summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-03-10 10:17:23 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2019-03-10 10:17:23 -0700
commit3d8dfe75ef69f4dd4ba35c09b20a5aa58b4a5078 (patch)
treee5dd2ba86a027007610df67331304e083fe560ec /arch
parentd6075262969321bcb5d795de25595fc2a141ac02 (diff)
parentb855b58ac1b7891b219e1d9ef60c45c774cadefe (diff)
downloadlinux-3d8dfe75ef69f4dd4ba35c09b20a5aa58b4a5078.tar.bz2
Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux
Pull arm64 updates from Catalin Marinas: - Pseudo NMI support for arm64 using GICv3 interrupt priorities - uaccess macros clean-up (unsafe user accessors also merged but reverted, waiting for objtool support on arm64) - ptrace regsets for Pointer Authentication (ARMv8.3) key management - inX() ordering w.r.t. delay() on arm64 and riscv (acks in place by the riscv maintainers) - arm64/perf updates: PMU bindings converted to json-schema, unused variable and misleading comment removed - arm64/debug fixes to ensure checking of the triggering exception level and to avoid the propagation of the UNKNOWN FAR value into the si_code for debug signals - Workaround for Fujitsu A64FX erratum 010001 - lib/raid6 ARM NEON optimisations - NR_CPUS now defaults to 256 on arm64 - Minor clean-ups (documentation/comments, Kconfig warning, unused asm-offsets, clang warnings) - MAINTAINERS update for list information to the ARM64 ACPI entry * tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (54 commits) arm64: mmu: drop paging_init comments arm64: debug: Ensure debug handlers check triggering exception level arm64: debug: Don't propagate UNKNOWN FAR into si_code for debug signals Revert "arm64: uaccess: Implement unsafe accessors" arm64: avoid clang warning about self-assignment arm64: Kconfig.platforms: fix warning unmet direct dependencies lib/raid6: arm: optimize away a mask operation in NEON recovery routine lib/raid6: use vdupq_n_u8 to avoid endianness warnings arm64: io: Hook up __io_par() for inX() ordering riscv: io: Update __io_[p]ar() macros to take an argument asm-generic/io: Pass result of I/O accessor to __io_[p]ar() arm64: Add workaround for Fujitsu A64FX erratum 010001 arm64: Rename get_thread_info() arm64: Remove documentation about TIF_USEDFPU arm64: irqflags: Fix clang build warnings arm64: Enable the support of pseudo-NMIs arm64: Skip irqflags tracing for NMI in IRQs disabled context arm64: Skip preemption when exiting an NMI arm64: Handle serror in NMI context irqchip/gic-v3: Allow interrupts to be set as pseudo-NMI ...
Diffstat (limited to 'arch')
-rw-r--r--arch/arm/include/asm/arch_gicv3.h33
-rw-r--r--arch/arm64/Kconfig36
-rw-r--r--arch/arm64/Kconfig.platforms2
-rw-r--r--arch/arm64/include/asm/alternative.h4
-rw-r--r--arch/arm64/include/asm/arch_gicv3.h32
-rw-r--r--arch/arm64/include/asm/asm-uaccess.h2
-rw-r--r--arch/arm64/include/asm/assembler.h36
-rw-r--r--arch/arm64/include/asm/cpucaps.h3
-rw-r--r--arch/arm64/include/asm/cpufeature.h10
-rw-r--r--arch/arm64/include/asm/cputype.h9
-rw-r--r--arch/arm64/include/asm/daifflags.h60
-rw-r--r--arch/arm64/include/asm/efi.h11
-rw-r--r--arch/arm64/include/asm/hardirq.h31
-rw-r--r--arch/arm64/include/asm/io.h1
-rw-r--r--arch/arm64/include/asm/irqflags.h100
-rw-r--r--arch/arm64/include/asm/kvm_host.h16
-rw-r--r--arch/arm64/include/asm/memblock.h21
-rw-r--r--arch/arm64/include/asm/memory.h5
-rw-r--r--arch/arm64/include/asm/mmu.h1
-rw-r--r--arch/arm64/include/asm/pgtable-hwdef.h1
-rw-r--r--arch/arm64/include/asm/processor.h3
-rw-r--r--arch/arm64/include/asm/ptdump.h9
-rw-r--r--arch/arm64/include/asm/ptrace.h26
-rw-r--r--arch/arm64/include/asm/thread_info.h1
-rw-r--r--arch/arm64/include/asm/uaccess.h36
-rw-r--r--arch/arm64/include/uapi/asm/ptrace.h13
-rw-r--r--arch/arm64/kernel/alternative.c60
-rw-r--r--arch/arm64/kernel/asm-offsets.c21
-rw-r--r--arch/arm64/kernel/cpufeature.c41
-rw-r--r--arch/arm64/kernel/entry.S60
-rw-r--r--arch/arm64/kernel/irq.c3
-rw-r--r--arch/arm64/kernel/kgdb.c14
-rw-r--r--arch/arm64/kernel/perf_event.c2
-rw-r--r--arch/arm64/kernel/probes/kprobes.c6
-rw-r--r--arch/arm64/kernel/process.c51
-rw-r--r--arch/arm64/kernel/ptrace.c147
-rw-r--r--arch/arm64/kernel/setup.c1
-rw-r--r--arch/arm64/kernel/smp.c33
-rw-r--r--arch/arm64/kernel/traps.c8
-rw-r--r--arch/arm64/kvm/hyp/switch.c16
-rw-r--r--arch/arm64/mm/dump.c4
-rw-r--r--arch/arm64/mm/fault.c9
-rw-r--r--arch/arm64/mm/init.c20
-rw-r--r--arch/arm64/mm/mmu.c5
-rw-r--r--arch/arm64/mm/proc.S12
-rw-r--r--arch/arm64/mm/ptdump_debugfs.c7
-rw-r--r--arch/riscv/include/asm/io.h36
47 files changed, 826 insertions, 232 deletions
diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h
index 0bd530702118..f6f485f4744e 100644
--- a/arch/arm/include/asm/arch_gicv3.h
+++ b/arch/arm/include/asm/arch_gicv3.h
@@ -34,6 +34,7 @@
#define ICC_SRE __ACCESS_CP15(c12, 0, c12, 5)
#define ICC_IGRPEN1 __ACCESS_CP15(c12, 0, c12, 7)
#define ICC_BPR1 __ACCESS_CP15(c12, 0, c12, 3)
+#define ICC_RPR __ACCESS_CP15(c12, 0, c11, 3)
#define __ICC_AP0Rx(x) __ACCESS_CP15(c12, 0, c8, 4 | x)
#define ICC_AP0R0 __ICC_AP0Rx(0)
@@ -245,6 +246,21 @@ static inline void gic_write_bpr1(u32 val)
write_sysreg(val, ICC_BPR1);
}
+static inline u32 gic_read_pmr(void)
+{
+ return read_sysreg(ICC_PMR);
+}
+
+static inline void gic_write_pmr(u32 val)
+{
+ write_sysreg(val, ICC_PMR);
+}
+
+static inline u32 gic_read_rpr(void)
+{
+ return read_sysreg(ICC_RPR);
+}
+
/*
* Even in 32bit systems that use LPAE, there is no guarantee that the I/O
* interface provides true 64bit atomic accesses, so using strd/ldrd doesn't
@@ -347,5 +363,22 @@ static inline void gits_write_vpendbaser(u64 val, void * __iomem addr)
#define gits_read_vpendbaser(c) __gic_readq_nonatomic(c)
+static inline bool gic_prio_masking_enabled(void)
+{
+ return false;
+}
+
+static inline void gic_pmr_mask_irqs(void)
+{
+ /* Should not get called. */
+ WARN_ON_ONCE(true);
+}
+
+static inline void gic_arch_enable_irqs(void)
+{
+ /* Should not get called. */
+ WARN_ON_ONCE(true);
+}
+
#endif /* !__ASSEMBLY__ */
#endif /* !__ASM_ARCH_GICV3_H */
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index cfbf307d6dc4..4fab69620719 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -643,6 +643,25 @@ config QCOM_FALKOR_ERRATUM_E1041
If unsure, say Y.
+config FUJITSU_ERRATUM_010001
+ bool "Fujitsu-A64FX erratum E#010001: Undefined fault may occur wrongly"
+ default y
+ help
+ This option adds workaround for Fujitsu-A64FX erratum E#010001.
+ On some variants of the Fujitsu-A64FX cores ver(1.0, 1.1), memory
+ accesses may cause undefined fault (Data abort, DFSC=0b111111).
+ This fault occurs under a specific hardware condition when a
+ load/store instruction performs an address translation using:
+ case-1 TTBR0_EL1 with TCR_EL1.NFD0 == 1.
+ case-2 TTBR0_EL2 with TCR_EL2.NFD0 == 1.
+ case-3 TTBR1_EL1 with TCR_EL1.NFD1 == 1.
+ case-4 TTBR1_EL2 with TCR_EL2.NFD1 == 1.
+
+ The workaround is to ensure these bits are clear in TCR_ELx.
+ The workaround only affect the Fujitsu-A64FX.
+
+ If unsure, say Y.
+
endmenu
@@ -792,8 +811,7 @@ config SCHED_SMT
config NR_CPUS
int "Maximum number of CPUs (2-4096)"
range 2 4096
- # These have to remain sorted largest to smallest
- default "64"
+ default "256"
config HOTPLUG_CPU
bool "Support for hot-pluggable CPUs"
@@ -1328,6 +1346,20 @@ config ARM64_MODULE_PLTS
bool
select HAVE_MOD_ARCH_SPECIFIC
+config ARM64_PSEUDO_NMI
+ bool "Support for NMI-like interrupts"
+ select CONFIG_ARM_GIC_V3
+ help
+ Adds support for mimicking Non-Maskable Interrupts through the use of
+ GIC interrupt priority. This support requires version 3 or later of
+ Arm GIC.
+
+ This high priority configuration for interrupts needs to be
+ explicitly enabled by setting the kernel parameter
+ "irqchip.gicv3_pseudo_nmi" to 1.
+
+ If unsure, say N
+
config RELOCATABLE
bool
help
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index c5f6a57f16b8..70498a033cf5 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -151,7 +151,7 @@ config ARCH_MVEBU
config ARCH_MXC
bool "ARMv8 based NXP i.MX SoC family"
select ARM64_ERRATUM_843419
- select ARM64_ERRATUM_845719
+ select ARM64_ERRATUM_845719 if COMPAT
select IMX_GPCV2
select IMX_GPCV2_PM_DOMAINS
select PM
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index 4b650ec1d7dd..b9f8d787eea9 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -14,8 +14,6 @@
#include <linux/stddef.h>
#include <linux/stringify.h>
-extern int alternatives_applied;
-
struct alt_instr {
s32 orig_offset; /* offset to original instruction */
s32 alt_offset; /* offset to replacement instruction */
@@ -27,7 +25,9 @@ struct alt_instr {
typedef void (*alternative_cb_t)(struct alt_instr *alt,
__le32 *origptr, __le32 *updptr, int nr_inst);
+void __init apply_boot_alternatives(void);
void __init apply_alternatives_all(void);
+bool alternative_is_applied(u16 cpufeature);
#ifdef CONFIG_MODULES
void apply_alternatives_module(void *start, size_t length);
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index e278f94df0c9..14b41ddc68ba 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -22,6 +22,7 @@
#ifndef __ASSEMBLY__
+#include <linux/irqchip/arm-gic-common.h>
#include <linux/stringify.h>
#include <asm/barrier.h>
#include <asm/cacheflush.h>
@@ -114,6 +115,21 @@ static inline void gic_write_bpr1(u32 val)
write_sysreg_s(val, SYS_ICC_BPR1_EL1);
}
+static inline u32 gic_read_pmr(void)
+{
+ return read_sysreg_s(SYS_ICC_PMR_EL1);
+}
+
+static inline void gic_write_pmr(u32 val)
+{
+ write_sysreg_s(val, SYS_ICC_PMR_EL1);
+}
+
+static inline u32 gic_read_rpr(void)
+{
+ return read_sysreg_s(SYS_ICC_RPR_EL1);
+}
+
#define gic_read_typer(c) readq_relaxed(c)
#define gic_write_irouter(v, c) writeq_relaxed(v, c)
#define gic_read_lpir(c) readq_relaxed(c)
@@ -140,5 +156,21 @@ static inline void gic_write_bpr1(u32 val)
#define gits_write_vpendbaser(v, c) writeq_relaxed(v, c)
#define gits_read_vpendbaser(c) readq_relaxed(c)
+static inline bool gic_prio_masking_enabled(void)
+{
+ return system_uses_irq_prio_masking();
+}
+
+static inline void gic_pmr_mask_irqs(void)
+{
+ BUILD_BUG_ON(GICD_INT_DEF_PRI <= GIC_PRIO_IRQOFF);
+ gic_write_pmr(GIC_PRIO_IRQOFF);
+}
+
+static inline void gic_arch_enable_irqs(void)
+{
+ asm volatile ("msr daifclr, #2" : : : "memory");
+}
+
#endif /* __ASSEMBLY__ */
#endif /* __ASM_ARCH_GICV3_H */
diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h
index 4128bec033f6..f74909ba29bd 100644
--- a/arch/arm64/include/asm/asm-uaccess.h
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -24,7 +24,7 @@
.endm
.macro __uaccess_ttbr0_enable, tmp1, tmp2
- get_thread_info \tmp1
+ get_current_task \tmp1
ldr \tmp1, [\tmp1, #TSK_TI_TTBR0] // load saved TTBR0_EL1
mrs \tmp2, ttbr1_el1
extr \tmp2, \tmp2, \tmp1, #48
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 4feb6119c3c9..c5308d01e228 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -27,6 +27,7 @@
#include <asm/asm-offsets.h>
#include <asm/cpufeature.h>
+#include <asm/cputype.h>
#include <asm/debug-monitors.h>
#include <asm/page.h>
#include <asm/pgtable-hwdef.h>
@@ -62,16 +63,8 @@
.endm
/*
- * Enable and disable interrupts.
+ * Save/restore interrupts.
*/
- .macro disable_irq
- msr daifset, #2
- .endm
-
- .macro enable_irq
- msr daifclr, #2
- .endm
-
.macro save_and_disable_irq, flags
mrs \flags, daif
msr daifset, #2
@@ -536,9 +529,9 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU
.endm
/*
- * Return the current thread_info.
+ * Return the current task_struct.
*/
- .macro get_thread_info, rd
+ .macro get_current_task, rd
mrs \rd, sp_el0
.endm
@@ -604,6 +597,25 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU
#endif
.endm
+/*
+ * tcr_clear_errata_bits - Clear TCR bits that trigger an errata on this CPU.
+ */
+ .macro tcr_clear_errata_bits, tcr, tmp1, tmp2
+#ifdef CONFIG_FUJITSU_ERRATUM_010001
+ mrs \tmp1, midr_el1
+
+ mov_q \tmp2, MIDR_FUJITSU_ERRATUM_010001_MASK
+ and \tmp1, \tmp1, \tmp2
+ mov_q \tmp2, MIDR_FUJITSU_ERRATUM_010001
+ cmp \tmp1, \tmp2
+ b.ne 10f
+
+ mov_q \tmp2, TCR_CLEAR_FUJITSU_ERRATUM_010001
+ bic \tcr, \tcr, \tmp2
+10:
+#endif /* CONFIG_FUJITSU_ERRATUM_010001 */
+ .endm
+
/**
* Errata workaround prior to disable MMU. Insert an ISB immediately prior
* to executing the MSR that will change SCTLR_ELn[M] from a value of 1 to 0.
@@ -721,7 +733,7 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU
.macro if_will_cond_yield_neon
#ifdef CONFIG_PREEMPT
- get_thread_info x0
+ get_current_task x0
ldr x0, [x0, #TSK_TI_PREEMPT]
sub x0, x0, #PREEMPT_DISABLE_OFFSET
cbz x0, .Lyield_\@
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 82e9099834ae..f6a76e43f39e 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -60,7 +60,8 @@
#define ARM64_HAS_ADDRESS_AUTH_IMP_DEF 39
#define ARM64_HAS_GENERIC_AUTH_ARCH 40
#define ARM64_HAS_GENERIC_AUTH_IMP_DEF 41
+#define ARM64_HAS_IRQ_PRIO_MASKING 42
-#define ARM64_NCAPS 42
+#define ARM64_NCAPS 43
#endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index dfcfba725d72..e505e1fbd2b9 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -391,6 +391,10 @@ extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS];
extern struct static_key_false arm64_const_caps_ready;
+/* ARM64 CAPS + alternative_cb */
+#define ARM64_NPATCHABLE (ARM64_NCAPS + 1)
+extern DECLARE_BITMAP(boot_capabilities, ARM64_NPATCHABLE);
+
#define for_each_available_cap(cap) \
for_each_set_bit(cap, cpu_hwcaps, ARM64_NCAPS)
@@ -612,6 +616,12 @@ static inline bool system_supports_generic_auth(void)
cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH_IMP_DEF));
}
+static inline bool system_uses_irq_prio_masking(void)
+{
+ return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) &&
+ cpus_have_const_cap(ARM64_HAS_IRQ_PRIO_MASKING);
+}
+
#define ARM64_SSBD_UNKNOWN -1
#define ARM64_SSBD_FORCE_DISABLE 0
#define ARM64_SSBD_KERNEL 1
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 951ed1a4e5c9..2afb1338b48a 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -76,6 +76,7 @@
#define ARM_CPU_IMP_BRCM 0x42
#define ARM_CPU_IMP_QCOM 0x51
#define ARM_CPU_IMP_NVIDIA 0x4E
+#define ARM_CPU_IMP_FUJITSU 0x46
#define ARM_CPU_PART_AEM_V8 0xD0F
#define ARM_CPU_PART_FOUNDATION 0xD00
@@ -104,6 +105,8 @@
#define NVIDIA_CPU_PART_DENVER 0x003
#define NVIDIA_CPU_PART_CARMEL 0x004
+#define FUJITSU_CPU_PART_A64FX 0x001
+
#define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
#define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
#define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
@@ -122,6 +125,12 @@
#define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
#define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER)
#define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
+#define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX)
+
+/* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
+#define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX
+#define MIDR_FUJITSU_ERRATUM_010001_MASK (~MIDR_VARIANT(1))
+#define TCR_CLEAR_FUJITSU_ERRATUM_010001 (TCR_NFD1 | TCR_NFD0)
#ifndef __ASSEMBLY__
diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h
index fa90779fc752..db452aa9e651 100644
--- a/arch/arm64/include/asm/daifflags.h
+++ b/arch/arm64/include/asm/daifflags.h
@@ -18,6 +18,8 @@
#include <linux/irqflags.h>
+#include <asm/cpufeature.h>
+
#define DAIF_PROCCTX 0
#define DAIF_PROCCTX_NOIRQ PSR_I_BIT
#define DAIF_ERRCTX (PSR_I_BIT | PSR_A_BIT)
@@ -37,31 +39,61 @@ static inline unsigned long local_daif_save(void)
{
unsigned long flags;
- flags = arch_local_save_flags();
+ flags = read_sysreg(daif);
+
+ if (system_uses_irq_prio_masking()) {
+ /* If IRQs are masked with PMR, reflect it in the flags */
+ if (read_sysreg_s(SYS_ICC_PMR_EL1) <= GIC_PRIO_IRQOFF)
+ flags |= PSR_I_BIT;
+ }
local_daif_mask();
return flags;
}
-static inline void local_daif_unmask(void)
-{
- trace_hardirqs_on();
- asm volatile(
- "msr daifclr, #0xf // local_daif_unmask"
- :
- :
- : "memory");
-}
-
static inline void local_daif_restore(unsigned long flags)
{
- if (!arch_irqs_disabled_flags(flags))
+ bool irq_disabled = flags & PSR_I_BIT;
+
+ if (!irq_disabled) {
trace_hardirqs_on();
- arch_local_irq_restore(flags);
+ if (system_uses_irq_prio_masking())
+ arch_local_irq_enable();
+ } else if (!(flags & PSR_A_BIT)) {
+ /*
+ * If interrupts are disabled but we can take
+ * asynchronous errors, we can take NMIs
+ */
+ if (system_uses_irq_prio_masking()) {
+ flags &= ~PSR_I_BIT;
+ /*
+ * There has been concern that the write to daif
+ * might be reordered before this write to PMR.
+ * From the ARM ARM DDI 0487D.a, section D1.7.1
+ * "Accessing PSTATE fields":
+ * Writes to the PSTATE fields have side-effects on
+ * various aspects of the PE operation. All of these
+ * side-effects are guaranteed:
+ * - Not to be visible to earlier instructions in
+ * the execution stream.
+ * - To be visible to later instructions in the
+ * execution stream
+ *
+ * Also, writes to PMR are self-synchronizing, so no
+ * interrupts with a lower priority than PMR is signaled
+ * to the PE after the write.
+ *
+ * So we don't need additional synchronization here.
+ */
+ arch_local_irq_disable();
+ }
+ }
+
+ write_sysreg(flags, daif);
- if (arch_irqs_disabled_flags(flags))
+ if (irq_disabled)
trace_hardirqs_off();
}
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 7ed320895d1f..c9e9a6978e73 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -44,6 +44,17 @@ efi_status_t __efi_rt_asm_wrapper(void *, const char *, ...);
#define ARCH_EFI_IRQ_FLAGS_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT)
+/*
+ * Even when Linux uses IRQ priorities for IRQ disabling, EFI does not.
+ * And EFI shouldn't really play around with priority masking as it is not aware
+ * which priorities the OS has assigned to its interrupts.
+ */
+#define arch_efi_save_flags(state_flags) \
+ ((void)((state_flags) = read_sysreg(daif)))
+
+#define arch_efi_restore_flags(state_flags) write_sysreg(state_flags, daif)
+
+
/* arch specific definitions used by the stub code */
/*
diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
index 1473fc2f7ab7..89691c86640a 100644
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -17,8 +17,12 @@
#define __ASM_HARDIRQ_H
#include <linux/cache.h>
+#include <linux/percpu.h>
#include <linux/threads.h>
+#include <asm/barrier.h>
#include <asm/irq.h>
+#include <asm/kvm_arm.h>
+#include <asm/sysreg.h>
#define NR_IPI 7
@@ -37,6 +41,33 @@ u64 smp_irq_stat_cpu(unsigned int cpu);
#define __ARCH_IRQ_EXIT_IRQS_DISABLED 1
+struct nmi_ctx {
+ u64 hcr;
+};
+
+DECLARE_PER_CPU(struct nmi_ctx, nmi_contexts);
+
+#define arch_nmi_enter() \
+ do { \
+ if (is_kernel_in_hyp_mode()) { \
+ struct nmi_ctx *nmi_ctx = this_cpu_ptr(&nmi_contexts); \
+ nmi_ctx->hcr = read_sysreg(hcr_el2); \
+ if (!(nmi_ctx->hcr & HCR_TGE)) { \
+ write_sysreg(nmi_ctx->hcr | HCR_TGE, hcr_el2); \
+ isb(); \
+ } \
+ } \
+ } while (0)
+
+#define arch_nmi_exit() \
+ do { \
+ if (is_kernel_in_hyp_mode()) { \
+ struct nmi_ctx *nmi_ctx = this_cpu_ptr(&nmi_contexts); \
+ if (!(nmi_ctx->hcr & HCR_TGE)) \
+ write_sysreg(nmi_ctx->hcr, hcr_el2); \
+ } \
+ } while (0)
+
static inline void ack_bad_irq(unsigned int irq)
{
extern unsigned long irq_err_count;
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index ee723835c1f4..8bb7210ac286 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -121,6 +121,7 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
: "memory"); \
})
+#define __io_par(v) __iormb(v)
#define __iowmb() wmb()
#define mmiowb() do { } while (0)
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index 24692edf1a69..43d8366c1e87 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -18,7 +18,9 @@
#ifdef __KERNEL__
+#include <asm/alternative.h>
#include <asm/ptrace.h>
+#include <asm/sysreg.h>
/*
* Aarch64 has flags for masking: Debug, Asynchronous (serror), Interrupts and
@@ -36,33 +38,27 @@
/*
* CPU interrupt mask handling.
*/
-static inline unsigned long arch_local_irq_save(void)
-{
- unsigned long flags;
- asm volatile(
- "mrs %0, daif // arch_local_irq_save\n"
- "msr daifset, #2"
- : "=r" (flags)
- :
- : "memory");
- return flags;
-}
-
static inline void arch_local_irq_enable(void)
{
- asm volatile(
- "msr daifclr, #2 // arch_local_irq_enable"
- :
+ asm volatile(ALTERNATIVE(
+ "msr daifclr, #2 // arch_local_irq_enable\n"
+ "nop",
+ "msr_s " __stringify(SYS_ICC_PMR_EL1) ",%0\n"
+ "dsb sy",
+ ARM64_HAS_IRQ_PRIO_MASKING)
:
+ : "r" ((unsigned long) GIC_PRIO_IRQON)
: "memory");
}
static inline void arch_local_irq_disable(void)
{
- asm volatile(
- "msr daifset, #2 // arch_local_irq_disable"
- :
+ asm volatile(ALTERNATIVE(
+ "msr daifset, #2 // arch_local_irq_disable",
+ "msr_s " __stringify(SYS_ICC_PMR_EL1) ", %0",
+ ARM64_HAS_IRQ_PRIO_MASKING)
:
+ : "r" ((unsigned long) GIC_PRIO_IRQOFF)
: "memory");
}
@@ -71,12 +67,44 @@ static inline void arch_local_irq_disable(void)
*/
static inline unsigned long arch_local_save_flags(void)
{
+ unsigned long daif_bits;
unsigned long flags;
- asm volatile(
- "mrs %0, daif // arch_local_save_flags"
- : "=r" (flags)
- :
+
+ daif_bits = read_sysreg(daif);
+
+ /*
+ * The asm is logically equivalent to:
+ *
+ * if (system_uses_irq_prio_masking())
+ * flags = (daif_bits & PSR_I_BIT) ?
+ * GIC_PRIO_IRQOFF :
+ * read_sysreg_s(SYS_ICC_PMR_EL1);
+ * else
+ * flags = daif_bits;
+ */
+ asm volatile(ALTERNATIVE(
+ "mov %0, %1\n"
+ "nop\n"
+ "nop",
+ "mrs_s %0, " __stringify(SYS_ICC_PMR_EL1) "\n"
+ "ands %1, %1, " __stringify(PSR_I_BIT) "\n"
+ "csel %0, %0, %2, eq",
+ ARM64_HAS_IRQ_PRIO_MASKING)
+ : "=&r" (flags), "+r" (daif_bits)
+ : "r" ((unsigned long) GIC_PRIO_IRQOFF)
: "memory");
+
+ return flags;
+}
+
+static inline unsigned long arch_local_irq_save(void)
+{
+ unsigned long flags;
+
+ flags = arch_local_save_flags();
+
+ arch_local_irq_disable();
+
return flags;
}
@@ -85,16 +113,32 @@ static inline unsigned long arch_local_save_flags(void)
*/
static inline void arch_local_irq_restore(unsigned long flags)
{
- asm volatile(
- "msr daif, %0 // arch_local_irq_restore"
- :
- : "r" (flags)
- : "memory");
+ asm volatile(ALTERNATIVE(
+ "msr daif, %0\n"
+ "nop",
+ "msr_s " __stringify(SYS_ICC_PMR_EL1) ", %0\n"
+ "dsb sy",
+ ARM64_HAS_IRQ_PRIO_MASKING)
+ : "+r" (flags)
+ :
+ : "memory");
}
static inline int arch_irqs_disabled_flags(unsigned long flags)
{
- return flags & PSR_I_BIT;
+ int res;
+
+ asm volatile(ALTERNATIVE(
+ "and %w0, %w1, #" __stringify(PSR_I_BIT) "\n"
+ "nop",
+ "cmp %w1, #" __stringify(GIC_PRIO_IRQOFF) "\n"
+ "cset %w0, ls",
+ ARM64_HAS_IRQ_PRIO_MASKING)
+ : "=&r" (res)
+ : "r" ((int) flags)
+ : "memory");
+
+ return res;
}
#endif
#endif
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index da3fc7324d68..222af1d2c3e4 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -24,6 +24,7 @@
#include <linux/types.h>
#include <linux/kvm_types.h>
+#include <asm/arch_gicv3.h>
#include <asm/cpufeature.h>
#include <asm/daifflags.h>
#include <asm/fpsimd.h>
@@ -485,10 +486,25 @@ static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
static inline void kvm_arm_vhe_guest_enter(void)
{
local_daif_mask();
+
+ /*
+ * Having IRQs masked via PMR when entering the guest means the GIC
+ * will not signal the CPU of interrupts of lower priority, and the
+ * only way to get out will be via guest exceptions.
+ * Naturally, we want to avoid this.
+ */
+ if (system_uses_irq_prio_masking()) {
+ gic_write_pmr(GIC_PRIO_IRQON);
+ dsb(sy);
+ }
}
static inline void kvm_arm_vhe_guest_exit(void)
{
+ /*
+ * local_daif_restore() takes care to properly restore PSTATE.DAIF
+ * and the GIC PMR if the host is using IRQ priorities.
+ */
local_daif_restore(DAIF_PROCCTX_NOIRQ);
/*
diff --git a/arch/arm64/include/asm/memblock.h b/arch/arm64/include/asm/memblock.h
deleted file mode 100644
index 6afeed2467f1..000000000000
--- a/arch/arm64/include/asm/memblock.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-#ifndef __ASM_MEMBLOCK_H
-#define __ASM_MEMBLOCK_H
-
-extern void arm64_memblock_init(void);
-
-#endif
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index b01ef0180a03..290195168bb3 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -312,8 +312,9 @@ static inline void *phys_to_virt(phys_addr_t x)
#define page_to_virt(page) ({ \
unsigned long __addr = \
((__page_to_voff(page)) | PAGE_OFFSET); \
- __addr = __tag_set(__addr, page_kasan_tag(page)); \
- ((void *)__addr); \
+ unsigned long __addr_tag = \
+ __tag_set(__addr, page_kasan_tag(page)); \
+ ((void *)__addr_tag); \
})
#define virt_to_page(vaddr) ((struct page *)((__virt_to_pgoff(vaddr)) | VMEMMAP_START))
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 3e8063f4f9d3..67ef25d037ea 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -129,6 +129,7 @@ static inline struct bp_hardening_data *arm64_get_bp_hardening_data(void)
static inline void arm64_apply_bp_hardening(void) { }
#endif /* CONFIG_HARDEN_BRANCH_PREDICTOR */
+extern void arm64_memblock_init(void);
extern void paging_init(void);
extern void bootmem_init(void);
extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index e9b0a7d75184..a69259cc1f16 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -302,6 +302,7 @@
#define TCR_TBI1 (UL(1) << 38)
#define TCR_HA (UL(1) << 39)
#define TCR_HD (UL(1) << 40)
+#define TCR_NFD0 (UL(1) << 53)
#define TCR_NFD1 (UL(1) << 54)
/*
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index f1a7ab18faf3..5d9ce62bdebd 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -191,6 +191,9 @@ static inline void start_thread_common(struct pt_regs *regs, unsigned long pc)
memset(regs, 0, sizeof(*regs));
forget_syscall(regs);
regs->pc = pc;
+
+ if (system_uses_irq_prio_masking())
+ regs->pmr_save = GIC_PRIO_IRQON;
}
static inline void start_thread(struct pt_regs *regs, unsigned long pc,
diff --git a/arch/arm64/include/asm/ptdump.h b/arch/arm64/include/asm/ptdump.h
index 6afd8476c60c..9e948a93d26c 100644
--- a/arch/arm64/include/asm/ptdump.h
+++ b/arch/arm64/include/asm/ptdump.h
@@ -34,13 +34,10 @@ struct ptdump_info {
void ptdump_walk_pgd(struct seq_file *s, struct ptdump_info *info);
#ifdef CONFIG_ARM64_PTDUMP_DEBUGFS
-int ptdump_debugfs_register(struct ptdump_info *info, const char *name);
+void ptdump_debugfs_register(struct ptdump_info *info, const char *name);
#else
-static inline int ptdump_debugfs_register(struct ptdump_info *info,
- const char *name)
-{
- return 0;
-}
+static inline void ptdump_debugfs_register(struct ptdump_info *info,
+ const char *name) { }
#endif
void ptdump_check_wx(void);
#endif /* CONFIG_ARM64_PTDUMP_CORE */
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index fce22c4b2f73..ec60174c8c18 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -19,12 +19,26 @@
#ifndef __ASM_PTRACE_H
#define __ASM_PTRACE_H
+#include <asm/cpufeature.h>
+
#include <uapi/asm/ptrace.h>
/* Current Exception Level values, as contained in CurrentEL */
#define CurrentEL_EL1 (1 << 2)
#define CurrentEL_EL2 (2 << 2)
+/*
+ * PMR values used to mask/unmask interrupts.
+ *
+ * GIC priority masking works as follows: if an IRQ's priority is a higher value
+ * than the value held in PMR, that IRQ is masked. Lowering the value of PMR
+ * means masking more IRQs (or at least that the same IRQs remain masked).
+ *
+ * To mask interrupts, we clear the most significant bit of PMR.
+ */
+#define GIC_PRIO_IRQON 0xf0
+#define GIC_PRIO_IRQOFF (GIC_PRIO_IRQON & ~0x80)
+
/* Additional SPSR bits not exposed in the UABI */
#define PSR_IL_BIT (1 << 20)
@@ -167,7 +181,8 @@ struct pt_regs {
#endif
u64 orig_addr_limit;
- u64 unused; // maintain 16 byte alignment
+ /* Only valid when ARM64_HAS_IRQ_PRIO_MASKING is enabled. */
+ u64 pmr_save;
u64 stackframe[2];
};
@@ -202,8 +217,13 @@ static inline void forget_syscall(struct pt_regs *regs)
#define processor_mode(regs) \
((regs)->pstate & PSR_MODE_MASK)
-#define interrupts_enabled(regs) \
- (!((regs)->pstate & PSR_I_BIT))
+#define irqs_priority_unmasked(regs) \
+ (system_uses_irq_prio_masking() ? \
+ (regs)->pmr_save == GIC_PRIO_IRQON : \
+ true)
+
+#define interrupts_enabled(regs) \
+ (!((regs)->pstate & PSR_I_BIT) && irqs_priority_unmasked(regs))
#define fast_interrupts_enabled(regs) \
(!((regs)->pstate & PSR_F_BIT))
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index bbca68b54732..eb3ef73e07cf 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -79,7 +79,6 @@ void arch_release_task_struct(struct task_struct *tsk);
* TIF_SIGPENDING - signal pending
* TIF_NEED_RESCHED - rescheduling necessary
* TIF_NOTIFY_RESUME - callback before returning to user
- * TIF_USEDFPU - FPU was used by this task this quantum (SMP)
*/
#define TIF_SIGPENDING 0
#define TIF_NEED_RESCHED 1
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index f1e5c9165809..e5d5f31c6d36 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -267,7 +267,7 @@ static inline void __user *__uaccess_mask_ptr(const void __user *ptr)
: "+r" (err), "=&r" (x) \
: "r" (addr), "i" (-EFAULT))
-#define __get_user_err(x, ptr, err) \
+#define __raw_get_user(x, ptr, err) \
do { \
unsigned long __gu_val; \
__chk_user_ptr(ptr); \
@@ -296,28 +296,22 @@ do { \
(x) = (__force __typeof__(*(ptr)))__gu_val; \
} while (0)
-#define __get_user_check(x, ptr, err) \
-({ \
+#define __get_user_error(x, ptr, err) \
+do { \
__typeof__(*(ptr)) __user *__p = (ptr); \
might_fault(); \
if (access_ok(__p, sizeof(*__p))) { \
__p = uaccess_mask_ptr(__p); \
- __get_user_err((x), __p, (err)); \
+ __raw_get_user((x), __p, (err)); \
} else { \
(x) = 0; (err) = -EFAULT; \
} \
-})
-
-#define __get_user_error(x, ptr, err) \
-({ \
- __get_user_check((x), (ptr), (err)); \
- (void)0; \
-})
+} while (0)
#define __get_user(x, ptr) \
({ \
int __gu_err = 0; \
- __get_user_check((x), (ptr), __gu_err); \
+ __get_user_error((x), (ptr), __gu_err); \
__gu_err; \
})
@@ -337,7 +331,7 @@ do { \
: "+r" (err) \
: "r" (x), "r" (addr), "i" (-EFAULT))
-#define __put_user_err(x, ptr, err) \
+#define __raw_put_user(x, ptr, err) \
do { \
__typeof__(*(ptr)) __pu_val = (x); \
__chk_user_ptr(ptr); \
@@ -365,28 +359,22 @@ do { \
uaccess_disable_not_uao(); \
} while (0)
-#define __put_user_check(x, ptr, err) \
-({ \
+#define __put_user_error(x, ptr, err) \
+do { \
__typeof__(*(ptr)) __user *__p = (ptr); \
might_fault(); \
if (access_ok(__p, sizeof(*__p))) { \
__p = uaccess_mask_ptr(__p); \
- __put_user_err((x), __p, (err)); \
+ __raw_put_user((x), __p, (err)); \
} else { \
(err) = -EFAULT; \
} \
-})
-
-#define __put_user_error(x, ptr, err) \
-({ \
- __put_user_check((x), (ptr), (err)); \
- (void)0; \
-})
+} while (0)
#define __put_user(x, ptr) \
({ \
int __pu_err = 0; \
- __put_user_check((x), (ptr), __pu_err); \
+ __put_user_error((x), (ptr), __pu_err); \
__pu_err; \
})
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index 28d77c9ed531..d78623acb649 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -233,6 +233,19 @@ struct user_pac_mask {
__u64 insn_mask;
};
+/* pointer authentication keys (NT_ARM_PACA_KEYS, NT_ARM_PACG_KEYS) */
+
+struct user_pac_address_keys {
+ __uint128_t apiakey;
+ __uint128_t apibkey;
+ __uint128_t apdakey;
+ __uint128_t apdbkey;
+};
+
+struct user_pac_generic_keys {
+ __uint128_t apgakey;
+};
+
#endif /* __ASSEMBLY__ */
#endif /* _UAPI__ASM_PTRACE_H */
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index b5d603992d40..a9b467763153 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -32,13 +32,23 @@
#define ALT_ORIG_PTR(a) __ALT_PTR(a, orig_offset)
#define ALT_REPL_PTR(a) __ALT_PTR(a, alt_offset)
-int alternatives_applied;
+static int all_alternatives_applied;
+
+static DECLARE_BITMAP(applied_alternatives, ARM64_NCAPS);
struct alt_region {
struct alt_instr *begin;
struct alt_instr *end;
};
+bool alternative_is_applied(u16 cpufeature)
+{
+ if (WARN_ON(cpufeature >= ARM64_NCAPS))
+ return false;
+
+ return test_bit(cpufeature, applied_alternatives);
+}
+
/*
* Check if the target PC is within an alternative block.
*/
@@ -145,7 +155,8 @@ static void clean_dcache_range_nopatch(u64 start, u64 end)
} while (cur += d_size, cur < end);
}
-static void __apply_alternatives(void *alt_region, bool is_module)
+static void __apply_alternatives(void *alt_region, bool is_module,
+ unsigned long *feature_mask)
{
struct alt_instr *alt;
struct alt_region *region = alt_region;
@@ -155,6 +166,9 @@ static void __apply_alternatives(void *alt_region, bool is_module)
for (alt = region->begin; alt < region->end; alt++) {
int nr_inst;
+ if (!test_bit(alt->cpufeature, feature_mask))
+ continue;
+
/* Use ARM64_CB_PATCH as an unconditional patch */
if (alt->cpufeature < ARM64_CB_PATCH &&
!cpus_have_cap(alt->cpufeature))
@@ -192,6 +206,12 @@ static void __apply_alternatives(void *alt_region, bool is_module)
dsb(ish);
__flush_icache_all();
isb();
+
+ /* Ignore ARM64_CB bit from feature mask */
+ bitmap_or(applied_alternatives, applied_alternatives,
+ feature_mask, ARM64_NCAPS);
+ bitmap_and(applied_alternatives, applied_alternatives,
+ cpu_hwcaps, ARM64_NCAPS);
}
}
@@ -208,14 +228,19 @@ static int __apply_alternatives_multi_stop(void *unused)
/* We always have a CPU 0 at this point (__init) */
if (smp_processor_id()) {
- while (!READ_ONCE(alternatives_applied))
+ while (!READ_ONCE(all_alternatives_applied))
cpu_relax();
isb();
} else {
- BUG_ON(alternatives_applied);
- __apply_alternatives(&region, false);
+ DECLARE_BITMAP(remaining_capabilities, ARM64_NPATCHABLE);
+
+ bitmap_complement(remaining_capabilities, boot_capabilities,
+ ARM64_NPATCHABLE);
+
+ BUG_ON(all_alternatives_applied);
+ __apply_alternatives(&region, false, remaining_capabilities);
/* Barriers provided by the cache flushing */
- WRITE_ONCE(alternatives_applied, 1);
+ WRITE_ONCE(all_alternatives_applied, 1);
}
return 0;
@@ -227,6 +252,24 @@ void __init apply_alternatives_all(void)
stop_machine(__apply_alternatives_multi_stop, NULL, cpu_online_mask);
}
+/*
+ * This is called very early in the boot process (directly after we run
+ * a feature detect on the boot CPU). No need to worry about other CPUs
+ * here.
+ */
+void __init apply_boot_alternatives(void)
+{
+ struct alt_region region = {
+ .begin = (struct alt_instr *)__alt_instructions,
+ .end = (struct alt_instr *)__alt_instructions_end,
+ };
+
+ /* If called on non-boot cpu things could go wrong */
+ WARN_ON(smp_processor_id() != 0);
+
+ __apply_alternatives(&region, false, &boot_capabilities[0]);
+}
+
#ifdef CONFIG_MODULES
void apply_alternatives_module(void *start, size_t length)
{
@@ -234,7 +277,10 @@ void apply_alternatives_module(void *start, size_t length)
.begin = start,
.end = start + length,
};
+ DECLARE_BITMAP(all_capabilities, ARM64_NPATCHABLE);
+
+ bitmap_fill(all_capabilities, ARM64_NPATCHABLE);
- __apply_alternatives(&region, true);
+ __apply_alternatives(&region, true, &all_capabilities[0]);
}
#endif
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 65b8afc84466..7f40dcbdd51d 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -53,13 +53,9 @@ int main(void)
DEFINE(THREAD_CPU_CONTEXT, offsetof(struct task_struct, thread.cpu_context));
BLANK();
DEFINE(S_X0, offsetof(struct pt_regs, regs[0]));
- DEFINE(S_X1, offsetof(struct pt_regs, regs[1]));
DEFINE(S_X2, offsetof(struct pt_regs, regs[2]));
- DEFINE(S_X3, offsetof(struct pt_regs, regs[3]));
DEFINE(S_X4, offsetof(struct pt_regs, regs[4]));
- DEFINE(S_X5, offsetof(struct pt_regs, regs[5]));
DEFINE(S_X6, offsetof(struct pt_regs, regs[6]));
- DEFINE(S_X7, offsetof(struct pt_regs, regs[7]));
DEFINE(S_X8, offsetof(struct pt_regs, regs[8]));
DEFINE(S_X10, offsetof(struct pt_regs, regs[10]));
DEFINE(S_X12, offsetof(struct pt_regs, regs[12]));
@@ -73,14 +69,11 @@ int main(void)
DEFINE(S_X28, offsetof(struct pt_regs, regs[28]));
DEFINE(S_LR, offsetof(struct pt_regs, regs[30]));
DEFINE(S_SP, offsetof(struct pt_regs, sp));
-#ifdef CONFIG_COMPAT
- DEFINE(S_COMPAT_SP, offsetof(struct pt_regs, compat_sp));
-#endif
DEFINE(S_PSTATE, offsetof(struct pt_regs, pstate));
DEFINE(S_PC, offsetof(struct pt_regs, pc));
- DEFINE(S_ORIG_X0, offsetof(struct pt_regs, orig_x0));
DEFINE(S_SYSCALLNO, offsetof(struct pt_regs, syscallno));
DEFINE(S_ORIG_ADDR_LIMIT, offsetof(struct pt_regs, orig_addr_limit));
+ DEFINE(S_PMR_SAVE, offsetof(struct pt_regs, pmr_save));
DEFINE(S_STACKFRAME, offsetof(struct pt_regs, stackframe));
DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs));
BLANK();
@@ -93,7 +86,6 @@ int main(void)
BLANK();
DEFINE(PAGE_SZ, PAGE_SIZE);
BLANK();
- DEFINE(DMA_BIDIRECTIONAL, DMA_BIDIRECTIONAL);
DEFINE(DMA_TO_DEVICE, DMA_TO_DEVICE);
DEFINE(DMA_FROM_DEVICE, DMA_FROM_DEVICE);
BLANK();
@@ -110,25 +102,18 @@ int main(void)
BLANK();
DEFINE(VDSO_CS_CYCLE_LAST, offsetof(struct vdso_data, cs_cycle_last));
DEFINE(VDSO_RAW_TIME_SEC, offsetof(struct vdso_data, raw_time_sec));
- DEFINE(VDSO_RAW_TIME_NSEC, offsetof(struct vdso_data, raw_time_nsec));
DEFINE(VDSO_XTIME_CLK_SEC, offsetof(struct vdso_data, xtime_clock_sec));
- DEFINE(VDSO_XTIME_CLK_NSEC, offsetof(struct vdso_data, xtime_clock_nsec));
DEFINE(VDSO_XTIME_CRS_SEC, offsetof(struct vdso_data, xtime_coarse_sec));
DEFINE(VDSO_XTIME_CRS_NSEC, offsetof(struct vdso_data, xtime_coarse_nsec));
DEFINE(VDSO_WTM_CLK_SEC, offsetof(struct vdso_data, wtm_clock_sec));
- DEFINE(VDSO_WTM_CLK_NSEC, offsetof(struct vdso_data, wtm_clock_nsec));
DEFINE(VDSO_TB_SEQ_COUNT, offsetof(struct vdso_data, tb_seq_count));
DEFINE(VDSO_CS_MONO_MULT, offsetof(struct vdso_data, cs_mono_mult));
- DEFINE(VDSO_CS_RAW_MULT, offsetof(struct vdso_data, cs_raw_mult));
DEFINE(VDSO_CS_SHIFT, offsetof(struct vdso_data, cs_shift));
DEFINE(VDSO_TZ_MINWEST, offsetof(struct vdso_data, tz_minuteswest));
- DEFINE(VDSO_TZ_DSTTIME, offsetof(struct vdso_data, tz_dsttime));
DEFINE(VDSO_USE_SYSCALL, offsetof(struct vdso_data, use_syscall));
BLANK();
DEFINE(TVAL_TV_SEC, offsetof(struct timeval, tv_sec));
- DEFINE(TVAL_TV_USEC, offsetof(struct timeval, tv_usec));
DEFINE(TSPEC_TV_SEC, offsetof(struct timespec, tv_sec));
- DEFINE(TSPEC_TV_NSEC, offsetof(struct timespec, tv_nsec));
BLANK();
DEFINE(TZ_MINWEST, offsetof(struct timezone, tz_minuteswest));
DEFINE(TZ_DSTTIME, offsetof(struct timezone, tz_dsttime));
@@ -142,13 +127,9 @@ int main(void)
DEFINE(VCPU_WORKAROUND_FLAGS, offsetof(struct kvm_vcpu, arch.workaround_flags));
DEFINE(CPU_GP_REGS, offsetof(struct kvm_cpu_context, gp_regs));
DEFINE(CPU_USER_PT_REGS, offsetof(struct kvm_regs, regs));
- DEFINE(CPU_FP_REGS, offsetof(struct kvm_regs, fp_regs));
- DEFINE(VCPU_FPEXC32_EL2, offsetof(struct kvm_vcpu, arch.ctxt.sys_regs[FPEXC32_EL2]));
- DEFINE(VCPU_HOST_CONTEXT, offsetof(struct kvm_vcpu, arch.host_cpu_context));
DEFINE(HOST_CONTEXT_VCPU, offsetof(struct kvm_cpu_context, __hyp_running_vcpu));
#endif
#ifdef CONFIG_CPU_PM
- DEFINE(CPU_SUSPEND_SZ, sizeof(struct cpu_suspend_ctx));
DEFINE(CPU_CTX_SP, offsetof(struct cpu_suspend_ctx, sp));
DEFINE(MPIDR_HASH_MASK, offsetof(struct mpidr_hash, mask));
DEFINE(MPIDR_HASH_SHIFTS, offsetof(struct mpidr_hash, shift_aff));
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index f6d84e2c92fe..e24e94d28767 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -54,6 +54,9 @@ DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
EXPORT_SYMBOL(cpu_hwcaps);
static struct arm64_cpu_capabilities const __ro_after_init *cpu_hwcaps_ptrs[ARM64_NCAPS];
+/* Need also bit for ARM64_CB_PATCH */
+DECLARE_BITMAP(boot_capabilities, ARM64_NPATCHABLE);
+
/*
* Flag to indicate if we have computed the system wide
* capabilities based on the boot time active CPUs. This
@@ -1118,7 +1121,7 @@ static void cpu_copy_el2regs(const struct arm64_cpu_capabilities *__unused)
* that, freshly-onlined CPUs will set tpidr_el2, so we don't need to
* do anything here.
*/
- if (!alternatives_applied)
+ if (!alternative_is_applied(ARM64_HAS_VIRT_HOST_EXTN))
write_sysreg(read_sysreg(tpidr_el1), tpidr_el2);
}
#endif
@@ -1203,11 +1206,27 @@ static void cpu_enable_address_auth(struct arm64_cpu_capabilities const *cap)
}
#endif /* CONFIG_ARM64_PTR_AUTH */
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+static bool enable_pseudo_nmi;
+
+static int __init early_enable_pseudo_nmi(char *p)
+{
+ return strtobool(p, &enable_pseudo_nmi);
+}
+early_param("irqchip.gicv3_pseudo_nmi", early_enable_pseudo_nmi);
+
+static bool can_use_gic_priorities(const struct arm64_cpu_capabilities *entry,
+ int scope)
+{
+ return enable_pseudo_nmi && has_useable_gicv3_cpuif(entry, scope);
+}
+#endif
+
static const struct arm64_cpu_capabilities arm64_features[] = {
{
.desc = "GIC system register CPU interface",
.capability = ARM64_HAS_SYSREG_GIC_CPUIF,
- .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE,
.matches = has_useable_gicv3_cpuif,
.sys_reg = SYS_ID_AA64PFR0_EL1,
.field_pos = ID_AA64PFR0_GIC_SHIFT,
@@ -1480,6 +1499,21 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.matches = has_cpuid_feature,
},
#endif /* CONFIG_ARM64_PTR_AUTH */
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+ {
+ /*
+ * Depends on having GICv3
+ */
+ .desc = "IRQ priority masking",
+ .capability = ARM64_HAS_IRQ_PRIO_MASKING,
+ .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE,
+ .matches = can_use_gic_priorities,
+ .sys_reg = SYS_ID_AA64PFR0_EL1,
+ .field_pos = ID_AA64PFR0_GIC_SHIFT,
+ .sign = FTR_UNSIGNED,
+ .min_field_value = 1,
+ },
+#endif
{},
};
@@ -1654,6 +1688,9 @@ static void update_cpu_capabilities(u16 scope_mask)
if (caps->desc)
pr_info("detected: %s\n", caps->desc);
cpus_set_cap(caps->capability);
+
+ if ((scope_mask & SCOPE_BOOT_CPU) && (caps->type & SCOPE_BOOT_CPU))
+ set_bit(caps->capability, boot_capabilities);
}
}
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 0ec0c46b2c0c..c50a7a75f2e0 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -185,7 +185,7 @@ alternative_cb_end
.else
add x21, sp, #S_FRAME_SIZE
- get_thread_info tsk
+ get_current_task tsk
/* Save the task's original addr_limit and set USER_DS */
ldr x20, [tsk, #TSK_TI_ADDR_LIMIT]
str x20, [sp, #S_ORIG_ADDR_LIMIT]
@@ -249,6 +249,12 @@ alternative_else_nop_endif
msr sp_el0, tsk
.endif
+ /* Save pmr */
+alternative_if ARM64_HAS_IRQ_PRIO_MASKING
+ mrs_s x20, SYS_ICC_PMR_EL1
+ str x20, [sp, #S_PMR_SAVE]
+alternative_else_nop_endif
+
/*
* Registers that may be useful after this macro is invoked:
*
@@ -269,6 +275,14 @@ alternative_else_nop_endif
/* No need to restore UAO, it will be restored from SPSR_EL1 */
.endif
+ /* Restore pmr */
+alternative_if ARM64_HAS_IRQ_PRIO_MASKING
+ ldr x20, [sp, #S_PMR_SAVE]
+ msr_s SYS_ICC_PMR_EL1, x20
+ /* Ensure priority change is seen by redistributor */
+ dsb sy
+alternative_else_nop_endif
+
ldp x21, x22, [sp, #S_PC] // load ELR, SPSR
.if \el == 0
ct_user_enter
@@ -603,32 +617,52 @@ el1_irq:
kernel_entry 1
enable_da_f
#ifdef CONFIG_TRACE_IRQFLAGS
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+alternative_if ARM64_HAS_IRQ_PRIO_MASKING
+ ldr x20, [sp, #S_PMR_SAVE]
+alternative_else
+ mov x20, #GIC_PRIO_IRQON
+alternative_endif
+ cmp x20, #GIC_PRIO_IRQOFF
+ /* Irqs were disabled, don't trace */
+ b.ls 1f
+#endif
bl trace_hardirqs_off
+1:
#endif
irq_handler
#ifdef CONFIG_PREEMPT
ldr x24, [tsk, #TSK_TI_PREEMPT] // get preempt count
- cbnz x24, 1f // preempt count != 0
- bl el1_preempt
+alternative_if ARM64_HAS_IRQ_PRIO_MASKING
+ /*
+ * DA_F were cleared at start of handling. If anything is set in DAIF,
+ * we come back from an NMI, so skip preemption
+ */
+ mrs x0, daif
+ orr x24, x24, x0
+alternative_else_nop_endif
+ cbnz x24, 1f // preempt count != 0 || NMI return path
+ bl preempt_schedule_irq // irq en/disable is done inside
1:
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
+#ifdef CONFIG_ARM64_PSEUDO_NMI
+ /*
+ * if IRQs were disabled when we received the interrupt, we have an NMI
+ * and we are not re-enabling interrupt upon eret. Skip tracing.
+ */
+ cmp x20, #GIC_PRIO_IRQOFF
+ b.ls 1f
+#endif
bl trace_hardirqs_on
+1:
#endif
+
kernel_exit 1
ENDPROC(el1_irq)
-#ifdef CONFIG_PREEMPT
-el1_preempt:
- mov x24, lr
-1: bl preempt_schedule_irq // irq en/disable is done inside
- ldr x0, [tsk, #TSK_TI_FLAGS] // get new tasks TI_FLAGS
- tbnz x0, #TIF_NEED_RESCHED, 1b // needs rescheduling?
- ret x24
-#endif
-
/*
* EL0 mode handlers.
*/
@@ -1070,7 +1104,7 @@ ENTRY(ret_from_fork)
cbz x19, 1f // not a kernel thread
mov x0, x20
blr x19
-1: get_thread_info tsk
+1: get_current_task tsk
b ret_to_user
ENDPROC(ret_from_fork)
NOKPROBE(ret_from_fork)
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 780a12f59a8f..92fa81798fb9 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -33,6 +33,9 @@
unsigned long irq_err_count;
+/* Only access this in an NMI enter/exit */
+DEFINE_PER_CPU(struct nmi_ctx, nmi_contexts);
+
DEFINE_PER_CPU(unsigned long *, irq_stack_ptr);
int arch_show_interrupts(struct seq_file *p, int prec)
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index ce46c4cdf368..691854b77c7f 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -244,27 +244,33 @@ int kgdb_arch_handle_exception(int exception_vector, int signo,
static int kgdb_brk_fn(struct pt_regs *regs, unsigned int esr)
{
+ if (user_mode(regs))
+ return DBG_HOOK_ERROR;
+
kgdb_handle_exception(1, SIGTRAP, 0, regs);
- return 0;
+ return DBG_HOOK_HANDLED;
}
NOKPROBE_SYMBOL(kgdb_brk_fn)
static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr)
{
+ if (user_mode(regs))
+ return DBG_HOOK_ERROR;
+
compiled_break = 1;
kgdb_handle_exception(1, SIGTRAP, 0, regs);
- return 0;
+ return DBG_HOOK_HANDLED;
}
NOKPROBE_SYMBOL(kgdb_compiled_brk_fn);
static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
{
- if (!kgdb_single_step)
+ if (user_mode(regs) || !kgdb_single_step)
return DBG_HOOK_ERROR;
kgdb_handle_exception(1, SIGTRAP, 0, regs);
- return 0;
+ return DBG_HOOK_HANDLED;
}
NOKPROBE_SYMBOL(kgdb_step_brk_fn);
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 1620a371b1f5..4addb38bc250 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -810,7 +810,7 @@ static void armv8pmu_clear_event_idx(struct pmu_hw_events *cpuc,
}
/*
- * Add an event filter to a given event. This will only work for PMUv2 PMUs.
+ * Add an event filter to a given event.
*/
static int armv8pmu_set_event_filter(struct hw_perf_event *event,
struct perf_event_attr *attr)
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index f17afb99890c..7fb6f3aa5ceb 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -450,6 +450,9 @@ kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
int retval;
+ if (user_mode(regs))
+ return DBG_HOOK_ERROR;
+
/* return error if this is not our step */
retval = kprobe_ss_hit(kcb, instruction_pointer(regs));
@@ -466,6 +469,9 @@ kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
int __kprobes
kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr)
{
+ if (user_mode(regs))
+ return DBG_HOOK_ERROR;
+
kprobe_handler(regs);
return DBG_HOOK_HANDLED;
}
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index a0f985a6ac50..3767fb21a5b8 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -51,6 +51,7 @@
#include <linux/thread_info.h>
#include <asm/alternative.h>
+#include <asm/arch_gicv3.h>
#include <asm/compat.h>
#include <asm/cacheflush.h>
#include <asm/exec.h>
@@ -74,6 +75,50 @@ EXPORT_SYMBOL_GPL(pm_power_off);
void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
+static void __cpu_do_idle(void)
+{
+ dsb(sy);
+ wfi();
+}
+
+static void __cpu_do_idle_irqprio(void)
+{
+ unsigned long pmr;
+ unsigned long daif_bits;
+
+ daif_bits = read_sysreg(daif);
+ write_sysreg(daif_bits | PSR_I_BIT, daif);
+
+ /*
+ * Unmask PMR before going idle to make sure interrupts can
+ * be raised.
+ */
+ pmr = gic_read_pmr();
+ gic_write_pmr(GIC_PRIO_IRQON);
+
+ __cpu_do_idle();
+
+ gic_write_pmr(pmr);
+ write_sysreg(daif_bits, daif);
+}
+
+/*
+ * cpu_do_idle()
+ *
+ * Idle the processor (wait for interrupt).
+ *
+ * If the CPU supports priority masking we must do additional work to
+ * ensure that interrupts are not masked at the PMR (because the core will
+ * not wake up if we block the wake up signal in the interrupt controller).
+ */
+void cpu_do_idle(void)
+{
+ if (system_uses_irq_prio_masking())
+ __cpu_do_idle_irqprio();
+ else
+ __cpu_do_idle();
+}
+
/*
* This is our default idle handler.
*/
@@ -232,6 +277,9 @@ void __show_regs(struct pt_regs *regs)
printk("sp : %016llx\n", sp);
+ if (system_uses_irq_prio_masking())
+ printk("pmr_save: %08llx\n", regs->pmr_save);
+
i = top_reg;
while (i >= 0) {
@@ -363,6 +411,9 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE)
childregs->pstate |= PSR_SSBS_BIT;
+ if (system_uses_irq_prio_masking())
+ childregs->pmr_save = GIC_PRIO_IRQON;
+
p->thread.cpu_context.x19 = stack_start;
p->thread.cpu_context.x20 = stk_sz;
}
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index ddaea0fd2fa4..b82e0a9b3da3 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -979,6 +979,131 @@ static int pac_mask_get(struct task_struct *target,
return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &uregs, 0, -1);
}
+
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static __uint128_t pac_key_to_user(const struct ptrauth_key *key)
+{
+ return (__uint128_t)key->hi << 64 | key->lo;
+}
+
+static struct ptrauth_key pac_key_from_user(__uint128_t ukey)
+{
+ struct ptrauth_key key = {
+ .lo = (unsigned long)ukey,
+ .hi = (unsigned long)(ukey >> 64),
+ };
+
+ return key;
+}
+
+static void pac_address_keys_to_user(struct user_pac_address_keys *ukeys,
+ const struct ptrauth_keys *keys)
+{
+ ukeys->apiakey = pac_key_to_user(&keys->apia);
+ ukeys->apibkey = pac_key_to_user(&keys->apib);
+ ukeys->apdakey = pac_key_to_user(&keys->apda);
+ ukeys->apdbkey = pac_key_to_user(&keys->apdb);
+}
+
+static void pac_address_keys_from_user(struct ptrauth_keys *keys,
+ const struct user_pac_address_keys *ukeys)
+{
+ keys->apia = pac_key_from_user(ukeys->apiakey);
+ keys->apib = pac_key_from_user(ukeys->apibkey);
+ keys->apda = pac_key_from_user(ukeys->apdakey);
+ keys->apdb = pac_key_from_user(ukeys->apdbkey);
+}
+
+static int pac_address_keys_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ struct ptrauth_keys *keys = &target->thread.keys_user;
+ struct user_pac_address_keys user_keys;
+
+ if (!system_supports_address_auth())
+ return -EINVAL;
+
+ pac_address_keys_to_user(&user_keys, keys);
+
+ return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+ &user_keys, 0, -1);
+}
+
+static int pac_address_keys_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct ptrauth_keys *keys = &target->thread.keys_user;
+ struct user_pac_address_keys user_keys;
+ int ret;
+
+ if (!system_supports_address_auth())
+ return -EINVAL;
+
+ pac_address_keys_to_user(&user_keys, keys);
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &user_keys, 0, -1);
+ if (ret)
+ return ret;
+ pac_address_keys_from_user(keys, &user_keys);
+
+ return 0;
+}
+
+static void pac_generic_keys_to_user(struct user_pac_generic_keys *ukeys,
+ const struct ptrauth_keys *keys)
+{
+ ukeys->apgakey = pac_key_to_user(&keys->apga);
+}
+
+static void pac_generic_keys_from_user(struct ptrauth_keys *keys,
+ const struct user_pac_generic_keys *ukeys)
+{
+ keys->apga = pac_key_from_user(ukeys->apgakey);
+}
+
+static int pac_generic_keys_get(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ void *kbuf, void __user *ubuf)
+{
+ struct ptrauth_keys *keys = &target->thread.keys_user;
+ struct user_pac_generic_keys user_keys;
+
+ if (!system_supports_generic_auth())
+ return -EINVAL;
+
+ pac_generic_keys_to_user(&user_keys, keys);
+
+ return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+ &user_keys, 0, -1);
+}
+
+static int pac_generic_keys_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct ptrauth_keys *keys = &target->thread.keys_user;
+ struct user_pac_generic_keys user_keys;
+ int ret;
+
+ if (!system_supports_generic_auth())
+ return -EINVAL;
+
+ pac_generic_keys_to_user(&user_keys, keys);
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &user_keys, 0, -1);
+ if (ret)
+ return ret;
+ pac_generic_keys_from_user(keys, &user_keys);
+
+ return 0;
+}
+#endif /* CONFIG_CHECKPOINT_RESTORE */
#endif /* CONFIG_ARM64_PTR_AUTH */
enum aarch64_regset {
@@ -995,6 +1120,10 @@ enum aarch64_regset {
#endif
#ifdef CONFIG_ARM64_PTR_AUTH
REGSET_PAC_MASK,
+#ifdef CONFIG_CHECKPOINT_RESTORE
+ REGSET_PACA_KEYS,
+ REGSET_PACG_KEYS,
+#endif
#endif
};
@@ -1074,6 +1203,24 @@ static const struct user_regset aarch64_regsets[] = {
.get = pac_mask_get,
/* this cannot be set dynamically */
},
+#ifdef CONFIG_CHECKPOINT_RESTORE
+ [REGSET_PACA_KEYS] = {
+ .core_note_type = NT_ARM_PACA_KEYS,
+ .n = sizeof(struct user_pac_address_keys) / sizeof(__uint128_t),
+ .size = sizeof(__uint128_t),
+ .align = sizeof(__uint128_t),
+ .get = pac_address_keys_get,
+ .set = pac_address_keys_set,
+ },
+ [REGSET_PACG_KEYS] = {
+ .core_note_type = NT_ARM_PACG_KEYS,
+ .n = sizeof(struct user_pac_generic_keys) / sizeof(__uint128_t),
+ .size = sizeof(__uint128_t),
+ .align = sizeof(__uint128_t),
+ .get = pac_generic_keys_get,
+ .set = pac_generic_keys_set,
+ },
+#endif
#endif
};
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 009849328289..834b321a88f8 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -58,7 +58,6 @@
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/traps.h>
-#include <asm/memblock.h>
#include <asm/efi.h>
#include <asm/xen/hypervisor.h>
#include <asm/mmu_context.h>
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 1598d6f7200a..824de7038967 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -35,6 +35,7 @@
#include <linux/smp.h>
#include <linux/seq_file.h>
#include <linux/irq.h>
+#include <linux/irqchip/arm-gic-v3.h>
#include <linux/percpu.h>
#include <linux/clockchips.h>
#include <linux/completion.h>
@@ -180,6 +181,24 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
return ret;
}
+static void init_gic_priority_masking(void)
+{
+ u32 cpuflags;
+
+ if (WARN_ON(!gic_enable_sre()))
+ return;
+
+ cpuflags = read_sysreg(daif);
+
+ WARN_ON(!(cpuflags & PSR_I_BIT));
+
+ gic_write_pmr(GIC_PRIO_IRQOFF);
+
+ /* We can only unmask PSR.I if we can take aborts */
+ if (!(cpuflags & PSR_A_BIT))
+ write_sysreg(cpuflags & ~PSR_I_BIT, daif);
+}
+
/*
* This is the secondary CPU boot entry. We're using this CPUs
* idle thread stack, but a set of temporary page tables.
@@ -206,6 +225,9 @@ asmlinkage notrace void secondary_start_kernel(void)
*/
cpu_uninstall_idmap();
+ if (system_uses_irq_prio_masking())
+ init_gic_priority_masking();
+
preempt_disable();
trace_hardirqs_off();
@@ -419,6 +441,17 @@ void __init smp_prepare_boot_cpu(void)
*/
jump_label_init();
cpuinfo_store_boot_cpu();
+
+ /*
+ * We now know enough about the boot CPU to apply the
+ * alternatives that cannot wait until interrupt handling
+ * and/or scheduling is enabled.
+ */
+ apply_boot_alternatives();
+
+ /* Conditionally switch to GIC PMR for interrupt masking */
+ if (system_uses_irq_prio_masking())
+ init_gic_priority_masking();
}
static u64 __init of_get_cpu_mpidr(struct device_node *dn)
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 4e2fb877f8d5..8ad119c3f665 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -898,13 +898,17 @@ bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr)
asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr)
{
- nmi_enter();
+ const bool was_in_nmi = in_nmi();
+
+ if (!was_in_nmi)
+ nmi_enter();
/* non-RAS errors are not containable */
if (!arm64_is_ras_serror(esr) || arm64_is_fatal_ras_serror(regs, esr))
arm64_serror_panic(regs, esr);
- nmi_exit();
+ if (!was_in_nmi)
+ nmi_exit();
}
void __pte_error(const char *file, int line, unsigned long val)
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 421ebf6f7086..3563fe655cd5 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -22,6 +22,7 @@
#include <kvm/arm_psci.h>
+#include <asm/arch_gicv3.h>
#include <asm/cpufeature.h>
#include <asm/kprobes.h>
#include <asm/kvm_asm.h>
@@ -525,6 +526,17 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
struct kvm_cpu_context *guest_ctxt;
u64 exit_code;
+ /*
+ * Having IRQs masked via PMR when entering the guest means the GIC
+ * will not signal the CPU of interrupts of lower priority, and the
+ * only way to get out will be via guest exceptions.
+ * Naturally, we want to avoid this.
+ */
+ if (system_uses_irq_prio_masking()) {
+ gic_write_pmr(GIC_PRIO_IRQON);
+ dsb(sy);
+ }
+
vcpu = kern_hyp_va(vcpu);
host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
@@ -577,6 +589,10 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu)
*/
__debug_switch_to_host(vcpu);
+ /* Returning to host will clear PSR.I, remask PMR if needed */
+ if (system_uses_irq_prio_masking())
+ gic_write_pmr(GIC_PRIO_IRQOFF);
+
return exit_code;
}
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index 99bb8facb5cb..14fe23cd5932 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -406,7 +406,7 @@ void ptdump_check_wx(void)
static int ptdump_init(void)
{
ptdump_initialize();
- return ptdump_debugfs_register(&kernel_ptdump_info,
- "kernel_page_tables");
+ ptdump_debugfs_register(&kernel_ptdump_info, "kernel_page_tables");
+ return 0;
}
device_initcall(ptdump_init);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index e1c84c2e1cab..1a7e92ab69eb 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -810,11 +810,12 @@ void __init hook_debug_fault_code(int nr,
debug_fault_info[nr].name = name;
}
-asmlinkage int __exception do_debug_exception(unsigned long addr,
+asmlinkage int __exception do_debug_exception(unsigned long addr_if_watchpoint,
unsigned int esr,
struct pt_regs *regs)
{
const struct fault_info *inf = esr_to_debug_fault_info(esr);
+ unsigned long pc = instruction_pointer(regs);
int rv;
/*
@@ -824,14 +825,14 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
if (interrupts_enabled(regs))
trace_hardirqs_off();
- if (user_mode(regs) && !is_ttbr0_addr(instruction_pointer(regs)))
+ if (user_mode(regs) && !is_ttbr0_addr(pc))
arm64_apply_bp_hardening();
- if (!inf->fn(addr, esr, regs)) {
+ if (!inf->fn(addr_if_watchpoint, esr, regs)) {
rv = 1;
} else {
arm64_notify_die(inf->name, regs,
- inf->sig, inf->code, (void __user *)addr, esr);
+ inf->sig, inf->code, (void __user *)pc, esr);
rv = 0;
}
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index c38976b70069..6bc135042f5e 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -260,24 +260,6 @@ int pfn_valid(unsigned long pfn)
}
EXPORT_SYMBOL(pfn_valid);
-#ifndef CONFIG_SPARSEMEM
-static void __init arm64_memory_present(void)
-{
-}
-#else
-static void __init arm64_memory_present(void)
-{
- struct memblock_region *reg;
-
- for_each_memblock(memory, reg) {
- int nid = memblock_get_region_node(reg);
-
- memory_present(nid, memblock_region_memory_base_pfn(reg),
- memblock_region_memory_end_pfn(reg));
- }
-}
-#endif
-
static phys_addr_t memory_limit = PHYS_ADDR_MAX;
/*
@@ -464,7 +446,7 @@ void __init bootmem_init(void)
* Sparsemem tries to allocate bootmem in memory_present(), so must be
* done after the fixed reservations.
*/
- arm64_memory_present();
+ memblocks_present();
sparse_init();
zone_sizes_init(min, max);
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index b6f5aa52ac67..402b6495ff58 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -42,7 +42,6 @@
#include <asm/setup.h>
#include <asm/sizes.h>
#include <asm/tlb.h>
-#include <asm/memblock.h>
#include <asm/mmu_context.h>
#include <asm/ptdump.h>
#include <asm/tlbflush.h>
@@ -655,10 +654,6 @@ static void __init map_kernel(pgd_t *pgdp)
kasan_copy_shadow(pgdp);
}
-/*
- * paging_init() sets up the page tables, initialises the zone memory
- * maps and sets up the zero page.
- */
void __init paging_init(void)
{
pgd_t *pgdp = pgd_set_fixmap(__pa_symbol(swapper_pg_dir));
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 73886a5f1f30..aa0817c9c4c3 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -55,17 +55,6 @@
#define MAIR(attr, mt) ((attr) << ((mt) * 8))
-/*
- * cpu_do_idle()
- *
- * Idle the processor (wait for interrupt).
- */
-ENTRY(cpu_do_idle)
- dsb sy // WFI may enter a low-power mode
- wfi
- ret
-ENDPROC(cpu_do_idle)
-
#ifdef CONFIG_CPU_PM
/**
* cpu_do_suspend - save CPU registers context
@@ -456,6 +445,7 @@ ENTRY(__cpu_setup)
ldr 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
#ifdef CONFIG_ARM64_USER_VA_BITS_52
ldr_l x9, vabits_user
diff --git a/arch/arm64/mm/ptdump_debugfs.c b/arch/arm64/mm/ptdump_debugfs.c
index 24d786fc3a4c..064163f25592 100644
--- a/arch/arm64/mm/ptdump_debugfs.c
+++ b/arch/arm64/mm/ptdump_debugfs.c
@@ -12,10 +12,7 @@ static int ptdump_show(struct seq_file *m, void *v)
}
DEFINE_SHOW_ATTRIBUTE(ptdump);
-int ptdump_debugfs_register(struct ptdump_info *info, const char *name)
+void ptdump_debugfs_register(struct ptdump_info *info, const char *name)
{
- struct dentry *pe;
- pe = debugfs_create_file(name, 0400, NULL, info, &ptdump_fops);
- return pe ? 0 : -ENOMEM;
-
+ debugfs_create_file(name, 0400, NULL, info, &ptdump_fops);
}
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
index b269451e7e85..1d9c1376dc64 100644
--- a/arch/riscv/include/asm/io.h
+++ b/arch/riscv/include/asm/io.h
@@ -163,20 +163,20 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
* doesn't define any ordering between the memory space and the I/O space.
*/
#define __io_br() do {} while (0)
-#define __io_ar() __asm__ __volatile__ ("fence i,r" : : : "memory");
+#define __io_ar(v) __asm__ __volatile__ ("fence i,r" : : : "memory");
#define __io_bw() __asm__ __volatile__ ("fence w,o" : : : "memory");
#define __io_aw() do {} while (0)
-#define readb(c) ({ u8 __v; __io_br(); __v = readb_cpu(c); __io_ar(); __v; })
-#define readw(c) ({ u16 __v; __io_br(); __v = readw_cpu(c); __io_ar(); __v; })
-#define readl(c) ({ u32 __v; __io_br(); __v = readl_cpu(c); __io_ar(); __v; })
+#define readb(c) ({ u8 __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; })
+#define readw(c) ({ u16 __v; __io_br(); __v = readw_cpu(c); __io_ar(__v); __v; })
+#define readl(c) ({ u32 __v; __io_br(); __v = readl_cpu(c); __io_ar(__v); __v; })
#define writeb(v,c) ({ __io_bw(); writeb_cpu((v),(c)); __io_aw(); })
#define writew(v,c) ({ __io_bw(); writew_cpu((v),(c)); __io_aw(); })
#define writel(v,c) ({ __io_bw(); writel_cpu((v),(c)); __io_aw(); })
#ifdef CONFIG_64BIT
-#define readq(c) ({ u64 __v; __io_br(); __v = readq_cpu(c); __io_ar(); __v; })
+#define readq(c) ({ u64 __v; __io_br(); __v = readq_cpu(c); __io_ar(__v); __v; })
#define writeq(v,c) ({ __io_bw(); writeq_cpu((v),(c)); __io_aw(); })
#endif
@@ -198,20 +198,20 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
* writes.
*/
#define __io_pbr() __asm__ __volatile__ ("fence io,i" : : : "memory");
-#define __io_par() __asm__ __volatile__ ("fence i,ior" : : : "memory");
+#define __io_par(v) __asm__ __volatile__ ("fence i,ior" : : : "memory");
#define __io_pbw() __asm__ __volatile__ ("fence iow,o" : : : "memory");
#define __io_paw() __asm__ __volatile__ ("fence o,io" : : : "memory");
-#define inb(c) ({ u8 __v; __io_pbr(); __v = readb_cpu((void*)(PCI_IOBASE + (c))); __io_par(); __v; })
-#define inw(c) ({ u16 __v; __io_pbr(); __v = readw_cpu((void*)(PCI_IOBASE + (c))); __io_par(); __v; })
-#define inl(c) ({ u32 __v; __io_pbr(); __v = readl_cpu((void*)(PCI_IOBASE + (c))); __io_par(); __v; })
+#define inb(c) ({ u8 __v; __io_pbr(); __v = readb_cpu((void*)(PCI_IOBASE + (c))); __io_par(__v); __v; })
+#define inw(c) ({ u16 __v; __io_pbr(); __v = readw_cpu((void*)(PCI_IOBASE + (c))); __io_par(__v); __v; })
+#define inl(c) ({ u32 __v; __io_pbr(); __v = readl_cpu((void*)(PCI_IOBASE + (c))); __io_par(__v); __v; })
#define outb(v,c) ({ __io_pbw(); writeb_cpu((v),(void*)(PCI_IOBASE + (c))); __io_paw(); })
#define outw(v,c) ({ __io_pbw(); writew_cpu((v),(void*)(PCI_IOBASE + (c))); __io_paw(); })
#define outl(v,c) ({ __io_pbw(); writel_cpu((v),(void*)(PCI_IOBASE + (c))); __io_paw(); })
#ifdef CONFIG_64BIT
-#define inq(c) ({ u64 __v; __io_pbr(); __v = readq_cpu((void*)(c)); __io_par(); __v; })
+#define inq(c) ({ u64 __v; __io_pbr(); __v = readq_cpu((void*)(c)); __io_par(__v); __v; })
#define outq(v,c) ({ __io_pbw(); writeq_cpu((v),(void*)(c)); __io_paw(); })
#endif
@@ -254,16 +254,16 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
afence; \
}
-__io_reads_ins(reads, u8, b, __io_br(), __io_ar())
-__io_reads_ins(reads, u16, w, __io_br(), __io_ar())
-__io_reads_ins(reads, u32, l, __io_br(), __io_ar())
+__io_reads_ins(reads, u8, b, __io_br(), __io_ar(addr))
+__io_reads_ins(reads, u16, w, __io_br(), __io_ar(addr))
+__io_reads_ins(reads, u32, l, __io_br(), __io_ar(addr))
#define readsb(addr, buffer, count) __readsb(addr, buffer, count)
#define readsw(addr, buffer, count) __readsw(addr, buffer, count)
#define readsl(addr, buffer, count) __readsl(addr, buffer, count)
-__io_reads_ins(ins, u8, b, __io_pbr(), __io_par())
-__io_reads_ins(ins, u16, w, __io_pbr(), __io_par())
-__io_reads_ins(ins, u32, l, __io_pbr(), __io_par())
+__io_reads_ins(ins, u8, b, __io_pbr(), __io_par(addr))
+__io_reads_ins(ins, u16, w, __io_pbr(), __io_par(addr))
+__io_reads_ins(ins, u32, l, __io_pbr(), __io_par(addr))
#define insb(addr, buffer, count) __insb((void __iomem *)(long)addr, buffer, count)
#define insw(addr, buffer, count) __insw((void __iomem *)(long)addr, buffer, count)
#define insl(addr, buffer, count) __insl((void __iomem *)(long)addr, buffer, count)
@@ -283,10 +283,10 @@ __io_writes_outs(outs, u32, l, __io_pbw(), __io_paw())
#define outsl(addr, buffer, count) __outsl((void __iomem *)(long)addr, buffer, count)
#ifdef CONFIG_64BIT
-__io_reads_ins(reads, u64, q, __io_br(), __io_ar())
+__io_reads_ins(reads, u64, q, __io_br(), __io_ar(addr))
#define readsq(addr, buffer, count) __readsq(addr, buffer, count)
-__io_reads_ins(ins, u64, q, __io_pbr(), __io_par())
+__io_reads_ins(ins, u64, q, __io_pbr(), __io_par(addr))
#define insq(addr, buffer, count) __insq((void __iomem *)addr, buffer, count)
__io_writes_outs(writes, u64, q, __io_bw(), __io_aw())