
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 3827ff4040a3..ab46187c6300 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -46,6 +46,8 @@ static inline void cpu_set_reserved_ttbr0(void)
isb();
}
+void cpu_do_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm);
+
static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm)
{
BUG_ON(pgd == swapper_pg_dir);
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index d39ddb258a04..75d6cd23a679 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -21,6 +21,10 @@ extern void __cpu_copy_user_page(void *to, const void *from,
extern void copy_page(void *to, const void *from);
extern void clear_page(void *to);
+#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
+ alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+
#define clear_user_page(addr,vaddr,pg) __cpu_clear_user_page(addr, vaddr)
#define copy_user_page(to,from,vaddr,pg) __cpu_copy_user_page(to, from, vaddr)
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index 2bdbc79bbd01..e7765b62c712 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -176,9 +176,10 @@
#define ARMV8_PMU_PMCR_X (1 << 4) /* Export to ETM */
#define ARMV8_PMU_PMCR_DP (1 << 5) /* Disable CCNT if non-invasive debug*/
#define ARMV8_PMU_PMCR_LC (1 << 6) /* Overflow on 64 bit cycle counter */
+#define ARMV8_PMU_PMCR_LP (1 << 7) /* Long event counter enable */
#define ARMV8_PMU_PMCR_N_SHIFT 11 /* Number of counters supported */
#define ARMV8_PMU_PMCR_N_MASK 0x1f
-#define ARMV8_PMU_PMCR_MASK 0x7f /* Mask for writable bits */
+#define ARMV8_PMU_PMCR_MASK 0xff /* Mask for writable bits */
/*
* PMOVSR: counters overflow flag status reg
diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h
index 7a24bad1a58b..70c47156e54b 100644
--- a/arch/arm64/include/asm/pointer_auth.h
+++ b/arch/arm64/include/asm/pointer_auth.h
@@ -22,7 +22,7 @@ struct ptrauth_key {
* We give each process its own keys, which are shared by all threads. The keys
* are inherited upon fork(), and reinitialised upon exec*().
*/
-struct ptrauth_keys {
+struct ptrauth_keys_user {
struct ptrauth_key apia;
struct ptrauth_key apib;
struct ptrauth_key apda;
@@ -30,7 +30,11 @@ struct ptrauth_keys {
struct ptrauth_key apga;
};
-static inline void ptrauth_keys_init(struct ptrauth_keys *keys)
+struct ptrauth_keys_kernel {
+ struct ptrauth_key apia;
+};
+
+static inline void ptrauth_keys_init_user(struct ptrauth_keys_user *keys)
{
if (system_supports_address_auth()) {
get_random_bytes(&keys->apia, sizeof(keys->apia));
@@ -50,48 +54,38 @@ do { \
write_sysreg_s(__pki_v.hi, SYS_ ## k ## KEYHI_EL1); \
} while (0)
-static inline void ptrauth_keys_switch(struct ptrauth_keys *keys)
+static __always_inline void ptrauth_keys_init_kernel(struct ptrauth_keys_kernel *keys)
{
- if (system_supports_address_auth()) {
- __ptrauth_key_install(APIA, keys->apia);
- __ptrauth_key_install(APIB, keys->apib);
- __ptrauth_key_install(APDA, keys->apda);
- __ptrauth_key_install(APDB, keys->apdb);
- }
+ if (system_supports_address_auth())
+ get_random_bytes(&keys->apia, sizeof(keys->apia));
+}
- if (system_supports_generic_auth())
- __ptrauth_key_install(APGA, keys->apga);
+static __always_inline void ptrauth_keys_switch_kernel(struct ptrauth_keys_kernel *keys)
+{
+ if (system_supports_address_auth())
+ __ptrauth_key_install(APIA, keys->apia);
}
extern int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg);
-/*
- * The EL0 pointer bits used by a pointer authentication code.
- * This is dependent on TBI0 being enabled, or bits 63:56 would also apply.
- */
-#define ptrauth_user_pac_mask() GENMASK(54, vabits_actual)
-
-/* Only valid for EL0 TTBR0 instruction pointers */
static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr)
{
- return ptr & ~ptrauth_user_pac_mask();
+ return ptrauth_clear_pac(ptr);
}
#define ptrauth_thread_init_user(tsk) \
-do { \
- struct task_struct *__ptiu_tsk = (tsk); \
- ptrauth_keys_init(&__ptiu_tsk->thread.keys_user); \
- ptrauth_keys_switch(&__ptiu_tsk->thread.keys_user); \
-} while (0)
-
-#define ptrauth_thread_switch(tsk) \
- ptrauth_keys_switch(&(tsk)->thread.keys_user)
+ ptrauth_keys_init_user(&(tsk)->thread.keys_user)
+#define ptrauth_thread_init_kernel(tsk) \
+ ptrauth_keys_init_kernel(&(tsk)->thread.keys_kernel)
+#define ptrauth_thread_switch_kernel(tsk) \
+ ptrauth_keys_switch_kernel(&(tsk)->thread.keys_kernel)
#else /* CONFIG_ARM64_PTR_AUTH */
#define ptrauth_prctl_reset_keys(tsk, arg) (-EINVAL)
#define ptrauth_strip_insn_pac(lr) (lr)
#define ptrauth_thread_init_user(tsk)
-#define ptrauth_thread_switch(tsk)
+#define ptrauth_thread_init_kernel(tsk)
+#define ptrauth_thread_switch_kernel(tsk)
#endif /* CONFIG_ARM64_PTR_AUTH */
#endif /* __ASM_POINTER_AUTH_H */
diff --git a/arch/arm64/include/asm/proc-fns.h b/arch/arm64/include/asm/proc-fns.h
index a2ce65a0c1fa..0d5d1f0525eb 100644
--- a/arch/arm64/include/asm/proc-fns.h
+++ b/arch/arm64/include/asm/proc-fns.h
@@ -13,11 +13,9 @@
#include <asm/page.h>
-struct mm_struct;
struct cpu_suspend_ctx;
extern void cpu_do_idle(void);
-extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr);
extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index e51ef2dc5749..240fe5e5b720 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -148,7 +148,8 @@ struct thread_struct {
unsigned long fault_code; /* ESR_EL1 value */
struct debug_info debug; /* debugging */
#ifdef CONFIG_ARM64_PTR_AUTH
- struct ptrauth_keys keys_user;
+ struct ptrauth_keys_user keys_user;
+ struct ptrauth_keys_kernel keys_kernel;
#endif
};
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index a0c8a0b65259..40d5ba029615 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -23,6 +23,14 @@
#define CPU_STUCK_REASON_52_BIT_VA (UL(1) << CPU_STUCK_REASON_SHIFT)
#define CPU_STUCK_REASON_NO_GRAN (UL(2) << CPU_STUCK_REASON_SHIFT)
+/* Possible options for __cpu_setup */
+/* Option to setup primary cpu */
+#define ARM64_CPU_BOOT_PRIMARY (1)
+/* Option to setup secondary cpus */
+#define ARM64_CPU_BOOT_SECONDARY (2)
+/* Option to setup cpus for different cpu run time services */
+#define ARM64_CPU_RUNTIME (3)
+
#ifndef __ASSEMBLY__
#include <asm/percpu.h>
@@ -30,6 +38,7 @@
#include <linux/threads.h>
#include <linux/cpumask.h>
#include <linux/thread_info.h>
+#include <asm/pointer_auth.h>
DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
@@ -87,6 +96,9 @@ asmlinkage void secondary_start_kernel(void);
struct secondary_data {
void *stack;
struct task_struct *task;
+#ifdef CONFIG_ARM64_PTR_AUTH
+ struct ptrauth_keys_kernel ptrauth_key;
+#endif
long status;
};
diff --git a/arch/arm64/include/asm/stackprotector.h b/arch/arm64/include/asm/stackprotector.h
index 5884a2b02827..7263e0bac680 100644
--- a/arch/arm64/include/asm/stackprotector.h
+++ b/arch/arm64/include/asm/stackprotector.h
@@ -15,6 +15,7 @@
#include <linux/random.h>
#include <linux/version.h>
+#include <asm/pointer_auth.h>
extern unsigned long __stack_chk_guard;
@@ -26,6 +27,7 @@ extern unsigned long __stack_chk_guard;
*/
static __always_inline void boot_init_stack_canary(void)
{
+#if defined(CONFIG_STACKPROTECTOR)
unsigned long canary;
/* Try to get a semi random initial value. */
@@ -36,6 +38,9 @@ static __always_inline void boot_init_stack_canary(void)
current->stack_canary = canary;
if (!IS_ENABLED(CONFIG_STACKPROTECTOR_PER_TASK))
__stack_chk_guard = current->stack_canary;
+#endif
+ ptrauth_thread_init_kernel(current);
+ ptrauth_thread_switch_kernel(current);
}
#endif /* _ASM_STACKPROTECTOR_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index b91570ff9db1..ebc622432831 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -386,6 +386,42 @@
#define SYS_TPIDR_EL0 sys_reg(3, 3, 13, 0, 2)
#define SYS_TPIDRRO_EL0 sys_reg(3, 3, 13, 0, 3)
+/* Definitions for system register interface to AMU for ARMv8.4 onwards */
+#define SYS_AM_EL0(crm, op2) sys_reg(3, 3, 13, (crm), (op2))
+#define SYS_AMCR_EL0 SYS_AM_EL0(2, 0)
+#define SYS_AMCFGR_EL0 SYS_AM_EL0(2, 1)
+#define SYS_AMCGCR_EL0 SYS_AM_EL0(2, 2)
+#define SYS_AMUSERENR_EL0 SYS_AM_EL0(2, 3)
+#define SYS_AMCNTENCLR0_EL0 SYS_AM_EL0(2, 4)
+#define SYS_AMCNTENSET0_EL0 SYS_AM_EL0(2, 5)
+#define SYS_AMCNTENCLR1_EL0 SYS_AM_EL0(3, 0)
+#define SYS_AMCNTENSET1_EL0 SYS_AM_EL0(3, 1)
+
+/*
+ * Group 0 of activity monitors (architected):
+ * op0 op1 CRn CRm op2
+ * Counter: 11 011 1101 010:n<3> n<2:0>
+ * Type: 11 011 1101 011:n<3> n<2:0>
+ * n: 0-15
+ *
+ * Group 1 of activity monitors (auxiliary):
+ * op0 op1 CRn CRm op2
+ * Counter: 11 011 1101 110:n<3> n<2:0>
+ * Type: 11 011 1101 111:n<3> n<2:0>
+ * n: 0-15
+ */
+
+#define SYS_AMEVCNTR0_EL0(n) SYS_AM_EL0(4 + ((n) >> 3), (n) & 7)
+#define SYS_AMEVTYPE0_EL0(n) SYS_AM_EL0(6 + ((n) >> 3), (n) & 7)
+#define SYS_AMEVCNTR1_EL0(n) SYS_AM_EL0(12 + ((n) >> 3), (n) & 7)
+#define SYS_AMEVTYPE1_EL0(n) SYS_AM_EL0(14 + ((n) >> 3), (n) & 7)
+
+/* AMU v1: Fixed (architecturally defined) activity monitors */
+#define SYS_AMEVCNTR0_CORE_EL0 SYS_AMEVCNTR0_EL0(0)
+#define SYS_AMEVCNTR0_CONST_EL0 SYS_AMEVCNTR0_EL0(1)
+#define SYS_AMEVCNTR0_INST_RET_EL0 SYS_AMEVCNTR0_EL0(2)
+#define SYS_AMEVCNTR0_MEM_STALL SYS_AMEVCNTR0_EL0(3)
+
#define SYS_CNTFRQ_EL0 sys_reg(3, 3, 14, 0, 0)
#define SYS_CNTP_TVAL_EL0 sys_reg(3, 3, 14, 2, 0)
@@ -598,6 +634,7 @@
#define ID_AA64PFR0_CSV3_SHIFT 60
#define ID_AA64PFR0_CSV2_SHIFT 56
#define ID_AA64PFR0_DIT_SHIFT 48
+#define ID_AA64PFR0_AMU_SHIFT 44
#define ID_AA64PFR0_SVE_SHIFT 32
#define ID_AA64PFR0_RAS_SHIFT 28
#define ID_AA64PFR0_GIC_SHIFT 24
@@ -608,6 +645,7 @@
#define ID_AA64PFR0_EL1_SHIFT 4
#define ID_AA64PFR0_EL0_SHIFT 0
+#define ID_AA64PFR0_AMU 0x1
#define ID_AA64PFR0_SVE 0x1
#define ID_AA64PFR0_RAS_V1 0x1
#define ID_AA64PFR0_FP_NI 0xf
@@ -702,6 +740,16 @@
#define ID_AA64DFR0_TRACEVER_SHIFT 4
#define ID_AA64DFR0_DEBUGVER_SHIFT 0
+#define ID_AA64DFR0_PMUVER_8_0 0x1
+#define ID_AA64DFR0_PMUVER_8_1 0x4
+#define ID_AA64DFR0_PMUVER_8_4 0x5
+#define ID_AA64DFR0_PMUVER_8_5 0x6
+#define ID_AA64DFR0_PMUVER_IMP_DEF 0xf
+
+#define ID_DFR0_PERFMON_SHIFT 24
+
+#define ID_DFR0_PERFMON_8_1 0x4
+
#define ID_ISAR5_RDM_SHIFT 24
#define ID_ISAR5_CRC32_SHIFT 16
#define ID_ISAR5_SHA2_SHIFT 12
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index cbd70d78ef15..0cc835ddfcd1 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -16,6 +16,15 @@ int pcibus_to_node(struct pci_bus *bus);
#include <linux/arch_topology.h>
+#ifdef CONFIG_ARM64_AMU_EXTN
+/*
+ * Replace task scheduler's default counter-based
+ * frequency-invariance scale factor setting.
+ */
+void topology_scale_freq_tick(void);
+#define arch_scale_freq_tick topology_scale_freq_tick
+#endif /* CONFIG_ARM64_AMU_EXTN */
+
/* Replace task scheduler's default frequency-invariant accounting */
#define arch_scale_freq_capacity topology_get_freq_scale
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index fc6488660f64..4e5b8ee31442 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -21,7 +21,7 @@ obj-y := debug-monitors.o entry.o irq.o fpsimd.o \
smp.o smp_spin_table.o topology.o smccc-call.o \
syscall.o
-extra-$(CONFIG_EFI) := efi-entry.o
+targets += efi-entry.o
OBJCOPYFLAGS := --prefix-symbols=__efistub_
$(obj)/%.stub.o: $(obj)/%.o FORCE
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index 7832b3216370..4cc581af2d96 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -630,7 +630,7 @@ static int __init armv8_deprecated_init(void)
register_insn_emulation(&cp15_barrier_ops);
if (IS_ENABLED(CONFIG_SETEND_EMULATION)) {
- if(system_supports_mixed_endian_el0())
+ if (system_supports_mixed_endian_el0())
register_insn_emulation(&setend_ops);
else
pr_info("setend instruction emulation is not supported on this system\n");
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index a5bdce8af65b..9981a0a5a87f 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -40,6 +40,10 @@ int main(void)
#endif
BLANK();
DEFINE(THREAD_CPU_CONTEXT, offsetof(struct task_struct, thread.cpu_context));
+#ifdef CONFIG_ARM64_PTR_AUTH
+ DEFINE(THREAD_KEYS_USER, offsetof(struct task_struct, thread.keys_user));
+ DEFINE(THREAD_KEYS_KERNEL, offsetof(struct task_struct, thread.keys_kernel));
+#endif
BLANK();
DEFINE(S_X0, offsetof(struct pt_regs, regs[0]));
DEFINE(S_X2, offsetof(struct pt_regs, regs[2]));
@@ -88,6 +92,9 @@ int main(void)
BLANK();
DEFINE(CPU_BOOT_STACK, offsetof(struct secondary_data, stack));
DEFINE(CPU_BOOT_TASK, offsetof(struct secondary_data, task));
+#ifdef CONFIG_ARM64_PTR_AUTH
+ DEFINE(CPU_BOOT_PTRAUTH_KEY, offsetof(struct secondary_data, ptrauth_key));
+#endif
BLANK();
#ifdef CONFIG_KVM_ARM_HOST
DEFINE(VCPU_CONTEXT, offsetof(struct kvm_vcpu, arch.ctxt));
@@ -128,5 +135,14 @@ int main(void)
DEFINE(SDEI_EVENT_INTREGS, offsetof(struct sdei_registered_event, interrupted_regs));
DEFINE(SDEI_EVENT_PRIORITY, offsetof(struct sdei_registered_event, priority));
#endif
+#ifdef CONFIG_ARM64_PTR_AUTH
+ DEFINE(PTRAUTH_USER_KEY_APIA, offsetof(struct ptrauth_keys_user, apia));
+ DEFINE(PTRAUTH_USER_KEY_APIB, offsetof(struct ptrauth_keys_user, apib));
+ DEFINE(PTRAUTH_USER_KEY_APDA, offsetof(struct ptrauth_keys_user, apda));
+ DEFINE(PTRAUTH_USER_KEY_APDB, offsetof(struct ptrauth_keys_user, apdb));
+ DEFINE(PTRAUTH_USER_KEY_APGA, offsetof(struct ptrauth_keys_user, apga));
+ DEFINE(PTRAUTH_KERNEL_KEY_APIA, offsetof(struct ptrauth_keys_kernel, apia));
+ BLANK();
+#endif
return 0;
}
diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S
index 32c7bf858dd9..38087b4c0432 100644
--- a/arch/arm64/kernel/cpu-reset.S
+++ b/arch/arm64/kernel/cpu-reset.S
@@ -32,7 +32,7 @@
ENTRY(__cpu_soft_restart)
/* Clear sctlr_el1 flags. */
mrs x12, sctlr_el1
- ldr x13, =SCTLR_ELx_FLAGS
+ mov_q x13, SCTLR_ELx_FLAGS
bic x12, x12, x13
pre_disable_mmu_workaround
msr sctlr_el1, x12
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 703ad0a84f99..df56d2295d16 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -11,6 +11,7 @@
#include <asm/cpu.h>
#include <asm/cputype.h>
#include <asm/cpufeature.h>
+#include <asm/kvm_asm.h>
#include <asm/smp_plat.h>
static bool __maybe_unused
@@ -113,13 +114,10 @@ atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1);
DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data);
#ifdef CONFIG_KVM_INDIRECT_VECTORS
-extern char __smccc_workaround_1_smc_start[];
-extern char __smccc_workaround_1_smc_end[];
-
static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
const char *hyp_vecs_end)
{
- void *dst = lm_alias(__bp_harden_hyp_vecs_start + slot * SZ_2K);
+ void *dst = lm_alias(__bp_harden_hyp_vecs + slot * SZ_2K);
int i;
for (i = 0; i < SZ_2K; i += 0x80)
@@ -163,9 +161,6 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn,
raw_spin_unlock(&bp_lock);
}
#else
-#define __smccc_workaround_1_smc_start NULL
-#define __smccc_workaround_1_smc_end NULL
-
static void install_bp_hardening_cb(bp_hardening_cb_t fn,
const char *hyp_vecs_start,
const char *hyp_vecs_end)
@@ -176,7 +171,7 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn,
#include <linux/arm-smccc.h>
-static void call_smc_arch_workaround_1(void)
+static void __maybe_unused call_smc_arch_workaround_1(void)
{
arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL);
}
@@ -239,11 +234,14 @@ static int detect_harden_bp_fw(void)
smccc_end = NULL;
break;
+#if IS_ENABLED(CONFIG_KVM_ARM_HOST)
case SMCCC_CONDUIT_SMC:
cb = call_smc_arch_workaround_1;
- smccc_start = __smccc_workaround_1_smc_start;
- smccc_end = __smccc_workaround_1_smc_end;
+ smccc_start = __smccc_workaround_1_smc;
+ smccc_end = __smccc_workaround_1_smc +
+ __SMCCC_WORKAROUND_1_SMC_SZ;
break;
+#endif
default:
return -1;
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index 7e07072757af..e133011f64b5 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -15,10 +15,12 @@
#include <asm/smp_plat.h>
extern const struct cpu_operations smp_spin_table_ops;
+#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
extern const struct cpu_operations acpi_parking_protocol_ops;
+#endif
extern const struct cpu_operations cpu_psci_ops;
-const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
+static const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
static const struct cpu_operations *const dt_supported_cpu_ops[] __initconst = {
&smp_spin_table_ops,
@@ -94,7 +96,7 @@ static const char *__init cpu_read_enable_method(int cpu)
/*
* Read a cpu's enable method and record it in cpu_ops.
*/
-int __init cpu_read_ops(int cpu)
+int __init init_cpu_ops(int cpu)
{
const char *enable_method = cpu_read_enable_method(cpu);
@@ -109,3 +111,8 @@ int __init cpu_read_ops(int cpu)
return 0;
}
+
+const struct cpu_operations *get_cpu_ops(int cpu)
+{
+ return cpu_ops[cpu];
+}
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 0b6715625cf6..9fac745aa7bb 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -116,6 +116,8 @@ cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused)
static void cpu_enable_cnp(struct arm64_cpu_capabilities const *cap);
+static bool __system_matches_cap(unsigned int n);
+
/*
* NOTE: Any changes to the visibility of features should be kept in
* sync with the documentation of the CPU feature register ABI.
@@ -163,6 +165,7 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV3_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV2_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_DIT_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_AMU_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_RAS_SHIFT, 4, 0),
@@ -551,7 +554,7 @@ static void __init init_cpu_ftr_reg(u32 sys_reg, u64 new)
BUG_ON(!reg);
- for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) {
+ for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) {
u64 ftr_mask = arm64_ftr_mask(ftrp);
s64 ftr_new = arm64_ftr_value(ftrp, new);
@@ -1222,6 +1225,57 @@ static bool has_hw_dbm(const struct arm64_cpu_capabilities *cap,
#endif
+#ifdef CONFIG_ARM64_AMU_EXTN
+
+/*
+ * The "amu_cpus" cpumask only signals that the CPU implementation for the
+ * flagged CPUs supports the Activity Monitors Unit (AMU) but does not provide
+ * information regarding all the events that it supports. When a CPU bit is
+ * set in the cpumask, the user of this feature can only rely on the presence
+ * of the 4 fixed counters for that CPU. But this does not guarantee that the
+ * counters are enabled or access to these counters is enabled by code
+ * executed at higher exception levels (firmware).
+ */
+static struct cpumask amu_cpus __read_mostly;
+
+bool cpu_has_amu_feat(int cpu)
+{
+ return cpumask_test_cpu(cpu, &amu_cpus);
+}
+
+/* Initialize the use of AMU counters for frequency invariance */
+extern void init_cpu_freq_invariance_counters(void);
+
+static void cpu_amu_enable(struct arm64_cpu_capabilities const *cap)
+{
+ if (has_cpuid_feature(cap, SCOPE_LOCAL_CPU)) {
+ pr_info("detected CPU%d: Activity Monitors Unit (AMU)\n",
+ smp_processor_id());
+ cpumask_set_cpu(smp_processor_id(), &amu_cpus);
+ init_cpu_freq_invariance_counters();
+ }
+}
+
+static bool has_amu(const struct arm64_cpu_capabilities *cap,
+ int __unused)
+{
+ /*
+ * The AMU extension is a non-conflicting feature: the kernel can
+ * safely run a mix of CPUs with and without support for the
+ * activity monitors extension. Therefore, unconditionally enable
+ * the capability to allow any late CPU to use the feature.
+ *
+ * With this feature unconditionally enabled, the cpu_enable
+ * function will be called for all CPUs that match the criteria,
+ * including secondary and hotplugged, marking this feature as
+ * present on that respective CPU. The enable function will also
+ * print a detection message.
+ */
+
+ return true;
+}
+#endif
+
#ifdef CONFIG_ARM64_VHE
static bool runs_at_el2(const struct arm64_cpu_capabilities *entry, int __unused)
{
@@ -1316,10 +1370,18 @@ static void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused)
#endif /* CONFIG_ARM64_RAS_EXTN */
#ifdef CONFIG_ARM64_PTR_AUTH
-static void cpu_enable_address_auth(struct arm64_cpu_capabilities const *cap)
+static bool has_address_auth(const struct arm64_cpu_capabilities *entry,
+ int __unused)
{
- sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_ENIA | SCTLR_ELx_ENIB |
- SCTLR_ELx_ENDA | SCTLR_ELx_ENDB);
+ return __system_matches_cap(ARM64_HAS_ADDRESS_AUTH_ARCH) ||
+ __system_matches_cap(ARM64_HAS_ADDRESS_AUTH_IMP_DEF);
+}
+
+static bool has_generic_auth(const struct arm64_cpu_capabilities *entry,
+ int __unused)
+{
+ return __system_matches_cap(ARM64_HAS_GENERIC_AUTH_ARCH) ||
+ __system_matches_cap(ARM64_HAS_GENERIC_AUTH_IMP_DEF);
}
#endif /* CONFIG_ARM64_PTR_AUTH */
@@ -1347,6 +1409,25 @@ static bool can_use_gic_priorities(const struct arm64_cpu_capabilities *entry,
}
#endif
+/* Internal helper functions to match cpu capability type */
+static bool
+cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap)
+{
+ return !!(cap->type & ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU);
+}
+
+static bool
+cpucap_late_cpu_permitted(const struct arm64_cpu_capabilities *cap)
+{
+ return !!(cap->type & ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU);
+}
+
+static bool
+cpucap_panic_on_conflict(const struct arm64_cpu_capabilities *cap)
+{
+ return !!(cap->type & ARM64_CPUCAP_PANIC_ON_CONFLICT);
+}
+
static const struct arm64_cpu_capabilities arm64_features[] = {
{
.desc = "GIC system register CPU interface",
@@ -1499,6 +1580,24 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.cpu_enable = cpu_clear_disr,
},
#endif /* CONFIG_ARM64_RAS_EXTN */
+#ifdef CONFIG_ARM64_AMU_EXTN
+ {
+ /*
+ * The feature is enabled by default if CONFIG_ARM64_AMU_EXTN=y.
+ * Therefore, don't provide .desc as we don't want the detection
+ * message to be shown until at least one CPU is detected to
+ * support the feature.
+ */
+ .capability = ARM64_HAS_AMU_EXTN,
+ .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
+ .matches = has_amu,
+ .sys_reg = SYS_ID_AA64PFR0_EL1,
+ .sign = FTR_UNSIGNED,
+ .field_pos = ID_AA64PFR0_AMU_SHIFT,
+ .min_field_value = ID_AA64PFR0_AMU,
+ .cpu_enable = cpu_amu_enable,
+ },
+#endif /* CONFIG_ARM64_AMU_EXTN */
{
.desc = "Data cache clean to the PoU not required for I/D coherence",
.capability = ARM64_HAS_CACHE_IDC,
@@ -1592,24 +1691,27 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
{
.desc = "Address authentication (architected algorithm)",
.capability = ARM64_HAS_ADDRESS_AUTH_ARCH,
- .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .type = ARM64_CPUCAP_BOOT_CPU_FEATURE,
.sys_reg = SYS_ID_AA64ISAR1_EL1,
.sign = FTR_UNSIGNED,
.field_pos = ID_AA64ISAR1_APA_SHIFT,
.min_field_value = ID_AA64ISAR1_APA_ARCHITECTED,
.matches = has_cpuid_feature,
- .cpu_enable = cpu_enable_address_auth,
},
{
.desc = "Address authentication (IMP DEF algorithm)",
.capability = ARM64_HAS_ADDRESS_AUTH_IMP_DEF,
- .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .type = ARM64_CPUCAP_BOOT_CPU_FEATURE,
.sys_reg = SYS_ID_AA64ISAR1_EL1,
.sign = FTR_UNSIGNED,
.field_pos = ID_AA64ISAR1_API_SHIFT,
.min_field_value = ID_AA64ISAR1_API_IMP_DEF,
.matches = has_cpuid_feature,
- .cpu_enable = cpu_enable_address_auth,
+ },
+ {
+ .capability = ARM64_HAS_ADDRESS_AUTH,
+ .type = ARM64_CPUCAP_BOOT_CPU_FEATURE,
+ .matches = has_address_auth,
},
{
.desc = "Generic authentication (architected algorithm)",
@@ -1631,6 +1733,11 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.min_field_value = ID_AA64ISAR1_GPI_IMP_DEF,
.matches = has_cpuid_feature,
},
+ {
+ .capability = ARM64_HAS_GENERIC_AUTH,
+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .matches = has_generic_auth,
+ },
#endif /* CONFIG_ARM64_PTR_AUTH */
#ifdef CONFIG_ARM64_PSEUDO_NMI
{
@@ -1980,10 +2087,8 @@ static void __init enable_cpu_capabilities(u16 scope_mask)
* Run through the list of capabilities to check for conflicts.
* If the system has already detected a capability, take necessary
* action on this CPU.
- *
- * Returns "false" on conflicts.
*/
-static bool verify_local_cpu_caps(u16 scope_mask)
+static void verify_local_cpu_caps(u16 scope_mask)
{
int i;
bool cpu_has_cap, system_has_cap;
@@ -2028,10 +2133,12 @@ static bool verify_local_cpu_caps(u16 scope_mask)
pr_crit("CPU%d: Detected conflict for capability %d (%s), System: %d, CPU: %d\n",
smp_processor_id(), caps->capability,
caps->desc, system_has_cap, cpu_has_cap);
- return false;
- }
- return true;
+ if (cpucap_panic_on_conflict(caps))
+ cpu_panic_kernel();
+ else
+ cpu_die_early();
+ }
}
/*
@@ -2041,12 +2148,8 @@ static bool verify_local_cpu_caps(u16 scope_mask)
static void check_early_cpu_features(void)
{
verify_cpu_asid_bits();
- /*
- * Early features are used by the kernel already. If there
- * is a conflict, we cannot proceed further.
- */
- if (!verify_local_cpu_caps(SCOPE_BOOT_CPU))
- cpu_panic_kernel();
+
+ verify_local_cpu_caps(SCOPE_BOOT_CPU);
}
static void
@@ -2094,8 +2197,7 @@ static void verify_local_cpu_capabilities(void)
* check_early_cpu_features(), as they need to be verified
* on all secondary CPUs.
*/
- if (!verify_local_cpu_caps(SCOPE_ALL & ~SCOPE_BOOT_CPU))
- cpu_die_early();
+ verify_local_cpu_caps(SCOPE_ALL & ~SCOPE_BOOT_CPU);
verify_local_elf_hwcaps(arm64_elf_hwcaps);
@@ -2146,6 +2248,23 @@ bool this_cpu_has_cap(unsigned int n)
return false;
}
+/*
+ * This helper function is used in a narrow window when,
+ * - The system wide safe registers are set with all the SMP CPUs and,
+ * - The SYSTEM_FEATURE cpu_hwcaps may not have been set.
+ * In all other cases cpus_have_{const_}cap() should be used.
+ */
+static bool __system_matches_cap(unsigned int n)
+{
+ if (n < ARM64_NCAPS) {
+ const struct arm64_cpu_capabilities *cap = cpu_hwcaps_ptrs[n];
+
+ if (cap)
+ return cap->matches(cap, SCOPE_SYSTEM);
+ }
+ return false;
+}
+
void cpu_set_feature(unsigned int num)
{
WARN_ON(num >= MAX_CPU_FEATURES);
@@ -2218,7 +2337,7 @@ void __init setup_cpu_features(void)
static bool __maybe_unused
cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused)
{
- return (cpus_have_const_cap(ARM64_HAS_PAN) && !cpus_have_const_cap(ARM64_HAS_UAO));
+ return (__system_matches_cap(ARM64_HAS_PAN) && !__system_matches_cap(ARM64_HAS_UAO));
}
static void __maybe_unused cpu_enable_cnp(struct arm64_cpu_capabilities const *cap)
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index e4d6af2fdec7..b512b5503f6e 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -18,11 +18,11 @@
int arm_cpuidle_init(unsigned int cpu)
{
+ const struct cpu_operations *ops = get_cpu_ops(cpu);
int ret = -EOPNOTSUPP;
- if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_suspend &&
- cpu_ops[cpu]->cpu_init_idle)
- ret = cpu_ops[cpu]->cpu_init_idle(cpu);
+ if (ops && ops->cpu_suspend && ops->cpu_init_idle)
+ ret = ops->cpu_init_idle(cpu);
return ret;
}
@@ -37,8 +37,9 @@ int arm_cpuidle_init(unsigned int cpu)
int arm_cpuidle_suspend(int index)
{
int cpu = smp_processor_id();
+ const struct cpu_operations *ops = get_cpu_ops(cpu);
- return cpu_ops[cpu]->cpu_suspend(index);
+ return ops->cpu_suspend(index);
}
#ifdef CONFIG_ACPI
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index fde59981445c..c839b5bf1904 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -175,7 +175,7 @@ NOKPROBE_SYMBOL(el0_pc);
static void notrace el0_sp(struct pt_regs *regs, unsigned long esr)
{
user_exit_irqoff();
- local_daif_restore(DAIF_PROCCTX_NOIRQ);
+ local_daif_restore(DAIF_PROCCTX);
do_sp_pc_abort(regs->sp, esr, regs);
}
NOKPROBE_SYMBOL(el0_sp);
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index 7d02f9966d34..833d48c9acb5 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -75,27 +75,27 @@
add x29, sp, #S_STACKFRAME
.endm
-ENTRY(ftrace_regs_caller)
+SYM_CODE_START(ftrace_regs_caller)
ftrace_regs_entry 1
b ftrace_common
-ENDPROC(ftrace_regs_caller)
+SYM_CODE_END(ftrace_regs_caller)
-ENTRY(ftrace_caller)
+SYM_CODE_START(ftrace_caller)
ftrace_regs_entry 0
b ftrace_common
-ENDPROC(ftrace_caller)
+SYM_CODE_END(ftrace_caller)
-ENTRY(ftrace_common)
+SYM_CODE_START(ftrace_common)
sub x0, x30, #AARCH64_INSN_SIZE // ip (callsite's BL insn)
mov x1, x9 // parent_ip (callsite's LR)
ldr_l x2, function_trace_op // op
mov x3, sp // regs
-GLOBAL(ftrace_call)
+SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
bl ftrace_stub
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-GLOBAL(ftrace_graph_call) // ftrace_graph_caller();
+SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) // ftrace_graph_caller();
nop // If enabled, this will be replaced
// "b ftrace_graph_caller"
#endif
@@ -122,17 +122,17 @@ ftrace_common_return:
add sp, sp, #S_FRAME_SIZE + 16
ret x9
-ENDPROC(ftrace_common)
+SYM_CODE_END(ftrace_common)
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-ENTRY(ftrace_graph_caller)
+SYM_CODE_START(ftrace_graph_caller)
ldr x0, [sp, #S_PC]
sub x0, x0, #AARCH64_INSN_SIZE // ip (callsite's BL insn)
add x1, sp, #S_LR // parent_ip (callsite's LR)
ldr x2, [sp, #S_FRAME_SIZE] // parent fp (callsite's FP)
bl prepare_ftrace_return
b ftrace_common_return
-ENDPROC(ftrace_graph_caller)
+SYM_CODE_END(ftrace_graph_caller)
#endif
#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
@@ -218,7 +218,7 @@ ENDPROC(ftrace_graph_caller)
* - tracer function to probe instrumented function's entry,
* - ftrace_graph_caller to set up an exit hook
*/
-ENTRY(_mcount)
+SYM_FUNC_START(_mcount)
mcount_enter
ldr_l x2, ftrace_trace_function
@@ -242,7 +242,7 @@ skip_ftrace_call: // }
b.ne ftrace_graph_caller // ftrace_graph_caller();
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
mcount_exit
-ENDPROC(_mcount)
+SYM_FUNC_END(_mcount)
EXPORT_SYMBOL(_mcount)
NOKPROBE(_mcount)
@@ -253,9 +253,9 @@ NOKPROBE(_mcount)
* and later on, NOP to branch to ftrace_caller() when enabled or branch to
* NOP when disabled per-function base.
*/
-ENTRY(_mcount)
+SYM_FUNC_START(_mcount)
ret
-ENDPROC(_mcount)
+SYM_FUNC_END(_mcount)
EXPORT_SYMBOL(_mcount)
NOKPROBE(_mcount)
@@ -268,24 +268,24 @@ NOKPROBE(_mcount)
* - tracer function to probe instrumented function's entry,
* - ftrace_graph_caller to set up an exit hook
*/
-ENTRY(ftrace_caller)
+SYM_FUNC_START(ftrace_caller)
mcount_enter
mcount_get_pc0 x0 // function's pc
mcount_get_lr x1 // function's lr
-GLOBAL(ftrace_call) // tracer(pc, lr);
+SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) // tracer(pc, lr);
nop // This will be replaced with "bl xxx"
// where xxx can be any kind of tracer.
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-GLOBAL(ftrace_graph_call) // ftrace_graph_caller();
+SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) // ftrace_graph_caller();
nop // If enabled, this will be replaced
// "b ftrace_graph_caller"
#endif
mcount_exit
-ENDPROC(ftrace_caller)
+SYM_FUNC_END(ftrace_caller)
#endif /* CONFIG_DYNAMIC_FTRACE */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -298,20 +298,20 @@ ENDPROC(ftrace_caller)
* the call stack in order to intercept instrumented function's return path
* and run return_to_handler() later on its exit.
*/
-ENTRY(ftrace_graph_caller)
+SYM_FUNC_START(ftrace_graph_caller)
mcount_get_pc x0 // function's pc
mcount_get_lr_addr x1 // pointer to function's saved lr
mcount_get_parent_fp x2 // parent's fp
bl prepare_ftrace_return // prepare_ftrace_return(pc, &lr, fp)
mcount_exit
-ENDPROC(ftrace_graph_caller)
+SYM_FUNC_END(ftrace_graph_caller)
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
-ENTRY(ftrace_stub)
+SYM_FUNC_START(ftrace_stub)
ret
-ENDPROC(ftrace_stub)
+SYM_FUNC_END(ftrace_stub)
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
/*
@@ -320,7 +320,7 @@ ENDPROC(ftrace_stub)
* Run ftrace_return_to_handler() before going back to parent.
* @fp is checked against the value passed by ftrace_graph_caller().
*/
-ENTRY(return_to_handler)
+SYM_CODE_START(return_to_handler)
/* save return value regs */
sub sp, sp, #64
stp x0, x1, [sp]
@@ -340,5 +340,5 @@ ENTRY(return_to_handler)
add sp, sp, #64
ret
-END(return_to_handler)
+SYM_CODE_END(return_to_handler)
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 9461d812ae27..ddcde093c433 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -14,6 +14,7 @@
#include <asm/alternative.h>
#include <asm/assembler.h>
#include <asm/asm-offsets.h>
+#include <asm/asm_pointer_auth.h>
#include <asm/cpufeature.h>
#include <asm/errno.h>
#include <asm/esr.h>
@@ -177,6 +178,7 @@ alternative_cb_end
apply_ssbd 1, x22, x23
+ ptrauth_keys_install_kernel tsk, 1, x20, x22, x23
.else
add x21, sp, #S_FRAME_SIZE
get_current_task tsk
@@ -341,6 +343,9 @@ alternative_else_nop_endif
msr cntkctl_el1, x1
4:
#endif
+ /* No kernel C function calls after this as user keys are set. */
+ ptrauth_keys_install_user tsk, x0, x1, x2
+
apply_ssbd 0, x0, x1
.endif
@@ -465,7 +470,7 @@ alternative_endif
.pushsection ".entry.text", "ax"
.align 11
-ENTRY(vectors)
+SYM_CODE_START(vectors)
kernel_ventry 1, sync_invalid // Synchronous EL1t
kernel_ventry 1, irq_invalid // IRQ EL1t
kernel_ventry 1, fiq_invalid // FIQ EL1t
@@ -492,7 +497,7 @@ ENTRY(vectors)
kernel_ventry 0, fiq_invalid, 32 // FIQ 32-bit EL0
kernel_ventry 0, error_invalid, 32 // Error 32-bit EL0
#endif
-END(vectors)
+SYM_CODE_END(vectors)
#ifdef CONFIG_VMAP_STACK
/*
@@ -534,57 +539,57 @@ __bad_stack:
ASM_BUG()
.endm
-el0_sync_invalid:
+SYM_CODE_START_LOCAL(el0_sync_invalid)
inv_entry 0, BAD_SYNC
-ENDPROC(el0_sync_invalid)
+SYM_CODE_END(el0_sync_invalid)
-el0_irq_invalid:
+SYM_CODE_START_LOCAL(el0_irq_invalid)
inv_entry 0, BAD_IRQ
-ENDPROC(el0_irq_invalid)
+SYM_CODE_END(el0_irq_invalid)
-el0_fiq_invalid:
+SYM_CODE_START_LOCAL(el0_fiq_invalid)
inv_entry 0, BAD_FIQ
-ENDPROC(el0_fiq_invalid)
+SYM_CODE_END(el0_fiq_invalid)
-el0_error_invalid:
+SYM_CODE_START_LOCAL(el0_error_invalid)
inv_entry 0, BAD_ERROR
-ENDPROC(el0_error_invalid)
+SYM_CODE_END(el0_error_invalid)
#ifdef CONFIG_COMPAT
-el0_fiq_invalid_compat:
+SYM_CODE_START_LOCAL(el0_fiq_invalid_compat)
inv_entry 0, BAD_FIQ, 32
-ENDPROC(el0_fiq_invalid_compat)
+SYM_CODE_END(el0_fiq_invalid_compat)
#endif
-el1_sync_invalid:
+SYM_CODE_START_LOCAL(el1_sync_invalid)
inv_entry 1, BAD_SYNC
-ENDPROC(el1_sync_invalid)
+SYM_CODE_END(el1_sync_invalid)
-el1_irq_invalid:
+SYM_CODE_START_LOCAL(el1_irq_invalid)
inv_entry 1, BAD_IRQ
-ENDPROC(el1_irq_invalid)
+SYM_CODE_END(el1_irq_invalid)
-el1_fiq_invalid:
+SYM_CODE_START_LOCAL(el1_fiq_invalid)
inv_entry 1, BAD_FIQ
-ENDPROC(el1_fiq_invalid)
+SYM_CODE_END(el1_fiq_invalid)
-el1_error_invalid:
+SYM_CODE_START_LOCAL(el1_error_invalid)
inv_entry 1, BAD_ERROR
-ENDPROC(el1_error_invalid)
+SYM_CODE_END(el1_error_invalid)
/*
* EL1 mode handlers.
*/
.align 6
-el1_sync:
+SYM_CODE_START_LOCAL_NOALIGN(el1_sync)
kernel_entry 1
mov x0, sp
bl el1_sync_handler
kernel_exit 1
-ENDPROC(el1_sync)
+SYM_CODE_END(el1_sync)
.align 6
-el1_irq:
+SYM_CODE_START_LOCAL_NOALIGN(el1_irq)
kernel_entry 1
gic_prio_irq_setup pmr=x20, tmp=x1
enable_da_f
@@ -639,42 +644,42 @@ alternative_else_nop_endif
#endif
kernel_exit 1
-ENDPROC(el1_irq)
+SYM_CODE_END(el1_irq)
/*
* EL0 mode handlers.
*/
.align 6
-el0_sync:
+SYM_CODE_START_LOCAL_NOALIGN(el0_sync)
kernel_entry 0
mov x0, sp
bl el0_sync_handler
b ret_to_user
-ENDPROC(el0_sync)
+SYM_CODE_END(el0_sync)
#ifdef CONFIG_COMPAT
.align 6
-el0_sync_compat:
+SYM_CODE_START_LOCAL_NOALIGN(el0_sync_compat)
kernel_entry 0, 32
mov x0, sp
bl el0_sync_compat_handler
b ret_to_user
-ENDPROC(el0_sync_compat)
+SYM_CODE_END(el0_sync_compat)
.align 6
-el0_irq_compat:
+SYM_CODE_START_LOCAL_NOALIGN(el0_irq_compat)
kernel_entry 0, 32
b el0_irq_naked
-ENDPROC(el0_irq_compat)
+SYM_CODE_END(el0_irq_compat)
-el0_error_compat:
+SYM_CODE_START_LOCAL_NOALIGN(el0_error_compat)
kernel_entry 0, 32
b el0_error_naked
-ENDPROC(el0_error_compat)
+SYM_CODE_END(el0_error_compat)
#endif
.align 6
-el0_irq:
+SYM_CODE_START_LOCAL_NOALIGN(el0_irq)
kernel_entry 0
el0_irq_naked:
gic_prio_irq_setup pmr=x20, tmp=x0
@@ -696,9 +701,9 @@ el0_irq_naked:
bl trace_hardirqs_on
#endif
b ret_to_user
-ENDPROC(el0_irq)
+SYM_CODE_END(el0_irq)
-el1_error:
+SYM_CODE_START_LOCAL(el1_error)
kernel_entry 1
mrs x1, esr_el1
gic_prio_kentry_setup tmp=x2
@@ -706,9 +711,9 @@ el1_error:
mov x0, sp
bl do_serror
kernel_exit 1
-ENDPROC(el1_error)
+SYM_CODE_END(el1_error)
-el0_error:
+SYM_CODE_START_LOCAL(el0_error)
kernel_entry 0
el0_error_naked:
mrs x25, esr_el1
@@ -720,7 +725,7 @@ el0_error_naked:
bl do_serror
enable_da_f
b ret_to_user
-ENDPROC(el0_error)
+SYM_CODE_END(el0_error)
/*
* Ok, we need to do extra processing, enter the slow path.
@@ -832,7 +837,7 @@ alternative_else_nop_endif
.endm
.align 11
-ENTRY(tramp_vectors)
+SYM_CODE_START_NOALIGN(tramp_vectors)
.space 0x400
tramp_ventry
@@ -844,24 +849,24 @@ ENTRY(tramp_vectors)
tramp_ventry 32
tramp_ventry 32
tramp_ventry 32
-END(tramp_vectors)
+SYM_CODE_END(tramp_vectors)
-ENTRY(tramp_exit_native)
+SYM_CODE_START(tramp_exit_native)
tramp_exit
-END(tramp_exit_native)
+SYM_CODE_END(tramp_exit_native)
-ENTRY(tramp_exit_compat)
+SYM_CODE_START(tramp_exit_compat)
tramp_exit 32
-END(tramp_exit_compat)
+SYM_CODE_END(tramp_exit_compat)
.ltorg
.popsection // .entry.tramp.text
#ifdef CONFIG_RANDOMIZE_BASE
.pushsection ".rodata", "a"
.align PAGE_SHIFT
- .globl __entry_tramp_data_start
-__entry_tramp_data_start:
+SYM_DATA_START(__entry_tramp_data_start)
.quad vectors
+SYM_DATA_END(__entry_tramp_data_start)
.popsection // .rodata
#endif /* CONFIG_RANDOMIZE_BASE */
#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
@@ -874,7 +879,7 @@ __entry_tramp_data_start:
* Previous and next are guaranteed not to be the same.
*
*/
-ENTRY(cpu_switch_to)
+SYM_FUNC_START(cpu_switch_to)
mov x10, #THREAD_CPU_CONTEXT
add x8, x0, x10
mov x9, sp
@@ -895,21 +900,22 @@ ENTRY(cpu_switch_to)
ldr lr, [x8]
mov sp, x9
msr sp_el0, x1
+ ptrauth_keys_install_kernel x1, 1, x8, x9, x10
ret
-ENDPROC(cpu_switch_to)
+SYM_FUNC_END(cpu_switch_to)
NOKPROBE(cpu_switch_to)
/*
* This is how we return from a fork.
*/
-ENTRY(ret_from_fork)
+SYM_CODE_START(ret_from_fork)
bl schedule_tail
cbz x19, 1f // not a kernel thread
mov x0, x20
blr x19
1: get_current_task tsk
b ret_to_user
-ENDPROC(ret_from_fork)
+SYM_CODE_END(ret_from_fork)
NOKPROBE(ret_from_fork)
#ifdef CONFIG_ARM_SDE_INTERFACE
@@ -938,7 +944,7 @@ NOKPROBE(ret_from_fork)
*/
.ltorg
.pushsection ".entry.tramp.text", "ax"
-ENTRY(__sdei_asm_entry_trampoline)
+SYM_CODE_START(__sdei_asm_entry_trampoline)
mrs x4, ttbr1_el1
tbz x4, #USER_ASID_BIT, 1f
@@ -960,7 +966,7 @@ ENTRY(__sdei_asm_entry_trampoline)
ldr x4, =__sdei_asm_handler
#endif
br x4
-ENDPROC(__sdei_asm_entry_trampoline)
+SYM_CODE_END(__sdei_asm_entry_trampoline)
NOKPROBE(__sdei_asm_entry_trampoline)
/*
@@ -970,21 +976,22 @@ NOKPROBE(__sdei_asm_entry_trampoline)
* x2: exit_mode
* x4: struct sdei_registered_event argument from registration time.
*/
-ENTRY(__sdei_asm_exit_trampoline)
+SYM_CODE_START(__sdei_asm_exit_trampoline)
ldr x4, [x4, #(SDEI_EVENT_INTREGS + S_ORIG_ADDR_LIMIT)]
cbnz x4, 1f
tramp_unmap_kernel tmp=x4
1: sdei_handler_exit exit_mode=x2
-ENDPROC(__sdei_asm_exit_trampoline)
+SYM_CODE_END(__sdei_asm_exit_trampoline)
NOKPROBE(__sdei_asm_exit_trampoline)
.ltorg
.popsection // .entry.tramp.text
#ifdef CONFIG_RANDOMIZE_BASE
.pushsection ".rodata", "a"
-__sdei_asm_trampoline_next_handler:
+SYM_DATA_START(__sdei_asm_trampoline_next_handler)
.quad __sdei_asm_handler
+SYM_DATA_END(__sdei_asm_trampoline_next_handler)
.popsection // .rodata
#endif /* CONFIG_RANDOMIZE_BASE */
#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
@@ -1002,7 +1009,7 @@ __sdei_asm_trampoline_next_handler:
* follow SMC-CC. We save (or retrieve) all the registers as the handler may
* want them.
*/
-ENTRY(__sdei_asm_handler)
+SYM_CODE_START(__sdei_asm_handler)
stp x2, x3, [x1, #SDEI_EVENT_INTREGS + S_PC]
stp x4, x5, [x1, #SDEI_EVENT_INTREGS + 16 * 2]
stp x6, x7, [x1, #SDEI_EVENT_INTREGS + 16 * 3]
@@ -1085,6 +1092,6 @@ alternative_else_nop_endif
tramp_alias dst=x5, sym=__sdei_asm_exit_trampoline
br x5
#endif
-ENDPROC(__sdei_asm_handler)
+SYM_CODE_END(__sdei_asm_handler)
NOKPROBE(__sdei_asm_handler)
#endif /* CONFIG_ARM_SDE_INTERFACE */
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 989b1944cb71..57a91032b4c2 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -105,7 +105,7 @@ pe_header:
* x24 __primary_switch() .. relocate_kernel()
* current RELR displacement
*/
-ENTRY(stext)
+SYM_CODE_START(stext)
bl preserve_boot_args
bl el2_setup // Drop to EL1, w0=cpu_boot_mode
adrp x23, __PHYS_OFFSET
@@ -118,14 +118,15 @@ ENTRY(stext)
* On return, the CPU will be ready for the MMU to be turned on and
* the TCR will have been set.
*/
+ mov x0, #ARM64_CPU_BOOT_PRIMARY
bl __cpu_setup // initialise processor
b __primary_switch
-ENDPROC(stext)
+SYM_CODE_END(stext)
/*
* Preserve the arguments passed by the bootloader in x0 .. x3
*/
-preserve_boot_args:
+SYM_CODE_START_LOCAL(preserve_boot_args)
mov x21, x0 // x21=FDT
adr_l x0, boot_args // record the contents of
@@ -137,7 +138,7 @@ preserve_boot_args:
mov x1, #0x20 // 4 x 8 bytes
b __inval_dcache_area // tail call
-ENDPROC(preserve_boot_args)
+SYM_CODE_END(preserve_boot_args)
/*
* Macro to create a table entry to the next page.
@@ -275,7 +276,7 @@ ENDPROC(preserve_boot_args)
* - first few MB of the kernel linear mapping to jump to once the MMU has
* been enabled
*/
-__create_page_tables:
+SYM_FUNC_START_LOCAL(__create_page_tables)
mov x28, lr
/*
@@ -403,15 +404,14 @@ __create_page_tables:
bl __inval_dcache_area
ret x28
-ENDPROC(__create_page_tables)
- .ltorg
+SYM_FUNC_END(__create_page_tables)
/*
* The following fragment of code is executed with the MMU enabled.
*
* x0 = __PHYS_OFFSET
*/
-__primary_switched:
+SYM_FUNC_START_LOCAL(__primary_switched)
adrp x4, init_thread_union
add sp, x4, #THREAD_SIZE
adr_l x5, init_task
@@ -456,7 +456,14 @@ __primary_switched:
mov x29, #0
mov x30, #0
b start_kernel
-ENDPROC(__primary_switched)
+SYM_FUNC_END(__primary_switched)
+
+ .pushsection ".rodata", "a"
+SYM_DATA_START(kimage_vaddr)
+ .quad _text - TEXT_OFFSET
+SYM_DATA_END(kimage_vaddr)
+EXPORT_SYMBOL(kimage_vaddr)
+ .popsection
/*
* end early head section, begin head code that is also used for
@@ -464,10 +471,6 @@ ENDPROC(__primary_switched)
*/
.section ".idmap.text","awx"
-ENTRY(kimage_vaddr)
- .quad _text - TEXT_OFFSET
-EXPORT_SYMBOL(kimage_vaddr)
-
/*
* If we're fortunate enough to boot at EL2, ensure that the world is
* sane before dropping to EL1.
@@ -475,7 +478,7 @@ EXPORT_SYMBOL(kimage_vaddr)
* Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in w0 if
* booted in EL1 or EL2 respectively.
*/
-ENTRY(el2_setup)
+SYM_FUNC_START(el2_setup)
msr SPsel, #1 // We want to use SP_EL{1,2}
mrs x0, CurrentEL
cmp x0, #CurrentEL_EL2
@@ -599,7 +602,7 @@ set_hcr:
isb
ret
-install_el2_stub:
+SYM_INNER_LABEL(install_el2_stub, SYM_L_LOCAL)
/*
* When VHE is not in use, early init of EL2 and EL1 needs to be
* done here.
@@ -636,13 +639,13 @@ install_el2_stub:
msr elr_el2, lr
mov w0, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2
eret
-ENDPROC(el2_setup)
+SYM_FUNC_END(el2_setup)
/*
* Sets the __boot_cpu_mode flag depending on the CPU boot mode passed
* in w0. See arch/arm64/include/asm/virt.h for more info.
*/
-set_cpu_boot_mode_flag:
+SYM_FUNC_START_LOCAL(set_cpu_boot_mode_flag)
adr_l x1, __boot_cpu_mode
cmp w0, #BOOT_CPU_MODE_EL2
b.ne 1f
@@ -651,7 +654,7 @@ set_cpu_boot_mode_flag:
dmb sy
dc ivac, x1 // Invalidate potentially stale cache line
ret
-ENDPROC(set_cpu_boot_mode_flag)
+SYM_FUNC_END(set_cpu_boot_mode_flag)
/*
* These values are written with the MMU off, but read with the MMU on.
@@ -667,15 +670,17 @@ ENDPROC(set_cpu_boot_mode_flag)
* This is not in .bss, because we set it sufficiently early that the boot-time
* zeroing of .bss would clobber it.
*/
-ENTRY(__boot_cpu_mode)
+SYM_DATA_START(__boot_cpu_mode)
.long BOOT_CPU_MODE_EL2
.long BOOT_CPU_MODE_EL1
+SYM_DATA_END(__boot_cpu_mode)
/*
* The booting CPU updates the failed status @__early_cpu_boot_status,
* with MMU turned off.
*/
-ENTRY(__early_cpu_boot_status)
+SYM_DATA_START(__early_cpu_boot_status)
.quad 0
+SYM_DATA_END(__early_cpu_boot_status)
.popsection
@@ -683,7 +688,7 @@ ENTRY(__early_cpu_boot_status)
* This provides a "holding pen" for platforms to hold all secondary
* cores are held until we're ready for them to initialise.
*/
-ENTRY(secondary_holding_pen)
+SYM_FUNC_START(secondary_holding_pen)
bl el2_setup // Drop to EL1, w0=cpu_boot_mode
bl set_cpu_boot_mode_flag
mrs x0, mpidr_el1
@@ -695,31 +700,32 @@ pen: ldr x4, [x3]
b.eq secondary_startup
wfe
b pen
-ENDPROC(secondary_holding_pen)
+SYM_FUNC_END(secondary_holding_pen)
/*
* Secondary entry point that jumps straight into the kernel. Only to
* be used where CPUs are brought online dynamically by the kernel.
*/
-ENTRY(secondary_entry)
+SYM_FUNC_START(secondary_entry)
bl el2_setup // Drop to EL1
bl set_cpu_boot_mode_flag
b secondary_startup
-ENDPROC(secondary_entry)
+SYM_FUNC_END(secondary_entry)
-secondary_startup:
+SYM_FUNC_START_LOCAL(secondary_startup)
/*
* Common entry point for secondary CPUs.
*/
bl __cpu_secondary_check52bitva
+ mov x0, #ARM64_CPU_BOOT_SECONDARY
bl __cpu_setup // initialise processor
adrp x1, swapper_pg_dir
bl __enable_mmu
ldr x8, =__secondary_switched
br x8
-ENDPROC(secondary_startup)
+SYM_FUNC_END(secondary_startup)
-__secondary_switched:
+SYM_FUNC_START_LOCAL(__secondary_switched)
adr_l x5, vectors
msr vbar_el1, x5
isb
@@ -734,13 +740,13 @@ __secondary_switched:
mov x29, #0
mov x30, #0
b secondary_start_kernel
-ENDPROC(__secondary_switched)
+SYM_FUNC_END(__secondary_switched)
-__secondary_too_slow:
+SYM_FUNC_START_LOCAL(__secondary_too_slow)
wfe
wfi
b __secondary_too_slow
-ENDPROC(__secondary_too_slow)
+SYM_FUNC_END(__secondary_too_slow)
/*
* The booting CPU updates the failed status @__early_cpu_boot_status,
@@ -772,7 +778,7 @@ ENDPROC(__secondary_too_slow)
* Checks if the selected granule size is supported by the CPU.
* If it isn't, park the CPU
*/
-ENTRY(__enable_mmu)
+SYM_FUNC_START(__enable_mmu)
mrs x2, ID_AA64MMFR0_EL1
ubfx x2, x2, #ID_AA64MMFR0_TGRAN_SHIFT, 4
cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED
@@ -796,9 +802,9 @@ ENTRY(__enable_mmu)
dsb nsh
isb
ret
-ENDPROC(__enable_mmu)
+SYM_FUNC_END(__enable_mmu)
-ENTRY(__cpu_secondary_check52bitva)
+SYM_FUNC_START(__cpu_secondary_check52bitva)
#ifdef CONFIG_ARM64_VA_BITS_52
ldr_l x0, vabits_actual
cmp x0, #52
@@ -816,9 +822,9 @@ ENTRY(__cpu_secondary_check52bitva)
#endif
2: ret
-ENDPROC(__cpu_secondary_check52bitva)
+SYM_FUNC_END(__cpu_secondary_check52bitva)
-__no_granule_support:
+SYM_FUNC_START_LOCAL(__no_granule_support)
/* Indicate that this CPU can't boot and is stuck in the kernel */
update_early_cpu_boot_status \
CPU_STUCK_IN_KERNEL | CPU_STUCK_REASON_NO_GRAN, x1, x2
@@ -826,10 +832,10 @@ __no_granule_support:
wfe
wfi
b 1b
-ENDPROC(__no_granule_support)
+SYM_FUNC_END(__no_granule_support)
#ifdef CONFIG_RELOCATABLE
-__relocate_kernel:
+SYM_FUNC_START_LOCAL(__relocate_kernel)
/*
* Iterate over each entry in the relocation table, and apply the
* relocations in place.
@@ -931,10 +937,10 @@ __relocate_kernel:
#endif
ret
-ENDPROC(__relocate_kernel)
+SYM_FUNC_END(__relocate_kernel)
#endif
-__primary_switch:
+SYM_FUNC_START_LOCAL(__primary_switch)
#ifdef CONFIG_RANDOMIZE_BASE
mov x19, x0 // preserve new SCTLR_EL1 value
mrs x20, sctlr_el1 // preserve old SCTLR_EL1 value
@@ -977,4 +983,4 @@ __primary_switch:
ldr x8, =__primary_switched
adrp x0, __PHYS_OFFSET
br x8
-ENDPROC(__primary_switch)
+SYM_FUNC_END(__primary_switch)
diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S
index 38bcd4d4e43b..6532105b3e32 100644
--- a/arch/arm64/kernel/hibernate-asm.S
+++ b/arch/arm64/kernel/hibernate-asm.S
@@ -110,8 +110,6 @@ ENTRY(swsusp_arch_suspend_exit)
cbz x24, 3f /* Do we need to re-initialise EL2? */
hvc #0
3: ret
-
- .ltorg
ENDPROC(swsusp_arch_suspend_exit)
/*
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index 73d46070b315..e473ead806ed 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -63,7 +63,7 @@ el1_sync:
beq 9f // Nothing to reset!
/* Someone called kvm_call_hyp() against the hyp-stub... */
- ldr x0, =HVC_STUB_ERR
+ mov_q x0, HVC_STUB_ERR
eret
9: mov x0, xzr
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index dd3ae8081b38..b40c3b0def92 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -121,7 +121,7 @@ static int setup_dtb(struct kimage *image,
/* add kaslr-seed */
ret = fdt_delprop(dtb, off, FDT_PROP_KASLR_SEED);
- if (ret == -FDT_ERR_NOTFOUND)
+ if (ret == -FDT_ERR_NOTFOUND)
ret = 0;
else if (ret)
goto out;
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index e40b65645c86..4d7879484cec 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -285,6 +285,17 @@ static struct attribute_group armv8_pmuv3_format_attr_group = {
#define ARMV8_IDX_COUNTER_LAST(cpu_pmu) \
(ARMV8_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1)
+
+/*
+ * We unconditionally enable ARMv8.5-PMU long event counter support
+ * (64-bit events) where supported. Indicate if this arm_pmu has long
+ * event counter support.
+ */
+static bool armv8pmu_has_long_event(struct arm_pmu *cpu_pmu)
+{
+ return (cpu_pmu->pmuver >= ID_AA64DFR0_PMUVER_8_5);
+}
+
/*
* We must chain two programmable counters for 64 bit events,
* except when we have allocated the 64bit cycle counter (for CPU
@@ -294,9 +305,11 @@ static struct attribute_group armv8_pmuv3_format_attr_group = {
static inline bool armv8pmu_event_is_chained(struct perf_event *event)
{
int idx = event->hw.idx;
+ struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
return !WARN_ON(idx < 0) &&
armv8pmu_event_is_64bit(event) &&
+ !armv8pmu_has_long_event(cpu_pmu) &&
(idx != ARMV8_IDX_CYCLE_COUNTER);
}
@@ -345,7 +358,7 @@ static inline void armv8pmu_select_counter(int idx)
isb();
}
-static inline u32 armv8pmu_read_evcntr(int idx)
+static inline u64 armv8pmu_read_evcntr(int idx)
{
armv8pmu_select_counter(idx);
return read_sysreg(pmxevcntr_el0);
@@ -362,6 +375,44 @@ static inline u64 armv8pmu_read_hw_counter(struct perf_event *event)
return val;
}
+/*
+ * The cycle counter is always a 64-bit counter. When ARMV8_PMU_PMCR_LP
+ * is set the event counters also become 64-bit counters. Unless the
+ * user has requested a long counter (attr.config1) then we want to
+ * interrupt upon 32-bit overflow - we achieve this by applying a bias.
+ */
+static bool armv8pmu_event_needs_bias(struct perf_event *event)
+{
+ struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+ struct hw_perf_event *hwc = &event->hw;
+ int idx = hwc->idx;
+
+ if (armv8pmu_event_is_64bit(event))
+ return false;
+
+ if (armv8pmu_has_long_event(cpu_pmu) ||
+ idx == ARMV8_IDX_CYCLE_COUNTER)
+ return true;
+
+ return false;
+}
+
+static u64 armv8pmu_bias_long_counter(struct perf_event *event, u64 value)
+{
+ if (armv8pmu_event_needs_bias(event))
+ value |= GENMASK(63, 32);
+
+ return value;
+}
+
+static u64 armv8pmu_unbias_long_counter(struct perf_event *event, u64 value)
+{
+ if (armv8pmu_event_needs_bias(event))
+ value &= ~GENMASK(63, 32);
+
+ return value;
+}
+
static u64 armv8pmu_read_counter(struct perf_event *event)
{
struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
@@ -377,10 +428,10 @@ static u64 armv8pmu_read_counter(struct perf_event *event)
else
value = armv8pmu_read_hw_counter(event);
- return value;
+ return armv8pmu_unbias_long_counter(event, value);
}
-static inline void armv8pmu_write_evcntr(int idx, u32 value)
+static inline void armv8pmu_write_evcntr(int idx, u64 value)
{
armv8pmu_select_counter(idx);
write_sysreg(value, pmxevcntr_el0);
@@ -405,20 +456,14 @@ static void armv8pmu_write_counter(struct perf_event *event, u64 value)
struct hw_perf_event *hwc = &event->hw;
int idx = hwc->idx;
+ value = armv8pmu_bias_long_counter(event, value);
+
if (!armv8pmu_counter_valid(cpu_pmu, idx))
pr_err("CPU%u writing wrong counter %d\n",
smp_processor_id(), idx);
- else if (idx == ARMV8_IDX_CYCLE_COUNTER) {
- /*
- * The cycles counter is really a 64-bit counter.
- * When treating it as a 32-bit counter, we only count
- * the lower 32 bits, and set the upper 32-bits so that
- * we get an interrupt upon 32-bit overflow.
- */
- if (!armv8pmu_event_is_64bit(event))
- value |= 0xffffffff00000000ULL;
+ else if (idx == ARMV8_IDX_CYCLE_COUNTER)
write_sysreg(value, pmccntr_el0);
- } else
+ else
armv8pmu_write_hw_counter(event, value);
}
@@ -450,86 +495,74 @@ static inline void armv8pmu_write_event_type(struct perf_event *event)
}
}
-static inline int armv8pmu_enable_counter(int idx)
+static u32 armv8pmu_event_cnten_mask(struct perf_event *event)
{
- u32 counter = ARMV8_IDX_TO_COUNTER(idx);
- write_sysreg(BIT(counter), pmcntenset_el0);
- return idx;
+ int counter = ARMV8_IDX_TO_COUNTER(event->hw.idx);
+ u32 mask = BIT(counter);
+
+ if (armv8pmu_event_is_chained(event))
+ mask |= BIT(counter - 1);
+ return mask;
+}
+
+static inline void armv8pmu_enable_counter(u32 mask)
+{
+ write_sysreg(mask, pmcntenset_el0);
}
static inline void armv8pmu_enable_event_counter(struct perf_event *event)
{
struct perf_event_attr *attr = &event->attr;
- int idx = event->hw.idx;
- u32 counter_bits = BIT(ARMV8_IDX_TO_COUNTER(idx));
+ u32 mask = armv8pmu_event_cnten_mask(event);
- if (armv8pmu_event_is_chained(event))
- counter_bits |= BIT(ARMV8_IDX_TO_COUNTER(idx - 1));
-
- kvm_set_pmu_events(counter_bits, attr);
+ kvm_set_pmu_events(mask, attr);
/* We rely on the hypervisor switch code to enable guest counters */
- if (!kvm_pmu_counter_deferred(attr)) {
- armv8pmu_enable_counter(idx);
- if (armv8pmu_event_is_chained(event))
- armv8pmu_enable_counter(idx - 1);
- }
+ if (!kvm_pmu_counter_deferred(attr))
+ armv8pmu_enable_counter(mask);
}
-static inline int armv8pmu_disable_counter(int idx)
+static inline void armv8pmu_disable_counter(u32 mask)
{
- u32 counter = ARMV8_IDX_TO_COUNTER(idx);
- write_sysreg(BIT(counter), pmcntenclr_el0);
- return idx;
+ write_sysreg(mask, pmcntenclr_el0);
}
static inline void armv8pmu_disable_event_counter(struct perf_event *event)
{
- struct hw_perf_event *hwc = &event->hw;
struct perf_event_attr *attr = &event->attr;
- int idx = hwc->idx;
- u32 counter_bits = BIT(ARMV8_IDX_TO_COUNTER(idx));
-
- if (armv8pmu_event_is_chained(event))
- counter_bits |= BIT(ARMV8_IDX_TO_COUNTER(idx - 1));
+ u32 mask = armv8pmu_event_cnten_mask(event);
- kvm_clr_pmu_events(counter_bits);
+ kvm_clr_pmu_events(mask);
/* We rely on the hypervisor switch code to disable guest counters */
- if (!kvm_pmu_counter_deferred(attr)) {
- if (armv8pmu_event_is_chained(event))
- armv8pmu_disable_counter(idx - 1);
- armv8pmu_disable_counter(idx);
- }
+ if (!kvm_pmu_counter_deferred(attr))
+ armv8pmu_disable_counter(mask);
}
-static inline int armv8pmu_enable_intens(int idx)
+static inline void armv8pmu_enable_intens(u32 mask)
{
- u32 counter = ARMV8_IDX_TO_COUNTER(idx);
- write_sysreg(BIT(counter), pmintenset_el1);
- return idx;
+ write_sysreg(mask, pmintenset_el1);
}
-static inline int armv8pmu_enable_event_irq(struct perf_event *event)
+static inline void armv8pmu_enable_event_irq(struct perf_event *event)
{
- return armv8pmu_enable_intens(event->hw.idx);
+ u32 counter = ARMV8_IDX_TO_COUNTER(event->hw.idx);
+ armv8pmu_enable_intens(BIT(counter));
}
-static inline int armv8pmu_disable_intens(int idx)
+static inline void armv8pmu_disable_intens(u32 mask)
{
- u32 counter = ARMV8_IDX_TO_COUNTER(idx);
- write_sysreg(BIT(counter), pmintenclr_el1);
+ write_sysreg(mask, pmintenclr_el1);
isb();
/* Clear the overflow flag in case an interrupt is pending. */
- write_sysreg(BIT(counter), pmovsclr_el0);
+ write_sysreg(mask, pmovsclr_el0);
isb();
-
- return idx;
}
-static inline int armv8pmu_disable_event_irq(struct perf_event *event)
+static inline void armv8pmu_disable_event_irq(struct perf_event *event)
{
- return armv8pmu_disable_intens(event->hw.idx);
+ u32 counter = ARMV8_IDX_TO_COUNTER(event->hw.idx);
+ armv8pmu_disable_intens(BIT(counter));
}
static inline u32 armv8pmu_getreset_flags(void)
@@ -743,7 +776,8 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
/*
* Otherwise use events counters
*/
- if (armv8pmu_event_is_64bit(event))
+ if (armv8pmu_event_is_64bit(event) &&
+ !armv8pmu_has_long_event(cpu_pmu))
return armv8pmu_get_chain_idx(cpuc, cpu_pmu);
else
return armv8pmu_get_single_idx(cpuc, cpu_pmu);
@@ -815,13 +849,11 @@ static int armv8pmu_filter_match(struct perf_event *event)
static void armv8pmu_reset(void *info)
{
struct arm_pmu *cpu_pmu = (struct arm_pmu *)info;
- u32 idx, nb_cnt = cpu_pmu->num_events;
+ u32 pmcr;
/* The counter and interrupt enable registers are unknown at reset. */
- for (idx = ARMV8_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) {
- armv8pmu_disable_counter(idx);
- armv8pmu_disable_intens(idx);
- }
+ armv8pmu_disable_counter(U32_MAX);
+ armv8pmu_disable_intens(U32_MAX);
/* Clear the counters we flip at guest entry/exit */
kvm_clr_pmu_events(U32_MAX);
@@ -830,8 +862,13 @@ static void armv8pmu_reset(void *info)
* Initialize & Reset PMNC. Request overflow interrupt for
* 64 bit cycle counter but cheat in armv8pmu_write_counter().
*/
- armv8pmu_pmcr_write(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C |
- ARMV8_PMU_PMCR_LC);
+ pmcr = ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_LC;
+
+ /* Enable long event counter support where available */
+ if (armv8pmu_has_long_event(cpu_pmu))
+ pmcr |= ARMV8_PMU_PMCR_LP;
+
+ armv8pmu_pmcr_write(pmcr);
}
static int __armv8_pmuv3_map_event(struct perf_event *event,
@@ -914,6 +951,7 @@ static void __armv8pmu_probe_pmu(void *info)
if (pmuver == 0xf || pmuver == 0)
return;
+ cpu_pmu->pmuver = pmuver;
probe->present = true;
/* Read the nb of CNTx counters supported from PMNC */
@@ -953,7 +991,10 @@ static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
return probe.present ? 0 : -ENODEV;
}
-static int armv8_pmu_init(struct arm_pmu *cpu_pmu)
+static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
+ int (*map_event)(struct perf_event *event),
+ const struct attribute_group *events,
+ const struct attribute_group *format)
{
int ret = armv8pmu_probe_pmu(cpu_pmu);
if (ret)
@@ -972,144 +1013,127 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu)
cpu_pmu->set_event_filter = armv8pmu_set_event_filter;
cpu_pmu->filter_match = armv8pmu_filter_match;
+ cpu_pmu->name = name;
+ cpu_pmu->map_event = map_event;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = events ?
+ events : &armv8_pmuv3_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = format ?
+ format : &armv8_pmuv3_format_attr_group;
+
return 0;
}
static int armv8_pmuv3_init(struct arm_pmu *cpu_pmu)
{
- int ret = armv8_pmu_init(cpu_pmu);
- if (ret)
- return ret;
-
- cpu_pmu->name = "armv8_pmuv3";
- cpu_pmu->map_event = armv8_pmuv3_map_event;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
- &armv8_pmuv3_events_attr_group;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
- &armv8_pmuv3_format_attr_group;
+ return armv8_pmu_init(cpu_pmu, "armv8_pmuv3",
+ armv8_pmuv3_map_event, NULL, NULL);
+}
- return 0;
+static int armv8_a34_pmu_init(struct arm_pmu *cpu_pmu)
+{
+ return armv8_pmu_init(cpu_pmu, "armv8_cortex_a34",
+ armv8_pmuv3_map_event, NULL, NULL);
}
static int armv8_a35_pmu_init(struct arm_pmu *cpu_pmu)
{
- int ret = armv8_pmu_init(cpu_pmu);
- if (ret)
- return ret;
-
- cpu_pmu->name = "armv8_cortex_a35";
- cpu_pmu->map_event = armv8_a53_map_event;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
- &armv8_pmuv3_events_attr_group;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
- &armv8_pmuv3_format_attr_group;
-
- return 0;
+ return armv8_pmu_init(cpu_pmu, "armv8_cortex_a35",
+ armv8_a53_map_event, NULL, NULL);
}
static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu)
{
- int ret = armv8_pmu_init(cpu_pmu);
- if (ret)
- return ret;
-
- cpu_pmu->name = "armv8_cortex_a53";
- cpu_pmu->map_event = armv8_a53_map_event;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
- &armv8_pmuv3_events_attr_group;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
- &armv8_pmuv3_format_attr_group;
+ return armv8_pmu_init(cpu_pmu, "armv8_cortex_a53",
+ armv8_a53_map_event, NULL, NULL);
+}
- return 0;
+static int armv8_a55_pmu_init(struct arm_pmu *cpu_pmu)
+{
+ return armv8_pmu_init(cpu_pmu, "armv8_cortex_a55",
+ armv8_pmuv3_map_event, NULL, NULL);
}
static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu)
{
- int ret = armv8_pmu_init(cpu_pmu);
- if (ret)
- return ret;
-
- cpu_pmu->name = "armv8_cortex_a57";
- cpu_pmu->map_event = armv8_a57_map_event;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
- &armv8_pmuv3_events_attr_group;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
- &armv8_pmuv3_format_attr_group;
+ return armv8_pmu_init(cpu_pmu, "armv8_cortex_a57",
+ armv8_a57_map_event, NULL, NULL);
+}
- return 0;
+static int armv8_a65_pmu_init(struct arm_pmu *cpu_pmu)
+{
+ return armv8_pmu_init(cpu_pmu, "armv8_cortex_a65",
+ armv8_pmuv3_map_event, NULL, NULL);
}
static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu)
{
- int ret = armv8_pmu_init(cpu_pmu);
- if (ret)
- return ret;
-
- cpu_pmu->name = "armv8_cortex_a72";
- cpu_pmu->map_event = armv8_a57_map_event;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
- &armv8_pmuv3_events_attr_group;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
- &armv8_pmuv3_format_attr_group;
-
- return 0;
+ return armv8_pmu_init(cpu_pmu, "armv8_cortex_a72",
+ armv8_a57_map_event, NULL, NULL);
}
static int armv8_a73_pmu_init(struct arm_pmu *cpu_pmu)
{
- int ret = armv8_pmu_init(cpu_pmu);
- if (ret)
- return ret;
-
- cpu_pmu->name = "armv8_cortex_a73";
- cpu_pmu->map_event = armv8_a73_map_event;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
- &armv8_pmuv3_events_attr_group;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
- &armv8_pmuv3_format_attr_group;
+ return armv8_pmu_init(cpu_pmu, "armv8_cortex_a73",
+ armv8_a73_map_event, NULL, NULL);
+}
- return 0;
+static int armv8_a75_pmu_init(struct arm_pmu *cpu_pmu)
+{
+ return armv8_pmu_init(cpu_pmu, "armv8_cortex_a75",
+ armv8_pmuv3_map_event, NULL, NULL);
}
-static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu)
+static int armv8_a76_pmu_init(struct arm_pmu *cpu_pmu)
{
- int ret = armv8_pmu_init(cpu_pmu);
- if (ret)
- return ret;
+ return armv8_pmu_init(cpu_pmu, "armv8_cortex_a76",
+ armv8_pmuv3_map_event, NULL, NULL);
+}
- cpu_pmu->name = "armv8_cavium_thunder";
- cpu_pmu->map_event = armv8_thunder_map_event;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
- &armv8_pmuv3_events_attr_group;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
- &armv8_pmuv3_format_attr_group;
+static int armv8_a77_pmu_init(struct arm_pmu *cpu_pmu)
+{
+ return armv8_pmu_init(cpu_pmu, "armv8_cortex_a77",
+ armv8_pmuv3_map_event, NULL, NULL);
+}
- return 0;
+static int armv8_e1_pmu_init(struct arm_pmu *cpu_pmu)
+{
+ return armv8_pmu_init(cpu_pmu, "armv8_neoverse_e1",
+ armv8_pmuv3_map_event, NULL, NULL);
}
-static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu)
+static int armv8_n1_pmu_init(struct arm_pmu *cpu_pmu)
{
- int ret = armv8_pmu_init(cpu_pmu);
- if (ret)
- return ret;
+ return armv8_pmu_init(cpu_pmu, "armv8_neoverse_n1",
+ armv8_pmuv3_map_event, NULL, NULL);
+}
- cpu_pmu->name = "armv8_brcm_vulcan";
- cpu_pmu->map_event = armv8_vulcan_map_event;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
- &armv8_pmuv3_events_attr_group;
- cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
- &armv8_pmuv3_format_attr_group;
+static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu)
+{
+ return armv8_pmu_init(cpu_pmu, "armv8_cavium_thunder",
+ armv8_thunder_map_event, NULL, NULL);
+}
- return 0;
+static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu)
+{
+ return armv8_pmu_init(cpu_pmu, "armv8_brcm_vulcan",
+ armv8_vulcan_map_event, NULL, NULL);
}
static const struct of_device_id armv8_pmu_of_device_ids[] = {
{.compatible = "arm,armv8-pmuv3", .data = armv8_pmuv3_init},
+ {.compatible = "arm,cortex-a34-pmu", .data = armv8_a34_pmu_init},
{.compatible = "arm,cortex-a35-pmu", .data = armv8_a35_pmu_init},
{.compatible = "arm,cortex-a53-pmu", .data = armv8_a53_pmu_init},
+ {.compatible = "arm,cortex-a55-pmu", .data = armv8_a55_pmu_init},
{.compatible = "arm,cortex-a57-pmu", .data = armv8_a57_pmu_init},
+ {.compatible = "arm,cortex-a65-pmu", .data = armv8_a65_pmu_init},
{.compatible = "arm,cortex-a72-pmu", .data = armv8_a72_pmu_init},
{.compatible = "arm,cortex-a73-pmu", .data = armv8_a73_pmu_init},
+ {.compatible = "arm,cortex-a75-pmu", .data = armv8_a75_pmu_init},
+ {.compatible = "arm,cortex-a76-pmu", .data = armv8_a76_pmu_init},
+ {.compatible = "arm,cortex-a77-pmu", .data = armv8_a77_pmu_init},
+ {.compatible = "arm,neoverse-e1-pmu", .data = armv8_e1_pmu_init},
+ {.compatible = "arm,neoverse-n1-pmu", .data = armv8_n1_pmu_init},
{.compatible = "cavium,thunder-pmu", .data = armv8_thunder_pmu_init},
{.compatible = "brcm,vulcan-pmu", .data = armv8_vulcan_pmu_init},
{},
diff --git a/arch/arm64/kernel/pointer_auth.c b/arch/arm64/kernel/pointer_auth.c
index c507b584259d..1e77736a4f66 100644
--- a/arch/arm64/kernel/pointer_auth.c
+++ b/arch/arm64/kernel/pointer_auth.c
@@ -9,7 +9,7 @@
int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg)
{
- struct ptrauth_keys *keys = &tsk->thread.keys_user;
+ struct ptrauth_keys_user *keys = &tsk->thread.keys_user;
unsigned long addr_key_mask = PR_PAC_APIAKEY | PR_PAC_APIBKEY |
PR_PAC_APDAKEY | PR_PAC_APDBKEY;
unsigned long key_mask = addr_key_mask | PR_PAC_APGAKEY;
@@ -18,8 +18,7 @@ int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg)
return -EINVAL;
if (!arg) {
- ptrauth_keys_init(keys);
- ptrauth_keys_switch(keys);
+ ptrauth_keys_init_user(keys);
return 0;
}
@@ -41,7 +40,5 @@ int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg)
if (arg & PR_PAC_APGAKEY)
get_random_bytes(&keys->apga, sizeof(keys->apga));
- ptrauth_keys_switch(keys);
-
return 0;
}
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 3e5a6ad66cbe..56be4cbf771f 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -262,7 +262,7 @@ void __show_regs(struct pt_regs *regs)
if (!user_mode(regs)) {
printk("pc : %pS\n", (void *)regs->pc);
- printk("lr : %pS\n", (void *)lr);
+ printk("lr : %pS\n", (void *)ptrauth_strip_insn_pac(lr));
} else {
printk("pc : %016llx\n", regs->pc);
printk("lr : %016llx\n", lr);
@@ -376,6 +376,8 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long stack_start,
*/
fpsimd_flush_task_state(p);
+ ptrauth_thread_init_kernel(p);
+
if (likely(!(p->flags & PF_KTHREAD))) {
*childregs = *current_pt_regs();
childregs->regs[0] = 0;
@@ -512,7 +514,6 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
contextidr_thread_switch(next);
entry_task_switch(next);
uao_thread_switch(next);
- ptrauth_thread_switch(next);
ssbs_thread_switch(next);
/*
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index cd6e5fa48b9c..b3d3005d9515 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -999,7 +999,7 @@ static struct ptrauth_key pac_key_from_user(__uint128_t ukey)
}
static void pac_address_keys_to_user(struct user_pac_address_keys *ukeys,
- const struct ptrauth_keys *keys)
+ const struct ptrauth_keys_user *keys)
{
ukeys->apiakey = pac_key_to_user(&keys->apia);
ukeys->apibkey = pac_key_to_user(&keys->apib);
@@ -1007,7 +1007,7 @@ static void pac_address_keys_to_user(struct user_pac_address_keys *ukeys,
ukeys->apdbkey = pac_key_to_user(&keys->apdb);
}
-static void pac_address_keys_from_user(struct ptrauth_keys *keys,
+static void pac_address_keys_from_user(struct ptrauth_keys_user *keys,
const struct user_pac_address_keys *ukeys)
{
keys->apia = pac_key_from_user(ukeys->apiakey);
@@ -1021,7 +1021,7 @@ static int pac_address_keys_get(struct task_struct *target,
unsigned int pos, unsigned int count,
void *kbuf, void __user *ubuf)
{
- struct ptrauth_keys *keys = &target->thread.keys_user;
+ struct ptrauth_keys_user *keys = &target->thread.keys_user;
struct user_pac_address_keys user_keys;
if (!system_supports_address_auth())
@@ -1038,7 +1038,7 @@ static int pac_address_keys_set(struct task_struct *target,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
- struct ptrauth_keys *keys = &target->thread.keys_user;
+ struct ptrauth_keys_user *keys = &target->thread.keys_user;
struct user_pac_address_keys user_keys;
int ret;
@@ -1056,12 +1056,12 @@ static int pac_address_keys_set(struct task_struct *target,
}
static void pac_generic_keys_to_user(struct user_pac_generic_keys *ukeys,
- const struct ptrauth_keys *keys)
+ const struct ptrauth_keys_user *keys)
{
ukeys->apgakey = pac_key_to_user(&keys->apga);
}
-static void pac_generic_keys_from_user(struct ptrauth_keys *keys,
+static void pac_generic_keys_from_user(struct ptrauth_keys_user *keys,
const struct user_pac_generic_keys *ukeys)
{
keys->apga = pac_key_from_user(ukeys->apgakey);
@@ -1072,7 +1072,7 @@ static int pac_generic_keys_get(struct task_struct *target,
unsigned int pos, unsigned int count,
void *kbuf, void __user *ubuf)
{
- struct ptrauth_keys *keys = &target->thread.keys_user;
+ struct ptrauth_keys_user *keys = &target->thread.keys_user;
struct user_pac_generic_keys user_keys;
if (!system_supports_generic_auth())
@@ -1089,7 +1089,7 @@ static int pac_generic_keys_set(struct task_struct *target,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
- struct ptrauth_keys *keys = &target->thread.keys_user;
+ struct ptrauth_keys_user *keys = &target->thread.keys_user;
struct user_pac_generic_keys user_keys;
int ret;
diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S
index c1d7db71a726..c40ce496c78b 100644
--- a/arch/arm64/kernel/relocate_kernel.S
+++ b/arch/arm64/kernel/relocate_kernel.S
@@ -41,7 +41,7 @@ ENTRY(arm64_relocate_new_kernel)
cmp x0, #CurrentEL_EL2
b.ne 1f
mrs x0, sctlr_el2
- ldr x1, =SCTLR_ELx_FLAGS
+ mov_q x1, SCTLR_ELx_FLAGS
bic x0, x0, x1
pre_disable_mmu_workaround
msr sctlr_el2, x0
@@ -113,8 +113,6 @@ ENTRY(arm64_relocate_new_kernel)
ENDPROC(arm64_relocate_new_kernel)
-.ltorg
-
.align 3 /* To keep the 64-bit values below naturally aligned. */
.Lcopy_end:
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index a34890bf309f..3fd2c11c09fc 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -344,7 +344,7 @@ void __init setup_arch(char **cmdline_p)
else
psci_acpi_init();
- cpu_read_bootcpu_ops();
+ init_bootcpu_ops();
smp_init_cpus();
smp_build_mpidr_hash();
@@ -371,8 +371,10 @@ void __init setup_arch(char **cmdline_p)
static inline bool cpu_can_disable(unsigned int cpu)
{
#ifdef CONFIG_HOTPLUG_CPU
- if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_can_disable)
- return cpu_ops[cpu]->cpu_can_disable(cpu);
+ const struct cpu_operations *ops = get_cpu_ops(cpu);
+
+ if (ops && ops->cpu_can_disable)
+ return ops->cpu_can_disable(cpu);
#endif
return false;
}
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index f5b04dd8a710..7b2f2e650c44 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -3,6 +3,7 @@
#include <linux/linkage.h>
#include <asm/asm-offsets.h>
#include <asm/assembler.h>
+#include <asm/smp.h>
.text
/*
@@ -99,6 +100,7 @@ ENDPROC(__cpu_suspend_enter)
.pushsection ".idmap.text", "awx"
ENTRY(cpu_resume)
bl el2_setup // if in EL2 drop to EL1 cleanly
+ mov x0, #ARM64_CPU_RUNTIME
bl __cpu_setup
/* enable the MMU early - so we can access sleep_save_stash by va */
adrp x1, swapper_pg_dir
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 5407bf5d98ac..061f60fe452f 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -93,8 +93,10 @@ static inline int op_cpu_kill(unsigned int cpu)
*/
static int boot_secondary(unsigned int cpu, struct task_struct *idle)
{
- if (cpu_ops[cpu]->cpu_boot)
- return cpu_ops[cpu]->cpu_boot(cpu);
+ const struct cpu_operations *ops = get_cpu_ops(cpu);
+
+ if (ops->cpu_boot)
+ return ops->cpu_boot(cpu);
return -EOPNOTSUPP;
}
@@ -112,63 +114,66 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
*/
secondary_data.task = idle;
secondary_data.stack = task_stack_page(idle) + THREAD_SIZE;
+#if defined(CONFIG_ARM64_PTR_AUTH)
+ secondary_data.ptrauth_key.apia.lo = idle->thread.keys_kernel.apia.lo;
+ secondary_data.ptrauth_key.apia.hi = idle->thread.keys_kernel.apia.hi;
+#endif
update_cpu_boot_status(CPU_MMU_OFF);
__flush_dcache_area(&secondary_data, sizeof(secondary_data));
- /*
- * Now bring the CPU into our world.
- */
+ /* Now bring the CPU into our world */
ret = boot_secondary(cpu, idle);
- if (ret == 0) {
- /*
- * CPU was successfully started, wait for it to come online or
- * time out.
- */
- wait_for_completion_timeout(&cpu_running,
- msecs_to_jiffies(5000));
-
- if (!cpu_online(cpu)) {
- pr_crit("CPU%u: failed to come online\n", cpu);
- ret = -EIO;
- }
- } else {
+ if (ret) {
pr_err("CPU%u: failed to boot: %d\n", cpu, ret);
return ret;
}
+ /*
+ * CPU was successfully started, wait for it to come online or
+ * time out.
+ */
+ wait_for_completion_timeout(&cpu_running,
+ msecs_to_jiffies(5000));
+ if (cpu_online(cpu))
+ return 0;
+
+ pr_crit("CPU%u: failed to come online\n", cpu);
secondary_data.task = NULL;
secondary_data.stack = NULL;
+#if defined(CONFIG_ARM64_PTR_AUTH)
+ secondary_data.ptrauth_key.apia.lo = 0;
+ secondary_data.ptrauth_key.apia.hi = 0;
+#endif
__flush_dcache_area(&secondary_data, sizeof(secondary_data));
status = READ_ONCE(secondary_data.status);
- if (ret && status) {
-
- if (status == CPU_MMU_OFF)
- status = READ_ONCE(__early_cpu_boot_status);
+ if (status == CPU_MMU_OFF)
+ status = READ_ONCE(__early_cpu_boot_status);
- switch (status & CPU_BOOT_STATUS_MASK) {
- default:
- pr_err("CPU%u: failed in unknown state : 0x%lx\n",
- cpu, status);
- cpus_stuck_in_kernel++;
- break;
- case CPU_KILL_ME:
- if (!op_cpu_kill(cpu)) {
- pr_crit("CPU%u: died during early boot\n", cpu);
- break;
- }
- pr_crit("CPU%u: may not have shut down cleanly\n", cpu);
- /* Fall through */
- case CPU_STUCK_IN_KERNEL:
- pr_crit("CPU%u: is stuck in kernel\n", cpu);
- if (status & CPU_STUCK_REASON_52_BIT_VA)
- pr_crit("CPU%u: does not support 52-bit VAs\n", cpu);
- if (status & CPU_STUCK_REASON_NO_GRAN)
- pr_crit("CPU%u: does not support %luK granule \n", cpu, PAGE_SIZE / SZ_1K);
- cpus_stuck_in_kernel++;
+ switch (status & CPU_BOOT_STATUS_MASK) {
+ default:
+ pr_err("CPU%u: failed in unknown state : 0x%lx\n",
+ cpu, status);
+ cpus_stuck_in_kernel++;
+ break;
+ case CPU_KILL_ME:
+ if (!op_cpu_kill(cpu)) {
+ pr_crit("CPU%u: died during early boot\n", cpu);
break;
- case CPU_PANIC_KERNEL:
- panic("CPU%u detected unsupported configuration\n", cpu);
}
+ pr_crit("CPU%u: may not have shut down cleanly\n", cpu);
+ /* Fall through */
+ case CPU_STUCK_IN_KERNEL:
+ pr_crit("CPU%u: is stuck in kernel\n", cpu);
+ if (status & CPU_STUCK_REASON_52_BIT_VA)
+ pr_crit("CPU%u: does not support 52-bit VAs\n", cpu);
+ if (status & CPU_STUCK_REASON_NO_GRAN) {
+ pr_crit("CPU%u: does not support %luK granule\n",
+ cpu, PAGE_SIZE / SZ_1K);
+ }
+ cpus_stuck_in_kernel++;
+ break;
+ case CPU_PANIC_KERNEL:
+ panic("CPU%u detected unsupported configuration\n", cpu);
}
return ret;
@@ -196,6 +201,7 @@ asmlinkage notrace void secondary_start_kernel(void)
{
u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
struct mm_struct *mm = &init_mm;
+ const struct cpu_operations *ops;
unsigned int cpu;
cpu = task_cpu(current);
@@ -227,8 +233,9 @@ asmlinkage notrace void secondary_start_kernel(void)
*/
check_local_cpu_capabilities();
- if (cpu_ops[cpu]->cpu_postboot)
- cpu_ops[cpu]->cpu_postboot();
+ ops = get_cpu_ops(cpu);
+ if (ops->cpu_postboot)
+ ops->cpu_postboot();
/*
* Log the CPU info before it is marked online and might get read.
@@ -266,19 +273,21 @@ asmlinkage notrace void secondary_start_kernel(void)
#ifdef CONFIG_HOTPLUG_CPU
static int op_cpu_disable(unsigned int cpu)
{
+ const struct cpu_operations *ops = get_cpu_ops(cpu);
+
/*
* If we don't have a cpu_die method, abort before we reach the point
* of no return. CPU0 may not have an cpu_ops, so test for it.
*/
- if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_die)
+ if (!ops || !ops->cpu_die)
return -EOPNOTSUPP;
/*
* We may need to abort a hot unplug for some other mechanism-specific
* reason.
*/
- if (cpu_ops[cpu]->cpu_disable)
- return cpu_ops[cpu]->cpu_disable(cpu);
+ if (ops->cpu_disable)
+ return ops->cpu_disable(cpu);
return 0;
}
@@ -314,15 +323,17 @@ int __cpu_disable(void)
static int op_cpu_kill(unsigned int cpu)
{
+ const struct cpu_operations *ops = get_cpu_ops(cpu);
+
/*
* If we have no means of synchronising with the dying CPU, then assume
* that it is really dead. We can only wait for an arbitrary length of
* time and hope that it's dead, so let's skip the wait and just hope.
*/
- if (!cpu_ops[cpu]->cpu_kill)
+ if (!ops->cpu_kill)
return 0;
- return cpu_ops[cpu]->cpu_kill(cpu);
+ return ops->cpu_kill(cpu);
}
/*
@@ -357,6 +368,7 @@ void __cpu_die(unsigned int cpu)
void cpu_die(void)
{
unsigned int cpu = smp_processor_id();
+ const struct cpu_operations *ops = get_cpu_ops(cpu);
idle_task_exit();
@@ -370,12 +382,22 @@ void cpu_die(void)
* mechanism must perform all required cache maintenance to ensure that
* no dirty lines are lost in the process of shutting down the CPU.
*/
- cpu_ops[cpu]->cpu_die(cpu);
+ ops->cpu_die(cpu);
BUG();
}
#endif
+static void __cpu_try_die(int cpu)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+ const struct cpu_operations *ops = get_cpu_ops(cpu);
+
+ if (ops && ops->cpu_die)
+ ops->cpu_die(cpu);
+#endif
+}
+
/*
* Kill the calling secondary CPU, early in bringup before it is turned
* online.
@@ -389,12 +411,11 @@ void cpu_die_early(void)
/* Mark this CPU absent */
set_cpu_present(cpu, 0);
-#ifdef CONFIG_HOTPLUG_CPU
- update_cpu_boot_status(CPU_KILL_ME);
- /* Check if we can park ourselves */
- if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die)
- cpu_ops[cpu]->cpu_die(cpu);
-#endif
+ if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
+ update_cpu_boot_status(CPU_KILL_ME);
+ __cpu_try_die(cpu);
+ }
+
update_cpu_boot_status(CPU_STUCK_IN_KERNEL);
cpu_park_loop();
@@ -488,10 +509,13 @@ static bool __init is_mpidr_duplicate(unsigned int cpu, u64 hwid)
*/
static int __init smp_cpu_setup(int cpu)
{
- if (cpu_read_ops(cpu))
+ const struct cpu_operations *ops;
+
+ if (init_cpu_ops(cpu))
return -ENODEV;
- if (cpu_ops[cpu]->cpu_init(cpu))
+ ops = get_cpu_ops(cpu);
+ if (ops->cpu_init(cpu))
return -ENODEV;
set_cpu_possible(cpu, true);
@@ -714,6 +738,7 @@ void __init smp_init_cpus(void)
void __init smp_prepare_cpus(unsigned int max_cpus)
{
+ const struct cpu_operations *ops;
int err;
unsigned int cpu;
unsigned int this_cpu;
@@ -744,10 +769,11 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
if (cpu == smp_processor_id())
continue;
- if (!cpu_ops[cpu])
+ ops = get_cpu_ops(cpu);
+ if (!ops)
continue;
- err = cpu_ops[cpu]->cpu_prepare(cpu);
+ err = ops->cpu_prepare(cpu);
if (err)
continue;
@@ -863,10 +889,8 @@ static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
local_irq_disable();
sdei_mask_local_cpu();
-#ifdef CONFIG_HOTPLUG_CPU
- if (cpu_ops[cpu]->cpu_die)
- cpu_ops[cpu]->cpu_die(cpu);
-#endif
+ if (IS_ENABLED(CONFIG_HOTPLUG_CPU))
+ __cpu_try_die(cpu);
/* just in case */
cpu_park_loop();
@@ -1059,8 +1083,9 @@ static bool have_cpu_die(void)
{
#ifdef CONFIG_HOTPLUG_CPU
int any_cpu = raw_smp_processor_id();
+ const struct cpu_operations *ops = get_cpu_ops(any_cpu);
- if (cpu_ops[any_cpu] && cpu_ops[any_cpu]->cpu_die)
+ if (ops && ops->cpu_die)
return true;
#endif
return false;
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index a336cb124320..139679c745bf 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -14,6 +14,7 @@
#include <linux/stacktrace.h>
#include <asm/irq.h>
+#include <asm/pointer_auth.h>
#include <asm/stack_pointer.h>
#include <asm/stacktrace.h>
@@ -86,7 +87,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
if (tsk->ret_stack &&
- (frame->pc == (unsigned long)return_to_handler)) {
+ (ptrauth_strip_insn_pac(frame->pc) == (unsigned long)return_to_handler)) {
struct ftrace_ret_stack *ret_stack;
/*
* This is a case where function graph tracer has
@@ -101,6 +102,8 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+ frame->pc = ptrauth_strip_insn_pac(frame->pc);
+
/*
* Frames created upon entry from EL0 have NULL FP and PC values, so
* don't bother reporting these. Frames created by __noreturn functions
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index fa9528dfd0ce..0801a0f3c156 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -14,6 +14,7 @@
#include <linux/acpi.h>
#include <linux/arch_topology.h>
#include <linux/cacheinfo.h>
+#include <linux/cpufreq.h>
#include <linux/init.h>
#include <linux/percpu.h>
@@ -120,4 +121,183 @@ int __init parse_acpi_topology(void)
}
#endif
+#ifdef CONFIG_ARM64_AMU_EXTN
+#undef pr_fmt
+#define pr_fmt(fmt) "AMU: " fmt
+
+static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale);
+static DEFINE_PER_CPU(u64, arch_const_cycles_prev);
+static DEFINE_PER_CPU(u64, arch_core_cycles_prev);
+static cpumask_var_t amu_fie_cpus;
+
+/* Initialize counter reference per-cpu variables for the current CPU */
+void init_cpu_freq_invariance_counters(void)
+{
+ this_cpu_write(arch_core_cycles_prev,
+ read_sysreg_s(SYS_AMEVCNTR0_CORE_EL0));
+ this_cpu_write(arch_const_cycles_prev,
+ read_sysreg_s(SYS_AMEVCNTR0_CONST_EL0));
+}
+
+static int validate_cpu_freq_invariance_counters(int cpu)
+{
+ u64 max_freq_hz, ratio;
+
+ if (!cpu_has_amu_feat(cpu)) {
+ pr_debug("CPU%d: counters are not supported.\n", cpu);
+ return -EINVAL;
+ }
+
+ if (unlikely(!per_cpu(arch_const_cycles_prev, cpu) ||
+ !per_cpu(arch_core_cycles_prev, cpu))) {
+ pr_debug("CPU%d: cycle counters are not enabled.\n", cpu);
+ return -EINVAL;
+ }
+
+ /* Convert maximum frequency from KHz to Hz and validate */
+ max_freq_hz = cpufreq_get_hw_max_freq(cpu) * 1000;
+ if (unlikely(!max_freq_hz)) {
+ pr_debug("CPU%d: invalid maximum frequency.\n", cpu);
+ return -EINVAL;
+ }
+
+ /*
+ * Pre-compute the fixed ratio between the frequency of the constant
+ * counter and the maximum frequency of the CPU.
+ *
+ * const_freq
+ * arch_max_freq_scale = ---------------- * SCHED_CAPACITY_SCALE²
+ * cpuinfo_max_freq
+ *
+ * We use a factor of 2 * SCHED_CAPACITY_SHIFT -> SCHED_CAPACITY_SCALE²
+ * in order to ensure a good resolution for arch_max_freq_scale for
+ * very low arch timer frequencies (down to the KHz range which should
+ * be unlikely).
+ */
+ ratio = (u64)arch_timer_get_rate() << (2 * SCHED_CAPACITY_SHIFT);
+ ratio = div64_u64(ratio, max_freq_hz);
+ if (!ratio) {
+ WARN_ONCE(1, "System timer frequency too low.\n");
+ return -EINVAL;
+ }
+
+ per_cpu(arch_max_freq_scale, cpu) = (unsigned long)ratio;
+
+ return 0;
+}
+
+static inline bool
+enable_policy_freq_counters(int cpu, cpumask_var_t valid_cpus)
+{
+ struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+
+ if (!policy) {
+ pr_debug("CPU%d: No cpufreq policy found.\n", cpu);
+ return false;
+ }
+
+ if (cpumask_subset(policy->related_cpus, valid_cpus))
+ cpumask_or(amu_fie_cpus, policy->related_cpus,
+ amu_fie_cpus);
+
+ cpufreq_cpu_put(policy);
+
+ return true;
+}
+
+static DEFINE_STATIC_KEY_FALSE(amu_fie_key);
+#define amu_freq_invariant() static_branch_unlikely(&amu_fie_key)
+
+static int __init init_amu_fie(void)
+{
+ cpumask_var_t valid_cpus;
+ bool have_policy = false;
+ int ret = 0;
+ int cpu;
+
+ if (!zalloc_cpumask_var(&valid_cpus, GFP_KERNEL))
+ return -ENOMEM;
+
+ if (!zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL)) {
+ ret = -ENOMEM;
+ goto free_valid_mask;
+ }
+
+ for_each_present_cpu(cpu) {
+ if (validate_cpu_freq_invariance_counters(cpu))
+ continue;
+ cpumask_set_cpu(cpu, valid_cpus);
+ have_policy |= enable_policy_freq_counters(cpu, valid_cpus);
+ }
+
+ /*
+ * If we are not restricted by cpufreq policies, we only enable
+ * the use of the AMU feature for FIE if all CPUs support AMU.
+ * Otherwise, enable_policy_freq_counters has already enabled
+ * policy cpus.
+ */
+ if (!have_policy && cpumask_equal(valid_cpus, cpu_present_mask))
+ cpumask_or(amu_fie_cpus, amu_fie_cpus, valid_cpus);
+
+ if (!cpumask_empty(amu_fie_cpus)) {
+ pr_info("CPUs[%*pbl]: counters will be used for FIE.",
+ cpumask_pr_args(amu_fie_cpus));
+ static_branch_enable(&amu_fie_key);
+ }
+
+free_valid_mask:
+ free_cpumask_var(valid_cpus);
+
+ return ret;
+}
+late_initcall_sync(init_amu_fie);
+
+bool arch_freq_counters_available(struct cpumask *cpus)
+{
+ return amu_freq_invariant() &&
+ cpumask_subset(cpus, amu_fie_cpus);
+}
+
+void topology_scale_freq_tick(void)
+{
+ u64 prev_core_cnt, prev_const_cnt;
+ u64 core_cnt, const_cnt, scale;
+ int cpu = smp_processor_id();
+
+ if (!amu_freq_invariant())
+ return;
+
+ if (!cpumask_test_cpu(cpu, amu_fie_cpus))
+ return;
+
+ const_cnt = read_sysreg_s(SYS_AMEVCNTR0_CONST_EL0);
+ core_cnt = read_sysreg_s(SYS_AMEVCNTR0_CORE_EL0);
+ prev_const_cnt = this_cpu_read(arch_const_cycles_prev);
+ prev_core_cnt = this_cpu_read(arch_core_cycles_prev);
+
+ if (unlikely(core_cnt <= prev_core_cnt ||
+ const_cnt <= prev_const_cnt))
+ goto store_and_exit;
+
+ /*
+ * /\core arch_max_freq_scale
+ * scale = ------- * --------------------
+ * /\const SCHED_CAPACITY_SCALE
+ *
+ * See validate_cpu_freq_invariance_counters() for details on
+ * arch_max_freq_scale and the use of SCHED_CAPACITY_SHIFT.
+ */
+ scale = core_cnt - prev_core_cnt;
+ scale *= this_cpu_read(arch_max_freq_scale);
+ scale = div64_u64(scale >> SCHED_CAPACITY_SHIFT,
+ const_cnt - prev_const_cnt);
+
+ scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE);
+ this_cpu_write(freq_scale, (unsigned long)scale);
+
+store_and_exit:
+ this_cpu_write(arch_core_cycles_prev, core_cnt);
+ this_cpu_write(arch_const_cycles_prev, const_cnt);
+}
+#endif /* CONFIG_ARM64_AMU_EXTN */
diff --git a/arch/arm64/kernel/vdso/sigreturn.S b/arch/arm64/kernel/vdso/sigreturn.S
index 0723aa398d6e..12324863d5c2 100644
--- a/arch/arm64/kernel/vdso/sigreturn.S
+++ b/arch/arm64/kernel/vdso/sigreturn.S
@@ -14,7 +14,7 @@
.text
nop
-ENTRY(__kernel_rt_sigreturn)
+SYM_FUNC_START(__kernel_rt_sigreturn)
.cfi_startproc
.cfi_signal_frame
.cfi_def_cfa x29, 0
@@ -23,4 +23,4 @@ ENTRY(__kernel_rt_sigreturn)
mov x8, #__NR_rt_sigreturn
svc #0
.cfi_endproc
-ENDPROC(__kernel_rt_sigreturn)
+SYM_FUNC_END(__kernel_rt_sigreturn)
diff --git a/arch/arm64/kernel/vdso32/sigreturn.S b/arch/arm64/kernel/vdso32/sigreturn.S
index 1a81277c2d09..620524969696 100644
--- a/arch/arm64/kernel/vdso32/sigreturn.S
+++ b/arch/arm64/kernel/vdso32/sigreturn.S
@@ -10,13 +10,6 @@
#include <asm/asm-offsets.h>
#include <asm/unistd.h>
-#define ARM_ENTRY(name) \
- ENTRY(name)
-
-#define ARM_ENDPROC(name) \
- .type name, %function; \
- END(name)
-
.text
.arm
@@ -24,39 +17,39 @@
.save {r0-r15}
.pad #COMPAT_SIGFRAME_REGS_OFFSET
nop
-ARM_ENTRY(__kernel_sigreturn_arm)
+SYM_FUNC_START(__kernel_sigreturn_arm)
mov r7, #__NR_compat_sigreturn
svc #0
.fnend
-ARM_ENDPROC(__kernel_sigreturn_arm)
+SYM_FUNC_END(__kernel_sigreturn_arm)
.fnstart
.save {r0-r15}
.pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
nop
-ARM_ENTRY(__kernel_rt_sigreturn_arm)
+SYM_FUNC_START(__kernel_rt_sigreturn_arm)
mov r7, #__NR_compat_rt_sigreturn
svc #0
.fnend
-ARM_ENDPROC(__kernel_rt_sigreturn_arm)
+SYM_FUNC_END(__kernel_rt_sigreturn_arm)
.thumb
.fnstart
.save {r0-r15}
.pad #COMPAT_SIGFRAME_REGS_OFFSET
nop
-ARM_ENTRY(__kernel_sigreturn_thumb)
+SYM_FUNC_START(__kernel_sigreturn_thumb)
mov r7, #__NR_compat_sigreturn
svc #0
.fnend
-ARM_ENDPROC(__kernel_sigreturn_thumb)
+SYM_FUNC_END(__kernel_sigreturn_thumb)
.fnstart
.save {r0-r15}
.pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
nop
-ARM_ENTRY(__kernel_rt_sigreturn_thumb)
+SYM_FUNC_START(__kernel_rt_sigreturn_thumb)
mov r7, #__NR_compat_rt_sigreturn
svc #0
.fnend
-ARM_ENDPROC(__kernel_rt_sigreturn_thumb)
+SYM_FUNC_END(__kernel_rt_sigreturn_thumb)
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 160be2b4696d..6e6ed5581eed 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -18,7 +18,7 @@
.align 11
-ENTRY(__kvm_hyp_init)
+SYM_CODE_START(__kvm_hyp_init)
ventry __invalid // Synchronous EL2t
ventry __invalid // IRQ EL2t
ventry __invalid // FIQ EL2t
@@ -60,7 +60,7 @@ alternative_else_nop_endif
msr ttbr0_el2, x4
mrs x4, tcr_el1
- ldr x5, =TCR_EL2_MASK
+ mov_q x5, TCR_EL2_MASK
and x4, x4, x5
mov x5, #TCR_EL2_RES1
orr x4, x4, x5
@@ -102,7 +102,7 @@ alternative_else_nop_endif
* as well as the EE bit on BE. Drop the A flag since the compiler
* is allowed to generate unaligned accesses.
*/
- ldr x4, =(SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A))
+ mov_q x4, (SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A))
CPU_BE( orr x4, x4, #SCTLR_ELx_EE)
msr sctlr_el2, x4
isb
@@ -117,9 +117,9 @@ CPU_BE( orr x4, x4, #SCTLR_ELx_EE)
/* Hello, World! */
eret
-ENDPROC(__kvm_hyp_init)
+SYM_CODE_END(__kvm_hyp_init)
-ENTRY(__kvm_handle_stub_hvc)
+SYM_CODE_START(__kvm_handle_stub_hvc)
cmp x0, #HVC_SOFT_RESTART
b.ne 1f
@@ -142,7 +142,7 @@ reset:
* case we coming via HVC_SOFT_RESTART.
*/
mrs x5, sctlr_el2
- ldr x6, =SCTLR_ELx_FLAGS
+ mov_q x6, SCTLR_ELx_FLAGS
bic x5, x5, x6 // Clear SCTL_M and etc
pre_disable_mmu_workaround
msr sctlr_el2, x5
@@ -155,11 +155,9 @@ reset:
eret
1: /* Bad stub call */
- ldr x0, =HVC_STUB_ERR
+ mov_q x0, HVC_STUB_ERR
eret
-ENDPROC(__kvm_handle_stub_hvc)
-
- .ltorg
+SYM_CODE_END(__kvm_handle_stub_hvc)
.popsection
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index c0094d520dff..3c79a1124af2 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -28,7 +28,7 @@
* and is used to implement hyp stubs in the same way as in
* arch/arm64/kernel/hyp_stub.S.
*/
-ENTRY(__kvm_call_hyp)
+SYM_FUNC_START(__kvm_call_hyp)
hvc #0
ret
-ENDPROC(__kvm_call_hyp)
+SYM_FUNC_END(__kvm_call_hyp)
diff --git a/arch/arm64/kvm/hyp/fpsimd.S b/arch/arm64/kvm/hyp/fpsimd.S
index 78ff53225691..5b8ff517ff10 100644
--- a/arch/arm64/kvm/hyp/fpsimd.S
+++ b/arch/arm64/kvm/hyp/fpsimd.S
@@ -11,12 +11,12 @@
.text
.pushsection .hyp.text, "ax"
-ENTRY(__fpsimd_save_state)
+SYM_FUNC_START(__fpsimd_save_state)
fpsimd_save x0, 1
ret
-ENDPROC(__fpsimd_save_state)
+SYM_FUNC_END(__fpsimd_save_state)
-ENTRY(__fpsimd_restore_state)
+SYM_FUNC_START(__fpsimd_restore_state)
fpsimd_restore x0, 1
ret
-ENDPROC(__fpsimd_restore_state)
+SYM_FUNC_END(__fpsimd_restore_state)
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index ffa68d5713f1..c2a13ab3c471 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -180,7 +180,7 @@ el2_error:
eret
sb
-ENTRY(__hyp_do_panic)
+SYM_FUNC_START(__hyp_do_panic)
mov lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
PSR_MODE_EL1h)
msr spsr_el2, lr
@@ -188,18 +188,19 @@ ENTRY(__hyp_do_panic)
msr elr_el2, lr
eret
sb
-ENDPROC(__hyp_do_panic)
+SYM_FUNC_END(__hyp_do_panic)
-ENTRY(__hyp_panic)
+SYM_CODE_START(__hyp_panic)
get_host_ctxt x0, x1
b hyp_panic
-ENDPROC(__hyp_panic)
+SYM_CODE_END(__hyp_panic)
.macro invalid_vector label, target = __hyp_panic
.align 2
+SYM_CODE_START(\label)
\label:
b \target
-ENDPROC(\label)
+SYM_CODE_END(\label)
.endm
/* None of these should ever happen */
@@ -246,7 +247,7 @@ check_preamble_length 661b, 662b
check_preamble_length 661b, 662b
.endm
-ENTRY(__kvm_hyp_vector)
+SYM_CODE_START(__kvm_hyp_vector)
invalid_vect el2t_sync_invalid // Synchronous EL2t
invalid_vect el2t_irq_invalid // IRQ EL2t
invalid_vect el2t_fiq_invalid // FIQ EL2t
@@ -266,7 +267,7 @@ ENTRY(__kvm_hyp_vector)
valid_vect el1_irq // IRQ 32-bit EL1
invalid_vect el1_fiq_invalid // FIQ 32-bit EL1
valid_vect el1_error // Error 32-bit EL1
-ENDPROC(__kvm_hyp_vector)
+SYM_CODE_END(__kvm_hyp_vector)
#ifdef CONFIG_KVM_INDIRECT_VECTORS
.macro hyp_ventry
@@ -311,15 +312,17 @@ alternative_cb_end
.endm
.align 11
-ENTRY(__bp_harden_hyp_vecs_start)
+SYM_CODE_START(__bp_harden_hyp_vecs)
.rept BP_HARDEN_EL2_SLOTS
generate_vectors
.endr
-ENTRY(__bp_harden_hyp_vecs_end)
+1: .org __bp_harden_hyp_vecs + __BP_HARDEN_HYP_VECS_SZ
+ .org 1b
+SYM_CODE_END(__bp_harden_hyp_vecs)
.popsection
-ENTRY(__smccc_workaround_1_smc_start)
+SYM_CODE_START(__smccc_workaround_1_smc)
esb
sub sp, sp, #(8 * 4)
stp x2, x3, [sp, #(8 * 0)]
@@ -329,5 +332,7 @@ ENTRY(__smccc_workaround_1_smc_start)
ldp x2, x3, [sp, #(8 * 0)]
ldp x0, x1, [sp, #(8 * 2)]
add sp, sp, #(8 * 4)
-ENTRY(__smccc_workaround_1_smc_end)
+1: .org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ
+ .org 1b
+SYM_CODE_END(__smccc_workaround_1_smc)
#endif
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 925086b46136..eaa05c3c7235 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -98,6 +98,18 @@ static void activate_traps_vhe(struct kvm_vcpu *vcpu)
val = read_sysreg(cpacr_el1);
val |= CPACR_EL1_TTA;
val &= ~CPACR_EL1_ZEN;
+
+ /*
+ * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
+ * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
+ * except for some missing controls, such as TAM.
+ * In this case, CPTR_EL2.TAM has the same position with or without
+ * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
+ * shift value for trapping the AMU accesses.
+ */
+
+ val |= CPTR_EL2_TAM;
+
if (update_fp_enabled(vcpu)) {
if (vcpu_has_sve(vcpu))
val |= CPACR_EL1_ZEN;
@@ -119,7 +131,7 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
__activate_traps_common(vcpu);
val = CPTR_EL2_DEFAULT;
- val |= CPTR_EL2_TTA | CPTR_EL2_TZ;
+ val |= CPTR_EL2_TTA | CPTR_EL2_TZ | CPTR_EL2_TAM;
if (!update_fp_enabled(vcpu)) {
val |= CPTR_EL2_TFP;
__activate_traps_fpsimd32(vcpu);
@@ -127,7 +139,7 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
write_sysreg(val, cptr_el2);
- if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+ if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
isb();
@@ -146,12 +158,12 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
{
u64 hcr = vcpu->arch.hcr_el2;
- if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
+ if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
hcr |= HCR_TVM;
write_sysreg(hcr, hcr_el2);
- if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
+ if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
if (has_vhe())
@@ -181,7 +193,7 @@ static void __hyp_text __deactivate_traps_nvhe(void)
{
u64 mdcr_el2 = read_sysreg(mdcr_el2);
- if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+ if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
u64 val;
/*
@@ -328,7 +340,7 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
* resolve the IPA using the AT instruction.
*/
if (!(esr & ESR_ELx_S1PTW) &&
- (cpus_have_const_cap(ARM64_WORKAROUND_834220) ||
+ (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
(esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
if (!__translate_far_to_hpfar(far, &hpfar))
return false;
@@ -498,7 +510,7 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
if (*exit_code != ARM_EXCEPTION_TRAP)
goto exit;
- if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
+ if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
handle_tx2_tvm(vcpu))
return true;
@@ -555,7 +567,7 @@ exit:
static inline bool __hyp_text __needs_ssbd_off(struct kvm_vcpu *vcpu)
{
- if (!cpus_have_const_cap(ARM64_SSBD))
+ if (!cpus_have_final_cap(ARM64_SSBD))
return false;
return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG);
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 7672a978926c..75b1925763f1 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -71,7 +71,7 @@ static void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_context *ct
ctxt->gp_regs.regs.pc = read_sysreg_el2(SYS_ELR);
ctxt->gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR);
- if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN))
+ if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
ctxt->sys_regs[DISR_EL1] = read_sysreg_s(SYS_VDISR_EL2);
}
@@ -118,7 +118,7 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
write_sysreg(ctxt->sys_regs[MPIDR_EL1], vmpidr_el2);
write_sysreg(ctxt->sys_regs[CSSELR_EL1], csselr_el1);
- if (!cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+ if (!cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR);
write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR);
} else if (!ctxt->__hyp_running_vcpu) {
@@ -149,7 +149,7 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
write_sysreg(ctxt->sys_regs[PAR_EL1], par_el1);
write_sysreg(ctxt->sys_regs[TPIDR_EL1], tpidr_el1);
- if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE) &&
+ if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE) &&
ctxt->__hyp_running_vcpu) {
/*
* Must only be done for host registers, hence the context
@@ -194,7 +194,7 @@ __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
write_sysreg_el2(ctxt->gp_regs.regs.pc, SYS_ELR);
write_sysreg_el2(pstate, SYS_SPSR);
- if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN))
+ if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN))
write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2);
}
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index 92f560e3e1aa..ceaddbe4279f 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -23,7 +23,7 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm,
local_irq_save(cxt->flags);
- if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) {
+ if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) {
/*
* For CPUs that are affected by ARM errata 1165522 or 1530923,
* we cannot trust stage-1 to be in a correct state at that
@@ -63,7 +63,7 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm,
static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
struct tlb_inv_context *cxt)
{
- if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+ if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
u64 val;
/*
@@ -103,7 +103,7 @@ static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm,
write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
isb();
- if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) {
+ if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_VHE)) {
/* Restore the registers to what they were */
write_sysreg_el1(cxt->tcr, SYS_TCR);
write_sysreg_el1(cxt->sctlr, SYS_SCTLR);
@@ -117,7 +117,7 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm,
{
write_sysreg(0, vttbr_el2);
- if (cpus_have_const_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
+ if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT_NVHE)) {
/* Ensure write of the host VMID */
isb();
/* Restore the host's TCR_EL1 */
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 3e909b117f0c..090f46d3add1 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1003,6 +1003,20 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
{ SYS_DESC(SYS_PMEVTYPERn_EL0(n)), \
access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), }
+static bool access_amu(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ kvm_inject_undefined(vcpu);
+
+ return false;
+}
+
+/* Macro to expand the AMU counter and type registers*/
+#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), access_amu }
+#define AMU_AMEVTYPE0_EL0(n) { SYS_DESC(SYS_AMEVTYPE0_EL0(n)), access_amu }
+#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), access_amu }
+#define AMU_AMEVTYPE1_EL0(n) { SYS_DESC(SYS_AMEVTYPE1_EL0(n)), access_amu }
+
static bool trap_ptrauth(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *rd)
@@ -1078,13 +1092,25 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
(u32)r->CRn, (u32)r->CRm, (u32)r->Op2);
u64 val = raz ? 0 : read_sanitised_ftr_reg(id);
- if (id == SYS_ID_AA64PFR0_EL1 && !vcpu_has_sve(vcpu)) {
- val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
+ if (id == SYS_ID_AA64PFR0_EL1) {
+ if (!vcpu_has_sve(vcpu))
+ val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
+ val &= ~(0xfUL << ID_AA64PFR0_AMU_SHIFT);
} else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) {
val &= ~((0xfUL << ID_AA64ISAR1_APA_SHIFT) |
(0xfUL << ID_AA64ISAR1_API_SHIFT) |
(0xfUL << ID_AA64ISAR1_GPA_SHIFT) |
(0xfUL << ID_AA64ISAR1_GPI_SHIFT));
+ } else if (id == SYS_ID_AA64DFR0_EL1) {
+ /* Limit guests to PMUv3 for ARMv8.1 */
+ val = cpuid_feature_cap_perfmon_field(val,
+ ID_AA64DFR0_PMUVER_SHIFT,
+ ID_AA64DFR0_PMUVER_8_1);
+ } else if (id == SYS_ID_DFR0_EL1) {
+ /* Limit guests to PMUv3 for ARMv8.1 */
+ val = cpuid_feature_cap_perfmon_field(val,
+ ID_DFR0_PERFMON_SHIFT,
+ ID_DFR0_PERFMON_8_1);
}
return val;
@@ -1565,6 +1591,79 @@ static const struct sys_reg_desc sys_reg_descs[] = {
{ SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 },
{ SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 },
+ { SYS_DESC(SYS_AMCR_EL0), access_amu },
+ { SYS_DESC(SYS_AMCFGR_EL0), access_amu },
+ { SYS_DESC(SYS_AMCGCR_EL0), access_amu },
+ { SYS_DESC(SYS_AMUSERENR_EL0), access_amu },
+ { SYS_DESC(SYS_AMCNTENCLR0_EL0), access_amu },
+ { SYS_DESC(SYS_AMCNTENSET0_EL0), access_amu },
+ { SYS_DESC(SYS_AMCNTENCLR1_EL0), access_amu },
+ { SYS_DESC(SYS_AMCNTENSET1_EL0), access_amu },
+ AMU_AMEVCNTR0_EL0(0),
+ AMU_AMEVCNTR0_EL0(1),
+ AMU_AMEVCNTR0_EL0(2),
+ AMU_AMEVCNTR0_EL0(3),
+ AMU_AMEVCNTR0_EL0(4),
+ AMU_AMEVCNTR0_EL0(5),
+ AMU_AMEVCNTR0_EL0(6),
+ AMU_AMEVCNTR0_EL0(7),
+ AMU_AMEVCNTR0_EL0(8),
+ AMU_AMEVCNTR0_EL0(9),
+ AMU_AMEVCNTR0_EL0(10),
+ AMU_AMEVCNTR0_EL0(11),
+ AMU_AMEVCNTR0_EL0(12),
+ AMU_AMEVCNTR0_EL0(13),
+ AMU_AMEVCNTR0_EL0(14),
+ AMU_AMEVCNTR0_EL0(15),
+ AMU_AMEVTYPE0_EL0(0),
+ AMU_AMEVTYPE0_EL0(1),
+ AMU_AMEVTYPE0_EL0(2),
+ AMU_AMEVTYPE0_EL0(3),
+ AMU_AMEVTYPE0_EL0(4),
+ AMU_AMEVTYPE0_EL0(5),
+ AMU_AMEVTYPE0_EL0(6),
+ AMU_AMEVTYPE0_EL0(7),
+ AMU_AMEVTYPE0_EL0(8),
+ AMU_AMEVTYPE0_EL0(9),
+ AMU_AMEVTYPE0_EL0(10),
+ AMU_AMEVTYPE0_EL0(11),
+ AMU_AMEVTYPE0_EL0(12),
+ AMU_AMEVTYPE0_EL0(13),
+ AMU_AMEVTYPE0_EL0(14),
+ AMU_AMEVTYPE0_EL0(15),
+ AMU_AMEVCNTR1_EL0(0),
+ AMU_AMEVCNTR1_EL0(1),
+ AMU_AMEVCNTR1_EL0(2),
+ AMU_AMEVCNTR1_EL0(3),
+ AMU_AMEVCNTR1_EL0(4),
+ AMU_AMEVCNTR1_EL0(5),
+ AMU_AMEVCNTR1_EL0(6),
+ AMU_AMEVCNTR1_EL0(7),
+ AMU_AMEVCNTR1_EL0(8),
+ AMU_AMEVCNTR1_EL0(9),
+ AMU_AMEVCNTR1_EL0(10),
+ AMU_AMEVCNTR1_EL0(11),
+ AMU_AMEVCNTR1_EL0(12),
+ AMU_AMEVCNTR1_EL0(13),
+ AMU_AMEVCNTR1_EL0(14),
+ AMU_AMEVCNTR1_EL0(15),
+ AMU_AMEVTYPE1_EL0(0),
+ AMU_AMEVTYPE1_EL0(1),
+ AMU_AMEVTYPE1_EL0(2),
+ AMU_AMEVTYPE1_EL0(3),
+ AMU_AMEVTYPE1_EL0(4),
+ AMU_AMEVTYPE1_EL0(5),
+ AMU_AMEVTYPE1_EL0(6),
+ AMU_AMEVTYPE1_EL0(7),
+ AMU_AMEVTYPE1_EL0(8),
+ AMU_AMEVTYPE1_EL0(9),
+ AMU_AMEVTYPE1_EL0(10),
+ AMU_AMEVTYPE1_EL0(11),
+ AMU_AMEVTYPE1_EL0(12),
+ AMU_AMEVTYPE1_EL0(13),
+ AMU_AMEVTYPE1_EL0(14),
+ AMU_AMEVTYPE1_EL0(15),
+
{ SYS_DESC(SYS_CNTP_TVAL_EL0), access_arch_timer },
{ SYS_DESC(SYS_CNTP_CTL_EL0), access_arch_timer },
{ SYS_DESC(SYS_CNTP_CVAL_EL0), access_arch_timer },
diff --git a/arch/arm64/lib/csum.c b/arch/arm64/lib/csum.c
index 1f82c66b32ea..60eccae2abad 100644
--- a/arch/arm64/lib/csum.c
+++ b/arch/arm64/lib/csum.c
@@ -124,3 +124,30 @@ unsigned int do_csum(const unsigned char *buff, int len)
return sum >> 16;
}
+
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+ const struct in6_addr *daddr,
+ __u32 len, __u8 proto, __wsum csum)
+{
+ __uint128_t src, dst;
+ u64 sum = (__force u64)csum;
+
+ src = *(const __uint128_t *)saddr->s6_addr;
+ dst = *(const __uint128_t *)daddr->s6_addr;
+
+ sum += (__force u32)htonl(len);
+#ifdef __LITTLE_ENDIAN
+ sum += (u32)proto << 24;
+#else
+ sum += proto;
+#endif
+ src += (src >> 64) | (src << 64);
+ dst += (dst >> 64) | (dst << 64);
+
+ sum = accumulate(sum, src >> 64);
+ sum = accumulate(sum, dst >> 64);
+
+ sum += ((sum >> 32) | (sum << 32));
+ return csum_fold((__force __wsum)(sum >> 32));
+}
+EXPORT_SYMBOL(csum_ipv6_magic);
diff --git a/arch/arm64/lib/strcmp.S b/arch/arm64/lib/strcmp.S
index 4767540d1b94..4e79566726c8 100644
--- a/arch/arm64/lib/strcmp.S
+++ b/arch/arm64/lib/strcmp.S
@@ -186,7 +186,7 @@ CPU_LE( rev data2, data2 )
* as carry-propagation can corrupt the upper bits if the trailing
* bytes in the string contain 0x01.
* However, if there is no NUL byte in the dword, we can generate
- * the result directly. We ca not just subtract the bytes as the
+ * the result directly. We cannot just subtract the bytes as the
* MSB might be significant.
*/
CPU_BE( cbnz has_nul, 1f )
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index d89bb22589f6..9b26f9a88724 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -6,6 +6,7 @@
* Copyright (C) 2012 ARM Ltd.
*/
+#include <linux/bitfield.h>
#include <linux/bitops.h>
#include <linux/sched.h>
#include <linux/slab.h>
@@ -254,10 +255,37 @@ switch_mm_fastpath:
/* Errata workaround post TTBRx_EL1 update. */
asmlinkage void post_ttbr_update_workaround(void)
{
+ if (!IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456))
+ return;
+
asm(ALTERNATIVE("nop; nop; nop",
"ic iallu; dsb nsh; isb",
- ARM64_WORKAROUND_CAVIUM_27456,
- CONFIG_CAVIUM_ERRATUM_27456));
+ ARM64_WORKAROUND_CAVIUM_27456));
+}
+
+void cpu_do_switch_mm(phys_addr_t pgd_phys, struct mm_struct *mm)
+{
+ unsigned long ttbr1 = read_sysreg(ttbr1_el1);
+ unsigned long asid = ASID(mm);
+ unsigned long ttbr0 = phys_to_ttbr(pgd_phys);
+
+ /* Skip CNP for the reserved ASID */
+ if (system_supports_cnp() && asid)
+ ttbr0 |= TTBR_CNP_BIT;
+
+ /* SW PAN needs a copy of the ASID in TTBR0 for entry */
+ if (IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN))
+ ttbr0 |= FIELD_PREP(TTBR_ASID_MASK, asid);
+
+ /* Set ASID in TTBR1 since TCR.A1 is set */
+ ttbr1 &= ~TTBR_ASID_MASK;
+ ttbr1 |= FIELD_PREP(TTBR_ASID_MASK, asid);
+
+ write_sysreg(ttbr1, ttbr1_el1);
+ isb();
+ write_sysreg(ttbr0, ttbr0_el1);
+ isb();
+ post_ttbr_update_workaround();
}
static int asids_update_limit(void)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 128f70852bf3..9b08f7c7e6f0 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -17,6 +17,7 @@
#include <linux/mman.h>
#include <linux/nodemask.h>
#include <linux/memblock.h>
+#include <linux/memory.h>
#include <linux/fs.h>
#include <linux/io.h>
#include <linux/mm.h>
@@ -724,6 +725,312 @@ int kern_addr_valid(unsigned long addr)
return pfn_valid(pte_pfn(pte));
}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+static void free_hotplug_page_range(struct page *page, size_t size)
+{
+ WARN_ON(PageReserved(page));
+ free_pages((unsigned long)page_address(page), get_order(size));
+}
+
+static void free_hotplug_pgtable_page(struct page *page)
+{
+ free_hotplug_page_range(page, PAGE_SIZE);
+}
+
+static bool pgtable_range_aligned(unsigned long start, unsigned long end,
+ unsigned long floor, unsigned long ceiling,
+ unsigned long mask)
+{
+ start &= mask;
+ if (start < floor)
+ return false;
+
+ if (ceiling) {
+ ceiling &= mask;
+ if (!ceiling)
+ return false;
+ }
+
+ if (end - 1 > ceiling - 1)
+ return false;
+ return true;
+}
+
+static void unmap_hotplug_pte_range(pmd_t *pmdp, unsigned long addr,
+ unsigned long end, bool free_mapped)
+{
+ pte_t *ptep, pte;
+
+ do {
+ ptep = pte_offset_kernel(pmdp, addr);
+ pte = READ_ONCE(*ptep);
+ if (pte_none(pte))
+ continue;
+
+ WARN_ON(!pte_present(pte));
+ pte_clear(&init_mm, addr, ptep);
+ flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+ if (free_mapped)
+ free_hotplug_page_range(pte_page(pte), PAGE_SIZE);
+ } while (addr += PAGE_SIZE, addr < end);
+}
+
+static void unmap_hotplug_pmd_range(pud_t *pudp, unsigned long addr,
+ unsigned long end, bool free_mapped)
+{
+ unsigned long next;
+ pmd_t *pmdp, pmd;
+
+ do {
+ next = pmd_addr_end(addr, end);
+ pmdp = pmd_offset(pudp, addr);
+ pmd = READ_ONCE(*pmdp);
+ if (pmd_none(pmd))
+ continue;
+
+ WARN_ON(!pmd_present(pmd));
+ if (pmd_sect(pmd)) {
+ pmd_clear(pmdp);
+
+ /*
+ * One TLBI should be sufficient here as the PMD_SIZE
+ * range is mapped with a single block entry.
+ */
+ flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+ if (free_mapped)
+ free_hotplug_page_range(pmd_page(pmd),
+ PMD_SIZE);
+ continue;
+ }
+ WARN_ON(!pmd_table(pmd));
+ unmap_hotplug_pte_range(pmdp, addr, next, free_mapped);
+ } while (addr = next, addr < end);
+}
+
+static void unmap_hotplug_pud_range(p4d_t *p4dp, unsigned long addr,
+ unsigned long end, bool free_mapped)
+{
+ unsigned long next;
+ pud_t *pudp, pud;
+
+ do {
+ next = pud_addr_end(addr, end);
+ pudp = pud_offset(p4dp, addr);
+ pud = READ_ONCE(*pudp);
+ if (pud_none(pud))
+ continue;
+
+ WARN_ON(!pud_present(pud));
+ if (pud_sect(pud)) {
+ pud_clear(pudp);
+
+ /*
+ * One TLBI should be sufficient here as the PUD_SIZE
+ * range is mapped with a single block entry.
+ */
+ flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+ if (free_mapped)
+ free_hotplug_page_range(pud_page(pud),
+ PUD_SIZE);
+ continue;
+ }
+ WARN_ON(!pud_table(pud));
+ unmap_hotplug_pmd_range(pudp, addr, next, free_mapped);
+ } while (addr = next, addr < end);
+}
+
+static void unmap_hotplug_p4d_range(pgd_t *pgdp, unsigned long addr,
+ unsigned long end, bool free_mapped)
+{
+ unsigned long next;
+ p4d_t *p4dp, p4d;
+
+ do {
+ next = p4d_addr_end(addr, end);
+ p4dp = p4d_offset(pgdp, addr);
+ p4d = READ_ONCE(*p4dp);
+ if (p4d_none(p4d))
+ continue;
+
+ WARN_ON(!p4d_present(p4d));
+ unmap_hotplug_pud_range(p4dp, addr, next, free_mapped);
+ } while (addr = next, addr < end);
+}
+
+static void unmap_hotplug_range(unsigned long addr, unsigned long end,
+ bool free_mapped)
+{
+ unsigned long next;
+ pgd_t *pgdp, pgd;
+
+ do {
+ next = pgd_addr_end(addr, end);
+ pgdp = pgd_offset_k(addr);
+ pgd = READ_ONCE(*pgdp);
+ if (pgd_none(pgd))
+ continue;
+
+ WARN_ON(!pgd_present(pgd));
+ unmap_hotplug_p4d_range(pgdp, addr, next, free_mapped);
+ } while (addr = next, addr < end);
+}
+
+static void free_empty_pte_table(pmd_t *pmdp, unsigned long addr,
+ unsigned long end, unsigned long floor,
+ unsigned long ceiling)
+{
+ pte_t *ptep, pte;
+ unsigned long i, start = addr;
+
+ do {
+ ptep = pte_offset_kernel(pmdp, addr);
+ pte = READ_ONCE(*ptep);
+
+ /*
+ * This is just a sanity check here which verifies that
+ * pte clearing has been done by earlier unmap loops.
+ */
+ WARN_ON(!pte_none(pte));
+ } while (addr += PAGE_SIZE, addr < end);
+
+ if (!pgtable_range_aligned(start, end, floor, ceiling, PMD_MASK))
+ return;
+
+ /*
+ * Check whether we can free the pte page if the rest of the
+ * entries are empty. Overlap with other regions have been
+ * handled by the floor/ceiling check.
+ */
+ ptep = pte_offset_kernel(pmdp, 0UL);
+ for (i = 0; i < PTRS_PER_PTE; i++) {
+ if (!pte_none(READ_ONCE(ptep[i])))
+ return;
+ }
+
+ pmd_clear(pmdp);
+ __flush_tlb_kernel_pgtable(start);
+ free_hotplug_pgtable_page(virt_to_page(ptep));
+}
+
+static void free_empty_pmd_table(pud_t *pudp, unsigned long addr,
+ unsigned long end, unsigned long floor,
+ unsigned long ceiling)
+{
+ pmd_t *pmdp, pmd;
+ unsigned long i, next, start = addr;
+
+ do {
+ next = pmd_addr_end(addr, end);
+ pmdp = pmd_offset(pudp, addr);
+ pmd = READ_ONCE(*pmdp);
+ if (pmd_none(pmd))
+ continue;
+
+ WARN_ON(!pmd_present(pmd) || !pmd_table(pmd) || pmd_sect(pmd));
+ free_empty_pte_table(pmdp, addr, next, floor, ceiling);
+ } while (addr = next, addr < end);
+
+ if (CONFIG_PGTABLE_LEVELS <= 2)
+ return;
+
+ if (!pgtable_range_aligned(start, end, floor, ceiling, PUD_MASK))
+ return;
+
+ /*
+ * Check whether we can free the pmd page if the rest of the
+ * entries are empty. Overlap with other regions have been
+ * handled by the floor/ceiling check.
+ */
+ pmdp = pmd_offset(pudp, 0UL);
+ for (i = 0; i < PTRS_PER_PMD; i++) {
+ if (!pmd_none(READ_ONCE(pmdp[i])))
+ return;
+ }
+
+ pud_clear(pudp);
+ __flush_tlb_kernel_pgtable(start);
+ free_hotplug_pgtable_page(virt_to_page(pmdp));
+}
+
+static void free_empty_pud_table(p4d_t *p4dp, unsigned long addr,
+ unsigned long end, unsigned long floor,
+ unsigned long ceiling)
+{
+ pud_t *pudp, pud;
+ unsigned long i, next, start = addr;
+
+ do {
+ next = pud_addr_end(addr, end);
+ pudp = pud_offset(p4dp, addr);
+ pud = READ_ONCE(*pudp);
+ if (pud_none(pud))
+ continue;
+
+ WARN_ON(!pud_present(pud) || !pud_table(pud) || pud_sect(pud));
+ free_empty_pmd_table(pudp, addr, next, floor, ceiling);
+ } while (addr = next, addr < end);
+
+ if (CONFIG_PGTABLE_LEVELS <= 3)
+ return;
+
+ if (!pgtable_range_aligned(start, end, floor, ceiling, PGDIR_MASK))
+ return;
+
+ /*
+ * Check whether we can free the pud page if the rest of the
+ * entries are empty. Overlap with other regions have been
+ * handled by the floor/ceiling check.
+ */
+ pudp = pud_offset(p4dp, 0UL);
+ for (i = 0; i < PTRS_PER_PUD; i++) {
+ if (!pud_none(READ_ONCE(pudp[i])))
+ return;
+ }
+
+ p4d_clear(p4dp);
+ __flush_tlb_kernel_pgtable(start);
+ free_hotplug_pgtable_page(virt_to_page(pudp));
+}
+
+static void free_empty_p4d_table(pgd_t *pgdp, unsigned long addr,
+ unsigned long end, unsigned long floor,
+ unsigned long ceiling)
+{
+ unsigned long next;
+ p4d_t *p4dp, p4d;
+
+ do {
+ next = p4d_addr_end(addr, end);
+ p4dp = p4d_offset(pgdp, addr);
+ p4d = READ_ONCE(*p4dp);
+ if (p4d_none(p4d))
+ continue;
+
+ WARN_ON(!p4d_present(p4d));
+ free_empty_pud_table(p4dp, addr, next, floor, ceiling);
+ } while (addr = next, addr < end);
+}
+
+static void free_empty_tables(unsigned long addr, unsigned long end,
+ unsigned long floor, unsigned long ceiling)
+{
+ unsigned long next;
+ pgd_t *pgdp, pgd;
+
+ do {
+ next = pgd_addr_end(addr, end);
+ pgdp = pgd_offset_k(addr);
+ pgd = READ_ONCE(*pgdp);
+ if (pgd_none(pgd))
+ continue;
+
+ WARN_ON(!pgd_present(pgd));
+ free_empty_p4d_table(pgdp, addr, next, floor, ceiling);
+ } while (addr = next, addr < end);
+}
+#endif
+
#ifdef CONFIG_SPARSEMEM_VMEMMAP
#if !ARM64_SWAPPER_USES_SECTION_MAPS
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
@@ -771,6 +1078,12 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
void vmemmap_free(unsigned long start, unsigned long end,
struct vmem_altmap *altmap)
{
+#ifdef CONFIG_MEMORY_HOTPLUG
+ WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
+
+ unmap_hotplug_range(start, end, true);
+ free_empty_tables(start, end, VMEMMAP_START, VMEMMAP_END);
+#endif
}
#endif /* CONFIG_SPARSEMEM_VMEMMAP */
@@ -1049,10 +1362,21 @@ int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
}
#ifdef CONFIG_MEMORY_HOTPLUG
+static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size)
+{
+ unsigned long end = start + size;
+
+ WARN_ON(pgdir != init_mm.pgd);
+ WARN_ON((start < PAGE_OFFSET) || (end > PAGE_END));
+
+ unmap_hotplug_range(start, end, false);
+ free_empty_tables(start, end, PAGE_OFFSET, PAGE_END);
+}
+
int arch_add_memory(int nid, u64 start, u64 size,
struct mhp_restrictions *restrictions)
{
- int flags = 0;
+ int ret, flags = 0;
if (rodata_full || debug_pagealloc_enabled())
flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
@@ -1062,22 +1386,59 @@ int arch_add_memory(int nid, u64 start, u64 size,
memblock_clear_nomap(start, size);
- return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
+ ret = __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
restrictions);
+ if (ret)
+ __remove_pgd_mapping(swapper_pg_dir,
+ __phys_to_virt(start), size);
+ return ret;
}
+
void arch_remove_memory(int nid, u64 start, u64 size,
struct vmem_altmap *altmap)
{
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
- /*
- * FIXME: Cleanup page tables (also in arch_add_memory() in case
- * adding fails). Until then, this function should only be used
- * during memory hotplug (adding memory), not for memory
- * unplug. ARCH_ENABLE_MEMORY_HOTREMOVE must not be
- * unlocked yet.
- */
__remove_pages(start_pfn, nr_pages, altmap);
+ __remove_pgd_mapping(swapper_pg_dir, __phys_to_virt(start), size);
+}
+
+/*
+ * This memory hotplug notifier helps prevent boot memory from being
+ * inadvertently removed as it blocks pfn range offlining process in
+ * __offline_pages(). Hence this prevents both offlining as well as
+ * removal process for boot memory which is initially always online.
+ * In future if and when boot memory could be removed, this notifier
+ * should be dropped and free_hotplug_page_range() should handle any
+ * reserved pages allocated during boot.
+ */
+static int prevent_bootmem_remove_notifier(struct notifier_block *nb,
+ unsigned long action, void *data)
+{
+ struct mem_section *ms;
+ struct memory_notify *arg = data;
+ unsigned long end_pfn = arg->start_pfn + arg->nr_pages;
+ unsigned long pfn = arg->start_pfn;
+
+ if (action != MEM_GOING_OFFLINE)
+ return NOTIFY_OK;
+
+ for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+ ms = __pfn_to_section(pfn);
+ if (early_section(ms))
+ return NOTIFY_BAD;
+ }
+ return NOTIFY_OK;
+}
+
+static struct notifier_block prevent_bootmem_remove_nb = {
+ .notifier_call = prevent_bootmem_remove_notifier,
+};
+
+static int __init prevent_bootmem_remove_init(void)
+{
+ return register_memory_notifier(&prevent_bootmem_remove_nb);
}
+device_initcall(prevent_bootmem_remove_init);
#endif
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index aafed6902411..197a9ba2d5ea 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -11,11 +11,13 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
#include <asm/asm-offsets.h>
+#include <asm/asm_pointer_auth.h>
#include <asm/hwcap.h>
#include <asm/pgtable.h>
#include <asm/pgtable-hwdef.h>
#include <asm/cpufeature.h>
#include <asm/alternative.h>
+#include <asm/smp.h>
#ifdef CONFIG_ARM64_64K_PAGES
#define TCR_TG_FLAGS TCR_TG0_64K | TCR_TG1_64K
@@ -131,45 +133,19 @@ alternative_endif
ubfx x11, x11, #1, #1
msr oslar_el1, x11
reset_pmuserenr_el0 x0 // Disable PMU access from EL0
+ reset_amuserenr_el0 x0 // Disable AMU access from EL0
alternative_if ARM64_HAS_RAS_EXTN
msr_s SYS_DISR_EL1, xzr
alternative_else_nop_endif
+ ptrauth_keys_install_kernel x14, 0, x1, x2, x3
isb
ret
SYM_FUNC_END(cpu_do_resume)
.popsection
#endif
-/*
- * cpu_do_switch_mm(pgd_phys, tsk)
- *
- * Set the translation table base pointer to be pgd_phys.
- *
- * - pgd_phys - physical address of new TTB
- */
-SYM_FUNC_START(cpu_do_switch_mm)
- 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
- bfi x2, x1, #48, #16 // set the ASID
- msr ttbr1_el1, x2 // in TTBR1 (since TCR.A1 is set)
- isb
- msr ttbr0_el1, x3 // now update TTBR0
- isb
- b post_ttbr_update_workaround // Back to C code...
-SYM_FUNC_END(cpu_do_switch_mm)
-
.pushsection ".idmap.text", "awx"
.macro __idmap_cpu_set_reserved_ttbr1, tmp1, tmp2
@@ -408,35 +384,37 @@ SYM_FUNC_END(idmap_kpti_install_ng_mappings)
/*
* __cpu_setup
*
- * Initialise the processor for turning the MMU on. Return in x0 the
- * value of the SCTLR_EL1 register.
+ * Initialise the processor for turning the MMU on.
+ *
+ * Input:
+ * x0 with a flag ARM64_CPU_BOOT_PRIMARY/ARM64_CPU_BOOT_SECONDARY/ARM64_CPU_RUNTIME.
+ * Output:
+ * Return in x0 the value of the SCTLR_EL1 register.
*/
.pushsection ".idmap.text", "awx"
SYM_FUNC_START(__cpu_setup)
tlbi vmalle1 // Invalidate local TLB
dsb nsh
- mov x0, #3 << 20
- msr cpacr_el1, x0 // Enable FP/ASIMD
- mov x0, #1 << 12 // Reset mdscr_el1 and disable
- msr mdscr_el1, x0 // access to the DCC from EL0
+ mov x1, #3 << 20
+ msr cpacr_el1, x1 // Enable FP/ASIMD
+ mov x1, #1 << 12 // Reset mdscr_el1 and disable
+ msr mdscr_el1, x1 // access to the DCC from EL0
isb // Unmask debug exceptions now,
enable_dbg // since this is per-cpu
- reset_pmuserenr_el0 x0 // Disable PMU access from EL0
+ reset_pmuserenr_el0 x1 // Disable PMU access from EL0
+ reset_amuserenr_el0 x1 // Disable AMU access from EL0
+
/*
* Memory region attributes
*/
mov_q x5, MAIR_EL1_SET
msr mair_el1, x5
/*
- * Prepare SCTLR
- */
- mov_q x0, SCTLR_EL1_SET
- /*
* Set/prepare TCR and TTBR. We use 512GB (39-bit) address range for
* both user and kernel.
*/
- ldr x10, =TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \
+ mov_q x10, TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \
TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \
TCR_TBI0 | TCR_A1 | TCR_KASAN_FLAGS
tcr_clear_errata_bits x10, x9, x5
@@ -468,5 +446,51 @@ SYM_FUNC_START(__cpu_setup)
1:
#endif /* CONFIG_ARM64_HW_AFDBM */
msr tcr_el1, x10
+ mov x1, x0
+ /*
+ * Prepare SCTLR
+ */
+ mov_q x0, SCTLR_EL1_SET
+
+#ifdef CONFIG_ARM64_PTR_AUTH
+ /* No ptrauth setup for run time cpus */
+ cmp x1, #ARM64_CPU_RUNTIME
+ b.eq 3f
+
+ /* Check if the CPU supports ptrauth */
+ mrs x2, id_aa64isar1_el1
+ ubfx x2, x2, #ID_AA64ISAR1_APA_SHIFT, #8
+ cbz x2, 3f
+
+ /*
+ * The primary cpu keys are reset here and can be
+ * re-initialised with some proper values later.
+ */
+ msr_s SYS_APIAKEYLO_EL1, xzr
+ msr_s SYS_APIAKEYHI_EL1, xzr
+
+ /* Just enable ptrauth for primary cpu */
+ cmp x1, #ARM64_CPU_BOOT_PRIMARY
+ b.eq 2f
+
+ /* if !system_supports_address_auth() then skip enable */
+alternative_if_not ARM64_HAS_ADDRESS_AUTH
+ b 3f
+alternative_else_nop_endif
+
+ /* Install ptrauth key for secondary cpus */
+ adr_l x2, secondary_data
+ ldr x3, [x2, #CPU_BOOT_TASK] // get secondary_data.task
+ cbz x3, 2f // check for slow booting cpus
+ ldp x3, x4, [x2, #CPU_BOOT_PTRAUTH_KEY]
+ msr_s SYS_APIAKEYLO_EL1, x3
+ msr_s SYS_APIAKEYHI_EL1, x4
+
+2: /* Enable ptrauth instructions */
+ ldr x2, =SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | \
+ SCTLR_ELx_ENDA | SCTLR_ELx_ENDB
+ orr x0, x0, x2
+3:
+#endif
ret // return to head.S
SYM_FUNC_END(__cpu_setup)
diff --git a/arch/arm64/mm/ptdump_debugfs.c b/arch/arm64/mm/ptdump_debugfs.c
index 1f2eae3e988b..d29d722ec3ec 100644
--- a/arch/arm64/mm/ptdump_debugfs.c
+++ b/arch/arm64/mm/ptdump_debugfs.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/debugfs.h>
+#include <linux/memory_hotplug.h>
#include <linux/seq_file.h>
#include <asm/ptdump.h>
@@ -7,7 +8,10 @@
static int ptdump_show(struct seq_file *m, void *v)
{
struct ptdump_info *info = m->private;
+
+ get_online_mems();
ptdump_walk(m, info);
+ put_online_mems();
return 0;
}
DEFINE_SHOW_ATTRIBUTE(ptdump);