Merge tag 'powerpc-6.2-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Add powerpc qspinlock implementation optimised for large system
   scalability and paravirt. See the merge message for more details

 - Enable objtool to be built on powerpc to generate mcount locations

 - Use a temporary mm for code patching with the Radix MMU, so the
   writable mapping is restricted to the patching CPU

 - Add an option to build the 64-bit big-endian kernel with the ELFv2
   ABI

 - Sanitise user registers on interrupt entry on 64-bit Book3S

 - Many other small features and fixes

Thanks to Aboorva Devarajan, Angel Iglesias, Benjamin Gray, Bjorn
Helgaas, Bo Liu, Chen Lifu, Christoph Hellwig, Christophe JAILLET,
Christophe Leroy, Christopher M. Riedl, Colin Ian King, Deming Wang,
Disha Goel, Dmitry Torokhov, Finn Thain, Geert Uytterhoeven, Gustavo A.
R. Silva, Haowen Bai, Joel Stanley, Jordan Niethe, Julia Lawall, Kajol
Jain, Laurent Dufour, Li zeming, Miaoqian Lin, Michael Jeanson, Nathan
Lynch, Naveen N. Rao, Nayna Jain, Nicholas Miehlbradt, Nicholas Piggin,
Pali Rohár, Randy Dunlap, Rohan McLure, Russell Currey, Sathvika
Vasireddy, Shaomin Deng, Stephen Kitt, Stephen Rothwell, Thomas
Weißschuh, Tiezhu Yang, Uwe Kleine-König, Xie Shaowen, Xiu Jianfeng,
XueBing Chen, Yang Yingliang, Zhang Jiaming, ruanjinjie, Jessica Yu,
and Wolfram Sang.

* tag 'powerpc-6.2-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (181 commits)
  powerpc/code-patching: Fix oops with DEBUG_VM enabled
  powerpc/qspinlock: Fix 32-bit build
  powerpc/prom: Fix 32-bit build
  powerpc/rtas: mandate RTAS syscall filtering
  powerpc/rtas: define pr_fmt and convert printk call sites
  powerpc/rtas: clean up includes
  powerpc/rtas: clean up rtas_error_log_max initialization
  powerpc/pseries/eeh: use correct API for error log size
  powerpc/rtas: avoid scheduling in rtas_os_term()
  powerpc/rtas: avoid device tree lookups in rtas_os_term()
  powerpc/rtasd: use correct OF API for event scan rate
  powerpc/rtas: document rtas_call()
  powerpc/pseries: unregister VPA when hot unplugging a CPU
  powerpc/pseries: reset the RCU watchdogs after a LPM
  powerpc: Take in account addition CPU node when building kexec FDT
  powerpc: export the CPU node count
  powerpc/cpuidle: Set CPUIDLE_FLAG_POLLING for snooze state
  powerpc/dts/fsl: Fix pca954x i2c-mux node names
  cxl: Remove unnecessary cxl_pci_window_alignment()
  selftests/powerpc: Fix resource leaks
  ...

1 files changed, 230 insertions, 1 deletions

diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h
index 05f246c0e36e..d0ea0571e79a 100644
--- a/arch/powerpc/include/asm/cmpxchg.h
+++ b/arch/powerpc/include/asm/cmpxchg.h
@@ -77,10 +77,76 @@ u32 __cmpxchg_##type##sfx(volatile void *p, u32 old, u32 new)	\
  * the previous value stored there.
  */
 
+#ifndef CONFIG_PPC_HAS_LBARX_LHARX
 XCHG_GEN(u8, _local, "memory");
 XCHG_GEN(u8, _relaxed, "cc");
 XCHG_GEN(u16, _local, "memory");
 XCHG_GEN(u16, _relaxed, "cc");
+#else
+static __always_inline unsigned long
+__xchg_u8_local(volatile void *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	lbarx	%0,0,%2		# __xchg_u8_local\n"
+"	stbcx.	%3,0,%2 \n"
+"	bne-	1b"
+	: "=&r" (prev), "+m" (*(volatile unsigned char *)p)
+	: "r" (p), "r" (val)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__xchg_u8_relaxed(u8 *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	lbarx	%0,0,%2		# __xchg_u8_relaxed\n"
+"	stbcx.	%3,0,%2\n"
+"	bne-	1b"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (val)
+	: "cc");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__xchg_u16_local(volatile void *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	lharx	%0,0,%2		# __xchg_u16_local\n"
+"	sthcx.	%3,0,%2\n"
+"	bne-	1b"
+	: "=&r" (prev), "+m" (*(volatile unsigned short *)p)
+	: "r" (p), "r" (val)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__xchg_u16_relaxed(u16 *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	lharx	%0,0,%2		# __xchg_u16_relaxed\n"
+"	sthcx.	%3,0,%2\n"
+"	bne-	1b"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (val)
+	: "cc");
+
+	return prev;
+}
+#endif
 
 static __always_inline unsigned long
 __xchg_u32_local(volatile void *p, unsigned long val)
@@ -198,11 +264,12 @@ __xchg_relaxed(void *ptr, unsigned long x, unsigned int size)
 	(__typeof__(*(ptr))) __xchg_relaxed((ptr),			\
 			(unsigned long)_x_, sizeof(*(ptr)));		\
 })
+
 /*
  * Compare and exchange - if *p == old, set it to new,
  * and return the old value of *p.
  */
-
+#ifndef CONFIG_PPC_HAS_LBARX_LHARX
 CMPXCHG_GEN(u8, , PPC_ATOMIC_ENTRY_BARRIER, PPC_ATOMIC_EXIT_BARRIER, "memory");
 CMPXCHG_GEN(u8, _local, , , "memory");
 CMPXCHG_GEN(u8, _acquire, , PPC_ACQUIRE_BARRIER, "memory");
@@ -211,6 +278,168 @@ CMPXCHG_GEN(u16, , PPC_ATOMIC_ENTRY_BARRIER, PPC_ATOMIC_EXIT_BARRIER, "memory");
 CMPXCHG_GEN(u16, _local, , , "memory");
 CMPXCHG_GEN(u16, _acquire, , PPC_ACQUIRE_BARRIER, "memory");
 CMPXCHG_GEN(u16, _relaxed, , , "cc");
+#else
+static __always_inline unsigned long
+__cmpxchg_u8(volatile unsigned char *p, unsigned long old, unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+	PPC_ATOMIC_ENTRY_BARRIER
+"1:	lbarx	%0,0,%2		# __cmpxchg_u8\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	stbcx.	%4,0,%2\n"
+"	bne-	1b"
+	PPC_ATOMIC_EXIT_BARRIER
+	"\n\
+2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u8_local(volatile unsigned char *p, unsigned long old,
+			unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+"1:	lbarx	%0,0,%2		# __cmpxchg_u8_local\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	stbcx.	%4,0,%2\n"
+"	bne-	1b\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u8_relaxed(u8 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	lbarx	%0,0,%2		# __cmpxchg_u8_relaxed\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	stbcx.	%4,0,%2\n"
+"	bne-	1b\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u8_acquire(u8 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	lbarx	%0,0,%2		# __cmpxchg_u8_acquire\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	stbcx.	%4,0,%2\n"
+"	bne-	1b\n"
+	PPC_ACQUIRE_BARRIER
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u16(volatile unsigned short *p, unsigned long old, unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+	PPC_ATOMIC_ENTRY_BARRIER
+"1:	lharx	%0,0,%2		# __cmpxchg_u16\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	sthcx.	%4,0,%2\n"
+"	bne-	1b\n"
+	PPC_ATOMIC_EXIT_BARRIER
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u16_local(volatile unsigned short *p, unsigned long old,
+			unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+"1:	lharx	%0,0,%2		# __cmpxchg_u16_local\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	sthcx.	%4,0,%2\n"
+"	bne-	1b"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u16_relaxed(u16 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	lharx	%0,0,%2		# __cmpxchg_u16_relaxed\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	sthcx.	%4,0,%2\n"
+"	bne-	1b\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u16_acquire(u16 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	lharx	%0,0,%2		# __cmpxchg_u16_acquire\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	sthcx.	%4,0,%2\n"
+"	bne-	1b\n"
+	PPC_ACQUIRE_BARRIER
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+#endif
 
 static __always_inline unsigned long
 __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)