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

6 files changed, 543 insertions, 380 deletions

diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile
index c155dcbb8691..53d614e98537 100644
--- a/arch/powerpc/perf/Makefile
+++ b/arch/powerpc/perf/Makefile
@@ -1,6 +1,9 @@
 # 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 \
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index cbc251981209..dd5051015008 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/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)
 {
diff --git a/arch/powerpc/perf/callchain.h b/arch/powerpc/perf/callchain.h
new file mode 100644
index 000000000000..7a2cb9e1181a
--- /dev/null
+++ b/arch/powerpc/perf/callchain.h
@@ -0,0 +1,19 @@
+/* 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 */
diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c
new file mode 100644
index 000000000000..8aa951003141
--- /dev/null
+++ b/arch/powerpc/perf/callchain_32.c
@@ -0,0 +1,196 @@
+// 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;
+	}
+}
diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c
new file mode 100644
index 000000000000..df1ffd8b20f2
--- /dev/null
+++ b/arch/powerpc/perf/callchain_64.c
@@ -0,0 +1,174 @@
+// 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;
+	}
+}
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index cb50a9e1fd2d..eb82dda884e5 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/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)