summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--Documentation/arm64/acpi_object_usage.rst2
-rw-r--r--Documentation/arm64/elf_hwcaps.rst9
-rw-r--r--Documentation/arm64/sve.rst1
-rw-r--r--Makefile2
-rw-r--r--arch/Kconfig7
-rw-r--r--arch/arm64/Kconfig13
-rw-r--r--arch/arm64/Makefile15
-rw-r--r--arch/arm64/include/asm/alternative-macros.h4
-rw-r--r--arch/arm64/include/asm/hwcap.h3
-rw-r--r--arch/arm64/include/asm/jump_label.h8
-rw-r--r--arch/arm64/include/asm/module.lds.h8
-rw-r--r--arch/arm64/include/asm/scs.h49
-rw-r--r--arch/arm64/include/asm/sysreg.h12
-rw-r--r--arch/arm64/include/uapi/asm/hwcap.h3
-rw-r--r--arch/arm64/kernel/Makefile2
-rw-r--r--arch/arm64/kernel/cpufeature.c22
-rw-r--r--arch/arm64/kernel/cpuinfo.c3
-rw-r--r--arch/arm64/kernel/entry.S3
-rw-r--r--arch/arm64/kernel/head.S3
-rw-r--r--arch/arm64/kernel/irq.c2
-rw-r--r--arch/arm64/kernel/module.c8
-rw-r--r--arch/arm64/kernel/patch-scs.c257
-rw-r--r--arch/arm64/kernel/pi/Makefile1
-rw-r--r--arch/arm64/kernel/sdei.c2
-rw-r--r--arch/arm64/kernel/setup.c4
-rw-r--r--arch/arm64/kernel/suspend.c2
-rw-r--r--arch/arm64/kernel/vmlinux.lds.S13
-rw-r--r--arch/arm64/kvm/hyp/nvhe/Makefile1
-rw-r--r--arch/arm64/tools/cpucaps1
-rw-r--r--arch/arm64/tools/sysreg12
-rw-r--r--drivers/acpi/Kconfig2
-rw-r--r--drivers/acpi/arm64/Kconfig3
-rw-r--r--drivers/acpi/arm64/Makefile1
-rw-r--r--drivers/acpi/arm64/apmt.c178
-rw-r--r--drivers/acpi/arm64/iort.c16
-rw-r--r--drivers/acpi/bus.c2
-rw-r--r--drivers/firmware/efi/libstub/Makefile1
-rw-r--r--drivers/perf/arm_pmu.c17
-rw-r--r--drivers/perf/arm_pmu_acpi.c114
-rw-r--r--include/asm-generic/vmlinux.lds.h9
-rw-r--r--include/linux/acpi_apmt.h19
-rw-r--r--include/linux/perf/arm_pmu.h1
-rw-r--r--include/linux/scs.h18
-rw-r--r--kernel/scs.c14
-rw-r--r--scripts/module.lds.S6
-rw-r--r--tools/testing/selftests/arm64/abi/hwcap.c32
46 files changed, 818 insertions, 87 deletions
diff --git a/Documentation/arm64/acpi_object_usage.rst b/Documentation/arm64/acpi_object_usage.rst
index 0609da73970b..484ef9676653 100644
--- a/Documentation/arm64/acpi_object_usage.rst
+++ b/Documentation/arm64/acpi_object_usage.rst
@@ -163,7 +163,7 @@ FPDT Section 5.2.23 (signature == "FPDT")
**Firmware Performance Data Table**
- Optional, not currently supported.
+ Optional, useful for boot performance profiling.
GTDT Section 5.2.24 (signature == "GTDT")
diff --git a/Documentation/arm64/elf_hwcaps.rst b/Documentation/arm64/elf_hwcaps.rst
index bb34287c8e01..6fed84f935df 100644
--- a/Documentation/arm64/elf_hwcaps.rst
+++ b/Documentation/arm64/elf_hwcaps.rst
@@ -275,6 +275,15 @@ HWCAP2_EBF16
HWCAP2_SVE_EBF16
Functionality implied by ID_AA64ZFR0_EL1.BF16 == 0b0010.
+HWCAP2_CSSC
+ Functionality implied by ID_AA64ISAR2_EL1.CSSC == 0b0001.
+
+HWCAP2_RPRFM
+ Functionality implied by ID_AA64ISAR2_EL1.RPRFM == 0b0001.
+
+HWCAP2_SVE2P1
+ Functionality implied by ID_AA64ZFR0_EL1.SVEver == 0b0010.
+
4. Unused AT_HWCAP bits
-----------------------
diff --git a/Documentation/arm64/sve.rst b/Documentation/arm64/sve.rst
index f338ee2df46d..c7a356bf4e8f 100644
--- a/Documentation/arm64/sve.rst
+++ b/Documentation/arm64/sve.rst
@@ -52,6 +52,7 @@ model features for SVE is included in Appendix A.
HWCAP2_SVEBITPERM
HWCAP2_SVESHA3
HWCAP2_SVESM4
+ HWCAP2_SVE2P1
This list may be extended over time as the SVE architecture evolves.
diff --git a/Makefile b/Makefile
index ac2ec990422d..69b40b629f3c 100644
--- a/Makefile
+++ b/Makefile
@@ -966,8 +966,10 @@ LDFLAGS_vmlinux += --gc-sections
endif
ifdef CONFIG_SHADOW_CALL_STACK
+ifndef CONFIG_DYNAMIC_SCS
CC_FLAGS_SCS := -fsanitize=shadow-call-stack
KBUILD_CFLAGS += $(CC_FLAGS_SCS)
+endif
export CC_FLAGS_SCS
endif
diff --git a/arch/Kconfig b/arch/Kconfig
index 8f138e580d1a..072a1b39e3af 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -651,6 +651,13 @@ config SHADOW_CALL_STACK
reading and writing arbitrary memory may be able to locate them
and hijack control flow by modifying the stacks.
+config DYNAMIC_SCS
+ bool
+ help
+ Set by the arch code if it relies on code patching to insert the
+ shadow call stack push and pop instructions rather than on the
+ compiler.
+
config LTO
bool
help
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 56c3381e9d94..0cb1443cc26f 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1,6 +1,7 @@
# SPDX-License-Identifier: GPL-2.0-only
config ARM64
def_bool y
+ select ACPI_APMT if ACPI
select ACPI_CCA_REQUIRED if ACPI
select ACPI_GENERIC_GSI if ACPI
select ACPI_GTDT if ACPI
@@ -370,6 +371,9 @@ config KASAN_SHADOW_OFFSET
default 0xeffffff800000000 if ARM64_VA_BITS_36 && KASAN_SW_TAGS
default 0xffffffffffffffff
+config UNWIND_TABLES
+ bool
+
source "arch/arm64/Kconfig.platforms"
menu "Kernel Features"
@@ -2173,6 +2177,15 @@ config ARCH_NR_GPIO
If unsure, leave the default value.
+config UNWIND_PATCH_PAC_INTO_SCS
+ bool "Enable shadow call stack dynamically using code patching"
+ # needs Clang with https://reviews.llvm.org/D111780 incorporated
+ depends on CC_IS_CLANG && CLANG_VERSION >= 150000
+ depends on ARM64_PTR_AUTH_KERNEL && CC_HAS_BRANCH_PROT_PAC_RET
+ depends on SHADOW_CALL_STACK
+ select UNWIND_TABLES
+ select DYNAMIC_SCS
+
endmenu # "Kernel Features"
menu "Boot options"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 5e56d26a2239..4d272ad1df1f 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -45,8 +45,13 @@ KBUILD_CFLAGS += $(call cc-option,-mabi=lp64)
KBUILD_AFLAGS += $(call cc-option,-mabi=lp64)
# Avoid generating .eh_frame* sections.
+ifneq ($(CONFIG_UNWIND_TABLES),y)
KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables
KBUILD_AFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables
+else
+KBUILD_CFLAGS += -fasynchronous-unwind-tables
+KBUILD_AFLAGS += -fasynchronous-unwind-tables
+endif
ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y)
prepare: stack_protector_prepare
@@ -72,10 +77,16 @@ branch-prot-flags-$(CONFIG_CC_HAS_SIGN_RETURN_ADDRESS) := -msign-return-address=
# We enable additional protection for leaf functions as there is some
# narrow potential for ROP protection benefits and no substantial
# performance impact has been observed.
+PACRET-y := pac-ret+leaf
+
+# Using a shadow call stack in leaf functions is too costly, so avoid PAC there
+# as well when we may be patching PAC into SCS
+PACRET-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS) := pac-ret
+
ifeq ($(CONFIG_ARM64_BTI_KERNEL),y)
-branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET_BTI) := -mbranch-protection=pac-ret+leaf+bti
+branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET_BTI) := -mbranch-protection=$(PACRET-y)+bti
else
-branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET) := -mbranch-protection=pac-ret+leaf
+branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET) := -mbranch-protection=$(PACRET-y)
endif
# -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
diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h
index 3622e9f4fb44..bdf1f6bcd010 100644
--- a/arch/arm64/include/asm/alternative-macros.h
+++ b/arch/arm64/include/asm/alternative-macros.h
@@ -224,7 +224,7 @@ alternative_endif
#include <linux/types.h>
static __always_inline bool
-alternative_has_feature_likely(unsigned long feature)
+alternative_has_feature_likely(const unsigned long feature)
{
compiletime_assert(feature < ARM64_NCAPS,
"feature must be < ARM64_NCAPS");
@@ -242,7 +242,7 @@ l_no:
}
static __always_inline bool
-alternative_has_feature_unlikely(unsigned long feature)
+alternative_has_feature_unlikely(const unsigned long feature)
{
compiletime_assert(feature < ARM64_NCAPS,
"feature must be < ARM64_NCAPS");
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 298b386d3ebe..06dd12c514e6 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -120,6 +120,9 @@
#define KERNEL_HWCAP_WFXT __khwcap2_feature(WFXT)
#define KERNEL_HWCAP_EBF16 __khwcap2_feature(EBF16)
#define KERNEL_HWCAP_SVE_EBF16 __khwcap2_feature(SVE_EBF16)
+#define KERNEL_HWCAP_CSSC __khwcap2_feature(CSSC)
+#define KERNEL_HWCAP_RPRFM __khwcap2_feature(RPRFM)
+#define KERNEL_HWCAP_SVE2P1 __khwcap2_feature(SVE2P1)
/*
* This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
index cea441b6aa5d..48ddc0f45d22 100644
--- a/arch/arm64/include/asm/jump_label.h
+++ b/arch/arm64/include/asm/jump_label.h
@@ -15,8 +15,8 @@
#define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE
-static __always_inline bool arch_static_branch(struct static_key *key,
- bool branch)
+static __always_inline bool arch_static_branch(struct static_key * const key,
+ const bool branch)
{
asm_volatile_goto(
"1: nop \n\t"
@@ -32,8 +32,8 @@ l_yes:
return true;
}
-static __always_inline bool arch_static_branch_jump(struct static_key *key,
- bool branch)
+static __always_inline bool arch_static_branch_jump(struct static_key * const key,
+ const bool branch)
{
asm_volatile_goto(
"1: b %l[l_yes] \n\t"
diff --git a/arch/arm64/include/asm/module.lds.h b/arch/arm64/include/asm/module.lds.h
index 094701ec5500..dbba4b7559aa 100644
--- a/arch/arm64/include/asm/module.lds.h
+++ b/arch/arm64/include/asm/module.lds.h
@@ -17,4 +17,12 @@ SECTIONS {
*/
.text.hot : { *(.text.hot) }
#endif
+
+#ifdef CONFIG_UNWIND_TABLES
+ /*
+ * Currently, we only use unwind info at module load time, so we can
+ * put it into the .init allocation.
+ */
+ .init.eh_frame : { *(.eh_frame) }
+#endif
}
diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h
index 8297bccf0784..ff7da1268a52 100644
--- a/arch/arm64/include/asm/scs.h
+++ b/arch/arm64/include/asm/scs.h
@@ -5,6 +5,7 @@
#ifdef __ASSEMBLY__
#include <asm/asm-offsets.h>
+#include <asm/sysreg.h>
#ifdef CONFIG_SHADOW_CALL_STACK
scs_sp .req x18
@@ -24,6 +25,54 @@
.endm
#endif /* CONFIG_SHADOW_CALL_STACK */
+
+#else
+
+#include <linux/scs.h>
+#include <asm/cpufeature.h>
+
+#ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS
+static inline bool should_patch_pac_into_scs(void)
+{
+ u64 reg;
+
+ /*
+ * We only enable the shadow call stack dynamically if we are running
+ * on a system that does not implement PAC or BTI. PAC and SCS provide
+ * roughly the same level of protection, and BTI relies on the PACIASP
+ * instructions serving as landing pads, preventing us from patching
+ * those instructions into something else.
+ */
+ reg = read_sysreg_s(SYS_ID_AA64ISAR1_EL1);
+ if (SYS_FIELD_GET(ID_AA64ISAR1_EL1, APA, reg) |
+ SYS_FIELD_GET(ID_AA64ISAR1_EL1, API, reg))
+ return false;
+
+ reg = read_sysreg_s(SYS_ID_AA64ISAR2_EL1);
+ if (SYS_FIELD_GET(ID_AA64ISAR2_EL1, APA3, reg))
+ return false;
+
+ if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) {
+ reg = read_sysreg_s(SYS_ID_AA64PFR1_EL1);
+ if (reg & (0xf << ID_AA64PFR1_EL1_BT_SHIFT))
+ return false;
+ }
+ return true;
+}
+
+static inline void dynamic_scs_init(void)
+{
+ if (should_patch_pac_into_scs()) {
+ pr_info("Enabling dynamic shadow call stack\n");
+ static_branch_enable(&dynamic_scs_enabled);
+ }
+}
+#else
+static inline void dynamic_scs_init(void) {}
+#endif
+
+int scs_patch(const u8 eh_frame[], int size);
+
#endif /* __ASSEMBLY __ */
#endif /* _ASM_SCS_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 7d301700d1a9..1f3f52ce407f 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -90,20 +90,24 @@
*/
#define pstate_field(op1, op2) ((op1) << Op1_shift | (op2) << Op2_shift)
#define PSTATE_Imm_shift CRm_shift
+#define SET_PSTATE(x, r) __emit_inst(0xd500401f | PSTATE_ ## r | ((!!x) << PSTATE_Imm_shift))
#define PSTATE_PAN pstate_field(0, 4)
#define PSTATE_UAO pstate_field(0, 3)
#define PSTATE_SSBS pstate_field(3, 1)
+#define PSTATE_DIT pstate_field(3, 2)
#define PSTATE_TCO pstate_field(3, 4)
-#define SET_PSTATE_PAN(x) __emit_inst(0xd500401f | PSTATE_PAN | ((!!x) << PSTATE_Imm_shift))
-#define SET_PSTATE_UAO(x) __emit_inst(0xd500401f | PSTATE_UAO | ((!!x) << PSTATE_Imm_shift))
-#define SET_PSTATE_SSBS(x) __emit_inst(0xd500401f | PSTATE_SSBS | ((!!x) << PSTATE_Imm_shift))
-#define SET_PSTATE_TCO(x) __emit_inst(0xd500401f | PSTATE_TCO | ((!!x) << PSTATE_Imm_shift))
+#define SET_PSTATE_PAN(x) SET_PSTATE((x), PAN)
+#define SET_PSTATE_UAO(x) SET_PSTATE((x), UAO)
+#define SET_PSTATE_SSBS(x) SET_PSTATE((x), SSBS)
+#define SET_PSTATE_DIT(x) SET_PSTATE((x), DIT)
+#define SET_PSTATE_TCO(x) SET_PSTATE((x), TCO)
#define set_pstate_pan(x) asm volatile(SET_PSTATE_PAN(x))
#define set_pstate_uao(x) asm volatile(SET_PSTATE_UAO(x))
#define set_pstate_ssbs(x) asm volatile(SET_PSTATE_SSBS(x))
+#define set_pstate_dit(x) asm volatile(SET_PSTATE_DIT(x))
#define __SYS_BARRIER_INSN(CRm, op2, Rt) \
__emit_inst(0xd5000000 | sys_insn(0, 3, 3, (CRm), (op2)) | ((Rt) & 0x1f))
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 9b245da6f507..b713d30544f1 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -93,5 +93,8 @@
#define HWCAP2_WFXT (1UL << 31)
#define HWCAP2_EBF16 (1UL << 32)
#define HWCAP2_SVE_EBF16 (1UL << 33)
+#define HWCAP2_CSSC (1UL << 34)
+#define HWCAP2_RPRFM (1UL << 35)
+#define HWCAP2_SVE2P1 (1UL << 36)
#endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 2f361a883d8c..8dd925f4a4c6 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -80,6 +80,8 @@ obj-$(CONFIG_ARM64_PTR_AUTH) += pointer_auth.o
obj-$(CONFIG_ARM64_MTE) += mte.o
obj-y += vdso-wrap.o
obj-$(CONFIG_COMPAT_VDSO) += vdso32-wrap.o
+obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS) += patch-scs.o
+CFLAGS_patch-scs.o += -mbranch-protection=none
# Force dependency (vdso*-wrap.S includes vdso.so through incbin)
$(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index b3f37e2209ad..3e3af6b8cc85 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -212,6 +212,8 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
};
static const struct arm64_ftr_bits ftr_id_aa64isar2[] = {
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH),
FTR_STRICT, FTR_EXACT, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, 0),
@@ -2101,6 +2103,11 @@ static void cpu_trap_el0_impdef(const struct arm64_cpu_capabilities *__unused)
sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_TIDCP);
}
+static void cpu_enable_dit(const struct arm64_cpu_capabilities *__unused)
+{
+ set_pstate_dit(1);
+}
+
/* Internal helper functions to match cpu capability type */
static bool
cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap)
@@ -2664,6 +2671,18 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.matches = has_cpuid_feature,
.cpu_enable = cpu_trap_el0_impdef,
},
+ {
+ .desc = "Data independent timing control (DIT)",
+ .capability = ARM64_HAS_DIT,
+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .sys_reg = SYS_ID_AA64PFR0_EL1,
+ .sign = FTR_UNSIGNED,
+ .field_pos = ID_AA64PFR0_EL1_DIT_SHIFT,
+ .field_width = 4,
+ .min_field_value = ID_AA64PFR0_EL1_DIT_IMP,
+ .matches = has_cpuid_feature,
+ .cpu_enable = cpu_enable_dit,
+ },
{},
};
@@ -2772,6 +2791,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_EL1_AT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT),
#ifdef CONFIG_ARM64_SVE
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_SVE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR0_EL1_SVE_IMP, CAP_HWCAP, KERNEL_HWCAP_SVE),
+ HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_SVEver_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_SVEver_SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_SVEver_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_SVEver_SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_AES_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_AES_PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL),
@@ -2798,6 +2818,8 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
#endif /* CONFIG_ARM64_MTE */
HWCAP_CAP(SYS_ID_AA64MMFR0_EL1, ID_AA64MMFR0_EL1_ECV_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ECV),
HWCAP_CAP(SYS_ID_AA64MMFR1_EL1, ID_AA64MMFR1_EL1_AFP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AFP),
+ HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_CSSC_IMP, CAP_HWCAP, KERNEL_HWCAP_CSSC),
+ HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_RPRFM_IMP, CAP_HWCAP, KERNEL_HWCAP_RPRFM),
HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_RPRES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RPRES),
HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_WFxT_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_WFxT_IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT),
#ifdef CONFIG_ARM64_SME
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 28d4f442b0bc..379695262b77 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -116,6 +116,9 @@ static const char *const hwcap_str[] = {
[KERNEL_HWCAP_WFXT] = "wfxt",
[KERNEL_HWCAP_EBF16] = "ebf16",
[KERNEL_HWCAP_SVE_EBF16] = "sveebf16",
+ [KERNEL_HWCAP_CSSC] = "cssc",
+ [KERNEL_HWCAP_RPRFM] = "rprfm",
+ [KERNEL_HWCAP_SVE2P1] = "sve2p1",
};
#ifdef CONFIG_COMPAT
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index e28137d64b76..11cb99c4d298 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -197,6 +197,9 @@ alternative_cb_end
.endm
.macro kernel_entry, el, regsize = 64
+ .if \el == 0
+ alternative_insn nop, SET_PSTATE_DIT(1), ARM64_HAS_DIT
+ .endif
.if \regsize == 32
mov w0, w0 // zero upper 32 bits of x0
.endif
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 2196aad7b55b..952e17bd1c0b 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -462,6 +462,9 @@ SYM_FUNC_START_LOCAL(__primary_switched)
bl early_fdt_map // Try mapping the FDT early
mov x0, x20 // pass the full boot status
bl init_feature_override // Parse cpu feature overrides
+#ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS
+ bl scs_patch_vmlinux
+#endif
mov x0, x20
bl finalise_el2 // Prefer VHE if possible
ldp x29, x30, [sp], #16
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 38dbd3828f13..9d8eaab742a4 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -41,7 +41,7 @@ static void init_irq_scs(void)
{
int cpu;
- if (!IS_ENABLED(CONFIG_SHADOW_CALL_STACK))
+ if (!scs_is_enabled())
return;
for_each_possible_cpu(cpu)
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 76b41e4ca9fa..fa7b3228944b 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -15,9 +15,11 @@
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/moduleloader.h>
+#include <linux/scs.h>
#include <linux/vmalloc.h>
#include <asm/alternative.h>
#include <asm/insn.h>
+#include <asm/scs.h>
#include <asm/sections.h>
void *module_alloc(unsigned long size)
@@ -514,5 +516,11 @@ int module_finalize(const Elf_Ehdr *hdr,
if (s)
apply_alternatives_module((void *)s->sh_addr, s->sh_size);
+ if (scs_is_dynamic()) {
+ s = find_section(hdr, sechdrs, ".init.eh_frame");
+ if (s)
+ scs_patch((void *)s->sh_addr, s->sh_size);
+ }
+
return module_init_ftrace_plt(hdr, sechdrs, me);
}
diff --git a/arch/arm64/kernel/patch-scs.c b/arch/arm64/kernel/patch-scs.c
new file mode 100644
index 000000000000..1b3da02d5b74
--- /dev/null
+++ b/arch/arm64/kernel/patch-scs.c
@@ -0,0 +1,257 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2022 - Google LLC
+ * Author: Ard Biesheuvel <ardb@google.com>
+ */
+
+#include <linux/bug.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <linux/printk.h>
+#include <linux/types.h>
+
+#include <asm/cacheflush.h>
+#include <asm/scs.h>
+
+//
+// This minimal DWARF CFI parser is partially based on the code in
+// arch/arc/kernel/unwind.c, and on the document below:
+// https://refspecs.linuxbase.org/LSB_4.0.0/LSB-Core-generic/LSB-Core-generic/ehframechpt.html
+//
+
+#define DW_CFA_nop 0x00
+#define DW_CFA_set_loc 0x01
+#define DW_CFA_advance_loc1 0x02
+#define DW_CFA_advance_loc2 0x03
+#define DW_CFA_advance_loc4 0x04
+#define DW_CFA_offset_extended 0x05
+#define DW_CFA_restore_extended 0x06
+#define DW_CFA_undefined 0x07
+#define DW_CFA_same_value 0x08
+#define DW_CFA_register 0x09
+#define DW_CFA_remember_state 0x0a
+#define DW_CFA_restore_state 0x0b
+#define DW_CFA_def_cfa 0x0c
+#define DW_CFA_def_cfa_register 0x0d
+#define DW_CFA_def_cfa_offset 0x0e
+#define DW_CFA_def_cfa_expression 0x0f
+#define DW_CFA_expression 0x10
+#define DW_CFA_offset_extended_sf 0x11
+#define DW_CFA_def_cfa_sf 0x12
+#define DW_CFA_def_cfa_offset_sf 0x13
+#define DW_CFA_val_offset 0x14
+#define DW_CFA_val_offset_sf 0x15
+#define DW_CFA_val_expression 0x16
+#define DW_CFA_lo_user 0x1c
+#define DW_CFA_negate_ra_state 0x2d
+#define DW_CFA_GNU_args_size 0x2e
+#define DW_CFA_GNU_negative_offset_extended 0x2f
+#define DW_CFA_hi_user 0x3f
+
+extern const u8 __eh_frame_start[], __eh_frame_end[];
+
+enum {
+ PACIASP = 0xd503233f,
+ AUTIASP = 0xd50323bf,
+ SCS_PUSH = 0xf800865e,
+ SCS_POP = 0xf85f8e5e,
+};
+
+static void __always_inline scs_patch_loc(u64 loc)
+{
+ u32 insn = le32_to_cpup((void *)loc);
+
+ switch (insn) {
+ case PACIASP:
+ *(u32 *)loc = cpu_to_le32(SCS_PUSH);
+ break;
+ case AUTIASP:
+ *(u32 *)loc = cpu_to_le32(SCS_POP);
+ break;
+ default:
+ /*
+ * While the DW_CFA_negate_ra_state directive is guaranteed to
+ * appear right after a PACIASP/AUTIASP instruction, it may
+ * also appear after a DW_CFA_restore_state directive that
+ * restores a state that is only partially accurate, and is
+ * followed by DW_CFA_negate_ra_state directive to toggle the
+ * PAC bit again. So we permit other instructions here, and ignore
+ * them.
+ */
+ return;
+ }
+ dcache_clean_pou(loc, loc + sizeof(u32));
+}
+
+/*
+ * Skip one uleb128/sleb128 encoded quantity from the opcode stream. All bytes
+ * except the last one have bit #7 set.
+ */
+static int __always_inline skip_xleb128(const u8 **opcode, int size)
+{
+ u8 c;
+
+ do {
+ c = *(*opcode)++;
+ size--;
+ } while (c & BIT(7));
+
+ return size;
+}
+
+struct eh_frame {
+ /*
+ * The size of this frame if 0 < size < U32_MAX, 0 terminates the list.
+ */
+ u32 size;
+
+ /*
+ * The first frame is a Common Information Entry (CIE) frame, followed
+ * by one or more Frame Description Entry (FDE) frames. In the former
+ * case, this field is 0, otherwise it is the negated offset relative
+ * to the associated CIE frame.
+ */
+ u32 cie_id_or_pointer;
+
+ union {
+ struct { // CIE
+ u8 version;
+ u8 augmentation_string[];
+ };
+
+ struct { // FDE
+ s32 initial_loc;
+ s32 range;
+ u8 opcodes[];
+ };
+ };
+};
+
+static int noinstr scs_handle_fde_frame(const struct eh_frame *frame,
+ bool fde_has_augmentation_data,
+ int code_alignment_factor)
+{
+ int size = frame->size - offsetof(struct eh_frame, opcodes) + 4;
+ u64 loc = (u64)offset_to_ptr(&frame->initial_loc);
+ const u8 *opcode = frame->opcodes;
+
+ if (fde_has_augmentation_data) {
+ int l;
+
+ // assume single byte uleb128_t
+ if (WARN_ON(*opcode & BIT(7)))
+ return -ENOEXEC;
+
+ l = *opcode++;
+ opcode += l;
+ size -= l + 1;
+ }
+
+ /*
+ * Starting from 'loc', apply the CFA opcodes that advance the location
+ * pointer, and identify the locations of the PAC instructions.
+ */
+ while (size-- > 0) {
+ switch (*opcode++) {
+ case DW_CFA_nop:
+ case DW_CFA_remember_state:
+ case DW_CFA_restore_state:
+ break;
+
+ case DW_CFA_advance_loc1:
+ loc += *opcode++ * code_alignment_factor;
+ size--;
+ break;
+
+ case DW_CFA_advance_loc2:
+ loc += *opcode++ * code_alignment_factor;
+ loc += (*opcode++ << 8) * code_alignment_factor;
+ size -= 2;
+ break;
+
+ case DW_CFA_def_cfa:
+ case DW_CFA_offset_extended:
+ size = skip_xleb128(&opcode, size);
+ fallthrough;
+ case DW_CFA_def_cfa_offset:
+ case DW_CFA_def_cfa_offset_sf:
+ case DW_CFA_def_cfa_register:
+ case DW_CFA_same_value:
+ case DW_CFA_restore_extended:
+ case 0x80 ... 0xbf:
+ size = skip_xleb128(&opcode, size);
+ break;
+
+ case DW_CFA_negate_ra_state:
+ scs_patch_loc(loc - 4);
+ break;
+
+ case 0x40 ... 0x7f:
+ // advance loc
+ loc += (opcode[-1] & 0x3f) * code_alignment_factor;
+ break;
+
+ case 0xc0 ... 0xff:
+ break;
+
+ default:
+ pr_err("unhandled opcode: %02x in FDE frame %lx\n", opcode[-1], (uintptr_t)frame);
+ return -ENOEXEC;
+ }
+ }
+ return 0;
+}
+
+int noinstr scs_patch(const u8 eh_frame[], int size)
+{
+ const u8 *p = eh_frame;
+
+ while (size > 4) {
+ const struct eh_frame *frame = (const void *)p;
+ bool fde_has_augmentation_data = true;
+ int code_alignment_factor = 1;
+ int ret;
+
+ if (frame->size == 0 ||
+ frame->size == U32_MAX ||
+ frame->size > size)
+ break;
+
+ if (frame->cie_id_or_pointer == 0) {
+ const u8 *p = frame->augmentation_string;
+
+ /* a 'z' in the augmentation string must come first */
+ fde_has_augmentation_data = *p == 'z';
+
+ /*
+ * The code alignment factor is a uleb128 encoded field
+ * but given that the only sensible values are 1 or 4,
+ * there is no point in decoding the whole thing.
+ */
+ p += strlen(p) + 1;
+ if (!WARN_ON(*p & BIT(7)))
+ code_alignment_factor = *p;
+ } else {
+ ret = scs_handle_fde_frame(frame,
+ fde_has_augmentation_data,
+ code_alignment_factor);
+ if (ret)
+ return ret;
+ }
+
+ p += sizeof(frame->size) + frame->size;
+ size -= sizeof(frame->size) + frame->size;
+ }
+ return 0;
+}
+
+asmlinkage void __init scs_patch_vmlinux(void)
+{
+ if (!should_patch_pac_into_scs())
+ return;
+
+ WARN_ON(scs_patch(__eh_frame_start, __eh_frame_end - __eh_frame_start));
+ icache_inval_all_pou();
+ isb();
+}
diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile
index 839291430cb3..4c0ea3cd4ea4 100644
--- a/arch/arm64/kernel/pi/Makefile
+++ b/arch/arm64/kernel/pi/Makefile
@@ -7,6 +7,7 @@ KBUILD_CFLAGS := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) -fpie \
-I$(srctree)/scripts/dtc/libfdt -fno-stack-protector \
-include $(srctree)/include/linux/hidden.h \
-D__DISABLE_EXPORTS -ffreestanding -D__NO_FORTIFY \
+ -fno-asynchronous-unwind-tables -fno-unwind-tables \
$(call cc-option,-fno-addrsig)
# remove SCS flags from all objects in this directory
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index d56e170e1ca7..830be01af32d 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -144,7 +144,7 @@ static int init_sdei_scs(void)
int cpu;
int err = 0;
- if (!IS_ENABLED(CONFIG_SHADOW_CALL_STACK))
+ if (!scs_is_enabled())
return 0;
for_each_possible_cpu(cpu) {
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index fea3223704b6..12cfe9d0d3fa 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -30,6 +30,7 @@
#include <linux/efi.h>
#include <linux/psci.h>
#include <linux/sched/task.h>
+#include <linux/scs.h>
#include <linux/mm.h>
#include <asm/acpi.h>
@@ -42,6 +43,7 @@
#include <asm/cpu_ops.h>
#include <asm/kasan.h>
#include <asm/numa.h>
+#include <asm/scs.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/smp_plat.h>
@@ -312,6 +314,8 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)
jump_label_init();
parse_early_param();
+ dynamic_scs_init();
+
/*
* Unmask asynchronous aborts and fiq after bringing up possible
* earlycon. (Report possible System Errors once we can report this
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index 8b02d310838f..e7163f31f716 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -60,6 +60,8 @@ void notrace __cpu_suspend_exit(void)
* PSTATE was not saved over suspend/resume, re-enable any detected
* features that might not have been set correctly.
*/
+ if (cpus_have_const_cap(ARM64_HAS_DIT))
+ set_pstate_dit(1);
__uaccess_enable_hw_pan();
/*
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 45131e354e27..4c13dafc98b8 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -121,6 +121,17 @@ jiffies = jiffies_64;
#define TRAMP_TEXT
#endif
+#ifdef CONFIG_UNWIND_TABLES
+#define UNWIND_DATA_SECTIONS \
+ .eh_frame : { \
+ __eh_frame_start = .; \
+ *(.eh_frame) \
+ __eh_frame_end = .; \
+ }
+#else
+#define UNWIND_DATA_SECTIONS
+#endif
+
/*
* The size of the PE/COFF section that covers the kernel image, which
* runs from _stext to _edata, must be a round multiple of the PE/COFF
@@ -231,6 +242,8 @@ SECTIONS
__alt_instructions_end = .;
}
+ UNWIND_DATA_SECTIONS
+
. = ALIGN(SEGMENT_ALIGN);
__inittext_end = .;
__initdata_begin = .;
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index be0a2bc3e20d..530347cdebe3 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -96,6 +96,7 @@ KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_CFI)
# when profile optimization is applied. gen-hyprel does not support SHT_REL and
# causes a build failure. Remove profile optimization flags.
KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%, $(KBUILD_CFLAGS))
+KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables
# KVM nVHE code is run at a different exception code with a different map, so
# compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index 2274d836fcfe..dfeb2c51e257 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -20,6 +20,7 @@ HAS_CNP
HAS_CRC32
HAS_DCPODP
HAS_DCPOP
+HAS_DIT
HAS_E0PD
HAS_ECV
HAS_EPAN
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index 384757a7eda9..b2782b8faa01 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -210,6 +210,7 @@ EndEnum
Enum 3:0 SVEver
0b0000 IMP
0b0001 SVE2
+ 0b0010 SVE2p1
EndEnum
EndSysreg
@@ -484,7 +485,16 @@ EndEnum
EndSysreg
Sysreg ID_AA64ISAR2_EL1 3 0 0 6 2
-Res0 63:28
+Res0 63:56
+Enum 55:52 CSSC
+ 0b0000 NI
+ 0b0001 IMP
+EndEnum
+Enum 51:48 RPRFM
+ 0b0000 NI
+ 0b0001 IMP
+EndEnum
+Res0 47:28
Enum 27:24 PAC_frac
0b0000 NI
0b0001 IMP
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 473241b5193f..1cc11d2a2a88 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -90,7 +90,7 @@ config ACPI_SPCR_TABLE
config ACPI_FPDT
bool "ACPI Firmware Performance Data Table (FPDT) support"
- depends on X86_64
+ depends on X86_64 || ARM64
help
Enable support for the Firmware Performance Data Table (FPDT).
This table provides information on the timing of the system
diff --git a/drivers/acpi/arm64/Kconfig b/drivers/acpi/arm64/Kconfig
index d4a72835f328..b3ed6212244c 100644
--- a/drivers/acpi/arm64/Kconfig
+++ b/drivers/acpi/arm64/Kconfig
@@ -18,3 +18,6 @@ config ACPI_AGDI
reset command.
If set, the kernel parses AGDI table and listens for the command.
+
+config ACPI_APMT
+ bool
diff --git a/drivers/acpi/arm64/Makefile b/drivers/acpi/arm64/Makefile
index 7b9e4045659d..e21a9e84e394 100644
--- a/drivers/acpi/arm64/Makefile
+++ b/drivers/acpi/arm64/Makefile
@@ -2,4 +2,5 @@
obj-$(CONFIG_ACPI_AGDI) += agdi.o
obj-$(CONFIG_ACPI_IORT) += iort.o
obj-$(CONFIG_ACPI_GTDT) += gtdt.o
+obj-$(CONFIG_ACPI_APMT) += apmt.o
obj-y += dma.o
diff --git a/drivers/acpi/arm64/apmt.c b/drivers/acpi/arm64/apmt.c
new file mode 100644
index 000000000000..8cab69fa5d59
--- /dev/null
+++ b/drivers/acpi/arm64/apmt.c
@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM APMT table support.
+ * Design document number: ARM DEN0117.
+ *
+ * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES.
+ *
+ */
+
+#define pr_fmt(fmt) "ACPI: APMT: " fmt
+
+#include <linux/acpi.h>
+#include <linux/acpi_apmt.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+
+#define DEV_NAME "arm-cs-arch-pmu"
+
+/* There can be up to 3 resources: page 0 and 1 address, and interrupt. */
+#define DEV_MAX_RESOURCE_COUNT 3
+
+/* Root pointer to the mapped APMT table */
+static struct acpi_table_header *apmt_table;
+
+static int __init apmt_init_resources(struct resource *res,
+ struct acpi_apmt_node *node)
+{
+ int irq, trigger;
+ int num_res = 0;
+
+ res[num_res].start = node->base_address0;
+ res[num_res].end = node->base_address0 + SZ_4K - 1;
+ res[num_res].flags = IORESOURCE_MEM;
+
+ num_res++;
+
+ res[num_res].start = node->base_address1;
+ res[num_res].end = node->base_address1 + SZ_4K - 1;
+ res[num_res].flags = IORESOURCE_MEM;
+
+ num_res++;
+
+ if (node->ovflw_irq != 0) {
+ trigger = (node->ovflw_irq_flags & ACPI_APMT_OVFLW_IRQ_FLAGS_MODE);
+ trigger = (trigger == ACPI_APMT_OVFLW_IRQ_FLAGS_MODE_LEVEL) ?
+ ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
+ irq = acpi_register_gsi(NULL, node->ovflw_irq, trigger,
+ ACPI_ACTIVE_HIGH);
+
+ if (irq <= 0) {
+ pr_warn("APMT could not register gsi hwirq %d\n", irq);
+ return num_res;
+ }
+
+ res[num_res].start = irq;
+ res[num_res].end = irq;
+ res[num_res].flags = IORESOURCE_IRQ;
+
+ num_res++;
+ }
+
+ return num_res;
+}
+
+/**
+ * apmt_add_platform_device() - Allocate a platform device for APMT node
+ * @node: Pointer to device ACPI APMT node
+ * @fwnode: fwnode associated with the APMT node
+ *
+ * Returns: 0 on success, <0 failure
+ */
+static int __init apmt_add_platform_device(struct acpi_apmt_node *node,
+ struct fwnode_handle *fwnode)
+{
+ struct platform_device *pdev;
+ int ret, count;
+ struct resource res[DEV_MAX_RESOURCE_COUNT];
+
+ pdev = platform_device_alloc(DEV_NAME, PLATFORM_DEVID_AUTO);
+ if (!pdev)
+ return -ENOMEM;
+
+ memset(res, 0, sizeof(res));
+
+ count = apmt_init_resources(res, node);
+
+ ret = platform_device_add_resources(pdev, res, count);
+ if (ret)
+ goto dev_put;
+
+ /*
+ * Add a copy of APMT node pointer to platform_data to be used to
+ * retrieve APMT data information.
+ */
+ ret = platform_device_add_data(pdev, &node, sizeof(node));
+ if (ret)
+ goto dev_put;
+
+ pdev->dev.fwnode = fwnode;
+
+ ret = platform_device_add(pdev);
+
+ if (ret)
+ goto dev_put;
+
+ return 0;
+
+dev_put:
+ platform_device_put(pdev);
+
+ return ret;
+}
+
+static int __init apmt_init_platform_devices(void)
+{
+ struct acpi_apmt_node *apmt_node;
+ struct acpi_table_apmt *apmt;
+ struct fwnode_handle *fwnode;
+ u64 offset, end;
+ int ret;
+
+ /*
+ * apmt_table and apmt both point to the start of APMT table, but
+ * have different struct types
+ */
+ apmt = (struct acpi_table_apmt *)apmt_table;
+ offset = sizeof(*apmt);
+ end = apmt->header.length;
+
+ while (offset < end) {
+ apmt_node = ACPI_ADD_PTR(struct acpi_apmt_node, apmt,
+ offset);
+
+ fwnode = acpi_alloc_fwnode_static();
+ if (!fwnode)
+ return -ENOMEM;
+
+ ret = apmt_add_platform_device(apmt_node, fwnode);
+ if (ret) {
+ acpi_free_fwnode_static(fwnode);
+ return ret;
+ }
+
+ offset += apmt_node->length;
+ }
+
+ return 0;
+}
+
+void __init acpi_apmt_init(void)
+{
+ acpi_status status;
+ int ret;
+
+ /**
+ * APMT table nodes will be used at runtime after the apmt init,
+ * so we don't need to call acpi_put_table() to release
+ * the APMT table mapping.
+ */
+ status = acpi_get_table(ACPI_SIG_APMT, 0, &apmt_table);
+
+ if (ACPI_FAILURE(status)) {
+ if (status != AE_NOT_FOUND) {
+ const char *msg = acpi_format_exception(status);
+
+ pr_err("Failed to get APMT table, %s\n", msg);
+ }
+
+ return;
+ }
+
+ ret = apmt_init_platform_devices();
+ if (ret) {
+ pr_err("Failed to initialize APMT platform devices, ret: %d\n", ret);
+ acpi_put_table(apmt_table);
+ }
+}
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 8059baf4ef27..38fb84974f35 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -402,6 +402,10 @@ static struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node,
return NULL;
}
+#ifndef ACPI_IORT_SMMU_V3_DEVICEID_VALID
+#define ACPI_IORT_SMMU_V3_DEVICEID_VALID (1 << 4)
+#endif
+
static int iort_get_id_mapping_index(struct acpi_iort_node *node)
{
struct acpi_iort_smmu_v3 *smmu;
@@ -418,12 +422,16 @@ static int iort_get_id_mapping_index(struct acpi_iort_node *node)
smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
/*
- * ID mapping index is only ignored if all interrupts are
- * GSIV based
+ * Until IORT E.e (node rev. 5), the ID mapping index was
+ * defined to be valid unless all interrupts are GSIV-based.
*/
- if (smmu->event_gsiv && smmu->pri_gsiv && smmu->gerr_gsiv
- && smmu->sync_gsiv)
+ if (node->revision < 5) {
+ if (smmu->event_gsiv && smmu->pri_gsiv &&
+ smmu->gerr_gsiv && smmu->sync_gsiv)
+ return -EINVAL;
+ } else if (!(smmu->flags & ACPI_IORT_SMMU_V3_DEVICEID_VALID)) {
return -EINVAL;
+ }
if (smmu->id_mapping_index >= node->mapping_count) {
pr_err(FW_BUG "[node %p type %d] ID mapping index overflows valid mappings\n",
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index d466c8195314..351208eda9be 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -27,6 +27,7 @@
#include <linux/dmi.h>
#endif
#include <linux/acpi_agdi.h>
+#include <linux/acpi_apmt.h>
#include <linux/acpi_iort.h>
#include <linux/acpi_viot.h>
#include <linux/pci.h>
@@ -1423,6 +1424,7 @@ static int __init acpi_init(void)
acpi_setup_sb_notify_handler();
acpi_viot_init();
acpi_agdi_init();
+ acpi_apmt_init();
return 0;
}
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index b1601aad7e1a..1016f0b5311d 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -20,6 +20,7 @@ cflags-$(CONFIG_X86) += -m$(BITS) -D__KERNEL__ \
# disable the stackleak plugin
cflags-$(CONFIG_ARM64) := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \
-fpie $(DISABLE_STACKLEAK_PLUGIN) \
+ -fno-unwind-tables -fno-asynchronous-unwind-tables \
$(call cc-option,-mbranch-protection=none)
cflags-$(CONFIG_ARM) := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \
-fno-builtin -fpic \
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 3f07df5a7e95..82a6d22e8ee2 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -861,16 +861,16 @@ static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu)
&cpu_pmu->node);
}
-static struct arm_pmu *__armpmu_alloc(gfp_t flags)
+struct arm_pmu *armpmu_alloc(void)
{
struct arm_pmu *pmu;
int cpu;
- pmu = kzalloc(sizeof(*pmu), flags);
+ pmu = kzalloc(sizeof(*pmu), GFP_KERNEL);
if (!pmu)
goto out;
- pmu->hw_events = alloc_percpu_gfp(struct pmu_hw_events, flags);
+ pmu->hw_events = alloc_percpu_gfp(struct pmu_hw_events, GFP_KERNEL);
if (!pmu->hw_events) {
pr_info("failed to allocate per-cpu PMU data.\n");
goto out_free_pmu;
@@ -916,17 +916,6 @@ out:
return NULL;
}
-struct arm_pmu *armpmu_alloc(void)
-{
- return __armpmu_alloc(GFP_KERNEL);
-}
-
-struct arm_pmu *armpmu_alloc_atomic(void)
-{
- return __armpmu_alloc(GFP_ATOMIC);
-}
-
-
void armpmu_free(struct arm_pmu *pmu)
{
free_percpu(pmu->hw_events);
diff --git a/drivers/perf/arm_pmu_acpi.c b/drivers/perf/arm_pmu_acpi.c
index 96ffadd654ff..90815ad762eb 100644
--- a/drivers/perf/arm_pmu_acpi.c
+++ b/drivers/perf/arm_pmu_acpi.c
@@ -13,6 +13,7 @@
#include <linux/percpu.h>
#include <linux/perf/arm_pmu.h>
+#include <asm/cpu.h>
#include <asm/cputype.h>
static DEFINE_PER_CPU(struct arm_pmu *, probed_pmus);
@@ -187,7 +188,7 @@ out_err:
return err;
}
-static struct arm_pmu *arm_pmu_acpi_find_alloc_pmu(void)
+static struct arm_pmu *arm_pmu_acpi_find_pmu(void)
{
unsigned long cpuid = read_cpuid_id();
struct arm_pmu *pmu;
@@ -201,16 +202,7 @@ static struct arm_pmu *arm_pmu_acpi_find_alloc_pmu(void)
return pmu;
}
- pmu = armpmu_alloc_atomic();
- if (!pmu) {
- pr_warn("Unable to allocate PMU for CPU%d\n",
- smp_processor_id());
- return NULL;
- }
-
- pmu->acpi_cpuid = cpuid;
-
- return pmu;
+ return NULL;
}
/*
@@ -242,6 +234,22 @@ static bool pmu_irq_matches(struct arm_pmu *pmu, int irq)
return true;
}
+static void arm_pmu_acpi_associate_pmu_cpu(struct arm_pmu *pmu,
+ unsigned int cpu)
+{
+ int irq = per_cpu(pmu_irqs, cpu);
+
+ per_cpu(probed_pmus, cpu) = pmu;
+
+ if (pmu_irq_matches(pmu, irq)) {
+ struct pmu_hw_events __percpu *hw_events;
+ hw_events = pmu->hw_events;
+ per_cpu(hw_events->irq, cpu) = irq;
+ }
+
+ cpumask_set_cpu(cpu, &pmu->supported_cpus);
+}
+
/*
* This must run before the common arm_pmu hotplug logic, so that we can
* associate a CPU and its interrupt before the common code tries to manage the
@@ -254,42 +262,50 @@ static bool pmu_irq_matches(struct arm_pmu *pmu, int irq)
static int arm_pmu_acpi_cpu_starting(unsigned int cpu)
{
struct arm_pmu *pmu;
- struct pmu_hw_events __percpu *hw_events;
- int irq;
/* If we've already probed this CPU, we have nothing to do */
if (per_cpu(probed_pmus, cpu))
return 0;
- irq = per_cpu(pmu_irqs, cpu);
-
- pmu = arm_pmu_acpi_find_alloc_pmu();
- if (!pmu)
- return -ENOMEM;
+ pmu = arm_pmu_acpi_find_pmu();
+ if (!pmu) {
+ pr_warn_ratelimited("Unable to associate CPU%d with a PMU\n",
+ cpu);
+ return 0;
+ }
- per_cpu(probed_pmus, cpu) = pmu;
+ arm_pmu_acpi_associate_pmu_cpu(pmu, cpu);
+ return 0;
+}
- if (pmu_irq_matches(pmu, irq)) {
- hw_events = pmu->hw_events;
- per_cpu(hw_events->irq, cpu) = irq;
- }
+static void arm_pmu_acpi_probe_matching_cpus(struct arm_pmu *pmu,
+ unsigned long cpuid)
+{
+ int cpu;
- cpumask_set_cpu(cpu, &pmu->supported_cpus);
+ for_each_online_cpu(cpu) {
+ unsigned long cpu_cpuid = per_cpu(cpu_data, cpu).reg_midr;
- /*
- * Ideally, we'd probe the PMU here when we find the first matching
- * CPU. We can't do that for several reasons; see the comment in
- * arm_pmu_acpi_init().
- *
- * So for the time being, we're done.
- */
- return 0;
+ if (cpu_cpuid == cpuid)
+ arm_pmu_acpi_associate_pmu_cpu(pmu, cpu);
+ }
}
int arm_pmu_acpi_probe(armpmu_init_fn init_fn)
{
int pmu_idx = 0;
- int cpu, ret;
+ unsigned int cpu;
+ int ret;
+
+ ret = arm_pmu_acpi_parse_irqs();
+ if (ret)
+ return ret;
+
+ ret = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_ACPI_STARTING,
+ "perf/arm/pmu_acpi:starting",
+ arm_pmu_acpi_cpu_starting, NULL);
+ if (ret)
+ return ret;
/*
* Initialise and register the set of PMUs which we know about right
@@ -304,13 +320,27 @@ int arm_pmu_acpi_probe(armpmu_init_fn init_fn)
* For the moment, as with the platform/DT case, we need at least one
* of a PMU's CPUs to be online at probe time.
*/
- for_each_possible_cpu(cpu) {
+ for_each_online_cpu(cpu) {
struct arm_pmu *pmu = per_cpu(probed_pmus, cpu);
+ unsigned long cpuid;
char *base_name;
- if (!pmu || pmu->name)
+ /* If we've already probed this CPU, we have nothing to do */
+ if (pmu)
continue;
+ pmu = armpmu_alloc();
+ if (!pmu) {
+ pr_warn("Unable to allocate PMU for CPU%d\n",
+ cpu);
+ return -ENOMEM;
+ }
+
+ cpuid = per_cpu(cpu_data, cpu).reg_midr;
+ pmu->acpi_cpuid = cpuid;
+
+ arm_pmu_acpi_probe_matching_cpus(pmu, cpuid);
+
ret = init_fn(pmu);
if (ret == -ENODEV) {
/* PMU not handled by this driver, or not present */
@@ -335,26 +365,16 @@ int arm_pmu_acpi_probe(armpmu_init_fn init_fn)
}
}
- return 0;
+ return ret;
}
static int arm_pmu_acpi_init(void)
{
- int ret;
-
if (acpi_disabled)
return 0;
arm_spe_acpi_register_device();
- ret = arm_pmu_acpi_parse_irqs();
- if (ret)
- return ret;
-
- ret = cpuhp_setup_state(CPUHP_AP_PERF_ARM_ACPI_STARTING,
- "perf/arm/pmu_acpi:starting",
- arm_pmu_acpi_cpu_starting, NULL);
-
- return ret;
+ return 0;
}
subsys_initcall(arm_pmu_acpi_init)
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index d06ada2341cb..0cca179e5106 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -1027,14 +1027,19 @@
* keep any .init_array.* sections.
* https://bugs.llvm.org/show_bug.cgi?id=46478
*/
+#ifdef CONFIG_UNWIND_TABLES
+#define DISCARD_EH_FRAME
+#else
+#define DISCARD_EH_FRAME *(.eh_frame)
+#endif
#if defined(CONFIG_GCOV_KERNEL) || defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KCSAN)
# ifdef CONFIG_CONSTRUCTORS
# define SANITIZER_DISCARDS \
- *(.eh_frame)
+ DISCARD_EH_FRAME
# else
# define SANITIZER_DISCARDS \
*(.init_array) *(.init_array.*) \
- *(.eh_frame)
+ DISCARD_EH_FRAME
# endif
#else
# define SANITIZER_DISCARDS
diff --git a/include/linux/acpi_apmt.h b/include/linux/acpi_apmt.h
new file mode 100644
index 000000000000..40bd634d082f
--- /dev/null
+++ b/include/linux/acpi_apmt.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * ARM CoreSight PMU driver.
+ * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES.
+ *
+ */
+
+#ifndef __ACPI_APMT_H__
+#define __ACPI_APMT_H__
+
+#include <linux/acpi.h>
+
+#ifdef CONFIG_ACPI_APMT
+void acpi_apmt_init(void);
+#else
+static inline void acpi_apmt_init(void) { }
+#endif /* CONFIG_ACPI_APMT */
+
+#endif /* __ACPI_APMT_H__ */
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 0356cb6a215d..0c15c5b7f801 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -174,7 +174,6 @@ void kvm_host_pmu_init(struct arm_pmu *pmu);
/* Internal functions only for core arm_pmu code */
struct arm_pmu *armpmu_alloc(void);
-struct arm_pmu *armpmu_alloc_atomic(void);
void armpmu_free(struct arm_pmu *pmu);
int armpmu_register(struct arm_pmu *pmu);
int armpmu_request_irq(int irq, int cpu);
diff --git a/include/linux/scs.h b/include/linux/scs.h
index 18122d9e17ff..4ab5bdc898cf 100644
--- a/include/linux/scs.h
+++ b/include/linux/scs.h
@@ -53,6 +53,22 @@ static inline bool task_scs_end_corrupted(struct task_struct *tsk)
return sz >= SCS_SIZE - 1 || READ_ONCE_NOCHECK(*magic) != SCS_END_MAGIC;
}
+DECLARE_STATIC_KEY_FALSE(dynamic_scs_enabled);
+
+static inline bool scs_is_dynamic(void)
+{
+ if (!IS_ENABLED(CONFIG_DYNAMIC_SCS))
+ return false;
+ return static_branch_likely(&dynamic_scs_enabled);
+}
+
+static inline bool scs_is_enabled(void)
+{
+ if (!IS_ENABLED(CONFIG_DYNAMIC_SCS))
+ return true;
+ return scs_is_dynamic();
+}
+
#else /* CONFIG_SHADOW_CALL_STACK */
static inline void *scs_alloc(int node) { return NULL; }
@@ -62,6 +78,8 @@ static inline void scs_task_reset(struct task_struct *tsk) {}
static inline int scs_prepare(struct task_struct *tsk, int node) { return 0; }
static inline void scs_release(struct task_struct *tsk) {}
static inline bool task_scs_end_corrupted(struct task_struct *tsk) { return false; }
+static inline bool scs_is_enabled(void) { return false; }
+static inline bool scs_is_dynamic(void) { return false; }
#endif /* CONFIG_SHADOW_CALL_STACK */
diff --git a/kernel/scs.c b/kernel/scs.c
index b7e1b096d906..d7809affe740 100644
--- a/kernel/scs.c
+++ b/kernel/scs.c
@@ -12,6 +12,10 @@
#include <linux/vmalloc.h>
#include <linux/vmstat.h>
+#ifdef CONFIG_DYNAMIC_SCS
+DEFINE_STATIC_KEY_FALSE(dynamic_scs_enabled);
+#endif
+
static void __scs_account(void *s, int account)
{
struct page *scs_page = vmalloc_to_page(s);
@@ -101,14 +105,20 @@ static int scs_cleanup(unsigned int cpu)
void __init scs_init(void)
{
+ if (!scs_is_enabled())
+ return;
cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "scs:scs_cache", NULL,
scs_cleanup);
}
int scs_prepare(struct task_struct *tsk, int node)
{
- void *s = scs_alloc(node);
+ void *s;
+ if (!scs_is_enabled())
+ return 0;
+
+ s = scs_alloc(node);
if (!s)
return -ENOMEM;
@@ -148,7 +158,7 @@ void scs_release(struct task_struct *tsk)
{
void *s = task_scs(tsk);
- if (!s)
+ if (!scs_is_enabled() || !s)
return;
WARN(task_scs_end_corrupted(tsk),
diff --git a/scripts/module.lds.S b/scripts/module.lds.S
index da4bddd26171..bf5bcf2836d8 100644
--- a/scripts/module.lds.S
+++ b/scripts/module.lds.S
@@ -3,6 +3,12 @@
* Archs are free to supply their own linker scripts. ld will
* combine them automatically.
*/
+#ifdef CONFIG_UNWIND_TABLES
+#define DISCARD_EH_FRAME
+#else
+#define DISCARD_EH_FRAME *(.eh_frame)
+#endif
+
SECTIONS {
/DISCARD/ : {
*(.discard)
diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c
index 9f1a7b5c6193..9f255bc5f31c 100644
--- a/tools/testing/selftests/arm64/abi/hwcap.c
+++ b/tools/testing/selftests/arm64/abi/hwcap.c
@@ -33,6 +33,12 @@
*/
typedef void (*sigill_fn)(void);
+static void cssc_sigill(void)
+{
+ /* CNT x0, x0 */
+ asm volatile(".inst 0xdac01c00" : : : "x0");
+}
+
static void rng_sigill(void)
{
asm volatile("mrs x0, S3_3_C2_C4_0" : : : "x0");
@@ -56,6 +62,12 @@ static void sve2_sigill(void)
asm volatile(".inst 0x4408A000" : : : "z0");
}
+static void sve2p1_sigill(void)
+{
+ /* BFADD Z0.H, Z0.H, Z0.H */
+ asm volatile(".inst 0x65000000" : : : "z0");
+}
+
static void sveaes_sigill(void)
{
/* AESD z0.b, z0.b, z0.b */
@@ -119,6 +131,13 @@ static const struct hwcap_data {
bool sigill_reliable;
} hwcaps[] = {
{
+ .name = "CSSC",
+ .at_hwcap = AT_HWCAP2,
+ .hwcap_bit = HWCAP2_CSSC,
+ .cpuinfo = "cssc",
+ .sigill_fn = cssc_sigill,
+ },
+ {
.name = "RNG",
.at_hwcap = AT_HWCAP2,
.hwcap_bit = HWCAP2_RNG,
@@ -126,6 +145,12 @@ static const struct hwcap_data {
.sigill_fn = rng_sigill,
},
{
+ .name = "RPRFM",
+ .at_hwcap = AT_HWCAP2,
+ .hwcap_bit = HWCAP2_RPRFM,
+ .cpuinfo = "rprfm",
+ },
+ {
.name = "SME",
.at_hwcap = AT_HWCAP2,
.hwcap_bit = HWCAP2_SME,
@@ -149,6 +174,13 @@ static const struct hwcap_data {
.sigill_fn = sve2_sigill,
},
{
+ .name = "SVE 2.1",
+ .at_hwcap = AT_HWCAP2,
+ .hwcap_bit = HWCAP2_SVE2P1,
+ .cpuinfo = "sve2p1",
+ .sigill_fn = sve2p1_sigill,
+ },
+ {
.name = "SVE AES",
.at_hwcap = AT_HWCAP2,
.hwcap_bit = HWCAP2_SVEAES,