summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/Kconfig9
-rw-r--r--arch/arm/Kconfig1
-rw-r--r--arch/arm/Makefile4
-rw-r--r--arch/arm/boot/compressed/Makefile4
-rw-r--r--arch/arm/configs/omap2plus_defconfig1
-rw-r--r--arch/arm64/Kconfig1
-rw-r--r--arch/arm64/Makefile4
-rw-r--r--arch/arm64/include/asm/daifflags.h3
-rw-r--r--arch/arm64/include/asm/exception.h5
-rw-r--r--arch/arm64/include/asm/ptrace.h4
-rw-r--r--arch/arm64/include/asm/sysreg.h2
-rw-r--r--arch/arm64/kernel/entry-common.c254
-rw-r--r--arch/arm64/kernel/entry.S78
-rw-r--r--arch/arm64/kernel/irq.c15
-rw-r--r--arch/arm64/kernel/process.c8
-rw-r--r--arch/arm64/kernel/sdei.c7
-rw-r--r--arch/arm64/kernel/syscall.c1
-rw-r--r--arch/arm64/kernel/traps.c22
-rw-r--r--arch/arm64/mm/fault.c25
-rw-r--r--arch/powerpc/Kconfig1
-rw-r--r--arch/powerpc/Makefile1
-rw-r--r--arch/powerpc/include/asm/book3s/64/mmu.h12
-rw-r--r--arch/powerpc/kvm/book3s_xive.c7
-rw-r--r--arch/powerpc/mm/book3s64/hash_native.c23
-rw-r--r--arch/powerpc/mm/book3s64/mmu_context.c20
-rw-r--r--arch/powerpc/mm/numa.c3
-rw-r--r--arch/powerpc/platforms/powermac/smp.c2
-rw-r--r--arch/powerpc/platforms/powernv/setup.c9
-rw-r--r--arch/powerpc/platforms/powernv/smp.c3
-rw-r--r--arch/powerpc/platforms/pseries/hotplug-cpu.c3
-rw-r--r--arch/powerpc/platforms/pseries/msi.c3
-rw-r--r--arch/s390/kernel/entry.S15
-rw-r--r--arch/s390/lib/delay.c5
-rw-r--r--arch/s390/pci/pci_irq.c14
-rw-r--r--arch/x86/Kconfig1
-rw-r--r--arch/x86/Makefile3
-rw-r--r--arch/x86/boot/compressed/Makefile4
-rw-r--r--arch/x86/boot/compressed/sev-es.c5
-rw-r--r--arch/x86/events/intel/ds.c4
-rw-r--r--arch/x86/include/asm/insn.h15
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c2
-rw-r--r--arch/x86/kernel/cpu/resctrl/core.c4
-rw-r--r--arch/x86/kernel/cpu/resctrl/internal.h3
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c9
-rw-r--r--arch/x86/kernel/uprobes.c10
-rw-r--r--arch/x86/lib/insn-eval.c10
46 files changed, 387 insertions, 252 deletions
diff --git a/arch/Kconfig b/arch/Kconfig
index 56b6ccc0e32d..ba4e966484ab 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1028,6 +1028,15 @@ config HAVE_STATIC_CALL_INLINE
bool
depends on HAVE_STATIC_CALL
+config ARCH_WANT_LD_ORPHAN_WARN
+ bool
+ help
+ An arch should select this symbol once all linker sections are explicitly
+ included, size-asserted, or discarded in the linker scripts. This is
+ important because we never want expected sections to be placed heuristically
+ by the linker, since the locations of such sections can change between linker
+ versions.
+
source "kernel/gcov/Kconfig"
source "scripts/gcc-plugins/Kconfig"
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index fe2f17eb2b50..002e0cf025f5 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -35,6 +35,7 @@ config ARM
select ARCH_USE_CMPXCHG_LOCKREF
select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
select ARCH_WANT_IPC_PARSE_VERSION
+ select ARCH_WANT_LD_ORPHAN_WARN
select BINFMT_FLAT_ARGVP_ENVP_ON_STACK
select BUILDTIME_TABLE_SORT if MMU
select CLONE_BACKWARDS
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 4d76eab2b22d..e15f76ca2887 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -16,10 +16,6 @@ LDFLAGS_vmlinux += --be8
KBUILD_LDFLAGS_MODULE += --be8
endif
-# We never want expected sections to be placed heuristically by the
-# linker. All sections should be explicitly named in the linker script.
-LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn)
-
GZFLAGS :=-9
#KBUILD_CFLAGS +=-pipe
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 47f001ca5499..e1567418a2b1 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -129,7 +129,9 @@ LDFLAGS_vmlinux += --no-undefined
# Delete all temporary local symbols
LDFLAGS_vmlinux += -X
# Report orphan sections
-LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn)
+ifdef CONFIG_LD_ORPHAN_WARN
+LDFLAGS_vmlinux += --orphan-handling=warn
+endif
# Next argument is a linker script
LDFLAGS_vmlinux += -T
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 34793aabdb65..58df9fd79a76 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -81,7 +81,6 @@ CONFIG_PARTITION_ADVANCED=y
CONFIG_BINFMT_MISC=y
CONFIG_CMA=y
CONFIG_ZSMALLOC=m
-CONFIG_ZSMALLOC_PGTABLE_MAPPING=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1515f6f153a0..a6b5b7ef40ae 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -81,6 +81,7 @@ config ARM64
select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
select ARCH_WANT_FRAME_POINTERS
select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36)
+ select ARCH_WANT_LD_ORPHAN_WARN
select ARCH_HAS_UBSAN_SANITIZE_ALL
select ARM_AMBA
select ARM_ARCH_TIMER
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 5789c2d18d43..6a87d592bd00 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -28,10 +28,6 @@ LDFLAGS_vmlinux += --fix-cortex-a53-843419
endif
endif
-# We never want expected sections to be placed heuristically by the
-# linker. All sections should be explicitly named in the linker script.
-LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn)
-
ifeq ($(CONFIG_ARM64_USE_LSE_ATOMICS), y)
ifneq ($(CONFIG_ARM64_LSE_ATOMICS), y)
$(warning LSE atomics not supported by binutils)
diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h
index ec213b4a1650..1c26d7baa67f 100644
--- a/arch/arm64/include/asm/daifflags.h
+++ b/arch/arm64/include/asm/daifflags.h
@@ -128,6 +128,9 @@ static inline void local_daif_inherit(struct pt_regs *regs)
{
unsigned long flags = regs->pstate & DAIF_MASK;
+ if (interrupts_enabled(regs))
+ trace_hardirqs_on();
+
/*
* We can't use local_daif_restore(regs->pstate) here as
* system_has_prio_mask_debugging() won't restore the I bit if it can
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index 99b9383cd036..0756191f44f6 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -31,7 +31,12 @@ static inline u32 disr_to_esr(u64 disr)
return esr;
}
+asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs);
+asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs);
asmlinkage void enter_from_user_mode(void);
+asmlinkage void exit_to_user_mode(void);
+void arm64_enter_nmi(struct pt_regs *regs);
+void arm64_exit_nmi(struct pt_regs *regs);
void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
void do_undefinstr(struct pt_regs *regs);
void do_bti(struct pt_regs *regs);
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 997cf8c8cd52..28c85b87b8cd 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -193,6 +193,10 @@ struct pt_regs {
/* Only valid when ARM64_HAS_IRQ_PRIO_MASKING is enabled. */
u64 pmr_save;
u64 stackframe[2];
+
+ /* Only valid for some EL1 exceptions. */
+ u64 lockdep_hardirqs;
+ u64 exit_rcu;
};
static inline bool in_syscall(struct pt_regs const *regs)
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index e2ef4c2edf06..801861d05426 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -987,7 +987,7 @@
#define SYS_TFSR_EL1_TF0_SHIFT 0
#define SYS_TFSR_EL1_TF1_SHIFT 1
#define SYS_TFSR_EL1_TF0 (UL(1) << SYS_TFSR_EL1_TF0_SHIFT)
-#define SYS_TFSR_EL1_TF1 (UK(2) << SYS_TFSR_EL1_TF1_SHIFT)
+#define SYS_TFSR_EL1_TF1 (UL(1) << SYS_TFSR_EL1_TF1_SHIFT)
/* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */
#define SYS_MPIDR_SAFE_VAL (BIT(31))
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 43d4c329775f..70e0a7591245 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -17,40 +17,164 @@
#include <asm/mmu.h>
#include <asm/sysreg.h>
-static void notrace el1_abort(struct pt_regs *regs, unsigned long esr)
+/*
+ * This is intended to match the logic in irqentry_enter(), handling the kernel
+ * mode transitions only.
+ */
+static void noinstr enter_from_kernel_mode(struct pt_regs *regs)
+{
+ regs->exit_rcu = false;
+
+ if (!IS_ENABLED(CONFIG_TINY_RCU) && is_idle_task(current)) {
+ lockdep_hardirqs_off(CALLER_ADDR0);
+ rcu_irq_enter();
+ trace_hardirqs_off_finish();
+
+ regs->exit_rcu = true;
+ return;
+ }
+
+ lockdep_hardirqs_off(CALLER_ADDR0);
+ rcu_irq_enter_check_tick();
+ trace_hardirqs_off_finish();
+}
+
+/*
+ * This is intended to match the logic in irqentry_exit(), handling the kernel
+ * mode transitions only, and with preemption handled elsewhere.
+ */
+static void noinstr exit_to_kernel_mode(struct pt_regs *regs)
+{
+ lockdep_assert_irqs_disabled();
+
+ if (interrupts_enabled(regs)) {
+ if (regs->exit_rcu) {
+ trace_hardirqs_on_prepare();
+ lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+ rcu_irq_exit();
+ lockdep_hardirqs_on(CALLER_ADDR0);
+ return;
+ }
+
+ trace_hardirqs_on();
+ } else {
+ if (regs->exit_rcu)
+ rcu_irq_exit();
+ }
+}
+
+void noinstr arm64_enter_nmi(struct pt_regs *regs)
+{
+ regs->lockdep_hardirqs = lockdep_hardirqs_enabled();
+
+ __nmi_enter();
+ lockdep_hardirqs_off(CALLER_ADDR0);
+ lockdep_hardirq_enter();
+ rcu_nmi_enter();
+
+ trace_hardirqs_off_finish();
+ ftrace_nmi_enter();
+}
+
+void noinstr arm64_exit_nmi(struct pt_regs *regs)
+{
+ bool restore = regs->lockdep_hardirqs;
+
+ ftrace_nmi_exit();
+ if (restore) {
+ trace_hardirqs_on_prepare();
+ lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+ }
+
+ rcu_nmi_exit();
+ lockdep_hardirq_exit();
+ if (restore)
+ lockdep_hardirqs_on(CALLER_ADDR0);
+ __nmi_exit();
+}
+
+asmlinkage void noinstr enter_el1_irq_or_nmi(struct pt_regs *regs)
+{
+ if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs))
+ arm64_enter_nmi(regs);
+ else
+ enter_from_kernel_mode(regs);
+}
+
+asmlinkage void noinstr exit_el1_irq_or_nmi(struct pt_regs *regs)
+{
+ if (IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && !interrupts_enabled(regs))
+ arm64_exit_nmi(regs);
+ else
+ exit_to_kernel_mode(regs);
+}
+
+static void noinstr el1_abort(struct pt_regs *regs, unsigned long esr)
{
unsigned long far = read_sysreg(far_el1);
+ enter_from_kernel_mode(regs);
local_daif_inherit(regs);
far = untagged_addr(far);
do_mem_abort(far, esr, regs);
+ local_daif_mask();
+ exit_to_kernel_mode(regs);
}
-NOKPROBE_SYMBOL(el1_abort);
-static void notrace el1_pc(struct pt_regs *regs, unsigned long esr)
+static void noinstr el1_pc(struct pt_regs *regs, unsigned long esr)
{
unsigned long far = read_sysreg(far_el1);
+ enter_from_kernel_mode(regs);
local_daif_inherit(regs);
do_sp_pc_abort(far, esr, regs);
+ local_daif_mask();
+ exit_to_kernel_mode(regs);
}
-NOKPROBE_SYMBOL(el1_pc);
-static void notrace el1_undef(struct pt_regs *regs)
+static void noinstr el1_undef(struct pt_regs *regs)
{
+ enter_from_kernel_mode(regs);
local_daif_inherit(regs);
do_undefinstr(regs);
+ local_daif_mask();
+ exit_to_kernel_mode(regs);
}
-NOKPROBE_SYMBOL(el1_undef);
-static void notrace el1_inv(struct pt_regs *regs, unsigned long esr)
+static void noinstr el1_inv(struct pt_regs *regs, unsigned long esr)
{
+ enter_from_kernel_mode(regs);
local_daif_inherit(regs);
bad_mode(regs, 0, esr);
+ local_daif_mask();
+ exit_to_kernel_mode(regs);
}
-NOKPROBE_SYMBOL(el1_inv);
-static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr)
+static void noinstr arm64_enter_el1_dbg(struct pt_regs *regs)
+{
+ regs->lockdep_hardirqs = lockdep_hardirqs_enabled();
+
+ lockdep_hardirqs_off(CALLER_ADDR0);
+ rcu_nmi_enter();
+
+ trace_hardirqs_off_finish();
+}
+
+static void noinstr arm64_exit_el1_dbg(struct pt_regs *regs)
+{
+ bool restore = regs->lockdep_hardirqs;
+
+ if (restore) {
+ trace_hardirqs_on_prepare();
+ lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+ }
+
+ rcu_nmi_exit();
+ if (restore)
+ lockdep_hardirqs_on(CALLER_ADDR0);
+}
+
+static void noinstr el1_dbg(struct pt_regs *regs, unsigned long esr)
{
unsigned long far = read_sysreg(far_el1);
@@ -62,18 +186,21 @@ static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr)
if (system_uses_irq_prio_masking())
gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+ arm64_enter_el1_dbg(regs);
do_debug_exception(far, esr, regs);
+ arm64_exit_el1_dbg(regs);
}
-NOKPROBE_SYMBOL(el1_dbg);
-static void notrace el1_fpac(struct pt_regs *regs, unsigned long esr)
+static void noinstr el1_fpac(struct pt_regs *regs, unsigned long esr)
{
+ enter_from_kernel_mode(regs);
local_daif_inherit(regs);
do_ptrauth_fault(regs, esr);
+ local_daif_mask();
+ exit_to_kernel_mode(regs);
}
-NOKPROBE_SYMBOL(el1_fpac);
-asmlinkage void notrace el1_sync_handler(struct pt_regs *regs)
+asmlinkage void noinstr el1_sync_handler(struct pt_regs *regs)
{
unsigned long esr = read_sysreg(esr_el1);
@@ -106,20 +233,34 @@ asmlinkage void notrace el1_sync_handler(struct pt_regs *regs)
el1_inv(regs, esr);
}
}
-NOKPROBE_SYMBOL(el1_sync_handler);
-static void notrace el0_da(struct pt_regs *regs, unsigned long esr)
+asmlinkage void noinstr enter_from_user_mode(void)
+{
+ lockdep_hardirqs_off(CALLER_ADDR0);
+ CT_WARN_ON(ct_state() != CONTEXT_USER);
+ user_exit_irqoff();
+ trace_hardirqs_off_finish();
+}
+
+asmlinkage void noinstr exit_to_user_mode(void)
+{
+ trace_hardirqs_on_prepare();
+ lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+ user_enter_irqoff();
+ lockdep_hardirqs_on(CALLER_ADDR0);
+}
+
+static void noinstr el0_da(struct pt_regs *regs, unsigned long esr)
{
unsigned long far = read_sysreg(far_el1);
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
far = untagged_addr(far);
do_mem_abort(far, esr, regs);
}
-NOKPROBE_SYMBOL(el0_da);
-static void notrace el0_ia(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_ia(struct pt_regs *regs, unsigned long esr)
{
unsigned long far = read_sysreg(far_el1);
@@ -131,90 +272,80 @@ static void notrace el0_ia(struct pt_regs *regs, unsigned long esr)
if (!is_ttbr0_addr(far))
arm64_apply_bp_hardening();
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_mem_abort(far, esr, regs);
}
-NOKPROBE_SYMBOL(el0_ia);
-static void notrace el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_fpsimd_acc(struct pt_regs *regs, unsigned long esr)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_fpsimd_acc(esr, regs);
}
-NOKPROBE_SYMBOL(el0_fpsimd_acc);
-static void notrace el0_sve_acc(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_sve_acc(struct pt_regs *regs, unsigned long esr)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_sve_acc(esr, regs);
}
-NOKPROBE_SYMBOL(el0_sve_acc);
-static void notrace el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_fpsimd_exc(struct pt_regs *regs, unsigned long esr)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_fpsimd_exc(esr, regs);
}
-NOKPROBE_SYMBOL(el0_fpsimd_exc);
-static void notrace el0_sys(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_sys(struct pt_regs *regs, unsigned long esr)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_sysinstr(esr, regs);
}
-NOKPROBE_SYMBOL(el0_sys);
-static void notrace el0_pc(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_pc(struct pt_regs *regs, unsigned long esr)
{
unsigned long far = read_sysreg(far_el1);
if (!is_ttbr0_addr(instruction_pointer(regs)))
arm64_apply_bp_hardening();
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_sp_pc_abort(far, esr, regs);
}
-NOKPROBE_SYMBOL(el0_pc);
-static void notrace el0_sp(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_sp(struct pt_regs *regs, unsigned long esr)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_sp_pc_abort(regs->sp, esr, regs);
}
-NOKPROBE_SYMBOL(el0_sp);
-static void notrace el0_undef(struct pt_regs *regs)
+static void noinstr el0_undef(struct pt_regs *regs)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_undefinstr(regs);
}
-NOKPROBE_SYMBOL(el0_undef);
-static void notrace el0_bti(struct pt_regs *regs)
+static void noinstr el0_bti(struct pt_regs *regs)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_bti(regs);
}
-NOKPROBE_SYMBOL(el0_bti);
-static void notrace el0_inv(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_inv(struct pt_regs *regs, unsigned long esr)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
bad_el0_sync(regs, 0, esr);
}
-NOKPROBE_SYMBOL(el0_inv);
-static void notrace el0_dbg(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_dbg(struct pt_regs *regs, unsigned long esr)
{
/* Only watchpoints write FAR_EL1, otherwise its UNKNOWN */
unsigned long far = read_sysreg(far_el1);
@@ -222,30 +353,28 @@ static void notrace el0_dbg(struct pt_regs *regs, unsigned long esr)
if (system_uses_irq_prio_masking())
gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
- user_exit_irqoff();
+ enter_from_user_mode();
do_debug_exception(far, esr, regs);
local_daif_restore(DAIF_PROCCTX_NOIRQ);
}
-NOKPROBE_SYMBOL(el0_dbg);
-static void notrace el0_svc(struct pt_regs *regs)
+static void noinstr el0_svc(struct pt_regs *regs)
{
if (system_uses_irq_prio_masking())
gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+ enter_from_user_mode();
do_el0_svc(regs);
}
-NOKPROBE_SYMBOL(el0_svc);
-static void notrace el0_fpac(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_fpac(struct pt_regs *regs, unsigned long esr)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_ptrauth_fault(regs, esr);
}
-NOKPROBE_SYMBOL(el0_fpac);
-asmlinkage void notrace el0_sync_handler(struct pt_regs *regs)
+asmlinkage void noinstr el0_sync_handler(struct pt_regs *regs)
{
unsigned long esr = read_sysreg(esr_el1);
@@ -297,27 +426,25 @@ asmlinkage void notrace el0_sync_handler(struct pt_regs *regs)
el0_inv(regs, esr);
}
}
-NOKPROBE_SYMBOL(el0_sync_handler);
#ifdef CONFIG_COMPAT
-static void notrace el0_cp15(struct pt_regs *regs, unsigned long esr)
+static void noinstr el0_cp15(struct pt_regs *regs, unsigned long esr)
{
- user_exit_irqoff();
+ enter_from_user_mode();
local_daif_restore(DAIF_PROCCTX);
do_cp15instr(esr, regs);
}
-NOKPROBE_SYMBOL(el0_cp15);
-static void notrace el0_svc_compat(struct pt_regs *regs)
+static void noinstr el0_svc_compat(struct pt_regs *regs)
{
if (system_uses_irq_prio_masking())
gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
+ enter_from_user_mode();
do_el0_svc_compat(regs);
}
-NOKPROBE_SYMBOL(el0_svc_compat);
-asmlinkage void notrace el0_sync_compat_handler(struct pt_regs *regs)
+asmlinkage void noinstr el0_sync_compat_handler(struct pt_regs *regs)
{
unsigned long esr = read_sysreg(esr_el1);
@@ -360,5 +487,4 @@ asmlinkage void notrace el0_sync_compat_handler(struct pt_regs *regs)
el0_inv(regs, esr);
}
}
-NOKPROBE_SYMBOL(el0_sync_compat_handler);
#endif /* CONFIG_COMPAT */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index b295fb912b12..d72c818b019c 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -30,18 +30,18 @@
#include <asm/unistd.h>
/*
- * Context tracking subsystem. Used to instrument transitions
- * between user and kernel mode.
+ * Context tracking and irqflag tracing need to instrument transitions between
+ * user and kernel mode.
*/
- .macro ct_user_exit_irqoff
-#ifdef CONFIG_CONTEXT_TRACKING
+ .macro user_exit_irqoff
+#if defined(CONFIG_CONTEXT_TRACKING) || defined(CONFIG_TRACE_IRQFLAGS)
bl enter_from_user_mode
#endif
.endm
- .macro ct_user_enter
-#ifdef CONFIG_CONTEXT_TRACKING
- bl context_tracking_user_enter
+ .macro user_enter_irqoff
+#if defined(CONFIG_CONTEXT_TRACKING) || defined(CONFIG_TRACE_IRQFLAGS)
+ bl exit_to_user_mode
#endif
.endm
@@ -298,9 +298,6 @@ alternative_if ARM64_HAS_IRQ_PRIO_MASKING
alternative_else_nop_endif
ldp x21, x22, [sp, #S_PC] // load ELR, SPSR
- .if \el == 0
- ct_user_enter
- .endif
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
alternative_if_not ARM64_HAS_PAN
@@ -637,16 +634,8 @@ SYM_CODE_START_LOCAL_NOALIGN(el1_irq)
gic_prio_irq_setup pmr=x20, tmp=x1
enable_da_f
-#ifdef CONFIG_ARM64_PSEUDO_NMI
- test_irqs_unmasked res=x0, pmr=x20
- cbz x0, 1f
- bl asm_nmi_enter
-1:
-#endif
-
-#ifdef CONFIG_TRACE_IRQFLAGS
- bl trace_hardirqs_off
-#endif
+ mov x0, sp
+ bl enter_el1_irq_or_nmi
irq_handler
@@ -665,26 +654,8 @@ alternative_else_nop_endif
1:
#endif
-#ifdef CONFIG_ARM64_PSEUDO_NMI
- /*
- * When using IRQ priority masking, we can get spurious interrupts while
- * PMR is set to GIC_PRIO_IRQOFF. An NMI might also have occurred in a
- * section with interrupts disabled. Skip tracing in those cases.
- */
- test_irqs_unmasked res=x0, pmr=x20
- cbz x0, 1f
- bl asm_nmi_exit
-1:
-#endif
-
-#ifdef CONFIG_TRACE_IRQFLAGS
-#ifdef CONFIG_ARM64_PSEUDO_NMI
- test_irqs_unmasked res=x0, pmr=x20
- cbnz x0, 1f
-#endif
- bl trace_hardirqs_on
-1:
-#endif
+ mov x0, sp
+ bl exit_el1_irq_or_nmi
kernel_exit 1
SYM_CODE_END(el1_irq)
@@ -726,21 +697,14 @@ SYM_CODE_START_LOCAL_NOALIGN(el0_irq)
kernel_entry 0
el0_irq_naked:
gic_prio_irq_setup pmr=x20, tmp=x0
- ct_user_exit_irqoff
+ user_exit_irqoff
enable_da_f
-#ifdef CONFIG_TRACE_IRQFLAGS
- bl trace_hardirqs_off
-#endif
-
tbz x22, #55, 1f
bl do_el0_irq_bp_hardening
1:
irq_handler
-#ifdef CONFIG_TRACE_IRQFLAGS
- bl trace_hardirqs_on
-#endif
b ret_to_user
SYM_CODE_END(el0_irq)
@@ -759,7 +723,7 @@ SYM_CODE_START_LOCAL(el0_error)
el0_error_naked:
mrs x25, esr_el1
gic_prio_kentry_setup tmp=x2
- ct_user_exit_irqoff
+ user_exit_irqoff
enable_dbg
mov x0, sp
mov x1, x25
@@ -774,13 +738,17 @@ SYM_CODE_END(el0_error)
SYM_CODE_START_LOCAL(ret_to_user)
disable_daif
gic_prio_kentry_setup tmp=x3
- ldr x1, [tsk, #TSK_TI_FLAGS]
- and x2, x1, #_TIF_WORK_MASK
+#ifdef CONFIG_TRACE_IRQFLAGS
+ bl trace_hardirqs_off
+#endif
+ ldr x19, [tsk, #TSK_TI_FLAGS]
+ and x2, x19, #_TIF_WORK_MASK
cbnz x2, work_pending
finish_ret_to_user:
+ user_enter_irqoff
/* Ignore asynchronous tag check faults in the uaccess routines */
clear_mte_async_tcf
- enable_step_tsk x1, x2
+ enable_step_tsk x19, x2
#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
bl stackleak_erase
#endif
@@ -791,11 +759,9 @@ finish_ret_to_user:
*/
work_pending:
mov x0, sp // 'regs'
+ mov x1, x19
bl do_notify_resume
-#ifdef CONFIG_TRACE_IRQFLAGS
- bl trace_hardirqs_on // enabled while in userspace
-#endif
- ldr x1, [tsk, #TSK_TI_FLAGS] // re-check for single-step
+ ldr x19, [tsk, #TSK_TI_FLAGS] // re-check for single-step
b finish_ret_to_user
SYM_CODE_END(ret_to_user)
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 9cf2fb87584a..60456a62da11 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -67,18 +67,3 @@ void __init init_IRQ(void)
local_daif_restore(DAIF_PROCCTX_NOIRQ);
}
}
-
-/*
- * Stubs to make nmi_enter/exit() code callable from ASM
- */
-asmlinkage void notrace asm_nmi_enter(void)
-{
- nmi_enter();
-}
-NOKPROBE_SYMBOL(asm_nmi_enter);
-
-asmlinkage void notrace asm_nmi_exit(void)
-{
- nmi_exit();
-}
-NOKPROBE_SYMBOL(asm_nmi_exit);
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 7697a4b48b7c..ed919f633ed8 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -72,13 +72,13 @@ EXPORT_SYMBOL_GPL(pm_power_off);
void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
-static void __cpu_do_idle(void)
+static void noinstr __cpu_do_idle(void)
{
dsb(sy);
wfi();
}
-static void __cpu_do_idle_irqprio(void)
+static void noinstr __cpu_do_idle_irqprio(void)
{
unsigned long pmr;
unsigned long daif_bits;
@@ -108,7 +108,7 @@ static void __cpu_do_idle_irqprio(void)
* 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)
+void noinstr cpu_do_idle(void)
{
if (system_uses_irq_prio_masking())
__cpu_do_idle_irqprio();
@@ -119,7 +119,7 @@ void cpu_do_idle(void)
/*
* This is our default idle handler.
*/
-void arch_cpu_idle(void)
+void noinstr arch_cpu_idle(void)
{
/*
* This should do all the clock switching and wait for interrupt
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index 7689f2031c0c..793c46d6a447 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -10,6 +10,7 @@
#include <linux/uaccess.h>
#include <asm/alternative.h>
+#include <asm/exception.h>
#include <asm/kprobes.h>
#include <asm/mmu.h>
#include <asm/ptrace.h>
@@ -223,16 +224,16 @@ static __kprobes unsigned long _sdei_handler(struct pt_regs *regs,
}
-asmlinkage __kprobes notrace unsigned long
+asmlinkage noinstr unsigned long
__sdei_handler(struct pt_regs *regs, struct sdei_registered_event *arg)
{
unsigned long ret;
- nmi_enter();
+ arm64_enter_nmi(regs);
ret = _sdei_handler(regs, arg);
- nmi_exit();
+ arm64_exit_nmi(regs);
return ret;
}
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index e4c0dadf0d92..f8f758e4a306 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -121,7 +121,6 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
cortex_a76_erratum_1463225_svc_handler();
local_daif_restore(DAIF_PROCCTX);
- user_exit();
if (system_supports_mte() && (flags & _TIF_MTE_ASYNC_FAULT)) {
/*
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 8af4e0e85736..2059d8f43f55 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -34,6 +34,7 @@
#include <asm/daifflags.h>
#include <asm/debug-monitors.h>
#include <asm/esr.h>
+#include <asm/exception.h>
#include <asm/extable.h>
#include <asm/insn.h>
#include <asm/kprobes.h>
@@ -753,8 +754,10 @@ const char *esr_get_class_string(u32 esr)
* bad_mode handles the impossible case in the exception vector. This is always
* fatal.
*/
-asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
+asmlinkage void notrace bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
{
+ arm64_enter_nmi(regs);
+
console_verbose();
pr_crit("Bad mode in %s handler detected on CPU%d, code 0x%08x -- %s\n",
@@ -786,7 +789,7 @@ void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack)
__aligned(16);
-asmlinkage void handle_bad_stack(struct pt_regs *regs)
+asmlinkage void noinstr handle_bad_stack(struct pt_regs *regs)
{
unsigned long tsk_stk = (unsigned long)current->stack;
unsigned long irq_stk = (unsigned long)this_cpu_read(irq_stack_ptr);
@@ -794,6 +797,8 @@ asmlinkage void handle_bad_stack(struct pt_regs *regs)
unsigned int esr = read_sysreg(esr_el1);
unsigned long far = read_sysreg(far_el1);
+ arm64_enter_nmi(regs);
+
console_verbose();
pr_emerg("Insufficient stack space to handle exception!");
@@ -865,23 +870,16 @@ bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr)
}
}
-asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr)
+asmlinkage void noinstr do_serror(struct pt_regs *regs, unsigned int esr)
{
- nmi_enter();
+ arm64_enter_nmi(regs);
/* 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();
-}
-
-asmlinkage void enter_from_user_mode(void)
-{
- CT_WARN_ON(ct_state() != CONTEXT_USER);
- user_exit_irqoff();
+ arm64_exit_nmi(regs);
}
-NOKPROBE_SYMBOL(enter_from_user_mode);
/* GENERIC_BUG traps */
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 1ee94002801f..795d224f184f 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -789,25 +789,6 @@ void __init hook_debug_fault_code(int nr,
*/
static void debug_exception_enter(struct pt_regs *regs)
{
- /*
- * Tell lockdep we disabled irqs in entry.S. Do nothing if they were
- * already disabled to preserve the last enabled/disabled addresses.
- */
- if (interrupts_enabled(regs))
- trace_hardirqs_off();
-
- if (user_mode(regs)) {
- RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
- } else {
- /*
- * We might have interrupted pretty much anything. In
- * fact, if we're a debug exception, we can even interrupt
- * NMI processing. We don't want this code makes in_nmi()
- * to return true, but we need to notify RCU.
- */
- rcu_nmi_enter();
- }
-
preempt_disable();
/* This code is a bit fragile. Test it. */
@@ -818,12 +799,6 @@ NOKPROBE_SYMBOL(debug_exception_enter);
static void debug_exception_exit(struct pt_regs *regs)
{
preempt_enable_no_resched();
-
- if (!user_mode(regs))
- rcu_nmi_exit();
-
- if (interrupts_enabled(regs))
- trace_hardirqs_on();
}
NOKPROBE_SYMBOL(debug_exception_exit);
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index e9f13fe08492..5181872f9452 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -152,6 +152,7 @@ config PPC
select ARCH_USE_QUEUED_SPINLOCKS if PPC_QUEUED_SPINLOCKS
select ARCH_WANT_IPC_PARSE_VERSION
select ARCH_WANT_IRQS_OFF_ACTIVATE_MM
+ select ARCH_WANT_LD_ORPHAN_WARN
select ARCH_WEAK_RELEASE_ACQUIRE
select BINFMT_ELF
select BUILDTIME_TABLE_SORT
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 16b8336f91dd..5c8c06215dd4 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -123,7 +123,6 @@ endif
LDFLAGS_vmlinux-y := -Bstatic
LDFLAGS_vmlinux-$(CONFIG_RELOCATABLE) := -pie
LDFLAGS_vmlinux := $(LDFLAGS_vmlinux-y)
-LDFLAGS_vmlinux += $(call ld-option,--orphan-handling=warn)
ifdef CONFIG_PPC64
ifeq ($(call cc-option-yn,-mcmodel=medium),y)
diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index e0b52940e43c..750918451dd2 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -242,6 +242,18 @@ extern void radix_init_pseries(void);
static inline void radix_init_pseries(void) { };
#endif
+#ifdef CONFIG_HOTPLUG_CPU
+#define arch_clear_mm_cpumask_cpu(cpu, mm) \
+ do { \
+ if (cpumask_test_cpu(cpu, mm_cpumask(mm))) { \
+ atomic_dec(&(mm)->context.active_cpus); \
+ cpumask_clear_cpu(cpu, mm_cpumask(mm)); \
+ } \
+ } while (0)
+
+void cleanup_cpu_mmu_context(void);
+#endif
+
static inline int get_user_context(mm_context_t *ctx, unsigned long ea)
{
int index = ea >> MAX_EA_BITS_PER_CONTEXT;
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index 85215e79db42..a0ebc29f30b2 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -1214,12 +1214,9 @@ void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu)
static bool kvmppc_xive_vcpu_id_valid(struct kvmppc_xive *xive, u32 cpu)
{
/* We have a block of xive->nr_servers VPs. We just need to check
- * raw vCPU ids are below the expected limit for this guest's
- * core stride ; kvmppc_pack_vcpu_id() will pack them down to an
- * index that can be safely used to compute a VP id that belongs
- * to the VP block.
+ * packed vCPU ids are below that.
*/
- return cpu < xive->nr_servers * xive->kvm->arch.emul_smt_mode;
+ return kvmppc_pack_vcpu_id(xive->kvm, cpu) < xive->nr_servers;
}
int kvmppc_xive_compute_vp_id(struct kvmppc_xive *xive, u32 cpu, u32 *vp)
diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c
index 0203cdf48c54..52e170bd95ae 100644
--- a/arch/powerpc/mm/book3s64/hash_native.c
+++ b/arch/powerpc/mm/book3s64/hash_native.c
@@ -68,7 +68,7 @@ static __always_inline void tlbiel_hash_set_isa300(unsigned int set, unsigned in
rs = ((unsigned long)pid << PPC_BITLSHIFT(31));
asm volatile(PPC_TLBIEL(%0, %1, %2, %3, %4)
- : : "r"(rb), "r"(rs), "i"(ric), "i"(prs), "r"(r)
+ : : "r"(rb), "r"(rs), "i"(ric), "i"(prs), "i"(r)
: "memory");
}
@@ -92,16 +92,15 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is)
asm volatile("ptesync": : :"memory");
/*
- * Flush the first set of the TLB, and any caching of partition table
- * entries. Then flush the remaining sets of the TLB. Hash mode uses
- * partition scoped TLB translations.
+ * Flush the partition table cache if this is HV mode.
*/
- tlbiel_hash_set_isa300(0, is, 0, 2, 0);
- for (set = 1; set < num_sets; set++)
- tlbiel_hash_set_isa300(set, is, 0, 0, 0);
+ if (early_cpu_has_feature(CPU_FTR_HVMODE))
+ tlbiel_hash_set_isa300(0, is, 0, 2, 0);
/*
- * Now invalidate the process table cache.
+ * Now invalidate the process table cache. UPRT=0 HPT modes (what
+ * current hardware implements) do not use the process table, but
+ * add the flushes anyway.
*
* From ISA v3.0B p. 1078:
* The following forms are invalid.
@@ -110,6 +109,14 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is)
*/
tlbiel_hash_set_isa300(0, is, 0, 2, 1);
+ /*
+ * Then flush the sets of the TLB proper. Hash mode uses
+ * partition scoped TLB translations, which may be flushed
+ * in !HV mode.
+ */
+ for (set = 0; set < num_sets; set++)
+ tlbiel_hash_set_isa300(set, is, 0, 0, 0);
+
ppc_after_tlbiel_barrier();
asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT "; isync" : : :"memory");
diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c
index 1c54821de7bf..0c8557220ae2 100644
--- a/arch/powerpc/mm/book3s64/mmu_context.c
+++ b/arch/powerpc/mm/book3s64/mmu_context.c
@@ -17,6 +17,7 @@
#include <linux/export.h>
#include <linux/gfp.h>
#include <linux/slab.h>
+#include <linux/cpu.h>
#include <asm/mmu_context.h>
#include <asm/pgalloc.h>
@@ -307,3 +308,22 @@ void radix__switch_mmu_context(struct mm_struct *prev, struct mm_struct *next)
isync();
}
#endif
+
+/**
+ * cleanup_cpu_mmu_context - Clean up MMU details for this CPU (newly offlined)
+ *
+ * This clears the CPU from mm_cpumask for all processes, and then flushes the
+ * local TLB to ensure TLB coherency in case the CPU is onlined again.
+ *
+ * KVM guest translations are not necessarily flushed here. If KVM started
+ * using mm_cpumask or the Linux APIs which do, this would have to be resolved.
+ */
+#ifdef CONFIG_HOTPLUG_CPU
+void cleanup_cpu_mmu_context(void)
+{
+ int cpu = smp_processor_id();
+
+ clear_tasks_mm_cpumask(cpu);
+ tlbiel_all();
+}
+#endif
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 63f61d8b55e5..f2bf98bdcea2 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -742,8 +742,7 @@ static int __init parse_numa_properties(void)
of_node_put(cpu);
}
- if (likely(nid > 0))
- node_set_online(nid);
+ node_set_online(nid);
}
get_n_mem_cells(&n_mem_addr_cells, &n_mem_size_cells);
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 74ebe664b016..adae2a6712e1 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -911,6 +911,8 @@ static int smp_core99_cpu_disable(void)
mpic_cpu_set_priority(0xf);
+ cleanup_cpu_mmu_context();
+
return 0;
}
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 46115231a3b2..4426a109ec2f 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -211,11 +211,16 @@ static void __init pnv_init(void)
add_preferred_console("hvc", 0, NULL);
if (!radix_enabled()) {
+ size_t size = sizeof(struct slb_entry) * mmu_slb_size;
int i;
/* Allocate per cpu area to save old slb contents during MCE */
- for_each_possible_cpu(i)
- paca_ptrs[i]->mce_faulty_slbs = memblock_alloc_node(mmu_slb_size, __alignof__(*paca_ptrs[i]->mce_faulty_slbs), cpu_to_node(i));
+ for_each_possible_cpu(i) {
+ paca_ptrs[i]->mce_faulty_slbs =
+ memblock_alloc_node(size,
+ __alignof__(struct slb_entry),
+ cpu_to_node(i));
+ }
}
}
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 54c4ba45c7ce..cbb67813cd5d 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -143,6 +143,9 @@ static int pnv_smp_cpu_disable(void)
xive_smp_disable_cpu();
else
xics_migrate_irqs_away();
+
+ cleanup_cpu_mmu_context();
+
return 0;
}
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index f2837e33bf5d..a02012f1b04a 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -90,6 +90,9 @@ static int pseries_cpu_disable(void)
xive_smp_disable_cpu();
else
xics_migrate_irqs_away();
+
+ cleanup_cpu_mmu_context();
+
return 0;
}
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index 133f6adcb39c..b3ac2455faad 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -458,7 +458,8 @@ again:
return hwirq;
}
- virq = irq_create_mapping(NULL, hwirq);
+ virq = irq_create_mapping_affinity(NULL, hwirq,
+ entry->affinity);
if (!virq) {
pr_debug("rtas_msi: Failed mapping hwirq %d\n", hwirq);
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 26bb0603c5a1..92beb1444644 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -763,12 +763,7 @@ ENTRY(io_int_handler)
xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ
jo .Lio_restore
-#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS)
- tmhh %r8,0x300
- jz 1f
TRACE_IRQS_OFF
-1:
-#endif
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
.Lio_loop:
lgr %r2,%r11 # pass pointer to pt_regs
@@ -791,12 +786,7 @@ ENTRY(io_int_handler)
TSTMSK __LC_CPU_FLAGS,_CIF_WORK
jnz .Lio_work
.Lio_restore:
-#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS)
- tm __PT_PSW(%r11),3
- jno 0f
TRACE_IRQS_ON
-0:
-#endif
mvc __LC_RETURN_PSW(16),__PT_PSW(%r11)
tm __PT_PSW+1(%r11),0x01 # returning to user ?
jno .Lio_exit_kernel
@@ -976,12 +966,7 @@ ENTRY(ext_int_handler)
xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ
jo .Lio_restore
-#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS)
- tmhh %r8,0x300
- jz 1f
TRACE_IRQS_OFF
-1:
-#endif
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
lgr %r2,%r11 # pass pointer to pt_regs
lghi %r3,EXT_INTERRUPT
diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c
index daca7bad66de..8c0c68e7770e 100644
--- a/arch/s390/lib/delay.c
+++ b/arch/s390/lib/delay.c
@@ -33,7 +33,7 @@ EXPORT_SYMBOL(__delay);
static void __udelay_disabled(unsigned long long usecs)
{
- unsigned long cr0, cr0_new, psw_mask, flags;
+ unsigned long cr0, cr0_new, psw_mask;
struct s390_idle_data idle;
u64 end;
@@ -45,9 +45,8 @@ static void __udelay_disabled(unsigned long long usecs)
psw_mask = __extract_psw() | PSW_MASK_EXT | PSW_MASK_WAIT;
set_clock_comparator(end);
set_cpu_flag(CIF_IGNORE_IRQ);
- local_irq_save(flags);
psw_idle(&idle, psw_mask);
- local_irq_restore(flags);
+ trace_hardirqs_off();
clear_cpu_flag(CIF_IGNORE_IRQ);
set_clock_comparator(S390_lowcore.clock_comparator);
__ctl_load(cr0, 0, 0);
diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c
index 743f257cf2cb..75217fb63d7b 100644
--- a/arch/s390/pci/pci_irq.c
+++ b/arch/s390/pci/pci_irq.c
@@ -103,9 +103,10 @@ static int zpci_set_irq_affinity(struct irq_data *data, const struct cpumask *de
{
struct msi_desc *entry = irq_get_msi_desc(data->irq);
struct msi_msg msg = entry->msg;
+ int cpu_addr = smp_cpu_get_cpu_address(cpumask_first(dest));
msg.address_lo &= 0xff0000ff;
- msg.address_lo |= (cpumask_first(dest) << 8);
+ msg.address_lo |= (cpu_addr << 8);
pci_write_msi_msg(data->irq, &msg);
return IRQ_SET_MASK_OK;
@@ -238,6 +239,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
unsigned long bit;
struct msi_desc *msi;
struct msi_msg msg;
+ int cpu_addr;
int rc, irq;
zdev->aisb = -1UL;
@@ -287,9 +289,15 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
handle_percpu_irq);
msg.data = hwirq - bit;
if (irq_delivery == DIRECTED) {
+ if (msi->affinity)
+ cpu = cpumask_first(&msi->affinity->mask);
+ else
+ cpu = 0;
+ cpu_addr = smp_cpu_get_cpu_address(cpu);
+
msg.address_lo = zdev->msi_addr & 0xff0000ff;
- msg.address_lo |= msi->affinity ?
- (cpumask_first(&msi->affinity->mask) << 8) : 0;
+ msg.address_lo |= (cpu_addr << 8);
+
for_each_possible_cpu(cpu) {
airq_iv_set_data(zpci_ibv[cpu], hwirq, irq);
}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f6946b81f74a..fbf26e0f7a6a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -100,6 +100,7 @@ config X86
select ARCH_WANT_DEFAULT_BPF_JIT if X86_64
select ARCH_WANTS_DYNAMIC_TASK_STRUCT
select ARCH_WANT_HUGE_PMD_SHARE
+ select ARCH_WANT_LD_ORPHAN_WARN
select ARCH_WANTS_THP_SWAP if X86_64
select BUILDTIME_TABLE_SORT
select CLKEVT_I8253
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 154259f18b8b..1bf21746f4ce 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -209,9 +209,6 @@ ifdef CONFIG_X86_64
LDFLAGS_vmlinux += -z max-page-size=0x200000
endif
-# We never want expected sections to be placed heuristically by the
-# linker. All sections should be explicitly named in the linker script.
-LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn)
archscripts: scripts_basic
$(Q)$(MAKE) $(build)=arch/x86/tools relocs
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index ee249088cbfe..40b8fd375d52 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -61,7 +61,9 @@ KBUILD_LDFLAGS += $(call ld-option,--no-ld-generated-unwind-info)
# Compressed kernel should be built as PIE since it may be loaded at any
# address by the bootloader.
LDFLAGS_vmlinux := -pie $(call ld-option, --no-dynamic-linker)
-LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn)
+ifdef CONFIG_LD_ORPHAN_WARN
+LDFLAGS_vmlinux += --orphan-handling=warn
+endif
LDFLAGS_vmlinux += -T
hostprogs := mkpiggy
diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c
index 954cb2702e23..27826c265aab 100644
--- a/arch/x86/boot/compressed/sev-es.c
+++ b/arch/x86/boot/compressed/sev-es.c
@@ -32,13 +32,12 @@ struct ghcb *boot_ghcb;
*/
static bool insn_has_rep_prefix(struct insn *insn)
{
+ insn_byte_t p;
int i;
insn_get_prefixes(insn);
- for (i = 0; i < insn->prefixes.nbytes; i++) {
- insn_byte_t p = insn->prefixes.bytes[i];
-
+ for_each_insn_prefix(insn, i, p) {
if (p == 0xf2 || p == 0xf3)
return true;
}
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index b47cc4226934..485c5066f8b8 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1916,7 +1916,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
* that caused the PEBS record. It's called collision.
* If collision happened, the record will be dropped.
*/
- if (p->status != (1ULL << bit)) {
+ if (pebs_status != (1ULL << bit)) {
for_each_set_bit(i, (unsigned long *)&pebs_status, size)
error[i]++;
continue;
@@ -1940,7 +1940,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
if (error[bit]) {
perf_log_lost_samples(event, error[bit]);
- if (perf_event_account_interrupt(event))
+ if (iregs && perf_event_account_interrupt(event))
x86_pmu_stop(event, 0);
}
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 5c1ae3eff9d4..a8c3d284fa46 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -201,6 +201,21 @@ static inline int insn_offset_immediate(struct insn *insn)
return insn_offset_displacement(insn) + insn->displacement.nbytes;
}
+/**
+ * for_each_insn_prefix() -- Iterate prefixes in the instruction
+ * @insn: Pointer to struct insn.
+ * @idx: Index storage.
+ * @prefix: Prefix byte.
+ *
+ * Iterate prefix bytes of given @insn. Each prefix byte is stored in @prefix
+ * and the index is stored in @idx (note that this @idx is just for a cursor,
+ * do not change it.)
+ * Since prefixes.nbytes can be bigger than 4 if some prefixes
+ * are repeated, it cannot be used for looping over the prefixes.
+ */
+#define for_each_insn_prefix(insn, idx, prefix) \
+ for (idx = 0; idx < ARRAY_SIZE(insn->prefixes.bytes) && (prefix = insn->prefixes.bytes[idx]) != 0; idx++)
+
#define POP_SS_OPCODE 0x1f
#define MOV_SREG_OPCODE 0x8e
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 1b98f8c12b96..235f5cde06fc 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -161,7 +161,7 @@ static int __init early_set_hub_type(void)
/* UV4/4A only have a revision difference */
case UV4_HUB_PART_NUMBER:
uv_min_hub_revision_id = node_id.s.revision
- + UV4_HUB_REVISION_BASE;
+ + UV4_HUB_REVISION_BASE - 1;
uv_hub_type_set(UV4);
if (uv_min_hub_revision_id == UV4A_HUB_REVISION_BASE)
uv_hub_type_set(UV4|UV4A);
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index e5f4ee8f4c3b..e8b5f1cf1ae8 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -570,6 +570,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
if (d) {
cpumask_set_cpu(cpu, &d->cpu_mask);
+ if (r->cache.arch_has_per_cpu_cfg)
+ rdt_domain_reconfigure_cdp(r);
return;
}
@@ -923,6 +925,7 @@ static __init void rdt_init_res_defs_intel(void)
r->rid == RDT_RESOURCE_L2CODE) {
r->cache.arch_has_sparse_bitmaps = false;
r->cache.arch_has_empty_bitmaps = false;
+ r->cache.arch_has_per_cpu_cfg = false;
} else if (r->rid == RDT_RESOURCE_MBA) {
r->msr_base = MSR_IA32_MBA_THRTL_BASE;
r->msr_update = mba_wrmsr_intel;
@@ -943,6 +946,7 @@ static __init void rdt_init_res_defs_amd(void)
r->rid == RDT_RESOURCE_L2CODE) {
r->cache.arch_has_sparse_bitmaps = true;
r->cache.arch_has_empty_bitmaps = true;
+ r->cache.arch_has_per_cpu_cfg = true;
} else if (r->rid == RDT_RESOURCE_MBA) {
r->msr_base = MSR_IA32_MBA_BW_BASE;
r->msr_update = mba_wrmsr_amd;
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 80fa997fae60..f65d3c0dbc41 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -360,6 +360,8 @@ struct msr_param {
* executing entities
* @arch_has_sparse_bitmaps: True if a bitmap like f00f is valid.
* @arch_has_empty_bitmaps: True if the '0' bitmap is valid.
+ * @arch_has_per_cpu_cfg: True if QOS_CFG register for this cache
+ * level has CPU scope.
*/
struct rdt_cache {
unsigned int cbm_len;
@@ -369,6 +371,7 @@ struct rdt_cache {
unsigned int shareable_bits;
bool arch_has_sparse_bitmaps;
bool arch_has_empty_bitmaps;
+ bool arch_has_per_cpu_cfg;
};
/**
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 6f4ca4bea625..f3418428682b 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1909,8 +1909,13 @@ static int set_cache_qos_cfg(int level, bool enable)
r_l = &rdt_resources_all[level];
list_for_each_entry(d, &r_l->domains, list) {
- /* Pick one CPU from each domain instance to update MSR */
- cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+ if (r_l->cache.arch_has_per_cpu_cfg)
+ /* Pick all the CPUs in the domain instance */
+ for_each_cpu(cpu, &d->cpu_mask)
+ cpumask_set_cpu(cpu, cpu_mask);
+ else
+ /* Pick one CPU from each domain instance to update MSR */
+ cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
}
cpu = get_cpu();
/* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 3fdaa042823d..138bdb1fd136 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -255,12 +255,13 @@ static volatile u32 good_2byte_insns[256 / 32] = {
static bool is_prefix_bad(struct insn *insn)
{
+ insn_byte_t p;
int i;
- for (i = 0; i < insn->prefixes.nbytes; i++) {
+ for_each_insn_prefix(insn, i, p) {
insn_attr_t attr;
- attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]);
+ attr = inat_get_opcode_attribute(p);
switch (attr) {
case INAT_MAKE_PREFIX(INAT_PFX_ES):
case INAT_MAKE_PREFIX(INAT_PFX_CS):
@@ -715,6 +716,7 @@ static const struct uprobe_xol_ops push_xol_ops = {
static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
{
u8 opc1 = OPCODE1(insn);
+ insn_byte_t p;
int i;
switch (opc1) {
@@ -746,8 +748,8 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
* Intel and AMD behavior differ in 64-bit mode: Intel ignores 66 prefix.
* No one uses these insns, reject any branch insns with such prefix.
*/
- for (i = 0; i < insn->prefixes.nbytes; i++) {
- if (insn->prefixes.bytes[i] == 0x66)
+ for_each_insn_prefix(insn, i, p) {
+ if (p == 0x66)
return -ENOTSUPP;
}
diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 58f7fb95c7f4..4229950a5d78 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -63,13 +63,12 @@ static bool is_string_insn(struct insn *insn)
*/
bool insn_has_rep_prefix(struct insn *insn)
{
+ insn_byte_t p;
int i;
insn_get_prefixes(insn);
- for (i = 0; i < insn->prefixes.nbytes; i++) {
- insn_byte_t p = insn->prefixes.bytes[i];
-
+ for_each_insn_prefix(insn, i, p) {
if (p == 0xf2 || p == 0xf3)
return true;
}
@@ -95,14 +94,15 @@ static int get_seg_reg_override_idx(struct insn *insn)
{
int idx = INAT_SEG_REG_DEFAULT;
int num_overrides = 0, i;
+ insn_byte_t p;
insn_get_prefixes(insn);
/* Look for any segment override prefixes. */
- for (i = 0; i < insn->prefixes.nbytes; i++) {
+ for_each_insn_prefix(insn, i, p) {
insn_attr_t attr;
- attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]);
+ attr = inat_get_opcode_attribute(p);
switch (attr) {
case INAT_MAKE_PREFIX(INAT_PFX_CS):
idx = INAT_SEG_REG_CS;