Merge branch 'sched/urgent' into sched/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

21 files changed, 256 insertions, 114 deletions

diff --git a/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
index c2717f31925a..ccda0a91abf0 100644
--- a/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
@@ -122,7 +122,15 @@
 	};
 
 /include/ "pq3-i2c-0.dtsi"
+	i2c@3000 {
+		fsl,i2c-erratum-a004447;
+	};
+
 /include/ "pq3-i2c-1.dtsi"
+	i2c@3100 {
+		fsl,i2c-erratum-a004447;
+	};
+
 /include/ "pq3-duart-0.dtsi"
 /include/ "pq3-espi-0.dtsi"
 	spi0: spi@7000 {
diff --git a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
index 872e4485dc3f..ddc018d42252 100644
--- a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
@@ -371,7 +371,23 @@
 	};
 
 /include/ "qoriq-i2c-0.dtsi"
+	i2c@118000 {
+		fsl,i2c-erratum-a004447;
+	};
+
+	i2c@118100 {
+		fsl,i2c-erratum-a004447;
+	};
+
 /include/ "qoriq-i2c-1.dtsi"
+	i2c@119000 {
+		fsl,i2c-erratum-a004447;
+	};
+
+	i2c@119100 {
+		fsl,i2c-erratum-a004447;
+	};
+
 /include/ "qoriq-duart-0.dtsi"
 /include/ "qoriq-duart-1.dtsi"
 /include/ "qoriq-gpio-0.dtsi"
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index 443050906018..e3b29eda8074 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -448,6 +448,9 @@
  */
 long plpar_hcall_norets(unsigned long opcode, ...);
 
+/* Variant which does not do hcall tracing */
+long plpar_hcall_norets_notrace(unsigned long opcode, ...);
+
 /**
  * plpar_hcall: - Make a pseries hypervisor call
  * @opcode: The hypervisor call to make.
diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h
index 44cde2e129b8..59f704408d65 100644
--- a/arch/powerpc/include/asm/interrupt.h
+++ b/arch/powerpc/include/asm/interrupt.h
@@ -153,8 +153,6 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup
  */
 static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt_state *state)
 {
-	if (user_mode(regs))
-		kuep_unlock();
 }
 
 static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state)
@@ -222,6 +220,13 @@ static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct inte
 	local_paca->irq_soft_mask = IRQS_ALL_DISABLED;
 	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
 
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !(regs->msr & MSR_PR) &&
+				regs->nip < (unsigned long)__end_interrupts) {
+		// Kernel code running below __end_interrupts is
+		// implicitly soft-masked.
+		regs->softe = IRQS_ALL_DISABLED;
+	}
+
 	/* Don't do any per-CPU operations until interrupt state is fixed */
 
 	if (nmi_disables_ftrace(regs)) {
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 1e83359f286b..7f2e90db2050 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -51,6 +51,7 @@
 /* PPC-specific vcpu->requests bit members */
 #define KVM_REQ_WATCHDOG	KVM_ARCH_REQ(0)
 #define KVM_REQ_EPR_EXIT	KVM_ARCH_REQ(1)
+#define KVM_REQ_PENDING_TIMER	KVM_ARCH_REQ(2)
 
 #include <linux/mmu_notifier.h>
 
diff --git a/arch/powerpc/include/asm/paravirt.h b/arch/powerpc/include/asm/paravirt.h
index 5d1726bb28e7..bcb7b5f917be 100644
--- a/arch/powerpc/include/asm/paravirt.h
+++ b/arch/powerpc/include/asm/paravirt.h
@@ -28,19 +28,35 @@ static inline u32 yield_count_of(int cpu)
 	return be32_to_cpu(yield_count);
 }
 
+/*
+ * Spinlock code confers and prods, so don't trace the hcalls because the
+ * tracing code takes spinlocks which can cause recursion deadlocks.
+ *
+ * These calls are made while the lock is not held: the lock slowpath yields if
+ * it can not acquire the lock, and unlock slow path might prod if a waiter has
+ * yielded). So this may not be a problem for simple spin locks because the
+ * tracing does not technically recurse on the lock, but we avoid it anyway.
+ *
+ * However the queued spin lock contended path is more strictly ordered: the
+ * H_CONFER hcall is made after the task has queued itself on the lock, so then
+ * recursing on that lock will cause the task to then queue up again behind the
+ * first instance (or worse: queued spinlocks use tricks that assume a context
+ * never waits on more than one spinlock, so such recursion may cause random
+ * corruption in the lock code).
+ */
 static inline void yield_to_preempted(int cpu, u32 yield_count)
 {
-	plpar_hcall_norets(H_CONFER, get_hard_smp_processor_id(cpu), yield_count);
+	plpar_hcall_norets_notrace(H_CONFER, get_hard_smp_processor_id(cpu), yield_count);
 }
 
 static inline void prod_cpu(int cpu)
 {
-	plpar_hcall_norets(H_PROD, get_hard_smp_processor_id(cpu));
+	plpar_hcall_norets_notrace(H_PROD, get_hard_smp_processor_id(cpu));
 }
 
 static inline void yield_to_any(void)
 {
-	plpar_hcall_norets(H_CONFER, -1, 0);
+	plpar_hcall_norets_notrace(H_CONFER, -1, 0);
 }
 #else
 static inline bool is_shared_processor(void)
diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h
index ece84a430701..83e0f701ebc6 100644
--- a/arch/powerpc/include/asm/plpar_wrappers.h
+++ b/arch/powerpc/include/asm/plpar_wrappers.h
@@ -28,7 +28,11 @@ static inline void set_cede_latency_hint(u8 latency_hint)
 
 static inline long cede_processor(void)
 {
-	return plpar_hcall_norets(H_CEDE);
+	/*
+	 * We cannot call tracepoints inside RCU idle regions which
+	 * means we must not trace H_CEDE.
+	 */
+	return plpar_hcall_norets_notrace(H_CEDE);
 }
 
 static inline long extended_cede_processor(unsigned long latency_hint)
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 9c9ab2746168..b476a685f066 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -19,6 +19,7 @@
 #ifndef _ASM_POWERPC_PTRACE_H
 #define _ASM_POWERPC_PTRACE_H
 
+#include <linux/err.h>
 #include <uapi/asm/ptrace.h>
 #include <asm/asm-const.h>
 
@@ -152,25 +153,6 @@ extern unsigned long profile_pc(struct pt_regs *regs);
 long do_syscall_trace_enter(struct pt_regs *regs);
 void do_syscall_trace_leave(struct pt_regs *regs);
 
-#define kernel_stack_pointer(regs) ((regs)->gpr[1])
-static inline int is_syscall_success(struct pt_regs *regs)
-{
-	return !(regs->ccr & 0x10000000);
-}
-
-static inline long regs_return_value(struct pt_regs *regs)
-{
-	if (is_syscall_success(regs))
-		return regs->gpr[3];
-	else
-		return -regs->gpr[3];
-}
-
-static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
-{
-	regs->gpr[3] = rc;
-}
-
 #ifdef __powerpc64__
 #define user_mode(regs) ((((regs)->msr) >> MSR_PR_LG) & 0x1)
 #else
@@ -235,6 +217,31 @@ static __always_inline void set_trap_norestart(struct pt_regs *regs)
 	regs->trap |= 0x1;
 }
 
+#define kernel_stack_pointer(regs) ((regs)->gpr[1])
+static inline int is_syscall_success(struct pt_regs *regs)
+{
+	if (trap_is_scv(regs))
+		return !IS_ERR_VALUE((unsigned long)regs->gpr[3]);
+	else
+		return !(regs->ccr & 0x10000000);
+}
+
+static inline long regs_return_value(struct pt_regs *regs)
+{
+	if (trap_is_scv(regs))
+		return regs->gpr[3];
+
+	if (is_syscall_success(regs))
+		return regs->gpr[3];
+	else
+		return -regs->gpr[3];
+}
+
+static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
+{
+	regs->gpr[3] = rc;
+}
+
 #define arch_has_single_step()	(1)
 #define arch_has_block_step()	(true)
 #define ARCH_HAS_USER_SINGLE_STEP_REPORT
diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index fd1b518eed17..ba0f88f3a30d 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/arch/powerpc/include/asm/syscall.h
@@ -41,11 +41,17 @@ static inline void syscall_rollback(struct task_struct *task,
 static inline long syscall_get_error(struct task_struct *task,
 				     struct pt_regs *regs)
 {
-	/*
-	 * If the system call failed,
-	 * regs->gpr[3] contains a positive ERRORCODE.
-	 */
-	return (regs->ccr & 0x10000000UL) ? -regs->gpr[3] : 0;
+	if (trap_is_scv(regs)) {
+		unsigned long error = regs->gpr[3];
+
+		return IS_ERR_VALUE(error) ? error : 0;
+	} else {
+		/*
+		 * If the system call failed,
+		 * regs->gpr[3] contains a positive ERRORCODE.
+		 */
+		return (regs->ccr & 0x10000000UL) ? -regs->gpr[3] : 0;
+	}
 }
 
 static inline long syscall_get_return_value(struct task_struct *task,
@@ -58,18 +64,22 @@ static inline void syscall_set_return_value(struct task_struct *task,
 					    struct pt_regs *regs,
 					    int error, long val)
 {
-	/*
-	 * In the general case it's not obvious that we must deal with CCR
-	 * here, as the syscall exit path will also do that for us. However
-	 * there are some places, eg. the signal code, which check ccr to
-	 * decide if the value in r3 is actually an error.
-	 */
-	if (error) {
-		regs->ccr |= 0x10000000L;
-		regs->gpr[3] = error;
+	if (trap_is_scv(regs)) {
+		regs->gpr[3] = (long) error ?: val;
 	} else {
-		regs->ccr &= ~0x10000000L;
-		regs->gpr[3] = val;
+		/*
+		 * In the general case it's not obvious that we must deal with
+		 * CCR here, as the syscall exit path will also do that for us.
+		 * However there are some places, eg. the signal code, which
+		 * check ccr to decide if the value in r3 is actually an error.
+		 */
+		if (error) {
+			regs->ccr |= 0x10000000L;
+			regs->gpr[3] = error;
+		} else {
+			regs->ccr &= ~0x10000000L;
+			regs->gpr[3] = val;
+		}
 	}
 }
 
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index a09e4240c5b1..22c79ab40006 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -157,7 +157,7 @@ do {								\
 		"2:	lwz%X1 %L0, %L1\n"			\
 		EX_TABLE(1b, %l2)				\
 		EX_TABLE(2b, %l2)				\
-		: "=r" (x)					\
+		: "=&r" (x)					\
 		: "m" (*addr)					\
 		:						\
 		: label)
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 7c3654b0d0f4..f1ae710274bc 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -340,6 +340,12 @@ ret_from_mc_except:
 	andi.	r10,r10,IRQS_DISABLED;	/* yes -> go out of line */ \
 	bne	masked_interrupt_book3e_##n
 
+/*
+ * Additional regs must be re-loaded from paca before EXCEPTION_COMMON* is
+ * called, because that does SAVE_NVGPRS which must see the original register
+ * values, otherwise the scratch values might be restored when exiting the
+ * interrupt.
+ */
 #define PROLOG_ADDITION_2REGS_GEN(n)					    \
 	std	r14,PACA_EXGEN+EX_R14(r13);				    \
 	std	r15,PACA_EXGEN+EX_R15(r13)
@@ -535,6 +541,10 @@ __end_interrupts:
 				PROLOG_ADDITION_2REGS)
 	mfspr	r14,SPRN_DEAR
 	mfspr	r15,SPRN_ESR
+	std	r14,_DAR(r1)
+	std	r15,_DSISR(r1)
+	ld	r14,PACA_EXGEN+EX_R14(r13)
+	ld	r15,PACA_EXGEN+EX_R15(r13)
 	EXCEPTION_COMMON(0x300)
 	b	storage_fault_common
 
@@ -544,6 +554,10 @@ __end_interrupts:
 				PROLOG_ADDITION_2REGS)
 	li	r15,0
 	mr	r14,r10
+	std	r14,_DAR(r1)
+	std	r15,_DSISR(r1)
+	ld	r14,PACA_EXGEN+EX_R14(r13)
+	ld	r15,PACA_EXGEN+EX_R15(r13)
 	EXCEPTION_COMMON(0x400)
 	b	storage_fault_common
 
@@ -557,6 +571,10 @@ __end_interrupts:
 				PROLOG_ADDITION_2REGS)
 	mfspr	r14,SPRN_DEAR
 	mfspr	r15,SPRN_ESR
+	std	r14,_DAR(r1)
+	std	r15,_DSISR(r1)
+	ld	r14,PACA_EXGEN+EX_R14(r13)
+	ld	r15,PACA_EXGEN+EX_R15(r13)
 	EXCEPTION_COMMON(0x600)
 	b	alignment_more	/* no room, go out of line */
 
@@ -565,10 +583,10 @@ __end_interrupts:
 	NORMAL_EXCEPTION_PROLOG(0x700, BOOKE_INTERRUPT_PROGRAM,
 				PROLOG_ADDITION_1REG)
 	mfspr	r14,SPRN_ESR
-	EXCEPTION_COMMON(0x700)
 	std	r14,_DSISR(r1)
-	addi	r3,r1,STACK_FRAME_OVERHEAD
 	ld	r14,PACA_EXGEN+EX_R14(r13)
+	EXCEPTION_COMMON(0x700)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	program_check_exception
 	REST_NVGPRS(r1)
 	b	interrupt_return
@@ -725,11 +743,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	 * normal exception
 	 */
 	mfspr	r14,SPRN_DBSR
-	EXCEPTION_COMMON_CRIT(0xd00)
 	std	r14,_DSISR(r1)
-	addi	r3,r1,STACK_FRAME_OVERHEAD
 	ld	r14,PACA_EXCRIT+EX_R14(r13)
 	ld	r15,PACA_EXCRIT+EX_R15(r13)
+	EXCEPTION_COMMON_CRIT(0xd00)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	DebugException
 	REST_NVGPRS(r1)
 	b	interrupt_return
@@ -796,11 +814,11 @@ kernel_dbg_exc:
 	 * normal exception
 	 */
 	mfspr	r14,SPRN_DBSR
-	EXCEPTION_COMMON_DBG(0xd08)
 	std	r14,_DSISR(r1)
-	addi	r3,r1,STACK_FRAME_OVERHEAD
 	ld	r14,PACA_EXDBG+EX_R14(r13)
 	ld	r15,PACA_EXDBG+EX_R15(r13)
+	EXCEPTION_COMMON_DBG(0xd08)
+	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	DebugException
 	REST_NVGPRS(r1)
 	b	interrupt_return
@@ -931,11 +949,7 @@ masked_interrupt_book3e_0x2c0:
  * original values stashed away in the PACA
  */
 storage_fault_common:
-	std	r14,_DAR(r1)
-	std	r15,_DSISR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	ld	r14,PACA_EXGEN+EX_R14(r13)
-	ld	r15,PACA_EXGEN+EX_R15(r13)
 	bl	do_page_fault
 	b	interrupt_return
 
@@ -944,11 +958,7 @@ storage_fault_common:
  * continues here.
  */
 alignment_more:
-	std	r14,_DAR(r1)
-	std	r15,_DSISR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	ld	r14,PACA_EXGEN+EX_R14(r13)
-	ld	r15,PACA_EXGEN+EX_R15(r13)
 	bl	alignment_exception
 	REST_NVGPRS(r1)
 	b	interrupt_return
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index e4559f8914eb..e0938ba298f2 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -34,9 +34,6 @@ notrace long system_call_exception(long r3, long r4, long r5,
 	syscall_fn f;
 
 	kuep_lock();
-#ifdef CONFIG_PPC32
-	kuap_save_and_lock(regs);
-#endif
 
 	regs->orig_gpr3 = r3;
 
@@ -427,6 +424,7 @@ again:
 
 	/* Restore user access locks last */
 	kuap_user_restore(regs);
+	kuep_unlock();
 
 	return ret;
 }
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index 8b2c1a8553a0..cfc03e016ff2 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -356,13 +356,16 @@ static void __init setup_legacy_serial_console(int console)
 
 static int __init ioremap_legacy_serial_console(void)
 {
-	struct legacy_serial_info *info = &legacy_serial_infos[legacy_serial_console];
-	struct plat_serial8250_port *port = &legacy_serial_ports[legacy_serial_console];
+	struct plat_serial8250_port *port;
+	struct legacy_serial_info *info;
 	void __iomem *vaddr;
 
 	if (legacy_serial_console < 0)
 		return 0;
 
+	info = &legacy_serial_infos[legacy_serial_console];
+	port = &legacy_serial_ports[legacy_serial_console];
+
 	if (!info->early_addr)
 		return 0;
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index b779d25761cf..e42b85e4f1aa 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -369,11 +369,11 @@ void __init early_setup(unsigned long dt_ptr)
 	apply_feature_fixups();
 	setup_feature_keys();
 
-	early_ioremap_setup();
-
 	/* Initialize the hash table or TLB handling */
 	early_init_mmu();
 
+	early_ioremap_setup();
+
 	/*
 	 * After firmware and early platform setup code has set things up,
 	 * we note the SPR values for configurable control/performance
diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h
index f4aafa337c2e..1f07317964e4 100644
--- a/arch/powerpc/kernel/signal.h
+++ b/arch/powerpc/kernel/signal.h
@@ -166,9 +166,9 @@ copy_ckfpr_from_user(struct task_struct *task, void __user *from)
 }
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 #else
-#define unsafe_copy_fpr_to_user(to, task, label) do { } while (0)
+#define unsafe_copy_fpr_to_user(to, task, label) do { if (0) goto label;} while (0)
 
-#define unsafe_copy_fpr_from_user(task, from, label) do { } while (0)
+#define unsafe_copy_fpr_from_user(task, from, label) do { if (0) goto label;} while (0)
 
 static inline unsigned long
 copy_fpr_to_user(void __user *to, struct task_struct *task)
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 2e68fbb57cc6..8f052ff4058c 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -522,7 +522,7 @@
 440	common	process_madvise			sys_process_madvise
 441	common	epoll_pwait2			sys_epoll_pwait2		compat_sys_epoll_pwait2
 442	common	mount_setattr			sys_mount_setattr
-443	common	quotactl_path			sys_quotactl_path
+# 443 reserved for quotactl_path
 444	common	landlock_create_ruleset		sys_landlock_create_ruleset
 445	common	landlock_add_rule		sys_landlock_add_rule
 446	common	landlock_restrict_self		sys_landlock_restrict_self
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 2d9193cd73be..c63e263312a4 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -840,7 +840,7 @@ bool kvm_unmap_gfn_range_hv(struct kvm *kvm, struct kvm_gfn_range *range)
 			kvm_unmap_radix(kvm, range->slot, gfn);
 	} else {
 		for (gfn = range->start; gfn < range->end; gfn++)
-			kvm_unmap_rmapp(kvm, range->slot, range->start);
+			kvm_unmap_rmapp(kvm, range->slot, gfn);
 	}
 
 	return false;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 28a80d240b76..7360350e66ff 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3936,7 +3936,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 				break;
 			}
 			cur = ktime_get();
-		} while (single_task_running() && ktime_before(cur, stop));
+		} while (kvm_vcpu_can_poll(cur, stop));
 
 		spin_lock(&vc->lock);
 		vc->vcore_state = VCORE_INACTIVE;
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 1fd31b4b0e13..fe26f2fa0f3f 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -14,6 +14,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/sched/mm.h>
+#include <linux/stop_machine.h>
 #include <asm/cputable.h>
 #include <asm/code-patching.h>
 #include <asm/page.h>
@@ -149,17 +150,17 @@ static void do_stf_entry_barrier_fixups(enum stf_barrier_type types)
 
 		pr_devel("patching dest %lx\n", (unsigned long)dest);
 
-		patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0]));
-
-		if (types & STF_BARRIER_FALLBACK)
+		// See comment in do_entry_flush_fixups() RE order of patching
+		if (types & STF_BARRIER_FALLBACK) {
+			patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0]));
+			patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2]));
 			patch_branch((struct ppc_inst *)(dest + 1),
-				     (unsigned long)&stf_barrier_fallback,
-				     BRANCH_SET_LINK);
-		else
-			patch_instruction((struct ppc_inst *)(dest + 1),
-					  ppc_inst(instrs[1]));
-
-		patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2]));
+				     (unsigned long)&stf_barrier_fallback, BRANCH_SET_LINK);
+		} else {
+			patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1]));
+			patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2]));
+			patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0]));
+		}
 	}
 
 	printk(KERN_DEBUG "stf-barrier: patched %d entry locations (%s barrier)\n", i,
@@ -227,11 +228,25 @@ static void do_stf_exit_barrier_fixups(enum stf_barrier_type types)
 		                                           : "unknown");
 }
 
+static int __do_stf_barrier_fixups(void *data)
+{
+	enum stf_barrier_type *types = data;
+
+	do_stf_entry_barrier_fixups(*types);
+	do_stf_exit_barrier_fixups(*types);
+
+	return 0;
+}
 
 void do_stf_barrier_fixups(enum stf_barrier_type types)
 {
-	do_stf_entry_barrier_fixups(types);
-	do_stf_exit_barrier_fixups(types);
+	/*
+	 * The call to the fallback entry flush, and the fallback/sync-ori exit
+	 * flush can not be safely patched in/out while other CPUs are executing
+	 * them. So call __do_stf_barrier_fixups() on one CPU while all other CPUs
+	 * spin in the stop machine core with interrupts hard disabled.
+	 */
+	stop_machine(__do_stf_barrier_fixups, &types, NULL);
 }
 
 void do_uaccess_flush_fixups(enum l1d_flush_type types)
@@ -284,8 +299,9 @@ void do_uaccess_flush_fixups(enum l1d_flush_type types)
 						: "unknown");
 }
 
-void do_entry_flush_fixups(enum l1d_flush_type types)
+static int __do_entry_flush_fixups(void *data)
 {
+	enum l1d_flush_type types = *(enum l1d_flush_type *)data;
 	unsigned int instrs[3], *dest;
 	long *start, *end;
 	int i;
@@ -309,6 +325,31 @@ void do_entry_flush_fixups(enum l1d_flush_type types)
 	if (types & L1D_FLUSH_MTTRIG)
 		instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
 
+	/*
+	 * If we're patching in or out the fallback flush we need to be careful about the
+	 * order in which we patch instructions. That's because it's possible we could
+	 * take a page fault after patching one instruction, so the sequence of
+	 * instructions must be safe even in a half patched state.
+	 *
+	 * To make that work, when patching in the fallback flush we patch in this order:
+	 *  - the mflr		(dest)
+	 *  - the mtlr		(dest + 2)
+	 *  - the branch	(dest + 1)
+	 *
+	 * That ensures the sequence is safe to execute at any point. In contrast if we
+	 * patch the mtlr last, it's possible we could return from the branch and not
+	 * restore LR, leading to a crash later.
+	 *
+	 * When patching out the fallback flush (either with nops or another flush type),
+	 * we patch in this order:
+	 *  - the branch	(dest + 1)
+	 *  - the mtlr		(dest + 2)
+	 *  - the mflr		(dest)
+	 *
+	 * Note we are protected by stop_machine() from other CPUs executing the code in a
+	 * semi-patched state.
+	 */
+
 	start = PTRRELOC(&__start___entry_flush_fixup);
 	end = PTRRELOC(&__stop___entry_flush_fixup);
 	for (i = 0; start < end; start++, i++) {
@@ -316,15 +357,16 @@ void do_entry_flush_fixups(enum l1d_flush_type types)
 
 		pr_devel("patching dest %lx\n", (unsigned long)dest);
 
-		patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0]));
-
-		if (types == L1D_FLUSH_FALLBACK)
-			patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&entry_flush_fallback,
-				     BRANCH_SET_LINK);
-		else
+		if (types == L1D_FLUSH_FALLBACK) {
+			patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0]));
+			patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2]));
+			patch_branch((struct ppc_inst *)(dest + 1),
+				     (unsigned long)&entry_flush_fallback, BRANCH_SET_LINK);
+		} else {
 			patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1]));
-
-		patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2]));
+			patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2]));
+			patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0]));
+		}
 	}
 
 	start = PTRRELOC(&__start___scv_entry_flush_fixup);
@@ -334,15 +376,16 @@ void do_entry_flush_fixups(enum l1d_flush_type types)
 
 		pr_devel("patching dest %lx\n", (unsigned long)dest);
 
-		patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0]));
-
-		if (types == L1D_FLUSH_FALLBACK)
-			patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&scv_entry_flush_fallback,
-				     BRANCH_SET_LINK);
-		else
+		if (types == L1D_FLUSH_FALLBACK) {
+			patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0]));
+			patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2]));
+			patch_branch((struct ppc_inst *)(dest + 1),
+				     (unsigned long)&scv_entry_flush_fallback, BRANCH_SET_LINK);
+		} else {
 			patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1]));
-
-		patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2]));
+			patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2]));
+			patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0]));
+		}
 	}
 
 
@@ -354,6 +397,19 @@ void do_entry_flush_fixups(enum l1d_flush_type types)
 							: "ori type" :
 		(types &  L1D_FLUSH_MTTRIG)     ? "mttrig type"
 						: "unknown");
+
+	return 0;
+}
+
+void do_entry_flush_fixups(enum l1d_flush_type types)
+{
+	/*
+	 * The call to the fallback flush can not be safely patched in/out while
+	 * other CPUs are executing it. So call __do_entry_flush_fixups() on one
+	 * CPU while all other CPUs spin in the stop machine core with interrupts
+	 * hard disabled.
+	 */
+	stop_machine(__do_entry_flush_fixups, &types, NULL);
 }
 
 void do_rfi_flush_fixups(enum l1d_flush_type types)
diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S
index 2136e42833af..8a2b8d64265b 100644
--- a/arch/powerpc/platforms/pseries/hvCall.S
+++ b/arch/powerpc/platforms/pseries/hvCall.S
@@ -102,6 +102,16 @@ END_FTR_SECTION(0, 1);						\
 #define HCALL_BRANCH(LABEL)
 #endif
 
+_GLOBAL_TOC(plpar_hcall_norets_notrace)
+	HMT_MEDIUM
+
+	mfcr	r0
+	stw	r0,8(r1)
+	HVSC				/* invoke the hypervisor */
+	lwz	r0,8(r1)
+	mtcrf	0xff,r0
+	blr				/* return r3 = status */
+
 _GLOBAL_TOC(plpar_hcall_norets)
 	HMT_MEDIUM
 
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 1f3152ad7213..dab356e3ff87 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -1829,30 +1829,28 @@ void hcall_tracepoint_unregfunc(void)
 #endif
 
 /*
- * Since the tracing code might execute hcalls we need to guard against
- * recursion. One example of this are spinlocks calling H_YIELD on
- * shared processor partitions.
+ * Keep track of hcall tracing depth and prevent recursion. Warn if any is
+ * detected because it may indicate a problem. This will not catch all
+ * problems with tracing code making hcalls, because the tracing might have
+ * been invoked from a non-hcall, so the first hcall could recurse into it
+ * without warning here, but this better than nothing.
+ *
+ * Hcalls with specific problems being traced should use the _notrace
+ * plpar_hcall variants.
  */
 static DEFINE_PER_CPU(unsigned int, hcall_trace_depth);
 
 
-void __trace_hcall_entry(unsigned long opcode, unsigned long *args)
+notrace void __trace_hcall_entry(unsigned long opcode, unsigned long *args)
 {
 	unsigned long flags;
 	unsigned int *depth;
 
-	/*
-	 * We cannot call tracepoints inside RCU idle regions which
-	 * means we must not trace H_CEDE.
-	 */
-	if (opcode == H_CEDE)
-		return;
-
 	local_irq_save(flags);
 
 	depth = this_cpu_ptr(&hcall_trace_depth);
 
-	if (*depth)
+	if (WARN_ON_ONCE(*depth))
 		goto out;
 
 	(*depth)++;
@@ -1864,19 +1862,16 @@ out:
 	local_irq_restore(flags);
 }
 
-void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf)
+notrace void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf)
 {
 	unsigned long flags;
 	unsigned int *depth;
 
-	if (opcode == H_CEDE)
-		return;
-
 	local_irq_save(flags);
 
 	depth = this_cpu_ptr(&hcall_trace_depth);
 
-	if (*depth)
+	if (*depth) /* Don't warn again on the way out */
 		goto out;
 
 	(*depth)++;