Merge tag 'powerpc-5.7-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull more powerpc updates from Michael Ellerman:
 "The bulk of this is the series to make CONFIG_COMPAT user-selectable,
  it's been around for a long time but was blocked behind the
  syscall-in-C series.

  Plus there's also a few fixes and other minor things.

  Summary:

   - A fix for a crash in machine check handling on pseries (ie. guests)

   - A small series to make it possible to disable CONFIG_COMPAT, and
     turn it off by default for ppc64le where it's not used.

   - A few other miscellaneous fixes and small improvements.

  Thanks to: Alexey Kardashevskiy, Anju T Sudhakar, Arnd Bergmann,
  Christophe Leroy, Dan Carpenter, Ganesh Goudar, Geert Uytterhoeven,
  Geoff Levand, Mahesh Salgaonkar, Markus Elfring, Michal Suchanek,
  Nicholas Piggin, Stephen Boyd, Wen Xiong"

* tag 'powerpc-5.7-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  selftests/powerpc: Always build the tm-poison test 64-bit
  powerpc: Improve ppc_save_regs()
  Revert "powerpc/64: irq_work avoid interrupt when called with hardware irqs enabled"
  powerpc/time: Replace <linux/clk-provider.h> by <linux/of_clk.h>
  powerpc/pseries/ddw: Extend upper limit for huge DMA window for persistent memory
  powerpc/perf: split callchain.c by bitness
  powerpc/64: Make COMPAT user-selectable disabled on littleendian by default.
  powerpc/64: make buildable without CONFIG_COMPAT
  powerpc/perf: consolidate valid_user_sp -> invalid_user_sp
  powerpc/perf: consolidate read_user_stack_32
  powerpc: move common register copy functions from signal_32.c to signal.c
  powerpc: Add back __ARCH_WANT_SYS_LLSEEK macro
  powerpc/ps3: Set CONFIG_UEVENT_HELPER=y in ps3_defconfig
  powerpc/ps3: Remove an unneeded NULL check
  powerpc/ps3: Remove duplicate error message
  powerpc/powernv: Re-enable imc trace-mode in kernel
  powerpc/perf: Implement a global lock to avoid races between trace, core and thread imc events.
  powerpc/pseries: Fix MCE handling on pseries
  selftests/eeh: Skip ahci adapters
  powerpc/64s: Fix doorbell wakeup msgclr optimisation

arch/powerpc/Kconfig

@@ -266,8 +266,9 @@ config PANIC_TIMEOUT
 	default 180
 
 config COMPAT
-	bool
-	default y if PPC64
+	bool "Enable support for 32bit binaries"
+	depends on PPC64
+	default y if !CPU_LITTLE_ENDIAN
 	select COMPAT_BINFMT_ELF
 	select ARCH_WANT_OLD_COMPAT_IPC
 	select COMPAT_OLD_SIGACTION

arch/powerpc/configs/ps3_defconfig

@@ -60,6 +60,8 @@ CONFIG_CFG80211=m
 CONFIG_CFG80211_WEXT=y
 CONFIG_MAC80211=m
 # CONFIG_MAC80211_RC_MINSTREL is not set
+CONFIG_UEVENT_HELPER=y
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=65535

arch/powerpc/include/asm/thread_info.h

@@ -162,10 +162,10 @@ static inline bool test_thread_local_flags(unsigned int flags)
 	return (ti->local_flags & flags) != 0;
 }
 
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_COMPAT
 #define is_32bit_task()	(test_thread_flag(TIF_32BIT))
 #else
-#define is_32bit_task()	(1)
+#define is_32bit_task()	(IS_ENABLED(CONFIG_PPC32))
 #endif
 
 #if defined(CONFIG_PPC64)

arch/powerpc/include/asm/unistd.h

@@ -31,6 +31,7 @@
 #define __ARCH_WANT_SYS_SOCKETCALL
 #define __ARCH_WANT_SYS_FADVISE64
 #define __ARCH_WANT_SYS_GETPGRP
+#define __ARCH_WANT_SYS_LLSEEK
 #define __ARCH_WANT_SYS_NICE
 #define __ARCH_WANT_SYS_OLD_GETRLIMIT
 #define __ARCH_WANT_SYS_OLD_UNAME

arch/powerpc/kernel/Makefile

@@ -40,16 +40,17 @@ CFLAGS_btext.o += -DDISABLE_BRANCH_PROFILING
 endif
 
 obj-y				:= cputable.o syscalls.o \
-				   irq.o align.o signal_32.o pmc.o vdso.o \
+				   irq.o align.o signal_$(BITS).o pmc.o vdso.o \
 				   process.o systbl.o idle.o \
 				   signal.o sysfs.o cacheinfo.o time.o \
 				   prom.o traps.o setup-common.o \
 				   udbg.o misc.o io.o misc_$(BITS).o \
 				   of_platform.o prom_parse.o
 obj-y				+= ptrace/
-obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o signal_64.o \
+obj-$(CONFIG_PPC64)		+= setup_64.o \
 				   paca.o nvram_64.o firmware.o note.o \
 				   syscall_64.o
+obj-$(CONFIG_COMPAT)		+= sys_ppc32.o signal_32.o
 obj-$(CONFIG_VDSO32)		+= vdso32/
 obj-$(CONFIG_PPC_WATCHDOG)	+= watchdog.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o

arch/powerpc/kernel/entry_64.S

@@ -52,8 +52,10 @@
 SYS_CALL_TABLE:
 	.tc sys_call_table[TC],sys_call_table
 
+#ifdef CONFIG_COMPAT
 COMPAT_SYS_CALL_TABLE:
 	.tc compat_sys_call_table[TC],compat_sys_call_table
+#endif
 
 /* This value is used to mark exception frames on the stack. */
 exception_marker:

arch/powerpc/kernel/exceptions-64s.S

@@ -3121,22 +3121,3 @@ handle_dabr_fault:
 	li	r5,SIGSEGV
 	bl	bad_page_fault
 	b	interrupt_return
-
-/*
- * When doorbell is triggered from system reset wakeup, the message is
- * not cleared, so it would fire again when EE is enabled.
- *
- * When coming from local_irq_enable, there may be the same problem if
- * we were hard disabled.
- *
- * Execute msgclr to clear pending exceptions before handling it.
- */
-h_doorbell_common_msgclr:
-	LOAD_REG_IMMEDIATE(r3, PPC_DBELL_MSGTYPE << (63-36))
-	PPC_MSGCLR(3)
-	b 	h_doorbell_common_virt
-
-doorbell_super_common_msgclr:
-	LOAD_REG_IMMEDIATE(r3, PPC_DBELL_MSGTYPE << (63-36))
-	PPC_MSGCLRP(3)
-	b 	doorbell_super_common_virt

arch/powerpc/kernel/irq.c

@@ -527,6 +527,19 @@ void irq_set_pending_from_srr1(unsigned long srr1)
 		return;
 	}
 
+	if (reason == PACA_IRQ_DBELL) {
+		/*
+		 * When doorbell triggers a system reset wakeup, the message
+		 * is not cleared, so if the doorbell interrupt is replayed
+		 * and the IPI handled, the doorbell interrupt would still
+		 * fire when EE is enabled.
+		 *
+		 * To avoid taking the superfluous doorbell interrupt,
+		 * execute a msgclr here before the interrupt is replayed.
+		 */
+		ppc_msgclr(PPC_DBELL_MSGTYPE);
+	}
+
 	/*
 	 * The 0 index (SRR1[42:45]=b0000) must always evaluate to 0,
 	 * so this can be called unconditionally with the SRR1 wake

arch/powerpc/kernel/ppc_save_regs.S

@@ -55,14 +55,17 @@ _GLOBAL(ppc_save_regs)
 	PPC_STL	r29,29*SZL(r3)
 	PPC_STL	r30,30*SZL(r3)
 	PPC_STL	r31,31*SZL(r3)
+	lbz	r0,PACAIRQSOFTMASK(r13)
+	PPC_STL	r0,SOFTE-STACK_FRAME_OVERHEAD(r3)
 #endif
 	/* go up one stack frame for SP */
 	PPC_LL	r4,0(r1)
 	PPC_STL	r4,1*SZL(r3)
 	/* get caller's LR */
 	PPC_LL	r0,LRSAVE(r4)
-	PPC_STL	r0,_NIP-STACK_FRAME_OVERHEAD(r3)
 	PPC_STL	r0,_LINK-STACK_FRAME_OVERHEAD(r3)
+	mflr	r0
+	PPC_STL	r0,_NIP-STACK_FRAME_OVERHEAD(r3)
 	mfmsr	r0
 	PPC_STL	r0,_MSR-STACK_FRAME_OVERHEAD(r3)
 	mfctr	r0
@@ -73,4 +76,5 @@ _GLOBAL(ppc_save_regs)
 	PPC_STL	r0,_CCR-STACK_FRAME_OVERHEAD(r3)
 	li	r0,0
 	PPC_STL	r0,_TRAP-STACK_FRAME_OVERHEAD(r3)
+	PPC_STL	r0,ORIG_GPR3-STACK_FRAME_OVERHEAD(r3)
 	blr

arch/powerpc/kernel/ptrace/Makefile

@@ -6,7 +6,7 @@
 CFLAGS_ptrace-view.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
 obj-y				+= ptrace.o ptrace-view.o
-obj-$(CONFIG_PPC64)		+= ptrace32.o
+obj-$(CONFIG_COMPAT)		+= ptrace32.o
 obj-$(CONFIG_VSX)		+= ptrace-vsx.o
 ifneq ($(CONFIG_VSX),y)
 obj-y				+= ptrace-novsx.o

arch/powerpc/kernel/signal.c

@@ -18,12 +18,153 @@
 #include <linux/syscalls.h>
 #include <asm/hw_breakpoint.h>
 #include <linux/uaccess.h>
+#include <asm/switch_to.h>
 #include <asm/unistd.h>
 #include <asm/debug.h>
 #include <asm/tm.h>
 
 #include "signal.h"
 
+#ifdef CONFIG_VSX
+unsigned long copy_fpr_to_user(void __user *to,
+			       struct task_struct *task)
+{
+	u64 buf[ELF_NFPREG];
+	int i;
+
+	/* save FPR copy to local buffer then write to the thread_struct */
+	for (i = 0; i < (ELF_NFPREG - 1) ; i++)
+		buf[i] = task->thread.TS_FPR(i);
+	buf[i] = task->thread.fp_state.fpscr;
+	return __copy_to_user(to, buf, ELF_NFPREG * sizeof(double));
+}
+
+unsigned long copy_fpr_from_user(struct task_struct *task,
+				 void __user *from)
+{
+	u64 buf[ELF_NFPREG];
+	int i;
+
+	if (__copy_from_user(buf, from, ELF_NFPREG * sizeof(double)))
+		return 1;
+	for (i = 0; i < (ELF_NFPREG - 1) ; i++)
+		task->thread.TS_FPR(i) = buf[i];
+	task->thread.fp_state.fpscr = buf[i];
+
+	return 0;
+}
+
+unsigned long copy_vsx_to_user(void __user *to,
+			       struct task_struct *task)
+{
+	u64 buf[ELF_NVSRHALFREG];
+	int i;
+
+	/* save FPR copy to local buffer then write to the thread_struct */
+	for (i = 0; i < ELF_NVSRHALFREG; i++)
+		buf[i] = task->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
+	return __copy_to_user(to, buf, ELF_NVSRHALFREG * sizeof(double));
+}
+
+unsigned long copy_vsx_from_user(struct task_struct *task,
+				 void __user *from)
+{
+	u64 buf[ELF_NVSRHALFREG];
+	int i;
+
+	if (__copy_from_user(buf, from, ELF_NVSRHALFREG * sizeof(double)))
+		return 1;
+	for (i = 0; i < ELF_NVSRHALFREG ; i++)
+		task->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
+	return 0;
+}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+unsigned long copy_ckfpr_to_user(void __user *to,
+				  struct task_struct *task)
+{
+	u64 buf[ELF_NFPREG];
+	int i;
+
+	/* save FPR copy to local buffer then write to the thread_struct */
+	for (i = 0; i < (ELF_NFPREG - 1) ; i++)
+		buf[i] = task->thread.TS_CKFPR(i);
+	buf[i] = task->thread.ckfp_state.fpscr;
+	return __copy_to_user(to, buf, ELF_NFPREG * sizeof(double));
+}
+
+unsigned long copy_ckfpr_from_user(struct task_struct *task,
+					  void __user *from)
+{
+	u64 buf[ELF_NFPREG];
+	int i;
+
+	if (__copy_from_user(buf, from, ELF_NFPREG * sizeof(double)))
+		return 1;
+	for (i = 0; i < (ELF_NFPREG - 1) ; i++)
+		task->thread.TS_CKFPR(i) = buf[i];
+	task->thread.ckfp_state.fpscr = buf[i];
+
+	return 0;
+}
+
+unsigned long copy_ckvsx_to_user(void __user *to,
+				  struct task_struct *task)
+{
+	u64 buf[ELF_NVSRHALFREG];
+	int i;
+
+	/* save FPR copy to local buffer then write to the thread_struct */
+	for (i = 0; i < ELF_NVSRHALFREG; i++)
+		buf[i] = task->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET];
+	return __copy_to_user(to, buf, ELF_NVSRHALFREG * sizeof(double));
+}
+
+unsigned long copy_ckvsx_from_user(struct task_struct *task,
+					  void __user *from)
+{
+	u64 buf[ELF_NVSRHALFREG];
+	int i;
+
+	if (__copy_from_user(buf, from, ELF_NVSRHALFREG * sizeof(double)))
+		return 1;
+	for (i = 0; i < ELF_NVSRHALFREG ; i++)
+		task->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
+	return 0;
+}
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+#else
+inline unsigned long copy_fpr_to_user(void __user *to,
+				      struct task_struct *task)
+{
+	return __copy_to_user(to, task->thread.fp_state.fpr,
+			      ELF_NFPREG * sizeof(double));
+}
+
+inline unsigned long copy_fpr_from_user(struct task_struct *task,
+					void __user *from)
+{
+	return __copy_from_user(task->thread.fp_state.fpr, from,
+			      ELF_NFPREG * sizeof(double));
+}
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+inline unsigned long copy_ckfpr_to_user(void __user *to,
+					 struct task_struct *task)
+{
+	return __copy_to_user(to, task->thread.ckfp_state.fpr,
+			      ELF_NFPREG * sizeof(double));
+}
+
+inline unsigned long copy_ckfpr_from_user(struct task_struct *task,
+						 void __user *from)
+{
+	return __copy_from_user(task->thread.ckfp_state.fpr, from,
+				ELF_NFPREG * sizeof(double));
+}
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+#endif
+
 /* Log an error when sending an unhandled signal to a process. Controlled
  * through debug.exception-trace sysctl.
  */
@@ -106,7 +247,6 @@ static void do_signal(struct task_struct *tsk)
 	sigset_t *oldset = sigmask_to_save();
 	struct ksignal ksig = { .sig = 0 };
 	int ret;
-	int is32 = is_32bit_task();
 
 	BUG_ON(tsk != current);
 
@@ -136,7 +276,7 @@ static void do_signal(struct task_struct *tsk)
 
 	rseq_signal_deliver(&ksig, tsk->thread.regs);
 
-	if (is32) {
+	if (is_32bit_task()) {
         	if (ksig.ka.sa.sa_flags & SA_SIGINFO)
 			ret = handle_rt_signal32(&ksig, oldset, tsk);
 		else

arch/powerpc/kernel/signal_32.c

@@ -235,146 +235,6 @@ struct rt_sigframe {
 	int			abigap[56];
 };
 
-#ifdef CONFIG_VSX
-unsigned long copy_fpr_to_user(void __user *to,
-			       struct task_struct *task)
-{
-	u64 buf[ELF_NFPREG];
-	int i;
-
-	/* save FPR copy to local buffer then write to the thread_struct */
-	for (i = 0; i < (ELF_NFPREG - 1) ; i++)
-		buf[i] = task->thread.TS_FPR(i);
-	buf[i] = task->thread.fp_state.fpscr;
-	return __copy_to_user(to, buf, ELF_NFPREG * sizeof(double));
-}
-
-unsigned long copy_fpr_from_user(struct task_struct *task,
-				 void __user *from)
-{
-	u64 buf[ELF_NFPREG];
-	int i;
-
-	if (__copy_from_user(buf, from, ELF_NFPREG * sizeof(double)))
-		return 1;
-	for (i = 0; i < (ELF_NFPREG - 1) ; i++)
-		task->thread.TS_FPR(i) = buf[i];
-	task->thread.fp_state.fpscr = buf[i];
-
-	return 0;
-}
-
-unsigned long copy_vsx_to_user(void __user *to,
-			       struct task_struct *task)
-{
-	u64 buf[ELF_NVSRHALFREG];
-	int i;
-
-	/* save FPR copy to local buffer then write to the thread_struct */
-	for (i = 0; i < ELF_NVSRHALFREG; i++)
-		buf[i] = task->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
-	return __copy_to_user(to, buf, ELF_NVSRHALFREG * sizeof(double));
-}
-
-unsigned long copy_vsx_from_user(struct task_struct *task,
-				 void __user *from)
-{
-	u64 buf[ELF_NVSRHALFREG];
-	int i;
-
-	if (__copy_from_user(buf, from, ELF_NVSRHALFREG * sizeof(double)))
-		return 1;
-	for (i = 0; i < ELF_NVSRHALFREG ; i++)
-		task->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
-	return 0;
-}
-
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-unsigned long copy_ckfpr_to_user(void __user *to,
-				  struct task_struct *task)
-{
-	u64 buf[ELF_NFPREG];
-	int i;
-
-	/* save FPR copy to local buffer then write to the thread_struct */
-	for (i = 0; i < (ELF_NFPREG - 1) ; i++)
-		buf[i] = task->thread.TS_CKFPR(i);
-	buf[i] = task->thread.ckfp_state.fpscr;
-	return __copy_to_user(to, buf, ELF_NFPREG * sizeof(double));
-}
-
-unsigned long copy_ckfpr_from_user(struct task_struct *task,
-					  void __user *from)
-{
-	u64 buf[ELF_NFPREG];
-	int i;
-
-	if (__copy_from_user(buf, from, ELF_NFPREG * sizeof(double)))
-		return 1;
-	for (i = 0; i < (ELF_NFPREG - 1) ; i++)
-		task->thread.TS_CKFPR(i) = buf[i];
-	task->thread.ckfp_state.fpscr = buf[i];
-
-	return 0;
-}
-
-unsigned long copy_ckvsx_to_user(void __user *to,
-				  struct task_struct *task)
-{
-	u64 buf[ELF_NVSRHALFREG];
-	int i;
-
-	/* save FPR copy to local buffer then write to the thread_struct */
-	for (i = 0; i < ELF_NVSRHALFREG; i++)
-		buf[i] = task->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET];
-	return __copy_to_user(to, buf, ELF_NVSRHALFREG * sizeof(double));
-}
-
-unsigned long copy_ckvsx_from_user(struct task_struct *task,
-					  void __user *from)
-{
-	u64 buf[ELF_NVSRHALFREG];
-	int i;
-
-	if (__copy_from_user(buf, from, ELF_NVSRHALFREG * sizeof(double)))
-		return 1;
-	for (i = 0; i < ELF_NVSRHALFREG ; i++)
-		task->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
-	return 0;
-}
-#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
-#else
-inline unsigned long copy_fpr_to_user(void __user *to,
-				      struct task_struct *task)
-{
-	return __copy_to_user(to, task->thread.fp_state.fpr,
-			      ELF_NFPREG * sizeof(double));
-}
-
-inline unsigned long copy_fpr_from_user(struct task_struct *task,
-					void __user *from)
-{
-	return __copy_from_user(task->thread.fp_state.fpr, from,
-			      ELF_NFPREG * sizeof(double));
-}
-
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-inline unsigned long copy_ckfpr_to_user(void __user *to,
-					 struct task_struct *task)
-{
-	return __copy_to_user(to, task->thread.ckfp_state.fpr,
-			      ELF_NFPREG * sizeof(double));
-}
-
-inline unsigned long copy_ckfpr_from_user(struct task_struct *task,
-						 void __user *from)
-{
-	return __copy_from_user(task->thread.ckfp_state.fpr, from,
-				ELF_NFPREG * sizeof(double));
-}
-#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
-#endif
-
 /*
  * Save the current user registers on the user stack.
  * We only save the altivec/spe registers if the process has used

arch/powerpc/kernel/syscall_64.c

@@ -22,7 +22,6 @@ notrace long system_call_exception(long r3, long r4, long r5,
 				   long r6, long r7, long r8,
 				   unsigned long r0, struct pt_regs *regs)
 {
-	unsigned long ti_flags;
 	syscall_fn f;
 
 	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
@@ -60,8 +59,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
 
 	local_irq_enable();
 
-	ti_flags = current_thread_info()->flags;
-	if (unlikely(ti_flags & _TIF_SYSCALL_DOTRACE)) {
+	if (unlikely(current_thread_info()->flags & _TIF_SYSCALL_DOTRACE)) {
 		/*
 		 * We use the return value of do_syscall_trace_enter() as the
 		 * syscall number. If the syscall was rejected for any reason
@@ -86,7 +84,7 @@ notrace long system_call_exception(long r3, long r4, long r5,
 	/* May be faster to do array_index_nospec? */
 	barrier_nospec();
 
-	if (unlikely(ti_flags & _TIF_32BIT)) {
+	if (unlikely(is_32bit_task())) {
 		f = (void *)compat_sys_call_table[r0];
 
 		r3 &= 0x00000000ffffffffULL;

arch/powerpc/kernel/time.c

@@ -50,7 +50,7 @@
 #include <linux/irq.h>
 #include <linux/delay.h>
 #include <linux/irq_work.h>
-#include <linux/clk-provider.h>
+#include <linux/of_clk.h>
 #include <linux/suspend.h>
 #include <linux/sched/cputime.h>
 #include <linux/processor.h>
@@ -522,35 +522,6 @@ static inline void clear_irq_work_pending(void)
 		"i" (offsetof(struct paca_struct, irq_work_pending)));
 }
 
-void arch_irq_work_raise(void)
-{
-	preempt_disable();
-	set_irq_work_pending_flag();
-	/*
-	 * Non-nmi code running with interrupts disabled will replay
-	 * irq_happened before it re-enables interrupts, so setthe
-	 * decrementer there instead of causing a hardware exception
-	 * which would immediately hit the masked interrupt handler
-	 * and have the net effect of setting the decrementer in
-	 * irq_happened.
-	 *
-	 * NMI interrupts can not check this when they return, so the
-	 * decrementer hardware exception is raised, which will fire
-	 * when interrupts are next enabled.
-	 *
-	 * BookE does not support this yet, it must audit all NMI
-	 * interrupt handlers to ensure they call nmi_enter() so this
-	 * check would be correct.
-	 */
-	if (IS_ENABLED(CONFIG_BOOKE) || !irqs_disabled() || in_nmi()) {
-		set_dec(1);
-	} else {
-		hard_irq_disable();
-		local_paca->irq_happened |= PACA_IRQ_DEC;
-	}
-	preempt_enable();
-}
-
 #else /* 32-bit */
 
 DEFINE_PER_CPU(u8, irq_work_pending);
@@ -559,16 +530,27 @@ DEFINE_PER_CPU(u8, irq_work_pending);
 #define test_irq_work_pending()		__this_cpu_read(irq_work_pending)
 #define clear_irq_work_pending()	__this_cpu_write(irq_work_pending, 0)
 
+#endif /* 32 vs 64 bit */
+
 void arch_irq_work_raise(void)
 {
+	/*
+	 * 64-bit code that uses irq soft-mask can just cause an immediate
+	 * interrupt here that gets soft masked, if this is called under
+	 * local_irq_disable(). It might be possible to prevent that happening
+	 * by noticing interrupts are disabled and setting decrementer pending
+	 * to be replayed when irqs are enabled. The problem there is that
+	 * tracing can call irq_work_raise, including in code that does low
+	 * level manipulations of irq soft-mask state (e.g., trace_hardirqs_on)
+	 * which could get tangled up if we're messing with the same state
+	 * here.
+	 */
 	preempt_disable();
 	set_irq_work_pending_flag();
 	set_dec(1);
 	preempt_enable();
 }
 
-#endif /* 32 vs 64 bit */
-
 #else  /* CONFIG_IRQ_WORK */
 
 #define test_irq_work_pending()	0
@@ -1149,9 +1131,7 @@ void __init time_init(void)
 	init_decrementer_clockevent();
 	tick_setup_hrtimer_broadcast();
 
-#ifdef CONFIG_COMMON_CLK
 	of_clk_init(NULL);
-#endif
 }
 
 /*

arch/powerpc/kernel/vdso.c

@@ -651,7 +651,8 @@ static void __init vdso_setup_syscall_map(void)
 		if (sys_call_table[i] != sys_ni_syscall)
 			vdso_data->syscall_map_64[i >> 5] |=
 				0x80000000UL >> (i & 0x1f);
-		if (compat_sys_call_table[i] != sys_ni_syscall)
+		if (IS_ENABLED(CONFIG_COMPAT) &&
+		    compat_sys_call_table[i] != sys_ni_syscall)
 			vdso_data->syscall_map_32[i >> 5] |=
 				0x80000000UL >> (i & 0x1f);
 #else /* CONFIG_PPC64 */

arch/powerpc/perf/Makefile

 # SPDX-License-Identifier: GPL-2.0
 
-obj-$(CONFIG_PERF_EVENTS)	+= callchain.o perf_regs.o
+obj-$(CONFIG_PERF_EVENTS)	+= callchain.o callchain_$(BITS).o perf_regs.o
+ifdef CONFIG_COMPAT
+obj-$(CONFIG_PERF_EVENTS)	+= callchain_32.o
+endif
 
 obj-$(CONFIG_PPC_PERF_CTRS)	+= core-book3s.o bhrb.o
 obj64-$(CONFIG_PPC_PERF_CTRS)	+= ppc970-pmu.o power5-pmu.o \

arch/powerpc/perf/callchain.c

@@ -15,11 +15,9 @@
 #include <asm/sigcontext.h>
 #include <asm/ucontext.h>
 #include <asm/vdso.h>
-#ifdef CONFIG_PPC64
-#include "../kernel/ppc32.h"
-#endif
 #include <asm/pte-walk.h>
 
+#include "callchain.h"
 
 /*
  * Is sp valid as the address of the next kernel stack frame after prev_sp?
@@ -102,358 +100,6 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 	}
 }
 
-#ifdef CONFIG_PPC64
-/*
- * On 64-bit we don't want to invoke hash_page on user addresses from
- * interrupt context, so if the access faults, we read the page tables
- * to find which page (if any) is mapped and access it directly.
- */
-static int read_user_stack_slow(void __user *ptr, void *buf, int nb)
-{
-	int ret = -EFAULT;
-	pgd_t *pgdir;
-	pte_t *ptep, pte;
-	unsigned shift;
-	unsigned long addr = (unsigned long) ptr;
-	unsigned long offset;
-	unsigned long pfn, flags;
-	void *kaddr;
-
-	pgdir = current->mm->pgd;
-	if (!pgdir)
-		return -EFAULT;
-
-	local_irq_save(flags);
-	ptep = find_current_mm_pte(pgdir, addr, NULL, &shift);
-	if (!ptep)
-		goto err_out;
-	if (!shift)
-		shift = PAGE_SHIFT;
-
-	/* align address to page boundary */
-	offset = addr & ((1UL << shift) - 1);
-
-	pte = READ_ONCE(*ptep);
-	if (!pte_present(pte) || !pte_user(pte))
-		goto err_out;
-	pfn = pte_pfn(pte);
-	if (!page_is_ram(pfn))
-		goto err_out;
-
-	/* no highmem to worry about here */
-	kaddr = pfn_to_kaddr(pfn);
-	memcpy(buf, kaddr + offset, nb);
-	ret = 0;
-err_out:
-	local_irq_restore(flags);
-	return ret;
-}
-
-static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret)
-{
-	if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned long) ||
-	    ((unsigned long)ptr & 7))
-		return -EFAULT;
-
-	if (!probe_user_read(ret, ptr, sizeof(*ret)))
-		return 0;
-
-	return read_user_stack_slow(ptr, ret, 8);
-}
-
-static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
-{
-	if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned int) ||
-	    ((unsigned long)ptr & 3))
-		return -EFAULT;
-
-	if (!probe_user_read(ret, ptr, sizeof(*ret)))
-		return 0;
-
-	return read_user_stack_slow(ptr, ret, 4);
-}
-
-static inline int valid_user_sp(unsigned long sp, int is_64)
-{
-	if (!sp || (sp & 7) || sp > (is_64 ? TASK_SIZE : 0x100000000UL) - 32)
-		return 0;
-	return 1;
-}
-
-/*
- * 64-bit user processes use the same stack frame for RT and non-RT signals.
- */
-struct signal_frame_64 {
-	char		dummy[__SIGNAL_FRAMESIZE];
-	struct ucontext	uc;
-	unsigned long	unused[2];
-	unsigned int	tramp[6];
-	struct siginfo	*pinfo;
-	void		*puc;
-	struct siginfo	info;
-	char		abigap[288];
-};
-
-static int is_sigreturn_64_address(unsigned long nip, unsigned long fp)
-{
-	if (nip == fp + offsetof(struct signal_frame_64, tramp))
-		return 1;
-	if (vdso64_rt_sigtramp && current->mm->context.vdso_base &&
-	    nip == current->mm->context.vdso_base + vdso64_rt_sigtramp)
-		return 1;
-	return 0;
-}
-
-/*
- * Do some sanity checking on the signal frame pointed to by sp.
- * We check the pinfo and puc pointers in the frame.
- */
-static int sane_signal_64_frame(unsigned long sp)
-{
-	struct signal_frame_64 __user *sf;
-	unsigned long pinfo, puc;
-
-	sf = (struct signal_frame_64 __user *) sp;
-	if (read_user_stack_64((unsigned long __user *) &sf->pinfo, &pinfo) ||
-	    read_user_stack_64((unsigned long __user *) &sf->puc, &puc))
-		return 0;
-	return pinfo == (unsigned long) &sf->info &&
-		puc == (unsigned long) &sf->uc;
-}
-
-static void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
-				   struct pt_regs *regs)
-{
-	unsigned long sp, next_sp;
-	unsigned long next_ip;
-	unsigned long lr;
-	long level = 0;
-	struct signal_frame_64 __user *sigframe;
-	unsigned long __user *fp, *uregs;
-
-	next_ip = perf_instruction_pointer(regs);
-	lr = regs->link;
-	sp = regs->gpr[1];
-	perf_callchain_store(entry, next_ip);
-
-	while (entry->nr < entry->max_stack) {
-		fp = (unsigned long __user *) sp;
-		if (!valid_user_sp(sp, 1) || read_user_stack_64(fp, &next_sp))
-			return;
-		if (level > 0 && read_user_stack_64(&fp[2], &next_ip))
-			return;
-
-		/*
-		 * Note: the next_sp - sp >= signal frame size check
-		 * is true when next_sp < sp, which can happen when
-		 * transitioning from an alternate signal stack to the
-		 * normal stack.
-		 */
-		if (next_sp - sp >= sizeof(struct signal_frame_64) &&
-		    (is_sigreturn_64_address(next_ip, sp) ||
-		     (level <= 1 && is_sigreturn_64_address(lr, sp))) &&
-		    sane_signal_64_frame(sp)) {
-			/*
-			 * This looks like an signal frame
-			 */
-			sigframe = (struct signal_frame_64 __user *) sp;
-			uregs = sigframe->uc.uc_mcontext.gp_regs;
-			if (read_user_stack_64(&uregs[PT_NIP], &next_ip) ||
-			    read_user_stack_64(&uregs[PT_LNK], &lr) ||
-			    read_user_stack_64(&uregs[PT_R1], &sp))
-				return;
-			level = 0;
-			perf_callchain_store_context(entry, PERF_CONTEXT_USER);
-			perf_callchain_store(entry, next_ip);
-			continue;
-		}
-
-		if (level == 0)
-			next_ip = lr;
-		perf_callchain_store(entry, next_ip);
-		++level;
-		sp = next_sp;
-	}
-}
-
-#else  /* CONFIG_PPC64 */
-/*
- * On 32-bit we just access the address and let hash_page create a
- * HPTE if necessary, so there is no need to fall back to reading
- * the page tables.  Since this is called at interrupt level,
- * do_page_fault() won't treat a DSI as a page fault.
- */
-static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
-{
-	if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned int) ||
-	    ((unsigned long)ptr & 3))
-		return -EFAULT;
-
-	return probe_user_read(ret, ptr, sizeof(*ret));
-}
-
-static inline void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
-					  struct pt_regs *regs)
-{
-}
-
-static inline int valid_user_sp(unsigned long sp, int is_64)
-{
-	if (!sp || (sp & 7) || sp > TASK_SIZE - 32)
-		return 0;
-	return 1;
-}
-
-#define __SIGNAL_FRAMESIZE32	__SIGNAL_FRAMESIZE
-#define sigcontext32		sigcontext
-#define mcontext32		mcontext
-#define ucontext32		ucontext
-#define compat_siginfo_t	struct siginfo
-
-#endif /* CONFIG_PPC64 */
-
-/*
- * Layout for non-RT signal frames
- */
-struct signal_frame_32 {
-	char			dummy[__SIGNAL_FRAMESIZE32];
-	struct sigcontext32	sctx;
-	struct mcontext32	mctx;
-	int			abigap[56];
-};
-
-/*
- * Layout for RT signal frames
- */
-struct rt_signal_frame_32 {
-	char			dummy[__SIGNAL_FRAMESIZE32 + 16];
-	compat_siginfo_t	info;
-	struct ucontext32	uc;
-	int			abigap[56];
-};
-
-static int is_sigreturn_32_address(unsigned int nip, unsigned int fp)
-{
-	if (nip == fp + offsetof(struct signal_frame_32, mctx.mc_pad))
-		return 1;
-	if (vdso32_sigtramp && current->mm->context.vdso_base &&
-	    nip == current->mm->context.vdso_base + vdso32_sigtramp)
-		return 1;
-	return 0;
-}
-
-static int is_rt_sigreturn_32_address(unsigned int nip, unsigned int fp)
-{
-	if (nip == fp + offsetof(struct rt_signal_frame_32,
-				 uc.uc_mcontext.mc_pad))
-		return 1;
-	if (vdso32_rt_sigtramp && current->mm->context.vdso_base &&
-	    nip == current->mm->context.vdso_base + vdso32_rt_sigtramp)
-		return 1;
-	return 0;
-}
-
-static int sane_signal_32_frame(unsigned int sp)
-{
-	struct signal_frame_32 __user *sf;
-	unsigned int regs;
-
-	sf = (struct signal_frame_32 __user *) (unsigned long) sp;
-	if (read_user_stack_32((unsigned int __user *) &sf->sctx.regs, &regs))
-		return 0;
-	return regs == (unsigned long) &sf->mctx;
-}
-
-static int sane_rt_signal_32_frame(unsigned int sp)
-{
-	struct rt_signal_frame_32 __user *sf;
-	unsigned int regs;
-
-	sf = (struct rt_signal_frame_32 __user *) (unsigned long) sp;
-	if (read_user_stack_32((unsigned int __user *) &sf->uc.uc_regs, &regs))
-		return 0;
-	return regs == (unsigned long) &sf->uc.uc_mcontext;
-}
-
-static unsigned int __user *signal_frame_32_regs(unsigned int sp,
-				unsigned int next_sp, unsigned int next_ip)
-{
-	struct mcontext32 __user *mctx = NULL;
-	struct signal_frame_32 __user *sf;
-	struct rt_signal_frame_32 __user *rt_sf;
-
-	/*
-	 * Note: the next_sp - sp >= signal frame size check
-	 * is true when next_sp < sp, for example, when
-	 * transitioning from an alternate signal stack to the
-	 * normal stack.
-	 */
-	if (next_sp - sp >= sizeof(struct signal_frame_32) &&
-	    is_sigreturn_32_address(next_ip, sp) &&
-	    sane_signal_32_frame(sp)) {
-		sf = (struct signal_frame_32 __user *) (unsigned long) sp;
-		mctx = &sf->mctx;
-	}
-
-	if (!mctx && next_sp - sp >= sizeof(struct rt_signal_frame_32) &&
-	    is_rt_sigreturn_32_address(next_ip, sp) &&
-	    sane_rt_signal_32_frame(sp)) {
-		rt_sf = (struct rt_signal_frame_32 __user *) (unsigned long) sp;
-		mctx = &rt_sf->uc.uc_mcontext;
-	}
-
-	if (!mctx)
-		return NULL;
-	return mctx->mc_gregs;
-}
-
-static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
-				   struct pt_regs *regs)
-{
-	unsigned int sp, next_sp;
-	unsigned int next_ip;
-	unsigned int lr;
-	long level = 0;
-	unsigned int __user *fp, *uregs;
-
-	next_ip = perf_instruction_pointer(regs);
-	lr = regs->link;
-	sp = regs->gpr[1];
-	perf_callchain_store(entry, next_ip);
-
-	while (entry->nr < entry->max_stack) {
-		fp = (unsigned int __user *) (unsigned long) sp;
-		if (!valid_user_sp(sp, 0) || read_user_stack_32(fp, &next_sp))
-			return;
-		if (level > 0 && read_user_stack_32(&fp[1], &next_ip))
-			return;
-
-		uregs = signal_frame_32_regs(sp, next_sp, next_ip);
-		if (!uregs && level <= 1)
-			uregs = signal_frame_32_regs(sp, next_sp, lr);
-		if (uregs) {
-			/*
-			 * This looks like an signal frame, so restart
-			 * the stack trace with the values in it.
-			 */
-			if (read_user_stack_32(&uregs[PT_NIP], &next_ip) ||
-			    read_user_stack_32(&uregs[PT_LNK], &lr) ||
-			    read_user_stack_32(&uregs[PT_R1], &sp))
-				return;
-			level = 0;
-			perf_callchain_store_context(entry, PERF_CONTEXT_USER);
-			perf_callchain_store(entry, next_ip);
-			continue;
-		}
-
-		if (level == 0)
-			next_ip = lr;
-		perf_callchain_store(entry, next_ip);
-		++level;
-		sp = next_sp;
-	}
-}
-
 void
 perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {

arch/powerpc/perf/callchain.h

+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _POWERPC_PERF_CALLCHAIN_H
+#define _POWERPC_PERF_CALLCHAIN_H
+
+int read_user_stack_slow(void __user *ptr, void *buf, int nb);
+void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
+			    struct pt_regs *regs);
+void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
+			    struct pt_regs *regs);
+
+static inline bool invalid_user_sp(unsigned long sp)
+{
+	unsigned long mask = is_32bit_task() ? 3 : 7;
+	unsigned long top = STACK_TOP - (is_32bit_task() ? 16 : 32);
+
+	return (!sp || (sp & mask) || (sp > top));
+}
+
+#endif /* _POWERPC_PERF_CALLCHAIN_H */

arch/powerpc/perf/callchain_32.c

+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Performance counter callchain support - powerpc architecture code
+ *
+ * Copyright © 2009 Paul Mackerras, IBM Corporation.
+ */
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/perf_event.h>
+#include <linux/percpu.h>
+#include <linux/uaccess.h>
+#include <linux/mm.h>
+#include <asm/ptrace.h>
+#include <asm/pgtable.h>
+#include <asm/sigcontext.h>
+#include <asm/ucontext.h>
+#include <asm/vdso.h>
+#include <asm/pte-walk.h>
+
+#include "callchain.h"
+
+#ifdef CONFIG_PPC64
+#include "../kernel/ppc32.h"
+#else  /* CONFIG_PPC64 */
+
+#define __SIGNAL_FRAMESIZE32	__SIGNAL_FRAMESIZE
+#define sigcontext32		sigcontext
+#define mcontext32		mcontext
+#define ucontext32		ucontext
+#define compat_siginfo_t	struct siginfo
+
+#endif /* CONFIG_PPC64 */
+
+/*
+ * On 32-bit we just access the address and let hash_page create a
+ * HPTE if necessary, so there is no need to fall back to reading
+ * the page tables.  Since this is called at interrupt level,
+ * do_page_fault() won't treat a DSI as a page fault.
+ */
+static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
+{
+	int rc;
+
+	if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned int) ||
+	    ((unsigned long)ptr & 3))
+		return -EFAULT;
+
+	rc = probe_user_read(ret, ptr, sizeof(*ret));
+
+	if (IS_ENABLED(CONFIG_PPC64) && rc)
+		return read_user_stack_slow(ptr, ret, 4);
+
+	return rc;
+}
+
+/*
+ * Layout for non-RT signal frames
+ */
+struct signal_frame_32 {
+	char			dummy[__SIGNAL_FRAMESIZE32];
+	struct sigcontext32	sctx;
+	struct mcontext32	mctx;
+	int			abigap[56];
+};
+
+/*
+ * Layout for RT signal frames
+ */
+struct rt_signal_frame_32 {
+	char			dummy[__SIGNAL_FRAMESIZE32 + 16];
+	compat_siginfo_t	info;
+	struct ucontext32	uc;
+	int			abigap[56];
+};
+
+static int is_sigreturn_32_address(unsigned int nip, unsigned int fp)
+{
+	if (nip == fp + offsetof(struct signal_frame_32, mctx.mc_pad))
+		return 1;
+	if (vdso32_sigtramp && current->mm->context.vdso_base &&
+	    nip == current->mm->context.vdso_base + vdso32_sigtramp)
+		return 1;
+	return 0;
+}
+
+static int is_rt_sigreturn_32_address(unsigned int nip, unsigned int fp)
+{
+	if (nip == fp + offsetof(struct rt_signal_frame_32,
+				 uc.uc_mcontext.mc_pad))
+		return 1;
+	if (vdso32_rt_sigtramp && current->mm->context.vdso_base &&
+	    nip == current->mm->context.vdso_base + vdso32_rt_sigtramp)
+		return 1;
+	return 0;
+}
+
+static int sane_signal_32_frame(unsigned int sp)
+{
+	struct signal_frame_32 __user *sf;
+	unsigned int regs;
+
+	sf = (struct signal_frame_32 __user *) (unsigned long) sp;
+	if (read_user_stack_32((unsigned int __user *) &sf->sctx.regs, &regs))
+		return 0;
+	return regs == (unsigned long) &sf->mctx;
+}
+
+static int sane_rt_signal_32_frame(unsigned int sp)
+{
+	struct rt_signal_frame_32 __user *sf;
+	unsigned int regs;
+
+	sf = (struct rt_signal_frame_32 __user *) (unsigned long) sp;
+	if (read_user_stack_32((unsigned int __user *) &sf->uc.uc_regs, &regs))
+		return 0;
+	return regs == (unsigned long) &sf->uc.uc_mcontext;
+}
+
+static unsigned int __user *signal_frame_32_regs(unsigned int sp,
+				unsigned int next_sp, unsigned int next_ip)
+{
+	struct mcontext32 __user *mctx = NULL;
+	struct signal_frame_32 __user *sf;
+	struct rt_signal_frame_32 __user *rt_sf;
+
+	/*
+	 * Note: the next_sp - sp >= signal frame size check
+	 * is true when next_sp < sp, for example, when
+	 * transitioning from an alternate signal stack to the
+	 * normal stack.
+	 */
+	if (next_sp - sp >= sizeof(struct signal_frame_32) &&
+	    is_sigreturn_32_address(next_ip, sp) &&
+	    sane_signal_32_frame(sp)) {
+		sf = (struct signal_frame_32 __user *) (unsigned long) sp;
+		mctx = &sf->mctx;
+	}
+
+	if (!mctx && next_sp - sp >= sizeof(struct rt_signal_frame_32) &&
+	    is_rt_sigreturn_32_address(next_ip, sp) &&
+	    sane_rt_signal_32_frame(sp)) {
+		rt_sf = (struct rt_signal_frame_32 __user *) (unsigned long) sp;
+		mctx = &rt_sf->uc.uc_mcontext;
+	}
+
+	if (!mctx)
+		return NULL;
+	return mctx->mc_gregs;
+}
+
+void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
+			    struct pt_regs *regs)
+{
+	unsigned int sp, next_sp;
+	unsigned int next_ip;
+	unsigned int lr;
+	long level = 0;
+	unsigned int __user *fp, *uregs;
+
+	next_ip = perf_instruction_pointer(regs);
+	lr = regs->link;
+	sp = regs->gpr[1];
+	perf_callchain_store(entry, next_ip);
+
+	while (entry->nr < entry->max_stack) {
+		fp = (unsigned int __user *) (unsigned long) sp;
+		if (invalid_user_sp(sp) || read_user_stack_32(fp, &next_sp))
+			return;
+		if (level > 0 && read_user_stack_32(&fp[1], &next_ip))
+			return;
+
+		uregs = signal_frame_32_regs(sp, next_sp, next_ip);
+		if (!uregs && level <= 1)
+			uregs = signal_frame_32_regs(sp, next_sp, lr);
+		if (uregs) {
+			/*
+			 * This looks like an signal frame, so restart
+			 * the stack trace with the values in it.
+			 */
+			if (read_user_stack_32(&uregs[PT_NIP], &next_ip) ||
+			    read_user_stack_32(&uregs[PT_LNK], &lr) ||
+			    read_user_stack_32(&uregs[PT_R1], &sp))
+				return;
+			level = 0;
+			perf_callchain_store_context(entry, PERF_CONTEXT_USER);
+			perf_callchain_store(entry, next_ip);
+			continue;
+		}
+
+		if (level == 0)
+			next_ip = lr;
+		perf_callchain_store(entry, next_ip);
+		++level;
+		sp = next_sp;
+	}
+}

arch/powerpc/perf/callchain_64.c

+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Performance counter callchain support - powerpc architecture code
+ *
+ * Copyright © 2009 Paul Mackerras, IBM Corporation.
+ */
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/perf_event.h>
+#include <linux/percpu.h>
+#include <linux/uaccess.h>
+#include <linux/mm.h>
+#include <asm/ptrace.h>
+#include <asm/pgtable.h>
+#include <asm/sigcontext.h>
+#include <asm/ucontext.h>
+#include <asm/vdso.h>
+#include <asm/pte-walk.h>
+
+#include "callchain.h"
+
+/*
+ * On 64-bit we don't want to invoke hash_page on user addresses from
+ * interrupt context, so if the access faults, we read the page tables
+ * to find which page (if any) is mapped and access it directly.
+ */
+int read_user_stack_slow(void __user *ptr, void *buf, int nb)
+{
+	int ret = -EFAULT;
+	pgd_t *pgdir;
+	pte_t *ptep, pte;
+	unsigned int shift;
+	unsigned long addr = (unsigned long) ptr;
+	unsigned long offset;
+	unsigned long pfn, flags;
+	void *kaddr;
+
+	pgdir = current->mm->pgd;
+	if (!pgdir)
+		return -EFAULT;
+
+	local_irq_save(flags);
+	ptep = find_current_mm_pte(pgdir, addr, NULL, &shift);
+	if (!ptep)
+		goto err_out;
+	if (!shift)
+		shift = PAGE_SHIFT;
+
+	/* align address to page boundary */
+	offset = addr & ((1UL << shift) - 1);
+
+	pte = READ_ONCE(*ptep);
+	if (!pte_present(pte) || !pte_user(pte))
+		goto err_out;
+	pfn = pte_pfn(pte);
+	if (!page_is_ram(pfn))
+		goto err_out;
+
+	/* no highmem to worry about here */
+	kaddr = pfn_to_kaddr(pfn);
+	memcpy(buf, kaddr + offset, nb);
+	ret = 0;
+err_out:
+	local_irq_restore(flags);
+	return ret;
+}
+
+static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret)
+{
+	if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned long) ||
+	    ((unsigned long)ptr & 7))
+		return -EFAULT;
+
+	if (!probe_user_read(ret, ptr, sizeof(*ret)))
+		return 0;
+
+	return read_user_stack_slow(ptr, ret, 8);
+}
+
+/*
+ * 64-bit user processes use the same stack frame for RT and non-RT signals.
+ */
+struct signal_frame_64 {
+	char		dummy[__SIGNAL_FRAMESIZE];
+	struct ucontext	uc;
+	unsigned long	unused[2];
+	unsigned int	tramp[6];
+	struct siginfo	*pinfo;
+	void		*puc;
+	struct siginfo	info;
+	char		abigap[288];
+};
+
+static int is_sigreturn_64_address(unsigned long nip, unsigned long fp)
+{
+	if (nip == fp + offsetof(struct signal_frame_64, tramp))
+		return 1;
+	if (vdso64_rt_sigtramp && current->mm->context.vdso_base &&
+	    nip == current->mm->context.vdso_base + vdso64_rt_sigtramp)
+		return 1;
+	return 0;
+}
+
+/*
+ * Do some sanity checking on the signal frame pointed to by sp.
+ * We check the pinfo and puc pointers in the frame.
+ */
+static int sane_signal_64_frame(unsigned long sp)
+{
+	struct signal_frame_64 __user *sf;
+	unsigned long pinfo, puc;
+
+	sf = (struct signal_frame_64 __user *) sp;
+	if (read_user_stack_64((unsigned long __user *) &sf->pinfo, &pinfo) ||
+	    read_user_stack_64((unsigned long __user *) &sf->puc, &puc))
+		return 0;
+	return pinfo == (unsigned long) &sf->info &&
+		puc == (unsigned long) &sf->uc;
+}
+
+void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
+			    struct pt_regs *regs)
+{
+	unsigned long sp, next_sp;
+	unsigned long next_ip;
+	unsigned long lr;
+	long level = 0;
+	struct signal_frame_64 __user *sigframe;
+	unsigned long __user *fp, *uregs;
+
+	next_ip = perf_instruction_pointer(regs);
+	lr = regs->link;
+	sp = regs->gpr[1];
+	perf_callchain_store(entry, next_ip);
+
+	while (entry->nr < entry->max_stack) {
+		fp = (unsigned long __user *) sp;
+		if (invalid_user_sp(sp) || read_user_stack_64(fp, &next_sp))
+			return;
+		if (level > 0 && read_user_stack_64(&fp[2], &next_ip))
+			return;
+
+		/*
+		 * Note: the next_sp - sp >= signal frame size check
+		 * is true when next_sp < sp, which can happen when
+		 * transitioning from an alternate signal stack to the
+		 * normal stack.
+		 */
+		if (next_sp - sp >= sizeof(struct signal_frame_64) &&
+		    (is_sigreturn_64_address(next_ip, sp) ||
+		     (level <= 1 && is_sigreturn_64_address(lr, sp))) &&
+		    sane_signal_64_frame(sp)) {
+			/*
+			 * This looks like an signal frame
+			 */
+			sigframe = (struct signal_frame_64 __user *) sp;
+			uregs = sigframe->uc.uc_mcontext.gp_regs;
+			if (read_user_stack_64(&uregs[PT_NIP], &next_ip) ||
+			    read_user_stack_64(&uregs[PT_LNK], &lr) ||
+			    read_user_stack_64(&uregs[PT_R1], &sp))
+				return;
+			level = 0;
+			perf_callchain_store_context(entry, PERF_CONTEXT_USER);
+			perf_callchain_store(entry, next_ip);
+			continue;
+		}
+
+		if (level == 0)
+			next_ip = lr;
+		perf_callchain_store(entry, next_ip);
+		++level;
+		sp = next_sp;
+	}
+}

arch/powerpc/perf/imc-pmu.c

@@ -44,6 +44,16 @@ static DEFINE_PER_CPU(u64 *, trace_imc_mem);
 static struct imc_pmu_ref *trace_imc_refc;
 static int trace_imc_mem_size;
 
+/*
+ * Global data structure used to avoid races between thread,
+ * core and trace-imc
+ */
+static struct imc_pmu_ref imc_global_refc = {
+	.lock = __MUTEX_INITIALIZER(imc_global_refc.lock),
+	.id = 0,
+	.refc = 0,
+};
+
 static struct imc_pmu *imc_event_to_pmu(struct perf_event *event)
 {
 	return container_of(event->pmu, struct imc_pmu, pmu);
@@ -698,6 +708,16 @@ static int ppc_core_imc_cpu_offline(unsigned int cpu)
 			return -EINVAL;
 
 		ref->refc = 0;
+		/*
+		 * Reduce the global reference count, if this is the
+		 * last cpu in this core and core-imc event running
+		 * in this cpu.
+		 */
+		mutex_lock(&imc_global_refc.lock);
+		if (imc_global_refc.id == IMC_DOMAIN_CORE)
+			imc_global_refc.refc--;
+
+		mutex_unlock(&imc_global_refc.lock);
 	}
 	return 0;
 }
@@ -710,6 +730,23 @@ static int core_imc_pmu_cpumask_init(void)
 				 ppc_core_imc_cpu_offline);
 }
 
+static void reset_global_refc(struct perf_event *event)
+{
+		mutex_lock(&imc_global_refc.lock);
+		imc_global_refc.refc--;
+
+		/*
+		 * If no other thread is running any
+		 * event for this domain(thread/core/trace),
+		 * set the global id to zero.
+		 */
+		if (imc_global_refc.refc <= 0) {
+			imc_global_refc.refc = 0;
+			imc_global_refc.id = 0;
+		}
+		mutex_unlock(&imc_global_refc.lock);
+}
+
 static void core_imc_counters_release(struct perf_event *event)
 {
 	int rc, core_id;
@@ -759,6 +796,8 @@ static void core_imc_counters_release(struct perf_event *event)
 		ref->refc = 0;
 	}
 	mutex_unlock(&ref->lock);
+
+	reset_global_refc(event);
 }
 
 static int core_imc_event_init(struct perf_event *event)
@@ -819,6 +858,29 @@ static int core_imc_event_init(struct perf_event *event)
 	++ref->refc;
 	mutex_unlock(&ref->lock);
 
+	/*
+	 * Since the system can run either in accumulation or trace-mode
+	 * of IMC at a time, core-imc events are allowed only if no other
+	 * trace/thread imc events are enabled/monitored.
+	 *
+	 * Take the global lock, and check the refc.id
+	 * to know whether any other trace/thread imc
+	 * events are running.
+	 */
+	mutex_lock(&imc_global_refc.lock);
+	if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_CORE) {
+		/*
+		 * No other trace/thread imc events are running in
+		 * the system, so set the refc.id to core-imc.
+		 */
+		imc_global_refc.id = IMC_DOMAIN_CORE;
+		imc_global_refc.refc++;
+	} else {
+		mutex_unlock(&imc_global_refc.lock);
+		return -EBUSY;
+	}
+	mutex_unlock(&imc_global_refc.lock);
+
 	event->hw.event_base = (u64)pcmi->vbase + (config & IMC_EVENT_OFFSET_MASK);
 	event->destroy = core_imc_counters_release;
 	return 0;
@@ -877,7 +939,23 @@ static int ppc_thread_imc_cpu_online(unsigned int cpu)
 
 static int ppc_thread_imc_cpu_offline(unsigned int cpu)
 {
-	mtspr(SPRN_LDBAR, 0);
+	/*
+	 * Set the bit 0 of LDBAR to zero.
+	 *
+	 * If bit 0 of LDBAR is unset, it will stop posting
+	 * the counter data to memory.
+	 * For thread-imc, bit 0 of LDBAR will be set to 1 in the
+	 * event_add function. So reset this bit here, to stop the updates
+	 * to memory in the cpu_offline path.
+	 */
+	mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63))));
+
+	/* Reduce the refc if thread-imc event running on this cpu */
+	mutex_lock(&imc_global_refc.lock);
+	if (imc_global_refc.id == IMC_DOMAIN_THREAD)
+		imc_global_refc.refc--;
+	mutex_unlock(&imc_global_refc.lock);
+
 	return 0;
 }
 
@@ -916,7 +994,22 @@ static int thread_imc_event_init(struct perf_event *event)
 	if (!target)
 		return -EINVAL;
 
+	mutex_lock(&imc_global_refc.lock);
+	/*
+	 * Check if any other trace/core imc events are running in the
+	 * system, if not set the global id to thread-imc.
+	 */
+	if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_THREAD) {
+		imc_global_refc.id = IMC_DOMAIN_THREAD;
+		imc_global_refc.refc++;
+	} else {
+		mutex_unlock(&imc_global_refc.lock);
+		return -EBUSY;
+	}
+	mutex_unlock(&imc_global_refc.lock);
+
 	event->pmu->task_ctx_nr = perf_sw_context;
+	event->destroy = reset_global_refc;
 	return 0;
 }
 
@@ -1063,10 +1156,12 @@ static void thread_imc_event_del(struct perf_event *event, int flags)
 	int core_id;
 	struct imc_pmu_ref *ref;
 
-	mtspr(SPRN_LDBAR, 0);
-
 	core_id = smp_processor_id() / threads_per_core;
 	ref = &core_imc_refc[core_id];
+	if (!ref) {
+		pr_debug("imc: Failed to get event reference count\n");
+		return;
+	}
 
 	mutex_lock(&ref->lock);
 	ref->refc--;
@@ -1082,6 +1177,10 @@ static void thread_imc_event_del(struct perf_event *event, int flags)
 		ref->refc = 0;
 	}
 	mutex_unlock(&ref->lock);
+
+	/* Set bit 0 of LDBAR to zero, to stop posting updates to memory */
+	mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63))));
+
 	/*
 	 * Take a snapshot and calculate the delta and update
 	 * the event counter values.
@@ -1133,7 +1232,18 @@ static int ppc_trace_imc_cpu_online(unsigned int cpu)
 
 static int ppc_trace_imc_cpu_offline(unsigned int cpu)
 {
-	mtspr(SPRN_LDBAR, 0);
+	/*
+	 * No need to set bit 0 of LDBAR to zero, as
+	 * it is set to zero for imc trace-mode
+	 *
+	 * Reduce the refc if any trace-imc event running
+	 * on this cpu.
+	 */
+	mutex_lock(&imc_global_refc.lock);
+	if (imc_global_refc.id == IMC_DOMAIN_TRACE)
+		imc_global_refc.refc--;
+	mutex_unlock(&imc_global_refc.lock);
+
 	return 0;
 }
 
@@ -1226,15 +1336,14 @@ static int trace_imc_event_add(struct perf_event *event, int flags)
 	local_mem = get_trace_imc_event_base_addr();
 	ldbar_value = ((u64)local_mem & THREAD_IMC_LDBAR_MASK) | TRACE_IMC_ENABLE;
 
-	if (core_imc_refc)
-		ref = &core_imc_refc[core_id];
+	/* trace-imc reference count */
+	if (trace_imc_refc)
+		ref = &trace_imc_refc[core_id];
 	if (!ref) {
-		/* If core-imc is not enabled, use trace-imc reference count */
-		if (trace_imc_refc)
-			ref = &trace_imc_refc[core_id];
-		if (!ref)
-			return -EINVAL;
+		pr_debug("imc: Failed to get the event reference count\n");
+		return -EINVAL;
 	}
+
 	mtspr(SPRN_LDBAR, ldbar_value);
 	mutex_lock(&ref->lock);
 	if (ref->refc == 0) {
@@ -1242,13 +1351,11 @@ static int trace_imc_event_add(struct perf_event *event, int flags)
 				get_hard_smp_processor_id(smp_processor_id()))) {
 			mutex_unlock(&ref->lock);
 			pr_err("trace-imc: Unable to start the counters for core %d\n", core_id);
-			mtspr(SPRN_LDBAR, 0);
 			return -EINVAL;
 		}
 	}
 	++ref->refc;
 	mutex_unlock(&ref->lock);
-
 	return 0;
 }
 
@@ -1274,16 +1381,13 @@ static void trace_imc_event_del(struct perf_event *event, int flags)
 	int core_id = smp_processor_id() / threads_per_core;
 	struct imc_pmu_ref *ref = NULL;
 
-	if (core_imc_refc)
-		ref = &core_imc_refc[core_id];
+	if (trace_imc_refc)
+		ref = &trace_imc_refc[core_id];
 	if (!ref) {
-		/* If core-imc is not enabled, use trace-imc reference count */
-		if (trace_imc_refc)
-			ref = &trace_imc_refc[core_id];
-		if (!ref)
-			return;
+		pr_debug("imc: Failed to get event reference count\n");
+		return;
 	}
-	mtspr(SPRN_LDBAR, 0);
+
 	mutex_lock(&ref->lock);
 	ref->refc--;
 	if (ref->refc == 0) {
@@ -1297,6 +1401,7 @@ static void trace_imc_event_del(struct perf_event *event, int flags)
 		ref->refc = 0;
 	}
 	mutex_unlock(&ref->lock);
+
 	trace_imc_event_stop(event, flags);
 }
 
@@ -1314,10 +1419,30 @@ static int trace_imc_event_init(struct perf_event *event)
 	if (event->attr.sample_period == 0)
 		return -ENOENT;
 
+	/*
+	 * Take the global lock, and make sure
+	 * no other thread is running any core/thread imc
+	 * events
+	 */
+	mutex_lock(&imc_global_refc.lock);
+	if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_TRACE) {
+		/*
+		 * No core/thread imc events are running in the
+		 * system, so set the refc.id to trace-imc.
+		 */
+		imc_global_refc.id = IMC_DOMAIN_TRACE;
+		imc_global_refc.refc++;
+	} else {
+		mutex_unlock(&imc_global_refc.lock);
+		return -EBUSY;
+	}
+	mutex_unlock(&imc_global_refc.lock);
+
 	event->hw.idx = -1;
 	target = event->hw.target;
 
 	event->pmu->task_ctx_nr = perf_hw_context;
+	event->destroy = reset_global_refc;
 	return 0;
 }
 
@@ -1429,10 +1554,10 @@ static void cleanup_all_core_imc_memory(void)
 static void thread_imc_ldbar_disable(void *dummy)
 {
 	/*
-	 * By Zeroing LDBAR, we disable thread-imc
-	 * updates.
+	 * By setting 0th bit of LDBAR to zero, we disable thread-imc
+	 * updates to memory.
 	 */
-	mtspr(SPRN_LDBAR, 0);
+	mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63))));
 }
 
 void thread_imc_disable(void)

arch/powerpc/platforms/powernv/opal-imc.c

@@ -268,14 +268,7 @@ static int opal_imc_counters_probe(struct platform_device *pdev)
 			domain = IMC_DOMAIN_THREAD;
 			break;
 		case IMC_TYPE_TRACE:
-			/*
-			 * FIXME. Using trace_imc events to monitor application
-			 * or KVM thread performance can cause a checkstop
-			 * (system crash).
-			 * Disable it for now.
-			 */
-			pr_info_once("IMC: disabling trace_imc PMU\n");
-			domain = -1;
+			domain = IMC_DOMAIN_TRACE;
 			break;
 		default:
 			pr_warn("IMC Unknown Device type \n");

arch/powerpc/platforms/ps3/os-area.c

@@ -613,10 +613,8 @@ static int update_flash_db(void)
 	/* Read in header and db from flash. */
 
 	header = kmalloc(buf_len, GFP_KERNEL);
-	if (!header) {
-		pr_debug("%s: kmalloc failed\n", __func__);
+	if (!header)
 		return -ENOMEM;
-	}
 
 	count = os_area_flash_read(header, buf_len, 0);
 	if (count < 0) {

arch/powerpc/platforms/pseries/iommu.c

@@ -945,6 +945,15 @@ static phys_addr_t ddw_memory_hotplug_max(void)
 	phys_addr_t max_addr = memory_hotplug_max();
 	struct device_node *memory;
 
+	/*
+	 * The "ibm,pmemory" can appear anywhere in the address space.
+	 * Assuming it is still backed by page structs, set the upper limit
+	 * for the huge DMA window as MAX_PHYSMEM_BITS.
+	 */
+	if (of_find_node_by_type(NULL, "ibm,pmemory"))
+		return (sizeof(phys_addr_t) * 8 <= MAX_PHYSMEM_BITS) ?
+			(phys_addr_t) -1 : (1ULL << MAX_PHYSMEM_BITS);
+
 	for_each_node_by_type(memory, "memory") {
 		unsigned long start, size;
 		int n_mem_addr_cells, n_mem_size_cells, len;

arch/powerpc/platforms/pseries/ras.c

@@ -686,6 +686,17 @@ static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp)
 #endif
 
 out:
+	/*
+	 * Enable translation as we will be accessing per-cpu variables
+	 * in save_mce_event() which may fall outside RMO region, also
+	 * leave it enabled because subsequently we will be queuing work
+	 * to workqueues where again per-cpu variables accessed, besides
+	 * fwnmi_release_errinfo() crashes when called in realmode on
+	 * pseries.
+	 * Note: All the realmode handling like flushing SLB entries for
+	 *       SLB multihit is done by now.
+	 */
+	mtmsr(mfmsr() | MSR_IR | MSR_DR);
 	save_mce_event(regs, disposition == RTAS_DISP_FULLY_RECOVERED,
 			&mce_err, regs->nip, eaddr, paddr);
 

drivers/ps3/sys-manager-core.c

@@ -31,7 +31,7 @@ void ps3_sys_manager_register_ops(const struct ps3_sys_manager_ops *ops)
 {
 	BUG_ON(!ops);
 	BUG_ON(!ops->dev);
-	ps3_sys_manager_ops = ops ? *ops : ps3_sys_manager_ops;
+	ps3_sys_manager_ops = *ops;
 }
 EXPORT_SYMBOL_GPL(ps3_sys_manager_register_ops);
 

fs/read_write.c

@@ -331,7 +331,8 @@ COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned i
 }
 #endif
 
-#if !defined(CONFIG_64BIT) || defined(CONFIG_COMPAT)
+#if !defined(CONFIG_64BIT) || defined(CONFIG_COMPAT) || \
+	defined(__ARCH_WANT_SYS_LLSEEK)
 SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
 		unsigned long, offset_low, loff_t __user *, result,
 		unsigned int, whence)

tools/testing/selftests/powerpc/eeh/eeh-basic.sh

@@ -41,6 +41,11 @@ for dev in `ls -1 /sys/bus/pci/devices/ | grep '\.0$'` ; do
 		continue;
 	fi
 
+	if [ "ahci" = "$(basename $(realpath /sys/bus/pci/devices/$dev/driver))" ] ; then
+		echo "$dev, Skipped: ahci doesn't support recovery"
+		continue
+	fi
+
 	# Don't inject errosr into an already-frozen PE. This happens with
 	# PEs that contain multiple PCI devices (e.g. multi-function cards)
 	# and injecting new errors during the recovery process will probably

tools/testing/selftests/powerpc/tm/Makefile

@@ -25,6 +25,7 @@ $(OUTPUT)/tm-unavailable: CFLAGS += -O0 -pthread -m64 -Wno-error=uninitialized -
 $(OUTPUT)/tm-trap: CFLAGS += -O0 -pthread -m64
 $(OUTPUT)/tm-signal-context-force-tm: CFLAGS += -pthread -m64
 $(OUTPUT)/tm-signal-pagefault: CFLAGS += -pthread -m64
+$(OUTPUT)/tm-poison: CFLAGS += -m64
 
 SIGNAL_CONTEXT_CHK_TESTS := $(patsubst %,$(OUTPUT)/%,$(SIGNAL_CONTEXT_CHK_TESTS))
 $(SIGNAL_CONTEXT_CHK_TESTS): tm-signal.S