[PATCH v6 0/6] Disable compat cruft on ppc64le v6

[PATCH v6 0/6] Disable compat cruft on ppc64le v6

[Michal Suchanek]

Less code means less bugs so add a knob to skip the compat stuff.

This is tested on ppc64le top of

https://patchwork.ozlabs.org/cover/1153556/

Changes in v2: saner CONFIG_COMPAT ifdefs
Changes in v3:
 - change llseek to 32bit instead of builing it unconditionally in fs
 - clanup the makefile conditionals
 - remove some ifdefs or convert to IS_DEFINED where possible
Changes in v4:
 - cleanup is_32bit_task and current_is_64bit
 - more makefile cleanup
Changes in v5:
 - more current_is_64bit cleanup
 - split off callchain.c 32bit and 64bit parts
Changes in v6:
 - cleanup makefile after split
 - consolidate read_user_stack_32
 - fix some checkpatch warnings

Michal Suchanek (6):
  powerpc: make llseek 32bit-only.
  powerpc: move common register copy functions from signal_32.c to
    signal.c
  powerpc/perf: consolidate read_user_stack_32
  powerpc/64: make buildable without CONFIG_COMPAT
  powerpc/64: Make COMPAT user-selectable disabled on littleendian by
    default.
  powerpc/perf: split callchain.c by bitness

 arch/powerpc/Kconfig                     |   5 +-
 arch/powerpc/include/asm/thread_info.h   |   4 +-
 arch/powerpc/kernel/Makefile             |   7 +-
 arch/powerpc/kernel/entry_64.S           |   2 +
 arch/powerpc/kernel/signal.c             | 144 ++++++++-
 arch/powerpc/kernel/signal_32.c          | 140 ---------
 arch/powerpc/kernel/syscall_64.c         |   6 +-
 arch/powerpc/kernel/syscalls/syscall.tbl |   2 +-
 arch/powerpc/kernel/vdso.c               |   5 +-
 arch/powerpc/perf/Makefile               |   5 +-
 arch/powerpc/perf/callchain.c            | 377 +----------------------
 arch/powerpc/perf/callchain.h            |  11 +
 arch/powerpc/perf/callchain_32.c         | 204 ++++++++++++
 arch/powerpc/perf/callchain_64.c         | 185 +++++++++++
 14 files changed, 564 insertions(+), 533 deletions(-)
 create mode 100644 arch/powerpc/perf/callchain.h
 create mode 100644 arch/powerpc/perf/callchain_32.c
 create mode 100644 arch/powerpc/perf/callchain_64.c

-- 
2.22.0

[PATCH v6 1/6] powerpc: make llseek 32bit-only.

[Michal Suchanek]

The llseek syscall is not built in fs/read_write.c when !64bit && !COMPAT
With the syscall marked as common in syscall.tbl build fails in this
case.

The llseek interface does not make sense on 64bit and it is explicitly
described as 32bit interface. Use on 64bit is not well-defined so just
drop it for 64bit.

Fixes: caf6f9c8a326 ("asm-generic: Remove unneeded __ARCH_WANT_SYS_LLSEEK macro")
Link: https://lore.kernel.org/lkml/20190828151552.GA16855@infradead.org/
Link: https://lore.kernel.org/lkml/20190829214319.498c7de2@naga/

Signed-off-by: Michal Suchanek <msuchanek@suse.de>
---
v5: update commit message.
---
 arch/powerpc/kernel/syscalls/syscall.tbl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 010b9f445586..53e427606f6c 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -188,7 +188,7 @@
 137	common	afs_syscall			sys_ni_syscall
 138	common	setfsuid			sys_setfsuid
 139	common	setfsgid			sys_setfsgid
-140	common	_llseek				sys_llseek
+140	32	_llseek				sys_llseek
 141	common	getdents			sys_getdents			compat_sys_getdents
 142	common	_newselect			sys_select			compat_sys_select
 143	common	flock				sys_flock
-- 
2.22.0

[PATCH] Revert "asm-generic: Remove unneeded __ARCH_WANT_SYS_LLSEEK macro"

[Michal Suchanek]

This reverts commit caf6f9c8a326cffd1d4b3ff3f1cfba75d159d70b.

Maybe it was needed after all.

When CONFIG_COMPAT is disabled on ppc64 the kernel does not build.

There is resistance to both removing the llseek syscall from the 64bit
syscall tables and building the llseek interface unconditionally.

Link: https://lore.kernel.org/lkml/20190828151552.GA16855@infradead.org/
Link: https://lore.kernel.org/lkml/20190829214319.498c7de2@naga/

Signed-off-by: Michal Suchanek <msuchanek@suse.de>
---
 arch/arm/include/asm/unistd.h        |  1 +
 arch/arm64/include/asm/unistd.h      |  1 +
 arch/csky/include/asm/unistd.h       |  2 +-
 arch/m68k/include/asm/unistd.h       |  1 +
 arch/microblaze/include/asm/unistd.h |  1 +
 arch/mips/include/asm/unistd.h       |  1 +
 arch/parisc/include/asm/unistd.h     |  1 +
 arch/powerpc/include/asm/unistd.h    |  1 +
 arch/s390/include/asm/unistd.h       |  1 +
 arch/sh/include/asm/unistd.h         |  1 +
 arch/sparc/include/asm/unistd.h      |  1 +
 arch/x86/include/asm/unistd.h        |  1 +
 arch/xtensa/include/asm/unistd.h     |  1 +
 fs/read_write.c                      |  2 +-
 include/asm-generic/unistd.h         | 12 ++++++++++++
 15 files changed, 26 insertions(+), 2 deletions(-)
 create mode 100644 include/asm-generic/unistd.h

diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 3676e82cf95c..e35ec8100a21 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -18,6 +18,7 @@
 #define __ARCH_WANT_SYS_GETHOSTNAME
 #define __ARCH_WANT_SYS_PAUSE
 #define __ARCH_WANT_SYS_GETPGRP
+#define __ARCH_WANT_SYS_LLSEEK
 #define __ARCH_WANT_SYS_NICE
 #define __ARCH_WANT_SYS_SIGPENDING
 #define __ARCH_WANT_SYS_SIGPROCMASK
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 2629a68b8724..2c9d8d91e347 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -7,6 +7,7 @@
 #define __ARCH_WANT_SYS_GETHOSTNAME
 #define __ARCH_WANT_SYS_PAUSE
 #define __ARCH_WANT_SYS_GETPGRP
+#define __ARCH_WANT_SYS_LLSEEK
 #define __ARCH_WANT_SYS_NICE
 #define __ARCH_WANT_SYS_SIGPENDING
 #define __ARCH_WANT_SYS_SIGPROCMASK
diff --git a/arch/csky/include/asm/unistd.h b/arch/csky/include/asm/unistd.h
index da7a18295615..bee8ba8309e7 100644
--- a/arch/csky/include/asm/unistd.h
+++ b/arch/csky/include/asm/unistd.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
 
-#include <uapi/asm/unistd.h>
+#include <asm-generic/unistd.h>
 
 #define NR_syscalls (__NR_syscalls)
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index 2e0047cf86f8..54c04eb4495a 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -21,6 +21,7 @@
 #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_MMAP
diff --git a/arch/microblaze/include/asm/unistd.h b/arch/microblaze/include/asm/unistd.h
index d79d35ac6253..c5fcbce1f997 100644
--- a/arch/microblaze/include/asm/unistd.h
+++ b/arch/microblaze/include/asm/unistd.h
@@ -27,6 +27,7 @@
 #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_OLDUMOUNT
diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h
index 071053ece677..8e8c7cab95ca 100644
--- a/arch/mips/include/asm/unistd.h
+++ b/arch/mips/include/asm/unistd.h
@@ -38,6 +38,7 @@
 #define __ARCH_WANT_SYS_WAITPID
 #define __ARCH_WANT_SYS_SOCKETCALL
 #define __ARCH_WANT_SYS_GETPGRP
+#define __ARCH_WANT_SYS_LLSEEK
 #define __ARCH_WANT_SYS_NICE
 #define __ARCH_WANT_SYS_OLD_UNAME
 #define __ARCH_WANT_SYS_OLDUMOUNT
diff --git a/arch/parisc/include/asm/unistd.h b/arch/parisc/include/asm/unistd.h
index cd438e4150f6..29bd46381f2e 100644
--- a/arch/parisc/include/asm/unistd.h
+++ b/arch/parisc/include/asm/unistd.h
@@ -159,6 +159,7 @@ type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, type5 arg5)	\
 #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_OLDUMOUNT
 #define __ARCH_WANT_SYS_SIGPENDING
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index b0720c7c3fcf..700fcdac2e3c 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/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
diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h
index 9e9f75ef046a..52e9e2fe3768 100644
--- a/arch/s390/include/asm/unistd.h
+++ b/arch/s390/include/asm/unistd.h
@@ -21,6 +21,7 @@
 #define __ARCH_WANT_SYS_IPC
 #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_MMAP
diff --git a/arch/sh/include/asm/unistd.h b/arch/sh/include/asm/unistd.h
index 9c7d9d9999c6..4899b6b72f1a 100644
--- a/arch/sh/include/asm/unistd.h
+++ b/arch/sh/include/asm/unistd.h
@@ -22,6 +22,7 @@
 # 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
diff --git a/arch/sparc/include/asm/unistd.h b/arch/sparc/include/asm/unistd.h
index 1e66278ba4a5..7edfc208e2af 100644
--- a/arch/sparc/include/asm/unistd.h
+++ b/arch/sparc/include/asm/unistd.h
@@ -36,6 +36,7 @@
 #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_OLDUMOUNT
 #define __ARCH_WANT_SYS_SIGPENDING
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 097589753fec..9e5a1748b4ce 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -39,6 +39,7 @@
 # define __ARCH_WANT_SYS_FADVISE64
 # define __ARCH_WANT_SYS_GETHOSTNAME
 # define __ARCH_WANT_SYS_GETPGRP
+# define __ARCH_WANT_SYS_LLSEEK
 # define __ARCH_WANT_SYS_NICE
 # define __ARCH_WANT_SYS_OLDUMOUNT
 # define __ARCH_WANT_SYS_OLD_GETRLIMIT
diff --git a/arch/xtensa/include/asm/unistd.h b/arch/xtensa/include/asm/unistd.h
index b52236245e51..9fd236a7825e 100644
--- a/arch/xtensa/include/asm/unistd.h
+++ b/arch/xtensa/include/asm/unistd.h
@@ -9,6 +9,7 @@
 #define __ARCH_WANT_NEW_STAT
 #define __ARCH_WANT_STAT64
 #define __ARCH_WANT_SYS_UTIME32
+#define __ARCH_WANT_SYS_LLSEEK
 #define __ARCH_WANT_SYS_GETPGRP
 
 #define NR_syscalls				__NR_syscalls
diff --git a/fs/read_write.c b/fs/read_write.c
index 5bbf587f5bc1..2f3c4bb138c4 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -331,7 +331,7 @@ COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned i
 }
 #endif
 
-#if !defined(CONFIG_64BIT) || defined(CONFIG_COMPAT)
+#ifdef __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)
diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h
new file mode 100644
index 000000000000..ea74eca8463f
--- /dev/null
+++ b/include/asm-generic/unistd.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <uapi/asm-generic/unistd.h>
+#include <linux/export.h>
+
+/*
+ * These are required system calls, we should
+ * invert the logic eventually and let them
+ * be selected by default.
+ */
+#if __BITS_PER_LONG == 32
+#define __ARCH_WANT_SYS_LLSEEK
+#endif
-- 
2.22.0

[PATCH v6 2/6] powerpc: move common register copy functions from signal_32.c to signal.c

[Michal Suchanek]

These functions are required for 64bit as well.

Signed-off-by: Michal Suchanek <msuchanek@suse.de>
---
 arch/powerpc/kernel/signal.c    | 141 ++++++++++++++++++++++++++++++++
 arch/powerpc/kernel/signal_32.c | 140 -------------------------------
 2 files changed, 141 insertions(+), 140 deletions(-)

diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index e6c30cee6abf..60436432399f 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/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.
  */
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 98600b276f76..c93c937ea568 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/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
-- 
2.22.0

Re: [PATCH v6 2/6] powerpc: move common register copy functions from signal_32.c to signal.c

[Christophe Leroy]

Le 30/08/2019 à 20:57, Michal Suchanek a écrit :
> These functions are required for 64bit as well.
> 
> Signed-off-by: Michal Suchanek <msuchanek@suse.de>

Reviewed-by: christophe.leroy@c-s.fr


> ---
>   arch/powerpc/kernel/signal.c    | 141 ++++++++++++++++++++++++++++++++
>   arch/powerpc/kernel/signal_32.c | 140 -------------------------------
>   2 files changed, 141 insertions(+), 140 deletions(-)
> 
> diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
> index e6c30cee6abf..60436432399f 100644
> --- a/arch/powerpc/kernel/signal.c
> +++ b/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.
>    */
> diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
> index 98600b276f76..c93c937ea568 100644
> --- a/arch/powerpc/kernel/signal_32.c
> +++ b/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
> 

[PATCH v6 3/6] powerpc/perf: consolidate read_user_stack_32

[Michal Suchanek]

There are two almost identical copies for 32bit and 64bit.

The function is used only in 32bit code which will be split out in next
patch so consolidate to one function.

Signed-off-by: Michal Suchanek <msuchanek@suse.de>
---
new patch in v6
---
 arch/powerpc/perf/callchain.c | 25 +++++++++----------------
 1 file changed, 9 insertions(+), 16 deletions(-)

diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index c84bbd4298a0..b7cdcce20280 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -165,22 +165,6 @@ static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret)
 	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;
-
-	pagefault_disable();
-	if (!__get_user_inatomic(*ret, ptr)) {
-		pagefault_enable();
-		return 0;
-	}
-	pagefault_enable();
-
-	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)
@@ -295,6 +279,12 @@ static inline int current_is_64bit(void)
 }
 
 #else  /* CONFIG_PPC64 */
+static int read_user_stack_slow(void __user *ptr, void *buf, int nb)
+{
+	return 0;
+}
+#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
@@ -313,9 +303,12 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
 	rc = __get_user_inatomic(*ret, ptr);
 	pagefault_enable();
 
+	if (IS_ENABLED(CONFIG_PPC64) && rc)
+		return read_user_stack_slow(ptr, ret, 4);
 	return rc;
 }
 
+#ifndef CONFIG_PPC64
 static inline void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
 					  struct pt_regs *regs)
 {
-- 
2.22.0

Re: [PATCH v6 3/6] powerpc/perf: consolidate read_user_stack_32

[Christophe Leroy]

Le 30/08/2019 à 20:57, Michal Suchanek a écrit :
> There are two almost identical copies for 32bit and 64bit.
> 
> The function is used only in 32bit code which will be split out in next
> patch so consolidate to one function.
> 
> Signed-off-by: Michal Suchanek <msuchanek@suse.de>

Reviewed-by: Christophe.Leroy@c-s.fr

> ---
> new patch in v6
> ---
>   arch/powerpc/perf/callchain.c | 25 +++++++++----------------
>   1 file changed, 9 insertions(+), 16 deletions(-)
> 
> diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
> index c84bbd4298a0..b7cdcce20280 100644
> --- a/arch/powerpc/perf/callchain.c
> +++ b/arch/powerpc/perf/callchain.c
> @@ -165,22 +165,6 @@ static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret)
>   	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;
> -
> -	pagefault_disable();
> -	if (!__get_user_inatomic(*ret, ptr)) {
> -		pagefault_enable();
> -		return 0;
> -	}
> -	pagefault_enable();
> -
> -	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)
> @@ -295,6 +279,12 @@ static inline int current_is_64bit(void)
>   }
>   
>   #else  /* CONFIG_PPC64 */
> +static int read_user_stack_slow(void __user *ptr, void *buf, int nb)
> +{
> +	return 0;
> +}
> +#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
> @@ -313,9 +303,12 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
>   	rc = __get_user_inatomic(*ret, ptr);
>   	pagefault_enable();
>   
> +	if (IS_ENABLED(CONFIG_PPC64) && rc)
> +		return read_user_stack_slow(ptr, ret, 4);
>   	return rc;
>   }
>   
> +#ifndef CONFIG_PPC64
>   static inline void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
>   					  struct pt_regs *regs)
>   {
> 

[PATCH v6 4/6] powerpc/64: make buildable without CONFIG_COMPAT

[Michal Suchanek]

There are numerous references to 32bit functions in generic and 64bit
code so ifdef them out.

Signed-off-by: Michal Suchanek <msuchanek@suse.de>
---
v2:
- fix 32bit ifdef condition in signal.c
- simplify the compat ifdef condition in vdso.c - 64bit is redundant
- simplify the compat ifdef condition in callchain.c - 64bit is redundant
v3:
- use IS_ENABLED and maybe_unused where possible
- do not ifdef declarations
- clean up Makefile
v4:
- further makefile cleanup
- simplify is_32bit_task conditions
- avoid ifdef in condition by using return
v5:
- avoid unreachable code on 32bit
- make is_current_64bit constant on !COMPAT
- add stub perf_callchain_user_32 to avoid some ifdefs
v6:
- consolidate current_is_64bit
---
 arch/powerpc/include/asm/thread_info.h |  4 +--
 arch/powerpc/kernel/Makefile           |  7 +++--
 arch/powerpc/kernel/entry_64.S         |  2 ++
 arch/powerpc/kernel/signal.c           |  3 +--
 arch/powerpc/kernel/syscall_64.c       |  6 ++---
 arch/powerpc/kernel/vdso.c             |  5 ++--
 arch/powerpc/perf/callchain.c          | 37 +++++++++++++++-----------
 7 files changed, 33 insertions(+), 31 deletions(-)

diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 8e1d0195ac36..c128d8a48ea3 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -144,10 +144,10 @@ 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)
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 1d646a94d96c..9d8772e863b9 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -44,16 +44,15 @@ CFLAGS_btext.o += -DDISABLE_BRANCH_PROFILING
 endif
 
 obj-y				:= cputable.o ptrace.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-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
-				   signal_64.o ptrace32.o \
-				   paca.o nvram_64.o firmware.o \
+obj-$(CONFIG_PPC64)		+= setup_64.o paca.o nvram_64.o firmware.o \
 				   syscall_64.o
+obj-$(CONFIG_COMPAT)		+= sys_ppc32.o ptrace32.o signal_32.o
 obj-$(CONFIG_VDSO32)		+= vdso32/
 obj-$(CONFIG_PPC_WATCHDOG)	+= watchdog.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 2ec825a85f5b..a2dbf216f607 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -51,8 +51,10 @@
 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:
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index 60436432399f..61678cb0e6a1 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -247,7 +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);
 
@@ -277,7 +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
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index 98ed970796d5..0d5cbbe54cf1 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -38,7 +38,6 @@ typedef long (*syscall_fn)(long, long, long, long, long, long);
 
 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;
 
 	BUG_ON(!(regs->msr & MSR_PR));
@@ -83,8 +82,7 @@ long system_call_exception(long r3, long r4, long r5, long r6, long r7, long r8,
 	 */
 	regs->softe = IRQS_ENABLED;
 
-	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
@@ -100,7 +98,7 @@ long system_call_exception(long r3, long r4, long r5, long r6, long r7, long r8,
 	/* 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;
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index d60598113a9f..6d4a077f74d6 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -667,9 +667,7 @@ static void __init vdso_setup_syscall_map(void)
 {
 	unsigned int i;
 	extern unsigned long *sys_call_table;
-#ifdef CONFIG_PPC64
 	extern unsigned long *compat_sys_call_table;
-#endif
 	extern unsigned long sys_ni_syscall;
 
 
@@ -678,7 +676,8 @@ 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 */
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index b7cdcce20280..788ad2c63f18 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -15,7 +15,7 @@
 #include <asm/sigcontext.h>
 #include <asm/ucontext.h>
 #include <asm/vdso.h>
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_COMPAT
 #include "../kernel/ppc32.h"
 #endif
 #include <asm/pte-walk.h>
@@ -268,16 +268,6 @@ static void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
 	}
 }
 
-static inline int current_is_64bit(void)
-{
-	/*
-	 * We can't use test_thread_flag() here because we may be on an
-	 * interrupt stack, and the thread flags don't get copied over
-	 * from the thread_info on the main stack to the interrupt stack.
-	 */
-	return !test_ti_thread_flag(task_thread_info(current), TIF_32BIT);
-}
-
 #else  /* CONFIG_PPC64 */
 static int read_user_stack_slow(void __user *ptr, void *buf, int nb)
 {
@@ -314,11 +304,6 @@ static inline void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry
 {
 }
 
-static inline int current_is_64bit(void)
-{
-	return 0;
-}
-
 static inline int valid_user_sp(unsigned long sp, int is_64)
 {
 	if (!sp || (sp & 7) || sp > TASK_SIZE - 32)
@@ -334,6 +319,7 @@ static inline int valid_user_sp(unsigned long sp, int is_64)
 
 #endif /* CONFIG_PPC64 */
 
+#if defined(CONFIG_PPC32) || defined(CONFIG_COMPAT)
 /*
  * Layout for non-RT signal frames
  */
@@ -475,6 +461,25 @@ static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
 		sp = next_sp;
 	}
 }
+#else /* 32bit */
+static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
+				   struct pt_regs *regs)
+{
+	(void)&read_user_stack_32; /* unused if !COMPAT */
+}
+#endif /* 32bit */
+
+static inline int current_is_64bit(void)
+{
+	if (!IS_ENABLED(CONFIG_COMPAT))
+		return IS_ENABLED(CONFIG_PPC64);
+	/*
+	 * We can't use test_thread_flag() here because we may be on an
+	 * interrupt stack, and the thread flags don't get copied over
+	 * from the thread_info on the main stack to the interrupt stack.
+	 */
+	return !test_ti_thread_flag(task_thread_info(current), TIF_32BIT);
+}
 
 void
 perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
-- 
2.22.0

Re: [PATCH v6 4/6] powerpc/64: make buildable without CONFIG_COMPAT

[Christophe Leroy]

Le 30/08/2019 à 20:57, Michal Suchanek a écrit :
> There are numerous references to 32bit functions in generic and 64bit
> code so ifdef them out.
> 
> Signed-off-by: Michal Suchanek <msuchanek@suse.de>
> ---
> v2:
> - fix 32bit ifdef condition in signal.c
> - simplify the compat ifdef condition in vdso.c - 64bit is redundant
> - simplify the compat ifdef condition in callchain.c - 64bit is redundant
> v3:
> - use IS_ENABLED and maybe_unused where possible
> - do not ifdef declarations
> - clean up Makefile
> v4:
> - further makefile cleanup
> - simplify is_32bit_task conditions
> - avoid ifdef in condition by using return
> v5:
> - avoid unreachable code on 32bit
> - make is_current_64bit constant on !COMPAT
> - add stub perf_callchain_user_32 to avoid some ifdefs
> v6:
> - consolidate current_is_64bit
> ---
>   arch/powerpc/include/asm/thread_info.h |  4 +--
>   arch/powerpc/kernel/Makefile           |  7 +++--
>   arch/powerpc/kernel/entry_64.S         |  2 ++
>   arch/powerpc/kernel/signal.c           |  3 +--
>   arch/powerpc/kernel/syscall_64.c       |  6 ++---
>   arch/powerpc/kernel/vdso.c             |  5 ++--
>   arch/powerpc/perf/callchain.c          | 37 +++++++++++++++-----------
>   7 files changed, 33 insertions(+), 31 deletions(-)
> 

[...]

> diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
> index b7cdcce20280..788ad2c63f18 100644
> --- a/arch/powerpc/perf/callchain.c
> +++ b/arch/powerpc/perf/callchain.c
> @@ -15,7 +15,7 @@
>   #include <asm/sigcontext.h>
>   #include <asm/ucontext.h>
>   #include <asm/vdso.h>
> -#ifdef CONFIG_PPC64
> +#ifdef CONFIG_COMPAT
>   #include "../kernel/ppc32.h"
>   #endif
>   #include <asm/pte-walk.h>
> @@ -268,16 +268,6 @@ static void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
>   	}
>   }
>   
> -static inline int current_is_64bit(void)
> -{
> -	/*
> -	 * We can't use test_thread_flag() here because we may be on an
> -	 * interrupt stack, and the thread flags don't get copied over
> -	 * from the thread_info on the main stack to the interrupt stack.
> -	 */
> -	return !test_ti_thread_flag(task_thread_info(current), TIF_32BIT);
> -}
> -
>   #else  /* CONFIG_PPC64 */
>   static int read_user_stack_slow(void __user *ptr, void *buf, int nb)
>   {
> @@ -314,11 +304,6 @@ static inline void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry
>   {
>   }
>   
> -static inline int current_is_64bit(void)
> -{
> -	return 0;
> -}
> -
>   static inline int valid_user_sp(unsigned long sp, int is_64)
>   {
>   	if (!sp || (sp & 7) || sp > TASK_SIZE - 32)
> @@ -334,6 +319,7 @@ static inline int valid_user_sp(unsigned long sp, int is_64)
>   
>   #endif /* CONFIG_PPC64 */
>   
> +#if defined(CONFIG_PPC32) || defined(CONFIG_COMPAT)
>   /*
>    * Layout for non-RT signal frames
>    */
> @@ -475,6 +461,25 @@ static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
>   		sp = next_sp;
>   	}
>   }
> +#else /* 32bit */
> +static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
> +				   struct pt_regs *regs)
> +{
> +	(void)&read_user_stack_32; /* unused if !COMPAT */

You don't need that anymore do you ?

Christophe

> +}
> +#endif /* 32bit */
> +
> +static inline int current_is_64bit(void)
> +{
> +	if (!IS_ENABLED(CONFIG_COMPAT))
> +		return IS_ENABLED(CONFIG_PPC64);
> +	/*
> +	 * We can't use test_thread_flag() here because we may be on an
> +	 * interrupt stack, and the thread flags don't get copied over
> +	 * from the thread_info on the main stack to the interrupt stack.
> +	 */
> +	return !test_ti_thread_flag(task_thread_info(current), TIF_32BIT);
> +}
>   
>   void
>   perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
> 

Re: [PATCH v6 4/6] powerpc/64: make buildable without CONFIG_COMPAT

[Michal Suchánek]

On Fri, 30 Aug 2019 22:21:09 +0200
Christophe Leroy <christophe.leroy@c-s.fr> wrote:

> Le 30/08/2019 à 20:57, Michal Suchanek a écrit :
> > There are numerous references to 32bit functions in generic and 64bit
> > code so ifdef them out.
> > 
> > Signed-off-by: Michal Suchanek <msuchanek@suse.de>
> > ---
> > v2:
> > - fix 32bit ifdef condition in signal.c
> > - simplify the compat ifdef condition in vdso.c - 64bit is redundant
> > - simplify the compat ifdef condition in callchain.c - 64bit is redundant
> > v3:
> > - use IS_ENABLED and maybe_unused where possible
> > - do not ifdef declarations
> > - clean up Makefile
> > v4:
> > - further makefile cleanup
> > - simplify is_32bit_task conditions
> > - avoid ifdef in condition by using return
> > v5:
> > - avoid unreachable code on 32bit
> > - make is_current_64bit constant on !COMPAT
> > - add stub perf_callchain_user_32 to avoid some ifdefs
> > v6:
> > - consolidate current_is_64bit
> > ---
> >   arch/powerpc/include/asm/thread_info.h |  4 +--
> >   arch/powerpc/kernel/Makefile           |  7 +++--
> >   arch/powerpc/kernel/entry_64.S         |  2 ++
> >   arch/powerpc/kernel/signal.c           |  3 +--
> >   arch/powerpc/kernel/syscall_64.c       |  6 ++---
> >   arch/powerpc/kernel/vdso.c             |  5 ++--
> >   arch/powerpc/perf/callchain.c          | 37 +++++++++++++++-----------
> >   7 files changed, 33 insertions(+), 31 deletions(-)
> >   
> 
> [...]
> 
> > diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
> > index b7cdcce20280..788ad2c63f18 100644
> > --- a/arch/powerpc/perf/callchain.c
> > +++ b/arch/powerpc/perf/callchain.c
> > @@ -15,7 +15,7 @@
> >   #include <asm/sigcontext.h>
> >   #include <asm/ucontext.h>
> >   #include <asm/vdso.h>
> > -#ifdef CONFIG_PPC64
> > +#ifdef CONFIG_COMPAT
> >   #include "../kernel/ppc32.h"
> >   #endif
> >   #include <asm/pte-walk.h>
> > @@ -268,16 +268,6 @@ static void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
> >   	}
> >   }
> >   
> > -static inline int current_is_64bit(void)
> > -{
> > -	/*
> > -	 * We can't use test_thread_flag() here because we may be on an
> > -	 * interrupt stack, and the thread flags don't get copied over
> > -	 * from the thread_info on the main stack to the interrupt stack.
> > -	 */
> > -	return !test_ti_thread_flag(task_thread_info(current), TIF_32BIT);
> > -}
> > -
> >   #else  /* CONFIG_PPC64 */
> >   static int read_user_stack_slow(void __user *ptr, void *buf, int nb)
> >   {
> > @@ -314,11 +304,6 @@ static inline void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry
> >   {
> >   }
> >   
> > -static inline int current_is_64bit(void)
> > -{
> > -	return 0;
> > -}
> > -
> >   static inline int valid_user_sp(unsigned long sp, int is_64)
> >   {
> >   	if (!sp || (sp & 7) || sp > TASK_SIZE - 32)
> > @@ -334,6 +319,7 @@ static inline int valid_user_sp(unsigned long sp, int is_64)
> >   
> >   #endif /* CONFIG_PPC64 */
> >   
> > +#if defined(CONFIG_PPC32) || defined(CONFIG_COMPAT)
> >   /*
> >    * Layout for non-RT signal frames
> >    */
> > @@ -475,6 +461,25 @@ static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
> >   		sp = next_sp;
> >   	}
> >   }
> > +#else /* 32bit */
> > +static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
> > +				   struct pt_regs *regs)
> > +{
> > +	(void)&read_user_stack_32; /* unused if !COMPAT */  
> 
> You don't need that anymore do you ?

Yes, this part is not needed. It was removed later anyway but this
state is broken.

Thanks

Michal

> 
> Christophe
> 
> > +}
> > +#endif /* 32bit */
> > +
> > +static inline int current_is_64bit(void)
> > +{
> > +	if (!IS_ENABLED(CONFIG_COMPAT))
> > +		return IS_ENABLED(CONFIG_PPC64);
> > +	/*
> > +	 * We can't use test_thread_flag() here because we may be on an
> > +	 * interrupt stack, and the thread flags don't get copied over
> > +	 * from the thread_info on the main stack to the interrupt stack.
> > +	 */
> > +	return !test_ti_thread_flag(task_thread_info(current), TIF_32BIT);
> > +}
> >   
> >   void
> >   perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
> >   

[PATCH v6 5/6] powerpc/64: Make COMPAT user-selectable disabled on littleendian by default.

[Michal Suchanek]

On bigendian ppc64 it is common to have 32bit legacy binaries but much
less so on littleendian.

Signed-off-by: Michal Suchanek <msuchanek@suse.de>
---
v3: make configurable
---
 arch/powerpc/Kconfig | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 5bab0bb6b833..b0339e892329 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -264,8 +264,9 @@ 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
-- 
2.22.0

Re: [PATCH v6 5/6] powerpc/64: Make COMPAT user-selectable disabled on littleendian by default.

[Christophe Leroy]

Le 30/08/2019 à 20:57, Michal Suchanek a écrit :
> On bigendian ppc64 it is common to have 32bit legacy binaries but much
> less so on littleendian.
> 
> Signed-off-by: Michal Suchanek <msuchanek@suse.de>

Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>


> ---
> v3: make configurable
> ---
>   arch/powerpc/Kconfig | 5 +++--
>   1 file changed, 3 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
> index 5bab0bb6b833..b0339e892329 100644
> --- a/arch/powerpc/Kconfig
> +++ b/arch/powerpc/Kconfig
> @@ -264,8 +264,9 @@ 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
> 

[PATCH v6 6/6] powerpc/perf: split callchain.c by bitness

[Michal Suchanek]

Building callchain.c with !COMPAT proved quite ugly with all the
defines. Splitting out the 32bit and 64bit parts looks better.

No code change intended.

Signed-off-by: Michal Suchanek <msuchanek@suse.de>
---
v6:
 - move current_is_64bit consolidetaion to earlier patch
 - move defines to the top of callchain_32.c
 - Makefile cleanup
---
 arch/powerpc/perf/Makefile       |   5 +-
 arch/powerpc/perf/callchain.c    | 371 +------------------------------
 arch/powerpc/perf/callchain.h    |  11 +
 arch/powerpc/perf/callchain_32.c | 204 +++++++++++++++++
 arch/powerpc/perf/callchain_64.c | 185 +++++++++++++++
 5 files changed, 405 insertions(+), 371 deletions(-)
 create mode 100644 arch/powerpc/perf/callchain.h
 create mode 100644 arch/powerpc/perf/callchain_32.c
 create mode 100644 arch/powerpc/perf/callchain_64.c

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 788ad2c63f18..8f30f1b47c78 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_COMPAT
-#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?
@@ -102,373 +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;
-
-	pagefault_disable();
-	if (!__get_user_inatomic(*ret, ptr)) {
-		pagefault_enable();
-		return 0;
-	}
-	pagefault_enable();
-
-	return read_user_stack_slow(ptr, ret, 8);
-}
-
-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 */
-static int read_user_stack_slow(void __user *ptr, void *buf, int nb)
-{
-	return 0;
-}
-#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;
-
-	pagefault_disable();
-	rc = __get_user_inatomic(*ret, ptr);
-	pagefault_enable();
-
-	if (IS_ENABLED(CONFIG_PPC64) && rc)
-		return read_user_stack_slow(ptr, ret, 4);
-	return rc;
-}
-
-#ifndef CONFIG_PPC64
-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 */
-
-#if defined(CONFIG_PPC32) || defined(CONFIG_COMPAT)
-/*
- * 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;
-	}
-}
-#else /* 32bit */
-static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
-				   struct pt_regs *regs)
-{
-	(void)&read_user_stack_32; /* unused if !COMPAT */
-}
-#endif /* 32bit */
-
 static inline int current_is_64bit(void)
 {
 	if (!IS_ENABLED(CONFIG_COMPAT))
diff --git a/arch/powerpc/perf/callchain.h b/arch/powerpc/perf/callchain.h
new file mode 100644
index 000000000000..63ffb43f3668
--- /dev/null
+++ b/arch/powerpc/perf/callchain.h
@@ -0,0 +1,11 @@
+/* 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);
+
+#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..01a38d929078
--- /dev/null
+++ b/arch/powerpc/perf/callchain_32.c
@@ -0,0 +1,204 @@
+// 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;
+
+	pagefault_disable();
+	rc = __get_user_inatomic(*ret, ptr);
+	pagefault_enable();
+
+	if (IS_ENABLED(CONFIG_PPC64) && rc)
+		return read_user_stack_slow(ptr, ret, 4);
+	return rc;
+}
+
+static inline int valid_user_sp(unsigned long sp, int is_64)
+{
+	if (!sp || (sp & 7) || sp > TASK_SIZE - 32)
+		return 0;
+	return 1;
+}
+
+/*
+ * 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 (!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;
+	}
+}
diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c
new file mode 100644
index 000000000000..60308c2221a8
--- /dev/null
+++ b/arch/powerpc/perf/callchain_64.c
@@ -0,0 +1,185 @@
+// 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;
+
+	pagefault_disable();
+	if (!__get_user_inatomic(*ret, ptr)) {
+		pagefault_enable();
+		return 0;
+	}
+	pagefault_enable();
+
+	return read_user_stack_slow(ptr, ret, 8);
+}
+
+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;
+}
+
+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;
+	}
+}
-- 
2.22.0

Re: [PATCH v6 6/6] powerpc/perf: split callchain.c by bitness

[Michal Suchánek]

On Fri, 30 Aug 2019 20:57:57 +0200
Michal Suchanek <msuchanek@suse.de> wrote:

> Building callchain.c with !COMPAT proved quite ugly with all the
> defines. Splitting out the 32bit and 64bit parts looks better.
> 

BTW the powerpc callchain.c does not match any of the patterns of PERF
CORE in MAINTAINERS (unlike callchain implementation on other
platforms). Is that intentional?

Thanks

Michal

Re: [PATCH v6 6/6] powerpc/perf: split callchain.c by bitness

[Michael Ellerman]

Michal Suchánek <msuchanek@suse.de> writes:
> On Fri, 30 Aug 2019 20:57:57 +0200
> Michal Suchanek <msuchanek@suse.de> wrote:
>
>> Building callchain.c with !COMPAT proved quite ugly with all the
>> defines. Splitting out the 32bit and 64bit parts looks better.
>> 
>
> BTW the powerpc callchain.c does not match any of the patterns of PERF
> CORE in MAINTAINERS (unlike callchain implementation on other
> platforms). Is that intentional?

No.

cheers

Re: [PATCH v6 6/6] powerpc/perf: split callchain.c by bitness

[Christophe Leroy]

Le 30/08/2019 à 20:57, Michal Suchanek a écrit :
> Building callchain.c with !COMPAT proved quite ugly with all the
> defines. Splitting out the 32bit and 64bit parts looks better.
> 
> No code change intended.
> 
> Signed-off-by: Michal Suchanek <msuchanek@suse.de>

Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>

> ---
> v6:
>   - move current_is_64bit consolidetaion to earlier patch
>   - move defines to the top of callchain_32.c
>   - Makefile cleanup
> ---
>   arch/powerpc/perf/Makefile       |   5 +-
>   arch/powerpc/perf/callchain.c    | 371 +------------------------------
>   arch/powerpc/perf/callchain.h    |  11 +
>   arch/powerpc/perf/callchain_32.c | 204 +++++++++++++++++
>   arch/powerpc/perf/callchain_64.c | 185 +++++++++++++++
>   5 files changed, 405 insertions(+), 371 deletions(-)
>   create mode 100644 arch/powerpc/perf/callchain.h
>   create mode 100644 arch/powerpc/perf/callchain_32.c
>   create mode 100644 arch/powerpc/perf/callchain_64.c
> 
> 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 788ad2c63f18..8f30f1b47c78 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_COMPAT
> -#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?
> @@ -102,373 +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;
> -
> -	pagefault_disable();
> -	if (!__get_user_inatomic(*ret, ptr)) {
> -		pagefault_enable();
> -		return 0;
> -	}
> -	pagefault_enable();
> -
> -	return read_user_stack_slow(ptr, ret, 8);
> -}
> -
> -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 */
> -static int read_user_stack_slow(void __user *ptr, void *buf, int nb)
> -{
> -	return 0;
> -}
> -#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;
> -
> -	pagefault_disable();
> -	rc = __get_user_inatomic(*ret, ptr);
> -	pagefault_enable();
> -
> -	if (IS_ENABLED(CONFIG_PPC64) && rc)
> -		return read_user_stack_slow(ptr, ret, 4);
> -	return rc;
> -}
> -
> -#ifndef CONFIG_PPC64
> -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 */
> -
> -#if defined(CONFIG_PPC32) || defined(CONFIG_COMPAT)
> -/*
> - * 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;
> -	}
> -}
> -#else /* 32bit */
> -static void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
> -				   struct pt_regs *regs)
> -{
> -	(void)&read_user_stack_32; /* unused if !COMPAT */
> -}
> -#endif /* 32bit */
> -
>   static inline int current_is_64bit(void)
>   {
>   	if (!IS_ENABLED(CONFIG_COMPAT))
> diff --git a/arch/powerpc/perf/callchain.h b/arch/powerpc/perf/callchain.h
> new file mode 100644
> index 000000000000..63ffb43f3668
> --- /dev/null
> +++ b/arch/powerpc/perf/callchain.h
> @@ -0,0 +1,11 @@
> +/* 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);
> +
> +#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..01a38d929078
> --- /dev/null
> +++ b/arch/powerpc/perf/callchain_32.c
> @@ -0,0 +1,204 @@
> +// 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;
> +
> +	pagefault_disable();
> +	rc = __get_user_inatomic(*ret, ptr);
> +	pagefault_enable();
> +
> +	if (IS_ENABLED(CONFIG_PPC64) && rc)
> +		return read_user_stack_slow(ptr, ret, 4);
> +	return rc;
> +}
> +
> +static inline int valid_user_sp(unsigned long sp, int is_64)
> +{
> +	if (!sp || (sp & 7) || sp > TASK_SIZE - 32)
> +		return 0;
> +	return 1;
> +}
> +
> +/*
> + * 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 (!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;
> +	}
> +}
> diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c
> new file mode 100644
> index 000000000000..60308c2221a8
> --- /dev/null
> +++ b/arch/powerpc/perf/callchain_64.c
> @@ -0,0 +1,185 @@
> +// 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;
> +
> +	pagefault_disable();
> +	if (!__get_user_inatomic(*ret, ptr)) {
> +		pagefault_enable();
> +		return 0;
> +	}
> +	pagefault_enable();
> +
> +	return read_user_stack_slow(ptr, ret, 8);
> +}
> +
> +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;
> +}
> +
> +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;
> +	}
> +}
>