Merge tag 'powerpc-5.7-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
"Slightly late as I had to rebase mid-week to insert a bug fix:

- A large series from Nick for 64-bit to further rework our exception
vectors, and rewrite portions of the syscall entry/exit and
interrupt return in C. The result is much easier to follow code
that is also faster in general.

- Cleanup of our ptrace code to split various parts out that had
become badly intertwined with #ifdefs over the years.

- Changes to our NUMA setup under the PowerVM hypervisor which should
hopefully avoid non-sensical topologies which can lead to warnings
from the workqueue code and other problems.

- MAINTAINERS updates to remove some of our old orphan entries and
update the status of others.

- Quite a few other small changes and fixes all over the map.

Thanks to: Abdul Haleem, afzal mohammed, Alexey Kardashevskiy, Andrew
Donnellan, Aneesh Kumar K.V, Balamuruhan S, Cédric Le Goater, Chen
Zhou, Christophe JAILLET, Christophe Leroy, Christoph Hellwig, Clement
Courbet, Daniel Axtens, David Gibson, Douglas Miller, Fabiano Rosas,
Fangrui Song, Ganesh Goudar, Gautham R. Shenoy, Greg Kroah-Hartman,
Greg Kurz, Gustavo Luiz Duarte, Hari Bathini, Ilie Halip, Jan Kara,
Joe Lawrence, Joe Perches, Kajol Jain, Larry Finger, Laurentiu Tudor,
Leonardo Bras, Libor Pechacek, Madhavan Srinivasan, Mahesh Salgaonkar,
Masahiro Yamada, Masami Hiramatsu, Mauricio Faria de Oliveira, Michael
Neuling, Michal Suchanek, Mike Rapoport, Nageswara R Sastry, Nathan
Chancellor, Nathan Lynch, Naveen N. Rao, Nicholas Piggin, Nick
Desaulniers, Oliver O'Halloran, Po-Hsu Lin, Pratik Rajesh Sampat,
Rasmus Villemoes, Ravi Bangoria, Roman Bolshakov, Sam Bobroff,
Sandipan Das, Santosh S, Sedat Dilek, Segher Boessenkool, Shilpasri G
Bhat, Sourabh Jain, Srikar Dronamraju, Stephen Rothwell, Tyrel
Datwyler, Vaibhav Jain, YueHaibing"

* tag 'powerpc-5.7-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (158 commits)
powerpc: Make setjmp/longjmp signature standard
powerpc/cputable: Remove unnecessary copy of cpu_spec->oprofile_type
powerpc: Suppress .eh_frame generation
powerpc: Drop -fno-dwarf2-cfi-asm
powerpc/32: drop unused ISA_DMA_THRESHOLD
powerpc/powernv: Add documentation for the opal sensor_groups sysfs interfaces
selftests/powerpc: Fix try-run when source tree is not writable
powerpc/vmlinux.lds: Explicitly retain .gnu.hash
powerpc/ptrace: move ptrace_triggered() into hw_breakpoint.c
powerpc/ptrace: create ppc_gethwdinfo()
powerpc/ptrace: create ptrace_get_debugreg()
powerpc/ptrace: split out ADV_DEBUG_REGS related functions.
powerpc/ptrace: move register viewing functions out of ptrace.c
powerpc/ptrace: split out TRANSACTIONAL_MEM related functions.
powerpc/ptrace: split out SPE related functions.
powerpc/ptrace: split out ALTIVEC related functions.
powerpc/ptrace: split out VSX related functions.
powerpc/ptrace: drop PARAMETER_SAVE_AREA_OFFSET
powerpc/ptrace: drop unnecessary #ifdefs CONFIG_PPC64
powerpc/ptrace: remove unused header includes
...

Documentation/ABI/obsolete/sysfs-kernel-fadump_enabled

···
+This ABI is renamed and moved to a new location /sys/kernel/fadump/enabled.
+
+What:		/sys/kernel/fadump_enabled
+Date:		Feb 2012
+Contact:	[e-mail]
+Description:	read only
+		Primarily used to identify whether the FADump is enabled in
+		the kernel or not.
+User:		Kdump service

Documentation/ABI/obsolete/sysfs-kernel-fadump_registered

···
+This ABI is renamed and moved to a new location /sys/kernel/fadump/registered.¬
+
+What:		/sys/kernel/fadump_registered
+Date:		Feb 2012
+Contact:	[e-mail]
+Description:	read/write
+		Helps to control the dump collect feature from userspace.
+		Setting 1 to this file enables the system to collect the
+		dump and 0 to disable it.
+User:		Kdump service

Documentation/ABI/obsolete/sysfs-kernel-fadump_release_mem

···
+This ABI is renamed and moved to a new location /sys/kernel/fadump/release_mem.¬
+
+What:		/sys/kernel/fadump_release_mem
+Date:		Feb 2012
+Contact:	[e-mail]
+Description:	write only
+		This is a special sysfs file and only available when
+		the system is booted to capture the vmcore using FADump.
+		It is used to release the memory reserved by FADump to
+		save the crash dump.

Documentation/ABI/removed/sysfs-kernel-fadump_release_opalcore

···
+This ABI is moved to /sys/firmware/opal/mpipl/release_core.
+
+What:		/sys/kernel/fadump_release_opalcore
+Date:		Sep 2019
+Contact:	[e-mail]
+Description:	write only
+		The sysfs file is available when the system is booted to
+		collect the dump on OPAL based machine. It used to release
+		the memory used to collect the opalcore.

Documentation/ABI/testing/sysfs-firmware-opal-sensor-groups

···
+What:		/sys/firmware/opal/sensor_groups
+Date:		August 2017
+Contact:	Linux for PowerPC mailing list <[e-mail]>
+Description:	Sensor groups directory for POWER9 powernv servers
+
+		Each folder in this directory contains a sensor group
+		which are classified based on type of the sensor
+		like power, temperature, frequency, current, etc. They
+		can also indicate the group of sensors belonging to
+		different owners like CSM, Profiler, Job-Scheduler
+
+What:		/sys/firmware/opal/sensor_groups/<sensor_group_name>/clear
+Date:		August 2017
+Contact:	Linux for PowerPC mailing list <[e-mail]>
+Description:	Sysfs file to clear the min-max of all the sensors
+		belonging to the group.
+
+		Writing 1 to this file will clear the minimum and
+		maximum values of all the sensors in the group.
+		In POWER9, the min-max of a sensor is the historical minimum
+		and maximum value of the sensor cached by OCC.

Documentation/ABI/testing/sysfs-kernel-fadump

···
+What:		/sys/kernel/fadump/*
+Date:		Dec 2019
+Contact:	[e-mail]
+Description:
+		The /sys/kernel/fadump/* is a collection of FADump sysfs
+		file provide information about the configuration status
+		of Firmware Assisted Dump (FADump).
+
+What:		/sys/kernel/fadump/enabled
+Date:		Dec 2019
+Contact:	[e-mail]
+Description:	read only
+		Primarily used to identify whether the FADump is enabled in
+		the kernel or not.
+User:		Kdump service
+
+What:		/sys/kernel/fadump/registered
+Date:		Dec 2019
+Contact:	[e-mail]
+Description:	read/write
+		Helps to control the dump collect feature from userspace.
+		Setting 1 to this file enables the system to collect the
+		dump and 0 to disable it.
+User:		Kdump service
+
+What:		/sys/kernel/fadump/release_mem
+Date:		Dec 2019
+Contact:	[e-mail]
+Description:	write only
+		This is a special sysfs file and only available when
+		the system is booted to capture the vmcore using FADump.
+		It is used to release the memory reserved by FADump to
+		save the crash dump.
+
+What:		/sys/kernel/fadump/mem_reserved
+Date:		Dec 2019
+Contact:	[e-mail]
+Description:	read only
+		Provide information about the amount of memory reserved by
+		FADump to save the crash dump in bytes.

Documentation/powerpc/firmware-assisted-dump.rst

···
 
 -- On OPAL based machines (PowerNV), if the kernel is build with
    CONFIG_OPAL_CORE=y, OPAL memory at the time of crash is also
-   exported as /sys/firmware/opal/core file. This procfs file is
+   exported as /sys/firmware/opal/mpipl/core file. This procfs file is
    helpful in debugging OPAL crashes with GDB. The kernel memory
    used for exporting this procfs file can be released by echo'ing
-   '1' to /sys/kernel/fadump_release_opalcore node.
+   '1' to /sys/firmware/opal/mpipl/release_core node.
 
    e.g.
-     # echo 1 > /sys/kernel/fadump_release_opalcore
+     # echo 1 > /sys/firmware/opal/mpipl/release_core
 
 Implementation details:
 -----------------------
···
     be handled and vmcore will not be captured. This interface can be
     easily integrated with kdump service start/stop.
 
+ /sys/kernel/fadump/mem_reserved
+
+   This is used to display the memory reserved by FADump for saving the
+   crash dump.
+
  /sys/kernel/fadump_release_mem
     This file is available only when FADump is active during
     second kernel. This is used to release the reserved memory
···
     enhanced to use this interface to release the memory reserved for
     dump and continue without 2nd reboot.
 
- /sys/kernel/fadump_release_opalcore
+Note: /sys/kernel/fadump_release_opalcore sysfs has moved to
+      /sys/firmware/opal/mpipl/release_core
+
+ /sys/firmware/opal/mpipl/release_core
 
     This file is available only on OPAL based machines when FADump is
     active during capture kernel. This is used to release the memory
-    used by the kernel to export /sys/firmware/opal/core file. To
+    used by the kernel to export /sys/firmware/opal/mpipl/core file. To
     release this memory, echo '1' to it:
 
-    echo 1  > /sys/kernel/fadump_release_opalcore
+    echo 1  > /sys/firmware/opal/mpipl/release_core
+
+Note: The following FADump sysfs files are deprecated.
+
++----------------------------------+--------------------------------+
+| Deprecated                       | Alternative                    |
++----------------------------------+--------------------------------+
+| /sys/kernel/fadump_enabled       | /sys/kernel/fadump/enabled     |
++----------------------------------+--------------------------------+
+| /sys/kernel/fadump_registered    | /sys/kernel/fadump/registered  |
++----------------------------------+--------------------------------+
+| /sys/kernel/fadump_release_mem   | /sys/kernel/fadump/release_mem |
++----------------------------------+--------------------------------+
 
 Here is the list of files under powerpc debugfs:
 (Assuming debugfs is mounted on /sys/kernel/debug directory.)

MAINTAINERS

···
 
 LINUX FOR POWER MACINTOSH
 M:	Benjamin Herrenschmidt <[e-mail]>
-W:	http://www.penguinppc.org/
 L:	[e-mail]
-S:	Maintained
+S:	Odd Fixes
 F:	arch/powerpc/platforms/powermac/
 F:	drivers/macintosh/
 
 LINUX FOR POWERPC (32-BIT AND 64-BIT)
-M:	Benjamin Herrenschmidt <[e-mail]>
-M:	Paul Mackerras <[e-mail]>
 M:	Michael Ellerman <[e-mail]>
-W:	https://github.com/linuxppc/linux/wiki
+R:	Benjamin Herrenschmidt <[e-mail]>
+R:	Paul Mackerras <[e-mail]>
+W:	https://github.com/linuxppc/wiki/wiki
 L:	[e-mail]
 Q:	http://patchwork.ozlabs.org/project/linuxppc-dev/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git
···
 F:	drivers/i2c/busses/i2c-opal.c
 F:	drivers/net/ethernet/ibm/ibmveth.*
 F:	drivers/net/ethernet/ibm/ibmvnic.*
+F:	drivers/*/*/*pasemi*
+F:	drivers/*/*pasemi*
 F:	drivers/pci/hotplug/pnv_php.c
 F:	drivers/pci/hotplug/rpa*
 F:	drivers/rtc/rtc-opal.c
···
 LINUX FOR POWERPC EMBEDDED MPC5XXX
 M:	Anatolij Gustschin <[e-mail]>
 L:	[e-mail]
-T:	git git://git.denx.de/linux-denx-agust.git
-S:	Maintained
+S:	Odd Fixes
 F:	arch/powerpc/platforms/512x/
 F:	arch/powerpc/platforms/52xx/
 
 LINUX FOR POWERPC EMBEDDED PPC4XX
-M:	Alistair Popple <[e-mail]>
-M:	Matt Porter <[e-mail]>
-W:	http://www.penguinppc.org/
 L:	[e-mail]
-S:	Maintained
+S:	Orphan
 F:	arch/powerpc/platforms/40x/
 F:	arch/powerpc/platforms/44x/
 
 LINUX FOR POWERPC EMBEDDED PPC83XX AND PPC85XX
 M:	Scott Wood <[e-mail]>
-M:	Kumar Gala <[e-mail]>
-W:	http://www.penguinppc.org/
 L:	[e-mail]
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/scottwood/linux.git
-S:	Maintained
+S:	Odd fixes
 F:	arch/powerpc/platforms/83xx/
 F:	arch/powerpc/platforms/85xx/
 F:	Documentation/devicetree/bindings/powerpc/fsl/
 
 LINUX FOR POWERPC EMBEDDED PPC8XX
-M:	Vitaly Bordug <[e-mail]>
-W:	http://www.penguinppc.org/
+M:	Christophe Leroy <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	arch/powerpc/platforms/8xx/
-
-LINUX FOR POWERPC EMBEDDED XILINX VIRTEX
-L:	[e-mail]
-S:	Orphan
-F:	arch/powerpc/*/*virtex*
-F:	arch/powerpc/*/*/*virtex*
-
-LINUX FOR POWERPC PA SEMI PWRFICIENT
-L:	[e-mail]
-S:	Orphan
-F:	arch/powerpc/platforms/pasemi/
-F:	drivers/*/*pasemi*
-F:	drivers/*/*/*pasemi*
 
 LINUX KERNEL DUMP TEST MODULE (LKDTM)
 M:	Kees Cook <[e-mail]>
···
 W:	http://wireless.kernel.org/en/users/Drivers/p54
 S:	Maintained
 F:	drivers/net/wireless/intersil/p54/
-
-PA SEMI ETHERNET DRIVER
-L:	[e-mail]
-S:	Orphan
-F:	drivers/net/ethernet/pasemi/*
-
-PA SEMI SMBUS DRIVER
-L:	[e-mail]
-S:	Orphan
-F:	drivers/i2c/busses/i2c-pasemi.c
 
 PACKING
 M:	Vladimir Oltean <[e-mail]>

arch/powerpc/Makefile

···
 KBUILD_CFLAGS += $(call cc-option,-mno-spe)
 KBUILD_CFLAGS += $(call cc-option,-mspe=no)
 
-# FIXME: the module load should be taught about the additional relocs
-# generated by this.
-# revert to pre-gcc-4.4 behaviour of .eh_frame
-KBUILD_CFLAGS	+= $(call cc-option,-fno-dwarf2-cfi-asm)
+# Don't emit .eh_frame since we have no use for it
+KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 
 # Never use string load/store instructions as they are
 # often slow when they are implemented at all
···
 	$(Q)$(MAKE) $(build)=$(boot) $(patsubst %,$(boot)/%,$@)
 
 
+PHONY += bootwrapper_install
 bootwrapper_install:
 	$(Q)$(MAKE) $(build)=$(boot) $(patsubst %,$(boot)/%,$@)
 
···
   @echo '  (minus the .dts extension).'
 endef
 
+PHONY += install
 install:
 	$(Q)$(MAKE) $(build)=$(boot) install
 
+PHONY += vdso_install
 vdso_install:
 ifdef CONFIG_PPC64
 	$(Q)$(MAKE) $(build)=arch/$(ARCH)/kernel/vdso64 $@
···
 ifdef CONFIG_STACKPROTECTOR
 prepare: stack_protector_prepare
 
+PHONY += stack_protector_prepare
 stack_protector_prepare: prepare0
 ifdef CONFIG_PPC64
 	$(eval KBUILD_CFLAGS += -mstack-protector-guard-offset=$(shell awk '{if ($$2 == "PACA_CANARY") print $$3;}' include/generated/asm-offsets.h))
···
 ifdef CONFIG_SMP
 prepare: task_cpu_prepare
 
+PHONY += task_cpu_prepare
 task_cpu_prepare: prepare0
 	$(eval KBUILD_CFLAGS += -D_TASK_CPU=$(shell awk '{if ($$2 == "TASK_CPU") print $$3;}' include/generated/asm-offsets.h))
 endif
 
+PHONY += checkbin
 # Check toolchain versions:
 # - gcc-4.6 is the minimum kernel-wide version so nothing required.
 checkbin:

arch/powerpc/boot/Makefile

···
 zInstall: $(CONFIGURE) $(addprefix $(obj)/, $(image-y))
 	sh -x $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" vmlinux System.map "$(INSTALL_PATH)" $^
 
+PHONY += install zInstall
+
 # anything not in $(targets)
 clean-files += $(image-) $(initrd-) cuImage.* dtbImage.* treeImage.* \
 	zImage zImage.initrd zImage.chrp zImage.coff zImage.holly \

arch/powerpc/boot/crt0.S

···
 p_pstack:	.long	_platform_stack_top
 #endif
 
-	.globl	_zimage_start
-	/* Clang appears to require the .weak directive to be after the symbol
-	 * is defined. See https://bugs.llvm.org/show_bug.cgi?id=38921  */
 	.weak	_zimage_start
 _zimage_start:
 	.globl	_zimage_start_lib

arch/powerpc/include/asm/asm-prototypes.h

···
 unsigned long __init early_init(unsigned long dt_ptr);
 void __init machine_init(u64 dt_ptr);
 #endif
+long system_call_exception(long r3, long r4, long r5, long r6, long r7, long r8, unsigned long r0, struct pt_regs *regs);
+notrace unsigned long syscall_exit_prepare(unsigned long r3, struct pt_regs *regs);
+notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned long msr);
+notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsigned long msr);
 
 long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low,
 		      u32 len_high, u32 len_low);
 long sys_switch_endian(void);
 notrace unsigned int __check_irq_replay(void);
 void notrace restore_interrupts(void);
-
-/* ptrace */
-long do_syscall_trace_enter(struct pt_regs *regs);
-void do_syscall_trace_leave(struct pt_regs *regs);
-
-/* process */
-void restore_math(struct pt_regs *regs);
-void restore_tm_state(struct pt_regs *regs);
 
 /* prom_init (OpenFirmware) */
 unsigned long __init prom_init(unsigned long r3, unsigned long r4,
···
 /* setup */
 void __init early_setup(unsigned long dt_ptr);
 void early_setup_secondary(void);
-
-/* time */
-void accumulate_stolen_time(void);
 
 /* misc runtime */
 extern u64 __bswapdi2(u64);

arch/powerpc/include/asm/book3s/32/hash.h

···
  * updating the accessed and modified bits in the page table tree.
  */
 
-#define _PAGE_PRESENT	0x001	/* software: pte contains a translation */
-#define _PAGE_HASHPTE	0x002	/* hash_page has made an HPTE for this pte */
-#define _PAGE_USER	0x004	/* usermode access allowed */
+#define _PAGE_USER	0x001	/* usermode access allowed */
+#define _PAGE_RW	0x002	/* software: user write access allowed */
+#define _PAGE_PRESENT	0x004	/* software: pte contains a translation */
 #define _PAGE_GUARDED	0x008	/* G: prohibit speculative access */
 #define _PAGE_COHERENT	0x010	/* M: enforce memory coherence (SMP systems) */
 #define _PAGE_NO_CACHE	0x020	/* I: cache inhibit */
···
 #define _PAGE_DIRTY	0x080	/* C: page changed */
 #define _PAGE_ACCESSED	0x100	/* R: page referenced */
 #define _PAGE_EXEC	0x200	/* software: exec allowed */
-#define _PAGE_RW	0x400	/* software: user write access allowed */
+#define _PAGE_HASHPTE	0x400	/* hash_page has made an HPTE for this pte */
 #define _PAGE_SPECIAL	0x800	/* software: Special page */
 
 #ifdef CONFIG_PTE_64BIT

arch/powerpc/include/asm/book3s/32/pgtable.h

···
 	(((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
 #define pte_offset_kernel(dir, addr)	\
 	((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(addr))
-#define pte_offset_map(dir, addr)		\
-	((pte_t *)(kmap_atomic(pmd_page(*(dir))) + \
-		   (pmd_page_vaddr(*(dir)) & ~PAGE_MASK)) + pte_index(addr))
-#define pte_unmap(pte)		kunmap_atomic(pte)
+#define pte_offset_map(dir, addr)	pte_offset_kernel((dir), (addr))
+static inline void pte_unmap(pte_t *pte) { }
 
 /*
  * Encode and decode a swap entry.

arch/powerpc/include/asm/book3s/64/hash-4k.h

···
 extern int hash__has_transparent_hugepage(void);
 #endif
 
+static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd)
+{
+	BUG();
+	return pmd;
+}
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_BOOK3S_64_HASH_4K_H */

arch/powerpc/include/asm/book3s/64/hash-64k.h

···
  */
 static inline int hash__pmd_trans_huge(pmd_t pmd)
 {
-	return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE)) ==
+	return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP)) ==
 		  (_PAGE_PTE | H_PAGE_THP_HUGE));
 }
 
···
 				       unsigned long addr, pmd_t *pmdp);
 extern int hash__has_transparent_hugepage(void);
 #endif /*  CONFIG_TRANSPARENT_HUGEPAGE */
+
+static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP));
+}
+
 #endif	/* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_BOOK3S_64_HASH_64K_H */

arch/powerpc/include/asm/book3s/64/kup-radix.h

···
 #define _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H
 
 #include <linux/const.h>
+#include <asm/reg.h>
 
 #define AMR_KUAP_BLOCK_READ	UL(0x4000000000000000)
 #define AMR_KUAP_BLOCK_WRITE	UL(0x8000000000000000)
···
 
 #ifdef CONFIG_PPC_KUAP
 
-#include <asm/reg.h>
+#include <asm/mmu.h>
+#include <asm/ptrace.h>
+
+static inline void kuap_restore_amr(struct pt_regs *regs)
+{
+	if (mmu_has_feature(MMU_FTR_RADIX_KUAP))
+		mtspr(SPRN_AMR, regs->kuap);
+}
+
+static inline void kuap_check_amr(void)
+{
+	if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG) && mmu_has_feature(MMU_FTR_RADIX_KUAP))
+		WARN_ON_ONCE(mfspr(SPRN_AMR) != AMR_KUAP_BLOCKED);
+}
 
 /*
  * We support individually allowing read or write, but we don't support nesting
···
 	return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) &&
 		    (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)),
 		    "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read");
+}
+#else /* CONFIG_PPC_KUAP */
+static inline void kuap_restore_amr(struct pt_regs *regs)
+{
+}
+
+static inline void kuap_check_amr(void)
+{
 }
 #endif /* CONFIG_PPC_KUAP */
 

arch/powerpc/include/asm/book3s/64/pgtable.h

···
 
 static inline pmd_t pmd_mkdevmap(pmd_t pmd)
 {
-	return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP));
+	if (radix_enabled())
+		return radix__pmd_mkdevmap(pmd);
+	return hash__pmd_mkdevmap(pmd);
 }
 
 static inline int pmd_devmap(pmd_t pmd)

arch/powerpc/include/asm/book3s/64/radix.h

···
 }
 #endif
 
+static inline pmd_t radix__pmd_mkdevmap(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP));
+}
+
 extern int __meminit radix__vmemmap_create_mapping(unsigned long start,
 					     unsigned long page_size,
 					     unsigned long phys);

arch/powerpc/include/asm/cache.h

···
 
 #endif
 
-#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+#define __read_mostly __section(.data..read_mostly)
 
 #ifdef CONFIG_PPC_BOOK3S_32
 extern long _get_L2CR(void);

arch/powerpc/include/asm/cacheflush.h

···
 	unsigned long size = stop - (unsigned long)addr + (bytes - 1);
 	unsigned long i;
 
-	if (IS_ENABLED(CONFIG_PPC64)) {
+	if (IS_ENABLED(CONFIG_PPC64))
 		mb();	/* sync */
-		isync();
-	}
 
 	for (i = 0; i < size >> shift; i++, addr += bytes)
 		dcbf(addr);
 	mb();	/* sync */
 
-	if (IS_ENABLED(CONFIG_PPC64))
-		isync();
 }
 
 /*

arch/powerpc/include/asm/cputime.h

···
  */
 #ifdef CONFIG_PPC64
 #define get_accounting(tsk)	(&get_paca()->accounting)
+#define raw_get_accounting(tsk)	(&local_paca->accounting)
 static inline void arch_vtime_task_switch(struct task_struct *tsk) { }
+
 #else
 #define get_accounting(tsk)	(&task_thread_info(tsk)->accounting)
+#define raw_get_accounting(tsk)	get_accounting(tsk)
 /*
  * Called from the context switch with interrupts disabled, to charge all
  * accumulated times to the current process, and to prepare accounting on
···
 }
 #endif
 
+/*
+ * account_cpu_user_entry/exit runs "unreconciled", so can't trace,
+ * can't use use get_paca()
+ */
+static notrace inline void account_cpu_user_entry(void)
+{
+	unsigned long tb = mftb();
+	struct cpu_accounting_data *acct = raw_get_accounting(current);
+
+	acct->utime += (tb - acct->starttime_user);
+	acct->starttime = tb;
+}
+
+static notrace inline void account_cpu_user_exit(void)
+{
+	unsigned long tb = mftb();
+	struct cpu_accounting_data *acct = raw_get_accounting(current);
+
+	acct->stime += (tb - acct->starttime);
+	acct->starttime_user = tb;
+}
+
+
 #endif /* __KERNEL__ */
+#else /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
+static inline void account_cpu_user_entry(void)
+{
+}
+static inline void account_cpu_user_exit(void)
+{
+}
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 #endif /* __POWERPC_CPUTIME_H */

arch/powerpc/include/asm/dma.h

···
 #define DMA2_EXT_REG		0x4D6
 
 #ifndef __powerpc64__
-    /* in arch/ppc/kernel/setup.c -- Cort */
+    /* in arch/powerpc/kernel/setup_32.c -- Cort */
     extern unsigned int DMA_MODE_WRITE;
     extern unsigned int DMA_MODE_READ;
-    extern unsigned long ISA_DMA_THRESHOLD;
 #else
     #define DMA_MODE_READ	0x44	/* I/O to memory, no autoinit, increment, single mode */
     #define DMA_MODE_WRITE	0x48	/* memory to I/O, no autoinit, increment, single mode */

arch/powerpc/include/asm/drmem.h

···
 extern struct drmem_lmb_info *drmem_info;
 
 #define for_each_drmem_lmb_in_range(lmb, start, end)		\
-	for ((lmb) = (start); (lmb) <= (end); (lmb)++)
+	for ((lmb) = (start); (lmb) < (end); (lmb)++)
 
 #define for_each_drmem_lmb(lmb)					\
 	for_each_drmem_lmb_in_range((lmb),			\
 		&drmem_info->lmbs[0],				\
-		&drmem_info->lmbs[drmem_info->n_lmbs - 1])
+		&drmem_info->lmbs[drmem_info->n_lmbs])
 
 /*
  * The of_drconf_cell_v1 struct defines the layout of the LMB data

arch/powerpc/include/asm/eeh.h

···
 struct eeh_ops {
 	char *name;
 	int (*init)(void);
-	void* (*probe)(struct pci_dn *pdn, void *data);
+	struct eeh_dev *(*probe)(struct pci_dev *pdev);
 	int (*set_option)(struct eeh_pe *pe, int option);
 	int (*get_pe_addr)(struct eeh_pe *pe);
 	int (*get_state)(struct eeh_pe *pe, int *delay);
···
 int eeh_check_failure(const volatile void __iomem *token);
 int eeh_dev_check_failure(struct eeh_dev *edev);
 void eeh_addr_cache_init(void);
-void eeh_add_device_early(struct pci_dn *);
-void eeh_add_device_tree_early(struct pci_dn *);
-void eeh_add_device_late(struct pci_dev *);
-void eeh_add_device_tree_late(struct pci_bus *);
-void eeh_add_sysfs_files(struct pci_bus *);
+void eeh_probe_device(struct pci_dev *pdev);
 void eeh_remove_device(struct pci_dev *);
 int eeh_unfreeze_pe(struct eeh_pe *pe);
 int eeh_pe_reset_and_recover(struct eeh_pe *pe);
···
 
 static inline void eeh_addr_cache_init(void) { }
 
-static inline void eeh_add_device_early(struct pci_dn *pdn) { }
-
-static inline void eeh_add_device_tree_early(struct pci_dn *pdn) { }
-
-static inline void eeh_add_device_late(struct pci_dev *dev) { }
-
-static inline void eeh_add_device_tree_late(struct pci_bus *bus) { }
-
-static inline void eeh_add_sysfs_files(struct pci_bus *bus) { }
+static inline void eeh_probe_device(struct pci_dev *dev) { }
 
 static inline void eeh_remove_device(struct pci_dev *dev) { }
 
 #define EEH_POSSIBLE_ERROR(val, type) (0)
 #define EEH_IO_ERROR_VALUE(size) (-1UL)
 #endif /* CONFIG_EEH */
+
+#if defined(CONFIG_PPC_PSERIES) && defined(CONFIG_EEH)
+void pseries_eeh_init_edev(struct pci_dn *pdn);
+void pseries_eeh_init_edev_recursive(struct pci_dn *pdn);
+#else
+static inline void pseries_eeh_add_device_early(struct pci_dn *pdn) { }
+static inline void pseries_eeh_add_device_tree_early(struct pci_dn *pdn) { }
+#endif
 
 #ifdef CONFIG_PPC64
 /*

arch/powerpc/include/asm/exception-64s.h

···
 #include <asm/feature-fixups.h>
 
 /* PACA save area size in u64 units (exgen, exmc, etc) */
-#if defined(CONFIG_RELOCATABLE)
 #define EX_SIZE		10
-#else
-#define EX_SIZE		9
-#endif
 
 /*
  * maximum recursive depth of MCE exceptions

arch/powerpc/include/asm/hw_irq.h

···
 #ifndef __ASSEMBLY__
 
 extern void replay_system_reset(void);
-extern void __replay_interrupt(unsigned int vector);
+extern void replay_soft_interrupts(void);
 
 extern void timer_interrupt(struct pt_regs *);
 extern void timer_broadcast_interrupt(void);
···
 #ifdef CONFIG_PPC_BOOK3E
 #define __hard_irq_enable()	wrtee(MSR_EE)
 #define __hard_irq_disable()	wrtee(0)
+#define __hard_EE_RI_disable()	wrtee(0)
+#define __hard_RI_enable()	do { } while (0)
 #else
 #define __hard_irq_enable()	__mtmsrd(MSR_EE|MSR_RI, 1)
 #define __hard_irq_disable()	__mtmsrd(MSR_RI, 1)
+#define __hard_EE_RI_disable()	__mtmsrd(0, 1)
+#define __hard_RI_enable()	__mtmsrd(MSR_RI, 1)
 #endif
 
 #define hard_irq_disable()	do {					\

arch/powerpc/include/asm/kvm_host.h

···
 	pgd_t *pgtable;
 	u64 process_table;
 	struct dentry *debugfs_dir;
-	struct dentry *htab_dentry;
-	struct dentry *radix_dentry;
 	struct kvm_resize_hpt *resize_hpt; /* protected by kvm->lock */
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
···
 	struct kvmhv_tb_accumulator cede_time;	/* time napping inside guest */
 
 	struct dentry *debugfs_dir;
-	struct dentry *debugfs_timings;
 #endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
 };
 

arch/powerpc/include/asm/mce.h

···
 extern void machine_check_print_event_info(struct machine_check_event *evt,
 					   bool user_mode, bool in_guest);
 unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr);
+extern void mce_common_process_ue(struct pt_regs *regs,
+				  struct mce_error_info *mce_err);
 #ifdef CONFIG_PPC_BOOK3S_64
 void flush_and_reload_slb(void);
 #endif /* CONFIG_PPC_BOOK3S_64 */

arch/powerpc/include/asm/nohash/32/pgtable.h

···
 #define pte_offset_kernel(dir, addr)	\
 	(pmd_bad(*(dir)) ? NULL : (pte_t *)pmd_page_vaddr(*(dir)) + \
 				  pte_index(addr))
-#define pte_offset_map(dir, addr)		\
-	((pte_t *)(kmap_atomic(pmd_page(*(dir))) + \
-		   (pmd_page_vaddr(*(dir)) & ~PAGE_MASK)) + pte_index(addr))
-#define pte_unmap(pte)		kunmap_atomic(pte)
+#define pte_offset_map(dir, addr)	pte_offset_kernel((dir), (addr))
+static inline void pte_unmap(pte_t *pte) { }
 
 /*
  * Encode and decode a swap entry.

arch/powerpc/include/asm/opal-api.h

···
 	OPAL_REBOOT_PLATFORM_ERROR	= 1,
 	OPAL_REBOOT_FULL_IPL		= 2,
 	OPAL_REBOOT_MPIPL		= 3,
+	OPAL_REBOOT_FAST		= 4,
 };
 
 /* Argument to OPAL_PCI_TCE_KILL */

arch/powerpc/include/asm/perf_event.h

···
 	do {							\
 		(regs)->result = 0;				\
 		(regs)->nip = __ip;				\
-		(regs)->gpr[1] = current_stack_pointer();	\
+		(regs)->gpr[1] = current_stack_frame();		\
 		asm volatile("mfmsr %0" : "=r" ((regs)->msr));	\
 	} while (0)
 

arch/powerpc/include/asm/pgtable.h

···
 
 #ifndef __ASSEMBLY__
 
+#ifdef CONFIG_PPC32
+static inline pmd_t *pmd_ptr(struct mm_struct *mm, unsigned long va)
+{
+	return pmd_offset(pud_offset(pgd_offset(mm, va), va), va);
+}
+
+static inline pmd_t *pmd_ptr_k(unsigned long va)
+{
+	return pmd_offset(pud_offset(pgd_offset_k(va), va), va);
+}
+
+static inline pte_t *virt_to_kpte(unsigned long vaddr)
+{
+	pmd_t *pmd = pmd_ptr_k(vaddr);
+
+	return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr);
+}
+#endif
+
 #include <asm/tlbflush.h>
 
 /* Keep these as a macros to avoid include dependency mess */

arch/powerpc/include/asm/ptrace.h

···
 #define profile_pc(regs) instruction_pointer(regs)
 #endif
 
+long do_syscall_trace_enter(struct pt_regs *regs);
+void do_syscall_trace_leave(struct pt_regs *regs);
+
 #define kernel_stack_pointer(regs) ((regs)->gpr[1])
 static inline int is_syscall_success(struct pt_regs *regs)
 {
···
 #endif /* __ASSEMBLY__ */
 
 #ifndef __powerpc64__
+/* We need PT_SOFTE defined at all time to avoid #ifdefs */
+#define PT_SOFTE PT_MQ
 #else /* __powerpc64__ */
 #define PT_FPSCR32 (PT_FPR0 + 2*32 + 1)	/* each FP reg occupies 2 32-bit userspace slots */
 #define PT_VR0_32 164	/* each Vector reg occupies 4 slots in 32-bit */

arch/powerpc/include/asm/reg.h

···
 
 #define proc_trap()	asm volatile("trap")
 
-extern unsigned long current_stack_pointer(void);
+extern unsigned long current_stack_frame(void);
+
+register unsigned long current_stack_pointer asm("r1");
 
 extern unsigned long scom970_read(unsigned int address);
 extern void scom970_write(unsigned int address, unsigned long value);

arch/powerpc/include/asm/setjmp.h

···
 
 #define JMP_BUF_LEN    23
 
-extern long setjmp(long *) __attribute__((returns_twice));
-extern void longjmp(long *, long) __attribute__((noreturn));
+typedef long jmp_buf[JMP_BUF_LEN];
+
+extern int setjmp(jmp_buf env) __attribute__((returns_twice));
+extern void longjmp(jmp_buf env, int val) __attribute__((noreturn));
 
 #endif /* _ASM_POWERPC_SETJMP_H */

arch/powerpc/include/asm/signal.h

···
 #include <uapi/asm/signal.h>
 #include <uapi/asm/ptrace.h>
 
+struct pt_regs;
+void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags);
+
 #endif /* _ASM_POWERPC_SIGNAL_H */

arch/powerpc/include/asm/switch_to.h

···
 #ifndef _ASM_POWERPC_SWITCH_TO_H
 #define _ASM_POWERPC_SWITCH_TO_H
 
+#include <linux/sched.h>
 #include <asm/reg.h>
 
 struct thread_struct;
···
 extern void switch_booke_debug_regs(struct debug_reg *new_debug);
 
 extern int emulate_altivec(struct pt_regs *);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+void restore_math(struct pt_regs *regs);
+#else
+static inline void restore_math(struct pt_regs *regs)
+{
+}
+#endif
+
+void restore_tm_state(struct pt_regs *regs);
 
 extern void flush_all_to_thread(struct task_struct *);
 extern void giveup_all(struct task_struct *);

arch/powerpc/include/asm/time.h

···
 
 
 extern void generic_calibrate_decr(void);
-extern void hdec_interrupt(struct pt_regs *regs);
 
 /* Some sane defaults: 125 MHz timebase, 1GHz processor */
 extern unsigned long ppc_proc_freq;
···
 
 /* Convert timebase ticks to nanoseconds */
 unsigned long long tb_to_ns(unsigned long long tb_ticks);
+
+/* SPLPAR */
+void accumulate_stolen_time(void);
 
 #endif /* __KERNEL__ */
 #endif /* __POWERPC_TIME_H */

arch/powerpc/include/asm/topology.h

···
 extern int prrn_is_enabled(void);
 extern int find_and_online_cpu_nid(int cpu);
 extern int timed_topology_update(int nsecs);
-extern void __init shared_proc_topology_init(void);
 #else
 static inline int start_topology_update(void)
 {
···
 	return 0;
 }
 
-#ifdef CONFIG_SMP
-static inline void shared_proc_topology_init(void) {}
-#endif
 #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
 
 #include <asm-generic/topology.h>
···
 #ifdef CONFIG_PPC64
 #include <asm/smp.h>
 
+#ifdef CONFIG_PPC_SPLPAR
+int get_physical_package_id(int cpu);
+#define topology_physical_package_id(cpu)	(get_physical_package_id(cpu))
+#else
 #define topology_physical_package_id(cpu)	(cpu_to_chip_id(cpu))
+#endif
+
 #define topology_sibling_cpumask(cpu)	(per_cpu(cpu_sibling_map, cpu))
 #define topology_core_cpumask(cpu)	(per_cpu(cpu_core_map, cpu))
 #define topology_core_id(cpu)		(cpu_to_core_id(cpu))

arch/powerpc/include/asm/vdso.h

···
 
 #define VDSO_VERSION_STRING	LINUX_2.6.15
 
-/* Define if 64 bits VDSO has procedure descriptors */
-#undef VDS64_HAS_DESCRIPTORS
-
 #ifndef __ASSEMBLY__
 
 /* Offsets relative to thread->vdso_base */
···
 #else /* __ASSEMBLY__ */
 
 #ifdef __VDSO64__
-#ifdef VDS64_HAS_DESCRIPTORS
-#define V_FUNCTION_BEGIN(name)		\
-	.globl name;			\
-        .section ".opd","a";		\
-        .align 3;			\
-	name:				\
-	.quad .name,.TOC.@tocbase,0;	\
-	.previous;			\
-	.globl .name;			\
-	.type .name,@function; 		\
-	.name:				\
-
-#define V_FUNCTION_END(name)		\
-	.size .name,.-.name;
-
-#define V_LOCAL_FUNC(name) (.name)
-
-#else /* VDS64_HAS_DESCRIPTORS */
-
 #define V_FUNCTION_BEGIN(name)		\
 	.globl name;			\
 	name:				\
···
 	.size name,.-name;
 
 #define V_LOCAL_FUNC(name) (name)
-
-#endif /* VDS64_HAS_DESCRIPTORS */
 #endif /* __VDSO64__ */
 
 #ifdef __VDSO32__

arch/powerpc/kernel/Makefile

···
 # Makefile for the linux kernel.
 #
 
-CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
-
 ifdef CONFIG_PPC64
 CFLAGS_prom_init.o	+= $(NO_MINIMAL_TOC)
 endif
···
 CFLAGS_btext.o += -DDISABLE_BRANCH_PROFILING
 endif
 
-obj-y				:= cputable.o ptrace.o syscalls.o \
+obj-y				:= cputable.o syscalls.o \
 				   irq.o align.o signal_32.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 note.o
+obj-y				+= ptrace/
+obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o signal_64.o \
+				   paca.o nvram_64.o firmware.o note.o \
+				   syscall_64.o
 obj-$(CONFIG_VDSO32)		+= vdso32/
 obj-$(CONFIG_PPC_WATCHDOG)	+= watchdog.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o

arch/powerpc/kernel/btext.c

···
 static void scrollscreen(void);
 #endif
 
-#define __force_data __attribute__((__section__(".data")))
+#define __force_data __section(.data)
 
 static int g_loc_X __force_data;
 static int g_loc_Y __force_data;

arch/powerpc/kernel/cputable.c

···
 		 */
 		if (old.oprofile_cpu_type != NULL) {
 			t->oprofile_cpu_type = old.oprofile_cpu_type;
-			t->oprofile_type = old.oprofile_type;
 			t->cpu_features |= old.cpu_features & CPU_FTR_PMAO_BUG;
 		}
 	}

arch/powerpc/kernel/dt_cpu_ftrs.c

···
 	/* Initialize the base environment -- clear FSCR/HFSCR.  */
 	hv_mode = !!(mfmsr() & MSR_HV);
 	if (hv_mode) {
-		/* CPU_FTR_HVMODE is used early in PACA setup */
 		cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE;
 		mtspr(SPRN_HFSCR, 0);
 	}

arch/powerpc/kernel/eeh.c

···
 core_initcall_sync(eeh_init);
 
 /**
- * eeh_add_device_early - Enable EEH for the indicated device node
- * @pdn: PCI device node for which to set up EEH
- *
- * This routine must be used to perform EEH initialization for PCI
- * devices that were added after system boot (e.g. hotplug, dlpar).
- * This routine must be called before any i/o is performed to the
- * adapter (inluding any config-space i/o).
- * Whether this actually enables EEH or not for this device depends
- * on the CEC architecture, type of the device, on earlier boot
- * command-line arguments & etc.
- */
-void eeh_add_device_early(struct pci_dn *pdn)
-{
-	struct pci_controller *phb = pdn ? pdn->phb : NULL;
-	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
-
-	if (!edev)
-		return;
-
-	if (!eeh_has_flag(EEH_PROBE_MODE_DEVTREE))
-		return;
-
-	/* USB Bus children of PCI devices will not have BUID's */
-	if (NULL == phb ||
-	    (eeh_has_flag(EEH_PROBE_MODE_DEVTREE) && 0 == phb->buid))
-		return;
-
-	eeh_ops->probe(pdn, NULL);
-}
-
-/**
- * eeh_add_device_tree_early - Enable EEH for the indicated device
- * @pdn: PCI device node
- *
- * This routine must be used to perform EEH initialization for the
- * indicated PCI device that was added after system boot (e.g.
- * hotplug, dlpar).
- */
-void eeh_add_device_tree_early(struct pci_dn *pdn)
-{
-	struct pci_dn *n;
-
-	if (!pdn)
-		return;
-
-	list_for_each_entry(n, &pdn->child_list, list)
-		eeh_add_device_tree_early(n);
-	eeh_add_device_early(pdn);
-}
-EXPORT_SYMBOL_GPL(eeh_add_device_tree_early);
-
-/**
- * eeh_add_device_late - Perform EEH initialization for the indicated pci device
+ * eeh_probe_device() - Perform EEH initialization for the indicated pci device
  * @dev: pci device for which to set up EEH
  *
  * This routine must be used to complete EEH initialization for PCI
  * devices that were added after system boot (e.g. hotplug, dlpar).
  */
-void eeh_add_device_late(struct pci_dev *dev)
+void eeh_probe_device(struct pci_dev *dev)
 {
-	struct pci_dn *pdn;
 	struct eeh_dev *edev;
 
-	if (!dev)
-		return;
+	pr_debug("EEH: Adding device %s\n", pci_name(dev));
 
-	pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn);
-	edev = pdn_to_eeh_dev(pdn);
-	eeh_edev_dbg(edev, "Adding device\n");
-	if (edev->pdev == dev) {
-		eeh_edev_dbg(edev, "Device already referenced!\n");
+	/*
+	 * pci_dev_to_eeh_dev() can only work if eeh_probe_dev() was
+	 * already called for this device.
+	 */
+	if (WARN_ON_ONCE(pci_dev_to_eeh_dev(dev))) {
+		pci_dbg(dev, "Already bound to an eeh_dev!\n");
+		return;
+	}
+
+	edev = eeh_ops->probe(dev);
+	if (!edev) {
+		pr_debug("EEH: Adding device failed\n");
 		return;
 	}
 
 	/*
-	 * The EEH cache might not be removed correctly because of
-	 * unbalanced kref to the device during unplug time, which
-	 * relies on pcibios_release_device(). So we have to remove
-	 * that here explicitly.
+	 * FIXME: We rely on pcibios_release_device() to remove the
+	 * existing EEH state. The release function is only called if
+	 * the pci_dev's refcount drops to zero so if something is
+	 * keeping a ref to a device (e.g. a filesystem) we need to
+	 * remove the old EEH state.
+	 *
+	 * FIXME: HEY MA, LOOK AT ME, NO LOCKING!
 	 */
-	if (edev->pdev) {
+	if (edev->pdev && edev->pdev != dev) {
 		eeh_rmv_from_parent_pe(edev);
 		eeh_addr_cache_rmv_dev(edev->pdev);
 		eeh_sysfs_remove_device(edev->pdev);
···
 		 * into error handler afterwards.
 		 */
 		edev->mode |= EEH_DEV_NO_HANDLER;
-
-		edev->pdev = NULL;
-		dev->dev.archdata.edev = NULL;
 	}
 
-	if (eeh_has_flag(EEH_PROBE_MODE_DEV))
-		eeh_ops->probe(pdn, NULL);
-
+	/* bind the pdev and the edev together */
 	edev->pdev = dev;
 	dev->dev.archdata.edev = edev;
-
 	eeh_addr_cache_insert_dev(dev);
+	eeh_sysfs_add_device(dev);
 }
-
-/**
- * eeh_add_device_tree_late - Perform EEH initialization for the indicated PCI bus
- * @bus: PCI bus
- *
- * This routine must be used to perform EEH initialization for PCI
- * devices which are attached to the indicated PCI bus. The PCI bus
- * is added after system boot through hotplug or dlpar.
- */
-void eeh_add_device_tree_late(struct pci_bus *bus)
-{
-	struct pci_dev *dev;
-
-	if (eeh_has_flag(EEH_FORCE_DISABLED))
-		return;
-	list_for_each_entry(dev, &bus->devices, bus_list) {
-		eeh_add_device_late(dev);
-		if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
-			struct pci_bus *subbus = dev->subordinate;
-			if (subbus)
-				eeh_add_device_tree_late(subbus);
-		}
-	}
-}
-EXPORT_SYMBOL_GPL(eeh_add_device_tree_late);
-
-/**
- * eeh_add_sysfs_files - Add EEH sysfs files for the indicated PCI bus
- * @bus: PCI bus
- *
- * This routine must be used to add EEH sysfs files for PCI
- * devices which are attached to the indicated PCI bus. The PCI bus
- * is added after system boot through hotplug or dlpar.
- */
-void eeh_add_sysfs_files(struct pci_bus *bus)
-{
-	struct pci_dev *dev;
-
-	list_for_each_entry(dev, &bus->devices, bus_list) {
-		eeh_sysfs_add_device(dev);
-		if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
-			struct pci_bus *subbus = dev->subordinate;
-			if (subbus)
-				eeh_add_sysfs_files(subbus);
-		}
-	}
-}
-EXPORT_SYMBOL_GPL(eeh_add_sysfs_files);
 
 /**
  * eeh_remove_device - Undo EEH setup for the indicated pci device

arch/powerpc/kernel/entry_32.S

···
 	 * r3 can be different from GPR3(r1) at this point, r9 and r11
 	 * contains the old MSR and handler address respectively,
 	 * r4 & r5 can contain page fault arguments that need to be passed
-	 * along as well. r12, CCR, CTR, XER etc... are left clobbered as
-	 * they aren't useful past this point (aren't syscall arguments),
-	 * the rest is restored from the exception frame.
+	 * along as well. r0, r6-r8, r12, CCR, CTR, XER etc... are left
+	 * clobbered as they aren't useful past this point.
 	 */
 
 	stwu	r1,-32(r1)
···
 	 * lockdep
 	 */
 1:	bl	trace_hardirqs_off
-2:	lwz	r5,24(r1)
+	lwz	r5,24(r1)
 	lwz	r4,20(r1)
 	lwz	r3,16(r1)
 	lwz	r11,12(r1)
 	lwz	r9,8(r1)
 	addi	r1,r1,32
-	lwz	r0,GPR0(r1)
-	lwz	r6,GPR6(r1)
-	lwz	r7,GPR7(r1)
-	lwz	r8,GPR8(r1)
 	mtctr	r11
 	mtlr	r9
 	bctr				/* jump to handler */
···
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_syscall_trace_leave
 	b	ret_from_except_full
+
+	/*
+	 * System call was called from kernel. We get here with SRR1 in r9.
+	 * Mark the exception as recoverable once we have retrieved SRR0,
+	 * trap a warning and return ENOSYS with CR[SO] set.
+	 */
+	.globl	ret_from_kernel_syscall
+ret_from_kernel_syscall:
+	mfspr	r9, SPRN_SRR0
+	mfspr	r10, SPRN_SRR1
+#if !defined(CONFIG_4xx) && !defined(CONFIG_BOOKE)
+	LOAD_REG_IMMEDIATE(r11, MSR_KERNEL & ~(MSR_IR|MSR_DR))
+	mtmsr	r11
+#endif
+
+0:	trap
+	EMIT_BUG_ENTRY 0b,__FILE__,__LINE__, BUGFLAG_WARNING
+
+	li	r3, ENOSYS
+	crset	so
+#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
+	mtspr	SPRN_NRI, r0
+#endif
+	mtspr	SPRN_SRR0, r9
+	mtspr	SPRN_SRR1, r10
+	SYNC
+	RFI
 
 /*
  * The fork/clone functions need to copy the full register set into

arch/powerpc/kernel/entry_64.S

···
 
 #include <linux/errno.h>
 #include <linux/err.h>
+#include <asm/cache.h>
 #include <asm/unistd.h>
 #include <asm/processor.h>
 #include <asm/page.h>
···
 	bne	.Ltabort_syscall
 END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
+_ASM_NOKPROBE_SYMBOL(system_call_common)
 	mr	r10,r1
 	ld	r1,PACAKSAVE(r13)
 	std	r10,0(r1)
···
 	std	r12,_MSR(r1)
 	std	r0,GPR0(r1)
 	std	r10,GPR1(r1)
+	std	r2,GPR2(r1)
 #ifdef CONFIG_PPC_FSL_BOOK3E
 START_BTB_FLUSH_SECTION
 	BTB_FLUSH(r10)
 END_BTB_FLUSH_SECTION
 #endif
-	ACCOUNT_CPU_USER_ENTRY(r13, r10, r11)
-	std	r2,GPR2(r1)
+	ld	r2,PACATOC(r13)
+	mfcr	r12
+	li	r11,0
+	/* Can we avoid saving r3-r8 in common case? */
 	std	r3,GPR3(r1)
-	mfcr	r2
 	std	r4,GPR4(r1)
 	std	r5,GPR5(r1)
 	std	r6,GPR6(r1)
 	std	r7,GPR7(r1)
 	std	r8,GPR8(r1)
-	li	r11,0
+	/* Zero r9-r12, this should only be required when restoring all GPRs */
 	std	r11,GPR9(r1)
 	std	r11,GPR10(r1)
 	std	r11,GPR11(r1)
 	std	r11,GPR12(r1)
+	std	r9,GPR13(r1)
+	SAVE_NVGPRS(r1)
 	std	r11,_XER(r1)
 	std	r11,_CTR(r1)
-	std	r9,GPR13(r1)
 	mflr	r10
+
 	/*
 	 * This clears CR0.SO (bit 28), which is the error indication on
 	 * return from this system call.
 	 */
-	rldimi	r2,r11,28,(63-28)
-	li	r11,0xc01
+	rldimi	r12,r11,28,(63-28)
+	li	r11,0xc00
 	std	r10,_LINK(r1)
 	std	r11,_TRAP(r1)
+	std	r12,_CCR(r1)
 	std	r3,ORIG_GPR3(r1)
-	std	r2,_CCR(r1)
-	ld	r2,PACATOC(r13)
-	addi	r9,r1,STACK_FRAME_OVERHEAD
+	addi	r10,r1,STACK_FRAME_OVERHEAD
 	ld	r11,exception_marker@toc(r2)
-	std	r11,-16(r9)		/* "regshere" marker */
-
-	kuap_check_amr r10, r11
-
-#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(CONFIG_PPC_SPLPAR)
-BEGIN_FW_FTR_SECTION
-	/* see if there are any DTL entries to process */
-	ld	r10,PACALPPACAPTR(r13)	/* get ptr to VPA */
-	ld	r11,PACA_DTL_RIDX(r13)	/* get log read index */
-	addi	r10,r10,LPPACA_DTLIDX
-	LDX_BE	r10,0,r10		/* get log write index */
-	cmpd	r11,r10
-	beq+	33f
-	bl	accumulate_stolen_time
-	REST_GPR(0,r1)
-	REST_4GPRS(3,r1)
-	REST_2GPRS(7,r1)
-	addi	r9,r1,STACK_FRAME_OVERHEAD
-33:
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
-#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE && CONFIG_PPC_SPLPAR */
+	std	r11,-16(r10)		/* "regshere" marker */
 
 	/*
-	 * A syscall should always be called with interrupts enabled
-	 * so we just unconditionally hard-enable here. When some kind
-	 * of irq tracing is used, we additionally check that condition
-	 * is correct
+	 * RECONCILE_IRQ_STATE without calling trace_hardirqs_off(), which
+	 * would clobber syscall parameters. Also we always enter with IRQs
+	 * enabled and nothing pending. system_call_exception() will call
+	 * trace_hardirqs_off().
 	 */
-#if defined(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && defined(CONFIG_BUG)
-	lbz	r10,PACAIRQSOFTMASK(r13)
-1:	tdnei	r10,IRQS_ENABLED
-	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
-#endif
+	li	r11,IRQS_ALL_DISABLED
+	li	r12,PACA_IRQ_HARD_DIS
+	stb	r11,PACAIRQSOFTMASK(r13)
+	stb	r12,PACAIRQHAPPENED(r13)
 
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	1
-#else
-	li	r11,MSR_RI
-	ori	r11,r11,MSR_EE
-	mtmsrd	r11,1
-#endif /* CONFIG_PPC_BOOK3E */
+	/* Calling convention has r9 = orig r0, r10 = regs */
+	mr	r9,r0
+	bl	system_call_exception
 
-system_call:			/* label this so stack traces look sane */
-	/* We do need to set SOFTE in the stack frame or the return
-	 * from interrupt will be painful
-	 */
-	li	r10,IRQS_ENABLED
-	std	r10,SOFTE(r1)
-
-	ld	r11, PACA_THREAD_INFO(r13)
-	ld	r10,TI_FLAGS(r11)
-	andi.	r11,r10,_TIF_SYSCALL_DOTRACE
-	bne	.Lsyscall_dotrace		/* does not return */
-	cmpldi	0,r0,NR_syscalls
-	bge-	.Lsyscall_enosys
-
-.Lsyscall:
-/*
- * Need to vector to 32 Bit or default sys_call_table here,
- * based on caller's run-mode / personality.
- */
-	ld	r11,SYS_CALL_TABLE@toc(2)
-	andis.	r10,r10,_TIF_32BIT@h
-	beq	15f
-	ld	r11,COMPAT_SYS_CALL_TABLE@toc(2)
-	clrldi	r3,r3,32
-	clrldi	r4,r4,32
-	clrldi	r5,r5,32
-	clrldi	r6,r6,32
-	clrldi	r7,r7,32
-	clrldi	r8,r8,32
-15:
-	slwi	r0,r0,3
-
-	barrier_nospec_asm
-	/*
-	 * Prevent the load of the handler below (based on the user-passed
-	 * system call number) being speculatively executed until the test
-	 * against NR_syscalls and branch to .Lsyscall_enosys above has
-	 * committed.
-	 */
-
-	ldx	r12,r11,r0	/* Fetch system call handler [ptr] */
-	mtctr   r12
-	bctrl			/* Call handler */
-
-	/* syscall_exit can exit to kernel mode, via ret_from_kernel_thread */
 .Lsyscall_exit:
-	std	r3,RESULT(r1)
+	addi    r4,r1,STACK_FRAME_OVERHEAD
+	bl	syscall_exit_prepare
 
-#ifdef CONFIG_DEBUG_RSEQ
-	/* Check whether the syscall is issued inside a restartable sequence */
-	addi    r3,r1,STACK_FRAME_OVERHEAD
-	bl      rseq_syscall
-	ld	r3,RESULT(r1)
-#endif
+	ld	r2,_CCR(r1)
+	ld	r4,_NIP(r1)
+	ld	r5,_MSR(r1)
+	ld	r6,_LINK(r1)
 
-	ld	r12, PACA_THREAD_INFO(r13)
-
-	ld	r8,_MSR(r1)
-
-/*
- * This is a few instructions into the actual syscall exit path (which actually
- * starts at .Lsyscall_exit) to cater to kprobe blacklisting and to reduce the
- * number of visible symbols for profiling purposes.
- *
- * We can probe from system_call until this point as MSR_RI is set. But once it
- * is cleared below, we won't be able to take a trap.
- *
- * This is blacklisted from kprobes further below with _ASM_NOKPROBE_SYMBOL().
- */
-system_call_exit:
-	/*
-	 * Disable interrupts so current_thread_info()->flags can't change,
-	 * and so that we don't get interrupted after loading SRR0/1.
-	 *
-	 * Leave MSR_RI enabled for now, because with THREAD_INFO_IN_TASK we
-	 * could fault on the load of the TI_FLAGS below.
-	 */
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	0
-#else
-	li	r11,MSR_RI
-	mtmsrd	r11,1
-#endif /* CONFIG_PPC_BOOK3E */
-
-	ld	r9,TI_FLAGS(r12)
-	li	r11,-MAX_ERRNO
-	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
-	bne-	.Lsyscall_exit_work
-
-	andi.	r0,r8,MSR_FP
-	beq 2f
-#ifdef CONFIG_ALTIVEC
-	andis.	r0,r8,MSR_VEC@h
-	bne	3f
-#endif
-2:	addi    r3,r1,STACK_FRAME_OVERHEAD
-	bl	restore_math
-	ld	r8,_MSR(r1)
-	ld	r3,RESULT(r1)
-	li	r11,-MAX_ERRNO
-
-3:	cmpld	r3,r11
-	ld	r5,_CCR(r1)
-	bge-	.Lsyscall_error
-.Lsyscall_error_cont:
-	ld	r7,_NIP(r1)
 BEGIN_FTR_SECTION
 	stdcx.	r0,0,r1			/* to clear the reservation */
 END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
-	andi.	r6,r8,MSR_PR
-	ld	r4,_LINK(r1)
 
-	kuap_check_amr r10, r11
+	mtspr	SPRN_SRR0,r4
+	mtspr	SPRN_SRR1,r5
+	mtlr	r6
 
-#ifdef CONFIG_PPC_BOOK3S
-	/*
-	 * Clear MSR_RI, MSR_EE is already and remains disabled. We could do
-	 * this later, but testing shows that doing it here causes less slow
-	 * down than doing it closer to the rfid.
-	 */
+	cmpdi	r3,0
+	bne	.Lsyscall_restore_regs
+	/* Zero volatile regs that may contain sensitive kernel data */
+	li	r0,0
+	li	r4,0
+	li	r5,0
+	li	r6,0
+	li	r7,0
+	li	r8,0
+	li	r9,0
+	li	r10,0
 	li	r11,0
-	mtmsrd	r11,1
-#endif
-
-	beq-	1f
-	ACCOUNT_CPU_USER_EXIT(r13, r11, r12)
+	li	r12,0
+	mtctr	r0
+	mtspr	SPRN_XER,r0
+.Lsyscall_restore_regs_cont:
 
 BEGIN_FTR_SECTION
 	HMT_MEDIUM_LOW
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	std	r8, PACATMSCRATCH(r13)
-#endif
-
 	/*
 	 * We don't need to restore AMR on the way back to userspace for KUAP.
 	 * The value of AMR only matters while we're in the kernel.
 	 */
-	ld	r13,GPR13(r1)	/* only restore r13 if returning to usermode */
+	mtcr	r2
 	ld	r2,GPR2(r1)
+	ld	r3,GPR3(r1)
+	ld	r13,GPR13(r1)
 	ld	r1,GPR1(r1)
-	mtlr	r4
-	mtcr	r5
-	mtspr	SPRN_SRR0,r7
-	mtspr	SPRN_SRR1,r8
 	RFI_TO_USER
 	b	.	/* prevent speculative execution */
 
-1:	/* exit to kernel */
-	kuap_restore_amr r2
-
-	ld	r2,GPR2(r1)
-	ld	r1,GPR1(r1)
-	mtlr	r4
-	mtcr	r5
-	mtspr	SPRN_SRR0,r7
-	mtspr	SPRN_SRR1,r8
-	RFI_TO_KERNEL
-	b	.	/* prevent speculative execution */
-
-.Lsyscall_error:
-	oris	r5,r5,0x1000	/* Set SO bit in CR */
-	neg	r3,r3
-	std	r5,_CCR(r1)
-	b	.Lsyscall_error_cont
-
-/* Traced system call support */
-.Lsyscall_dotrace:
-	bl	save_nvgprs
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	do_syscall_trace_enter
-
-	/*
-	 * We use the return value of do_syscall_trace_enter() as the syscall
-	 * number. If the syscall was rejected for any reason do_syscall_trace_enter()
-	 * returns an invalid syscall number and the test below against
-	 * NR_syscalls will fail.
-	 */
-	mr	r0,r3
-
-	/* Restore argument registers just clobbered and/or possibly changed. */
-	ld	r3,GPR3(r1)
-	ld	r4,GPR4(r1)
-	ld	r5,GPR5(r1)
-	ld	r6,GPR6(r1)
-	ld	r7,GPR7(r1)
-	ld	r8,GPR8(r1)
-
-	/* Repopulate r9 and r10 for the syscall path */
-	addi	r9,r1,STACK_FRAME_OVERHEAD
-	ld	r10, PACA_THREAD_INFO(r13)
-	ld	r10,TI_FLAGS(r10)
-
-	cmpldi	r0,NR_syscalls
-	blt+	.Lsyscall
-
-	/* Return code is already in r3 thanks to do_syscall_trace_enter() */
-	b	.Lsyscall_exit
-
-
-.Lsyscall_enosys:
-	li	r3,-ENOSYS
-	b	.Lsyscall_exit
-	
-.Lsyscall_exit_work:
-	/* If TIF_RESTOREALL is set, don't scribble on either r3 or ccr.
-	 If TIF_NOERROR is set, just save r3 as it is. */
-
-	andi.	r0,r9,_TIF_RESTOREALL
-	beq+	0f
+.Lsyscall_restore_regs:
+	ld	r3,_CTR(r1)
+	ld	r4,_XER(r1)
 	REST_NVGPRS(r1)
-	b	2f
-0:	cmpld	r3,r11		/* r11 is -MAX_ERRNO */
-	blt+	1f
-	andi.	r0,r9,_TIF_NOERROR
-	bne-	1f
-	ld	r5,_CCR(r1)
-	neg	r3,r3
-	oris	r5,r5,0x1000	/* Set SO bit in CR */
-	std	r5,_CCR(r1)
-1:	std	r3,GPR3(r1)
-2:	andi.	r0,r9,(_TIF_PERSYSCALL_MASK)
-	beq	4f
-
-	/* Clear per-syscall TIF flags if any are set.  */
-
-	li	r11,_TIF_PERSYSCALL_MASK
-	addi	r12,r12,TI_FLAGS
-3:	ldarx	r10,0,r12
-	andc	r10,r10,r11
-	stdcx.	r10,0,r12
-	bne-	3b
-	subi	r12,r12,TI_FLAGS
-
-4:	/* Anything else left to do? */
-BEGIN_FTR_SECTION
-	lis	r3,DEFAULT_PPR@highest	/* Set default PPR */
-	sldi	r3,r3,32	/* bits 11-13 are used for ppr */
-	std	r3,_PPR(r1)
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
-
-	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP)
-	beq	ret_from_except_lite
-
-	/* Re-enable interrupts */
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	1
-#else
-	li	r10,MSR_RI
-	ori	r10,r10,MSR_EE
-	mtmsrd	r10,1
-#endif /* CONFIG_PPC_BOOK3E */
-
-	bl	save_nvgprs
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	do_syscall_trace_leave
-	b	ret_from_except
+	mtctr	r3
+	mtspr	SPRN_XER,r4
+	ld	r0,GPR0(r1)
+	REST_8GPRS(4, r1)
+	ld	r12,GPR12(r1)
+	b	.Lsyscall_restore_regs_cont
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 .Ltabort_syscall:
···
 	RFI_TO_USER
 	b	.	/* prevent speculative execution */
 #endif
-_ASM_NOKPROBE_SYMBOL(system_call_common);
-_ASM_NOKPROBE_SYMBOL(system_call_exit);
-
-/* Save non-volatile GPRs, if not already saved. */
-_GLOBAL(save_nvgprs)
-	ld	r11,_TRAP(r1)
-	andi.	r0,r11,1
-	beqlr-
-	SAVE_NVGPRS(r1)
-	clrrdi	r0,r11,1
-	std	r0,_TRAP(r1)
-	blr
-_ASM_NOKPROBE_SYMBOL(save_nvgprs);
-
-	
-/*
- * The sigsuspend and rt_sigsuspend system calls can call do_signal
- * and thus put the process into the stopped state where we might
- * want to examine its user state with ptrace.  Therefore we need
- * to save all the nonvolatile registers (r14 - r31) before calling
- * the C code.  Similarly, fork, vfork and clone need the full
- * register state on the stack so that it can be copied to the child.
- */
-
-_GLOBAL(ppc_fork)
-	bl	save_nvgprs
-	bl	sys_fork
-	b	.Lsyscall_exit
-
-_GLOBAL(ppc_vfork)
-	bl	save_nvgprs
-	bl	sys_vfork
-	b	.Lsyscall_exit
-
-_GLOBAL(ppc_clone)
-	bl	save_nvgprs
-	bl	sys_clone
-	b	.Lsyscall_exit
-
-_GLOBAL(ppc_clone3)
-       bl      save_nvgprs
-       bl      sys_clone3
-       b       .Lsyscall_exit
-
-_GLOBAL(ppc32_swapcontext)
-	bl	save_nvgprs
-	bl	compat_sys_swapcontext
-	b	.Lsyscall_exit
-
-_GLOBAL(ppc64_swapcontext)
-	bl	save_nvgprs
-	bl	sys_swapcontext
-	b	.Lsyscall_exit
-
-_GLOBAL(ppc_switch_endian)
-	bl	save_nvgprs
-	bl	sys_switch_endian
-	b	.Lsyscall_exit
 
 _GLOBAL(ret_from_fork)
 	bl	schedule_tail
···
 	blrl
 	li	r3,0
 	b	.Lsyscall_exit
+
+#ifdef CONFIG_PPC_BOOK3E
+/* Save non-volatile GPRs, if not already saved. */
+_GLOBAL(save_nvgprs)
+	ld	r11,_TRAP(r1)
+	andi.	r0,r11,1
+	beqlr-
+	SAVE_NVGPRS(r1)
+	clrrdi	r0,r11,1
+	std	r0,_TRAP(r1)
+	blr
+_ASM_NOKPROBE_SYMBOL(save_nvgprs);
+#endif
 
 #ifdef CONFIG_PPC_BOOK3S_64
 
···
  * state of one is saved on its kernel stack.  Then the state
  * of the other is restored from its kernel stack.  The memory
  * management hardware is updated to the second process's state.
- * Finally, we can return to the second process, via ret_from_except.
+ * Finally, we can return to the second process, via interrupt_return.
  * On entry, r3 points to the THREAD for the current task, r4
  * points to the THREAD for the new task.
  *
···
 	addi	r1,r1,SWITCH_FRAME_SIZE
 	blr
 
-	.align	7
-_GLOBAL(ret_from_except)
-	ld	r11,_TRAP(r1)
-	andi.	r0,r11,1
-	bne	ret_from_except_lite
-	REST_NVGPRS(r1)
-
-_GLOBAL(ret_from_except_lite)
+#ifdef CONFIG_PPC_BOOK3S
 	/*
-	 * Disable interrupts so that current_thread_info()->flags
-	 * can't change between when we test it and when we return
-	 * from the interrupt.
+	 * If MSR EE/RI was never enabled, IRQs not reconciled, NVGPRs not
+	 * touched, AMR not set, no exit work created, then this can be used.
 	 */
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	0
-#else
-	li	r10,MSR_RI
-	mtmsrd	r10,1		  /* Update machine state */
-#endif /* CONFIG_PPC_BOOK3E */
-
-	ld	r9, PACA_THREAD_INFO(r13)
-	ld	r3,_MSR(r1)
-#ifdef CONFIG_PPC_BOOK3E
-	ld	r10,PACACURRENT(r13)
-#endif /* CONFIG_PPC_BOOK3E */
-	ld	r4,TI_FLAGS(r9)
-	andi.	r3,r3,MSR_PR
-	beq	resume_kernel
-#ifdef CONFIG_PPC_BOOK3E
-	lwz	r3,(THREAD+THREAD_DBCR0)(r10)
-#endif /* CONFIG_PPC_BOOK3E */
-
-	/* Check current_thread_info()->flags */
-	andi.	r0,r4,_TIF_USER_WORK_MASK
-	bne	1f
-#ifdef CONFIG_PPC_BOOK3E
-	/*
-	 * Check to see if the dbcr0 register is set up to debug.
-	 * Use the internal debug mode bit to do this.
-	 */
-	andis.	r0,r3,DBCR0_IDM@h
-	beq	restore
-	mfmsr	r0
-	rlwinm	r0,r0,0,~MSR_DE	/* Clear MSR.DE */
-	mtmsr	r0
-	mtspr	SPRN_DBCR0,r3
-	li	r10, -1
-	mtspr	SPRN_DBSR,r10
-	b	restore
-#else
+	.balign IFETCH_ALIGN_BYTES
+	.globl fast_interrupt_return
+fast_interrupt_return:
+_ASM_NOKPROBE_SYMBOL(fast_interrupt_return)
+	ld	r4,_MSR(r1)
+	andi.	r0,r4,MSR_PR
+	bne	.Lfast_user_interrupt_return
+	andi.	r0,r4,MSR_RI
+	li	r3,0 /* 0 return value, no EMULATE_STACK_STORE */
+	bne+	.Lfast_kernel_interrupt_return
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	restore_math
-	b	restore
-#endif
-1:	andi.	r0,r4,_TIF_NEED_RESCHED
-	beq	2f
-	bl	restore_interrupts
-	SCHEDULE_USER
-	b	ret_from_except_lite
-2:
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	andi.	r0,r4,_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM
-	bne	3f		/* only restore TM if nothing else to do */
+	bl	unrecoverable_exception
+	b	. /* should not get here */
+
+	.balign IFETCH_ALIGN_BYTES
+	.globl interrupt_return
+interrupt_return:
+_ASM_NOKPROBE_SYMBOL(interrupt_return)
+	ld	r4,_MSR(r1)
+	andi.	r0,r4,MSR_PR
+	beq	.Lkernel_interrupt_return
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	restore_tm_state
-	b	restore
-3:
-#endif
-	bl	save_nvgprs
-	/*
-	 * Use a non volatile GPR to save and restore our thread_info flags
-	 * across the call to restore_interrupts.
-	 */
-	mr	r30,r4
-	bl	restore_interrupts
-	mr	r4,r30
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	do_notify_resume
-	b	ret_from_except
+	bl	interrupt_exit_user_prepare
+	cmpdi	r3,0
+	bne-	.Lrestore_nvgprs
 
-resume_kernel:
-	/* check current_thread_info, _TIF_EMULATE_STACK_STORE */
-	andis.	r8,r4,_TIF_EMULATE_STACK_STORE@h
-	beq+	1f
+.Lfast_user_interrupt_return:
+	ld	r11,_NIP(r1)
+	ld	r12,_MSR(r1)
+BEGIN_FTR_SECTION
+	ld	r10,_PPR(r1)
+	mtspr	SPRN_PPR,r10
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+	mtspr	SPRN_SRR0,r11
+	mtspr	SPRN_SRR1,r12
 
-	addi	r8,r1,INT_FRAME_SIZE	/* Get the kprobed function entry */
-
-	ld	r3,GPR1(r1)
-	subi	r3,r3,INT_FRAME_SIZE	/* dst: Allocate a trampoline exception frame */
-	mr	r4,r1			/* src:  current exception frame */
-	mr	r1,r3			/* Reroute the trampoline frame to r1 */
-
-	/* Copy from the original to the trampoline. */
-	li	r5,INT_FRAME_SIZE/8	/* size: INT_FRAME_SIZE */
-	li	r6,0			/* start offset: 0 */
-	mtctr	r5
-2:	ldx	r0,r6,r4
-	stdx	r0,r6,r3
-	addi	r6,r6,8
-	bdnz	2b
-
-	/* Do real store operation to complete stdu */
-	ld	r5,GPR1(r1)
-	std	r8,0(r5)
-
-	/* Clear _TIF_EMULATE_STACK_STORE flag */
-	lis	r11,_TIF_EMULATE_STACK_STORE@h
-	addi	r5,r9,TI_FLAGS
-0:	ldarx	r4,0,r5
-	andc	r4,r4,r11
-	stdcx.	r4,0,r5
-	bne-	0b
-1:
-
-#ifdef CONFIG_PREEMPTION
-	/* Check if we need to preempt */
-	andi.	r0,r4,_TIF_NEED_RESCHED
-	beq+	restore
-	/* Check that preempt_count() == 0 and interrupts are enabled */
-	lwz	r8,TI_PREEMPT(r9)
-	cmpwi	cr0,r8,0
-	bne	restore
-	ld	r0,SOFTE(r1)
-	andi.	r0,r0,IRQS_DISABLED
-	bne	restore
-
-	/*
-	 * Here we are preempting the current task. We want to make
-	 * sure we are soft-disabled first and reconcile irq state.
-	 */
-	RECONCILE_IRQ_STATE(r3,r4)
-	bl	preempt_schedule_irq
-
-	/*
-	 * arch_local_irq_restore() from preempt_schedule_irq above may
-	 * enable hard interrupt but we really should disable interrupts
-	 * when we return from the interrupt, and so that we don't get
-	 * interrupted after loading SRR0/1.
-	 */
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	0
-#else
-	li	r10,MSR_RI
-	mtmsrd	r10,1		  /* Update machine state */
-#endif /* CONFIG_PPC_BOOK3E */
-#endif /* CONFIG_PREEMPTION */
-
-	.globl	fast_exc_return_irq
-fast_exc_return_irq:
-restore:
-	/*
-	 * This is the main kernel exit path. First we check if we
-	 * are about to re-enable interrupts
-	 */
-	ld	r5,SOFTE(r1)
-	lbz	r6,PACAIRQSOFTMASK(r13)
-	andi.	r5,r5,IRQS_DISABLED
-	bne	.Lrestore_irq_off
-
-	/* We are enabling, were we already enabled ? Yes, just return */
-	andi.	r6,r6,IRQS_DISABLED
-	beq	cr0,.Ldo_restore
-
-	/*
-	 * We are about to soft-enable interrupts (we are hard disabled
-	 * at this point). We check if there's anything that needs to
-	 * be replayed first.
-	 */
-	lbz	r0,PACAIRQHAPPENED(r13)
-	cmpwi	cr0,r0,0
-	bne-	.Lrestore_check_irq_replay
-
-	/*
-	 * Get here when nothing happened while soft-disabled, just
-	 * soft-enable and move-on. We will hard-enable as a side
-	 * effect of rfi
-	 */
-.Lrestore_no_replay:
-	TRACE_ENABLE_INTS
-	li	r0,IRQS_ENABLED
-	stb	r0,PACAIRQSOFTMASK(r13);
-
-	/*
-	 * Final return path. BookE is handled in a different file
-	 */
-.Ldo_restore:
-#ifdef CONFIG_PPC_BOOK3E
-	b	exception_return_book3e
-#else
-	/*
-	 * Clear the reservation. If we know the CPU tracks the address of
-	 * the reservation then we can potentially save some cycles and use
-	 * a larx. On POWER6 and POWER7 this is significantly faster.
-	 */
 BEGIN_FTR_SECTION
 	stdcx.	r0,0,r1		/* to clear the reservation */
 FTR_SECTION_ELSE
-	ldarx	r4,0,r1
+	ldarx	r0,0,r1
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 
-	/*
-	 * Some code path such as load_up_fpu or altivec return directly
-	 * here. They run entirely hard disabled and do not alter the
-	 * interrupt state. They also don't use lwarx/stwcx. and thus
-	 * are known not to leave dangling reservations.
-	 */
-	.globl	fast_exception_return
-fast_exception_return:
-	ld	r3,_MSR(r1)
-	ld	r4,_CTR(r1)
-	ld	r0,_LINK(r1)
-	mtctr	r4
-	mtlr	r0
-	ld	r4,_XER(r1)
-	mtspr	SPRN_XER,r4
+	ld	r3,_CCR(r1)
+	ld	r4,_LINK(r1)
+	ld	r5,_CTR(r1)
+	ld	r6,_XER(r1)
+	li	r0,0
 
-	kuap_check_amr r5, r6
-
-	REST_8GPRS(5, r1)
-
-	andi.	r0,r3,MSR_RI
-	beq-	.Lunrecov_restore
-
-	/*
-	 * Clear RI before restoring r13.  If we are returning to
-	 * userspace and we take an exception after restoring r13,
-	 * we end up corrupting the userspace r13 value.
-	 */
-	li	r4,0
-	mtmsrd	r4,1
-
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	/* TM debug */
-	std	r3, PACATMSCRATCH(r13) /* Stash returned-to MSR */
-#endif
-	/*
-	 * r13 is our per cpu area, only restore it if we are returning to
-	 * userspace the value stored in the stack frame may belong to
-	 * another CPU.
-	 */
-	andi.	r0,r3,MSR_PR
-	beq	1f
-BEGIN_FTR_SECTION
-	/* Restore PPR */
-	ld	r2,_PPR(r1)
-	mtspr	SPRN_PPR,r2
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
-	ACCOUNT_CPU_USER_EXIT(r13, r2, r4)
+	REST_4GPRS(7, r1)
+	REST_2GPRS(11, r1)
 	REST_GPR(13, r1)
 
-	/*
-	 * We don't need to restore AMR on the way back to userspace for KUAP.
-	 * The value of AMR only matters while we're in the kernel.
-	 */
-	mtspr	SPRN_SRR1,r3
+	mtcr	r3
+	mtlr	r4
+	mtctr	r5
+	mtspr	SPRN_XER,r6
 
-	ld	r2,_CCR(r1)
-	mtcrf	0xFF,r2
-	ld	r2,_NIP(r1)
-	mtspr	SPRN_SRR0,r2
-
-	ld	r0,GPR0(r1)
-	ld	r2,GPR2(r1)
-	ld	r3,GPR3(r1)
-	ld	r4,GPR4(r1)
-	ld	r1,GPR1(r1)
+	REST_4GPRS(2, r1)
+	REST_GPR(6, r1)
+	REST_GPR(0, r1)
+	REST_GPR(1, r1)
 	RFI_TO_USER
 	b	.	/* prevent speculative execution */
 
-1:	mtspr	SPRN_SRR1,r3
+.Lrestore_nvgprs:
+	REST_NVGPRS(r1)
+	b	.Lfast_user_interrupt_return
 
-	ld	r2,_CCR(r1)
-	mtcrf	0xFF,r2
-	ld	r2,_NIP(r1)
-	mtspr	SPRN_SRR0,r2
+	.balign IFETCH_ALIGN_BYTES
+.Lkernel_interrupt_return:
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	interrupt_exit_kernel_prepare
+
+.Lfast_kernel_interrupt_return:
+	cmpdi	cr1,r3,0
+	ld	r11,_NIP(r1)
+	ld	r12,_MSR(r1)
+	mtspr	SPRN_SRR0,r11
+	mtspr	SPRN_SRR1,r12
+
+BEGIN_FTR_SECTION
+	stdcx.	r0,0,r1		/* to clear the reservation */
+FTR_SECTION_ELSE
+	ldarx	r0,0,r1
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
+
+	ld	r3,_LINK(r1)
+	ld	r4,_CTR(r1)
+	ld	r5,_XER(r1)
+	ld	r6,_CCR(r1)
+	li	r0,0
+
+	REST_4GPRS(7, r1)
+	REST_2GPRS(11, r1)
+
+	mtlr	r3
+	mtctr	r4
+	mtspr	SPRN_XER,r5
 
 	/*
 	 * Leaving a stale exception_marker on the stack can confuse
 	 * the reliable stack unwinder later on. Clear it.
 	 */
-	li	r2,0
-	std	r2,STACK_FRAME_OVERHEAD-16(r1)
+	std	r0,STACK_FRAME_OVERHEAD-16(r1)
 
-	ld	r0,GPR0(r1)
-	ld	r2,GPR2(r1)
-	ld	r3,GPR3(r1)
+	REST_4GPRS(2, r1)
 
-	kuap_restore_amr r4
-
-	ld	r4,GPR4(r1)
-	ld	r1,GPR1(r1)
+	bne-	cr1,1f /* emulate stack store */
+	mtcr	r6
+	REST_GPR(6, r1)
+	REST_GPR(0, r1)
+	REST_GPR(1, r1)
 	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 
-#endif /* CONFIG_PPC_BOOK3E */
-
-	/*
-	 * We are returning to a context with interrupts soft disabled.
-	 *
-	 * However, we may also about to hard enable, so we need to
-	 * make sure that in this case, we also clear PACA_IRQ_HARD_DIS
-	 * or that bit can get out of sync and bad things will happen
+1:	/*
+	 * Emulate stack store with update. New r1 value was already calculated
+	 * and updated in our interrupt regs by emulate_loadstore, but we can't
+	 * store the previous value of r1 to the stack before re-loading our
+	 * registers from it, otherwise they could be clobbered.  Use
+	 * PACA_EXGEN as temporary storage to hold the store data, as
+	 * interrupts are disabled here so it won't be clobbered.
 	 */
-.Lrestore_irq_off:
-	ld	r3,_MSR(r1)
-	lbz	r7,PACAIRQHAPPENED(r13)
-	andi.	r0,r3,MSR_EE
-	beq	1f
-	rlwinm	r7,r7,0,~PACA_IRQ_HARD_DIS
-	stb	r7,PACAIRQHAPPENED(r13)
-1:
-#if defined(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && defined(CONFIG_BUG)
-	/* The interrupt should not have soft enabled. */
-	lbz	r7,PACAIRQSOFTMASK(r13)
-1:	tdeqi	r7,IRQS_ENABLED
-	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
-#endif
-	b	.Ldo_restore
+	mtcr	r6
+	std	r9,PACA_EXGEN+0(r13)
+	addi	r9,r1,INT_FRAME_SIZE /* get original r1 */
+	REST_GPR(6, r1)
+	REST_GPR(0, r1)
+	REST_GPR(1, r1)
+	std	r9,0(r1) /* perform store component of stdu */
+	ld	r9,PACA_EXGEN+0(r13)
 
-	/*
-	 * Something did happen, check if a re-emit is needed
-	 * (this also clears paca->irq_happened)
-	 */
-.Lrestore_check_irq_replay:
-	/* XXX: We could implement a fast path here where we check
-	 * for irq_happened being just 0x01, in which case we can
-	 * clear it and return. That means that we would potentially
-	 * miss a decrementer having wrapped all the way around.
-	 *
-	 * Still, this might be useful for things like hash_page
-	 */
-	bl	__check_irq_replay
-	cmpwi	cr0,r3,0
-	beq	.Lrestore_no_replay
- 
-	/*
-	 * We need to re-emit an interrupt. We do so by re-using our
-	 * existing exception frame. We first change the trap value,
-	 * but we need to ensure we preserve the low nibble of it
-	 */
-	ld	r4,_TRAP(r1)
-	clrldi	r4,r4,60
-	or	r4,r4,r3
-	std	r4,_TRAP(r1)
-
-	/*
-	 * PACA_IRQ_HARD_DIS won't always be set here, so set it now
-	 * to reconcile the IRQ state. Tracing is already accounted for.
-	 */
-	lbz	r4,PACAIRQHAPPENED(r13)
-	ori	r4,r4,PACA_IRQ_HARD_DIS
-	stb	r4,PACAIRQHAPPENED(r13)
-
-	/*
-	 * Then find the right handler and call it. Interrupts are
-	 * still soft-disabled and we keep them that way.
-	*/
-	cmpwi	cr0,r3,0x500
-	bne	1f
-	addi	r3,r1,STACK_FRAME_OVERHEAD;
- 	bl	do_IRQ
-	b	ret_from_except
-1:	cmpwi	cr0,r3,0xf00
-	bne	1f
-	addi	r3,r1,STACK_FRAME_OVERHEAD;
-	bl	performance_monitor_exception
-	b	ret_from_except
-1:	cmpwi	cr0,r3,0xe60
-	bne	1f
-	addi	r3,r1,STACK_FRAME_OVERHEAD;
-	bl	handle_hmi_exception
-	b	ret_from_except
-1:	cmpwi	cr0,r3,0x900
-	bne	1f
-	addi	r3,r1,STACK_FRAME_OVERHEAD;
-	bl	timer_interrupt
-	b	ret_from_except
-#ifdef CONFIG_PPC_DOORBELL
-1:
-#ifdef CONFIG_PPC_BOOK3E
-	cmpwi	cr0,r3,0x280
-#else
-	cmpwi	cr0,r3,0xa00
-#endif /* CONFIG_PPC_BOOK3E */
-	bne	1f
-	addi	r3,r1,STACK_FRAME_OVERHEAD;
-	bl	doorbell_exception
-#endif /* CONFIG_PPC_DOORBELL */
-1:	b	ret_from_except /* What else to do here ? */
- 
-.Lunrecov_restore:
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	unrecoverable_exception
-	b	.Lunrecov_restore
-
-_ASM_NOKPROBE_SYMBOL(ret_from_except);
-_ASM_NOKPROBE_SYMBOL(ret_from_except_lite);
-_ASM_NOKPROBE_SYMBOL(resume_kernel);
-_ASM_NOKPROBE_SYMBOL(fast_exc_return_irq);
-_ASM_NOKPROBE_SYMBOL(restore);
-_ASM_NOKPROBE_SYMBOL(fast_exception_return);
-
+	RFI_TO_KERNEL
+	b	.	/* prevent speculative execution */
+#endif /* CONFIG_PPC_BOOK3S */
 
 #ifdef CONFIG_PPC_RTAS
 /*

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

···
 #include <asm/kvm_asm.h>
 #include <asm/kvm_booke_hv_asm.h>
 #include <asm/feature-fixups.h>
+#include <asm/context_tracking.h>
 
 /* XXX This will ultimately add space for a special exception save
  *     structure used to save things like SRR0/SRR1, SPRGs, MAS, etc...
···
 	masked_interrupt_book3e PACA_IRQ_DBELL 0
 
 /*
- * Called from arch_local_irq_enable when an interrupt needs
- * to be resent. r3 contains either 0x500,0x900,0x260 or 0x280
- * to indicate the kind of interrupt. MSR:EE is already off.
- * We generate a stackframe like if a real interrupt had happened.
- *
- * Note: While MSR:EE is off, we need to make sure that _MSR
- * in the generated frame has EE set to 1 or the exception
- * handler will not properly re-enable them.
- */
-_GLOBAL(__replay_interrupt)
-	/* We are going to jump to the exception common code which
-	 * will retrieve various register values from the PACA which
-	 * we don't give a damn about.
-	 */
-	mflr	r10
-	mfmsr	r11
-	mfcr	r4
-	mtspr	SPRN_SPRG_GEN_SCRATCH,r13;
-	std	r1,PACA_EXGEN+EX_R1(r13);
-	stw	r4,PACA_EXGEN+EX_CR(r13);
-	ori	r11,r11,MSR_EE
-	subi	r1,r1,INT_FRAME_SIZE;
-	cmpwi	cr0,r3,0x500
-	beq	exc_0x500_common
-	cmpwi	cr0,r3,0x900
-	beq	exc_0x900_common
-	cmpwi	cr0,r3,0x280
-	beq	exc_0x280_common
-	blr
-
-
-/*
  * This is called from 0x300 and 0x400 handlers after the prologs with
  * r14 and r15 containing the fault address and error code, with the
  * original values stashed away in the PACA
···
 	bl	alignment_exception
 	b	ret_from_except
 
-/*
- * We branch here from entry_64.S for the last stage of the exception
- * return code path. MSR:EE is expected to be off at that point
- */
-_GLOBAL(exception_return_book3e)
-	b	1f
+	.align	7
+_GLOBAL(ret_from_except)
+	ld	r11,_TRAP(r1)
+	andi.	r0,r11,1
+	bne	ret_from_except_lite
+	REST_NVGPRS(r1)
+
+_GLOBAL(ret_from_except_lite)
+	/*
+	 * Disable interrupts so that current_thread_info()->flags
+	 * can't change between when we test it and when we return
+	 * from the interrupt.
+	 */
+	wrteei	0
+
+	ld	r9, PACA_THREAD_INFO(r13)
+	ld	r3,_MSR(r1)
+	ld	r10,PACACURRENT(r13)
+	ld	r4,TI_FLAGS(r9)
+	andi.	r3,r3,MSR_PR
+	beq	resume_kernel
+	lwz	r3,(THREAD+THREAD_DBCR0)(r10)
+
+	/* Check current_thread_info()->flags */
+	andi.	r0,r4,_TIF_USER_WORK_MASK
+	bne	1f
+	/*
+	 * Check to see if the dbcr0 register is set up to debug.
+	 * Use the internal debug mode bit to do this.
+	 */
+	andis.	r0,r3,DBCR0_IDM@h
+	beq	restore
+	mfmsr	r0
+	rlwinm	r0,r0,0,~MSR_DE	/* Clear MSR.DE */
+	mtmsr	r0
+	mtspr	SPRN_DBCR0,r3
+	li	r10, -1
+	mtspr	SPRN_DBSR,r10
+	b	restore
+1:	andi.	r0,r4,_TIF_NEED_RESCHED
+	beq	2f
+	bl	restore_interrupts
+	SCHEDULE_USER
+	b	ret_from_except_lite
+2:
+	bl	save_nvgprs
+	/*
+	 * Use a non volatile GPR to save and restore our thread_info flags
+	 * across the call to restore_interrupts.
+	 */
+	mr	r30,r4
+	bl	restore_interrupts
+	mr	r4,r30
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	do_notify_resume
+	b	ret_from_except
+
+resume_kernel:
+	/* check current_thread_info, _TIF_EMULATE_STACK_STORE */
+	andis.	r8,r4,_TIF_EMULATE_STACK_STORE@h
+	beq+	1f
+
+	addi	r8,r1,INT_FRAME_SIZE	/* Get the kprobed function entry */
+
+	ld	r3,GPR1(r1)
+	subi	r3,r3,INT_FRAME_SIZE	/* dst: Allocate a trampoline exception frame */
+	mr	r4,r1			/* src:  current exception frame */
+	mr	r1,r3			/* Reroute the trampoline frame to r1 */
+
+	/* Copy from the original to the trampoline. */
+	li	r5,INT_FRAME_SIZE/8	/* size: INT_FRAME_SIZE */
+	li	r6,0			/* start offset: 0 */
+	mtctr	r5
+2:	ldx	r0,r6,r4
+	stdx	r0,r6,r3
+	addi	r6,r6,8
+	bdnz	2b
+
+	/* Do real store operation to complete stdu */
+	ld	r5,GPR1(r1)
+	std	r8,0(r5)
+
+	/* Clear _TIF_EMULATE_STACK_STORE flag */
+	lis	r11,_TIF_EMULATE_STACK_STORE@h
+	addi	r5,r9,TI_FLAGS
+0:	ldarx	r4,0,r5
+	andc	r4,r4,r11
+	stdcx.	r4,0,r5
+	bne-	0b
+1:
+
+#ifdef CONFIG_PREEMPT
+	/* Check if we need to preempt */
+	andi.	r0,r4,_TIF_NEED_RESCHED
+	beq+	restore
+	/* Check that preempt_count() == 0 and interrupts are enabled */
+	lwz	r8,TI_PREEMPT(r9)
+	cmpwi	cr0,r8,0
+	bne	restore
+	ld	r0,SOFTE(r1)
+	andi.	r0,r0,IRQS_DISABLED
+	bne	restore
+
+	/*
+	 * Here we are preempting the current task. We want to make
+	 * sure we are soft-disabled first and reconcile irq state.
+	 */
+	RECONCILE_IRQ_STATE(r3,r4)
+	bl	preempt_schedule_irq
+
+	/*
+	 * arch_local_irq_restore() from preempt_schedule_irq above may
+	 * enable hard interrupt but we really should disable interrupts
+	 * when we return from the interrupt, and so that we don't get
+	 * interrupted after loading SRR0/1.
+	 */
+	wrteei	0
+#endif /* CONFIG_PREEMPT */
+
+restore:
+	/*
+	 * This is the main kernel exit path. First we check if we
+	 * are about to re-enable interrupts
+	 */
+	ld	r5,SOFTE(r1)
+	lbz	r6,PACAIRQSOFTMASK(r13)
+	andi.	r5,r5,IRQS_DISABLED
+	bne	.Lrestore_irq_off
+
+	/* We are enabling, were we already enabled ? Yes, just return */
+	andi.	r6,r6,IRQS_DISABLED
+	beq	cr0,fast_exception_return
+
+	/*
+	 * We are about to soft-enable interrupts (we are hard disabled
+	 * at this point). We check if there's anything that needs to
+	 * be replayed first.
+	 */
+	lbz	r0,PACAIRQHAPPENED(r13)
+	cmpwi	cr0,r0,0
+	bne-	.Lrestore_check_irq_replay
+
+	/*
+	 * Get here when nothing happened while soft-disabled, just
+	 * soft-enable and move-on. We will hard-enable as a side
+	 * effect of rfi
+	 */
+.Lrestore_no_replay:
+	TRACE_ENABLE_INTS
+	li	r0,IRQS_ENABLED
+	stb	r0,PACAIRQSOFTMASK(r13);
 
 /* This is the return from load_up_fpu fast path which could do with
  * less GPR restores in fact, but for now we have a single return path
  */
-	.globl fast_exception_return
 fast_exception_return:
 	wrteei	0
 1:	mr	r0,r13
···
 	ld	r11,PACA_EXGEN+EX_R11(r13)
 	mfspr	r13,SPRN_SPRG_GEN_SCRATCH
 	rfi
+
+	/*
+	 * We are returning to a context with interrupts soft disabled.
+	 *
+	 * However, we may also about to hard enable, so we need to
+	 * make sure that in this case, we also clear PACA_IRQ_HARD_DIS
+	 * or that bit can get out of sync and bad things will happen
+	 */
+.Lrestore_irq_off:
+	ld	r3,_MSR(r1)
+	lbz	r7,PACAIRQHAPPENED(r13)
+	andi.	r0,r3,MSR_EE
+	beq	1f
+	rlwinm	r7,r7,0,~PACA_IRQ_HARD_DIS
+	stb	r7,PACAIRQHAPPENED(r13)
+1:
+#if defined(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && defined(CONFIG_BUG)
+	/* The interrupt should not have soft enabled. */
+	lbz	r7,PACAIRQSOFTMASK(r13)
+1:	tdeqi	r7,IRQS_ENABLED
+	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
+#endif
+	b	fast_exception_return
+
+	/*
+	 * Something did happen, check if a re-emit is needed
+	 * (this also clears paca->irq_happened)
+	 */
+.Lrestore_check_irq_replay:
+	/* XXX: We could implement a fast path here where we check
+	 * for irq_happened being just 0x01, in which case we can
+	 * clear it and return. That means that we would potentially
+	 * miss a decrementer having wrapped all the way around.
+	 *
+	 * Still, this might be useful for things like hash_page
+	 */
+	bl	__check_irq_replay
+	cmpwi	cr0,r3,0
+	beq	.Lrestore_no_replay
+
+	/*
+	 * We need to re-emit an interrupt. We do so by re-using our
+	 * existing exception frame. We first change the trap value,
+	 * but we need to ensure we preserve the low nibble of it
+	 */
+	ld	r4,_TRAP(r1)
+	clrldi	r4,r4,60
+	or	r4,r4,r3
+	std	r4,_TRAP(r1)
+
+	/*
+	 * PACA_IRQ_HARD_DIS won't always be set here, so set it now
+	 * to reconcile the IRQ state. Tracing is already accounted for.
+	 */
+	lbz	r4,PACAIRQHAPPENED(r13)
+	ori	r4,r4,PACA_IRQ_HARD_DIS
+	stb	r4,PACAIRQHAPPENED(r13)
+
+	/*
+	 * Then find the right handler and call it. Interrupts are
+	 * still soft-disabled and we keep them that way.
+	*/
+	cmpwi	cr0,r3,0x500
+	bne	1f
+	addi	r3,r1,STACK_FRAME_OVERHEAD;
+	bl	do_IRQ
+	b	ret_from_except
+1:	cmpwi	cr0,r3,0xf00
+	bne	1f
+	addi	r3,r1,STACK_FRAME_OVERHEAD;
+	bl	performance_monitor_exception
+	b	ret_from_except
+1:	cmpwi	cr0,r3,0xe60
+	bne	1f
+	addi	r3,r1,STACK_FRAME_OVERHEAD;
+	bl	handle_hmi_exception
+	b	ret_from_except
+1:	cmpwi	cr0,r3,0x900
+	bne	1f
+	addi	r3,r1,STACK_FRAME_OVERHEAD;
+	bl	timer_interrupt
+	b	ret_from_except
+#ifdef CONFIG_PPC_DOORBELL
+1:
+	cmpwi	cr0,r3,0x280
+	bne	1f
+	addi	r3,r1,STACK_FRAME_OVERHEAD;
+	bl	doorbell_exception
+#endif /* CONFIG_PPC_DOORBELL */
+1:	b	ret_from_except /* What else to do here ? */
+
+_ASM_NOKPROBE_SYMBOL(ret_from_except);
+_ASM_NOKPROBE_SYMBOL(ret_from_except_lite);
+_ASM_NOKPROBE_SYMBOL(resume_kernel);
+_ASM_NOKPROBE_SYMBOL(restore);
+_ASM_NOKPROBE_SYMBOL(fast_exception_return);
 
 /*
  * Trampolines used when spotting a bad kernel stack pointer in

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

···
 #define EX_CCR		52
 #define EX_CFAR		56
 #define EX_PPR		64
-#if defined(CONFIG_RELOCATABLE)
 #define EX_CTR		72
 .if EX_SIZE != 10
 	.error "EX_SIZE is wrong"
 .endif
-#else
-.if EX_SIZE != 9
-	.error "EX_SIZE is wrong"
-.endif
-#endif
 
 /*
  * Following are fixed section helper macros.
···
  * EXC_VIRT_BEGIN/END  - virt (AIL), unrelocated exception vectors
  * TRAMP_REAL_BEGIN    - real, unrelocated helpers (virt may call these)
  * TRAMP_VIRT_BEGIN    - virt, unreloc helpers (in practice, real can use)
- * TRAMP_KVM_BEGIN     - KVM handlers, these are put into real, unrelocated
  * EXC_COMMON          - After switching to virtual, relocated mode.
  */
 
···
 
 #define TRAMP_VIRT_BEGIN(name)					\
 	FIXED_SECTION_ENTRY_BEGIN(virt_trampolines, name)
-
-#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-#define TRAMP_KVM_BEGIN(name)					\
-	TRAMP_VIRT_BEGIN(name)
-#else
-#define TRAMP_KVM_BEGIN(name)
-#endif
 
 #define EXC_REAL_NONE(start, size)				\
 	FIXED_SECTION_ENTRY_BEGIN_LOCATION(real_vectors, exc_real_##start##_##unused, start, size); \
···
 	ori	reg,reg,(ABS_ADDR(label))@l;				\
 	addis	reg,reg,(ABS_ADDR(label))@h
 
-/* Exception register prefixes */
-#define EXC_HV_OR_STD	2 /* depends on HVMODE */
-#define EXC_HV		1
-#define EXC_STD		0
-
-#if defined(CONFIG_RELOCATABLE)
-/*
- * If we support interrupts with relocation on AND we're a relocatable kernel,
- * we need to use CTR to get to the 2nd level handler.  So, save/restore it
- * when required.
- */
-#define SAVE_CTR(reg, area)	mfctr	reg ; 	std	reg,area+EX_CTR(r13)
-#define GET_CTR(reg, area) 			ld	reg,area+EX_CTR(r13)
-#define RESTORE_CTR(reg, area)	ld	reg,area+EX_CTR(r13) ; mtctr reg
-#else
-/* ...else CTR is unused and in register. */
-#define SAVE_CTR(reg, area)
-#define GET_CTR(reg, area) 	mfctr	reg
-#define RESTORE_CTR(reg, area)
-#endif
-
-/*
- * PPR save/restore macros used in exceptions-64s.S
- * Used for P7 or later processors
- */
-#define SAVE_PPR(area, ra)						\
-BEGIN_FTR_SECTION_NESTED(940)						\
-	ld	ra,area+EX_PPR(r13);	/* Read PPR from paca */	\
-	std	ra,_PPR(r1);						\
-END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,940)
-
-#define RESTORE_PPR_PACA(area, ra)					\
-BEGIN_FTR_SECTION_NESTED(941)						\
-	ld	ra,area+EX_PPR(r13);					\
-	mtspr	SPRN_PPR,ra;						\
-END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,941)
-
-/*
- * Get an SPR into a register if the CPU has the given feature
- */
-#define OPT_GET_SPR(ra, spr, ftr)					\
-BEGIN_FTR_SECTION_NESTED(943)						\
-	mfspr	ra,spr;							\
-END_FTR_SECTION_NESTED(ftr,ftr,943)
-
-/*
- * Set an SPR from a register if the CPU has the given feature
- */
-#define OPT_SET_SPR(ra, spr, ftr)					\
-BEGIN_FTR_SECTION_NESTED(943)						\
-	mtspr	spr,ra;							\
-END_FTR_SECTION_NESTED(ftr,ftr,943)
-
-/*
- * Save a register to the PACA if the CPU has the given feature
- */
-#define OPT_SAVE_REG_TO_PACA(offset, ra, ftr)				\
-BEGIN_FTR_SECTION_NESTED(943)						\
-	std	ra,offset(r13);						\
-END_FTR_SECTION_NESTED(ftr,ftr,943)
-
 /*
  * Branch to label using its 0xC000 address. This results in instruction
  * address suitable for MSR[IR]=0 or 1, which allows relocation to be turned
···
 	mtctr	reg;							\
 	bctr
 
-.macro INT_KVM_HANDLER name, vec, hsrr, area, skip
-	TRAMP_KVM_BEGIN(\name\()_kvm)
-	KVM_HANDLER \vec, \hsrr, \area, \skip
+/*
+ * Interrupt code generation macros
+ */
+#define IVEC		.L_IVEC_\name\()	/* Interrupt vector address */
+#define IHSRR		.L_IHSRR_\name\()	/* Sets SRR or HSRR registers */
+#define IHSRR_IF_HVMODE	.L_IHSRR_IF_HVMODE_\name\() /* HSRR if HV else SRR */
+#define IAREA		.L_IAREA_\name\()	/* PACA save area */
+#define IVIRT		.L_IVIRT_\name\()	/* Has virt mode entry point */
+#define IISIDE		.L_IISIDE_\name\()	/* Uses SRR0/1 not DAR/DSISR */
+#define IDAR		.L_IDAR_\name\()	/* Uses DAR (or SRR0) */
+#define IDSISR		.L_IDSISR_\name\()	/* Uses DSISR (or SRR1) */
+#define ISET_RI		.L_ISET_RI_\name\()	/* Run common code w/ MSR[RI]=1 */
+#define IBRANCH_TO_COMMON	.L_IBRANCH_TO_COMMON_\name\() /* ENTRY branch to common */
+#define IREALMODE_COMMON	.L_IREALMODE_COMMON_\name\() /* Common runs in realmode */
+#define IMASK		.L_IMASK_\name\()	/* IRQ soft-mask bit */
+#define IKVM_SKIP	.L_IKVM_SKIP_\name\()	/* Generate KVM skip handler */
+#define IKVM_REAL	.L_IKVM_REAL_\name\()	/* Real entry tests KVM */
+#define __IKVM_REAL(name)	.L_IKVM_REAL_ ## name
+#define IKVM_VIRT	.L_IKVM_VIRT_\name\()	/* Virt entry tests KVM */
+#define ISTACK		.L_ISTACK_\name\()	/* Set regular kernel stack */
+#define __ISTACK(name)	.L_ISTACK_ ## name
+#define IRECONCILE	.L_IRECONCILE_\name\()	/* Do RECONCILE_IRQ_STATE */
+#define IKUAP		.L_IKUAP_\name\()	/* Do KUAP lock */
+
+#define INT_DEFINE_BEGIN(n)						\
+.macro int_define_ ## n name
+
+#define INT_DEFINE_END(n)						\
+.endm ;									\
+int_define_ ## n n ;							\
+do_define_int n
+
+.macro do_define_int name
+	.ifndef IVEC
+		.error "IVEC not defined"
+	.endif
+	.ifndef IHSRR
+		IHSRR=0
+	.endif
+	.ifndef IHSRR_IF_HVMODE
+		IHSRR_IF_HVMODE=0
+	.endif
+	.ifndef IAREA
+		IAREA=PACA_EXGEN
+	.endif
+	.ifndef IVIRT
+		IVIRT=1
+	.endif
+	.ifndef IISIDE
+		IISIDE=0
+	.endif
+	.ifndef IDAR
+		IDAR=0
+	.endif
+	.ifndef IDSISR
+		IDSISR=0
+	.endif
+	.ifndef ISET_RI
+		ISET_RI=1
+	.endif
+	.ifndef IBRANCH_TO_COMMON
+		IBRANCH_TO_COMMON=1
+	.endif
+	.ifndef IREALMODE_COMMON
+		IREALMODE_COMMON=0
+	.else
+		.if ! IBRANCH_TO_COMMON
+			.error "IREALMODE_COMMON=1 but IBRANCH_TO_COMMON=0"
+		.endif
+	.endif
+	.ifndef IMASK
+		IMASK=0
+	.endif
+	.ifndef IKVM_SKIP
+		IKVM_SKIP=0
+	.endif
+	.ifndef IKVM_REAL
+		IKVM_REAL=0
+	.endif
+	.ifndef IKVM_VIRT
+		IKVM_VIRT=0
+	.endif
+	.ifndef ISTACK
+		ISTACK=1
+	.endif
+	.ifndef IRECONCILE
+		IRECONCILE=1
+	.endif
+	.ifndef IKUAP
+		IKUAP=1
+	.endif
 .endm
 
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 /*
- * If hv is possible, interrupts come into to the hv version
- * of the kvmppc_interrupt code, which then jumps to the PR handler,
- * kvmppc_interrupt_pr, if the guest is a PR guest.
+ * All interrupts which set HSRR registers, as well as SRESET and MCE and
+ * syscall when invoked with "sc 1" switch to MSR[HV]=1 (HVMODE) to be taken,
+ * so they all generally need to test whether they were taken in guest context.
+ *
+ * Note: SRESET and MCE may also be sent to the guest by the hypervisor, and be
+ * taken with MSR[HV]=0.
+ *
+ * Interrupts which set SRR registers (with the above exceptions) do not
+ * elevate to MSR[HV]=1 mode, though most can be taken when running with
+ * MSR[HV]=1  (e.g., bare metal kernel and userspace). So these interrupts do
+ * not need to test whether a guest is running because they get delivered to
+ * the guest directly, including nested HV KVM guests.
+ *
+ * The exception is PR KVM, where the guest runs with MSR[PR]=1 and the host
+ * runs with MSR[HV]=0, so the host takes all interrupts on behalf of the
+ * guest. PR KVM runs with LPCR[AIL]=0 which causes interrupts to always be
+ * delivered to the real-mode entry point, therefore such interrupts only test
+ * KVM in their real mode handlers, and only when PR KVM is possible.
+ *
+ * Interrupts that are taken in MSR[HV]=0 and escalate to MSR[HV]=1 are always
+ * delivered in real-mode when the MMU is in hash mode because the MMU
+ * registers are not set appropriately to translate host addresses. In nested
+ * radix mode these can be delivered in virt-mode as the host translations are
+ * used implicitly (see: effective LPID, effective PID).
+ */
+
+/*
+ * If an interrupt is taken while a guest is running, it is immediately routed
+ * to KVM to handle. If both HV and PR KVM arepossible, KVM interrupts go first
+ * to kvmppc_interrupt_hv, which handles the PR guest case.
  */
 #define kvmppc_interrupt kvmppc_interrupt_hv
 #else
 #define kvmppc_interrupt kvmppc_interrupt_pr
 #endif
 
-.macro KVMTEST name, hsrr, n
+.macro KVMTEST name
 	lbz	r10,HSTATE_IN_GUEST(r13)
 	cmpwi	r10,0
 	bne	\name\()_kvm
 .endm
 
-.macro KVM_HANDLER vec, hsrr, area, skip
-	.if \skip
+.macro GEN_KVM name
+	.balign IFETCH_ALIGN_BYTES
+\name\()_kvm:
+
+	.if IKVM_SKIP
 	cmpwi	r10,KVM_GUEST_MODE_SKIP
 	beq	89f
 	.else
-BEGIN_FTR_SECTION_NESTED(947)
-	ld	r10,\area+EX_CFAR(r13)
+BEGIN_FTR_SECTION
+	ld	r10,IAREA+EX_CFAR(r13)
 	std	r10,HSTATE_CFAR(r13)
-END_FTR_SECTION_NESTED(CPU_FTR_CFAR,CPU_FTR_CFAR,947)
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	.endif
 
-BEGIN_FTR_SECTION_NESTED(948)
-	ld	r10,\area+EX_PPR(r13)
+	ld	r10,PACA_EXGEN+EX_CTR(r13)
+	mtctr	r10
+BEGIN_FTR_SECTION
+	ld	r10,IAREA+EX_PPR(r13)
 	std	r10,HSTATE_PPR(r13)
-END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948)
-	ld	r10,\area+EX_R10(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+	ld	r11,IAREA+EX_R11(r13)
+	ld	r12,IAREA+EX_R12(r13)
 	std	r12,HSTATE_SCRATCH0(r13)
 	sldi	r12,r9,32
+	ld	r9,IAREA+EX_R9(r13)
+	ld	r10,IAREA+EX_R10(r13)
 	/* HSRR variants have the 0x2 bit added to their trap number */
-	.if \hsrr == EXC_HV_OR_STD
+	.if IHSRR_IF_HVMODE
 	BEGIN_FTR_SECTION
-	ori	r12,r12,(\vec + 0x2)
+	ori	r12,r12,(IVEC + 0x2)
 	FTR_SECTION_ELSE
-	ori	r12,r12,(\vec)
+	ori	r12,r12,(IVEC)
 	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-	.elseif \hsrr
-	ori	r12,r12,(\vec + 0x2)
+	.elseif IHSRR
+	ori	r12,r12,(IVEC+ 0x2)
 	.else
-	ori	r12,r12,(\vec)
+	ori	r12,r12,(IVEC)
 	.endif
-
-#ifdef CONFIG_RELOCATABLE
-	/*
-	 * KVM requires __LOAD_FAR_HANDLER beause kvmppc_interrupt lives
-	 * outside the head section. CONFIG_RELOCATABLE KVM expects CTR
-	 * to be saved in HSTATE_SCRATCH1.
-	 */
-	mfctr	r9
-	std	r9,HSTATE_SCRATCH1(r13)
-	__LOAD_FAR_HANDLER(r9, kvmppc_interrupt)
-	mtctr	r9
-	ld	r9,\area+EX_R9(r13)
-	bctr
-#else
-	ld	r9,\area+EX_R9(r13)
 	b	kvmppc_interrupt
-#endif
 
-
-	.if \skip
+	.if IKVM_SKIP
 89:	mtocrf	0x80,r9
-	ld	r9,\area+EX_R9(r13)
-	ld	r10,\area+EX_R10(r13)
-	.if \hsrr == EXC_HV_OR_STD
+	ld	r10,PACA_EXGEN+EX_CTR(r13)
+	mtctr	r10
+	ld	r9,IAREA+EX_R9(r13)
+	ld	r10,IAREA+EX_R10(r13)
+	ld	r11,IAREA+EX_R11(r13)
+	ld	r12,IAREA+EX_R12(r13)
+	.if IHSRR_IF_HVMODE
 	BEGIN_FTR_SECTION
 	b	kvmppc_skip_Hinterrupt
 	FTR_SECTION_ELSE
 	b	kvmppc_skip_interrupt
 	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-	.elseif \hsrr
+	.elseif IHSRR
 	b	kvmppc_skip_Hinterrupt
 	.else
 	b	kvmppc_skip_interrupt
···
 .endm
 
 #else
-.macro KVMTEST name, hsrr, n
+.macro KVMTEST name
 .endm
-.macro KVM_HANDLER name, vec, hsrr, area, skip
+.macro GEN_KVM name
 .endm
 #endif
-
-.macro INT_SAVE_SRR_AND_JUMP label, hsrr, set_ri
-	ld	r10,PACAKMSR(r13)	/* get MSR value for kernel */
-	.if ! \set_ri
-	xori	r10,r10,MSR_RI		/* Clear MSR_RI */
-	.endif
-	.if \hsrr == EXC_HV_OR_STD
-	BEGIN_FTR_SECTION
-	mfspr	r11,SPRN_HSRR0		/* save HSRR0 */
-	mfspr	r12,SPRN_HSRR1		/* and HSRR1 */
-	mtspr	SPRN_HSRR1,r10
-	FTR_SECTION_ELSE
-	mfspr	r11,SPRN_SRR0		/* save SRR0 */
-	mfspr	r12,SPRN_SRR1		/* and SRR1 */
-	mtspr	SPRN_SRR1,r10
-	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-	.elseif \hsrr
-	mfspr	r11,SPRN_HSRR0		/* save HSRR0 */
-	mfspr	r12,SPRN_HSRR1		/* and HSRR1 */
-	mtspr	SPRN_HSRR1,r10
-	.else
-	mfspr	r11,SPRN_SRR0		/* save SRR0 */
-	mfspr	r12,SPRN_SRR1		/* and SRR1 */
-	mtspr	SPRN_SRR1,r10
-	.endif
-	LOAD_HANDLER(r10, \label\())
-	.if \hsrr == EXC_HV_OR_STD
-	BEGIN_FTR_SECTION
-	mtspr	SPRN_HSRR0,r10
-	HRFI_TO_KERNEL
-	FTR_SECTION_ELSE
-	mtspr	SPRN_SRR0,r10
-	RFI_TO_KERNEL
-	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-	.elseif \hsrr
-	mtspr	SPRN_HSRR0,r10
-	HRFI_TO_KERNEL
-	.else
-	mtspr	SPRN_SRR0,r10
-	RFI_TO_KERNEL
-	.endif
-	b	.	/* prevent speculative execution */
-.endm
-
-/* INT_SAVE_SRR_AND_JUMP works for real or virt, this is faster but virt only */
-.macro INT_VIRT_SAVE_SRR_AND_JUMP label, hsrr
-#ifdef CONFIG_RELOCATABLE
-	.if \hsrr == EXC_HV_OR_STD
-	BEGIN_FTR_SECTION
-	mfspr	r11,SPRN_HSRR0	/* save HSRR0 */
-	FTR_SECTION_ELSE
-	mfspr	r11,SPRN_SRR0	/* save SRR0 */
-	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-	.elseif \hsrr
-	mfspr	r11,SPRN_HSRR0	/* save HSRR0 */
-	.else
-	mfspr	r11,SPRN_SRR0	/* save SRR0 */
-	.endif
-	LOAD_HANDLER(r12, \label\())
-	mtctr	r12
-	.if \hsrr == EXC_HV_OR_STD
-	BEGIN_FTR_SECTION
-	mfspr	r12,SPRN_HSRR1	/* and HSRR1 */
-	FTR_SECTION_ELSE
-	mfspr	r12,SPRN_SRR1	/* and HSRR1 */
-	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-	.elseif \hsrr
-	mfspr	r12,SPRN_HSRR1	/* and HSRR1 */
-	.else
-	mfspr	r12,SPRN_SRR1	/* and HSRR1 */
-	.endif
-	li	r10,MSR_RI
-	mtmsrd 	r10,1		/* Set RI (EE=0) */
-	bctr
-#else
-	.if \hsrr == EXC_HV_OR_STD
-	BEGIN_FTR_SECTION
-	mfspr	r11,SPRN_HSRR0		/* save HSRR0 */
-	mfspr	r12,SPRN_HSRR1		/* and HSRR1 */
-	FTR_SECTION_ELSE
-	mfspr	r11,SPRN_SRR0		/* save SRR0 */
-	mfspr	r12,SPRN_SRR1		/* and SRR1 */
-	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-	.elseif \hsrr
-	mfspr	r11,SPRN_HSRR0		/* save HSRR0 */
-	mfspr	r12,SPRN_HSRR1		/* and HSRR1 */
-	.else
-	mfspr	r11,SPRN_SRR0		/* save SRR0 */
-	mfspr	r12,SPRN_SRR1		/* and SRR1 */
-	.endif
-	li	r10,MSR_RI
-	mtmsrd 	r10,1			/* Set RI (EE=0) */
-	b	\label
-#endif
-.endm
 
 /*
  * This is the BOOK3S interrupt entry code macro.
···
  * - Fall through and continue executing in real, unrelocated mode.
  *   This is done if early=2.
  */
-.macro INT_HANDLER name, vec, ool=0, early=0, virt=0, hsrr=0, area=PACA_EXGEN, ri=1, dar=0, dsisr=0, bitmask=0, kvm=0
+
+.macro GEN_BRANCH_TO_COMMON name, virt
+	.if IREALMODE_COMMON
+	LOAD_HANDLER(r10, \name\()_common)
+	mtctr	r10
+	bctr
+	.else
+	.if \virt
+#ifndef CONFIG_RELOCATABLE
+	b	\name\()_common_virt
+#else
+	LOAD_HANDLER(r10, \name\()_common_virt)
+	mtctr	r10
+	bctr
+#endif
+	.else
+	LOAD_HANDLER(r10, \name\()_common_real)
+	mtctr	r10
+	bctr
+	.endif
+	.endif
+.endm
+
+.macro GEN_INT_ENTRY name, virt, ool=0
 	SET_SCRATCH0(r13)			/* save r13 */
 	GET_PACA(r13)
-	std	r9,\area\()+EX_R9(r13)		/* save r9 */
-	OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR)
+	std	r9,IAREA+EX_R9(r13)		/* save r9 */
+BEGIN_FTR_SECTION
+	mfspr	r9,SPRN_PPR
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	HMT_MEDIUM
-	std	r10,\area\()+EX_R10(r13)	/* save r10 - r12 */
-	OPT_GET_SPR(r10, SPRN_CFAR, CPU_FTR_CFAR)
+	std	r10,IAREA+EX_R10(r13)		/* save r10 - r12 */
+BEGIN_FTR_SECTION
+	mfspr	r10,SPRN_CFAR
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	.if \ool
 	.if !\virt
 	b	tramp_real_\name
···
 	.endif
 	.endif
 
-	OPT_SAVE_REG_TO_PACA(\area\()+EX_PPR, r9, CPU_FTR_HAS_PPR)
-	OPT_SAVE_REG_TO_PACA(\area\()+EX_CFAR, r10, CPU_FTR_CFAR)
+BEGIN_FTR_SECTION
+	std	r9,IAREA+EX_PPR(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+BEGIN_FTR_SECTION
+	std	r10,IAREA+EX_CFAR(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	INTERRUPT_TO_KERNEL
-	SAVE_CTR(r10, \area\())
+	mfctr	r10
+	std	r10,IAREA+EX_CTR(r13)
 	mfcr	r9
-	.if \kvm
-		KVMTEST \name \hsrr \vec
-	.endif
-	.if \bitmask
-		lbz	r10,PACAIRQSOFTMASK(r13)
-		andi.	r10,r10,\bitmask
-		/* Associate vector numbers with bits in paca->irq_happened */
-		.if \vec == 0x500 || \vec == 0xea0
-		li	r10,PACA_IRQ_EE
-		.elseif \vec == 0x900
-		li	r10,PACA_IRQ_DEC
-		.elseif \vec == 0xa00 || \vec == 0xe80
-		li	r10,PACA_IRQ_DBELL
-		.elseif \vec == 0xe60
-		li	r10,PACA_IRQ_HMI
-		.elseif \vec == 0xf00
-		li	r10,PACA_IRQ_PMI
-		.else
-		.abort "Bad maskable vector"
-		.endif
-
-		.if \hsrr == EXC_HV_OR_STD
-		BEGIN_FTR_SECTION
-		bne	masked_Hinterrupt
-		FTR_SECTION_ELSE
-		bne	masked_interrupt
-		ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-		.elseif \hsrr
-		bne	masked_Hinterrupt
-		.else
-		bne	masked_interrupt
-		.endif
-	.endif
-
-	std	r11,\area\()+EX_R11(r13)
-	std	r12,\area\()+EX_R12(r13)
+	std	r11,IAREA+EX_R11(r13)
+	std	r12,IAREA+EX_R12(r13)
 
 	/*
 	 * DAR/DSISR, SCRATCH0 must be read before setting MSR[RI],
···
 	 * not recoverable if they are live.
 	 */
 	GET_SCRATCH0(r10)
-	std	r10,\area\()+EX_R13(r13)
-	.if \dar
-	.if \hsrr
+	std	r10,IAREA+EX_R13(r13)
+	.if IDAR && !IISIDE
+	.if IHSRR
 	mfspr	r10,SPRN_HDAR
 	.else
 	mfspr	r10,SPRN_DAR
 	.endif
-	std	r10,\area\()+EX_DAR(r13)
+	std	r10,IAREA+EX_DAR(r13)
 	.endif
-	.if \dsisr
-	.if \hsrr
+	.if IDSISR && !IISIDE
+	.if IHSRR
 	mfspr	r10,SPRN_HDSISR
 	.else
 	mfspr	r10,SPRN_DSISR
 	.endif
-	stw	r10,\area\()+EX_DSISR(r13)
+	stw	r10,IAREA+EX_DSISR(r13)
 	.endif
 
-	.if \early == 2
-	/* nothing more */
-	.elseif \early
-	mfctr	r10			/* save ctr, even for !RELOCATABLE */
-	BRANCH_TO_C000(r11, \name\()_early_common)
-	.elseif !\virt
-	INT_SAVE_SRR_AND_JUMP \name\()_common, \hsrr, \ri
+	.if IHSRR_IF_HVMODE
+	BEGIN_FTR_SECTION
+	mfspr	r11,SPRN_HSRR0		/* save HSRR0 */
+	mfspr	r12,SPRN_HSRR1		/* and HSRR1 */
+	FTR_SECTION_ELSE
+	mfspr	r11,SPRN_SRR0		/* save SRR0 */
+	mfspr	r12,SPRN_SRR1		/* and SRR1 */
+	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+	.elseif IHSRR
+	mfspr	r11,SPRN_HSRR0		/* save HSRR0 */
+	mfspr	r12,SPRN_HSRR1		/* and HSRR1 */
 	.else
-	INT_VIRT_SAVE_SRR_AND_JUMP \name\()_common, \hsrr
+	mfspr	r11,SPRN_SRR0		/* save SRR0 */
+	mfspr	r12,SPRN_SRR1		/* and SRR1 */
 	.endif
+
+	.if IBRANCH_TO_COMMON
+	GEN_BRANCH_TO_COMMON \name \virt
+	.endif
+
 	.if \ool
 	.popsection
 	.endif
 .endm
 
 /*
- * On entry r13 points to the paca, r9-r13 are saved in the paca,
- * r9 contains the saved CR, r11 and r12 contain the saved SRR0 and
- * SRR1, and relocation is on.
+ * __GEN_COMMON_ENTRY is required to receive the branch from interrupt
+ * entry, except in the case of the real-mode handlers which require
+ * __GEN_REALMODE_COMMON_ENTRY.
  *
- * If stack=0, then the stack is already set in r1, and r1 is saved in r10.
- * PPR save and CPU accounting is not done for the !stack case (XXX why not?)
+ * This switches to virtual mode and sets MSR[RI].
  */
-.macro INT_COMMON vec, area, stack, kuap, reconcile, dar, dsisr
-	.if \stack
+.macro __GEN_COMMON_ENTRY name
+DEFINE_FIXED_SYMBOL(\name\()_common_real)
+\name\()_common_real:
+	.if IKVM_REAL
+		KVMTEST \name
+	.endif
+
+	ld	r10,PACAKMSR(r13)	/* get MSR value for kernel */
+	/* MSR[RI] is clear iff using SRR regs */
+	.if IHSRR == EXC_HV_OR_STD
+	BEGIN_FTR_SECTION
+	xori	r10,r10,MSR_RI
+	END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)
+	.elseif ! IHSRR
+	xori	r10,r10,MSR_RI
+	.endif
+	mtmsrd	r10
+
+	.if IVIRT
+	.if IKVM_VIRT
+	b	1f /* skip the virt test coming from real */
+	.endif
+
+	.balign IFETCH_ALIGN_BYTES
+DEFINE_FIXED_SYMBOL(\name\()_common_virt)
+\name\()_common_virt:
+	.if IKVM_VIRT
+		KVMTEST \name
+1:
+	.endif
+	.endif /* IVIRT */
+.endm
+
+/*
+ * Don't switch to virt mode. Used for early MCE and HMI handlers that
+ * want to run in real mode.
+ */
+.macro __GEN_REALMODE_COMMON_ENTRY name
+DEFINE_FIXED_SYMBOL(\name\()_common_real)
+\name\()_common_real:
+	.if IKVM_REAL
+		KVMTEST \name
+	.endif
+.endm
+
+.macro __GEN_COMMON_BODY name
+	.if IMASK
+		lbz	r10,PACAIRQSOFTMASK(r13)
+		andi.	r10,r10,IMASK
+		/* Associate vector numbers with bits in paca->irq_happened */
+		.if IVEC == 0x500 || IVEC == 0xea0
+		li	r10,PACA_IRQ_EE
+		.elseif IVEC == 0x900
+		li	r10,PACA_IRQ_DEC
+		.elseif IVEC == 0xa00 || IVEC == 0xe80
+		li	r10,PACA_IRQ_DBELL
+		.elseif IVEC == 0xe60
+		li	r10,PACA_IRQ_HMI
+		.elseif IVEC == 0xf00
+		li	r10,PACA_IRQ_PMI
+		.else
+		.abort "Bad maskable vector"
+		.endif
+
+		.if IHSRR_IF_HVMODE
+		BEGIN_FTR_SECTION
+		bne	masked_Hinterrupt
+		FTR_SECTION_ELSE
+		bne	masked_interrupt
+		ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+		.elseif IHSRR
+		bne	masked_Hinterrupt
+		.else
+		bne	masked_interrupt
+		.endif
+	.endif
+
+	.if ISTACK
 	andi.	r10,r12,MSR_PR		/* See if coming from user	*/
 	mr	r10,r1			/* Save r1			*/
 	subi	r1,r1,INT_FRAME_SIZE	/* alloc frame on kernel stack	*/
···
 	std	r0,GPR0(r1)		/* save r0 in stackframe	*/
 	std	r10,GPR1(r1)		/* save r1 in stackframe	*/
 
-	.if \stack
-	.if \kuap
+	.if ISET_RI
+	li	r10,MSR_RI
+	mtmsrd	r10,1			/* Set MSR_RI */
+	.endif
+
+	.if ISTACK
+	.if IKUAP
 	kuap_save_amr_and_lock r9, r10, cr1, cr0
 	.endif
 	beq	101f			/* if from kernel mode		*/
 	ACCOUNT_CPU_USER_ENTRY(r13, r9, r10)
-	SAVE_PPR(\area, r9)
+BEGIN_FTR_SECTION
+	ld	r9,IAREA+EX_PPR(r13)	/* Read PPR from paca		*/
+	std	r9,_PPR(r1)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 101:
 	.else
-	.if \kuap
+	.if IKUAP
 	kuap_save_amr_and_lock r9, r10, cr1
 	.endif
 	.endif
 
 	/* Save original regs values from save area to stack frame. */
-	ld	r9,\area+EX_R9(r13)	/* move r9, r10 to stackframe	*/
-	ld	r10,\area+EX_R10(r13)
+	ld	r9,IAREA+EX_R9(r13)	/* move r9, r10 to stackframe	*/
+	ld	r10,IAREA+EX_R10(r13)
 	std	r9,GPR9(r1)
 	std	r10,GPR10(r1)
-	ld	r9,\area+EX_R11(r13)	/* move r11 - r13 to stackframe	*/
-	ld	r10,\area+EX_R12(r13)
-	ld	r11,\area+EX_R13(r13)
+	ld	r9,IAREA+EX_R11(r13)	/* move r11 - r13 to stackframe	*/
+	ld	r10,IAREA+EX_R12(r13)
+	ld	r11,IAREA+EX_R13(r13)
 	std	r9,GPR11(r1)
 	std	r10,GPR12(r1)
 	std	r11,GPR13(r1)
-	.if \dar
-	.if \dar == 2
+
+	SAVE_NVGPRS(r1)
+
+	.if IDAR
+	.if IISIDE
 	ld	r10,_NIP(r1)
 	.else
-	ld	r10,\area+EX_DAR(r13)
+	ld	r10,IAREA+EX_DAR(r13)
 	.endif
 	std	r10,_DAR(r1)
 	.endif
-	.if \dsisr
-	.if \dsisr == 2
+
+	.if IDSISR
+	.if IISIDE
 	ld	r10,_MSR(r1)
 	lis	r11,DSISR_SRR1_MATCH_64S@h
 	and	r10,r10,r11
 	.else
-	lwz	r10,\area+EX_DSISR(r13)
+	lwz	r10,IAREA+EX_DSISR(r13)
 	.endif
 	std	r10,_DSISR(r1)
 	.endif
-BEGIN_FTR_SECTION_NESTED(66)
-	ld	r10,\area+EX_CFAR(r13)
+
+BEGIN_FTR_SECTION
+	ld	r10,IAREA+EX_CFAR(r13)
 	std	r10,ORIG_GPR3(r1)
-END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66)
-	GET_CTR(r10, \area)
+END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
+	ld	r10,IAREA+EX_CTR(r13)
 	std	r10,_CTR(r1)
 	std	r2,GPR2(r1)		/* save r2 in stackframe	*/
 	SAVE_4GPRS(3, r1)		/* save r3 - r6 in stackframe   */
···
 	mfspr	r11,SPRN_XER		/* save XER in stackframe	*/
 	std	r10,SOFTE(r1)
 	std	r11,_XER(r1)
-	li	r9,(\vec)+1
+	li	r9,IVEC
 	std	r9,_TRAP(r1)		/* set trap number		*/
 	li	r10,0
 	ld	r11,exception_marker@toc(r2)
 	std	r10,RESULT(r1)		/* clear regs->result		*/
 	std	r11,STACK_FRAME_OVERHEAD-16(r1) /* mark the frame	*/
 
-	.if \stack
+	.if ISTACK
 	ACCOUNT_STOLEN_TIME
 	.endif
 
-	.if \reconcile
+	.if IRECONCILE
 	RECONCILE_IRQ_STATE(r10, r11)
 	.endif
+.endm
+
+/*
+ * On entry r13 points to the paca, r9-r13 are saved in the paca,
+ * r9 contains the saved CR, r11 and r12 contain the saved SRR0 and
+ * SRR1, and relocation is on.
+ *
+ * If stack=0, then the stack is already set in r1, and r1 is saved in r10.
+ * PPR save and CPU accounting is not done for the !stack case (XXX why not?)
+ */
+.macro GEN_COMMON name
+	__GEN_COMMON_ENTRY \name
+	__GEN_COMMON_BODY \name
 .endm
 
 /*
  * Restore all registers including H/SRR0/1 saved in a stack frame of a
  * standard exception.
  */
-.macro EXCEPTION_RESTORE_REGS hsrr
+.macro EXCEPTION_RESTORE_REGS hsrr=0
 	/* Move original SRR0 and SRR1 into the respective regs */
 	ld	r9,_MSR(r1)
-	.if \hsrr == EXC_HV_OR_STD
-	.error "EXC_HV_OR_STD Not implemented for EXCEPTION_RESTORE_REGS"
-	.endif
 	.if \hsrr
 	mtspr	SPRN_HSRR1,r9
 	.else
···
 #else
 #define FINISH_NAP
 #endif
-
-#define EXC_COMMON(name, realvec, hdlr)					\
-	EXC_COMMON_BEGIN(name);						\
-	INT_COMMON realvec, PACA_EXGEN, 1, 1, 1, 0, 0 ;			\
-	bl	save_nvgprs;						\
-	addi	r3,r1,STACK_FRAME_OVERHEAD;				\
-	bl	hdlr;							\
-	b	ret_from_except
-
-/*
- * Like EXC_COMMON, but for exceptions that can occur in the idle task and
- * therefore need the special idle handling (finish nap and runlatch)
- */
-#define EXC_COMMON_ASYNC(name, realvec, hdlr)				\
-	EXC_COMMON_BEGIN(name);						\
-	INT_COMMON realvec, PACA_EXGEN, 1, 1, 1, 0, 0 ;			\
-	FINISH_NAP;							\
-	RUNLATCH_ON;							\
-	addi	r3,r1,STACK_FRAME_OVERHEAD;				\
-	bl	hdlr;							\
-	b	ret_from_except_lite
-
 
 /*
  * There are a few constraints to be concerned with.
···
 EXC_VIRT_NONE(0x4000, 0x100)
 
 
+/**
+ * Interrupt 0x100 - System Reset Interrupt (SRESET aka NMI).
+ * This is a non-maskable, asynchronous interrupt always taken in real-mode.
+ * It is caused by:
+ * - Wake from power-saving state, on powernv.
+ * - An NMI from another CPU, triggered by firmware or hypercall.
+ * - As crash/debug signal injected from BMC, firmware or hypervisor.
+ *
+ * Handling:
+ * Power-save wakeup is the only performance critical path, so this is
+ * determined quickly as possible first. In this case volatile registers
+ * can be discarded and SPRs like CFAR don't need to be read.
+ *
+ * If not a powersave wakeup, then it's run as a regular interrupt, however
+ * it uses its own stack and PACA save area to preserve the regular kernel
+ * environment for debugging.
+ *
+ * This interrupt is not maskable, so triggering it when MSR[RI] is clear,
+ * or SCRATCH0 is in use, etc. may cause a crash. It's also not entirely
+ * correct to switch to virtual mode to run the regular interrupt handler
+ * because it might be interrupted when the MMU is in a bad state (e.g., SLB
+ * is clear).
+ *
+ * FWNMI:
+ * PAPR specifies a "fwnmi" facility which sends the sreset to a different
+ * entry point with a different register set up. Some hypervisors will
+ * send the sreset to 0x100 in the guest if it is not fwnmi capable.
+ *
+ * KVM:
+ * Unlike most SRR interrupts, this may be taken by the host while executing
+ * in a guest, so a KVM test is required. KVM will pull the CPU out of guest
+ * mode and then raise the sreset.
+ */
+INT_DEFINE_BEGIN(system_reset)
+	IVEC=0x100
+	IAREA=PACA_EXNMI
+	IVIRT=0 /* no virt entry point */
+	/*
+	 * MSR_RI is not enabled, because PACA_EXNMI and nmi stack is
+	 * being used, so a nested NMI exception would corrupt it.
+	 */
+	ISET_RI=0
+	ISTACK=0
+	IRECONCILE=0
+	IKVM_REAL=1
+INT_DEFINE_END(system_reset)
+
 EXC_REAL_BEGIN(system_reset, 0x100, 0x100)
 #ifdef CONFIG_PPC_P7_NAP
 	/*
···
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
 #endif
 
-	INT_HANDLER system_reset, 0x100, area=PACA_EXNMI, ri=0, kvm=1
+	GEN_INT_ENTRY system_reset, virt=0
 	/*
-	 * MSR_RI is not enabled, because PACA_EXNMI and nmi stack is
-	 * being used, so a nested NMI exception would corrupt it.
-	 *
 	 * In theory, we should not enable relocation here if it was disabled
 	 * in SRR1, because the MMU may not be configured to support it (e.g.,
 	 * SLB may have been cleared). In practice, there should only be a few
···
 	 */
 EXC_REAL_END(system_reset, 0x100, 0x100)
 EXC_VIRT_NONE(0x4100, 0x100)
-INT_KVM_HANDLER system_reset 0x100, EXC_STD, PACA_EXNMI, 0
 
 #ifdef CONFIG_PPC_P7_NAP
 TRAMP_REAL_BEGIN(system_reset_idle_wake)
···
  * Vectors for the FWNMI option.  Share common code.
  */
 TRAMP_REAL_BEGIN(system_reset_fwnmi)
-	/* See comment at system_reset exception, don't turn on RI */
-	INT_HANDLER system_reset, 0x100, area=PACA_EXNMI, ri=0
+	/* XXX: fwnmi guest could run a nested/PR guest, so why no test?  */
+	__IKVM_REAL(system_reset)=0
+	GEN_INT_ENTRY system_reset, virt=0
 
 #endif /* CONFIG_PPC_PSERIES */
 
 EXC_COMMON_BEGIN(system_reset_common)
+	__GEN_COMMON_ENTRY system_reset
 	/*
 	 * Increment paca->in_nmi then enable MSR_RI. SLB or MCE will be able
 	 * to recover, but nested NMI will notice in_nmi and not recover
···
 	mr	r10,r1
 	ld	r1,PACA_NMI_EMERG_SP(r13)
 	subi	r1,r1,INT_FRAME_SIZE
-	INT_COMMON 0x100, PACA_EXNMI, 0, 1, 0, 0, 0
-	bl	save_nvgprs
+	__GEN_COMMON_BODY system_reset
 	/*
-	 * Set IRQS_ALL_DISABLED unconditionally so arch_irqs_disabled does
+	 * Set IRQS_ALL_DISABLED unconditionally so irqs_disabled() does
 	 * the right thing. We do not want to reconcile because that goes
 	 * through irq tracing which we don't want in NMI.
 	 *
-	 * Save PACAIRQHAPPENED because some code will do a hard disable
-	 * (e.g., xmon). So we want to restore this back to where it was
-	 * when we return. DAR is unused in the stack, so save it there.
+	 * Save PACAIRQHAPPENED to _DAR (otherwise unused), and set HARD_DIS
+	 * as we are running with MSR[EE]=0.
 	 */
 	li	r10,IRQS_ALL_DISABLED
 	stb	r10,PACAIRQSOFTMASK(r13)
 	lbz	r10,PACAIRQHAPPENED(r13)
 	std	r10,_DAR(r1)
+	ori	r10,r10,PACA_IRQ_HARD_DIS
+	stb	r10,PACAIRQHAPPENED(r13)
 
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	system_reset_exception
···
 	ld	r10,SOFTE(r1)
 	stb	r10,PACAIRQSOFTMASK(r13)
 
-	EXCEPTION_RESTORE_REGS EXC_STD
+	EXCEPTION_RESTORE_REGS
 	RFI_TO_USER_OR_KERNEL
 
+	GEN_KVM system_reset
 
-EXC_REAL_BEGIN(machine_check, 0x200, 0x100)
-	INT_HANDLER machine_check, 0x200, early=1, area=PACA_EXMC, dar=1, dsisr=1
+
+/**
+ * Interrupt 0x200 - Machine Check Interrupt (MCE).
+ * This is a non-maskable interrupt always taken in real-mode. It can be
+ * synchronous or asynchronous, caused by hardware or software, and it may be
+ * taken in a power-saving state.
+ *
+ * Handling:
+ * Similarly to system reset, this uses its own stack and PACA save area,
+ * the difference is re-entrancy is allowed on the machine check stack.
+ *
+ * machine_check_early is run in real mode, and carefully decodes the
+ * machine check and tries to handle it (e.g., flush the SLB if there was an
+ * error detected there), determines if it was recoverable and logs the
+ * event.
+ *
+ * This early code does not "reconcile" irq soft-mask state like SRESET or
+ * regular interrupts do, so irqs_disabled() among other things may not work
+ * properly (irq disable/enable already doesn't work because irq tracing can
+ * not work in real mode).
+ *
+ * Then, depending on the execution context when the interrupt is taken, there
+ * are 3 main actions:
+ * - Executing in kernel mode. The event is queued with irq_work, which means
+ *   it is handled when it is next safe to do so (i.e., the kernel has enabled
+ *   interrupts), which could be immediately when the interrupt returns. This
+ *   avoids nasty issues like switching to virtual mode when the MMU is in a
+ *   bad state, or when executing OPAL code. (SRESET is exposed to such issues,
+ *   but it has different priorities). Check to see if the CPU was in power
+ *   save, and return via the wake up code if it was.
+ *
+ * - Executing in user mode. machine_check_exception is run like a normal
+ *   interrupt handler, which processes the data generated by the early handler.
+ *
+ * - Executing in guest mode. The interrupt is run with its KVM test, and
+ *   branches to KVM to deal with. KVM may queue the event for the host
+ *   to report later.
+ *
+ * This interrupt is not maskable, so if it triggers when MSR[RI] is clear,
+ * or SCRATCH0 is in use, it may cause a crash.
+ *
+ * KVM:
+ * See SRESET.
+ */
+INT_DEFINE_BEGIN(machine_check_early)
+	IVEC=0x200
+	IAREA=PACA_EXMC
+	IVIRT=0 /* no virt entry point */
+	IREALMODE_COMMON=1
 	/*
 	 * MSR_RI is not enabled, because PACA_EXMC is being used, so a
 	 * nested machine check corrupts it. machine_check_common enables
 	 * MSR_RI.
 	 */
+	ISET_RI=0
+	ISTACK=0
+	IDAR=1
+	IDSISR=1
+	IRECONCILE=0
+	IKUAP=0 /* We don't touch AMR here, we never go to virtual mode */
+INT_DEFINE_END(machine_check_early)
+
+INT_DEFINE_BEGIN(machine_check)
+	IVEC=0x200
+	IAREA=PACA_EXMC
+	IVIRT=0 /* no virt entry point */
+	ISET_RI=0
+	IDAR=1
+	IDSISR=1
+	IKVM_SKIP=1
+	IKVM_REAL=1
+INT_DEFINE_END(machine_check)
+
+EXC_REAL_BEGIN(machine_check, 0x200, 0x100)
+	GEN_INT_ENTRY machine_check_early, virt=0
 EXC_REAL_END(machine_check, 0x200, 0x100)
 EXC_VIRT_NONE(0x4200, 0x100)
 
 #ifdef CONFIG_PPC_PSERIES
 TRAMP_REAL_BEGIN(machine_check_fwnmi)
 	/* See comment at machine_check exception, don't turn on RI */
-	INT_HANDLER machine_check, 0x200, early=1, area=PACA_EXMC, dar=1, dsisr=1
+	GEN_INT_ENTRY machine_check_early, virt=0
 #endif
-
-INT_KVM_HANDLER machine_check 0x200, EXC_STD, PACA_EXMC, 1
 
 #define MACHINE_CHECK_HANDLER_WINDUP			\
 	/* Clear MSR_RI before setting SRR0 and SRR1. */\
···
 	lhz	r12,PACA_IN_MCE(r13);			\
 	subi	r12,r12,1;				\
 	sth	r12,PACA_IN_MCE(r13);			\
-	EXCEPTION_RESTORE_REGS EXC_STD
+	EXCEPTION_RESTORE_REGS
 
 EXC_COMMON_BEGIN(machine_check_early_common)
-	mtctr	r10			/* Restore ctr */
-	mfspr	r11,SPRN_SRR0
-	mfspr	r12,SPRN_SRR1
+	__GEN_REALMODE_COMMON_ENTRY machine_check_early
 
 	/*
 	 * Switch to mc_emergency stack and handle re-entrancy (we limit
···
 	bgt	cr1,unrecoverable_mce	/* Check if we hit limit of 4 */
 	subi	r1,r1,INT_FRAME_SIZE	/* alloc stack frame */
 
-	/* We don't touch AMR here, we never go to virtual mode */
-	INT_COMMON 0x200, PACA_EXMC, 0, 0, 0, 1, 1
+	__GEN_COMMON_BODY machine_check_early
 
 BEGIN_FTR_SECTION
 	bl	enable_machine_check
···
 	li	r10,MSR_RI
 	mtmsrd	r10,1
 
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	machine_check_early
 	std	r3,RESULT(r1)	/* Save result */
···
 	mtspr	SPRN_CFAR,r10
 END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	MACHINE_CHECK_HANDLER_WINDUP
-	/* See comment at machine_check exception, don't turn on RI */
-	INT_HANDLER machine_check, 0x200, area=PACA_EXMC, ri=0, dar=1, dsisr=1, kvm=1
+	GEN_INT_ENTRY machine_check, virt=0
 
 EXC_COMMON_BEGIN(machine_check_common)
 	/*
 	 * Machine check is different because we use a different
 	 * save area: PACA_EXMC instead of PACA_EXGEN.
 	 */
-	INT_COMMON 0x200, PACA_EXMC, 1, 1, 1, 1, 1
+	GEN_COMMON machine_check
+
 	FINISH_NAP
 	/* Enable MSR_RI when finished with PACA_EXMC */
 	li	r10,MSR_RI
 	mtmsrd 	r10,1
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	machine_check_exception
-	b	ret_from_except
+	b	interrupt_return
+
+	GEN_KVM machine_check
+
 
 #ifdef CONFIG_PPC_P7_NAP
 /*
···
 	b	.
 
 
+/**
+ * Interrupt 0x300 - Data Storage Interrupt (DSI).
+ * This is a synchronous interrupt generated due to a data access exception,
+ * e.g., a load orstore which does not have a valid page table entry with
+ * permissions. DAWR matches also fault here, as do RC updates, and minor misc
+ * errors e.g., copy/paste, AMO, certain invalid CI accesses, etc.
+ *
+ * Handling:
+ * - Hash MMU
+ *   Go to do_hash_page first to see if the HPT can be filled from an entry in
+ *   the Linux page table. Hash faults can hit in kernel mode in a fairly
+ *   arbitrary state (e.g., interrupts disabled, locks held) when accessing
+ *   "non-bolted" regions, e.g., vmalloc space. However these should always be
+ *   backed by Linux page tables.
+ *
+ *   If none is found, do a Linux page fault. Linux page faults can happen in
+ *   kernel mode due to user copy operations of course.
+ *
+ * - Radix MMU
+ *   The hardware loads from the Linux page table directly, so a fault goes
+ *   immediately to Linux page fault.
+ *
+ * Conditions like DAWR match are handled on the way in to Linux page fault.
+ */
+INT_DEFINE_BEGIN(data_access)
+	IVEC=0x300
+	IDAR=1
+	IDSISR=1
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	IKVM_SKIP=1
+	IKVM_REAL=1
+#endif
+INT_DEFINE_END(data_access)
+
 EXC_REAL_BEGIN(data_access, 0x300, 0x80)
-	INT_HANDLER data_access, 0x300, ool=1, dar=1, dsisr=1, kvm=1
+	GEN_INT_ENTRY data_access, virt=0
 EXC_REAL_END(data_access, 0x300, 0x80)
 EXC_VIRT_BEGIN(data_access, 0x4300, 0x80)
-	INT_HANDLER data_access, 0x300, virt=1, dar=1, dsisr=1
+	GEN_INT_ENTRY data_access, virt=1
 EXC_VIRT_END(data_access, 0x4300, 0x80)
-INT_KVM_HANDLER data_access, 0x300, EXC_STD, PACA_EXGEN, 1
 EXC_COMMON_BEGIN(data_access_common)
-	/*
-	 * Here r13 points to the paca, r9 contains the saved CR,
-	 * SRR0 and SRR1 are saved in r11 and r12,
-	 * r9 - r13 are saved in paca->exgen.
-	 * EX_DAR and EX_DSISR have saved DAR/DSISR
-	 */
-	INT_COMMON 0x300, PACA_EXGEN, 1, 1, 1, 1, 1
+	GEN_COMMON data_access
 	ld	r4,_DAR(r1)
 	ld	r5,_DSISR(r1)
 BEGIN_MMU_FTR_SECTION
···
 	b	handle_page_fault
 ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 
+	GEN_KVM data_access
+
+
+/**
+ * Interrupt 0x380 - Data Segment Interrupt (DSLB).
+ * This is a synchronous interrupt in response to an MMU fault missing SLB
+ * entry for HPT, or an address outside RPT translation range.
+ *
+ * Handling:
+ * - HPT:
+ *   This refills the SLB, or reports an access fault similarly to a bad page
+ *   fault. When coming from user-mode, the SLB handler may access any kernel
+ *   data, though it may itself take a DSLB. When coming from kernel mode,
+ *   recursive faults must be avoided so access is restricted to the kernel
+ *   image text/data, kernel stack, and any data allocated below
+ *   ppc64_bolted_size (first segment). The kernel handler must avoid stomping
+ *   on user-handler data structures.
+ *
+ * A dedicated save area EXSLB is used (XXX: but it actually need not be
+ * these days, we could use EXGEN).
+ */
+INT_DEFINE_BEGIN(data_access_slb)
+	IVEC=0x380
+	IAREA=PACA_EXSLB
+	IRECONCILE=0
+	IDAR=1
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	IKVM_SKIP=1
+	IKVM_REAL=1
+#endif
+INT_DEFINE_END(data_access_slb)
 
 EXC_REAL_BEGIN(data_access_slb, 0x380, 0x80)
-	INT_HANDLER data_access_slb, 0x380, ool=1, area=PACA_EXSLB, dar=1, kvm=1
+	GEN_INT_ENTRY data_access_slb, virt=0
 EXC_REAL_END(data_access_slb, 0x380, 0x80)
 EXC_VIRT_BEGIN(data_access_slb, 0x4380, 0x80)
-	INT_HANDLER data_access_slb, 0x380, virt=1, area=PACA_EXSLB, dar=1
+	GEN_INT_ENTRY data_access_slb, virt=1
 EXC_VIRT_END(data_access_slb, 0x4380, 0x80)
-INT_KVM_HANDLER data_access_slb, 0x380, EXC_STD, PACA_EXSLB, 1
 EXC_COMMON_BEGIN(data_access_slb_common)
-	INT_COMMON 0x380, PACA_EXSLB, 1, 1, 0, 1, 0
+	GEN_COMMON data_access_slb
 	ld	r4,_DAR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 BEGIN_MMU_FTR_SECTION
···
 	bl	do_slb_fault
 	cmpdi	r3,0
 	bne-	1f
-	b	fast_exception_return
+	b	fast_interrupt_return
 1:	/* Error case */
 MMU_FTR_SECTION_ELSE
 	/* Radix case, access is outside page table range */
 	li	r3,-EFAULT
 ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 	std	r3,RESULT(r1)
-	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	ld	r4,_DAR(r1)
 	ld	r5,RESULT(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_bad_slb_fault
-	b	ret_from_except
+	b	interrupt_return
 
+	GEN_KVM data_access_slb
+
+
+/**
+ * Interrupt 0x400 - Instruction Storage Interrupt (ISI).
+ * This is a synchronous interrupt in response to an MMU fault due to an
+ * instruction fetch.
+ *
+ * Handling:
+ * Similar to DSI, though in response to fetch. The faulting address is found
+ * in SRR0 (rather than DAR), and status in SRR1 (rather than DSISR).
+ */
+INT_DEFINE_BEGIN(instruction_access)
+	IVEC=0x400
+	IISIDE=1
+	IDAR=1
+	IDSISR=1
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	IKVM_REAL=1
+#endif
+INT_DEFINE_END(instruction_access)
 
 EXC_REAL_BEGIN(instruction_access, 0x400, 0x80)
-	INT_HANDLER instruction_access, 0x400, kvm=1
+	GEN_INT_ENTRY instruction_access, virt=0
 EXC_REAL_END(instruction_access, 0x400, 0x80)
 EXC_VIRT_BEGIN(instruction_access, 0x4400, 0x80)
-	INT_HANDLER instruction_access, 0x400, virt=1
+	GEN_INT_ENTRY instruction_access, virt=1
 EXC_VIRT_END(instruction_access, 0x4400, 0x80)
-INT_KVM_HANDLER instruction_access, 0x400, EXC_STD, PACA_EXGEN, 0
 EXC_COMMON_BEGIN(instruction_access_common)
-	INT_COMMON 0x400, PACA_EXGEN, 1, 1, 1, 2, 2
+	GEN_COMMON instruction_access
 	ld	r4,_DAR(r1)
 	ld	r5,_DSISR(r1)
 BEGIN_MMU_FTR_SECTION
···
 	b	handle_page_fault
 ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 
+	GEN_KVM instruction_access
+
+
+/**
+ * Interrupt 0x480 - Instruction Segment Interrupt (ISLB).
+ * This is a synchronous interrupt in response to an MMU fault due to an
+ * instruction fetch.
+ *
+ * Handling:
+ * Similar to DSLB, though in response to fetch. The faulting address is found
+ * in SRR0 (rather than DAR).
+ */
+INT_DEFINE_BEGIN(instruction_access_slb)
+	IVEC=0x480
+	IAREA=PACA_EXSLB
+	IRECONCILE=0
+	IISIDE=1
+	IDAR=1
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	IKVM_REAL=1
+#endif
+INT_DEFINE_END(instruction_access_slb)
 
 EXC_REAL_BEGIN(instruction_access_slb, 0x480, 0x80)
-	INT_HANDLER instruction_access_slb, 0x480, area=PACA_EXSLB, kvm=1
+	GEN_INT_ENTRY instruction_access_slb, virt=0
 EXC_REAL_END(instruction_access_slb, 0x480, 0x80)
 EXC_VIRT_BEGIN(instruction_access_slb, 0x4480, 0x80)
-	INT_HANDLER instruction_access_slb, 0x480, virt=1, area=PACA_EXSLB
+	GEN_INT_ENTRY instruction_access_slb, virt=1
 EXC_VIRT_END(instruction_access_slb, 0x4480, 0x80)
-INT_KVM_HANDLER instruction_access_slb, 0x480, EXC_STD, PACA_EXSLB, 0
 EXC_COMMON_BEGIN(instruction_access_slb_common)
-	INT_COMMON 0x480, PACA_EXSLB, 1, 1, 0, 2, 0
+	GEN_COMMON instruction_access_slb
 	ld	r4,_DAR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 BEGIN_MMU_FTR_SECTION
···
 	bl	do_slb_fault
 	cmpdi	r3,0
 	bne-	1f
-	b	fast_exception_return
+	b	fast_interrupt_return
 1:	/* Error case */
 MMU_FTR_SECTION_ELSE
 	/* Radix case, access is outside page table range */
 	li	r3,-EFAULT
 ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 	std	r3,RESULT(r1)
-	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	ld	r4,_DAR(r1)
 	ld	r5,RESULT(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_bad_slb_fault
-	b	ret_from_except
+	b	interrupt_return
+
+	GEN_KVM instruction_access_slb
+
+
+/**
+ * Interrupt 0x500 - External Interrupt.
+ * This is an asynchronous maskable interrupt in response to an "external
+ * exception" from the interrupt controller or hypervisor (e.g., device
+ * interrupt). It is maskable in hardware by clearing MSR[EE], and
+ * soft-maskable with IRQS_DISABLED mask (i.e., local_irq_disable()).
+ *
+ * When running in HV mode, Linux sets up the LPCR[LPES] bit such that
+ * interrupts are delivered with HSRR registers, guests use SRRs, which
+ * reqiures IHSRR_IF_HVMODE.
+ *
+ * On bare metal POWER9 and later, Linux sets the LPCR[HVICE] bit such that
+ * external interrupts are delivered as Hypervisor Virtualization Interrupts
+ * rather than External Interrupts.
+ *
+ * Handling:
+ * This calls into Linux IRQ handler. NVGPRs are not saved to reduce overhead,
+ * because registers at the time of the interrupt are not so important as it is
+ * asynchronous.
+ *
+ * If soft masked, the masked handler will note the pending interrupt for
+ * replay, and clear MSR[EE] in the interrupted context.
+ */
+INT_DEFINE_BEGIN(hardware_interrupt)
+	IVEC=0x500
+	IHSRR_IF_HVMODE=1
+	IMASK=IRQS_DISABLED
+	IKVM_REAL=1
+	IKVM_VIRT=1
+INT_DEFINE_END(hardware_interrupt)
 
 EXC_REAL_BEGIN(hardware_interrupt, 0x500, 0x100)
-	INT_HANDLER hardware_interrupt, 0x500, hsrr=EXC_HV_OR_STD, bitmask=IRQS_DISABLED, kvm=1
+	GEN_INT_ENTRY hardware_interrupt, virt=0
 EXC_REAL_END(hardware_interrupt, 0x500, 0x100)
 EXC_VIRT_BEGIN(hardware_interrupt, 0x4500, 0x100)
-	INT_HANDLER hardware_interrupt, 0x500, virt=1, hsrr=EXC_HV_OR_STD, bitmask=IRQS_DISABLED, kvm=1
+	GEN_INT_ENTRY hardware_interrupt, virt=1
 EXC_VIRT_END(hardware_interrupt, 0x4500, 0x100)
-INT_KVM_HANDLER hardware_interrupt, 0x500, EXC_HV_OR_STD, PACA_EXGEN, 0
-EXC_COMMON_ASYNC(hardware_interrupt_common, 0x500, do_IRQ)
+EXC_COMMON_BEGIN(hardware_interrupt_common)
+	GEN_COMMON hardware_interrupt
+	FINISH_NAP
+	RUNLATCH_ON
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	do_IRQ
+	b	interrupt_return
 
+	GEN_KVM hardware_interrupt
+
+
+/**
+ * Interrupt 0x600 - Alignment Interrupt
+ * This is a synchronous interrupt in response to data alignment fault.
+ */
+INT_DEFINE_BEGIN(alignment)
+	IVEC=0x600
+	IDAR=1
+	IDSISR=1
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	IKVM_REAL=1
+#endif
+INT_DEFINE_END(alignment)
 
 EXC_REAL_BEGIN(alignment, 0x600, 0x100)
-	INT_HANDLER alignment, 0x600, dar=1, dsisr=1, kvm=1
+	GEN_INT_ENTRY alignment, virt=0
 EXC_REAL_END(alignment, 0x600, 0x100)
 EXC_VIRT_BEGIN(alignment, 0x4600, 0x100)
-	INT_HANDLER alignment, 0x600, virt=1, dar=1, dsisr=1
+	GEN_INT_ENTRY alignment, virt=1
 EXC_VIRT_END(alignment, 0x4600, 0x100)
-INT_KVM_HANDLER alignment, 0x600, EXC_STD, PACA_EXGEN, 0
 EXC_COMMON_BEGIN(alignment_common)
-	INT_COMMON 0x600, PACA_EXGEN, 1, 1, 1, 1, 1
-	bl	save_nvgprs
+	GEN_COMMON alignment
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	alignment_exception
-	b	ret_from_except
+	REST_NVGPRS(r1) /* instruction emulation may change GPRs */
+	b	interrupt_return
 
+	GEN_KVM alignment
+
+
+/**
+ * Interrupt 0x700 - Program Interrupt (program check).
+ * This is a synchronous interrupt in response to various instruction faults:
+ * traps, privilege errors, TM errors, floating point exceptions.
+ *
+ * Handling:
+ * This interrupt may use the "emergency stack" in some cases when being taken
+ * from kernel context, which complicates handling.
+ */
+INT_DEFINE_BEGIN(program_check)
+	IVEC=0x700
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	IKVM_REAL=1
+#endif
+INT_DEFINE_END(program_check)
 
 EXC_REAL_BEGIN(program_check, 0x700, 0x100)
-	INT_HANDLER program_check, 0x700, kvm=1
+	GEN_INT_ENTRY program_check, virt=0
 EXC_REAL_END(program_check, 0x700, 0x100)
 EXC_VIRT_BEGIN(program_check, 0x4700, 0x100)
-	INT_HANDLER program_check, 0x700, virt=1
+	GEN_INT_ENTRY program_check, virt=1
 EXC_VIRT_END(program_check, 0x4700, 0x100)
-INT_KVM_HANDLER program_check, 0x700, EXC_STD, PACA_EXGEN, 0
 EXC_COMMON_BEGIN(program_check_common)
+	__GEN_COMMON_ENTRY program_check
+
 	/*
 	 * It's possible to receive a TM Bad Thing type program check with
 	 * userspace register values (in particular r1), but with SRR1 reporting
···
 	mr	r10,r1			/* Save r1			*/
 	ld	r1,PACAEMERGSP(r13)	/* Use emergency stack		*/
 	subi	r1,r1,INT_FRAME_SIZE	/* alloc stack frame		*/
-	INT_COMMON 0x700, PACA_EXGEN, 0, 1, 1, 0, 0
+	__ISTACK(program_check)=0
+	__GEN_COMMON_BODY program_check
 	b 3f
 2:
-	INT_COMMON 0x700, PACA_EXGEN, 1, 1, 1, 0, 0
+	__ISTACK(program_check)=1
+	__GEN_COMMON_BODY program_check
 3:
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	program_check_exception
-	b	ret_from_except
+	REST_NVGPRS(r1) /* instruction emulation may change GPRs */
+	b	interrupt_return
 
+	GEN_KVM program_check
+
+
+/*
+ * Interrupt 0x800 - Floating-Point Unavailable Interrupt.
+ * This is a synchronous interrupt in response to executing an fp instruction
+ * with MSR[FP]=0.
+ *
+ * Handling:
+ * This will load FP registers and enable the FP bit if coming from userspace,
+ * otherwise report a bad kernel use of FP.
+ */
+INT_DEFINE_BEGIN(fp_unavailable)
+	IVEC=0x800
+	IRECONCILE=0
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	IKVM_REAL=1
+#endif
+INT_DEFINE_END(fp_unavailable)
 
 EXC_REAL_BEGIN(fp_unavailable, 0x800, 0x100)
-	INT_HANDLER fp_unavailable, 0x800, kvm=1
+	GEN_INT_ENTRY fp_unavailable, virt=0
 EXC_REAL_END(fp_unavailable, 0x800, 0x100)
 EXC_VIRT_BEGIN(fp_unavailable, 0x4800, 0x100)
-	INT_HANDLER fp_unavailable, 0x800, virt=1
+	GEN_INT_ENTRY fp_unavailable, virt=1
 EXC_VIRT_END(fp_unavailable, 0x4800, 0x100)
-INT_KVM_HANDLER fp_unavailable, 0x800, EXC_STD, PACA_EXGEN, 0
 EXC_COMMON_BEGIN(fp_unavailable_common)
-	INT_COMMON 0x800, PACA_EXGEN, 1, 1, 0, 0, 0
+	GEN_COMMON fp_unavailable
 	bne	1f			/* if from user, just load it up */
-	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	kernel_fp_unavailable_exception
···
 END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
 	bl	load_up_fpu
-	b	fast_exception_return
+	b	fast_interrupt_return
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 2:	/* User process was in a transaction */
-	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	fp_unavailable_tm
-	b	ret_from_except
+	b	interrupt_return
 #endif
 
+	GEN_KVM fp_unavailable
+
+
+/**
+ * Interrupt 0x900 - Decrementer Interrupt.
+ * This is an asynchronous interrupt in response to a decrementer exception
+ * (e.g., DEC has wrapped below zero). It is maskable in hardware by clearing
+ * MSR[EE], and soft-maskable with IRQS_DISABLED mask (i.e.,
+ * local_irq_disable()).
+ *
+ * Handling:
+ * This calls into Linux timer handler. NVGPRs are not saved (see 0x500).
+ *
+ * If soft masked, the masked handler will note the pending interrupt for
+ * replay, and bump the decrementer to a high value, leaving MSR[EE] enabled
+ * in the interrupted context.
+ * If PPC_WATCHDOG is configured, the soft masked handler will actually set
+ * things back up to run soft_nmi_interrupt as a regular interrupt handler
+ * on the emergency stack.
+ */
+INT_DEFINE_BEGIN(decrementer)
+	IVEC=0x900
+	IMASK=IRQS_DISABLED
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	IKVM_REAL=1
+#endif
+INT_DEFINE_END(decrementer)
 
 EXC_REAL_BEGIN(decrementer, 0x900, 0x80)
-	INT_HANDLER decrementer, 0x900, ool=1, bitmask=IRQS_DISABLED, kvm=1
+	GEN_INT_ENTRY decrementer, virt=0
 EXC_REAL_END(decrementer, 0x900, 0x80)
 EXC_VIRT_BEGIN(decrementer, 0x4900, 0x80)
-	INT_HANDLER decrementer, 0x900, virt=1, bitmask=IRQS_DISABLED
+	GEN_INT_ENTRY decrementer, virt=1
 EXC_VIRT_END(decrementer, 0x4900, 0x80)
-INT_KVM_HANDLER decrementer, 0x900, EXC_STD, PACA_EXGEN, 0
-EXC_COMMON_ASYNC(decrementer_common, 0x900, timer_interrupt)
+EXC_COMMON_BEGIN(decrementer_common)
+	GEN_COMMON decrementer
+	FINISH_NAP
+	RUNLATCH_ON
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	timer_interrupt
+	b	interrupt_return
 
+	GEN_KVM decrementer
+
+
+/**
+ * Interrupt 0x980 - Hypervisor Decrementer Interrupt.
+ * This is an asynchronous interrupt, similar to 0x900 but for the HDEC
+ * register.
+ *
+ * Handling:
+ * Linux does not use this outside KVM where it's used to keep a host timer
+ * while the guest is given control of DEC. It should normally be caught by
+ * the KVM test and routed there.
+ */
+INT_DEFINE_BEGIN(hdecrementer)
+	IVEC=0x980
+	IHSRR=1
+	ISTACK=0
+	IRECONCILE=0
+	IKVM_REAL=1
+	IKVM_VIRT=1
+INT_DEFINE_END(hdecrementer)
 
 EXC_REAL_BEGIN(hdecrementer, 0x980, 0x80)
-	INT_HANDLER hdecrementer, 0x980, hsrr=EXC_HV, kvm=1
+	GEN_INT_ENTRY hdecrementer, virt=0
 EXC_REAL_END(hdecrementer, 0x980, 0x80)
 EXC_VIRT_BEGIN(hdecrementer, 0x4980, 0x80)
-	INT_HANDLER hdecrementer, 0x980, virt=1, hsrr=EXC_HV, kvm=1
+	GEN_INT_ENTRY hdecrementer, virt=1
 EXC_VIRT_END(hdecrementer, 0x4980, 0x80)
-INT_KVM_HANDLER hdecrementer, 0x980, EXC_HV, PACA_EXGEN, 0
-EXC_COMMON(hdecrementer_common, 0x980, hdec_interrupt)
+EXC_COMMON_BEGIN(hdecrementer_common)
+	__GEN_COMMON_ENTRY hdecrementer
+	/*
+	 * Hypervisor decrementer interrupts not caught by the KVM test
+	 * shouldn't occur but are sometimes left pending on exit from a KVM
+	 * guest.  We don't need to do anything to clear them, as they are
+	 * edge-triggered.
+	 *
+	 * Be careful to avoid touching the kernel stack.
+	 */
+	ld	r10,PACA_EXGEN+EX_CTR(r13)
+	mtctr	r10
+	mtcrf	0x80,r9
+	ld	r9,PACA_EXGEN+EX_R9(r13)
+	ld	r10,PACA_EXGEN+EX_R10(r13)
+	ld	r11,PACA_EXGEN+EX_R11(r13)
+	ld	r12,PACA_EXGEN+EX_R12(r13)
+	ld	r13,PACA_EXGEN+EX_R13(r13)
+	HRFI_TO_KERNEL
 
+	GEN_KVM hdecrementer
+
+
+/**
+ * Interrupt 0xa00 - Directed Privileged Doorbell Interrupt.
+ * This is an asynchronous interrupt in response to a msgsndp doorbell.
+ * It is maskable in hardware by clearing MSR[EE], and soft-maskable with
+ * IRQS_DISABLED mask (i.e., local_irq_disable()).
+ *
+ * Handling:
+ * Guests may use this for IPIs between threads in a core if the
+ * hypervisor supports it. NVGPRS are not saved (see 0x500).
+ *
+ * If soft masked, the masked handler will note the pending interrupt for
+ * replay, leaving MSR[EE] enabled in the interrupted context because the
+ * doorbells are edge triggered.
+ */
+INT_DEFINE_BEGIN(doorbell_super)
+	IVEC=0xa00
+	IMASK=IRQS_DISABLED
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	IKVM_REAL=1
+#endif
+INT_DEFINE_END(doorbell_super)
 
 EXC_REAL_BEGIN(doorbell_super, 0xa00, 0x100)
-	INT_HANDLER doorbell_super, 0xa00, bitmask=IRQS_DISABLED, kvm=1
+	GEN_INT_ENTRY doorbell_super, virt=0
 EXC_REAL_END(doorbell_super, 0xa00, 0x100)
 EXC_VIRT_BEGIN(doorbell_super, 0x4a00, 0x100)
-	INT_HANDLER doorbell_super, 0xa00, virt=1, bitmask=IRQS_DISABLED
+	GEN_INT_ENTRY doorbell_super, virt=1
 EXC_VIRT_END(doorbell_super, 0x4a00, 0x100)
-INT_KVM_HANDLER doorbell_super, 0xa00, EXC_STD, PACA_EXGEN, 0
+EXC_COMMON_BEGIN(doorbell_super_common)
+	GEN_COMMON doorbell_super
+	FINISH_NAP
+	RUNLATCH_ON
+	addi	r3,r1,STACK_FRAME_OVERHEAD
 #ifdef CONFIG_PPC_DOORBELL
-EXC_COMMON_ASYNC(doorbell_super_common, 0xa00, doorbell_exception)
+	bl	doorbell_exception
 #else
-EXC_COMMON_ASYNC(doorbell_super_common, 0xa00, unknown_exception)
+	bl	unknown_exception
 #endif
+	b	interrupt_return
+
+	GEN_KVM doorbell_super
 
 
 EXC_REAL_NONE(0xb00, 0x100)
 EXC_VIRT_NONE(0x4b00, 0x100)
 
-/*
- * system call / hypercall (0xc00, 0x4c00)
- *
- * The system call exception is invoked with "sc 0" and does not alter HV bit.
- *
- * The hypercall is invoked with "sc 1" and sets HV=1.
+/**
+ * Interrupt 0xc00 - System Call Interrupt (syscall, hcall).
+ * This is a synchronous interrupt invoked with the "sc" instruction. The
+ * system call is invoked with "sc 0" and does not alter the HV bit, so it
+ * is directed to the currently running OS. The hypercall is invoked with
+ * "sc 1" and it sets HV=1, so it elevates to hypervisor.
  *
  * In HPT, sc 1 always goes to 0xc00 real mode. In RADIX, sc 1 can go to
  * 0x4c00 virtual mode.
+ *
+ * Handling:
+ * If the KVM test fires then it was due to a hypercall and is accordingly
+ * routed to KVM. Otherwise this executes a normal Linux system call.
  *
  * Call convention:
  *
···
  * without saving, though xer is not a good idea to use, as hardware may
  * interpret some bits so it may be costly to change them.
  */
+INT_DEFINE_BEGIN(system_call)
+	IVEC=0xc00
+	IKVM_REAL=1
+	IKVM_VIRT=1
+INT_DEFINE_END(system_call)
+
 .macro SYSTEM_CALL virt
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 	/*
···
 	GET_PACA(r13)
 	std	r10,PACA_EXGEN+EX_R10(r13)
 	INTERRUPT_TO_KERNEL
-	KVMTEST system_call EXC_STD 0xc00 /* uses r10, branch to system_call_kvm */
+	KVMTEST system_call /* uses r10, branch to system_call_kvm */
 	mfctr	r9
 #else
 	mr	r9,r13
···
 EXC_VIRT_END(system_call, 0x4c00, 0x100)
 
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+TRAMP_REAL_BEGIN(system_call_kvm)
 	/*
 	 * This is a hcall, so register convention is as above, with these
 	 * differences:
···
 	 * ctr = orig r13
 	 * orig r10 saved in PACA
 	 */
-TRAMP_KVM_BEGIN(system_call_kvm)
 	 /*
 	  * Save the PPR (on systems that support it) before changing to
 	  * HMT_MEDIUM. That allows the KVM code to save that value into the
 	  * guest state (it is the guest's PPR value).
 	  */
-	OPT_GET_SPR(r10, SPRN_PPR, CPU_FTR_HAS_PPR)
+BEGIN_FTR_SECTION
+	mfspr	r10,SPRN_PPR
+	std	r10,HSTATE_PPR(r13)
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	HMT_MEDIUM
-	OPT_SAVE_REG_TO_PACA(PACA_EXGEN+EX_PPR, r10, CPU_FTR_HAS_PPR)
 	mfctr	r10
 	SET_SCRATCH0(r10)
-	std	r9,PACA_EXGEN+EX_R9(r13)
-	mfcr	r9
-	KVM_HANDLER 0xc00, EXC_STD, PACA_EXGEN, 0
+	mfcr	r10
+	std	r12,HSTATE_SCRATCH0(r13)
+	sldi	r12,r10,32
+	ori	r12,r12,0xc00
+#ifdef CONFIG_RELOCATABLE
+	/*
+	 * Requires __LOAD_FAR_HANDLER beause kvmppc_interrupt lives
+	 * outside the head section.
+	 */
+	__LOAD_FAR_HANDLER(r10, kvmppc_interrupt)
+	mtctr   r10
+	ld	r10,PACA_EXGEN+EX_R10(r13)
+	bctr
+#else
+	ld	r10,PACA_EXGEN+EX_R10(r13)
+	b       kvmppc_interrupt
+#endif
 #endif
 
 
+/**
+ * Interrupt 0xd00 - Trace Interrupt.
+ * This is a synchronous interrupt in response to instruction step or
+ * breakpoint faults.
+ */
+INT_DEFINE_BEGIN(single_step)
+	IVEC=0xd00
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	IKVM_REAL=1
+#endif
+INT_DEFINE_END(single_step)
+
 EXC_REAL_BEGIN(single_step, 0xd00, 0x100)
-	INT_HANDLER single_step, 0xd00, kvm=1
+	GEN_INT_ENTRY single_step, virt=0
 EXC_REAL_END(single_step, 0xd00, 0x100)
 EXC_VIRT_BEGIN(single_step, 0x4d00, 0x100)
-	INT_HANDLER single_step, 0xd00, virt=1
+	GEN_INT_ENTRY single_step, virt=1
 EXC_VIRT_END(single_step, 0x4d00, 0x100)
-INT_KVM_HANDLER single_step, 0xd00, EXC_STD, PACA_EXGEN, 0
-EXC_COMMON(single_step_common, 0xd00, single_step_exception)
+EXC_COMMON_BEGIN(single_step_common)
+	GEN_COMMON single_step
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	single_step_exception
+	b	interrupt_return
 
+	GEN_KVM single_step
+
+
+/**
+ * Interrupt 0xe00 - Hypervisor Data Storage Interrupt (HDSI).
+ * This is a synchronous interrupt in response to an MMU fault caused by a
+ * guest data access.
+ *
+ * Handling:
+ * This should always get routed to KVM. In radix MMU mode, this is caused
+ * by a guest nested radix access that can't be performed due to the
+ * partition scope page table. In hash mode, this can be caused by guests
+ * running with translation disabled (virtual real mode) or with VPM enabled.
+ * KVM will update the page table structures or disallow the access.
+ */
+INT_DEFINE_BEGIN(h_data_storage)
+	IVEC=0xe00
+	IHSRR=1
+	IDAR=1
+	IDSISR=1
+	IKVM_SKIP=1
+	IKVM_REAL=1
+	IKVM_VIRT=1
+INT_DEFINE_END(h_data_storage)
 
 EXC_REAL_BEGIN(h_data_storage, 0xe00, 0x20)
-	INT_HANDLER h_data_storage, 0xe00, ool=1, hsrr=EXC_HV, dar=1, dsisr=1, kvm=1
+	GEN_INT_ENTRY h_data_storage, virt=0, ool=1
 EXC_REAL_END(h_data_storage, 0xe00, 0x20)
 EXC_VIRT_BEGIN(h_data_storage, 0x4e00, 0x20)
-	INT_HANDLER h_data_storage, 0xe00, ool=1, virt=1, hsrr=EXC_HV, dar=1, dsisr=1, kvm=1
+	GEN_INT_ENTRY h_data_storage, virt=1, ool=1
 EXC_VIRT_END(h_data_storage, 0x4e00, 0x20)
-INT_KVM_HANDLER h_data_storage, 0xe00, EXC_HV, PACA_EXGEN, 1
 EXC_COMMON_BEGIN(h_data_storage_common)
-	INT_COMMON 0xe00, PACA_EXGEN, 1, 1, 1, 1, 1
-	bl      save_nvgprs
+	GEN_COMMON h_data_storage
 	addi    r3,r1,STACK_FRAME_OVERHEAD
 BEGIN_MMU_FTR_SECTION
 	ld	r4,_DAR(r1)
···
 MMU_FTR_SECTION_ELSE
 	bl      unknown_exception
 ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_TYPE_RADIX)
-	b       ret_from_except
+	b       interrupt_return
 
+	GEN_KVM h_data_storage
+
+
+/**
+ * Interrupt 0xe20 - Hypervisor Instruction Storage Interrupt (HISI).
+ * This is a synchronous interrupt in response to an MMU fault caused by a
+ * guest instruction fetch, similar to HDSI.
+ */
+INT_DEFINE_BEGIN(h_instr_storage)
+	IVEC=0xe20
+	IHSRR=1
+	IKVM_REAL=1
+	IKVM_VIRT=1
+INT_DEFINE_END(h_instr_storage)
 
 EXC_REAL_BEGIN(h_instr_storage, 0xe20, 0x20)
-	INT_HANDLER h_instr_storage, 0xe20, ool=1, hsrr=EXC_HV, kvm=1
+	GEN_INT_ENTRY h_instr_storage, virt=0, ool=1
 EXC_REAL_END(h_instr_storage, 0xe20, 0x20)
 EXC_VIRT_BEGIN(h_instr_storage, 0x4e20, 0x20)
-	INT_HANDLER h_instr_storage, 0xe20, ool=1, virt=1, hsrr=EXC_HV, kvm=1
+	GEN_INT_ENTRY h_instr_storage, virt=1, ool=1
 EXC_VIRT_END(h_instr_storage, 0x4e20, 0x20)
-INT_KVM_HANDLER h_instr_storage, 0xe20, EXC_HV, PACA_EXGEN, 0
-EXC_COMMON(h_instr_storage_common, 0xe20, unknown_exception)
+EXC_COMMON_BEGIN(h_instr_storage_common)
+	GEN_COMMON h_instr_storage
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	unknown_exception
+	b	interrupt_return
 
+	GEN_KVM h_instr_storage
+
+
+/**
+ * Interrupt 0xe40 - Hypervisor Emulation Assistance Interrupt.
+ */
+INT_DEFINE_BEGIN(emulation_assist)
+	IVEC=0xe40
+	IHSRR=1
+	IKVM_REAL=1
+	IKVM_VIRT=1
+INT_DEFINE_END(emulation_assist)
 
 EXC_REAL_BEGIN(emulation_assist, 0xe40, 0x20)
-	INT_HANDLER emulation_assist, 0xe40, ool=1, hsrr=EXC_HV, kvm=1
+	GEN_INT_ENTRY emulation_assist, virt=0, ool=1
 EXC_REAL_END(emulation_assist, 0xe40, 0x20)
 EXC_VIRT_BEGIN(emulation_assist, 0x4e40, 0x20)
-	INT_HANDLER emulation_assist, 0xe40, ool=1, virt=1, hsrr=EXC_HV, kvm=1
+	GEN_INT_ENTRY emulation_assist, virt=1, ool=1
 EXC_VIRT_END(emulation_assist, 0x4e40, 0x20)
-INT_KVM_HANDLER emulation_assist, 0xe40, EXC_HV, PACA_EXGEN, 0
-EXC_COMMON(emulation_assist_common, 0xe40, emulation_assist_interrupt)
+EXC_COMMON_BEGIN(emulation_assist_common)
+	GEN_COMMON emulation_assist
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	emulation_assist_interrupt
+	REST_NVGPRS(r1) /* instruction emulation may change GPRs */
+	b	interrupt_return
+
+	GEN_KVM emulation_assist
 
 
-/*
- * hmi_exception trampoline is a special case. It jumps to hmi_exception_early
- * first, and then eventaully from there to the trampoline to get into virtual
- * mode.
+/**
+ * Interrupt 0xe60 - Hypervisor Maintenance Interrupt (HMI).
+ * This is an asynchronous interrupt caused by a Hypervisor Maintenance
+ * Exception. It is always taken in real mode but uses HSRR registers
+ * unlike SRESET and MCE.
+ *
+ * It is maskable in hardware by clearing MSR[EE], and partially soft-maskable
+ * with IRQS_DISABLED mask (i.e., local_irq_disable()).
+ *
+ * Handling:
+ * This is a special case, this is handled similarly to machine checks, with an
+ * initial real mode handler that is not soft-masked, which attempts to fix the
+ * problem. Then a regular handler which is soft-maskable and reports the
+ * problem.
+ *
+ * The emergency stack is used for the early real mode handler.
+ *
+ * XXX: unclear why MCE and HMI schemes could not be made common, e.g.,
+ * either use soft-masking for the MCE, or use irq_work for the HMI.
+ *
+ * KVM:
+ * Unlike MCE, this calls into KVM without calling the real mode handler
+ * first.
  */
+INT_DEFINE_BEGIN(hmi_exception_early)
+	IVEC=0xe60
+	IHSRR=1
+	IREALMODE_COMMON=1
+	ISTACK=0
+	IRECONCILE=0
+	IKUAP=0 /* We don't touch AMR here, we never go to virtual mode */
+	IKVM_REAL=1
+INT_DEFINE_END(hmi_exception_early)
+
+INT_DEFINE_BEGIN(hmi_exception)
+	IVEC=0xe60
+	IHSRR=1
+	IMASK=IRQS_DISABLED
+	IKVM_REAL=1
+INT_DEFINE_END(hmi_exception)
+
 EXC_REAL_BEGIN(hmi_exception, 0xe60, 0x20)
-	INT_HANDLER hmi_exception, 0xe60, ool=1, early=1, hsrr=EXC_HV, ri=0, kvm=1
+	GEN_INT_ENTRY hmi_exception_early, virt=0, ool=1
 EXC_REAL_END(hmi_exception, 0xe60, 0x20)
 EXC_VIRT_NONE(0x4e60, 0x20)
-INT_KVM_HANDLER hmi_exception, 0xe60, EXC_HV, PACA_EXGEN, 0
+
 EXC_COMMON_BEGIN(hmi_exception_early_common)
-	mtctr	r10			/* Restore ctr */
-	mfspr	r11,SPRN_HSRR0		/* Save HSRR0 */
-	mfspr	r12,SPRN_HSRR1		/* Save HSRR1 */
+	__GEN_REALMODE_COMMON_ENTRY hmi_exception_early
+
 	mr	r10,r1			/* Save r1 */
 	ld	r1,PACAEMERGSP(r13)	/* Use emergency stack for realmode */
 	subi	r1,r1,INT_FRAME_SIZE	/* alloc stack frame		*/
 
-	/* We don't touch AMR here, we never go to virtual mode */
-	INT_COMMON 0xe60, PACA_EXGEN, 0, 0, 0, 0, 0
+	__GEN_COMMON_BODY hmi_exception_early
 
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	hmi_exception_realmode
 	cmpdi	cr0,r3,0
 	bne	1f
 
-	EXCEPTION_RESTORE_REGS EXC_HV
+	EXCEPTION_RESTORE_REGS hsrr=1
 	HRFI_TO_USER_OR_KERNEL
 
 1:
···
 	 * Go to virtual mode and pull the HMI event information from
 	 * firmware.
 	 */
-	EXCEPTION_RESTORE_REGS EXC_HV
-	INT_HANDLER hmi_exception, 0xe60, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+	EXCEPTION_RESTORE_REGS hsrr=1
+	GEN_INT_ENTRY hmi_exception, virt=0
+
+	GEN_KVM hmi_exception_early
 
 EXC_COMMON_BEGIN(hmi_exception_common)
-	INT_COMMON 0xe60, PACA_EXGEN, 1, 1, 1, 0, 0
+	GEN_COMMON hmi_exception
 	FINISH_NAP
 	RUNLATCH_ON
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	handle_hmi_exception
-	b	ret_from_except
+	b	interrupt_return
 
+	GEN_KVM hmi_exception
+
+
+/**
+ * Interrupt 0xe80 - Directed Hypervisor Doorbell Interrupt.
+ * This is an asynchronous interrupt in response to a msgsnd doorbell.
+ * Similar to the 0xa00 doorbell but for host rather than guest.
+ */
+INT_DEFINE_BEGIN(h_doorbell)
+	IVEC=0xe80
+	IHSRR=1
+	IMASK=IRQS_DISABLED
+	IKVM_REAL=1
+	IKVM_VIRT=1
+INT_DEFINE_END(h_doorbell)
 
 EXC_REAL_BEGIN(h_doorbell, 0xe80, 0x20)
-	INT_HANDLER h_doorbell, 0xe80, ool=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+	GEN_INT_ENTRY h_doorbell, virt=0, ool=1
 EXC_REAL_END(h_doorbell, 0xe80, 0x20)
 EXC_VIRT_BEGIN(h_doorbell, 0x4e80, 0x20)
-	INT_HANDLER h_doorbell, 0xe80, ool=1, virt=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+	GEN_INT_ENTRY h_doorbell, virt=1, ool=1
 EXC_VIRT_END(h_doorbell, 0x4e80, 0x20)
-INT_KVM_HANDLER h_doorbell, 0xe80, EXC_HV, PACA_EXGEN, 0
+EXC_COMMON_BEGIN(h_doorbell_common)
+	GEN_COMMON h_doorbell
+	FINISH_NAP
+	RUNLATCH_ON
+	addi	r3,r1,STACK_FRAME_OVERHEAD
 #ifdef CONFIG_PPC_DOORBELL
-EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, doorbell_exception)
+	bl	doorbell_exception
 #else
-EXC_COMMON_ASYNC(h_doorbell_common, 0xe80, unknown_exception)
+	bl	unknown_exception
 #endif
+	b	interrupt_return
 
+	GEN_KVM h_doorbell
+
+
+/**
+ * Interrupt 0xea0 - Hypervisor Virtualization Interrupt.
+ * This is an asynchronous interrupt in response to an "external exception".
+ * Similar to 0x500 but for host only.
+ */
+INT_DEFINE_BEGIN(h_virt_irq)
+	IVEC=0xea0
+	IHSRR=1
+	IMASK=IRQS_DISABLED
+	IKVM_REAL=1
+	IKVM_VIRT=1
+INT_DEFINE_END(h_virt_irq)
 
 EXC_REAL_BEGIN(h_virt_irq, 0xea0, 0x20)
-	INT_HANDLER h_virt_irq, 0xea0, ool=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+	GEN_INT_ENTRY h_virt_irq, virt=0, ool=1
 EXC_REAL_END(h_virt_irq, 0xea0, 0x20)
 EXC_VIRT_BEGIN(h_virt_irq, 0x4ea0, 0x20)
-	INT_HANDLER h_virt_irq, 0xea0, ool=1, virt=1, hsrr=EXC_HV, bitmask=IRQS_DISABLED, kvm=1
+	GEN_INT_ENTRY h_virt_irq, virt=1, ool=1
 EXC_VIRT_END(h_virt_irq, 0x4ea0, 0x20)
-INT_KVM_HANDLER h_virt_irq, 0xea0, EXC_HV, PACA_EXGEN, 0
-EXC_COMMON_ASYNC(h_virt_irq_common, 0xea0, do_IRQ)
+EXC_COMMON_BEGIN(h_virt_irq_common)
+	GEN_COMMON h_virt_irq
+	FINISH_NAP
+	RUNLATCH_ON
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	do_IRQ
+	b	interrupt_return
+
+	GEN_KVM h_virt_irq
 
 
 EXC_REAL_NONE(0xec0, 0x20)
···
 EXC_VIRT_NONE(0x4ee0, 0x20)
 
 
+/*
+ * Interrupt 0xf00 - Performance Monitor Interrupt (PMI, PMU).
+ * This is an asynchronous interrupt in response to a PMU exception.
+ * It is maskable in hardware by clearing MSR[EE], and soft-maskable with
+ * IRQS_PMI_DISABLED mask (NOTE: NOT local_irq_disable()).
+ *
+ * Handling:
+ * This calls into the perf subsystem.
+ *
+ * Like the watchdog soft-nmi, it appears an NMI interrupt to Linux, in that it
+ * runs under local_irq_disable. However it may be soft-masked in
+ * powerpc-specific code.
+ *
+ * If soft masked, the masked handler will note the pending interrupt for
+ * replay, and clear MSR[EE] in the interrupted context.
+ */
+INT_DEFINE_BEGIN(performance_monitor)
+	IVEC=0xf00
+	IMASK=IRQS_PMI_DISABLED
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	IKVM_REAL=1
+#endif
+INT_DEFINE_END(performance_monitor)
+
 EXC_REAL_BEGIN(performance_monitor, 0xf00, 0x20)
-	INT_HANDLER performance_monitor, 0xf00, ool=1, bitmask=IRQS_PMI_DISABLED, kvm=1
+	GEN_INT_ENTRY performance_monitor, virt=0, ool=1
 EXC_REAL_END(performance_monitor, 0xf00, 0x20)
 EXC_VIRT_BEGIN(performance_monitor, 0x4f00, 0x20)
-	INT_HANDLER performance_monitor, 0xf00, ool=1, virt=1, bitmask=IRQS_PMI_DISABLED
+	GEN_INT_ENTRY performance_monitor, virt=1, ool=1
 EXC_VIRT_END(performance_monitor, 0x4f00, 0x20)
-INT_KVM_HANDLER performance_monitor, 0xf00, EXC_STD, PACA_EXGEN, 0
-EXC_COMMON_ASYNC(performance_monitor_common, 0xf00, performance_monitor_exception)
+EXC_COMMON_BEGIN(performance_monitor_common)
+	GEN_COMMON performance_monitor
+	FINISH_NAP
+	RUNLATCH_ON
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	performance_monitor_exception
+	b	interrupt_return
 
+	GEN_KVM performance_monitor
+
+
+/**
+ * Interrupt 0xf20 - Vector Unavailable Interrupt.
+ * This is a synchronous interrupt in response to
+ * executing a vector (or altivec) instruction with MSR[VEC]=0.
+ * Similar to FP unavailable.
+ */
+INT_DEFINE_BEGIN(altivec_unavailable)
+	IVEC=0xf20
+	IRECONCILE=0
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	IKVM_REAL=1
+#endif
+INT_DEFINE_END(altivec_unavailable)
 
 EXC_REAL_BEGIN(altivec_unavailable, 0xf20, 0x20)
-	INT_HANDLER altivec_unavailable, 0xf20, ool=1, kvm=1
+	GEN_INT_ENTRY altivec_unavailable, virt=0, ool=1
 EXC_REAL_END(altivec_unavailable, 0xf20, 0x20)
 EXC_VIRT_BEGIN(altivec_unavailable, 0x4f20, 0x20)
-	INT_HANDLER altivec_unavailable, 0xf20, ool=1, virt=1
+	GEN_INT_ENTRY altivec_unavailable, virt=1, ool=1
 EXC_VIRT_END(altivec_unavailable, 0x4f20, 0x20)
-INT_KVM_HANDLER altivec_unavailable, 0xf20, EXC_STD, PACA_EXGEN, 0
 EXC_COMMON_BEGIN(altivec_unavailable_common)
-	INT_COMMON 0xf20, PACA_EXGEN, 1, 1, 0, 0, 0
+	GEN_COMMON altivec_unavailable
 #ifdef CONFIG_ALTIVEC
 BEGIN_FTR_SECTION
 	beq	1f
···
   END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69)
 #endif
 	bl	load_up_altivec
-	b	fast_exception_return
+	b	fast_interrupt_return
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 2:	/* User process was in a transaction */
-	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	altivec_unavailable_tm
-	b	ret_from_except
+	b	interrupt_return
 #endif
 1:
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
-	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	altivec_unavailable_exception
-	b	ret_from_except
+	b	interrupt_return
 
+	GEN_KVM altivec_unavailable
+
+
+/**
+ * Interrupt 0xf40 - VSX Unavailable Interrupt.
+ * This is a synchronous interrupt in response to
+ * executing a VSX instruction with MSR[VSX]=0.
+ * Similar to FP unavailable.
+ */
+INT_DEFINE_BEGIN(vsx_unavailable)
+	IVEC=0xf40
+	IRECONCILE=0
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	IKVM_REAL=1
+#endif
+INT_DEFINE_END(vsx_unavailable)
 
 EXC_REAL_BEGIN(vsx_unavailable, 0xf40, 0x20)
-	INT_HANDLER vsx_unavailable, 0xf40, ool=1, kvm=1
+	GEN_INT_ENTRY vsx_unavailable, virt=0, ool=1
 EXC_REAL_END(vsx_unavailable, 0xf40, 0x20)
 EXC_VIRT_BEGIN(vsx_unavailable, 0x4f40, 0x20)
-	INT_HANDLER vsx_unavailable, 0xf40, ool=1, virt=1
+	GEN_INT_ENTRY vsx_unavailable, virt=1, ool=1
 EXC_VIRT_END(vsx_unavailable, 0x4f40, 0x20)
-INT_KVM_HANDLER vsx_unavailable, 0xf40, EXC_STD, PACA_EXGEN, 0
 EXC_COMMON_BEGIN(vsx_unavailable_common)
-	INT_COMMON 0xf40, PACA_EXGEN, 1, 1, 0, 0, 0
+	GEN_COMMON vsx_unavailable
 #ifdef CONFIG_VSX
 BEGIN_FTR_SECTION
 	beq	1f
···
 	b	load_up_vsx
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 2:	/* User process was in a transaction */
-	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	vsx_unavailable_tm
-	b	ret_from_except
+	b	interrupt_return
 #endif
 1:
 END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 #endif
-	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	vsx_unavailable_exception
-	b	ret_from_except
+	b	interrupt_return
 
+	GEN_KVM vsx_unavailable
+
+
+/**
+ * Interrupt 0xf60 - Facility Unavailable Interrupt.
+ * This is a synchronous interrupt in response to
+ * executing an instruction without access to the facility that can be
+ * resolved by the OS (e.g., FSCR, MSR).
+ * Similar to FP unavailable.
+ */
+INT_DEFINE_BEGIN(facility_unavailable)
+	IVEC=0xf60
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	IKVM_REAL=1
+#endif
+INT_DEFINE_END(facility_unavailable)
 
 EXC_REAL_BEGIN(facility_unavailable, 0xf60, 0x20)
-	INT_HANDLER facility_unavailable, 0xf60, ool=1, kvm=1
+	GEN_INT_ENTRY facility_unavailable, virt=0, ool=1
 EXC_REAL_END(facility_unavailable, 0xf60, 0x20)
 EXC_VIRT_BEGIN(facility_unavailable, 0x4f60, 0x20)
-	INT_HANDLER facility_unavailable, 0xf60, ool=1, virt=1
+	GEN_INT_ENTRY facility_unavailable, virt=1, ool=1
 EXC_VIRT_END(facility_unavailable, 0x4f60, 0x20)
-INT_KVM_HANDLER facility_unavailable, 0xf60, EXC_STD, PACA_EXGEN, 0
-EXC_COMMON(facility_unavailable_common, 0xf60, facility_unavailable_exception)
+EXC_COMMON_BEGIN(facility_unavailable_common)
+	GEN_COMMON facility_unavailable
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	facility_unavailable_exception
+	b	interrupt_return
 
+	GEN_KVM facility_unavailable
+
+
+/**
+ * Interrupt 0xf60 - Hypervisor Facility Unavailable Interrupt.
+ * This is a synchronous interrupt in response to
+ * executing an instruction without access to the facility that can only
+ * be resolved in HV mode (e.g., HFSCR).
+ * Similar to FP unavailable.
+ */
+INT_DEFINE_BEGIN(h_facility_unavailable)
+	IVEC=0xf80
+	IHSRR=1
+	IKVM_REAL=1
+	IKVM_VIRT=1
+INT_DEFINE_END(h_facility_unavailable)
 
 EXC_REAL_BEGIN(h_facility_unavailable, 0xf80, 0x20)
-	INT_HANDLER h_facility_unavailable, 0xf80, ool=1, hsrr=EXC_HV, kvm=1
+	GEN_INT_ENTRY h_facility_unavailable, virt=0, ool=1
 EXC_REAL_END(h_facility_unavailable, 0xf80, 0x20)
 EXC_VIRT_BEGIN(h_facility_unavailable, 0x4f80, 0x20)
-	INT_HANDLER h_facility_unavailable, 0xf80, ool=1, virt=1, hsrr=EXC_HV, kvm=1
+	GEN_INT_ENTRY h_facility_unavailable, virt=1, ool=1
 EXC_VIRT_END(h_facility_unavailable, 0x4f80, 0x20)
-INT_KVM_HANDLER h_facility_unavailable, 0xf80, EXC_HV, PACA_EXGEN, 0
-EXC_COMMON(h_facility_unavailable_common, 0xf80, facility_unavailable_exception)
+EXC_COMMON_BEGIN(h_facility_unavailable_common)
+	GEN_COMMON h_facility_unavailable
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	facility_unavailable_exception
+	b	interrupt_return
+
+	GEN_KVM h_facility_unavailable
 
 
 EXC_REAL_NONE(0xfa0, 0x20)
···
 EXC_VIRT_NONE(0x5100, 0x100)
 
 #ifdef CONFIG_CBE_RAS
+INT_DEFINE_BEGIN(cbe_system_error)
+	IVEC=0x1200
+	IHSRR=1
+	IKVM_SKIP=1
+	IKVM_REAL=1
+INT_DEFINE_END(cbe_system_error)
+
 EXC_REAL_BEGIN(cbe_system_error, 0x1200, 0x100)
-	INT_HANDLER cbe_system_error, 0x1200, ool=1, hsrr=EXC_HV, kvm=1
+	GEN_INT_ENTRY cbe_system_error, virt=0
 EXC_REAL_END(cbe_system_error, 0x1200, 0x100)
 EXC_VIRT_NONE(0x5200, 0x100)
-INT_KVM_HANDLER cbe_system_error, 0x1200, EXC_HV, PACA_EXGEN, 1
-EXC_COMMON(cbe_system_error_common, 0x1200, cbe_system_error_exception)
+EXC_COMMON_BEGIN(cbe_system_error_common)
+	GEN_COMMON cbe_system_error
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	cbe_system_error_exception
+	b	interrupt_return
+
+	GEN_KVM cbe_system_error
+
 #else /* CONFIG_CBE_RAS */
 EXC_REAL_NONE(0x1200, 0x100)
 EXC_VIRT_NONE(0x5200, 0x100)
 #endif
 
 
+INT_DEFINE_BEGIN(instruction_breakpoint)
+	IVEC=0x1300
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	IKVM_SKIP=1
+	IKVM_REAL=1
+#endif
+INT_DEFINE_END(instruction_breakpoint)
+
 EXC_REAL_BEGIN(instruction_breakpoint, 0x1300, 0x100)
-	INT_HANDLER instruction_breakpoint, 0x1300, kvm=1
+	GEN_INT_ENTRY instruction_breakpoint, virt=0
 EXC_REAL_END(instruction_breakpoint, 0x1300, 0x100)
 EXC_VIRT_BEGIN(instruction_breakpoint, 0x5300, 0x100)
-	INT_HANDLER instruction_breakpoint, 0x1300, virt=1
+	GEN_INT_ENTRY instruction_breakpoint, virt=1
 EXC_VIRT_END(instruction_breakpoint, 0x5300, 0x100)
-INT_KVM_HANDLER instruction_breakpoint, 0x1300, EXC_STD, PACA_EXGEN, 1
-EXC_COMMON(instruction_breakpoint_common, 0x1300, instruction_breakpoint_exception)
+EXC_COMMON_BEGIN(instruction_breakpoint_common)
+	GEN_COMMON instruction_breakpoint
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	instruction_breakpoint_exception
+	b	interrupt_return
+
+	GEN_KVM instruction_breakpoint
 
 
 EXC_REAL_NONE(0x1400, 0x100)
 EXC_VIRT_NONE(0x5400, 0x100)
 
-EXC_REAL_BEGIN(denorm_exception_hv, 0x1500, 0x100)
-	INT_HANDLER denorm_exception_hv, 0x1500, early=2, hsrr=EXC_HV
+/**
+ * Interrupt 0x1500 - Soft Patch Interrupt
+ *
+ * Handling:
+ * This is an implementation specific interrupt which can be used for a
+ * range of exceptions.
+ *
+ * This interrupt handler is unique in that it runs the denormal assist
+ * code even for guests (and even in guest context) without going to KVM,
+ * for speed. POWER9 does not raise denorm exceptions, so this special case
+ * could be phased out in future to reduce special cases.
+ */
+INT_DEFINE_BEGIN(denorm_exception)
+	IVEC=0x1500
+	IHSRR=1
+	IBRANCH_COMMON=0
+	IKVM_REAL=1
+INT_DEFINE_END(denorm_exception)
+
+EXC_REAL_BEGIN(denorm_exception, 0x1500, 0x100)
+	GEN_INT_ENTRY denorm_exception, virt=0
 #ifdef CONFIG_PPC_DENORMALISATION
-	mfspr	r10,SPRN_HSRR1
-	andis.	r10,r10,(HSRR1_DENORM)@h /* denorm? */
+	andis.	r10,r12,(HSRR1_DENORM)@h /* denorm? */
 	bne+	denorm_assist
 #endif
-	KVMTEST denorm_exception_hv, EXC_HV 0x1500
-	INT_SAVE_SRR_AND_JUMP denorm_common, EXC_HV, 1
-EXC_REAL_END(denorm_exception_hv, 0x1500, 0x100)
-
+	GEN_BRANCH_TO_COMMON denorm_exception, virt=0
+EXC_REAL_END(denorm_exception, 0x1500, 0x100)
 #ifdef CONFIG_PPC_DENORMALISATION
 EXC_VIRT_BEGIN(denorm_exception, 0x5500, 0x100)
-	INT_HANDLER denorm_exception, 0x1500, 0, 2, 1, EXC_HV, PACA_EXGEN, 1, 0, 0, 0, 0
-	mfspr	r10,SPRN_HSRR1
-	andis.	r10,r10,(HSRR1_DENORM)@h /* denorm? */
+	GEN_INT_ENTRY denorm_exception, virt=1
+	andis.	r10,r12,(HSRR1_DENORM)@h /* denorm? */
 	bne+	denorm_assist
-	INT_VIRT_SAVE_SRR_AND_JUMP denorm_common, EXC_HV
+	GEN_BRANCH_TO_COMMON denorm_exception, virt=1
 EXC_VIRT_END(denorm_exception, 0x5500, 0x100)
 #else
 EXC_VIRT_NONE(0x5500, 0x100)
 #endif
-
-INT_KVM_HANDLER denorm_exception_hv, 0x1500, EXC_HV, PACA_EXGEN, 0
 
 #ifdef CONFIG_PPC_DENORMALISATION
 TRAMP_REAL_BEGIN(denorm_assist)
···
 	mtspr	SPRN_HSRR0,r11
 	mtcrf	0x80,r9
 	ld	r9,PACA_EXGEN+EX_R9(r13)
-	RESTORE_PPR_PACA(PACA_EXGEN, r10)
+BEGIN_FTR_SECTION
+	ld	r10,PACA_EXGEN+EX_PPR(r13)
+	mtspr	SPRN_PPR,r10
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 BEGIN_FTR_SECTION
 	ld	r10,PACA_EXGEN+EX_CFAR(r13)
 	mtspr	SPRN_CFAR,r10
···
 	b	.
 #endif
 
-EXC_COMMON(denorm_common, 0x1500, unknown_exception)
+EXC_COMMON_BEGIN(denorm_exception_common)
+	GEN_COMMON denorm_exception
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	unknown_exception
+	b	interrupt_return
+
+	GEN_KVM denorm_exception
 
 
 #ifdef CONFIG_CBE_RAS
+INT_DEFINE_BEGIN(cbe_maintenance)
+	IVEC=0x1600
+	IHSRR=1
+	IKVM_SKIP=1
+	IKVM_REAL=1
+INT_DEFINE_END(cbe_maintenance)
+
 EXC_REAL_BEGIN(cbe_maintenance, 0x1600, 0x100)
-	INT_HANDLER cbe_maintenance, 0x1600, ool=1, hsrr=EXC_HV, kvm=1
+	GEN_INT_ENTRY cbe_maintenance, virt=0
 EXC_REAL_END(cbe_maintenance, 0x1600, 0x100)
 EXC_VIRT_NONE(0x5600, 0x100)
-INT_KVM_HANDLER cbe_maintenance, 0x1600, EXC_HV, PACA_EXGEN, 1
-EXC_COMMON(cbe_maintenance_common, 0x1600, cbe_maintenance_exception)
+EXC_COMMON_BEGIN(cbe_maintenance_common)
+	GEN_COMMON cbe_maintenance
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	cbe_maintenance_exception
+	b	interrupt_return
+
+	GEN_KVM cbe_maintenance
+
 #else /* CONFIG_CBE_RAS */
 EXC_REAL_NONE(0x1600, 0x100)
 EXC_VIRT_NONE(0x5600, 0x100)
 #endif
 
 
+INT_DEFINE_BEGIN(altivec_assist)
+	IVEC=0x1700
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	IKVM_REAL=1
+#endif
+INT_DEFINE_END(altivec_assist)
+
 EXC_REAL_BEGIN(altivec_assist, 0x1700, 0x100)
-	INT_HANDLER altivec_assist, 0x1700, kvm=1
+	GEN_INT_ENTRY altivec_assist, virt=0
 EXC_REAL_END(altivec_assist, 0x1700, 0x100)
 EXC_VIRT_BEGIN(altivec_assist, 0x5700, 0x100)
-	INT_HANDLER altivec_assist, 0x1700, virt=1
+	GEN_INT_ENTRY altivec_assist, virt=1
 EXC_VIRT_END(altivec_assist, 0x5700, 0x100)
-INT_KVM_HANDLER altivec_assist, 0x1700, EXC_STD, PACA_EXGEN, 0
+EXC_COMMON_BEGIN(altivec_assist_common)
+	GEN_COMMON altivec_assist
+	addi	r3,r1,STACK_FRAME_OVERHEAD
 #ifdef CONFIG_ALTIVEC
-EXC_COMMON(altivec_assist_common, 0x1700, altivec_assist_exception)
+	bl	altivec_assist_exception
+	REST_NVGPRS(r1) /* instruction emulation may change GPRs */
 #else
-EXC_COMMON(altivec_assist_common, 0x1700, unknown_exception)
+	bl	unknown_exception
 #endif
+	b	interrupt_return
+
+	GEN_KVM altivec_assist
 
 
 #ifdef CONFIG_CBE_RAS
+INT_DEFINE_BEGIN(cbe_thermal)
+	IVEC=0x1800
+	IHSRR=1
+	IKVM_SKIP=1
+	IKVM_REAL=1
+INT_DEFINE_END(cbe_thermal)
+
 EXC_REAL_BEGIN(cbe_thermal, 0x1800, 0x100)
-	INT_HANDLER cbe_thermal, 0x1800, ool=1, hsrr=EXC_HV, kvm=1
+	GEN_INT_ENTRY cbe_thermal, virt=0
 EXC_REAL_END(cbe_thermal, 0x1800, 0x100)
 EXC_VIRT_NONE(0x5800, 0x100)
-INT_KVM_HANDLER cbe_thermal, 0x1800, EXC_HV, PACA_EXGEN, 1
-EXC_COMMON(cbe_thermal_common, 0x1800, cbe_thermal_exception)
+EXC_COMMON_BEGIN(cbe_thermal_common)
+	GEN_COMMON cbe_thermal
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	cbe_thermal_exception
+	b	interrupt_return
+
+	GEN_KVM cbe_thermal
+
 #else /* CONFIG_CBE_RAS */
 EXC_REAL_NONE(0x1800, 0x100)
 EXC_VIRT_NONE(0x5800, 0x100)
···
 
 #ifdef CONFIG_PPC_WATCHDOG
 
-#define MASKED_DEC_HANDLER_LABEL 3f
-
-#define MASKED_DEC_HANDLER(_H)				\
-3: /* soft-nmi */					\
-	std	r12,PACA_EXGEN+EX_R12(r13);		\
-	GET_SCRATCH0(r10);				\
-	std	r10,PACA_EXGEN+EX_R13(r13);		\
-	INT_SAVE_SRR_AND_JUMP soft_nmi_common, _H, 1
+INT_DEFINE_BEGIN(soft_nmi)
+	IVEC=0x900
+	ISTACK=0
+	IRECONCILE=0	/* Soft-NMI may fire under local_irq_disable */
+INT_DEFINE_END(soft_nmi)
 
 /*
  * Branch to soft_nmi_interrupt using the emergency stack. The emergency
···
  * and run it entirely with interrupts hard disabled.
  */
 EXC_COMMON_BEGIN(soft_nmi_common)
+	mfspr	r11,SPRN_SRR0
 	mr	r10,r1
 	ld	r1,PACAEMERGSP(r13)
 	subi	r1,r1,INT_FRAME_SIZE
-	INT_COMMON 0x900, PACA_EXGEN, 0, 1, 1, 0, 0
-	bl	save_nvgprs
+	__GEN_COMMON_BODY soft_nmi
+
+	/*
+	 * Set IRQS_ALL_DISABLED and save PACAIRQHAPPENED (see
+	 * system_reset_common)
+	 */
+	li	r10,IRQS_ALL_DISABLED
+	stb	r10,PACAIRQSOFTMASK(r13)
+	lbz	r10,PACAIRQHAPPENED(r13)
+	std	r10,_DAR(r1)
+	ori	r10,r10,PACA_IRQ_HARD_DIS
+	stb	r10,PACAIRQHAPPENED(r13)
+
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	soft_nmi_interrupt
-	b	ret_from_except
 
-#else /* CONFIG_PPC_WATCHDOG */
-#define MASKED_DEC_HANDLER_LABEL 2f /* normal return */
-#define MASKED_DEC_HANDLER(_H)
+	/* Clear MSR_RI before setting SRR0 and SRR1. */
+	li	r9,0
+	mtmsrd	r9,1
+
+	/*
+	 * Restore soft mask settings.
+	 */
+	ld	r10,_DAR(r1)
+	stb	r10,PACAIRQHAPPENED(r13)
+	ld	r10,SOFTE(r1)
+	stb	r10,PACAIRQSOFTMASK(r13)
+
+	kuap_restore_amr r10
+	EXCEPTION_RESTORE_REGS hsrr=0
+	RFI_TO_KERNEL
+
 #endif /* CONFIG_PPC_WATCHDOG */
 
 /*
···
  * - Else it is one of PACA_IRQ_MUST_HARD_MASK, so hard disable and return.
  * This is called with r10 containing the value to OR to the paca field.
  */
-.macro MASKED_INTERRUPT hsrr
+.macro MASKED_INTERRUPT hsrr=0
 	.if \hsrr
 masked_Hinterrupt:
 	.else
 masked_interrupt:
 	.endif
-	std	r11,PACA_EXGEN+EX_R11(r13)
 	lbz	r11,PACAIRQHAPPENED(r13)
 	or	r11,r11,r10
 	stb	r11,PACAIRQHAPPENED(r13)
···
 	lis	r10,0x7fff
 	ori	r10,r10,0xffff
 	mtspr	SPRN_DEC,r10
-	b	MASKED_DEC_HANDLER_LABEL
+#ifdef CONFIG_PPC_WATCHDOG
+	b	soft_nmi_common
+#else
+	b	2f
+#endif
 1:	andi.	r10,r10,PACA_IRQ_MUST_HARD_MASK
 	beq	2f
+	xori	r12,r12,MSR_EE	/* clear MSR_EE */
 	.if \hsrr
-	mfspr	r10,SPRN_HSRR1
-	xori	r10,r10,MSR_EE	/* clear MSR_EE */
-	mtspr	SPRN_HSRR1,r10
+	mtspr	SPRN_HSRR1,r12
 	.else
-	mfspr	r10,SPRN_SRR1
-	xori	r10,r10,MSR_EE	/* clear MSR_EE */
-	mtspr	SPRN_SRR1,r10
+	mtspr	SPRN_SRR1,r12
 	.endif
 	ori	r11,r11,PACA_IRQ_HARD_DIS
 	stb	r11,PACAIRQHAPPENED(r13)
 2:	/* done */
+	ld	r10,PACA_EXGEN+EX_CTR(r13)
+	mtctr	r10
 	mtcrf	0x80,r9
 	std	r1,PACAR1(r13)
 	ld	r9,PACA_EXGEN+EX_R9(r13)
 	ld	r10,PACA_EXGEN+EX_R10(r13)
 	ld	r11,PACA_EXGEN+EX_R11(r13)
+	ld	r12,PACA_EXGEN+EX_R12(r13)
 	/* returns to kernel where r13 must be set up, so don't restore it */
 	.if \hsrr
 	HRFI_TO_KERNEL
···
 	RFI_TO_KERNEL
 	.endif
 	b	.
-	MASKED_DEC_HANDLER(\hsrr\())
 .endm
 
 TRAMP_REAL_BEGIN(stf_barrier_fallback)
···
 	GET_SCRATCH0(r13);
 	hrfid
 
-/*
- * Real mode exceptions actually use this too, but alternate
- * instruction code patches (which end up in the common .text area)
- * cannot reach these if they are put there.
- */
-USE_FIXED_SECTION(virt_trampolines)
-	MASKED_INTERRUPT EXC_STD
-	MASKED_INTERRUPT EXC_HV
+USE_TEXT_SECTION()
+	MASKED_INTERRUPT
+	MASKED_INTERRUPT hsrr=1
 
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-TRAMP_REAL_BEGIN(kvmppc_skip_interrupt)
+kvmppc_skip_interrupt:
 	/*
 	 * Here all GPRs are unchanged from when the interrupt happened
 	 * except for r13, which is saved in SPRG_SCRATCH0.
···
 	RFI_TO_KERNEL
 	b	.
 
-TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt)
+kvmppc_skip_Hinterrupt:
 	/*
 	 * Here all GPRs are unchanged from when the interrupt happened
 	 * except for r13, which is saved in SPRG_SCRATCH0.
···
 	HRFI_TO_KERNEL
 	b	.
 #endif
-
-/*
- * Ensure that any handlers that get invoked from the exception prologs
- * above are below the first 64KB (0x10000) of the kernel image because
- * the prologs assemble the addresses of these handlers using the
- * LOAD_HANDLER macro, which uses an ori instruction.
- */
-
-/*** Common interrupt handlers ***/
-
 
 	/*
 	 * Relocation-on interrupts: A subset of the interrupts can be delivered
···
         cmpdi	r3,0			/* see if __hash_page succeeded */
 
 	/* Success */
-	beq	fast_exc_return_irq	/* Return from exception on success */
+	beq	interrupt_return	/* Return from exception on success */
 
 	/* Error */
 	blt-	13f
···
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_page_fault
 	cmpdi	r3,0
-	beq+	ret_from_except_lite
-	bl	save_nvgprs
+	beq+	interrupt_return
 	mr	r5,r3
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	ld	r4,_DAR(r1)
 	bl	bad_page_fault
-	b	ret_from_except
+	b	interrupt_return
 
 /* We have a data breakpoint exception - handle it */
 handle_dabr_fault:
-	bl	save_nvgprs
 	ld      r4,_DAR(r1)
 	ld      r5,_DSISR(r1)
 	addi    r3,r1,STACK_FRAME_OVERHEAD
 	bl      do_break
 	/*
 	 * do_break() may have changed the NV GPRS while handling a breakpoint.
-	 * If so, we need to restore them with their updated values. Don't use
-	 * ret_from_except_lite here.
+	 * If so, we need to restore them with their updated values.
 	 */
-	b       ret_from_except
+	REST_NVGPRS(r1)
+	b       interrupt_return
 
 
 #ifdef CONFIG_PPC_BOOK3S_64
 /* We have a page fault that hash_page could handle but HV refused
  * the PTE insertion
  */
-13:	bl	save_nvgprs
-	mr	r5,r3
+13:	mr	r5,r3
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	ld	r4,_DAR(r1)
 	bl	low_hash_fault
-	b	ret_from_except
+	b	interrupt_return
 #endif
 
 /*
···
  * were soft-disabled.  We want to invoke the exception handler for
  * the access, or panic if there isn't a handler.
  */
-77:	bl	save_nvgprs
-	addi	r3,r1,STACK_FRAME_OVERHEAD
+77:	addi	r3,r1,STACK_FRAME_OVERHEAD
 	li	r5,SIGSEGV
 	bl	bad_page_fault
-	b	ret_from_except
+	b	interrupt_return
 
 /*
  * When doorbell is triggered from system reset wakeup, the message is
···
 h_doorbell_common_msgclr:
 	LOAD_REG_IMMEDIATE(r3, PPC_DBELL_MSGTYPE << (63-36))
 	PPC_MSGCLR(3)
-	b 	h_doorbell_common
+	b 	h_doorbell_common_virt
 
 doorbell_super_common_msgclr:
 	LOAD_REG_IMMEDIATE(r3, PPC_DBELL_MSGTYPE << (63-36))
 	PPC_MSGCLRP(3)
-	b 	doorbell_super_common
-
-/*
- * Called from arch_local_irq_enable when an interrupt needs
- * to be resent. r3 contains 0x500, 0x900, 0xa00 or 0xe80 to indicate
- * which kind of interrupt. MSR:EE is already off. We generate a
- * stackframe like if a real interrupt had happened.
- *
- * Note: While MSR:EE is off, we need to make sure that _MSR
- * in the generated frame has EE set to 1 or the exception
- * handler will not properly re-enable them.
- *
- * Note that we don't specify LR as the NIP (return address) for
- * the interrupt because that would unbalance the return branch
- * predictor.
- */
-_GLOBAL(__replay_interrupt)
-	/* We are going to jump to the exception common code which
-	 * will retrieve various register values from the PACA which
-	 * we don't give a damn about, so we don't bother storing them.
-	 */
-	mfmsr	r12
-	LOAD_REG_ADDR(r11, replay_interrupt_return)
-	mfcr	r9
-	ori	r12,r12,MSR_EE
-	cmpwi	r3,0x900
-	beq	decrementer_common
-	cmpwi	r3,0x500
-BEGIN_FTR_SECTION
-	beq	h_virt_irq_common
-FTR_SECTION_ELSE
-	beq	hardware_interrupt_common
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_300)
-	cmpwi	r3,0xf00
-	beq	performance_monitor_common
-BEGIN_FTR_SECTION
-	cmpwi	r3,0xa00
-	beq	h_doorbell_common_msgclr
-	cmpwi	r3,0xe60
-	beq	hmi_exception_common
-FTR_SECTION_ELSE
-	cmpwi	r3,0xa00
-	beq	doorbell_super_common_msgclr
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
-replay_interrupt_return:
-	blr
-
-_ASM_NOKPROBE_SYMBOL(__replay_interrupt)
+	b 	doorbell_super_common_virt

arch/powerpc/kernel/fadump.c

···
 
 static void __init fadump_reserve_crash_area(u64 base);
 
+struct kobject *fadump_kobj;
+
 #ifndef CONFIG_PRESERVE_FA_DUMP
 static DEFINE_MUTEX(fadump_mutex);
 struct fadump_mrange_info crash_mrange_info = { "crash", NULL, 0, 0, 0 };
···
 	fw_dump.ops->fadump_init_mem_struct(&fw_dump);
 }
 
-static ssize_t fadump_release_memory_store(struct kobject *kobj,
-					struct kobj_attribute *attr,
-					const char *buf, size_t count)
+static ssize_t release_mem_store(struct kobject *kobj,
+				 struct kobj_attribute *attr,
+				 const char *buf, size_t count)
 {
 	int input = -1;
 
···
 	return count;
 }
 
-static ssize_t fadump_enabled_show(struct kobject *kobj,
-					struct kobj_attribute *attr,
-					char *buf)
+/* Release the reserved memory and disable the FADump */
+static void unregister_fadump(void)
+{
+	fadump_cleanup();
+	fadump_release_memory(fw_dump.reserve_dump_area_start,
+			      fw_dump.reserve_dump_area_size);
+	fw_dump.fadump_enabled = 0;
+	kobject_put(fadump_kobj);
+}
+
+static ssize_t enabled_show(struct kobject *kobj,
+			    struct kobj_attribute *attr,
+			    char *buf)
 {
 	return sprintf(buf, "%d\n", fw_dump.fadump_enabled);
 }
 
-static ssize_t fadump_register_show(struct kobject *kobj,
-					struct kobj_attribute *attr,
-					char *buf)
+static ssize_t mem_reserved_show(struct kobject *kobj,
+				 struct kobj_attribute *attr,
+				 char *buf)
+{
+	return sprintf(buf, "%ld\n", fw_dump.reserve_dump_area_size);
+}
+
+static ssize_t registered_show(struct kobject *kobj,
+			       struct kobj_attribute *attr,
+			       char *buf)
 {
 	return sprintf(buf, "%d\n", fw_dump.dump_registered);
 }
 
-static ssize_t fadump_register_store(struct kobject *kobj,
-					struct kobj_attribute *attr,
-					const char *buf, size_t count)
+static ssize_t registered_store(struct kobject *kobj,
+				struct kobj_attribute *attr,
+				const char *buf, size_t count)
 {
 	int ret = 0;
 	int input = -1;
···
 	return 0;
 }
 
-static struct kobj_attribute fadump_release_attr = __ATTR(fadump_release_mem,
-						0200, NULL,
-						fadump_release_memory_store);
-static struct kobj_attribute fadump_attr = __ATTR(fadump_enabled,
-						0444, fadump_enabled_show,
-						NULL);
-static struct kobj_attribute fadump_register_attr = __ATTR(fadump_registered,
-						0644, fadump_register_show,
-						fadump_register_store);
+static struct kobj_attribute release_attr = __ATTR_WO(release_mem);
+static struct kobj_attribute enable_attr = __ATTR_RO(enabled);
+static struct kobj_attribute register_attr = __ATTR_RW(registered);
+static struct kobj_attribute mem_reserved_attr = __ATTR_RO(mem_reserved);
+
+static struct attribute *fadump_attrs[] = {
+	&enable_attr.attr,
+	&register_attr.attr,
+	&mem_reserved_attr.attr,
+	NULL,
+};
+
+ATTRIBUTE_GROUPS(fadump);
 
 DEFINE_SHOW_ATTRIBUTE(fadump_region);
 
 static void fadump_init_files(void)
 {
-	struct dentry *debugfs_file;
 	int rc = 0;
 
-	rc = sysfs_create_file(kernel_kobj, &fadump_attr.attr);
-	if (rc)
-		printk(KERN_ERR "fadump: unable to create sysfs file"
-			" fadump_enabled (%d)\n", rc);
+	fadump_kobj = kobject_create_and_add("fadump", kernel_kobj);
+	if (!fadump_kobj) {
+		pr_err("failed to create fadump kobject\n");
+		return;
+	}
 
-	rc = sysfs_create_file(kernel_kobj, &fadump_register_attr.attr);
-	if (rc)
-		printk(KERN_ERR "fadump: unable to create sysfs file"
-			" fadump_registered (%d)\n", rc);
-
-	debugfs_file = debugfs_create_file("fadump_region", 0444,
-					powerpc_debugfs_root, NULL,
-					&fadump_region_fops);
-	if (!debugfs_file)
-		printk(KERN_ERR "fadump: unable to create debugfs file"
-				" fadump_region\n");
+	debugfs_create_file("fadump_region", 0444, powerpc_debugfs_root, NULL,
+			    &fadump_region_fops);
 
 	if (fw_dump.dump_active) {
-		rc = sysfs_create_file(kernel_kobj, &fadump_release_attr.attr);
+		rc = sysfs_create_file(fadump_kobj, &release_attr.attr);
 		if (rc)
-			printk(KERN_ERR "fadump: unable to create sysfs file"
-				" fadump_release_mem (%d)\n", rc);
+			pr_err("unable to create release_mem sysfs file (%d)\n",
+			       rc);
+	}
+
+	rc = sysfs_create_groups(fadump_kobj, fadump_groups);
+	if (rc) {
+		pr_err("sysfs group creation failed (%d), unregistering FADump",
+		       rc);
+		unregister_fadump();
+		return;
+	}
+
+	/*
+	 * The FADump sysfs are moved from kernel_kobj to fadump_kobj need to
+	 * create symlink at old location to maintain backward compatibility.
+	 *
+	 *      - fadump_enabled -> fadump/enabled
+	 *      - fadump_registered -> fadump/registered
+	 *      - fadump_release_mem -> fadump/release_mem
+	 */
+	rc = compat_only_sysfs_link_entry_to_kobj(kernel_kobj, fadump_kobj,
+						  "enabled", "fadump_enabled");
+	if (rc) {
+		pr_err("unable to create fadump_enabled symlink (%d)", rc);
+		return;
+	}
+
+	rc = compat_only_sysfs_link_entry_to_kobj(kernel_kobj, fadump_kobj,
+						  "registered",
+						  "fadump_registered");
+	if (rc) {
+		pr_err("unable to create fadump_registered symlink (%d)", rc);
+		sysfs_remove_link(kernel_kobj, "fadump_enabled");
+		return;
+	}
+
+	if (fw_dump.dump_active) {
+		rc = compat_only_sysfs_link_entry_to_kobj(kernel_kobj,
+							  fadump_kobj,
+							  "release_mem",
+							  "fadump_release_mem");
+		if (rc)
+			pr_err("unable to create fadump_release_mem symlink (%d)",
+			       rc);
 	}
 	return;
 }

arch/powerpc/kernel/head_32.S

···
 	andis.	r0, r5, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH)@h
 #endif
 	bne	handle_page_fault_tramp_2	/* if not, try to put a PTE */
-	rlwinm	r3, r5, 32 - 15, 21, 21		/* DSISR_STORE -> _PAGE_RW */
+	rlwinm	r3, r5, 32 - 24, 30, 30		/* DSISR_STORE -> _PAGE_RW */
 	bl	hash_page
 	b	handle_page_fault_tramp_1
 FTR_SECTION_ELSE
···
 	andc.	r1,r1,r0		/* check access & ~permission */
 	bne-	InstructionAddressInvalid /* return if access not permitted */
 	/* Convert linux-style PTE to low word of PPC-style PTE */
-	rlwimi	r0,r0,32-2,31,31	/* _PAGE_USER -> PP lsb */
 	ori	r1, r1, 0xe06		/* clear out reserved bits */
 	andc	r1, r0, r1		/* PP = user? 1 : 0 */
 BEGIN_FTR_SECTION
···
 	 * we would need to update the pte atomically with lwarx/stwcx.
 	 */
 	/* Convert linux-style PTE to low word of PPC-style PTE */
-	rlwinm	r1,r0,32-9,30,30	/* _PAGE_RW -> PP msb */
-	rlwimi	r0,r0,32-1,30,30	/* _PAGE_USER -> PP msb */
-	rlwimi	r0,r0,32-1,31,31	/* _PAGE_USER -> PP lsb */
+	rlwinm	r1,r0,0,30,30		/* _PAGE_RW -> PP msb */
+	rlwimi	r0,r0,1,30,30		/* _PAGE_USER -> PP msb */
 	ori	r1,r1,0xe04		/* clear out reserved bits */
 	andc	r1,r0,r1		/* PP = user? rw? 1: 3: 0 */
 BEGIN_FTR_SECTION
···
 	 * we would need to update the pte atomically with lwarx/stwcx.
 	 */
 	/* Convert linux-style PTE to low word of PPC-style PTE */
-	rlwimi	r0,r0,32-2,31,31	/* _PAGE_USER -> PP lsb */
 	li	r1,0xe06		/* clear out reserved bits & PP msb */
 	andc	r1,r0,r1		/* PP = user? 1: 0 */
 BEGIN_FTR_SECTION

arch/powerpc/kernel/head_32.h

···
 
 .macro SYSCALL_ENTRY trapno
 	mfspr	r12,SPRN_SPRG_THREAD
+	mfspr	r9, SPRN_SRR1
 #ifdef CONFIG_VMAP_STACK
-	mfspr	r9, SPRN_SRR0
-	mfspr	r11, SPRN_SRR1
-	stw	r9, SRR0(r12)
-	stw	r11, SRR1(r12)
+	mfspr	r11, SPRN_SRR0
+	mtctr	r11
 #endif
-	mfcr	r10
+	andi.	r11, r9, MSR_PR
 	lwz	r11,TASK_STACK-THREAD(r12)
-	rlwinm	r10,r10,0,4,2	/* Clear SO bit in CR */
+	beq-	99f
 	addi	r11, r11, THREAD_SIZE - INT_FRAME_SIZE
 #ifdef CONFIG_VMAP_STACK
-	li	r9, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */
-	mtmsr	r9
+	li	r10, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */
+	mtmsr	r10
 	isync
 #endif
 	tovirt_vmstack r12, r12
 	tophys_novmstack r11, r11
-	mflr	r9
-	stw	r10,_CCR(r11)		/* save registers */
-	stw	r9, _LINK(r11)
+	mflr	r10
+	stw	r10, _LINK(r11)
 #ifdef CONFIG_VMAP_STACK
-	lwz	r10, SRR0(r12)
-	lwz	r9, SRR1(r12)
+	mfctr	r10
 #else
 	mfspr	r10,SPRN_SRR0
-	mfspr	r9,SPRN_SRR1
 #endif
 	stw	r1,GPR1(r11)
 	stw	r1,0(r11)
 	tovirt_novmstack r1, r11	/* set new kernel sp */
 	stw	r10,_NIP(r11)
+	mfcr	r10
+	rlwinm	r10,r10,0,4,2	/* Clear SO bit in CR */
+	stw	r10,_CCR(r11)		/* save registers */
 #ifdef CONFIG_40x
 	rlwinm	r9,r9,0,14,12		/* clear MSR_WE (necessary?) */
 #else
···
 	mtspr	SPRN_SRR0,r11
 	SYNC
 	RFI				/* jump to handler, enable MMU */
+99:	b	ret_from_kernel_syscall
 .endm
 
 .macro save_dar_dsisr_on_stack reg1, reg2, sp

arch/powerpc/kernel/head_64.S

···
 	b	__after_prom_start
 #endif /* CONFIG_PPC_BOOK3E */
 
+__REF
 __boot_from_prom:
 #ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE
 	/* Save parameters */
···
 	/* We never return. We also hit that trap if trying to boot
 	 * from OF while CONFIG_PPC_OF_BOOT_TRAMPOLINE isn't selected */
 	trap
+	.previous
 
 __after_prom_start:
 #ifdef CONFIG_RELOCATABLE
···
 	RFI
 	b	.	/* prevent speculative execution */
 
-	.previous
 	/* This is where all platforms converge execution */
 
 start_here_common:
···
 	/* Not reached */
 	trap
 	EMIT_BUG_ENTRY 0b, __FILE__, __LINE__, 0
+	.previous
 
 /*
  * We put a few things here that have to be page-aligned.

arch/powerpc/kernel/head_booke.h

···
 #ifdef CONFIG_KVM_BOOKE_HV
 ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV)
 #endif
+	mfspr	r9, SPRN_SRR1
 	BOOKE_CLEAR_BTB(r11)
+	andi.	r11, r9, MSR_PR
 	lwz	r11, TASK_STACK - THREAD(r10)
 	rlwinm	r12,r12,0,4,2	/* Clear SO bit in CR */
+	beq-	99f
 	ALLOC_STACK_FRAME(r11, THREAD_SIZE - INT_FRAME_SIZE)
 	stw	r12, _CCR(r11)		/* save various registers */
 	mflr	r12
 	stw	r12,_LINK(r11)
 	mfspr	r12,SPRN_SRR0
 	stw	r1, GPR1(r11)
-	mfspr	r9,SPRN_SRR1
 	stw	r1, 0(r11)
 	mr	r1, r11
 	stw	r12,_NIP(r11)
···
 	mtspr	SPRN_SRR0,r11
 	SYNC
 	RFI				/* jump to handler, enable MMU */
+99:	b	ret_from_kernel_syscall
 .endm
 
 /* To handle the additional exception priority levels on 40x and Book-E

arch/powerpc/kernel/hw_breakpoint.c

···
 {
 	/* TODO */
 }
+
+void ptrace_triggered(struct perf_event *bp,
+		      struct perf_sample_data *data, struct pt_regs *regs)
+{
+	struct perf_event_attr attr;
+
+	/*
+	 * Disable the breakpoint request here since ptrace has defined a
+	 * one-shot behaviour for breakpoint exceptions in PPC64.
+	 * The SIGTRAP signal is generated automatically for us in do_dabr().
+	 * We don't have to do anything about that here
+	 */
+	attr = bp->attr;
+	attr.disabled = true;
+	modify_user_hw_breakpoint(bp, &attr);
+}

arch/powerpc/kernel/irq.c

···
 #include <asm/paca.h>
 #include <asm/firmware.h>
 #include <asm/lv1call.h>
+#include <asm/dbell.h>
 #endif
 #define CREATE_TRACE_POINTS
 #include <asm/trace.h>
···
  
 	return now >= *next_tb;
 }
+
+#ifdef CONFIG_PPC_BOOK3E
 
 /* This is called whenever we are re-enabling interrupts
  * and returns either 0 (nothing to do) or 500/900/280/a00/e80 if
···
 		}
 	}
 
-	/*
-	 * Force the delivery of pending soft-disabled interrupts on PS3.
-	 * Any HV call will have this side effect.
-	 */
-	if (firmware_has_feature(FW_FEATURE_PS3_LV1)) {
-		u64 tmp, tmp2;
-		lv1_get_version_info(&tmp, &tmp2);
-	}
-
-	/*
-	 * Check if an hypervisor Maintenance interrupt happened.
-	 * This is a higher priority interrupt than the others, so
-	 * replay it first.
-	 */
-	if (happened & PACA_IRQ_HMI) {
-		local_paca->irq_happened &= ~PACA_IRQ_HMI;
-		return 0xe60;
-	}
-
 	if (happened & PACA_IRQ_DEC) {
 		local_paca->irq_happened &= ~PACA_IRQ_DEC;
 		return 0x900;
-	}
-
-	if (happened & PACA_IRQ_PMI) {
-		local_paca->irq_happened &= ~PACA_IRQ_PMI;
-		return 0xf00;
 	}
 
 	if (happened & PACA_IRQ_EE) {
···
 		return 0x500;
 	}
 
-#ifdef CONFIG_PPC_BOOK3E
 	/*
 	 * Check if an EPR external interrupt happened this bit is typically
 	 * set if we need to handle another "edge" interrupt from within the
···
 		local_paca->irq_happened &= ~PACA_IRQ_DBELL;
 		return 0x280;
 	}
-#else
-	if (happened & PACA_IRQ_DBELL) {
-		local_paca->irq_happened &= ~PACA_IRQ_DBELL;
-		return 0xa00;
-	}
-#endif /* CONFIG_PPC_BOOK3E */
 
 	/* There should be nothing left ! */
 	BUG_ON(local_paca->irq_happened != 0);
 
 	return 0;
 }
+#endif /* CONFIG_PPC_BOOK3E */
+
+void replay_soft_interrupts(void)
+{
+	/*
+	 * We use local_paca rather than get_paca() to avoid all
+	 * the debug_smp_processor_id() business in this low level
+	 * function
+	 */
+	unsigned char happened = local_paca->irq_happened;
+	struct pt_regs regs;
+
+	ppc_save_regs(&regs);
+	regs.softe = IRQS_ALL_DISABLED;
+
+again:
+	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+		WARN_ON_ONCE(mfmsr() & MSR_EE);
+
+	if (happened & PACA_IRQ_HARD_DIS) {
+		/*
+		 * We may have missed a decrementer interrupt if hard disabled.
+		 * Check the decrementer register in case we had a rollover
+		 * while hard disabled.
+		 */
+		if (!(happened & PACA_IRQ_DEC)) {
+			if (decrementer_check_overflow())
+				happened |= PACA_IRQ_DEC;
+		}
+	}
+
+	/*
+	 * Force the delivery of pending soft-disabled interrupts on PS3.
+	 * Any HV call will have this side effect.
+	 */
+	if (firmware_has_feature(FW_FEATURE_PS3_LV1)) {
+		u64 tmp, tmp2;
+		lv1_get_version_info(&tmp, &tmp2);
+	}
+
+	/*
+	 * Check if an hypervisor Maintenance interrupt happened.
+	 * This is a higher priority interrupt than the others, so
+	 * replay it first.
+	 */
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (happened & PACA_IRQ_HMI)) {
+		local_paca->irq_happened &= ~PACA_IRQ_HMI;
+		regs.trap = 0xe60;
+		handle_hmi_exception(&regs);
+		if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
+			hard_irq_disable();
+	}
+
+	if (happened & PACA_IRQ_DEC) {
+		local_paca->irq_happened &= ~PACA_IRQ_DEC;
+		regs.trap = 0x900;
+		timer_interrupt(&regs);
+		if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
+			hard_irq_disable();
+	}
+
+	if (happened & PACA_IRQ_EE) {
+		local_paca->irq_happened &= ~PACA_IRQ_EE;
+		regs.trap = 0x500;
+		do_IRQ(&regs);
+		if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
+			hard_irq_disable();
+	}
+
+	/*
+	 * Check if an EPR external interrupt happened this bit is typically
+	 * set if we need to handle another "edge" interrupt from within the
+	 * MPIC "EPR" handler.
+	 */
+	if (IS_ENABLED(CONFIG_PPC_BOOK3E) && (happened & PACA_IRQ_EE_EDGE)) {
+		local_paca->irq_happened &= ~PACA_IRQ_EE_EDGE;
+		regs.trap = 0x500;
+		do_IRQ(&regs);
+		if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
+			hard_irq_disable();
+	}
+
+	if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (happened & PACA_IRQ_DBELL)) {
+		local_paca->irq_happened &= ~PACA_IRQ_DBELL;
+		if (IS_ENABLED(CONFIG_PPC_BOOK3E))
+			regs.trap = 0x280;
+		else
+			regs.trap = 0xa00;
+		doorbell_exception(&regs);
+		if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
+			hard_irq_disable();
+	}
+
+	/* Book3E does not support soft-masking PMI interrupts */
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (happened & PACA_IRQ_PMI)) {
+		local_paca->irq_happened &= ~PACA_IRQ_PMI;
+		regs.trap = 0xf00;
+		performance_monitor_exception(&regs);
+		if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
+			hard_irq_disable();
+	}
+
+	happened = local_paca->irq_happened;
+	if (happened & ~PACA_IRQ_HARD_DIS) {
+		/*
+		 * We are responding to the next interrupt, so interrupt-off
+		 * latencies should be reset here.
+		 */
+		trace_hardirqs_on();
+		trace_hardirqs_off();
+		goto again;
+	}
+}
 
 notrace void arch_local_irq_restore(unsigned long mask)
 {
 	unsigned char irq_happened;
-	unsigned int replay;
 
 	/* Write the new soft-enabled value */
 	irq_soft_mask_set(mask);
···
 	 */
 	irq_happened = get_irq_happened();
 	if (!irq_happened) {
-#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
-		WARN_ON_ONCE(!(mfmsr() & MSR_EE));
-#endif
+		if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+			WARN_ON_ONCE(!(mfmsr() & MSR_EE));
 		return;
 	}
 
-	/*
-	 * We need to hard disable to get a trusted value from
-	 * __check_irq_replay(). We also need to soft-disable
-	 * again to avoid warnings in there due to the use of
-	 * per-cpu variables.
-	 */
+	/* We need to hard disable to replay. */
 	if (!(irq_happened & PACA_IRQ_HARD_DIS)) {
-#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
-		WARN_ON_ONCE(!(mfmsr() & MSR_EE));
-#endif
+		if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+			WARN_ON_ONCE(!(mfmsr() & MSR_EE));
 		__hard_irq_disable();
-#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
 	} else {
 		/*
 		 * We should already be hard disabled here. We had bugs
···
 		 * warn if we are wrong. Only do that when IRQ tracing
 		 * is enabled as mfmsr() can be costly.
 		 */
-		if (WARN_ON_ONCE(mfmsr() & MSR_EE))
-			__hard_irq_disable();
-#endif
+		if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
+			if (WARN_ON_ONCE(mfmsr() & MSR_EE))
+				__hard_irq_disable();
+		}
+
+		if (irq_happened == PACA_IRQ_HARD_DIS) {
+			local_paca->irq_happened = 0;
+			__hard_irq_enable();
+			return;
+		}
 	}
 
 	irq_soft_mask_set(IRQS_ALL_DISABLED);
 	trace_hardirqs_off();
 
-	/*
-	 * Check if anything needs to be re-emitted. We haven't
-	 * soft-enabled yet to avoid warnings in decrementer_check_overflow
-	 * accessing per-cpu variables
-	 */
-	replay = __check_irq_replay();
+	replay_soft_interrupts();
+	local_paca->irq_happened = 0;
 
-	/* We can soft-enable now */
 	trace_hardirqs_on();
 	irq_soft_mask_set(IRQS_ENABLED);
-
-	/*
-	 * And replay if we have to. This will return with interrupts
-	 * hard-enabled.
-	 */
-	if (replay) {
-		__replay_interrupt(replay);
-		return;
-	}
-
-	/* Finally, let's ensure we are hard enabled */
 	__hard_irq_enable();
 }
 EXPORT_SYMBOL(arch_local_irq_restore);
···
 
 static inline void check_stack_overflow(void)
 {
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
 	long sp;
 
-	sp = current_stack_pointer() & (THREAD_SIZE-1);
+	if (!IS_ENABLED(CONFIG_DEBUG_STACKOVERFLOW))
+		return;
+
+	sp = current_stack_pointer & (THREAD_SIZE - 1);
 
 	/* check for stack overflow: is there less than 2KB free? */
 	if (unlikely(sp < 2048)) {
 		pr_err("do_IRQ: stack overflow: %ld\n", sp);
 		dump_stack();
 	}
-#endif
 }
 
 void __do_irq(struct pt_regs *regs)
···
 	void *cursp, *irqsp, *sirqsp;
 
 	/* Switch to the irq stack to handle this */
-	cursp = (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
+	cursp = (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
 	irqsp = hardirq_ctx[raw_smp_processor_id()];
 	sirqsp = softirq_ctx[raw_smp_processor_id()];
 

arch/powerpc/kernel/kprobes.c

···
 	if (user_mode(regs))
 		return 0;
 
+	if (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR))
+		return 0;
+
 	/*
 	 * We don't want to be preempted for the entire
 	 * duration of kprobe processing
 	 */
 	preempt_disable();
 	kcb = get_kprobe_ctlblk();
-
-	/* Check we're not actually recursing */
-	if (kprobe_running()) {
-		p = get_kprobe(addr);
-		if (p) {
-			kprobe_opcode_t insn = *p->ainsn.insn;
-			if (kcb->kprobe_status == KPROBE_HIT_SS &&
-					is_trap(insn)) {
-				/* Turn off 'trace' bits */
-				regs->msr &= ~MSR_SINGLESTEP;
-				regs->msr |= kcb->kprobe_saved_msr;
-				goto no_kprobe;
-			}
-			/* We have reentered the kprobe_handler(), since
-			 * another probe was hit while within the handler.
-			 * We here save the original kprobes variables and
-			 * just single step on the instruction of the new probe
-			 * without calling any user handlers.
-			 */
-			save_previous_kprobe(kcb);
-			set_current_kprobe(p, regs, kcb);
-			kprobes_inc_nmissed_count(p);
-			kcb->kprobe_status = KPROBE_REENTER;
-			if (p->ainsn.boostable >= 0) {
-				ret = try_to_emulate(p, regs);
-
-				if (ret > 0) {
-					restore_previous_kprobe(kcb);
-					preempt_enable_no_resched();
-					return 1;
-				}
-			}
-			prepare_singlestep(p, regs);
-			return 1;
-		} else if (*addr != BREAKPOINT_INSTRUCTION) {
-			/* If trap variant, then it belongs not to us */
-			kprobe_opcode_t cur_insn = *addr;
-
-			if (is_trap(cur_insn))
-				goto no_kprobe;
-			/* The breakpoint instruction was removed by
-			 * another cpu right after we hit, no further
-			 * handling of this interrupt is appropriate
-			 */
-			ret = 1;
-		}
-		goto no_kprobe;
-	}
 
 	p = get_kprobe(addr);
 	if (!p) {
···
 		}
 		/* Not one of ours: let kernel handle it */
 		goto no_kprobe;
+	}
+
+	/* Check we're not actually recursing */
+	if (kprobe_running()) {
+		kprobe_opcode_t insn = *p->ainsn.insn;
+		if (kcb->kprobe_status == KPROBE_HIT_SS && is_trap(insn)) {
+			/* Turn off 'trace' bits */
+			regs->msr &= ~MSR_SINGLESTEP;
+			regs->msr |= kcb->kprobe_saved_msr;
+			goto no_kprobe;
+		}
+
+		/*
+		 * We have reentered the kprobe_handler(), since another probe
+		 * was hit while within the handler. We here save the original
+		 * kprobes variables and just single step on the instruction of
+		 * the new probe without calling any user handlers.
+		 */
+		save_previous_kprobe(kcb);
+		set_current_kprobe(p, regs, kcb);
+		kprobes_inc_nmissed_count(p);
+		kcb->kprobe_status = KPROBE_REENTER;
+		if (p->ainsn.boostable >= 0) {
+			ret = try_to_emulate(p, regs);
+
+			if (ret > 0) {
+				restore_previous_kprobe(kcb);
+				preempt_enable_no_resched();
+				return 1;
+			}
+		}
+		prepare_singlestep(p, regs);
+		return 1;
 	}
 
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;

arch/powerpc/kernel/mce.c

···
 #include <linux/percpu.h>
 #include <linux/export.h>
 #include <linux/irq_work.h>
+#include <linux/extable.h>
 
 #include <asm/machdep.h>
 #include <asm/mce.h>
···
 	/* Queue irq work to process this event later. */
 	irq_work_queue(&mce_event_process_work);
 }
+
+void mce_common_process_ue(struct pt_regs *regs,
+			   struct mce_error_info *mce_err)
+{
+	const struct exception_table_entry *entry;
+
+	entry = search_kernel_exception_table(regs->nip);
+	if (entry) {
+		mce_err->ignore_event = true;
+		regs->nip = extable_fixup(entry);
+	}
+}
+
 /*
  * process pending MCE event from the mce event queue. This function will be
  * called during syscall exit.

arch/powerpc/kernel/mce_power.c

···
 				struct mce_error_info *mce_err)
 {
 	long handled = 0;
-	const struct exception_table_entry *entry;
 
-	entry = search_kernel_exception_table(regs->nip);
-	if (entry) {
-		mce_err->ignore_event = true;
-		regs->nip = extable_fixup(entry);
+	mce_common_process_ue(regs, mce_err);
+	if (mce_err->ignore_event)
 		return 1;
-	}
 
 	/*
 	 * On specific SCOM read via MMIO we may get a machine check

arch/powerpc/kernel/misc.S

···
 	li	r3, 1
 	blr
 
-_GLOBAL(current_stack_pointer)
+_GLOBAL(current_stack_frame)
 	PPC_LL	r3,0(r1)
 	blr
-EXPORT_SYMBOL(current_stack_pointer)
+EXPORT_SYMBOL(current_stack_frame)

arch/powerpc/kernel/of_platform.c

···
 	/* Init pci_dn data structures */
 	pci_devs_phb_init_dynamic(phb);
 
-	/* Create EEH devices for the PHB */
+	/* Create EEH PEs for the PHB */
 	eeh_dev_phb_init_dynamic(phb);
-
-	/* Register devices with EEH */
-	if (dev->dev.of_node->child)
-		eeh_add_device_tree_early(PCI_DN(dev->dev.of_node));
 
 	/* Scan the bus */
 	pcibios_scan_phb(phb);
···
 	 */
 	pcibios_claim_one_bus(phb->bus);
 
-	/* Finish EEH setup */
-	eeh_add_device_tree_late(phb->bus);
-
 	/* Add probed PCI devices to the device model */
 	pci_bus_add_devices(phb->bus);
-
-	/* sysfs files should only be added after devices are added */
-	eeh_add_sysfs_files(phb->bus);
 
 	return 0;
 }

arch/powerpc/kernel/paca.c

···
 struct paca_struct **paca_ptrs __read_mostly;
 EXPORT_SYMBOL(paca_ptrs);
 
-void __init initialise_paca(struct paca_struct *new_paca, int cpu)
+void __init __nostackprotector initialise_paca(struct paca_struct *new_paca, int cpu)
 {
 #ifdef CONFIG_PPC_PSERIES
 	new_paca->lppaca_ptr = NULL;
···
 }
 
 /* Put the paca pointer into r13 and SPRG_PACA */
-void setup_paca(struct paca_struct *new_paca)
+void __nostackprotector setup_paca(struct paca_struct *new_paca)
 {
 	/* Setup r13 */
 	local_paca = new_paca;
···
 	/* On Book3E, initialize the TLB miss exception frames */
 	mtspr(SPRN_SPRG_TLB_EXFRAME, local_paca->extlb);
 #else
-	/* In HV mode, we setup both HPACA and PACA to avoid problems
+	/*
+	 * In HV mode, we setup both HPACA and PACA to avoid problems
 	 * if we do a GET_PACA() before the feature fixups have been
-	 * applied
+	 * applied.
+	 *
+	 * Normally you should test against CPU_FTR_HVMODE, but CPU features
+	 * are not yet set up when we first reach here.
 	 */
-	if (early_cpu_has_feature(CPU_FTR_HVMODE))
+	if (mfmsr() & MSR_HV)
 		mtspr(SPRN_SPRG_HPACA, local_paca);
 #endif
 	mtspr(SPRN_SPRG_PACA, local_paca);

arch/powerpc/kernel/pci-common.c

···
 			pci_assign_unassigned_bus_resources(bus);
 	}
 
-	/* Fixup EEH */
-	eeh_add_device_tree_late(bus);
-
 	/* Add new devices to global lists.  Register in proc, sysfs. */
 	pci_bus_add_devices(bus);
-
-	/* sysfs files should only be added after devices are added */
-	eeh_add_sysfs_files(bus);
 }
 EXPORT_SYMBOL_GPL(pcibios_finish_adding_to_bus);
 

arch/powerpc/kernel/pci-hotplug.c

···
 	struct pci_controller *phb;
 	struct device_node *dn = pci_bus_to_OF_node(bus);
 
-	eeh_add_device_tree_early(PCI_DN(dn));
-
 	phb = pci_bus_to_host(bus);
 
 	mode = PCI_PROBE_NORMAL;

arch/powerpc/kernel/process.c

···
 	}
 }
 EXPORT_SYMBOL(enable_kernel_fp);
-
-static int restore_fp(struct task_struct *tsk)
-{
-	if (tsk->thread.load_fp) {
-		load_fp_state(&current->thread.fp_state);
-		current->thread.load_fp++;
-		return 1;
-	}
-	return 0;
-}
-#else
-static int restore_fp(struct task_struct *tsk) { return 0; }
 #endif /* CONFIG_PPC_FPU */
 
 #ifdef CONFIG_ALTIVEC
-#define loadvec(thr) ((thr).load_vec)
-
 static void __giveup_altivec(struct task_struct *tsk)
 {
 	unsigned long msr;
···
 	}
 }
 EXPORT_SYMBOL_GPL(flush_altivec_to_thread);
-
-static int restore_altivec(struct task_struct *tsk)
-{
-	if (cpu_has_feature(CPU_FTR_ALTIVEC) && (tsk->thread.load_vec)) {
-		load_vr_state(&tsk->thread.vr_state);
-		tsk->thread.used_vr = 1;
-		tsk->thread.load_vec++;
-
-		return 1;
-	}
-	return 0;
-}
-#else
-#define loadvec(thr) 0
-static inline int restore_altivec(struct task_struct *tsk) { return 0; }
 #endif /* CONFIG_ALTIVEC */
 
 #ifdef CONFIG_VSX
···
 	}
 }
 EXPORT_SYMBOL_GPL(flush_vsx_to_thread);
-
-static int restore_vsx(struct task_struct *tsk)
-{
-	if (cpu_has_feature(CPU_FTR_VSX)) {
-		tsk->thread.used_vsr = 1;
-		return 1;
-	}
-
-	return 0;
-}
-#else
-static inline int restore_vsx(struct task_struct *tsk) { return 0; }
 #endif /* CONFIG_VSX */
 
 #ifdef CONFIG_SPE
···
 }
 EXPORT_SYMBOL(giveup_all);
 
+#ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_PPC_FPU
+static int restore_fp(struct task_struct *tsk)
+{
+	if (tsk->thread.load_fp) {
+		load_fp_state(&current->thread.fp_state);
+		current->thread.load_fp++;
+		return 1;
+	}
+	return 0;
+}
+#else
+static int restore_fp(struct task_struct *tsk) { return 0; }
+#endif /* CONFIG_PPC_FPU */
+
+#ifdef CONFIG_ALTIVEC
+#define loadvec(thr) ((thr).load_vec)
+static int restore_altivec(struct task_struct *tsk)
+{
+	if (cpu_has_feature(CPU_FTR_ALTIVEC) && (tsk->thread.load_vec)) {
+		load_vr_state(&tsk->thread.vr_state);
+		tsk->thread.used_vr = 1;
+		tsk->thread.load_vec++;
+
+		return 1;
+	}
+	return 0;
+}
+#else
+#define loadvec(thr) 0
+static inline int restore_altivec(struct task_struct *tsk) { return 0; }
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef CONFIG_VSX
+static int restore_vsx(struct task_struct *tsk)
+{
+	if (cpu_has_feature(CPU_FTR_VSX)) {
+		tsk->thread.used_vsr = 1;
+		return 1;
+	}
+
+	return 0;
+}
+#else
+static inline int restore_vsx(struct task_struct *tsk) { return 0; }
+#endif /* CONFIG_VSX */
+
 /*
  * The exception exit path calls restore_math() with interrupts hard disabled
  * but the soft irq state not "reconciled". ftrace code that calls
···
 
 	regs->msr = msr;
 }
+#endif
 
 static void save_all(struct task_struct *tsk)
 {
···
 		p->thread.regs = childregs;
 		childregs->gpr[3] = 0;  /* Result from fork() */
 		if (clone_flags & CLONE_SETTLS) {
-#ifdef CONFIG_PPC64
 			if (!is_32bit_task())
 				childregs->gpr[13] = tls;
 			else
-#endif
 				childregs->gpr[2] = tls;
 		}
 
···
 	return 0;
 }
 
+static inline int valid_emergency_stack(unsigned long sp, struct task_struct *p,
+					unsigned long nbytes)
+{
+#ifdef CONFIG_PPC64
+	unsigned long stack_page;
+	unsigned long cpu = task_cpu(p);
+
+	stack_page = (unsigned long)paca_ptrs[cpu]->emergency_sp - THREAD_SIZE;
+	if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+		return 1;
+
+# ifdef CONFIG_PPC_BOOK3S_64
+	stack_page = (unsigned long)paca_ptrs[cpu]->nmi_emergency_sp - THREAD_SIZE;
+	if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+		return 1;
+
+	stack_page = (unsigned long)paca_ptrs[cpu]->mc_emergency_sp - THREAD_SIZE;
+	if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+		return 1;
+# endif
+#endif
+
+	return 0;
+}
+
+
 int validate_sp(unsigned long sp, struct task_struct *p,
 		       unsigned long nbytes)
 {
···
 	if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
 		return 1;
 
-	return valid_irq_stack(sp, p, nbytes);
+	if (valid_irq_stack(sp, p, nbytes))
+		return 1;
+
+	return valid_emergency_stack(sp, p, nbytes);
 }
 
 EXPORT_SYMBOL(validate_sp);
···
 	sp = (unsigned long) stack;
 	if (sp == 0) {
 		if (tsk == current)
-			sp = current_stack_pointer();
+			sp = current_stack_frame();
 		else
 			sp = tsk->thread.ksp;
 	}

arch/powerpc/kernel/prom_init.c

···
 	if (token == 0)
 		prom_panic("Could not get token for ibm,os-term\n");
 	os_term_args.token = cpu_to_be32(token);
+	os_term_args.nargs = cpu_to_be32(1);
+	os_term_args.nret = cpu_to_be32(1);
+	os_term_args.args[0] = cpu_to_be32(__pa(str));
 	prom_rtas_hcall((uint64_t)&os_term_args);
 }
 #endif /* CONFIG_PPC_SVM */
···
 	 */
 	hdr = dt_header_start;
 
-	/* Don't print anything after quiesce under OPAL, it crashes OFW */
 	prom_printf("Booting Linux via __start() @ 0x%lx ...\n", kbase);
 	prom_debug("->dt_header_start=0x%lx\n", hdr);
 

arch/powerpc/kernel/ptrace.c

···
-/*
- *  PowerPC version
- *    Copyright (C) 1995-1996 Gary Thomas ([e-mail])
- *
- *  Derived from "arch/m68k/kernel/ptrace.c"
- *  Copyright (C) 1994 by Hamish Macdonald
- *  Taken from linux/kernel/ptrace.c and modified for M680x0.
- *  linux/kernel/ptrace.c is by Ross Biro 1/23/92, edited by Linus Torvalds
- *
- * Modified by Cort Dougan ([e-mail])
- * and Paul Mackerras ([e-mail]).
- *
- * This file is subject to the terms and conditions of the GNU General
- * Public License.  See the file README.legal in the main directory of
- * this archive for more details.
- */
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/errno.h>
-#include <linux/ptrace.h>
-#include <linux/regset.h>
-#include <linux/tracehook.h>
-#include <linux/elf.h>
-#include <linux/user.h>
-#include <linux/security.h>
-#include <linux/signal.h>
-#include <linux/seccomp.h>
-#include <linux/audit.h>
-#include <trace/syscall.h>
-#include <linux/hw_breakpoint.h>
-#include <linux/perf_event.h>
-#include <linux/context_tracking.h>
-#include <linux/nospec.h>
-
-#include <linux/uaccess.h>
-#include <linux/pkeys.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
-#include <asm/switch_to.h>
-#include <asm/tm.h>
-#include <asm/asm-prototypes.h>
-#include <asm/debug.h>
-#include <asm/hw_breakpoint.h>
-
-#define CREATE_TRACE_POINTS
-#include <trace/events/syscalls.h>
-
-/*
- * The parameter save area on the stack is used to store arguments being passed
- * to callee function and is located at fixed offset from stack pointer.
- */
-#ifdef CONFIG_PPC32
-#define PARAMETER_SAVE_AREA_OFFSET	24  /* bytes */
-#else /* CONFIG_PPC32 */
-#define PARAMETER_SAVE_AREA_OFFSET	48  /* bytes */
-#endif
-
-struct pt_regs_offset {
-	const char *name;
-	int offset;
-};
-
-#define STR(s)	#s			/* convert to string */
-#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)}
-#define GPR_OFFSET_NAME(num)	\
-	{.name = STR(r##num), .offset = offsetof(struct pt_regs, gpr[num])}, \
-	{.name = STR(gpr##num), .offset = offsetof(struct pt_regs, gpr[num])}
-#define REG_OFFSET_END {.name = NULL, .offset = 0}
-
-#define TVSO(f)	(offsetof(struct thread_vr_state, f))
-#define TFSO(f)	(offsetof(struct thread_fp_state, f))
-#define TSO(f)	(offsetof(struct thread_struct, f))
-
-static const struct pt_regs_offset regoffset_table[] = {
-	GPR_OFFSET_NAME(0),
-	GPR_OFFSET_NAME(1),
-	GPR_OFFSET_NAME(2),
-	GPR_OFFSET_NAME(3),
-	GPR_OFFSET_NAME(4),
-	GPR_OFFSET_NAME(5),
-	GPR_OFFSET_NAME(6),
-	GPR_OFFSET_NAME(7),
-	GPR_OFFSET_NAME(8),
-	GPR_OFFSET_NAME(9),
-	GPR_OFFSET_NAME(10),
-	GPR_OFFSET_NAME(11),
-	GPR_OFFSET_NAME(12),
-	GPR_OFFSET_NAME(13),
-	GPR_OFFSET_NAME(14),
-	GPR_OFFSET_NAME(15),
-	GPR_OFFSET_NAME(16),
-	GPR_OFFSET_NAME(17),
-	GPR_OFFSET_NAME(18),
-	GPR_OFFSET_NAME(19),
-	GPR_OFFSET_NAME(20),
-	GPR_OFFSET_NAME(21),
-	GPR_OFFSET_NAME(22),
-	GPR_OFFSET_NAME(23),
-	GPR_OFFSET_NAME(24),
-	GPR_OFFSET_NAME(25),
-	GPR_OFFSET_NAME(26),
-	GPR_OFFSET_NAME(27),
-	GPR_OFFSET_NAME(28),
-	GPR_OFFSET_NAME(29),
-	GPR_OFFSET_NAME(30),
-	GPR_OFFSET_NAME(31),
-	REG_OFFSET_NAME(nip),
-	REG_OFFSET_NAME(msr),
-	REG_OFFSET_NAME(ctr),
-	REG_OFFSET_NAME(link),
-	REG_OFFSET_NAME(xer),
-	REG_OFFSET_NAME(ccr),
-#ifdef CONFIG_PPC64
-	REG_OFFSET_NAME(softe),
-#else
-	REG_OFFSET_NAME(mq),
-#endif
-	REG_OFFSET_NAME(trap),
-	REG_OFFSET_NAME(dar),
-	REG_OFFSET_NAME(dsisr),
-	REG_OFFSET_END,
-};
-
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-static void flush_tmregs_to_thread(struct task_struct *tsk)
-{
-	/*
-	 * If task is not current, it will have been flushed already to
-	 * it's thread_struct during __switch_to().
-	 *
-	 * A reclaim flushes ALL the state or if not in TM save TM SPRs
-	 * in the appropriate thread structures from live.
-	 */
-
-	if ((!cpu_has_feature(CPU_FTR_TM)) || (tsk != current))
-		return;
-
-	if (MSR_TM_SUSPENDED(mfmsr())) {
-		tm_reclaim_current(TM_CAUSE_SIGNAL);
-	} else {
-		tm_enable();
-		tm_save_sprs(&(tsk->thread));
-	}
-}
-#else
-static inline void flush_tmregs_to_thread(struct task_struct *tsk) { }
-#endif
-
-/**
- * regs_query_register_offset() - query register offset from its name
- * @name:	the name of a register
- *
- * regs_query_register_offset() returns the offset of a register in struct
- * pt_regs from its name. If the name is invalid, this returns -EINVAL;
- */
-int regs_query_register_offset(const char *name)
-{
-	const struct pt_regs_offset *roff;
-	for (roff = regoffset_table; roff->name != NULL; roff++)
-		if (!strcmp(roff->name, name))
-			return roff->offset;
-	return -EINVAL;
-}
-
-/**
- * regs_query_register_name() - query register name from its offset
- * @offset:	the offset of a register in struct pt_regs.
- *
- * regs_query_register_name() returns the name of a register from its
- * offset in struct pt_regs. If the @offset is invalid, this returns NULL;
- */
-const char *regs_query_register_name(unsigned int offset)
-{
-	const struct pt_regs_offset *roff;
-	for (roff = regoffset_table; roff->name != NULL; roff++)
-		if (roff->offset == offset)
-			return roff->name;
-	return NULL;
-}
-
-/*
- * does not yet catch signals sent when the child dies.
- * in exit.c or in signal.c.
- */
-
-/*
- * Set of msr bits that gdb can change on behalf of a process.
- */
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-#define MSR_DEBUGCHANGE	0
-#else
-#define MSR_DEBUGCHANGE	(MSR_SE | MSR_BE)
-#endif
-
-/*
- * Max register writeable via put_reg
- */
-#ifdef CONFIG_PPC32
-#define PT_MAX_PUT_REG	PT_MQ
-#else
-#define PT_MAX_PUT_REG	PT_CCR
-#endif
-
-static unsigned long get_user_msr(struct task_struct *task)
-{
-	return task->thread.regs->msr | task->thread.fpexc_mode;
-}
-
-static int set_user_msr(struct task_struct *task, unsigned long msr)
-{
-	task->thread.regs->msr &= ~MSR_DEBUGCHANGE;
-	task->thread.regs->msr |= msr & MSR_DEBUGCHANGE;
-	return 0;
-}
-
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-static unsigned long get_user_ckpt_msr(struct task_struct *task)
-{
-	return task->thread.ckpt_regs.msr | task->thread.fpexc_mode;
-}
-
-static int set_user_ckpt_msr(struct task_struct *task, unsigned long msr)
-{
-	task->thread.ckpt_regs.msr &= ~MSR_DEBUGCHANGE;
-	task->thread.ckpt_regs.msr |= msr & MSR_DEBUGCHANGE;
-	return 0;
-}
-
-static int set_user_ckpt_trap(struct task_struct *task, unsigned long trap)
-{
-	task->thread.ckpt_regs.trap = trap & 0xfff0;
-	return 0;
-}
-#endif
-
-#ifdef CONFIG_PPC64
-static int get_user_dscr(struct task_struct *task, unsigned long *data)
-{
-	*data = task->thread.dscr;
-	return 0;
-}
-
-static int set_user_dscr(struct task_struct *task, unsigned long dscr)
-{
-	task->thread.dscr = dscr;
-	task->thread.dscr_inherit = 1;
-	return 0;
-}
-#else
-static int get_user_dscr(struct task_struct *task, unsigned long *data)
-{
-	return -EIO;
-}
-
-static int set_user_dscr(struct task_struct *task, unsigned long dscr)
-{
-	return -EIO;
-}
-#endif
-
-/*
- * We prevent mucking around with the reserved area of trap
- * which are used internally by the kernel.
- */
-static int set_user_trap(struct task_struct *task, unsigned long trap)
-{
-	task->thread.regs->trap = trap & 0xfff0;
-	return 0;
-}
-
-/*
- * Get contents of register REGNO in task TASK.
- */
-int ptrace_get_reg(struct task_struct *task, int regno, unsigned long *data)
-{
-	unsigned int regs_max;
-
-	if ((task->thread.regs == NULL) || !data)
-		return -EIO;
-
-	if (regno == PT_MSR) {
-		*data = get_user_msr(task);
-		return 0;
-	}
-
-	if (regno == PT_DSCR)
-		return get_user_dscr(task, data);
-
-#ifdef CONFIG_PPC64
-	/*
-	 * softe copies paca->irq_soft_mask variable state. Since irq_soft_mask is
-	 * no more used as a flag, lets force usr to alway see the softe value as 1
-	 * which means interrupts are not soft disabled.
-	 */
-	if (regno == PT_SOFTE) {
-		*data = 1;
-		return  0;
-	}
-#endif
-
-	regs_max = sizeof(struct user_pt_regs) / sizeof(unsigned long);
-	if (regno < regs_max) {
-		regno = array_index_nospec(regno, regs_max);
-		*data = ((unsigned long *)task->thread.regs)[regno];
-		return 0;
-	}
-
-	return -EIO;
-}
-
-/*
- * Write contents of register REGNO in task TASK.
- */
-int ptrace_put_reg(struct task_struct *task, int regno, unsigned long data)
-{
-	if (task->thread.regs == NULL)
-		return -EIO;
-
-	if (regno == PT_MSR)
-		return set_user_msr(task, data);
-	if (regno == PT_TRAP)
-		return set_user_trap(task, data);
-	if (regno == PT_DSCR)
-		return set_user_dscr(task, data);
-
-	if (regno <= PT_MAX_PUT_REG) {
-		regno = array_index_nospec(regno, PT_MAX_PUT_REG + 1);
-		((unsigned long *)task->thread.regs)[regno] = data;
-		return 0;
-	}
-	return -EIO;
-}
-
-static int gpr_get(struct task_struct *target, const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   void *kbuf, void __user *ubuf)
-{
-	int i, ret;
-
-	if (target->thread.regs == NULL)
-		return -EIO;
-
-	if (!FULL_REGS(target->thread.regs)) {
-		/* We have a partial register set.  Fill 14-31 with bogus values */
-		for (i = 14; i < 32; i++)
-			target->thread.regs->gpr[i] = NV_REG_POISON;
-	}
-
-	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				  target->thread.regs,
-				  0, offsetof(struct pt_regs, msr));
-	if (!ret) {
-		unsigned long msr = get_user_msr(target);
-		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &msr,
-					  offsetof(struct pt_regs, msr),
-					  offsetof(struct pt_regs, msr) +
-					  sizeof(msr));
-	}
-
-	BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
-		     offsetof(struct pt_regs, msr) + sizeof(long));
-
-	if (!ret)
-		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-					  &target->thread.regs->orig_gpr3,
-					  offsetof(struct pt_regs, orig_gpr3),
-					  sizeof(struct user_pt_regs));
-	if (!ret)
-		ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
-					       sizeof(struct user_pt_regs), -1);
-
-	return ret;
-}
-
-static int gpr_set(struct task_struct *target, const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   const void *kbuf, const void __user *ubuf)
-{
-	unsigned long reg;
-	int ret;
-
-	if (target->thread.regs == NULL)
-		return -EIO;
-
-	CHECK_FULL_REGS(target->thread.regs);
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 target->thread.regs,
-				 0, PT_MSR * sizeof(reg));
-
-	if (!ret && count > 0) {
-		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &reg,
-					 PT_MSR * sizeof(reg),
-					 (PT_MSR + 1) * sizeof(reg));
-		if (!ret)
-			ret = set_user_msr(target, reg);
-	}
-
-	BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
-		     offsetof(struct pt_regs, msr) + sizeof(long));
-
-	if (!ret)
-		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-					 &target->thread.regs->orig_gpr3,
-					 PT_ORIG_R3 * sizeof(reg),
-					 (PT_MAX_PUT_REG + 1) * sizeof(reg));
-
-	if (PT_MAX_PUT_REG + 1 < PT_TRAP && !ret)
-		ret = user_regset_copyin_ignore(
-			&pos, &count, &kbuf, &ubuf,
-			(PT_MAX_PUT_REG + 1) * sizeof(reg),
-			PT_TRAP * sizeof(reg));
-
-	if (!ret && count > 0) {
-		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &reg,
-					 PT_TRAP * sizeof(reg),
-					 (PT_TRAP + 1) * sizeof(reg));
-		if (!ret)
-			ret = set_user_trap(target, reg);
-	}
-
-	if (!ret)
-		ret = user_regset_copyin_ignore(
-			&pos, &count, &kbuf, &ubuf,
-			(PT_TRAP + 1) * sizeof(reg), -1);
-
-	return ret;
-}
-
-/*
- * Regardless of transactions, 'fp_state' holds the current running
- * value of all FPR registers and 'ckfp_state' holds the last checkpointed
- * value of all FPR registers for the current transaction.
- *
- * Userspace interface buffer layout:
- *
- * struct data {
- *	u64	fpr[32];
- *	u64	fpscr;
- * };
- */
-static int fpr_get(struct task_struct *target, const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   void *kbuf, void __user *ubuf)
-{
-#ifdef CONFIG_VSX
-	u64 buf[33];
-	int i;
-
-	flush_fp_to_thread(target);
-
-	/* copy to local buffer then write that out */
-	for (i = 0; i < 32 ; i++)
-		buf[i] = target->thread.TS_FPR(i);
-	buf[32] = target->thread.fp_state.fpscr;
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
-#else
-	BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
-		     offsetof(struct thread_fp_state, fpr[32]));
-
-	flush_fp_to_thread(target);
-
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				   &target->thread.fp_state, 0, -1);
-#endif
-}
-
-/*
- * Regardless of transactions, 'fp_state' holds the current running
- * value of all FPR registers and 'ckfp_state' holds the last checkpointed
- * value of all FPR registers for the current transaction.
- *
- * Userspace interface buffer layout:
- *
- * struct data {
- *	u64	fpr[32];
- *	u64	fpscr;
- * };
- *
- */
-static int fpr_set(struct task_struct *target, const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   const void *kbuf, const void __user *ubuf)
-{
-#ifdef CONFIG_VSX
-	u64 buf[33];
-	int i;
-
-	flush_fp_to_thread(target);
-
-	for (i = 0; i < 32 ; i++)
-		buf[i] = target->thread.TS_FPR(i);
-	buf[32] = target->thread.fp_state.fpscr;
-
-	/* copy to local buffer then write that out */
-	i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
-	if (i)
-		return i;
-
-	for (i = 0; i < 32 ; i++)
-		target->thread.TS_FPR(i) = buf[i];
-	target->thread.fp_state.fpscr = buf[32];
-	return 0;
-#else
-	BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
-		     offsetof(struct thread_fp_state, fpr[32]));
-
-	flush_fp_to_thread(target);
-
-	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				  &target->thread.fp_state, 0, -1);
-#endif
-}
-
-#ifdef CONFIG_ALTIVEC
-/*
- * Get/set all the altivec registers vr0..vr31, vscr, vrsave, in one go.
- * The transfer totals 34 quadword.  Quadwords 0-31 contain the
- * corresponding vector registers.  Quadword 32 contains the vscr as the
- * last word (offset 12) within that quadword.  Quadword 33 contains the
- * vrsave as the first word (offset 0) within the quadword.
- *
- * This definition of the VMX state is compatible with the current PPC32
- * ptrace interface.  This allows signal handling and ptrace to use the
- * same structures.  This also simplifies the implementation of a bi-arch
- * (combined (32- and 64-bit) gdb.
- */
-
-static int vr_active(struct task_struct *target,
-		     const struct user_regset *regset)
-{
-	flush_altivec_to_thread(target);
-	return target->thread.used_vr ? regset->n : 0;
-}
-
-/*
- * Regardless of transactions, 'vr_state' holds the current running
- * value of all the VMX registers and 'ckvr_state' holds the last
- * checkpointed value of all the VMX registers for the current
- * transaction to fall back on in case it aborts.
- *
- * Userspace interface buffer layout:
- *
- * struct data {
- *	vector128	vr[32];
- *	vector128	vscr;
- *	vector128	vrsave;
- * };
- */
-static int vr_get(struct task_struct *target, const struct user_regset *regset,
-		  unsigned int pos, unsigned int count,
-		  void *kbuf, void __user *ubuf)
-{
-	int ret;
-
-	flush_altivec_to_thread(target);
-
-	BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) !=
-		     offsetof(struct thread_vr_state, vr[32]));
-
-	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				  &target->thread.vr_state, 0,
-				  33 * sizeof(vector128));
-	if (!ret) {
-		/*
-		 * Copy out only the low-order word of vrsave.
-		 */
-		int start, end;
-		union {
-			elf_vrreg_t reg;
-			u32 word;
-		} vrsave;
-		memset(&vrsave, 0, sizeof(vrsave));
-
-		vrsave.word = target->thread.vrsave;
-
-		start = 33 * sizeof(vector128);
-		end = start + sizeof(vrsave);
-		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave,
-					  start, end);
-	}
-
-	return ret;
-}
-
-/*
- * Regardless of transactions, 'vr_state' holds the current running
- * value of all the VMX registers and 'ckvr_state' holds the last
- * checkpointed value of all the VMX registers for the current
- * transaction to fall back on in case it aborts.
- *
- * Userspace interface buffer layout:
- *
- * struct data {
- *	vector128	vr[32];
- *	vector128	vscr;
- *	vector128	vrsave;
- * };
- */
-static int vr_set(struct task_struct *target, const struct user_regset *regset,
-		  unsigned int pos, unsigned int count,
-		  const void *kbuf, const void __user *ubuf)
-{
-	int ret;
-
-	flush_altivec_to_thread(target);
-
-	BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) !=
-		     offsetof(struct thread_vr_state, vr[32]));
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 &target->thread.vr_state, 0,
-				 33 * sizeof(vector128));
-	if (!ret && count > 0) {
-		/*
-		 * We use only the first word of vrsave.
-		 */
-		int start, end;
-		union {
-			elf_vrreg_t reg;
-			u32 word;
-		} vrsave;
-		memset(&vrsave, 0, sizeof(vrsave));
-
-		vrsave.word = target->thread.vrsave;
-
-		start = 33 * sizeof(vector128);
-		end = start + sizeof(vrsave);
-		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave,
-					 start, end);
-		if (!ret)
-			target->thread.vrsave = vrsave.word;
-	}
-
-	return ret;
-}
-#endif /* CONFIG_ALTIVEC */
-
-#ifdef CONFIG_VSX
-/*
- * Currently to set and and get all the vsx state, you need to call
- * the fp and VMX calls as well.  This only get/sets the lower 32
- * 128bit VSX registers.
- */
-
-static int vsr_active(struct task_struct *target,
-		      const struct user_regset *regset)
-{
-	flush_vsx_to_thread(target);
-	return target->thread.used_vsr ? regset->n : 0;
-}
-
-/*
- * Regardless of transactions, 'fp_state' holds the current running
- * value of all FPR registers and 'ckfp_state' holds the last
- * checkpointed value of all FPR registers for the current
- * transaction.
- *
- * Userspace interface buffer layout:
- *
- * struct data {
- *	u64	vsx[32];
- * };
- */
-static int vsr_get(struct task_struct *target, const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   void *kbuf, void __user *ubuf)
-{
-	u64 buf[32];
-	int ret, i;
-
-	flush_tmregs_to_thread(target);
-	flush_fp_to_thread(target);
-	flush_altivec_to_thread(target);
-	flush_vsx_to_thread(target);
-
-	for (i = 0; i < 32 ; i++)
-		buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
-
-	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				  buf, 0, 32 * sizeof(double));
-
-	return ret;
-}
-
-/*
- * Regardless of transactions, 'fp_state' holds the current running
- * value of all FPR registers and 'ckfp_state' holds the last
- * checkpointed value of all FPR registers for the current
- * transaction.
- *
- * Userspace interface buffer layout:
- *
- * struct data {
- *	u64	vsx[32];
- * };
- */
-static int vsr_set(struct task_struct *target, const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   const void *kbuf, const void __user *ubuf)
-{
-	u64 buf[32];
-	int ret,i;
-
-	flush_tmregs_to_thread(target);
-	flush_fp_to_thread(target);
-	flush_altivec_to_thread(target);
-	flush_vsx_to_thread(target);
-
-	for (i = 0; i < 32 ; i++)
-		buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 buf, 0, 32 * sizeof(double));
-	if (!ret)
-		for (i = 0; i < 32 ; i++)
-			target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
-
-	return ret;
-}
-#endif /* CONFIG_VSX */
-
-#ifdef CONFIG_SPE
-
-/*
- * For get_evrregs/set_evrregs functions 'data' has the following layout:
- *
- * struct {
- *   u32 evr[32];
- *   u64 acc;
- *   u32 spefscr;
- * }
- */
-
-static int evr_active(struct task_struct *target,
-		      const struct user_regset *regset)
-{
-	flush_spe_to_thread(target);
-	return target->thread.used_spe ? regset->n : 0;
-}
-
-static int evr_get(struct task_struct *target, const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   void *kbuf, void __user *ubuf)
-{
-	int ret;
-
-	flush_spe_to_thread(target);
-
-	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				  &target->thread.evr,
-				  0, sizeof(target->thread.evr));
-
-	BUILD_BUG_ON(offsetof(struct thread_struct, acc) + sizeof(u64) !=
-		     offsetof(struct thread_struct, spefscr));
-
-	if (!ret)
-		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-					  &target->thread.acc,
-					  sizeof(target->thread.evr), -1);
-
-	return ret;
-}
-
-static int evr_set(struct task_struct *target, const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   const void *kbuf, const void __user *ubuf)
-{
-	int ret;
-
-	flush_spe_to_thread(target);
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 &target->thread.evr,
-				 0, sizeof(target->thread.evr));
-
-	BUILD_BUG_ON(offsetof(struct thread_struct, acc) + sizeof(u64) !=
-		     offsetof(struct thread_struct, spefscr));
-
-	if (!ret)
-		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-					 &target->thread.acc,
-					 sizeof(target->thread.evr), -1);
-
-	return ret;
-}
-#endif /* CONFIG_SPE */
-
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-/**
- * tm_cgpr_active - get active number of registers in CGPR
- * @target:	The target task.
- * @regset:	The user regset structure.
- *
- * This function checks for the active number of available
- * regisers in transaction checkpointed GPR category.
- */
-static int tm_cgpr_active(struct task_struct *target,
-			  const struct user_regset *regset)
-{
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
-		return 0;
-
-	return regset->n;
-}
-
-/**
- * tm_cgpr_get - get CGPR registers
- * @target:	The target task.
- * @regset:	The user regset structure.
- * @pos:	The buffer position.
- * @count:	Number of bytes to copy.
- * @kbuf:	Kernel buffer to copy from.
- * @ubuf:	User buffer to copy into.
- *
- * This function gets transaction checkpointed GPR registers.
- *
- * When the transaction is active, 'ckpt_regs' holds all the checkpointed
- * GPR register values for the current transaction to fall back on if it
- * aborts in between. This function gets those checkpointed GPR registers.
- * The userspace interface buffer layout is as follows.
- *
- * struct data {
- *	struct pt_regs ckpt_regs;
- * };
- */
-static int tm_cgpr_get(struct task_struct *target,
-			const struct user_regset *regset,
-			unsigned int pos, unsigned int count,
-			void *kbuf, void __user *ubuf)
-{
-	int ret;
-
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
-		return -ENODATA;
-
-	flush_tmregs_to_thread(target);
-	flush_fp_to_thread(target);
-	flush_altivec_to_thread(target);
-
-	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				  &target->thread.ckpt_regs,
-				  0, offsetof(struct pt_regs, msr));
-	if (!ret) {
-		unsigned long msr = get_user_ckpt_msr(target);
-
-		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &msr,
-					  offsetof(struct pt_regs, msr),
-					  offsetof(struct pt_regs, msr) +
-					  sizeof(msr));
-	}
-
-	BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
-		     offsetof(struct pt_regs, msr) + sizeof(long));
-
-	if (!ret)
-		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-					  &target->thread.ckpt_regs.orig_gpr3,
-					  offsetof(struct pt_regs, orig_gpr3),
-					  sizeof(struct user_pt_regs));
-	if (!ret)
-		ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
-					       sizeof(struct user_pt_regs), -1);
-
-	return ret;
-}
-
-/*
- * tm_cgpr_set - set the CGPR registers
- * @target:	The target task.
- * @regset:	The user regset structure.
- * @pos:	The buffer position.
- * @count:	Number of bytes to copy.
- * @kbuf:	Kernel buffer to copy into.
- * @ubuf:	User buffer to copy from.
- *
- * This function sets in transaction checkpointed GPR registers.
- *
- * When the transaction is active, 'ckpt_regs' holds the checkpointed
- * GPR register values for the current transaction to fall back on if it
- * aborts in between. This function sets those checkpointed GPR registers.
- * The userspace interface buffer layout is as follows.
- *
- * struct data {
- *	struct pt_regs ckpt_regs;
- * };
- */
-static int tm_cgpr_set(struct task_struct *target,
-			const struct user_regset *regset,
-			unsigned int pos, unsigned int count,
-			const void *kbuf, const void __user *ubuf)
-{
-	unsigned long reg;
-	int ret;
-
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
-		return -ENODATA;
-
-	flush_tmregs_to_thread(target);
-	flush_fp_to_thread(target);
-	flush_altivec_to_thread(target);
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 &target->thread.ckpt_regs,
-				 0, PT_MSR * sizeof(reg));
-
-	if (!ret && count > 0) {
-		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &reg,
-					 PT_MSR * sizeof(reg),
-					 (PT_MSR + 1) * sizeof(reg));
-		if (!ret)
-			ret = set_user_ckpt_msr(target, reg);
-	}
-
-	BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
-		     offsetof(struct pt_regs, msr) + sizeof(long));
-
-	if (!ret)
-		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-					 &target->thread.ckpt_regs.orig_gpr3,
-					 PT_ORIG_R3 * sizeof(reg),
-					 (PT_MAX_PUT_REG + 1) * sizeof(reg));
-
-	if (PT_MAX_PUT_REG + 1 < PT_TRAP && !ret)
-		ret = user_regset_copyin_ignore(
-			&pos, &count, &kbuf, &ubuf,
-			(PT_MAX_PUT_REG + 1) * sizeof(reg),
-			PT_TRAP * sizeof(reg));
-
-	if (!ret && count > 0) {
-		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &reg,
-					 PT_TRAP * sizeof(reg),
-					 (PT_TRAP + 1) * sizeof(reg));
-		if (!ret)
-			ret = set_user_ckpt_trap(target, reg);
-	}
-
-	if (!ret)
-		ret = user_regset_copyin_ignore(
-			&pos, &count, &kbuf, &ubuf,
-			(PT_TRAP + 1) * sizeof(reg), -1);
-
-	return ret;
-}
-
-/**
- * tm_cfpr_active - get active number of registers in CFPR
- * @target:	The target task.
- * @regset:	The user regset structure.
- *
- * This function checks for the active number of available
- * regisers in transaction checkpointed FPR category.
- */
-static int tm_cfpr_active(struct task_struct *target,
-				const struct user_regset *regset)
-{
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
-		return 0;
-
-	return regset->n;
-}
-
-/**
- * tm_cfpr_get - get CFPR registers
- * @target:	The target task.
- * @regset:	The user regset structure.
- * @pos:	The buffer position.
- * @count:	Number of bytes to copy.
- * @kbuf:	Kernel buffer to copy from.
- * @ubuf:	User buffer to copy into.
- *
- * This function gets in transaction checkpointed FPR registers.
- *
- * When the transaction is active 'ckfp_state' holds the checkpointed
- * values for the current transaction to fall back on if it aborts
- * in between. This function gets those checkpointed FPR registers.
- * The userspace interface buffer layout is as follows.
- *
- * struct data {
- *	u64	fpr[32];
- *	u64	fpscr;
- *};
- */
-static int tm_cfpr_get(struct task_struct *target,
-			const struct user_regset *regset,
-			unsigned int pos, unsigned int count,
-			void *kbuf, void __user *ubuf)
-{
-	u64 buf[33];
-	int i;
-
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
-		return -ENODATA;
-
-	flush_tmregs_to_thread(target);
-	flush_fp_to_thread(target);
-	flush_altivec_to_thread(target);
-
-	/* copy to local buffer then write that out */
-	for (i = 0; i < 32 ; i++)
-		buf[i] = target->thread.TS_CKFPR(i);
-	buf[32] = target->thread.ckfp_state.fpscr;
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
-}
-
-/**
- * tm_cfpr_set - set CFPR registers
- * @target:	The target task.
- * @regset:	The user regset structure.
- * @pos:	The buffer position.
- * @count:	Number of bytes to copy.
- * @kbuf:	Kernel buffer to copy into.
- * @ubuf:	User buffer to copy from.
- *
- * This function sets in transaction checkpointed FPR registers.
- *
- * When the transaction is active 'ckfp_state' holds the checkpointed
- * FPR register values for the current transaction to fall back on
- * if it aborts in between. This function sets these checkpointed
- * FPR registers. The userspace interface buffer layout is as follows.
- *
- * struct data {
- *	u64	fpr[32];
- *	u64	fpscr;
- *};
- */
-static int tm_cfpr_set(struct task_struct *target,
-			const struct user_regset *regset,
-			unsigned int pos, unsigned int count,
-			const void *kbuf, const void __user *ubuf)
-{
-	u64 buf[33];
-	int i;
-
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
-		return -ENODATA;
-
-	flush_tmregs_to_thread(target);
-	flush_fp_to_thread(target);
-	flush_altivec_to_thread(target);
-
-	for (i = 0; i < 32; i++)
-		buf[i] = target->thread.TS_CKFPR(i);
-	buf[32] = target->thread.ckfp_state.fpscr;
-
-	/* copy to local buffer then write that out */
-	i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
-	if (i)
-		return i;
-	for (i = 0; i < 32 ; i++)
-		target->thread.TS_CKFPR(i) = buf[i];
-	target->thread.ckfp_state.fpscr = buf[32];
-	return 0;
-}
-
-/**
- * tm_cvmx_active - get active number of registers in CVMX
- * @target:	The target task.
- * @regset:	The user regset structure.
- *
- * This function checks for the active number of available
- * regisers in checkpointed VMX category.
- */
-static int tm_cvmx_active(struct task_struct *target,
-				const struct user_regset *regset)
-{
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
-		return 0;
-
-	return regset->n;
-}
-
-/**
- * tm_cvmx_get - get CMVX registers
- * @target:	The target task.
- * @regset:	The user regset structure.
- * @pos:	The buffer position.
- * @count:	Number of bytes to copy.
- * @kbuf:	Kernel buffer to copy from.
- * @ubuf:	User buffer to copy into.
- *
- * This function gets in transaction checkpointed VMX registers.
- *
- * When the transaction is active 'ckvr_state' and 'ckvrsave' hold
- * the checkpointed values for the current transaction to fall
- * back on if it aborts in between. The userspace interface buffer
- * layout is as follows.
- *
- * struct data {
- *	vector128	vr[32];
- *	vector128	vscr;
- *	vector128	vrsave;
- *};
- */
-static int tm_cvmx_get(struct task_struct *target,
-			const struct user_regset *regset,
-			unsigned int pos, unsigned int count,
-			void *kbuf, void __user *ubuf)
-{
-	int ret;
-
-	BUILD_BUG_ON(TVSO(vscr) != TVSO(vr[32]));
-
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
-		return -ENODATA;
-
-	/* Flush the state */
-	flush_tmregs_to_thread(target);
-	flush_fp_to_thread(target);
-	flush_altivec_to_thread(target);
-
-	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-					&target->thread.ckvr_state, 0,
-					33 * sizeof(vector128));
-	if (!ret) {
-		/*
-		 * Copy out only the low-order word of vrsave.
-		 */
-		union {
-			elf_vrreg_t reg;
-			u32 word;
-		} vrsave;
-		memset(&vrsave, 0, sizeof(vrsave));
-		vrsave.word = target->thread.ckvrsave;
-		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave,
-						33 * sizeof(vector128), -1);
-	}
-
-	return ret;
-}
-
-/**
- * tm_cvmx_set - set CMVX registers
- * @target:	The target task.
- * @regset:	The user regset structure.
- * @pos:	The buffer position.
- * @count:	Number of bytes to copy.
- * @kbuf:	Kernel buffer to copy into.
- * @ubuf:	User buffer to copy from.
- *
- * This function sets in transaction checkpointed VMX registers.
- *
- * When the transaction is active 'ckvr_state' and 'ckvrsave' hold
- * the checkpointed values for the current transaction to fall
- * back on if it aborts in between. The userspace interface buffer
- * layout is as follows.
- *
- * struct data {
- *	vector128	vr[32];
- *	vector128	vscr;
- *	vector128	vrsave;
- *};
- */
-static int tm_cvmx_set(struct task_struct *target,
-			const struct user_regset *regset,
-			unsigned int pos, unsigned int count,
-			const void *kbuf, const void __user *ubuf)
-{
-	int ret;
-
-	BUILD_BUG_ON(TVSO(vscr) != TVSO(vr[32]));
-
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
-		return -ENODATA;
-
-	flush_tmregs_to_thread(target);
-	flush_fp_to_thread(target);
-	flush_altivec_to_thread(target);
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-					&target->thread.ckvr_state, 0,
-					33 * sizeof(vector128));
-	if (!ret && count > 0) {
-		/*
-		 * We use only the low-order word of vrsave.
-		 */
-		union {
-			elf_vrreg_t reg;
-			u32 word;
-		} vrsave;
-		memset(&vrsave, 0, sizeof(vrsave));
-		vrsave.word = target->thread.ckvrsave;
-		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave,
-						33 * sizeof(vector128), -1);
-		if (!ret)
-			target->thread.ckvrsave = vrsave.word;
-	}
-
-	return ret;
-}
-
-/**
- * tm_cvsx_active - get active number of registers in CVSX
- * @target:	The target task.
- * @regset:	The user regset structure.
- *
- * This function checks for the active number of available
- * regisers in transaction checkpointed VSX category.
- */
-static int tm_cvsx_active(struct task_struct *target,
-				const struct user_regset *regset)
-{
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
-		return 0;
-
-	flush_vsx_to_thread(target);
-	return target->thread.used_vsr ? regset->n : 0;
-}
-
-/**
- * tm_cvsx_get - get CVSX registers
- * @target:	The target task.
- * @regset:	The user regset structure.
- * @pos:	The buffer position.
- * @count:	Number of bytes to copy.
- * @kbuf:	Kernel buffer to copy from.
- * @ubuf:	User buffer to copy into.
- *
- * This function gets in transaction checkpointed VSX registers.
- *
- * When the transaction is active 'ckfp_state' holds the checkpointed
- * values for the current transaction to fall back on if it aborts
- * in between. This function gets those checkpointed VSX registers.
- * The userspace interface buffer layout is as follows.
- *
- * struct data {
- *	u64	vsx[32];
- *};
- */
-static int tm_cvsx_get(struct task_struct *target,
-			const struct user_regset *regset,
-			unsigned int pos, unsigned int count,
-			void *kbuf, void __user *ubuf)
-{
-	u64 buf[32];
-	int ret, i;
-
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
-		return -ENODATA;
-
-	/* Flush the state */
-	flush_tmregs_to_thread(target);
-	flush_fp_to_thread(target);
-	flush_altivec_to_thread(target);
-	flush_vsx_to_thread(target);
-
-	for (i = 0; i < 32 ; i++)
-		buf[i] = target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET];
-	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				  buf, 0, 32 * sizeof(double));
-
-	return ret;
-}
-
-/**
- * tm_cvsx_set - set CFPR registers
- * @target:	The target task.
- * @regset:	The user regset structure.
- * @pos:	The buffer position.
- * @count:	Number of bytes to copy.
- * @kbuf:	Kernel buffer to copy into.
- * @ubuf:	User buffer to copy from.
- *
- * This function sets in transaction checkpointed VSX registers.
- *
- * When the transaction is active 'ckfp_state' holds the checkpointed
- * VSX register values for the current transaction to fall back on
- * if it aborts in between. This function sets these checkpointed
- * FPR registers. The userspace interface buffer layout is as follows.
- *
- * struct data {
- *	u64	vsx[32];
- *};
- */
-static int tm_cvsx_set(struct task_struct *target,
-			const struct user_regset *regset,
-			unsigned int pos, unsigned int count,
-			const void *kbuf, const void __user *ubuf)
-{
-	u64 buf[32];
-	int ret, i;
-
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
-		return -ENODATA;
-
-	/* Flush the state */
-	flush_tmregs_to_thread(target);
-	flush_fp_to_thread(target);
-	flush_altivec_to_thread(target);
-	flush_vsx_to_thread(target);
-
-	for (i = 0; i < 32 ; i++)
-		buf[i] = target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET];
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 buf, 0, 32 * sizeof(double));
-	if (!ret)
-		for (i = 0; i < 32 ; i++)
-			target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
-
-	return ret;
-}
-
-/**
- * tm_spr_active - get active number of registers in TM SPR
- * @target:	The target task.
- * @regset:	The user regset structure.
- *
- * This function checks the active number of available
- * regisers in the transactional memory SPR category.
- */
-static int tm_spr_active(struct task_struct *target,
-			 const struct user_regset *regset)
-{
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	return regset->n;
-}
-
-/**
- * tm_spr_get - get the TM related SPR registers
- * @target:	The target task.
- * @regset:	The user regset structure.
- * @pos:	The buffer position.
- * @count:	Number of bytes to copy.
- * @kbuf:	Kernel buffer to copy from.
- * @ubuf:	User buffer to copy into.
- *
- * This function gets transactional memory related SPR registers.
- * The userspace interface buffer layout is as follows.
- *
- * struct {
- *	u64		tm_tfhar;
- *	u64		tm_texasr;
- *	u64		tm_tfiar;
- * };
- */
-static int tm_spr_get(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      void *kbuf, void __user *ubuf)
-{
-	int ret;
-
-	/* Build tests */
-	BUILD_BUG_ON(TSO(tm_tfhar) + sizeof(u64) != TSO(tm_texasr));
-	BUILD_BUG_ON(TSO(tm_texasr) + sizeof(u64) != TSO(tm_tfiar));
-	BUILD_BUG_ON(TSO(tm_tfiar) + sizeof(u64) != TSO(ckpt_regs));
-
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	/* Flush the states */
-	flush_tmregs_to_thread(target);
-	flush_fp_to_thread(target);
-	flush_altivec_to_thread(target);
-
-	/* TFHAR register */
-	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				&target->thread.tm_tfhar, 0, sizeof(u64));
-
-	/* TEXASR register */
-	if (!ret)
-		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				&target->thread.tm_texasr, sizeof(u64),
-				2 * sizeof(u64));
-
-	/* TFIAR register */
-	if (!ret)
-		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				&target->thread.tm_tfiar,
-				2 * sizeof(u64), 3 * sizeof(u64));
-	return ret;
-}
-
-/**
- * tm_spr_set - set the TM related SPR registers
- * @target:	The target task.
- * @regset:	The user regset structure.
- * @pos:	The buffer position.
- * @count:	Number of bytes to copy.
- * @kbuf:	Kernel buffer to copy into.
- * @ubuf:	User buffer to copy from.
- *
- * This function sets transactional memory related SPR registers.
- * The userspace interface buffer layout is as follows.
- *
- * struct {
- *	u64		tm_tfhar;
- *	u64		tm_texasr;
- *	u64		tm_tfiar;
- * };
- */
-static int tm_spr_set(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      const void *kbuf, const void __user *ubuf)
-{
-	int ret;
-
-	/* Build tests */
-	BUILD_BUG_ON(TSO(tm_tfhar) + sizeof(u64) != TSO(tm_texasr));
-	BUILD_BUG_ON(TSO(tm_texasr) + sizeof(u64) != TSO(tm_tfiar));
-	BUILD_BUG_ON(TSO(tm_tfiar) + sizeof(u64) != TSO(ckpt_regs));
-
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	/* Flush the states */
-	flush_tmregs_to_thread(target);
-	flush_fp_to_thread(target);
-	flush_altivec_to_thread(target);
-
-	/* TFHAR register */
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				&target->thread.tm_tfhar, 0, sizeof(u64));
-
-	/* TEXASR register */
-	if (!ret)
-		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				&target->thread.tm_texasr, sizeof(u64),
-				2 * sizeof(u64));
-
-	/* TFIAR register */
-	if (!ret)
-		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				&target->thread.tm_tfiar,
-				 2 * sizeof(u64), 3 * sizeof(u64));
-	return ret;
-}
-
-static int tm_tar_active(struct task_struct *target,
-			 const struct user_regset *regset)
-{
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (MSR_TM_ACTIVE(target->thread.regs->msr))
-		return regset->n;
-
-	return 0;
-}
-
-static int tm_tar_get(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      void *kbuf, void __user *ubuf)
-{
-	int ret;
-
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
-		return -ENODATA;
-
-	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				&target->thread.tm_tar, 0, sizeof(u64));
-	return ret;
-}
-
-static int tm_tar_set(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      const void *kbuf, const void __user *ubuf)
-{
-	int ret;
-
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
-		return -ENODATA;
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				&target->thread.tm_tar, 0, sizeof(u64));
-	return ret;
-}
-
-static int tm_ppr_active(struct task_struct *target,
-			 const struct user_regset *regset)
-{
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (MSR_TM_ACTIVE(target->thread.regs->msr))
-		return regset->n;
-
-	return 0;
-}
-
-
-static int tm_ppr_get(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      void *kbuf, void __user *ubuf)
-{
-	int ret;
-
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
-		return -ENODATA;
-
-	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				&target->thread.tm_ppr, 0, sizeof(u64));
-	return ret;
-}
-
-static int tm_ppr_set(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      const void *kbuf, const void __user *ubuf)
-{
-	int ret;
-
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
-		return -ENODATA;
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				&target->thread.tm_ppr, 0, sizeof(u64));
-	return ret;
-}
-
-static int tm_dscr_active(struct task_struct *target,
-			 const struct user_regset *regset)
-{
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (MSR_TM_ACTIVE(target->thread.regs->msr))
-		return regset->n;
-
-	return 0;
-}
-
-static int tm_dscr_get(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      void *kbuf, void __user *ubuf)
-{
-	int ret;
-
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
-		return -ENODATA;
-
-	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				&target->thread.tm_dscr, 0, sizeof(u64));
-	return ret;
-}
-
-static int tm_dscr_set(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      const void *kbuf, const void __user *ubuf)
-{
-	int ret;
-
-	if (!cpu_has_feature(CPU_FTR_TM))
-		return -ENODEV;
-
-	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
-		return -ENODATA;
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				&target->thread.tm_dscr, 0, sizeof(u64));
-	return ret;
-}
-#endif	/* CONFIG_PPC_TRANSACTIONAL_MEM */
-
-#ifdef CONFIG_PPC64
-static int ppr_get(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      void *kbuf, void __user *ubuf)
-{
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				   &target->thread.regs->ppr, 0, sizeof(u64));
-}
-
-static int ppr_set(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      const void *kbuf, const void __user *ubuf)
-{
-	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				  &target->thread.regs->ppr, 0, sizeof(u64));
-}
-
-static int dscr_get(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      void *kbuf, void __user *ubuf)
-{
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				   &target->thread.dscr, 0, sizeof(u64));
-}
-static int dscr_set(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      const void *kbuf, const void __user *ubuf)
-{
-	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				  &target->thread.dscr, 0, sizeof(u64));
-}
-#endif
-#ifdef CONFIG_PPC_BOOK3S_64
-static int tar_get(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      void *kbuf, void __user *ubuf)
-{
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				   &target->thread.tar, 0, sizeof(u64));
-}
-static int tar_set(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      const void *kbuf, const void __user *ubuf)
-{
-	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				  &target->thread.tar, 0, sizeof(u64));
-}
-
-static int ebb_active(struct task_struct *target,
-			 const struct user_regset *regset)
-{
-	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
-		return -ENODEV;
-
-	if (target->thread.used_ebb)
-		return regset->n;
-
-	return 0;
-}
-
-static int ebb_get(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      void *kbuf, void __user *ubuf)
-{
-	/* Build tests */
-	BUILD_BUG_ON(TSO(ebbrr) + sizeof(unsigned long) != TSO(ebbhr));
-	BUILD_BUG_ON(TSO(ebbhr) + sizeof(unsigned long) != TSO(bescr));
-
-	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
-		return -ENODEV;
-
-	if (!target->thread.used_ebb)
-		return -ENODATA;
-
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-			&target->thread.ebbrr, 0, 3 * sizeof(unsigned long));
-}
-
-static int ebb_set(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      const void *kbuf, const void __user *ubuf)
-{
-	int ret = 0;
-
-	/* Build tests */
-	BUILD_BUG_ON(TSO(ebbrr) + sizeof(unsigned long) != TSO(ebbhr));
-	BUILD_BUG_ON(TSO(ebbhr) + sizeof(unsigned long) != TSO(bescr));
-
-	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
-		return -ENODEV;
-
-	if (target->thread.used_ebb)
-		return -ENODATA;
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-			&target->thread.ebbrr, 0, sizeof(unsigned long));
-
-	if (!ret)
-		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-			&target->thread.ebbhr, sizeof(unsigned long),
-			2 * sizeof(unsigned long));
-
-	if (!ret)
-		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-			&target->thread.bescr,
-			2 * sizeof(unsigned long), 3 * sizeof(unsigned long));
-
-	return ret;
-}
-static int pmu_active(struct task_struct *target,
-			 const struct user_regset *regset)
-{
-	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
-		return -ENODEV;
-
-	return regset->n;
-}
-
-static int pmu_get(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      void *kbuf, void __user *ubuf)
-{
-	/* Build tests */
-	BUILD_BUG_ON(TSO(siar) + sizeof(unsigned long) != TSO(sdar));
-	BUILD_BUG_ON(TSO(sdar) + sizeof(unsigned long) != TSO(sier));
-	BUILD_BUG_ON(TSO(sier) + sizeof(unsigned long) != TSO(mmcr2));
-	BUILD_BUG_ON(TSO(mmcr2) + sizeof(unsigned long) != TSO(mmcr0));
-
-	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
-		return -ENODEV;
-
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-			&target->thread.siar, 0,
-			5 * sizeof(unsigned long));
-}
-
-static int pmu_set(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      const void *kbuf, const void __user *ubuf)
-{
-	int ret = 0;
-
-	/* Build tests */
-	BUILD_BUG_ON(TSO(siar) + sizeof(unsigned long) != TSO(sdar));
-	BUILD_BUG_ON(TSO(sdar) + sizeof(unsigned long) != TSO(sier));
-	BUILD_BUG_ON(TSO(sier) + sizeof(unsigned long) != TSO(mmcr2));
-	BUILD_BUG_ON(TSO(mmcr2) + sizeof(unsigned long) != TSO(mmcr0));
-
-	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
-		return -ENODEV;
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-			&target->thread.siar, 0,
-			sizeof(unsigned long));
-
-	if (!ret)
-		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-			&target->thread.sdar, sizeof(unsigned long),
-			2 * sizeof(unsigned long));
-
-	if (!ret)
-		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-			&target->thread.sier, 2 * sizeof(unsigned long),
-			3 * sizeof(unsigned long));
-
-	if (!ret)
-		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-			&target->thread.mmcr2, 3 * sizeof(unsigned long),
-			4 * sizeof(unsigned long));
-
-	if (!ret)
-		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-			&target->thread.mmcr0, 4 * sizeof(unsigned long),
-			5 * sizeof(unsigned long));
-	return ret;
-}
-#endif
-
-#ifdef CONFIG_PPC_MEM_KEYS
-static int pkey_active(struct task_struct *target,
-		       const struct user_regset *regset)
-{
-	if (!arch_pkeys_enabled())
-		return -ENODEV;
-
-	return regset->n;
-}
-
-static int pkey_get(struct task_struct *target,
-		    const struct user_regset *regset,
-		    unsigned int pos, unsigned int count,
-		    void *kbuf, void __user *ubuf)
-{
-	BUILD_BUG_ON(TSO(amr) + sizeof(unsigned long) != TSO(iamr));
-	BUILD_BUG_ON(TSO(iamr) + sizeof(unsigned long) != TSO(uamor));
-
-	if (!arch_pkeys_enabled())
-		return -ENODEV;
-
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				   &target->thread.amr, 0,
-				   ELF_NPKEY * sizeof(unsigned long));
-}
-
-static int pkey_set(struct task_struct *target,
-		      const struct user_regset *regset,
-		      unsigned int pos, unsigned int count,
-		      const void *kbuf, const void __user *ubuf)
-{
-	u64 new_amr;
-	int ret;
-
-	if (!arch_pkeys_enabled())
-		return -ENODEV;
-
-	/* Only the AMR can be set from userspace */
-	if (pos != 0 || count != sizeof(new_amr))
-		return -EINVAL;
-
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 &new_amr, 0, sizeof(new_amr));
-	if (ret)
-		return ret;
-
-	/* UAMOR determines which bits of the AMR can be set from userspace. */
-	target->thread.amr = (new_amr & target->thread.uamor) |
-		(target->thread.amr & ~target->thread.uamor);
-
-	return 0;
-}
-#endif /* CONFIG_PPC_MEM_KEYS */
-
-/*
- * These are our native regset flavors.
- */
-enum powerpc_regset {
-	REGSET_GPR,
-	REGSET_FPR,
-#ifdef CONFIG_ALTIVEC
-	REGSET_VMX,
-#endif
-#ifdef CONFIG_VSX
-	REGSET_VSX,
-#endif
-#ifdef CONFIG_SPE
-	REGSET_SPE,
-#endif
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	REGSET_TM_CGPR,		/* TM checkpointed GPR registers */
-	REGSET_TM_CFPR,		/* TM checkpointed FPR registers */
-	REGSET_TM_CVMX,		/* TM checkpointed VMX registers */
-	REGSET_TM_CVSX,		/* TM checkpointed VSX registers */
-	REGSET_TM_SPR,		/* TM specific SPR registers */
-	REGSET_TM_CTAR,		/* TM checkpointed TAR register */
-	REGSET_TM_CPPR,		/* TM checkpointed PPR register */
-	REGSET_TM_CDSCR,	/* TM checkpointed DSCR register */
-#endif
-#ifdef CONFIG_PPC64
-	REGSET_PPR,		/* PPR register */
-	REGSET_DSCR,		/* DSCR register */
-#endif
-#ifdef CONFIG_PPC_BOOK3S_64
-	REGSET_TAR,		/* TAR register */
-	REGSET_EBB,		/* EBB registers */
-	REGSET_PMR,		/* Performance Monitor Registers */
-#endif
-#ifdef CONFIG_PPC_MEM_KEYS
-	REGSET_PKEY,		/* AMR register */
-#endif
-};
-
-static const struct user_regset native_regsets[] = {
-	[REGSET_GPR] = {
-		.core_note_type = NT_PRSTATUS, .n = ELF_NGREG,
-		.size = sizeof(long), .align = sizeof(long),
-		.get = gpr_get, .set = gpr_set
-	},
-	[REGSET_FPR] = {
-		.core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
-		.size = sizeof(double), .align = sizeof(double),
-		.get = fpr_get, .set = fpr_set
-	},
-#ifdef CONFIG_ALTIVEC
-	[REGSET_VMX] = {
-		.core_note_type = NT_PPC_VMX, .n = 34,
-		.size = sizeof(vector128), .align = sizeof(vector128),
-		.active = vr_active, .get = vr_get, .set = vr_set
-	},
-#endif
-#ifdef CONFIG_VSX
-	[REGSET_VSX] = {
-		.core_note_type = NT_PPC_VSX, .n = 32,
-		.size = sizeof(double), .align = sizeof(double),
-		.active = vsr_active, .get = vsr_get, .set = vsr_set
-	},
-#endif
-#ifdef CONFIG_SPE
-	[REGSET_SPE] = {
-		.core_note_type = NT_PPC_SPE, .n = 35,
-		.size = sizeof(u32), .align = sizeof(u32),
-		.active = evr_active, .get = evr_get, .set = evr_set
-	},
-#endif
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	[REGSET_TM_CGPR] = {
-		.core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG,
-		.size = sizeof(long), .align = sizeof(long),
-		.active = tm_cgpr_active, .get = tm_cgpr_get, .set = tm_cgpr_set
-	},
-	[REGSET_TM_CFPR] = {
-		.core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG,
-		.size = sizeof(double), .align = sizeof(double),
-		.active = tm_cfpr_active, .get = tm_cfpr_get, .set = tm_cfpr_set
-	},
-	[REGSET_TM_CVMX] = {
-		.core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX,
-		.size = sizeof(vector128), .align = sizeof(vector128),
-		.active = tm_cvmx_active, .get = tm_cvmx_get, .set = tm_cvmx_set
-	},
-	[REGSET_TM_CVSX] = {
-		.core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX,
-		.size = sizeof(double), .align = sizeof(double),
-		.active = tm_cvsx_active, .get = tm_cvsx_get, .set = tm_cvsx_set
-	},
-	[REGSET_TM_SPR] = {
-		.core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG,
-		.size = sizeof(u64), .align = sizeof(u64),
-		.active = tm_spr_active, .get = tm_spr_get, .set = tm_spr_set
-	},
-	[REGSET_TM_CTAR] = {
-		.core_note_type = NT_PPC_TM_CTAR, .n = 1,
-		.size = sizeof(u64), .align = sizeof(u64),
-		.active = tm_tar_active, .get = tm_tar_get, .set = tm_tar_set
-	},
-	[REGSET_TM_CPPR] = {
-		.core_note_type = NT_PPC_TM_CPPR, .n = 1,
-		.size = sizeof(u64), .align = sizeof(u64),
-		.active = tm_ppr_active, .get = tm_ppr_get, .set = tm_ppr_set
-	},
-	[REGSET_TM_CDSCR] = {
-		.core_note_type = NT_PPC_TM_CDSCR, .n = 1,
-		.size = sizeof(u64), .align = sizeof(u64),
-		.active = tm_dscr_active, .get = tm_dscr_get, .set = tm_dscr_set
-	},
-#endif
-#ifdef CONFIG_PPC64
-	[REGSET_PPR] = {
-		.core_note_type = NT_PPC_PPR, .n = 1,
-		.size = sizeof(u64), .align = sizeof(u64),
-		.get = ppr_get, .set = ppr_set
-	},
-	[REGSET_DSCR] = {
-		.core_note_type = NT_PPC_DSCR, .n = 1,
-		.size = sizeof(u64), .align = sizeof(u64),
-		.get = dscr_get, .set = dscr_set
-	},
-#endif
-#ifdef CONFIG_PPC_BOOK3S_64
-	[REGSET_TAR] = {
-		.core_note_type = NT_PPC_TAR, .n = 1,
-		.size = sizeof(u64), .align = sizeof(u64),
-		.get = tar_get, .set = tar_set
-	},
-	[REGSET_EBB] = {
-		.core_note_type = NT_PPC_EBB, .n = ELF_NEBB,
-		.size = sizeof(u64), .align = sizeof(u64),
-		.active = ebb_active, .get = ebb_get, .set = ebb_set
-	},
-	[REGSET_PMR] = {
-		.core_note_type = NT_PPC_PMU, .n = ELF_NPMU,
-		.size = sizeof(u64), .align = sizeof(u64),
-		.active = pmu_active, .get = pmu_get, .set = pmu_set
-	},
-#endif
-#ifdef CONFIG_PPC_MEM_KEYS
-	[REGSET_PKEY] = {
-		.core_note_type = NT_PPC_PKEY, .n = ELF_NPKEY,
-		.size = sizeof(u64), .align = sizeof(u64),
-		.active = pkey_active, .get = pkey_get, .set = pkey_set
-	},
-#endif
-};
-
-static const struct user_regset_view user_ppc_native_view = {
-	.name = UTS_MACHINE, .e_machine = ELF_ARCH, .ei_osabi = ELF_OSABI,
-	.regsets = native_regsets, .n = ARRAY_SIZE(native_regsets)
-};
-
-#ifdef CONFIG_PPC64
-#include <linux/compat.h>
-
-static int gpr32_get_common(struct task_struct *target,
-		     const struct user_regset *regset,
-		     unsigned int pos, unsigned int count,
-			    void *kbuf, void __user *ubuf,
-			    unsigned long *regs)
-{
-	compat_ulong_t *k = kbuf;
-	compat_ulong_t __user *u = ubuf;
-	compat_ulong_t reg;
-
-	pos /= sizeof(reg);
-	count /= sizeof(reg);
-
-	if (kbuf)
-		for (; count > 0 && pos < PT_MSR; --count)
-			*k++ = regs[pos++];
-	else
-		for (; count > 0 && pos < PT_MSR; --count)
-			if (__put_user((compat_ulong_t) regs[pos++], u++))
-				return -EFAULT;
-
-	if (count > 0 && pos == PT_MSR) {
-		reg = get_user_msr(target);
-		if (kbuf)
-			*k++ = reg;
-		else if (__put_user(reg, u++))
-			return -EFAULT;
-		++pos;
-		--count;
-	}
-
-	if (kbuf)
-		for (; count > 0 && pos < PT_REGS_COUNT; --count)
-			*k++ = regs[pos++];
-	else
-		for (; count > 0 && pos < PT_REGS_COUNT; --count)
-			if (__put_user((compat_ulong_t) regs[pos++], u++))
-				return -EFAULT;
-
-	kbuf = k;
-	ubuf = u;
-	pos *= sizeof(reg);
-	count *= sizeof(reg);
-	return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
-					PT_REGS_COUNT * sizeof(reg), -1);
-}
-
-static int gpr32_set_common(struct task_struct *target,
-		     const struct user_regset *regset,
-		     unsigned int pos, unsigned int count,
-		     const void *kbuf, const void __user *ubuf,
-		     unsigned long *regs)
-{
-	const compat_ulong_t *k = kbuf;
-	const compat_ulong_t __user *u = ubuf;
-	compat_ulong_t reg;
-
-	pos /= sizeof(reg);
-	count /= sizeof(reg);
-
-	if (kbuf)
-		for (; count > 0 && pos < PT_MSR; --count)
-			regs[pos++] = *k++;
-	else
-		for (; count > 0 && pos < PT_MSR; --count) {
-			if (__get_user(reg, u++))
-				return -EFAULT;
-			regs[pos++] = reg;
-		}
-
-
-	if (count > 0 && pos == PT_MSR) {
-		if (kbuf)
-			reg = *k++;
-		else if (__get_user(reg, u++))
-			return -EFAULT;
-		set_user_msr(target, reg);
-		++pos;
-		--count;
-	}
-
-	if (kbuf) {
-		for (; count > 0 && pos <= PT_MAX_PUT_REG; --count)
-			regs[pos++] = *k++;
-		for (; count > 0 && pos < PT_TRAP; --count, ++pos)
-			++k;
-	} else {
-		for (; count > 0 && pos <= PT_MAX_PUT_REG; --count) {
-			if (__get_user(reg, u++))
-				return -EFAULT;
-			regs[pos++] = reg;
-		}
-		for (; count > 0 && pos < PT_TRAP; --count, ++pos)
-			if (__get_user(reg, u++))
-				return -EFAULT;
-	}
-
-	if (count > 0 && pos == PT_TRAP) {
-		if (kbuf)
-			reg = *k++;
-		else if (__get_user(reg, u++))
-			return -EFAULT;
-		set_user_trap(target, reg);
-		++pos;
-		--count;
-	}
-
-	kbuf = k;
-	ubuf = u;
-	pos *= sizeof(reg);
-	count *= sizeof(reg);
-	return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
-					 (PT_TRAP + 1) * sizeof(reg), -1);
-}
-
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-static int tm_cgpr32_get(struct task_struct *target,
-		     const struct user_regset *regset,
-		     unsigned int pos, unsigned int count,
-		     void *kbuf, void __user *ubuf)
-{
-	return gpr32_get_common(target, regset, pos, count, kbuf, ubuf,
-			&target->thread.ckpt_regs.gpr[0]);
-}
-
-static int tm_cgpr32_set(struct task_struct *target,
-		     const struct user_regset *regset,
-		     unsigned int pos, unsigned int count,
-		     const void *kbuf, const void __user *ubuf)
-{
-	return gpr32_set_common(target, regset, pos, count, kbuf, ubuf,
-			&target->thread.ckpt_regs.gpr[0]);
-}
-#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
-
-static int gpr32_get(struct task_struct *target,
-		     const struct user_regset *regset,
-		     unsigned int pos, unsigned int count,
-		     void *kbuf, void __user *ubuf)
-{
-	int i;
-
-	if (target->thread.regs == NULL)
-		return -EIO;
-
-	if (!FULL_REGS(target->thread.regs)) {
-		/*
-		 * We have a partial register set.
-		 * Fill 14-31 with bogus values.
-		 */
-		for (i = 14; i < 32; i++)
-			target->thread.regs->gpr[i] = NV_REG_POISON;
-	}
-	return gpr32_get_common(target, regset, pos, count, kbuf, ubuf,
-			&target->thread.regs->gpr[0]);
-}
-
-static int gpr32_set(struct task_struct *target,
-		     const struct user_regset *regset,
-		     unsigned int pos, unsigned int count,
-		     const void *kbuf, const void __user *ubuf)
-{
-	if (target->thread.regs == NULL)
-		return -EIO;
-
-	CHECK_FULL_REGS(target->thread.regs);
-	return gpr32_set_common(target, regset, pos, count, kbuf, ubuf,
-			&target->thread.regs->gpr[0]);
-}
-
-/*
- * These are the regset flavors matching the CONFIG_PPC32 native set.
- */
-static const struct user_regset compat_regsets[] = {
-	[REGSET_GPR] = {
-		.core_note_type = NT_PRSTATUS, .n = ELF_NGREG,
-		.size = sizeof(compat_long_t), .align = sizeof(compat_long_t),
-		.get = gpr32_get, .set = gpr32_set
-	},
-	[REGSET_FPR] = {
-		.core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
-		.size = sizeof(double), .align = sizeof(double),
-		.get = fpr_get, .set = fpr_set
-	},
-#ifdef CONFIG_ALTIVEC
-	[REGSET_VMX] = {
-		.core_note_type = NT_PPC_VMX, .n = 34,
-		.size = sizeof(vector128), .align = sizeof(vector128),
-		.active = vr_active, .get = vr_get, .set = vr_set
-	},
-#endif
-#ifdef CONFIG_SPE
-	[REGSET_SPE] = {
-		.core_note_type = NT_PPC_SPE, .n = 35,
-		.size = sizeof(u32), .align = sizeof(u32),
-		.active = evr_active, .get = evr_get, .set = evr_set
-	},
-#endif
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	[REGSET_TM_CGPR] = {
-		.core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG,
-		.size = sizeof(long), .align = sizeof(long),
-		.active = tm_cgpr_active,
-		.get = tm_cgpr32_get, .set = tm_cgpr32_set
-	},
-	[REGSET_TM_CFPR] = {
-		.core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG,
-		.size = sizeof(double), .align = sizeof(double),
-		.active = tm_cfpr_active, .get = tm_cfpr_get, .set = tm_cfpr_set
-	},
-	[REGSET_TM_CVMX] = {
-		.core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX,
-		.size = sizeof(vector128), .align = sizeof(vector128),
-		.active = tm_cvmx_active, .get = tm_cvmx_get, .set = tm_cvmx_set
-	},
-	[REGSET_TM_CVSX] = {
-		.core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX,
-		.size = sizeof(double), .align = sizeof(double),
-		.active = tm_cvsx_active, .get = tm_cvsx_get, .set = tm_cvsx_set
-	},
-	[REGSET_TM_SPR] = {
-		.core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG,
-		.size = sizeof(u64), .align = sizeof(u64),
-		.active = tm_spr_active, .get = tm_spr_get, .set = tm_spr_set
-	},
-	[REGSET_TM_CTAR] = {
-		.core_note_type = NT_PPC_TM_CTAR, .n = 1,
-		.size = sizeof(u64), .align = sizeof(u64),
-		.active = tm_tar_active, .get = tm_tar_get, .set = tm_tar_set
-	},
-	[REGSET_TM_CPPR] = {
-		.core_note_type = NT_PPC_TM_CPPR, .n = 1,
-		.size = sizeof(u64), .align = sizeof(u64),
-		.active = tm_ppr_active, .get = tm_ppr_get, .set = tm_ppr_set
-	},
-	[REGSET_TM_CDSCR] = {
-		.core_note_type = NT_PPC_TM_CDSCR, .n = 1,
-		.size = sizeof(u64), .align = sizeof(u64),
-		.active = tm_dscr_active, .get = tm_dscr_get, .set = tm_dscr_set
-	},
-#endif
-#ifdef CONFIG_PPC64
-	[REGSET_PPR] = {
-		.core_note_type = NT_PPC_PPR, .n = 1,
-		.size = sizeof(u64), .align = sizeof(u64),
-		.get = ppr_get, .set = ppr_set
-	},
-	[REGSET_DSCR] = {
-		.core_note_type = NT_PPC_DSCR, .n = 1,
-		.size = sizeof(u64), .align = sizeof(u64),
-		.get = dscr_get, .set = dscr_set
-	},
-#endif
-#ifdef CONFIG_PPC_BOOK3S_64
-	[REGSET_TAR] = {
-		.core_note_type = NT_PPC_TAR, .n = 1,
-		.size = sizeof(u64), .align = sizeof(u64),
-		.get = tar_get, .set = tar_set
-	},
-	[REGSET_EBB] = {
-		.core_note_type = NT_PPC_EBB, .n = ELF_NEBB,
-		.size = sizeof(u64), .align = sizeof(u64),
-		.active = ebb_active, .get = ebb_get, .set = ebb_set
-	},
-#endif
-};
-
-static const struct user_regset_view user_ppc_compat_view = {
-	.name = "ppc", .e_machine = EM_PPC, .ei_osabi = ELF_OSABI,
-	.regsets = compat_regsets, .n = ARRAY_SIZE(compat_regsets)
-};
-#endif	/* CONFIG_PPC64 */
-
-const struct user_regset_view *task_user_regset_view(struct task_struct *task)
-{
-#ifdef CONFIG_PPC64
-	if (test_tsk_thread_flag(task, TIF_32BIT))
-		return &user_ppc_compat_view;
-#endif
-	return &user_ppc_native_view;
-}
-
-
-void user_enable_single_step(struct task_struct *task)
-{
-	struct pt_regs *regs = task->thread.regs;
-
-	if (regs != NULL) {
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-		task->thread.debug.dbcr0 &= ~DBCR0_BT;
-		task->thread.debug.dbcr0 |= DBCR0_IDM | DBCR0_IC;
-		regs->msr |= MSR_DE;
-#else
-		regs->msr &= ~MSR_BE;
-		regs->msr |= MSR_SE;
-#endif
-	}
-	set_tsk_thread_flag(task, TIF_SINGLESTEP);
-}
-
-void user_enable_block_step(struct task_struct *task)
-{
-	struct pt_regs *regs = task->thread.regs;
-
-	if (regs != NULL) {
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-		task->thread.debug.dbcr0 &= ~DBCR0_IC;
-		task->thread.debug.dbcr0 = DBCR0_IDM | DBCR0_BT;
-		regs->msr |= MSR_DE;
-#else
-		regs->msr &= ~MSR_SE;
-		regs->msr |= MSR_BE;
-#endif
-	}
-	set_tsk_thread_flag(task, TIF_SINGLESTEP);
-}
-
-void user_disable_single_step(struct task_struct *task)
-{
-	struct pt_regs *regs = task->thread.regs;
-
-	if (regs != NULL) {
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-		/*
-		 * The logic to disable single stepping should be as
-		 * simple as turning off the Instruction Complete flag.
-		 * And, after doing so, if all debug flags are off, turn
-		 * off DBCR0(IDM) and MSR(DE) .... Torez
-		 */
-		task->thread.debug.dbcr0 &= ~(DBCR0_IC|DBCR0_BT);
-		/*
-		 * Test to see if any of the DBCR_ACTIVE_EVENTS bits are set.
-		 */
-		if (!DBCR_ACTIVE_EVENTS(task->thread.debug.dbcr0,
-					task->thread.debug.dbcr1)) {
-			/*
-			 * All debug events were off.....
-			 */
-			task->thread.debug.dbcr0 &= ~DBCR0_IDM;
-			regs->msr &= ~MSR_DE;
-		}
-#else
-		regs->msr &= ~(MSR_SE | MSR_BE);
-#endif
-	}
-	clear_tsk_thread_flag(task, TIF_SINGLESTEP);
-}
-
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
-void ptrace_triggered(struct perf_event *bp,
-		      struct perf_sample_data *data, struct pt_regs *regs)
-{
-	struct perf_event_attr attr;
-
-	/*
-	 * Disable the breakpoint request here since ptrace has defined a
-	 * one-shot behaviour for breakpoint exceptions in PPC64.
-	 * The SIGTRAP signal is generated automatically for us in do_dabr().
-	 * We don't have to do anything about that here
-	 */
-	attr = bp->attr;
-	attr.disabled = true;
-	modify_user_hw_breakpoint(bp, &attr);
-}
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
-
-static int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
-			       unsigned long data)
-{
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
-	int ret;
-	struct thread_struct *thread = &(task->thread);
-	struct perf_event *bp;
-	struct perf_event_attr attr;
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
-#ifndef CONFIG_PPC_ADV_DEBUG_REGS
-	bool set_bp = true;
-	struct arch_hw_breakpoint hw_brk;
-#endif
-
-	/* For ppc64 we support one DABR and no IABR's at the moment (ppc64).
-	 *  For embedded processors we support one DAC and no IAC's at the
-	 *  moment.
-	 */
-	if (addr > 0)
-		return -EINVAL;
-
-	/* The bottom 3 bits in dabr are flags */
-	if ((data & ~0x7UL) >= TASK_SIZE)
-		return -EIO;
-
-#ifndef CONFIG_PPC_ADV_DEBUG_REGS
-	/* For processors using DABR (i.e. 970), the bottom 3 bits are flags.
-	 *  It was assumed, on previous implementations, that 3 bits were
-	 *  passed together with the data address, fitting the design of the
-	 *  DABR register, as follows:
-	 *
-	 *  bit 0: Read flag
-	 *  bit 1: Write flag
-	 *  bit 2: Breakpoint translation
-	 *
-	 *  Thus, we use them here as so.
-	 */
-
-	/* Ensure breakpoint translation bit is set */
-	if (data && !(data & HW_BRK_TYPE_TRANSLATE))
-		return -EIO;
-	hw_brk.address = data & (~HW_BRK_TYPE_DABR);
-	hw_brk.type = (data & HW_BRK_TYPE_DABR) | HW_BRK_TYPE_PRIV_ALL;
-	hw_brk.len = DABR_MAX_LEN;
-	hw_brk.hw_len = DABR_MAX_LEN;
-	set_bp = (data) && (hw_brk.type & HW_BRK_TYPE_RDWR);
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
-	bp = thread->ptrace_bps[0];
-	if (!set_bp) {
-		if (bp) {
-			unregister_hw_breakpoint(bp);
-			thread->ptrace_bps[0] = NULL;
-		}
-		return 0;
-	}
-	if (bp) {
-		attr = bp->attr;
-		attr.bp_addr = hw_brk.address;
-		attr.bp_len = DABR_MAX_LEN;
-		arch_bp_generic_fields(hw_brk.type, &attr.bp_type);
-
-		/* Enable breakpoint */
-		attr.disabled = false;
-
-		ret =  modify_user_hw_breakpoint(bp, &attr);
-		if (ret) {
-			return ret;
-		}
-		thread->ptrace_bps[0] = bp;
-		thread->hw_brk = hw_brk;
-		return 0;
-	}
-
-	/* Create a new breakpoint request if one doesn't exist already */
-	hw_breakpoint_init(&attr);
-	attr.bp_addr = hw_brk.address;
-	attr.bp_len = DABR_MAX_LEN;
-	arch_bp_generic_fields(hw_brk.type,
-			       &attr.bp_type);
-
-	thread->ptrace_bps[0] = bp = register_user_hw_breakpoint(&attr,
-					       ptrace_triggered, NULL, task);
-	if (IS_ERR(bp)) {
-		thread->ptrace_bps[0] = NULL;
-		return PTR_ERR(bp);
-	}
-
-#else /* !CONFIG_HAVE_HW_BREAKPOINT */
-	if (set_bp && (!ppc_breakpoint_available()))
-		return -ENODEV;
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
-	task->thread.hw_brk = hw_brk;
-#else /* CONFIG_PPC_ADV_DEBUG_REGS */
-	/* As described above, it was assumed 3 bits were passed with the data
-	 *  address, but we will assume only the mode bits will be passed
-	 *  as to not cause alignment restrictions for DAC-based processors.
-	 */
-
-	/* DAC's hold the whole address without any mode flags */
-	task->thread.debug.dac1 = data & ~0x3UL;
-
-	if (task->thread.debug.dac1 == 0) {
-		dbcr_dac(task) &= ~(DBCR_DAC1R | DBCR_DAC1W);
-		if (!DBCR_ACTIVE_EVENTS(task->thread.debug.dbcr0,
-					task->thread.debug.dbcr1)) {
-			task->thread.regs->msr &= ~MSR_DE;
-			task->thread.debug.dbcr0 &= ~DBCR0_IDM;
-		}
-		return 0;
-	}
-
-	/* Read or Write bits must be set */
-
-	if (!(data & 0x3UL))
-		return -EINVAL;
-
-	/* Set the Internal Debugging flag (IDM bit 1) for the DBCR0
-	   register */
-	task->thread.debug.dbcr0 |= DBCR0_IDM;
-
-	/* Check for write and read flags and set DBCR0
-	   accordingly */
-	dbcr_dac(task) &= ~(DBCR_DAC1R|DBCR_DAC1W);
-	if (data & 0x1UL)
-		dbcr_dac(task) |= DBCR_DAC1R;
-	if (data & 0x2UL)
-		dbcr_dac(task) |= DBCR_DAC1W;
-	task->thread.regs->msr |= MSR_DE;
-#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
-	return 0;
-}
-
-/*
- * Called by kernel/ptrace.c when detaching..
- *
- * Make sure single step bits etc are not set.
- */
-void ptrace_disable(struct task_struct *child)
-{
-	/* make sure the single step bit is not set. */
-	user_disable_single_step(child);
-}
-
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-static long set_instruction_bp(struct task_struct *child,
-			      struct ppc_hw_breakpoint *bp_info)
-{
-	int slot;
-	int slot1_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC1) != 0);
-	int slot2_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC2) != 0);
-	int slot3_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC3) != 0);
-	int slot4_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC4) != 0);
-
-	if (dbcr_iac_range(child) & DBCR_IAC12MODE)
-		slot2_in_use = 1;
-	if (dbcr_iac_range(child) & DBCR_IAC34MODE)
-		slot4_in_use = 1;
-
-	if (bp_info->addr >= TASK_SIZE)
-		return -EIO;
-
-	if (bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT) {
-
-		/* Make sure range is valid. */
-		if (bp_info->addr2 >= TASK_SIZE)
-			return -EIO;
-
-		/* We need a pair of IAC regsisters */
-		if ((!slot1_in_use) && (!slot2_in_use)) {
-			slot = 1;
-			child->thread.debug.iac1 = bp_info->addr;
-			child->thread.debug.iac2 = bp_info->addr2;
-			child->thread.debug.dbcr0 |= DBCR0_IAC1;
-			if (bp_info->addr_mode ==
-					PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE)
-				dbcr_iac_range(child) |= DBCR_IAC12X;
-			else
-				dbcr_iac_range(child) |= DBCR_IAC12I;
-#if CONFIG_PPC_ADV_DEBUG_IACS > 2
-		} else if ((!slot3_in_use) && (!slot4_in_use)) {
-			slot = 3;
-			child->thread.debug.iac3 = bp_info->addr;
-			child->thread.debug.iac4 = bp_info->addr2;
-			child->thread.debug.dbcr0 |= DBCR0_IAC3;
-			if (bp_info->addr_mode ==
-					PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE)
-				dbcr_iac_range(child) |= DBCR_IAC34X;
-			else
-				dbcr_iac_range(child) |= DBCR_IAC34I;
-#endif
-		} else
-			return -ENOSPC;
-	} else {
-		/* We only need one.  If possible leave a pair free in
-		 * case a range is needed later
-		 */
-		if (!slot1_in_use) {
-			/*
-			 * Don't use iac1 if iac1-iac2 are free and either
-			 * iac3 or iac4 (but not both) are free
-			 */
-			if (slot2_in_use || (slot3_in_use == slot4_in_use)) {
-				slot = 1;
-				child->thread.debug.iac1 = bp_info->addr;
-				child->thread.debug.dbcr0 |= DBCR0_IAC1;
-				goto out;
-			}
-		}
-		if (!slot2_in_use) {
-			slot = 2;
-			child->thread.debug.iac2 = bp_info->addr;
-			child->thread.debug.dbcr0 |= DBCR0_IAC2;
-#if CONFIG_PPC_ADV_DEBUG_IACS > 2
-		} else if (!slot3_in_use) {
-			slot = 3;
-			child->thread.debug.iac3 = bp_info->addr;
-			child->thread.debug.dbcr0 |= DBCR0_IAC3;
-		} else if (!slot4_in_use) {
-			slot = 4;
-			child->thread.debug.iac4 = bp_info->addr;
-			child->thread.debug.dbcr0 |= DBCR0_IAC4;
-#endif
-		} else
-			return -ENOSPC;
-	}
-out:
-	child->thread.debug.dbcr0 |= DBCR0_IDM;
-	child->thread.regs->msr |= MSR_DE;
-
-	return slot;
-}
-
-static int del_instruction_bp(struct task_struct *child, int slot)
-{
-	switch (slot) {
-	case 1:
-		if ((child->thread.debug.dbcr0 & DBCR0_IAC1) == 0)
-			return -ENOENT;
-
-		if (dbcr_iac_range(child) & DBCR_IAC12MODE) {
-			/* address range - clear slots 1 & 2 */
-			child->thread.debug.iac2 = 0;
-			dbcr_iac_range(child) &= ~DBCR_IAC12MODE;
-		}
-		child->thread.debug.iac1 = 0;
-		child->thread.debug.dbcr0 &= ~DBCR0_IAC1;
-		break;
-	case 2:
-		if ((child->thread.debug.dbcr0 & DBCR0_IAC2) == 0)
-			return -ENOENT;
-
-		if (dbcr_iac_range(child) & DBCR_IAC12MODE)
-			/* used in a range */
-			return -EINVAL;
-		child->thread.debug.iac2 = 0;
-		child->thread.debug.dbcr0 &= ~DBCR0_IAC2;
-		break;
-#if CONFIG_PPC_ADV_DEBUG_IACS > 2
-	case 3:
-		if ((child->thread.debug.dbcr0 & DBCR0_IAC3) == 0)
-			return -ENOENT;
-
-		if (dbcr_iac_range(child) & DBCR_IAC34MODE) {
-			/* address range - clear slots 3 & 4 */
-			child->thread.debug.iac4 = 0;
-			dbcr_iac_range(child) &= ~DBCR_IAC34MODE;
-		}
-		child->thread.debug.iac3 = 0;
-		child->thread.debug.dbcr0 &= ~DBCR0_IAC3;
-		break;
-	case 4:
-		if ((child->thread.debug.dbcr0 & DBCR0_IAC4) == 0)
-			return -ENOENT;
-
-		if (dbcr_iac_range(child) & DBCR_IAC34MODE)
-			/* Used in a range */
-			return -EINVAL;
-		child->thread.debug.iac4 = 0;
-		child->thread.debug.dbcr0 &= ~DBCR0_IAC4;
-		break;
-#endif
-	default:
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static int set_dac(struct task_struct *child, struct ppc_hw_breakpoint *bp_info)
-{
-	int byte_enable =
-		(bp_info->condition_mode >> PPC_BREAKPOINT_CONDITION_BE_SHIFT)
-		& 0xf;
-	int condition_mode =
-		bp_info->condition_mode & PPC_BREAKPOINT_CONDITION_MODE;
-	int slot;
-
-	if (byte_enable && (condition_mode == 0))
-		return -EINVAL;
-
-	if (bp_info->addr >= TASK_SIZE)
-		return -EIO;
-
-	if ((dbcr_dac(child) & (DBCR_DAC1R | DBCR_DAC1W)) == 0) {
-		slot = 1;
-		if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
-			dbcr_dac(child) |= DBCR_DAC1R;
-		if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
-			dbcr_dac(child) |= DBCR_DAC1W;
-		child->thread.debug.dac1 = (unsigned long)bp_info->addr;
-#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
-		if (byte_enable) {
-			child->thread.debug.dvc1 =
-				(unsigned long)bp_info->condition_value;
-			child->thread.debug.dbcr2 |=
-				((byte_enable << DBCR2_DVC1BE_SHIFT) |
-				 (condition_mode << DBCR2_DVC1M_SHIFT));
-		}
-#endif
-#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
-	} else if (child->thread.debug.dbcr2 & DBCR2_DAC12MODE) {
-		/* Both dac1 and dac2 are part of a range */
-		return -ENOSPC;
-#endif
-	} else if ((dbcr_dac(child) & (DBCR_DAC2R | DBCR_DAC2W)) == 0) {
-		slot = 2;
-		if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
-			dbcr_dac(child) |= DBCR_DAC2R;
-		if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
-			dbcr_dac(child) |= DBCR_DAC2W;
-		child->thread.debug.dac2 = (unsigned long)bp_info->addr;
-#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
-		if (byte_enable) {
-			child->thread.debug.dvc2 =
-				(unsigned long)bp_info->condition_value;
-			child->thread.debug.dbcr2 |=
-				((byte_enable << DBCR2_DVC2BE_SHIFT) |
-				 (condition_mode << DBCR2_DVC2M_SHIFT));
-		}
-#endif
-	} else
-		return -ENOSPC;
-	child->thread.debug.dbcr0 |= DBCR0_IDM;
-	child->thread.regs->msr |= MSR_DE;
-
-	return slot + 4;
-}
-
-static int del_dac(struct task_struct *child, int slot)
-{
-	if (slot == 1) {
-		if ((dbcr_dac(child) & (DBCR_DAC1R | DBCR_DAC1W)) == 0)
-			return -ENOENT;
-
-		child->thread.debug.dac1 = 0;
-		dbcr_dac(child) &= ~(DBCR_DAC1R | DBCR_DAC1W);
-#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
-		if (child->thread.debug.dbcr2 & DBCR2_DAC12MODE) {
-			child->thread.debug.dac2 = 0;
-			child->thread.debug.dbcr2 &= ~DBCR2_DAC12MODE;
-		}
-		child->thread.debug.dbcr2 &= ~(DBCR2_DVC1M | DBCR2_DVC1BE);
-#endif
-#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
-		child->thread.debug.dvc1 = 0;
-#endif
-	} else if (slot == 2) {
-		if ((dbcr_dac(child) & (DBCR_DAC2R | DBCR_DAC2W)) == 0)
-			return -ENOENT;
-
-#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
-		if (child->thread.debug.dbcr2 & DBCR2_DAC12MODE)
-			/* Part of a range */
-			return -EINVAL;
-		child->thread.debug.dbcr2 &= ~(DBCR2_DVC2M | DBCR2_DVC2BE);
-#endif
-#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
-		child->thread.debug.dvc2 = 0;
-#endif
-		child->thread.debug.dac2 = 0;
-		dbcr_dac(child) &= ~(DBCR_DAC2R | DBCR_DAC2W);
-	} else
-		return -EINVAL;
-
-	return 0;
-}
-#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
-
-#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
-static int set_dac_range(struct task_struct *child,
-			 struct ppc_hw_breakpoint *bp_info)
-{
-	int mode = bp_info->addr_mode & PPC_BREAKPOINT_MODE_MASK;
-
-	/* We don't allow range watchpoints to be used with DVC */
-	if (bp_info->condition_mode)
-		return -EINVAL;
-
-	/*
-	 * Best effort to verify the address range.  The user/supervisor bits
-	 * prevent trapping in kernel space, but let's fail on an obvious bad
-	 * range.  The simple test on the mask is not fool-proof, and any
-	 * exclusive range will spill over into kernel space.
-	 */
-	if (bp_info->addr >= TASK_SIZE)
-		return -EIO;
-	if (mode == PPC_BREAKPOINT_MODE_MASK) {
-		/*
-		 * dac2 is a bitmask.  Don't allow a mask that makes a
-		 * kernel space address from a valid dac1 value
-		 */
-		if (~((unsigned long)bp_info->addr2) >= TASK_SIZE)
-			return -EIO;
-	} else {
-		/*
-		 * For range breakpoints, addr2 must also be a valid address
-		 */
-		if (bp_info->addr2 >= TASK_SIZE)
-			return -EIO;
-	}
-
-	if (child->thread.debug.dbcr0 &
-	    (DBCR0_DAC1R | DBCR0_DAC1W | DBCR0_DAC2R | DBCR0_DAC2W))
-		return -ENOSPC;
-
-	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
-		child->thread.debug.dbcr0 |= (DBCR0_DAC1R | DBCR0_IDM);
-	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
-		child->thread.debug.dbcr0 |= (DBCR0_DAC1W | DBCR0_IDM);
-	child->thread.debug.dac1 = bp_info->addr;
-	child->thread.debug.dac2 = bp_info->addr2;
-	if (mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE)
-		child->thread.debug.dbcr2  |= DBCR2_DAC12M;
-	else if (mode == PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE)
-		child->thread.debug.dbcr2  |= DBCR2_DAC12MX;
-	else	/* PPC_BREAKPOINT_MODE_MASK */
-		child->thread.debug.dbcr2  |= DBCR2_DAC12MM;
-	child->thread.regs->msr |= MSR_DE;
-
-	return 5;
-}
-#endif /* CONFIG_PPC_ADV_DEBUG_DAC_RANGE */
-
-static long ppc_set_hwdebug(struct task_struct *child,
-		     struct ppc_hw_breakpoint *bp_info)
-{
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
-	int len = 0;
-	struct thread_struct *thread = &(child->thread);
-	struct perf_event *bp;
-	struct perf_event_attr attr;
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
-#ifndef CONFIG_PPC_ADV_DEBUG_REGS
-	struct arch_hw_breakpoint brk;
-#endif
-
-	if (bp_info->version != 1)
-		return -ENOTSUPP;
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-	/*
-	 * Check for invalid flags and combinations
-	 */
-	if ((bp_info->trigger_type == 0) ||
-	    (bp_info->trigger_type & ~(PPC_BREAKPOINT_TRIGGER_EXECUTE |
-				       PPC_BREAKPOINT_TRIGGER_RW)) ||
-	    (bp_info->addr_mode & ~PPC_BREAKPOINT_MODE_MASK) ||
-	    (bp_info->condition_mode &
-	     ~(PPC_BREAKPOINT_CONDITION_MODE |
-	       PPC_BREAKPOINT_CONDITION_BE_ALL)))
-		return -EINVAL;
-#if CONFIG_PPC_ADV_DEBUG_DVCS == 0
-	if (bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE)
-		return -EINVAL;
-#endif
-
-	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_EXECUTE) {
-		if ((bp_info->trigger_type != PPC_BREAKPOINT_TRIGGER_EXECUTE) ||
-		    (bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE))
-			return -EINVAL;
-		return set_instruction_bp(child, bp_info);
-	}
-	if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_EXACT)
-		return set_dac(child, bp_info);
-
-#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
-	return set_dac_range(child, bp_info);
-#else
-	return -EINVAL;
-#endif
-#else /* !CONFIG_PPC_ADV_DEBUG_DVCS */
-	/*
-	 * We only support one data breakpoint
-	 */
-	if ((bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_RW) == 0 ||
-	    (bp_info->trigger_type & ~PPC_BREAKPOINT_TRIGGER_RW) != 0 ||
-	    bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE)
-		return -EINVAL;
-
-	if ((unsigned long)bp_info->addr >= TASK_SIZE)
-		return -EIO;
-
-	brk.address = bp_info->addr & ~HW_BREAKPOINT_ALIGN;
-	brk.type = HW_BRK_TYPE_TRANSLATE;
-	brk.len = DABR_MAX_LEN;
-	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
-		brk.type |= HW_BRK_TYPE_READ;
-	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
-		brk.type |= HW_BRK_TYPE_WRITE;
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
-	if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE)
-		len = bp_info->addr2 - bp_info->addr;
-	else if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_EXACT)
-		len = 1;
-	else
-		return -EINVAL;
-	bp = thread->ptrace_bps[0];
-	if (bp)
-		return -ENOSPC;
-
-	/* Create a new breakpoint request if one doesn't exist already */
-	hw_breakpoint_init(&attr);
-	attr.bp_addr = (unsigned long)bp_info->addr;
-	attr.bp_len = len;
-	arch_bp_generic_fields(brk.type, &attr.bp_type);
-
-	thread->ptrace_bps[0] = bp = register_user_hw_breakpoint(&attr,
-					       ptrace_triggered, NULL, child);
-	if (IS_ERR(bp)) {
-		thread->ptrace_bps[0] = NULL;
-		return PTR_ERR(bp);
-	}
-
-	return 1;
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
-
-	if (bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT)
-		return -EINVAL;
-
-	if (child->thread.hw_brk.address)
-		return -ENOSPC;
-
-	if (!ppc_breakpoint_available())
-		return -ENODEV;
-
-	child->thread.hw_brk = brk;
-
-	return 1;
-#endif /* !CONFIG_PPC_ADV_DEBUG_DVCS */
-}
-
-static long ppc_del_hwdebug(struct task_struct *child, long data)
-{
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
-	int ret = 0;
-	struct thread_struct *thread = &(child->thread);
-	struct perf_event *bp;
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-	int rc;
-
-	if (data <= 4)
-		rc = del_instruction_bp(child, (int)data);
-	else
-		rc = del_dac(child, (int)data - 4);
-
-	if (!rc) {
-		if (!DBCR_ACTIVE_EVENTS(child->thread.debug.dbcr0,
-					child->thread.debug.dbcr1)) {
-			child->thread.debug.dbcr0 &= ~DBCR0_IDM;
-			child->thread.regs->msr &= ~MSR_DE;
-		}
-	}
-	return rc;
-#else
-	if (data != 1)
-		return -EINVAL;
-
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
-	bp = thread->ptrace_bps[0];
-	if (bp) {
-		unregister_hw_breakpoint(bp);
-		thread->ptrace_bps[0] = NULL;
-	} else
-		ret = -ENOENT;
-	return ret;
-#else /* CONFIG_HAVE_HW_BREAKPOINT */
-	if (child->thread.hw_brk.address == 0)
-		return -ENOENT;
-
-	child->thread.hw_brk.address = 0;
-	child->thread.hw_brk.type = 0;
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
-
-	return 0;
-#endif
-}
-
-long arch_ptrace(struct task_struct *child, long request,
-		 unsigned long addr, unsigned long data)
-{
-	int ret = -EPERM;
-	void __user *datavp = (void __user *) data;
-	unsigned long __user *datalp = datavp;
-
-	switch (request) {
-	/* read the word at location addr in the USER area. */
-	case PTRACE_PEEKUSR: {
-		unsigned long index, tmp;
-
-		ret = -EIO;
-		/* convert to index and check */
-#ifdef CONFIG_PPC32
-		index = addr >> 2;
-		if ((addr & 3) || (index > PT_FPSCR)
-		    || (child->thread.regs == NULL))
-#else
-		index = addr >> 3;
-		if ((addr & 7) || (index > PT_FPSCR))
-#endif
-			break;
-
-		CHECK_FULL_REGS(child->thread.regs);
-		if (index < PT_FPR0) {
-			ret = ptrace_get_reg(child, (int) index, &tmp);
-			if (ret)
-				break;
-		} else {
-			unsigned int fpidx = index - PT_FPR0;
-
-			flush_fp_to_thread(child);
-			if (fpidx < (PT_FPSCR - PT_FPR0))
-				memcpy(&tmp, &child->thread.TS_FPR(fpidx),
-				       sizeof(long));
-			else
-				tmp = child->thread.fp_state.fpscr;
-		}
-		ret = put_user(tmp, datalp);
-		break;
-	}
-
-	/* write the word at location addr in the USER area */
-	case PTRACE_POKEUSR: {
-		unsigned long index;
-
-		ret = -EIO;
-		/* convert to index and check */
-#ifdef CONFIG_PPC32
-		index = addr >> 2;
-		if ((addr & 3) || (index > PT_FPSCR)
-		    || (child->thread.regs == NULL))
-#else
-		index = addr >> 3;
-		if ((addr & 7) || (index > PT_FPSCR))
-#endif
-			break;
-
-		CHECK_FULL_REGS(child->thread.regs);
-		if (index < PT_FPR0) {
-			ret = ptrace_put_reg(child, index, data);
-		} else {
-			unsigned int fpidx = index - PT_FPR0;
-
-			flush_fp_to_thread(child);
-			if (fpidx < (PT_FPSCR - PT_FPR0))
-				memcpy(&child->thread.TS_FPR(fpidx), &data,
-				       sizeof(long));
-			else
-				child->thread.fp_state.fpscr = data;
-			ret = 0;
-		}
-		break;
-	}
-
-	case PPC_PTRACE_GETHWDBGINFO: {
-		struct ppc_debug_info dbginfo;
-
-		dbginfo.version = 1;
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-		dbginfo.num_instruction_bps = CONFIG_PPC_ADV_DEBUG_IACS;
-		dbginfo.num_data_bps = CONFIG_PPC_ADV_DEBUG_DACS;
-		dbginfo.num_condition_regs = CONFIG_PPC_ADV_DEBUG_DVCS;
-		dbginfo.data_bp_alignment = 4;
-		dbginfo.sizeof_condition = 4;
-		dbginfo.features = PPC_DEBUG_FEATURE_INSN_BP_RANGE |
-				   PPC_DEBUG_FEATURE_INSN_BP_MASK;
-#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
-		dbginfo.features |=
-				   PPC_DEBUG_FEATURE_DATA_BP_RANGE |
-				   PPC_DEBUG_FEATURE_DATA_BP_MASK;
-#endif
-#else /* !CONFIG_PPC_ADV_DEBUG_REGS */
-		dbginfo.num_instruction_bps = 0;
-		if (ppc_breakpoint_available())
-			dbginfo.num_data_bps = 1;
-		else
-			dbginfo.num_data_bps = 0;
-		dbginfo.num_condition_regs = 0;
-#ifdef CONFIG_PPC64
-		dbginfo.data_bp_alignment = 8;
-#else
-		dbginfo.data_bp_alignment = 4;
-#endif
-		dbginfo.sizeof_condition = 0;
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
-		dbginfo.features = PPC_DEBUG_FEATURE_DATA_BP_RANGE;
-		if (dawr_enabled())
-			dbginfo.features |= PPC_DEBUG_FEATURE_DATA_BP_DAWR;
-#else
-		dbginfo.features = 0;
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
-#endif /* CONFIG_PPC_ADV_DEBUG_REGS */
-
-		if (copy_to_user(datavp, &dbginfo,
-				 sizeof(struct ppc_debug_info)))
-			return -EFAULT;
-		return 0;
-	}
-
-	case PPC_PTRACE_SETHWDEBUG: {
-		struct ppc_hw_breakpoint bp_info;
-
-		if (copy_from_user(&bp_info, datavp,
-				   sizeof(struct ppc_hw_breakpoint)))
-			return -EFAULT;
-		return ppc_set_hwdebug(child, &bp_info);
-	}
-
-	case PPC_PTRACE_DELHWDEBUG: {
-		ret = ppc_del_hwdebug(child, data);
-		break;
-	}
-
-	case PTRACE_GET_DEBUGREG: {
-#ifndef CONFIG_PPC_ADV_DEBUG_REGS
-		unsigned long dabr_fake;
-#endif
-		ret = -EINVAL;
-		/* We only support one DABR and no IABRS at the moment */
-		if (addr > 0)
-			break;
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-		ret = put_user(child->thread.debug.dac1, datalp);
-#else
-		dabr_fake = ((child->thread.hw_brk.address & (~HW_BRK_TYPE_DABR)) |
-			     (child->thread.hw_brk.type & HW_BRK_TYPE_DABR));
-		ret = put_user(dabr_fake, datalp);
-#endif
-		break;
-	}
-
-	case PTRACE_SET_DEBUGREG:
-		ret = ptrace_set_debugreg(child, addr, data);
-		break;
-
-#ifdef CONFIG_PPC64
-	case PTRACE_GETREGS64:
-#endif
-	case PTRACE_GETREGS:	/* Get all pt_regs from the child. */
-		return copy_regset_to_user(child, &user_ppc_native_view,
-					   REGSET_GPR,
-					   0, sizeof(struct user_pt_regs),
-					   datavp);
-
-#ifdef CONFIG_PPC64
-	case PTRACE_SETREGS64:
-#endif
-	case PTRACE_SETREGS:	/* Set all gp regs in the child. */
-		return copy_regset_from_user(child, &user_ppc_native_view,
-					     REGSET_GPR,
-					     0, sizeof(struct user_pt_regs),
-					     datavp);
-
-	case PTRACE_GETFPREGS: /* Get the child FPU state (FPR0...31 + FPSCR) */
-		return copy_regset_to_user(child, &user_ppc_native_view,
-					   REGSET_FPR,
-					   0, sizeof(elf_fpregset_t),
-					   datavp);
-
-	case PTRACE_SETFPREGS: /* Set the child FPU state (FPR0...31 + FPSCR) */
-		return copy_regset_from_user(child, &user_ppc_native_view,
-					     REGSET_FPR,
-					     0, sizeof(elf_fpregset_t),
-					     datavp);
-
-#ifdef CONFIG_ALTIVEC
-	case PTRACE_GETVRREGS:
-		return copy_regset_to_user(child, &user_ppc_native_view,
-					   REGSET_VMX,
-					   0, (33 * sizeof(vector128) +
-					       sizeof(u32)),
-					   datavp);
-
-	case PTRACE_SETVRREGS:
-		return copy_regset_from_user(child, &user_ppc_native_view,
-					     REGSET_VMX,
-					     0, (33 * sizeof(vector128) +
-						 sizeof(u32)),
-					     datavp);
-#endif
-#ifdef CONFIG_VSX
-	case PTRACE_GETVSRREGS:
-		return copy_regset_to_user(child, &user_ppc_native_view,
-					   REGSET_VSX,
-					   0, 32 * sizeof(double),
-					   datavp);
-
-	case PTRACE_SETVSRREGS:
-		return copy_regset_from_user(child, &user_ppc_native_view,
-					     REGSET_VSX,
-					     0, 32 * sizeof(double),
-					     datavp);
-#endif
-#ifdef CONFIG_SPE
-	case PTRACE_GETEVRREGS:
-		/* Get the child spe register state. */
-		return copy_regset_to_user(child, &user_ppc_native_view,
-					   REGSET_SPE, 0, 35 * sizeof(u32),
-					   datavp);
-
-	case PTRACE_SETEVRREGS:
-		/* Set the child spe register state. */
-		return copy_regset_from_user(child, &user_ppc_native_view,
-					     REGSET_SPE, 0, 35 * sizeof(u32),
-					     datavp);
-#endif
-
-	default:
-		ret = ptrace_request(child, request, addr, data);
-		break;
-	}
-	return ret;
-}
-
-#ifdef CONFIG_SECCOMP
-static int do_seccomp(struct pt_regs *regs)
-{
-	if (!test_thread_flag(TIF_SECCOMP))
-		return 0;
-
-	/*
-	 * The ABI we present to seccomp tracers is that r3 contains
-	 * the syscall return value and orig_gpr3 contains the first
-	 * syscall parameter. This is different to the ptrace ABI where
-	 * both r3 and orig_gpr3 contain the first syscall parameter.
-	 */
-	regs->gpr[3] = -ENOSYS;
-
-	/*
-	 * We use the __ version here because we have already checked
-	 * TIF_SECCOMP. If this fails, there is nothing left to do, we
-	 * have already loaded -ENOSYS into r3, or seccomp has put
-	 * something else in r3 (via SECCOMP_RET_ERRNO/TRACE).
-	 */
-	if (__secure_computing(NULL))
-		return -1;
-
-	/*
-	 * The syscall was allowed by seccomp, restore the register
-	 * state to what audit expects.
-	 * Note that we use orig_gpr3, which means a seccomp tracer can
-	 * modify the first syscall parameter (in orig_gpr3) and also
-	 * allow the syscall to proceed.
-	 */
-	regs->gpr[3] = regs->orig_gpr3;
-
-	return 0;
-}
-#else
-static inline int do_seccomp(struct pt_regs *regs) { return 0; }
-#endif /* CONFIG_SECCOMP */
-
-/**
- * do_syscall_trace_enter() - Do syscall tracing on kernel entry.
- * @regs: the pt_regs of the task to trace (current)
- *
- * Performs various types of tracing on syscall entry. This includes seccomp,
- * ptrace, syscall tracepoints and audit.
- *
- * The pt_regs are potentially visible to userspace via ptrace, so their
- * contents is ABI.
- *
- * One or more of the tracers may modify the contents of pt_regs, in particular
- * to modify arguments or even the syscall number itself.
- *
- * It's also possible that a tracer can choose to reject the system call. In
- * that case this function will return an illegal syscall number, and will put
- * an appropriate return value in regs->r3.
- *
- * Return: the (possibly changed) syscall number.
- */
-long do_syscall_trace_enter(struct pt_regs *regs)
-{
-	u32 flags;
-
-	user_exit();
-
-	flags = READ_ONCE(current_thread_info()->flags) &
-		(_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE);
-
-	if (flags) {
-		int rc = tracehook_report_syscall_entry(regs);
-
-		if (unlikely(flags & _TIF_SYSCALL_EMU)) {
-			/*
-			 * A nonzero return code from
-			 * tracehook_report_syscall_entry() tells us to prevent
-			 * the syscall execution, but we are not going to
-			 * execute it anyway.
-			 *
-			 * Returning -1 will skip the syscall execution. We want
-			 * to avoid clobbering any registers, so we don't goto
-			 * the skip label below.
-			 */
-			return -1;
-		}
-
-		if (rc) {
-			/*
-			 * The tracer decided to abort the syscall. Note that
-			 * the tracer may also just change regs->gpr[0] to an
-			 * invalid syscall number, that is handled below on the
-			 * exit path.
-			 */
-			goto skip;
-		}
-	}
-
-	/* Run seccomp after ptrace; allow it to set gpr[3]. */
-	if (do_seccomp(regs))
-		return -1;
-
-	/* Avoid trace and audit when syscall is invalid. */
-	if (regs->gpr[0] >= NR_syscalls)
-		goto skip;
-
-	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
-		trace_sys_enter(regs, regs->gpr[0]);
-
-#ifdef CONFIG_PPC64
-	if (!is_32bit_task())
-		audit_syscall_entry(regs->gpr[0], regs->gpr[3], regs->gpr[4],
-				    regs->gpr[5], regs->gpr[6]);
-	else
-#endif
-		audit_syscall_entry(regs->gpr[0],
-				    regs->gpr[3] & 0xffffffff,
-				    regs->gpr[4] & 0xffffffff,
-				    regs->gpr[5] & 0xffffffff,
-				    regs->gpr[6] & 0xffffffff);
-
-	/* Return the possibly modified but valid syscall number */
-	return regs->gpr[0];
-
-skip:
-	/*
-	 * If we are aborting explicitly, or if the syscall number is
-	 * now invalid, set the return value to -ENOSYS.
-	 */
-	regs->gpr[3] = -ENOSYS;
-	return -1;
-}
-
-void do_syscall_trace_leave(struct pt_regs *regs)
-{
-	int step;
-
-	audit_syscall_exit(regs);
-
-	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
-		trace_sys_exit(regs, regs->result);
-
-	step = test_thread_flag(TIF_SINGLESTEP);
-	if (step || test_thread_flag(TIF_SYSCALL_TRACE))
-		tracehook_report_syscall_exit(regs, step);
-
-	user_enter();
-}
-
-void __init pt_regs_check(void);
-
-/*
- * Dummy function, its purpose is to break the build if struct pt_regs and
- * struct user_pt_regs don't match.
- */
-void __init pt_regs_check(void)
-{
-	BUILD_BUG_ON(offsetof(struct pt_regs, gpr) !=
-		     offsetof(struct user_pt_regs, gpr));
-	BUILD_BUG_ON(offsetof(struct pt_regs, nip) !=
-		     offsetof(struct user_pt_regs, nip));
-	BUILD_BUG_ON(offsetof(struct pt_regs, msr) !=
-		     offsetof(struct user_pt_regs, msr));
-	BUILD_BUG_ON(offsetof(struct pt_regs, msr) !=
-		     offsetof(struct user_pt_regs, msr));
-	BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
-		     offsetof(struct user_pt_regs, orig_gpr3));
-	BUILD_BUG_ON(offsetof(struct pt_regs, ctr) !=
-		     offsetof(struct user_pt_regs, ctr));
-	BUILD_BUG_ON(offsetof(struct pt_regs, link) !=
-		     offsetof(struct user_pt_regs, link));
-	BUILD_BUG_ON(offsetof(struct pt_regs, xer) !=
-		     offsetof(struct user_pt_regs, xer));
-	BUILD_BUG_ON(offsetof(struct pt_regs, ccr) !=
-		     offsetof(struct user_pt_regs, ccr));
-#ifdef __powerpc64__
-	BUILD_BUG_ON(offsetof(struct pt_regs, softe) !=
-		     offsetof(struct user_pt_regs, softe));
-#else
-	BUILD_BUG_ON(offsetof(struct pt_regs, mq) !=
-		     offsetof(struct user_pt_regs, mq));
-#endif
-	BUILD_BUG_ON(offsetof(struct pt_regs, trap) !=
-		     offsetof(struct user_pt_regs, trap));
-	BUILD_BUG_ON(offsetof(struct pt_regs, dar) !=
-		     offsetof(struct user_pt_regs, dar));
-	BUILD_BUG_ON(offsetof(struct pt_regs, dsisr) !=
-		     offsetof(struct user_pt_regs, dsisr));
-	BUILD_BUG_ON(offsetof(struct pt_regs, result) !=
-		     offsetof(struct user_pt_regs, result));
-
-	BUILD_BUG_ON(sizeof(struct user_pt_regs) > sizeof(struct pt_regs));
-
-	// Now check that the pt_regs offsets match the uapi #defines
-	#define CHECK_REG(_pt, _reg) \
-		BUILD_BUG_ON(_pt != (offsetof(struct user_pt_regs, _reg) / \
-				     sizeof(unsigned long)));
-
-	CHECK_REG(PT_R0,  gpr[0]);
-	CHECK_REG(PT_R1,  gpr[1]);
-	CHECK_REG(PT_R2,  gpr[2]);
-	CHECK_REG(PT_R3,  gpr[3]);
-	CHECK_REG(PT_R4,  gpr[4]);
-	CHECK_REG(PT_R5,  gpr[5]);
-	CHECK_REG(PT_R6,  gpr[6]);
-	CHECK_REG(PT_R7,  gpr[7]);
-	CHECK_REG(PT_R8,  gpr[8]);
-	CHECK_REG(PT_R9,  gpr[9]);
-	CHECK_REG(PT_R10, gpr[10]);
-	CHECK_REG(PT_R11, gpr[11]);
-	CHECK_REG(PT_R12, gpr[12]);
-	CHECK_REG(PT_R13, gpr[13]);
-	CHECK_REG(PT_R14, gpr[14]);
-	CHECK_REG(PT_R15, gpr[15]);
-	CHECK_REG(PT_R16, gpr[16]);
-	CHECK_REG(PT_R17, gpr[17]);
-	CHECK_REG(PT_R18, gpr[18]);
-	CHECK_REG(PT_R19, gpr[19]);
-	CHECK_REG(PT_R20, gpr[20]);
-	CHECK_REG(PT_R21, gpr[21]);
-	CHECK_REG(PT_R22, gpr[22]);
-	CHECK_REG(PT_R23, gpr[23]);
-	CHECK_REG(PT_R24, gpr[24]);
-	CHECK_REG(PT_R25, gpr[25]);
-	CHECK_REG(PT_R26, gpr[26]);
-	CHECK_REG(PT_R27, gpr[27]);
-	CHECK_REG(PT_R28, gpr[28]);
-	CHECK_REG(PT_R29, gpr[29]);
-	CHECK_REG(PT_R30, gpr[30]);
-	CHECK_REG(PT_R31, gpr[31]);
-	CHECK_REG(PT_NIP, nip);
-	CHECK_REG(PT_MSR, msr);
-	CHECK_REG(PT_ORIG_R3, orig_gpr3);
-	CHECK_REG(PT_CTR, ctr);
-	CHECK_REG(PT_LNK, link);
-	CHECK_REG(PT_XER, xer);
-	CHECK_REG(PT_CCR, ccr);
-#ifdef CONFIG_PPC64
-	CHECK_REG(PT_SOFTE, softe);
-#else
-	CHECK_REG(PT_MQ, mq);
-#endif
-	CHECK_REG(PT_TRAP, trap);
-	CHECK_REG(PT_DAR, dar);
-	CHECK_REG(PT_DSISR, dsisr);
-	CHECK_REG(PT_RESULT, result);
-	#undef CHECK_REG
-
-	BUILD_BUG_ON(PT_REGS_COUNT != sizeof(struct user_pt_regs) / sizeof(unsigned long));
-
-	/*
-	 * PT_DSCR isn't a real reg, but it's important that it doesn't overlap the
-	 * real registers.
-	 */
-	BUILD_BUG_ON(PT_DSCR < sizeof(struct user_pt_regs) / sizeof(unsigned long));
-}

arch/powerpc/kernel/ptrace/Makefile

···
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the linux kernel.
+#
+
+CFLAGS_ptrace-view.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
+
+obj-y				+= ptrace.o ptrace-view.o
+obj-$(CONFIG_PPC64)		+= ptrace32.o
+obj-$(CONFIG_VSX)		+= ptrace-vsx.o
+ifneq ($(CONFIG_VSX),y)
+obj-y				+= ptrace-novsx.o
+endif
+obj-$(CONFIG_ALTIVEC)		+= ptrace-altivec.o
+obj-$(CONFIG_SPE)		+= ptrace-spe.o
+obj-$(CONFIG_PPC_TRANSACTIONAL_MEM)	+= ptrace-tm.o
+obj-$(CONFIG_PPC_ADV_DEBUG_REGS)	+= ptrace-adv.o
+ifneq ($(CONFIG_PPC_ADV_DEBUG_REGS),y)
+obj-y				+= ptrace-noadv.o
+endif

arch/powerpc/kernel/ptrace/ptrace-adv.c

···
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+#include <linux/hw_breakpoint.h>
+
+#include "ptrace-decl.h"
+
+void user_enable_single_step(struct task_struct *task)
+{
+	struct pt_regs *regs = task->thread.regs;
+
+	if (regs != NULL) {
+		task->thread.debug.dbcr0 &= ~DBCR0_BT;
+		task->thread.debug.dbcr0 |= DBCR0_IDM | DBCR0_IC;
+		regs->msr |= MSR_DE;
+	}
+	set_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
+void user_enable_block_step(struct task_struct *task)
+{
+	struct pt_regs *regs = task->thread.regs;
+
+	if (regs != NULL) {
+		task->thread.debug.dbcr0 &= ~DBCR0_IC;
+		task->thread.debug.dbcr0 = DBCR0_IDM | DBCR0_BT;
+		regs->msr |= MSR_DE;
+	}
+	set_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
+void user_disable_single_step(struct task_struct *task)
+{
+	struct pt_regs *regs = task->thread.regs;
+
+	if (regs != NULL) {
+		/*
+		 * The logic to disable single stepping should be as
+		 * simple as turning off the Instruction Complete flag.
+		 * And, after doing so, if all debug flags are off, turn
+		 * off DBCR0(IDM) and MSR(DE) .... Torez
+		 */
+		task->thread.debug.dbcr0 &= ~(DBCR0_IC | DBCR0_BT);
+		/*
+		 * Test to see if any of the DBCR_ACTIVE_EVENTS bits are set.
+		 */
+		if (!DBCR_ACTIVE_EVENTS(task->thread.debug.dbcr0,
+					task->thread.debug.dbcr1)) {
+			/*
+			 * All debug events were off.....
+			 */
+			task->thread.debug.dbcr0 &= ~DBCR0_IDM;
+			regs->msr &= ~MSR_DE;
+		}
+	}
+	clear_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
+void ppc_gethwdinfo(struct ppc_debug_info *dbginfo)
+{
+	dbginfo->version = 1;
+	dbginfo->num_instruction_bps = CONFIG_PPC_ADV_DEBUG_IACS;
+	dbginfo->num_data_bps = CONFIG_PPC_ADV_DEBUG_DACS;
+	dbginfo->num_condition_regs = CONFIG_PPC_ADV_DEBUG_DVCS;
+	dbginfo->data_bp_alignment = 4;
+	dbginfo->sizeof_condition = 4;
+	dbginfo->features = PPC_DEBUG_FEATURE_INSN_BP_RANGE |
+			    PPC_DEBUG_FEATURE_INSN_BP_MASK;
+	if (IS_ENABLED(CONFIG_PPC_ADV_DEBUG_DAC_RANGE))
+		dbginfo->features |= PPC_DEBUG_FEATURE_DATA_BP_RANGE |
+				     PPC_DEBUG_FEATURE_DATA_BP_MASK;
+}
+
+int ptrace_get_debugreg(struct task_struct *child, unsigned long addr,
+			unsigned long __user *datalp)
+{
+	/* We only support one DABR and no IABRS at the moment */
+	if (addr > 0)
+		return -EINVAL;
+	return put_user(child->thread.debug.dac1, datalp);
+}
+
+int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, unsigned long data)
+{
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	int ret;
+	struct thread_struct *thread = &task->thread;
+	struct perf_event *bp;
+	struct perf_event_attr attr;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+
+	/* For ppc64 we support one DABR and no IABR's at the moment (ppc64).
+	 *  For embedded processors we support one DAC and no IAC's at the
+	 *  moment.
+	 */
+	if (addr > 0)
+		return -EINVAL;
+
+	/* The bottom 3 bits in dabr are flags */
+	if ((data & ~0x7UL) >= TASK_SIZE)
+		return -EIO;
+
+	/* As described above, it was assumed 3 bits were passed with the data
+	 *  address, but we will assume only the mode bits will be passed
+	 *  as to not cause alignment restrictions for DAC-based processors.
+	 */
+
+	/* DAC's hold the whole address without any mode flags */
+	task->thread.debug.dac1 = data & ~0x3UL;
+
+	if (task->thread.debug.dac1 == 0) {
+		dbcr_dac(task) &= ~(DBCR_DAC1R | DBCR_DAC1W);
+		if (!DBCR_ACTIVE_EVENTS(task->thread.debug.dbcr0,
+					task->thread.debug.dbcr1)) {
+			task->thread.regs->msr &= ~MSR_DE;
+			task->thread.debug.dbcr0 &= ~DBCR0_IDM;
+		}
+		return 0;
+	}
+
+	/* Read or Write bits must be set */
+
+	if (!(data & 0x3UL))
+		return -EINVAL;
+
+	/* Set the Internal Debugging flag (IDM bit 1) for the DBCR0 register */
+	task->thread.debug.dbcr0 |= DBCR0_IDM;
+
+	/* Check for write and read flags and set DBCR0 accordingly */
+	dbcr_dac(task) &= ~(DBCR_DAC1R | DBCR_DAC1W);
+	if (data & 0x1UL)
+		dbcr_dac(task) |= DBCR_DAC1R;
+	if (data & 0x2UL)
+		dbcr_dac(task) |= DBCR_DAC1W;
+	task->thread.regs->msr |= MSR_DE;
+	return 0;
+}
+
+static long set_instruction_bp(struct task_struct *child,
+			       struct ppc_hw_breakpoint *bp_info)
+{
+	int slot;
+	int slot1_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC1) != 0);
+	int slot2_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC2) != 0);
+	int slot3_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC3) != 0);
+	int slot4_in_use = ((child->thread.debug.dbcr0 & DBCR0_IAC4) != 0);
+
+	if (dbcr_iac_range(child) & DBCR_IAC12MODE)
+		slot2_in_use = 1;
+	if (dbcr_iac_range(child) & DBCR_IAC34MODE)
+		slot4_in_use = 1;
+
+	if (bp_info->addr >= TASK_SIZE)
+		return -EIO;
+
+	if (bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT) {
+		/* Make sure range is valid. */
+		if (bp_info->addr2 >= TASK_SIZE)
+			return -EIO;
+
+		/* We need a pair of IAC regsisters */
+		if (!slot1_in_use && !slot2_in_use) {
+			slot = 1;
+			child->thread.debug.iac1 = bp_info->addr;
+			child->thread.debug.iac2 = bp_info->addr2;
+			child->thread.debug.dbcr0 |= DBCR0_IAC1;
+			if (bp_info->addr_mode ==
+					PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE)
+				dbcr_iac_range(child) |= DBCR_IAC12X;
+			else
+				dbcr_iac_range(child) |= DBCR_IAC12I;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+		} else if ((!slot3_in_use) && (!slot4_in_use)) {
+			slot = 3;
+			child->thread.debug.iac3 = bp_info->addr;
+			child->thread.debug.iac4 = bp_info->addr2;
+			child->thread.debug.dbcr0 |= DBCR0_IAC3;
+			if (bp_info->addr_mode ==
+					PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE)
+				dbcr_iac_range(child) |= DBCR_IAC34X;
+			else
+				dbcr_iac_range(child) |= DBCR_IAC34I;
+#endif
+		} else {
+			return -ENOSPC;
+		}
+	} else {
+		/* We only need one.  If possible leave a pair free in
+		 * case a range is needed later
+		 */
+		if (!slot1_in_use) {
+			/*
+			 * Don't use iac1 if iac1-iac2 are free and either
+			 * iac3 or iac4 (but not both) are free
+			 */
+			if (slot2_in_use || slot3_in_use == slot4_in_use) {
+				slot = 1;
+				child->thread.debug.iac1 = bp_info->addr;
+				child->thread.debug.dbcr0 |= DBCR0_IAC1;
+				goto out;
+			}
+		}
+		if (!slot2_in_use) {
+			slot = 2;
+			child->thread.debug.iac2 = bp_info->addr;
+			child->thread.debug.dbcr0 |= DBCR0_IAC2;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+		} else if (!slot3_in_use) {
+			slot = 3;
+			child->thread.debug.iac3 = bp_info->addr;
+			child->thread.debug.dbcr0 |= DBCR0_IAC3;
+		} else if (!slot4_in_use) {
+			slot = 4;
+			child->thread.debug.iac4 = bp_info->addr;
+			child->thread.debug.dbcr0 |= DBCR0_IAC4;
+#endif
+		} else {
+			return -ENOSPC;
+		}
+	}
+out:
+	child->thread.debug.dbcr0 |= DBCR0_IDM;
+	child->thread.regs->msr |= MSR_DE;
+
+	return slot;
+}
+
+static int del_instruction_bp(struct task_struct *child, int slot)
+{
+	switch (slot) {
+	case 1:
+		if ((child->thread.debug.dbcr0 & DBCR0_IAC1) == 0)
+			return -ENOENT;
+
+		if (dbcr_iac_range(child) & DBCR_IAC12MODE) {
+			/* address range - clear slots 1 & 2 */
+			child->thread.debug.iac2 = 0;
+			dbcr_iac_range(child) &= ~DBCR_IAC12MODE;
+		}
+		child->thread.debug.iac1 = 0;
+		child->thread.debug.dbcr0 &= ~DBCR0_IAC1;
+		break;
+	case 2:
+		if ((child->thread.debug.dbcr0 & DBCR0_IAC2) == 0)
+			return -ENOENT;
+
+		if (dbcr_iac_range(child) & DBCR_IAC12MODE)
+			/* used in a range */
+			return -EINVAL;
+		child->thread.debug.iac2 = 0;
+		child->thread.debug.dbcr0 &= ~DBCR0_IAC2;
+		break;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+	case 3:
+		if ((child->thread.debug.dbcr0 & DBCR0_IAC3) == 0)
+			return -ENOENT;
+
+		if (dbcr_iac_range(child) & DBCR_IAC34MODE) {
+			/* address range - clear slots 3 & 4 */
+			child->thread.debug.iac4 = 0;
+			dbcr_iac_range(child) &= ~DBCR_IAC34MODE;
+		}
+		child->thread.debug.iac3 = 0;
+		child->thread.debug.dbcr0 &= ~DBCR0_IAC3;
+		break;
+	case 4:
+		if ((child->thread.debug.dbcr0 & DBCR0_IAC4) == 0)
+			return -ENOENT;
+
+		if (dbcr_iac_range(child) & DBCR_IAC34MODE)
+			/* Used in a range */
+			return -EINVAL;
+		child->thread.debug.iac4 = 0;
+		child->thread.debug.dbcr0 &= ~DBCR0_IAC4;
+		break;
+#endif
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int set_dac(struct task_struct *child, struct ppc_hw_breakpoint *bp_info)
+{
+	int byte_enable =
+		(bp_info->condition_mode >> PPC_BREAKPOINT_CONDITION_BE_SHIFT)
+		& 0xf;
+	int condition_mode =
+		bp_info->condition_mode & PPC_BREAKPOINT_CONDITION_MODE;
+	int slot;
+
+	if (byte_enable && condition_mode == 0)
+		return -EINVAL;
+
+	if (bp_info->addr >= TASK_SIZE)
+		return -EIO;
+
+	if ((dbcr_dac(child) & (DBCR_DAC1R | DBCR_DAC1W)) == 0) {
+		slot = 1;
+		if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
+			dbcr_dac(child) |= DBCR_DAC1R;
+		if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
+			dbcr_dac(child) |= DBCR_DAC1W;
+		child->thread.debug.dac1 = (unsigned long)bp_info->addr;
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+		if (byte_enable) {
+			child->thread.debug.dvc1 =
+				(unsigned long)bp_info->condition_value;
+			child->thread.debug.dbcr2 |=
+				((byte_enable << DBCR2_DVC1BE_SHIFT) |
+				 (condition_mode << DBCR2_DVC1M_SHIFT));
+		}
+#endif
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+	} else if (child->thread.debug.dbcr2 & DBCR2_DAC12MODE) {
+		/* Both dac1 and dac2 are part of a range */
+		return -ENOSPC;
+#endif
+	} else if ((dbcr_dac(child) & (DBCR_DAC2R | DBCR_DAC2W)) == 0) {
+		slot = 2;
+		if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
+			dbcr_dac(child) |= DBCR_DAC2R;
+		if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
+			dbcr_dac(child) |= DBCR_DAC2W;
+		child->thread.debug.dac2 = (unsigned long)bp_info->addr;
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+		if (byte_enable) {
+			child->thread.debug.dvc2 =
+				(unsigned long)bp_info->condition_value;
+			child->thread.debug.dbcr2 |=
+				((byte_enable << DBCR2_DVC2BE_SHIFT) |
+				 (condition_mode << DBCR2_DVC2M_SHIFT));
+		}
+#endif
+	} else {
+		return -ENOSPC;
+	}
+	child->thread.debug.dbcr0 |= DBCR0_IDM;
+	child->thread.regs->msr |= MSR_DE;
+
+	return slot + 4;
+}
+
+static int del_dac(struct task_struct *child, int slot)
+{
+	if (slot == 1) {
+		if ((dbcr_dac(child) & (DBCR_DAC1R | DBCR_DAC1W)) == 0)
+			return -ENOENT;
+
+		child->thread.debug.dac1 = 0;
+		dbcr_dac(child) &= ~(DBCR_DAC1R | DBCR_DAC1W);
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+		if (child->thread.debug.dbcr2 & DBCR2_DAC12MODE) {
+			child->thread.debug.dac2 = 0;
+			child->thread.debug.dbcr2 &= ~DBCR2_DAC12MODE;
+		}
+		child->thread.debug.dbcr2 &= ~(DBCR2_DVC1M | DBCR2_DVC1BE);
+#endif
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+		child->thread.debug.dvc1 = 0;
+#endif
+	} else if (slot == 2) {
+		if ((dbcr_dac(child) & (DBCR_DAC2R | DBCR_DAC2W)) == 0)
+			return -ENOENT;
+
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+		if (child->thread.debug.dbcr2 & DBCR2_DAC12MODE)
+			/* Part of a range */
+			return -EINVAL;
+		child->thread.debug.dbcr2 &= ~(DBCR2_DVC2M | DBCR2_DVC2BE);
+#endif
+#if CONFIG_PPC_ADV_DEBUG_DVCS > 0
+		child->thread.debug.dvc2 = 0;
+#endif
+		child->thread.debug.dac2 = 0;
+		dbcr_dac(child) &= ~(DBCR_DAC2R | DBCR_DAC2W);
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+static int set_dac_range(struct task_struct *child,
+			 struct ppc_hw_breakpoint *bp_info)
+{
+	int mode = bp_info->addr_mode & PPC_BREAKPOINT_MODE_MASK;
+
+	/* We don't allow range watchpoints to be used with DVC */
+	if (bp_info->condition_mode)
+		return -EINVAL;
+
+	/*
+	 * Best effort to verify the address range.  The user/supervisor bits
+	 * prevent trapping in kernel space, but let's fail on an obvious bad
+	 * range.  The simple test on the mask is not fool-proof, and any
+	 * exclusive range will spill over into kernel space.
+	 */
+	if (bp_info->addr >= TASK_SIZE)
+		return -EIO;
+	if (mode == PPC_BREAKPOINT_MODE_MASK) {
+		/*
+		 * dac2 is a bitmask.  Don't allow a mask that makes a
+		 * kernel space address from a valid dac1 value
+		 */
+		if (~((unsigned long)bp_info->addr2) >= TASK_SIZE)
+			return -EIO;
+	} else {
+		/*
+		 * For range breakpoints, addr2 must also be a valid address
+		 */
+		if (bp_info->addr2 >= TASK_SIZE)
+			return -EIO;
+	}
+
+	if (child->thread.debug.dbcr0 &
+	    (DBCR0_DAC1R | DBCR0_DAC1W | DBCR0_DAC2R | DBCR0_DAC2W))
+		return -ENOSPC;
+
+	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
+		child->thread.debug.dbcr0 |= (DBCR0_DAC1R | DBCR0_IDM);
+	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
+		child->thread.debug.dbcr0 |= (DBCR0_DAC1W | DBCR0_IDM);
+	child->thread.debug.dac1 = bp_info->addr;
+	child->thread.debug.dac2 = bp_info->addr2;
+	if (mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE)
+		child->thread.debug.dbcr2  |= DBCR2_DAC12M;
+	else if (mode == PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE)
+		child->thread.debug.dbcr2  |= DBCR2_DAC12MX;
+	else	/* PPC_BREAKPOINT_MODE_MASK */
+		child->thread.debug.dbcr2  |= DBCR2_DAC12MM;
+	child->thread.regs->msr |= MSR_DE;
+
+	return 5;
+}
+#endif /* CONFIG_PPC_ADV_DEBUG_DAC_RANGE */
+
+long ppc_set_hwdebug(struct task_struct *child, struct ppc_hw_breakpoint *bp_info)
+{
+	if (bp_info->version != 1)
+		return -ENOTSUPP;
+	/*
+	 * Check for invalid flags and combinations
+	 */
+	if (bp_info->trigger_type == 0 ||
+	    (bp_info->trigger_type & ~(PPC_BREAKPOINT_TRIGGER_EXECUTE |
+				       PPC_BREAKPOINT_TRIGGER_RW)) ||
+	    (bp_info->addr_mode & ~PPC_BREAKPOINT_MODE_MASK) ||
+	    (bp_info->condition_mode &
+	     ~(PPC_BREAKPOINT_CONDITION_MODE |
+	       PPC_BREAKPOINT_CONDITION_BE_ALL)))
+		return -EINVAL;
+#if CONFIG_PPC_ADV_DEBUG_DVCS == 0
+	if (bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE)
+		return -EINVAL;
+#endif
+
+	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_EXECUTE) {
+		if (bp_info->trigger_type != PPC_BREAKPOINT_TRIGGER_EXECUTE ||
+		    bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE)
+			return -EINVAL;
+		return set_instruction_bp(child, bp_info);
+	}
+	if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_EXACT)
+		return set_dac(child, bp_info);
+
+#ifdef CONFIG_PPC_ADV_DEBUG_DAC_RANGE
+	return set_dac_range(child, bp_info);
+#else
+	return -EINVAL;
+#endif
+}
+
+long ppc_del_hwdebug(struct task_struct *child, long data)
+{
+	int rc;
+
+	if (data <= 4)
+		rc = del_instruction_bp(child, (int)data);
+	else
+		rc = del_dac(child, (int)data - 4);
+
+	if (!rc) {
+		if (!DBCR_ACTIVE_EVENTS(child->thread.debug.dbcr0,
+					child->thread.debug.dbcr1)) {
+			child->thread.debug.dbcr0 &= ~DBCR0_IDM;
+			child->thread.regs->msr &= ~MSR_DE;
+		}
+	}
+	return rc;
+}

arch/powerpc/kernel/ptrace/ptrace-altivec.c

···
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+#include <linux/elf.h>
+
+#include <asm/switch_to.h>
+
+#include "ptrace-decl.h"
+
+/*
+ * Get/set all the altivec registers vr0..vr31, vscr, vrsave, in one go.
+ * The transfer totals 34 quadword.  Quadwords 0-31 contain the
+ * corresponding vector registers.  Quadword 32 contains the vscr as the
+ * last word (offset 12) within that quadword.  Quadword 33 contains the
+ * vrsave as the first word (offset 0) within the quadword.
+ *
+ * This definition of the VMX state is compatible with the current PPC32
+ * ptrace interface.  This allows signal handling and ptrace to use the
+ * same structures.  This also simplifies the implementation of a bi-arch
+ * (combined (32- and 64-bit) gdb.
+ */
+
+int vr_active(struct task_struct *target, const struct user_regset *regset)
+{
+	flush_altivec_to_thread(target);
+	return target->thread.used_vr ? regset->n : 0;
+}
+
+/*
+ * Regardless of transactions, 'vr_state' holds the current running
+ * value of all the VMX registers and 'ckvr_state' holds the last
+ * checkpointed value of all the VMX registers for the current
+ * transaction to fall back on in case it aborts.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ *	vector128	vr[32];
+ *	vector128	vscr;
+ *	vector128	vrsave;
+ * };
+ */
+int vr_get(struct task_struct *target, const struct user_regset *regset,
+	   unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	int ret;
+
+	flush_altivec_to_thread(target);
+
+	BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) !=
+		     offsetof(struct thread_vr_state, vr[32]));
+
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.vr_state, 0,
+				  33 * sizeof(vector128));
+	if (!ret) {
+		/*
+		 * Copy out only the low-order word of vrsave.
+		 */
+		int start, end;
+		union {
+			elf_vrreg_t reg;
+			u32 word;
+		} vrsave;
+		memset(&vrsave, 0, sizeof(vrsave));
+
+		vrsave.word = target->thread.vrsave;
+
+		start = 33 * sizeof(vector128);
+		end = start + sizeof(vrsave);
+		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave,
+					  start, end);
+	}
+
+	return ret;
+}
+
+/*
+ * Regardless of transactions, 'vr_state' holds the current running
+ * value of all the VMX registers and 'ckvr_state' holds the last
+ * checkpointed value of all the VMX registers for the current
+ * transaction to fall back on in case it aborts.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ *	vector128	vr[32];
+ *	vector128	vscr;
+ *	vector128	vrsave;
+ * };
+ */
+int vr_set(struct task_struct *target, const struct user_regset *regset,
+	   unsigned int pos, unsigned int count,
+	   const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+
+	flush_altivec_to_thread(target);
+
+	BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) !=
+		     offsetof(struct thread_vr_state, vr[32]));
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &target->thread.vr_state, 0,
+				 33 * sizeof(vector128));
+	if (!ret && count > 0) {
+		/*
+		 * We use only the first word of vrsave.
+		 */
+		int start, end;
+		union {
+			elf_vrreg_t reg;
+			u32 word;
+		} vrsave;
+		memset(&vrsave, 0, sizeof(vrsave));
+
+		vrsave.word = target->thread.vrsave;
+
+		start = 33 * sizeof(vector128);
+		end = start + sizeof(vrsave);
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave,
+					 start, end);
+		if (!ret)
+			target->thread.vrsave = vrsave.word;
+	}
+
+	return ret;
+}

arch/powerpc/kernel/ptrace/ptrace-decl.h

···
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+/*
+ * Set of msr bits that gdb can change on behalf of a process.
+ */
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+#define MSR_DEBUGCHANGE	0
+#else
+#define MSR_DEBUGCHANGE	(MSR_SE | MSR_BE)
+#endif
+
+/*
+ * Max register writeable via put_reg
+ */
+#ifdef CONFIG_PPC32
+#define PT_MAX_PUT_REG	PT_MQ
+#else
+#define PT_MAX_PUT_REG	PT_CCR
+#endif
+
+#define TVSO(f)	(offsetof(struct thread_vr_state, f))
+#define TFSO(f)	(offsetof(struct thread_fp_state, f))
+#define TSO(f)	(offsetof(struct thread_struct, f))
+
+/*
+ * These are our native regset flavors.
+ */
+enum powerpc_regset {
+	REGSET_GPR,
+	REGSET_FPR,
+#ifdef CONFIG_ALTIVEC
+	REGSET_VMX,
+#endif
+#ifdef CONFIG_VSX
+	REGSET_VSX,
+#endif
+#ifdef CONFIG_SPE
+	REGSET_SPE,
+#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	REGSET_TM_CGPR,		/* TM checkpointed GPR registers */
+	REGSET_TM_CFPR,		/* TM checkpointed FPR registers */
+	REGSET_TM_CVMX,		/* TM checkpointed VMX registers */
+	REGSET_TM_CVSX,		/* TM checkpointed VSX registers */
+	REGSET_TM_SPR,		/* TM specific SPR registers */
+	REGSET_TM_CTAR,		/* TM checkpointed TAR register */
+	REGSET_TM_CPPR,		/* TM checkpointed PPR register */
+	REGSET_TM_CDSCR,	/* TM checkpointed DSCR register */
+#endif
+#ifdef CONFIG_PPC64
+	REGSET_PPR,		/* PPR register */
+	REGSET_DSCR,		/* DSCR register */
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+	REGSET_TAR,		/* TAR register */
+	REGSET_EBB,		/* EBB registers */
+	REGSET_PMR,		/* Performance Monitor Registers */
+#endif
+#ifdef CONFIG_PPC_MEM_KEYS
+	REGSET_PKEY,		/* AMR register */
+#endif
+};
+
+/* ptrace-(no)vsx */
+
+int fpr_get(struct task_struct *target, const struct user_regset *regset,
+	    unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf);
+int fpr_set(struct task_struct *target, const struct user_regset *regset,
+	    unsigned int pos, unsigned int count,
+	    const void *kbuf, const void __user *ubuf);
+
+/* ptrace-vsx */
+
+int vsr_active(struct task_struct *target, const struct user_regset *regset);
+int vsr_get(struct task_struct *target, const struct user_regset *regset,
+	    unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf);
+int vsr_set(struct task_struct *target, const struct user_regset *regset,
+	    unsigned int pos, unsigned int count,
+	    const void *kbuf, const void __user *ubuf);
+
+/* ptrace-altivec */
+
+int vr_active(struct task_struct *target, const struct user_regset *regset);
+int vr_get(struct task_struct *target, const struct user_regset *regset,
+	   unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf);
+int vr_set(struct task_struct *target, const struct user_regset *regset,
+	   unsigned int pos, unsigned int count,
+	   const void *kbuf, const void __user *ubuf);
+
+/* ptrace-spe */
+
+int evr_active(struct task_struct *target, const struct user_regset *regset);
+int evr_get(struct task_struct *target, const struct user_regset *regset,
+	    unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf);
+int evr_set(struct task_struct *target, const struct user_regset *regset,
+	    unsigned int pos, unsigned int count,
+	    const void *kbuf, const void __user *ubuf);
+
+/* ptrace */
+
+int gpr32_get_common(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+			    void *kbuf, void __user *ubuf,
+			    unsigned long *regs);
+int gpr32_set_common(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     const void *kbuf, const void __user *ubuf,
+		     unsigned long *regs);
+
+/* ptrace-tm */
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+void flush_tmregs_to_thread(struct task_struct *tsk);
+#else
+static inline void flush_tmregs_to_thread(struct task_struct *tsk) { }
+#endif
+
+int tm_cgpr_active(struct task_struct *target, const struct user_regset *regset);
+int tm_cgpr_get(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf);
+int tm_cgpr_set(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		const void *kbuf, const void __user *ubuf);
+int tm_cfpr_active(struct task_struct *target, const struct user_regset *regset);
+int tm_cfpr_get(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf);
+int tm_cfpr_set(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		const void *kbuf, const void __user *ubuf);
+int tm_cvmx_active(struct task_struct *target, const struct user_regset *regset);
+int tm_cvmx_get(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf);
+int tm_cvmx_set(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		const void *kbuf, const void __user *ubuf);
+int tm_cvsx_active(struct task_struct *target, const struct user_regset *regset);
+int tm_cvsx_get(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf);
+int tm_cvsx_set(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		const void *kbuf, const void __user *ubuf);
+int tm_spr_active(struct task_struct *target, const struct user_regset *regset);
+int tm_spr_get(struct task_struct *target, const struct user_regset *regset,
+	       unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf);
+int tm_spr_set(struct task_struct *target, const struct user_regset *regset,
+	       unsigned int pos, unsigned int count,
+	       const void *kbuf, const void __user *ubuf);
+int tm_tar_active(struct task_struct *target, const struct user_regset *regset);
+int tm_tar_get(struct task_struct *target, const struct user_regset *regset,
+	       unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf);
+int tm_tar_set(struct task_struct *target, const struct user_regset *regset,
+	       unsigned int pos, unsigned int count,
+	       const void *kbuf, const void __user *ubuf);
+int tm_ppr_active(struct task_struct *target, const struct user_regset *regset);
+int tm_ppr_get(struct task_struct *target, const struct user_regset *regset,
+	       unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf);
+int tm_ppr_set(struct task_struct *target, const struct user_regset *regset,
+	       unsigned int pos, unsigned int count,
+	       const void *kbuf, const void __user *ubuf);
+int tm_dscr_active(struct task_struct *target, const struct user_regset *regset);
+int tm_dscr_get(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf);
+int tm_dscr_set(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		const void *kbuf, const void __user *ubuf);
+int tm_cgpr32_get(struct task_struct *target, const struct user_regset *regset,
+		  unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf);
+int tm_cgpr32_set(struct task_struct *target, const struct user_regset *regset,
+		  unsigned int pos, unsigned int count,
+		  const void *kbuf, const void __user *ubuf);
+
+/* ptrace-view */
+
+extern const struct user_regset_view user_ppc_native_view;
+
+/* ptrace-(no)adv */
+void ppc_gethwdinfo(struct ppc_debug_info *dbginfo);
+int ptrace_get_debugreg(struct task_struct *child, unsigned long addr,
+			unsigned long __user *datalp);
+int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, unsigned long data);
+long ppc_set_hwdebug(struct task_struct *child, struct ppc_hw_breakpoint *bp_info);
+long ppc_del_hwdebug(struct task_struct *child, long data);

arch/powerpc/kernel/ptrace/ptrace-noadv.c

···
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+#include <linux/hw_breakpoint.h>
+
+#include <asm/debug.h>
+
+#include "ptrace-decl.h"
+
+void user_enable_single_step(struct task_struct *task)
+{
+	struct pt_regs *regs = task->thread.regs;
+
+	if (regs != NULL) {
+		regs->msr &= ~MSR_BE;
+		regs->msr |= MSR_SE;
+	}
+	set_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
+void user_enable_block_step(struct task_struct *task)
+{
+	struct pt_regs *regs = task->thread.regs;
+
+	if (regs != NULL) {
+		regs->msr &= ~MSR_SE;
+		regs->msr |= MSR_BE;
+	}
+	set_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
+void user_disable_single_step(struct task_struct *task)
+{
+	struct pt_regs *regs = task->thread.regs;
+
+	if (regs != NULL)
+		regs->msr &= ~(MSR_SE | MSR_BE);
+
+	clear_tsk_thread_flag(task, TIF_SINGLESTEP);
+}
+
+void ppc_gethwdinfo(struct ppc_debug_info *dbginfo)
+{
+	dbginfo->version = 1;
+	dbginfo->num_instruction_bps = 0;
+	if (ppc_breakpoint_available())
+		dbginfo->num_data_bps = 1;
+	else
+		dbginfo->num_data_bps = 0;
+	dbginfo->num_condition_regs = 0;
+	dbginfo->data_bp_alignment = sizeof(long);
+	dbginfo->sizeof_condition = 0;
+	if (IS_ENABLED(CONFIG_HAVE_HW_BREAKPOINT)) {
+		dbginfo->features = PPC_DEBUG_FEATURE_DATA_BP_RANGE;
+		if (dawr_enabled())
+			dbginfo->features |= PPC_DEBUG_FEATURE_DATA_BP_DAWR;
+	} else {
+		dbginfo->features = 0;
+	}
+}
+
+int ptrace_get_debugreg(struct task_struct *child, unsigned long addr,
+			unsigned long __user *datalp)
+{
+	unsigned long dabr_fake;
+
+	/* We only support one DABR and no IABRS at the moment */
+	if (addr > 0)
+		return -EINVAL;
+	dabr_fake = ((child->thread.hw_brk.address & (~HW_BRK_TYPE_DABR)) |
+		     (child->thread.hw_brk.type & HW_BRK_TYPE_DABR));
+	return put_user(dabr_fake, datalp);
+}
+
+int ptrace_set_debugreg(struct task_struct *task, unsigned long addr, unsigned long data)
+{
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	int ret;
+	struct thread_struct *thread = &task->thread;
+	struct perf_event *bp;
+	struct perf_event_attr attr;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+	bool set_bp = true;
+	struct arch_hw_breakpoint hw_brk;
+
+	/* For ppc64 we support one DABR and no IABR's at the moment (ppc64).
+	 *  For embedded processors we support one DAC and no IAC's at the
+	 *  moment.
+	 */
+	if (addr > 0)
+		return -EINVAL;
+
+	/* The bottom 3 bits in dabr are flags */
+	if ((data & ~0x7UL) >= TASK_SIZE)
+		return -EIO;
+
+	/* For processors using DABR (i.e. 970), the bottom 3 bits are flags.
+	 *  It was assumed, on previous implementations, that 3 bits were
+	 *  passed together with the data address, fitting the design of the
+	 *  DABR register, as follows:
+	 *
+	 *  bit 0: Read flag
+	 *  bit 1: Write flag
+	 *  bit 2: Breakpoint translation
+	 *
+	 *  Thus, we use them here as so.
+	 */
+
+	/* Ensure breakpoint translation bit is set */
+	if (data && !(data & HW_BRK_TYPE_TRANSLATE))
+		return -EIO;
+	hw_brk.address = data & (~HW_BRK_TYPE_DABR);
+	hw_brk.type = (data & HW_BRK_TYPE_DABR) | HW_BRK_TYPE_PRIV_ALL;
+	hw_brk.len = DABR_MAX_LEN;
+	hw_brk.hw_len = DABR_MAX_LEN;
+	set_bp = (data) && (hw_brk.type & HW_BRK_TYPE_RDWR);
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	bp = thread->ptrace_bps[0];
+	if (!set_bp) {
+		if (bp) {
+			unregister_hw_breakpoint(bp);
+			thread->ptrace_bps[0] = NULL;
+		}
+		return 0;
+	}
+	if (bp) {
+		attr = bp->attr;
+		attr.bp_addr = hw_brk.address;
+		attr.bp_len = DABR_MAX_LEN;
+		arch_bp_generic_fields(hw_brk.type, &attr.bp_type);
+
+		/* Enable breakpoint */
+		attr.disabled = false;
+
+		ret =  modify_user_hw_breakpoint(bp, &attr);
+		if (ret)
+			return ret;
+
+		thread->ptrace_bps[0] = bp;
+		thread->hw_brk = hw_brk;
+		return 0;
+	}
+
+	/* Create a new breakpoint request if one doesn't exist already */
+	hw_breakpoint_init(&attr);
+	attr.bp_addr = hw_brk.address;
+	attr.bp_len = DABR_MAX_LEN;
+	arch_bp_generic_fields(hw_brk.type,
+			       &attr.bp_type);
+
+	thread->ptrace_bps[0] = bp = register_user_hw_breakpoint(&attr,
+					       ptrace_triggered, NULL, task);
+	if (IS_ERR(bp)) {
+		thread->ptrace_bps[0] = NULL;
+		return PTR_ERR(bp);
+	}
+
+#else /* !CONFIG_HAVE_HW_BREAKPOINT */
+	if (set_bp && (!ppc_breakpoint_available()))
+		return -ENODEV;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+	task->thread.hw_brk = hw_brk;
+	return 0;
+}
+
+long ppc_set_hwdebug(struct task_struct *child, struct ppc_hw_breakpoint *bp_info)
+{
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	int len = 0;
+	struct thread_struct *thread = &child->thread;
+	struct perf_event *bp;
+	struct perf_event_attr attr;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+	struct arch_hw_breakpoint brk;
+
+	if (bp_info->version != 1)
+		return -ENOTSUPP;
+	/*
+	 * We only support one data breakpoint
+	 */
+	if ((bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_RW) == 0 ||
+	    (bp_info->trigger_type & ~PPC_BREAKPOINT_TRIGGER_RW) != 0 ||
+	    bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE)
+		return -EINVAL;
+
+	if ((unsigned long)bp_info->addr >= TASK_SIZE)
+		return -EIO;
+
+	brk.address = bp_info->addr & ~HW_BREAKPOINT_ALIGN;
+	brk.type = HW_BRK_TYPE_TRANSLATE;
+	brk.len = DABR_MAX_LEN;
+	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
+		brk.type |= HW_BRK_TYPE_READ;
+	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
+		brk.type |= HW_BRK_TYPE_WRITE;
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE)
+		len = bp_info->addr2 - bp_info->addr;
+	else if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_EXACT)
+		len = 1;
+	else
+		return -EINVAL;
+	bp = thread->ptrace_bps[0];
+	if (bp)
+		return -ENOSPC;
+
+	/* Create a new breakpoint request if one doesn't exist already */
+	hw_breakpoint_init(&attr);
+	attr.bp_addr = (unsigned long)bp_info->addr;
+	attr.bp_len = len;
+	arch_bp_generic_fields(brk.type, &attr.bp_type);
+
+	bp = register_user_hw_breakpoint(&attr, ptrace_triggered, NULL, child);
+	thread->ptrace_bps[0] = bp;
+	if (IS_ERR(bp)) {
+		thread->ptrace_bps[0] = NULL;
+		return PTR_ERR(bp);
+	}
+
+	return 1;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+
+	if (bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT)
+		return -EINVAL;
+
+	if (child->thread.hw_brk.address)
+		return -ENOSPC;
+
+	if (!ppc_breakpoint_available())
+		return -ENODEV;
+
+	child->thread.hw_brk = brk;
+
+	return 1;
+}
+
+long ppc_del_hwdebug(struct task_struct *child, long data)
+{
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	int ret = 0;
+	struct thread_struct *thread = &child->thread;
+	struct perf_event *bp;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+	if (data != 1)
+		return -EINVAL;
+
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	bp = thread->ptrace_bps[0];
+	if (bp) {
+		unregister_hw_breakpoint(bp);
+		thread->ptrace_bps[0] = NULL;
+	} else {
+		ret = -ENOENT;
+	}
+	return ret;
+#else /* CONFIG_HAVE_HW_BREAKPOINT */
+	if (child->thread.hw_brk.address == 0)
+		return -ENOENT;
+
+	child->thread.hw_brk.address = 0;
+	child->thread.hw_brk.type = 0;
+#endif /* CONFIG_HAVE_HW_BREAKPOINT */
+
+	return 0;
+}

arch/powerpc/kernel/ptrace/ptrace-novsx.c

···
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+
+#include <asm/switch_to.h>
+
+#include "ptrace-decl.h"
+
+/*
+ * Regardless of transactions, 'fp_state' holds the current running
+ * value of all FPR registers and 'ckfp_state' holds the last checkpointed
+ * value of all FPR registers for the current transaction.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ *	u64	fpr[32];
+ *	u64	fpscr;
+ * };
+ */
+int fpr_get(struct task_struct *target, const struct user_regset *regset,
+	    unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
+		     offsetof(struct thread_fp_state, fpr[32]));
+
+	flush_fp_to_thread(target);
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   &target->thread.fp_state, 0, -1);
+}
+
+/*
+ * Regardless of transactions, 'fp_state' holds the current running
+ * value of all FPR registers and 'ckfp_state' holds the last checkpointed
+ * value of all FPR registers for the current transaction.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ *	u64	fpr[32];
+ *	u64	fpscr;
+ * };
+ *
+ */
+int fpr_set(struct task_struct *target, const struct user_regset *regset,
+	    unsigned int pos, unsigned int count,
+	    const void *kbuf, const void __user *ubuf)
+{
+	BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
+		     offsetof(struct thread_fp_state, fpr[32]));
+
+	flush_fp_to_thread(target);
+
+	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.fp_state, 0, -1);
+}

arch/powerpc/kernel/ptrace/ptrace-spe.c

···
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+
+#include <asm/switch_to.h>
+
+#include "ptrace-decl.h"
+
+/*
+ * For get_evrregs/set_evrregs functions 'data' has the following layout:
+ *
+ * struct {
+ *   u32 evr[32];
+ *   u64 acc;
+ *   u32 spefscr;
+ * }
+ */
+
+int evr_active(struct task_struct *target, const struct user_regset *regset)
+{
+	flush_spe_to_thread(target);
+	return target->thread.used_spe ? regset->n : 0;
+}
+
+int evr_get(struct task_struct *target, const struct user_regset *regset,
+	    unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	int ret;
+
+	flush_spe_to_thread(target);
+
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.evr,
+				  0, sizeof(target->thread.evr));
+
+	BUILD_BUG_ON(offsetof(struct thread_struct, acc) + sizeof(u64) !=
+		     offsetof(struct thread_struct, spefscr));
+
+	if (!ret)
+		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+					  &target->thread.acc,
+					  sizeof(target->thread.evr), -1);
+
+	return ret;
+}
+
+int evr_set(struct task_struct *target, const struct user_regset *regset,
+	    unsigned int pos, unsigned int count,
+	    const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+
+	flush_spe_to_thread(target);
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &target->thread.evr,
+				 0, sizeof(target->thread.evr));
+
+	BUILD_BUG_ON(offsetof(struct thread_struct, acc) + sizeof(u64) !=
+		     offsetof(struct thread_struct, spefscr));
+
+	if (!ret)
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					 &target->thread.acc,
+					 sizeof(target->thread.evr), -1);
+
+	return ret;
+}

arch/powerpc/kernel/ptrace/ptrace-tm.c

···
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+
+#include <asm/switch_to.h>
+#include <asm/tm.h>
+#include <asm/asm-prototypes.h>
+
+#include "ptrace-decl.h"
+
+void flush_tmregs_to_thread(struct task_struct *tsk)
+{
+	/*
+	 * If task is not current, it will have been flushed already to
+	 * it's thread_struct during __switch_to().
+	 *
+	 * A reclaim flushes ALL the state or if not in TM save TM SPRs
+	 * in the appropriate thread structures from live.
+	 */
+
+	if (!cpu_has_feature(CPU_FTR_TM) || tsk != current)
+		return;
+
+	if (MSR_TM_SUSPENDED(mfmsr())) {
+		tm_reclaim_current(TM_CAUSE_SIGNAL);
+	} else {
+		tm_enable();
+		tm_save_sprs(&tsk->thread);
+	}
+}
+
+static unsigned long get_user_ckpt_msr(struct task_struct *task)
+{
+	return task->thread.ckpt_regs.msr | task->thread.fpexc_mode;
+}
+
+static int set_user_ckpt_msr(struct task_struct *task, unsigned long msr)
+{
+	task->thread.ckpt_regs.msr &= ~MSR_DEBUGCHANGE;
+	task->thread.ckpt_regs.msr |= msr & MSR_DEBUGCHANGE;
+	return 0;
+}
+
+static int set_user_ckpt_trap(struct task_struct *task, unsigned long trap)
+{
+	task->thread.ckpt_regs.trap = trap & 0xfff0;
+	return 0;
+}
+
+/**
+ * tm_cgpr_active - get active number of registers in CGPR
+ * @target:	The target task.
+ * @regset:	The user regset structure.
+ *
+ * This function checks for the active number of available
+ * regisers in transaction checkpointed GPR category.
+ */
+int tm_cgpr_active(struct task_struct *target, const struct user_regset *regset)
+{
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+		return 0;
+
+	return regset->n;
+}
+
+/**
+ * tm_cgpr_get - get CGPR registers
+ * @target:	The target task.
+ * @regset:	The user regset structure.
+ * @pos:	The buffer position.
+ * @count:	Number of bytes to copy.
+ * @kbuf:	Kernel buffer to copy from.
+ * @ubuf:	User buffer to copy into.
+ *
+ * This function gets transaction checkpointed GPR registers.
+ *
+ * When the transaction is active, 'ckpt_regs' holds all the checkpointed
+ * GPR register values for the current transaction to fall back on if it
+ * aborts in between. This function gets those checkpointed GPR registers.
+ * The userspace interface buffer layout is as follows.
+ *
+ * struct data {
+ *	struct pt_regs ckpt_regs;
+ * };
+ */
+int tm_cgpr_get(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	int ret;
+
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+		return -ENODATA;
+
+	flush_tmregs_to_thread(target);
+	flush_fp_to_thread(target);
+	flush_altivec_to_thread(target);
+
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.ckpt_regs,
+				  0, offsetof(struct pt_regs, msr));
+	if (!ret) {
+		unsigned long msr = get_user_ckpt_msr(target);
+
+		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &msr,
+					  offsetof(struct pt_regs, msr),
+					  offsetof(struct pt_regs, msr) +
+					  sizeof(msr));
+	}
+
+	BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
+		     offsetof(struct pt_regs, msr) + sizeof(long));
+
+	if (!ret)
+		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+					  &target->thread.ckpt_regs.orig_gpr3,
+					  offsetof(struct pt_regs, orig_gpr3),
+					  sizeof(struct user_pt_regs));
+	if (!ret)
+		ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+					       sizeof(struct user_pt_regs), -1);
+
+	return ret;
+}
+
+/*
+ * tm_cgpr_set - set the CGPR registers
+ * @target:	The target task.
+ * @regset:	The user regset structure.
+ * @pos:	The buffer position.
+ * @count:	Number of bytes to copy.
+ * @kbuf:	Kernel buffer to copy into.
+ * @ubuf:	User buffer to copy from.
+ *
+ * This function sets in transaction checkpointed GPR registers.
+ *
+ * When the transaction is active, 'ckpt_regs' holds the checkpointed
+ * GPR register values for the current transaction to fall back on if it
+ * aborts in between. This function sets those checkpointed GPR registers.
+ * The userspace interface buffer layout is as follows.
+ *
+ * struct data {
+ *	struct pt_regs ckpt_regs;
+ * };
+ */
+int tm_cgpr_set(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		const void *kbuf, const void __user *ubuf)
+{
+	unsigned long reg;
+	int ret;
+
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+		return -ENODATA;
+
+	flush_tmregs_to_thread(target);
+	flush_fp_to_thread(target);
+	flush_altivec_to_thread(target);
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &target->thread.ckpt_regs,
+				 0, PT_MSR * sizeof(reg));
+
+	if (!ret && count > 0) {
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &reg,
+					 PT_MSR * sizeof(reg),
+					 (PT_MSR + 1) * sizeof(reg));
+		if (!ret)
+			ret = set_user_ckpt_msr(target, reg);
+	}
+
+	BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
+		     offsetof(struct pt_regs, msr) + sizeof(long));
+
+	if (!ret)
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					 &target->thread.ckpt_regs.orig_gpr3,
+					 PT_ORIG_R3 * sizeof(reg),
+					 (PT_MAX_PUT_REG + 1) * sizeof(reg));
+
+	if (PT_MAX_PUT_REG + 1 < PT_TRAP && !ret)
+		ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+						(PT_MAX_PUT_REG + 1) * sizeof(reg),
+						PT_TRAP * sizeof(reg));
+
+	if (!ret && count > 0) {
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &reg,
+					 PT_TRAP * sizeof(reg),
+					 (PT_TRAP + 1) * sizeof(reg));
+		if (!ret)
+			ret = set_user_ckpt_trap(target, reg);
+	}
+
+	if (!ret)
+		ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+						(PT_TRAP + 1) * sizeof(reg), -1);
+
+	return ret;
+}
+
+/**
+ * tm_cfpr_active - get active number of registers in CFPR
+ * @target:	The target task.
+ * @regset:	The user regset structure.
+ *
+ * This function checks for the active number of available
+ * regisers in transaction checkpointed FPR category.
+ */
+int tm_cfpr_active(struct task_struct *target, const struct user_regset *regset)
+{
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+		return 0;
+
+	return regset->n;
+}
+
+/**
+ * tm_cfpr_get - get CFPR registers
+ * @target:	The target task.
+ * @regset:	The user regset structure.
+ * @pos:	The buffer position.
+ * @count:	Number of bytes to copy.
+ * @kbuf:	Kernel buffer to copy from.
+ * @ubuf:	User buffer to copy into.
+ *
+ * This function gets in transaction checkpointed FPR registers.
+ *
+ * When the transaction is active 'ckfp_state' holds the checkpointed
+ * values for the current transaction to fall back on if it aborts
+ * in between. This function gets those checkpointed FPR registers.
+ * The userspace interface buffer layout is as follows.
+ *
+ * struct data {
+ *	u64	fpr[32];
+ *	u64	fpscr;
+ *};
+ */
+int tm_cfpr_get(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	u64 buf[33];
+	int i;
+
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+		return -ENODATA;
+
+	flush_tmregs_to_thread(target);
+	flush_fp_to_thread(target);
+	flush_altivec_to_thread(target);
+
+	/* copy to local buffer then write that out */
+	for (i = 0; i < 32 ; i++)
+		buf[i] = target->thread.TS_CKFPR(i);
+	buf[32] = target->thread.ckfp_state.fpscr;
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
+}
+
+/**
+ * tm_cfpr_set - set CFPR registers
+ * @target:	The target task.
+ * @regset:	The user regset structure.
+ * @pos:	The buffer position.
+ * @count:	Number of bytes to copy.
+ * @kbuf:	Kernel buffer to copy into.
+ * @ubuf:	User buffer to copy from.
+ *
+ * This function sets in transaction checkpointed FPR registers.
+ *
+ * When the transaction is active 'ckfp_state' holds the checkpointed
+ * FPR register values for the current transaction to fall back on
+ * if it aborts in between. This function sets these checkpointed
+ * FPR registers. The userspace interface buffer layout is as follows.
+ *
+ * struct data {
+ *	u64	fpr[32];
+ *	u64	fpscr;
+ *};
+ */
+int tm_cfpr_set(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		const void *kbuf, const void __user *ubuf)
+{
+	u64 buf[33];
+	int i;
+
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+		return -ENODATA;
+
+	flush_tmregs_to_thread(target);
+	flush_fp_to_thread(target);
+	flush_altivec_to_thread(target);
+
+	for (i = 0; i < 32; i++)
+		buf[i] = target->thread.TS_CKFPR(i);
+	buf[32] = target->thread.ckfp_state.fpscr;
+
+	/* copy to local buffer then write that out */
+	i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
+	if (i)
+		return i;
+	for (i = 0; i < 32 ; i++)
+		target->thread.TS_CKFPR(i) = buf[i];
+	target->thread.ckfp_state.fpscr = buf[32];
+	return 0;
+}
+
+/**
+ * tm_cvmx_active - get active number of registers in CVMX
+ * @target:	The target task.
+ * @regset:	The user regset structure.
+ *
+ * This function checks for the active number of available
+ * regisers in checkpointed VMX category.
+ */
+int tm_cvmx_active(struct task_struct *target, const struct user_regset *regset)
+{
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+		return 0;
+
+	return regset->n;
+}
+
+/**
+ * tm_cvmx_get - get CMVX registers
+ * @target:	The target task.
+ * @regset:	The user regset structure.
+ * @pos:	The buffer position.
+ * @count:	Number of bytes to copy.
+ * @kbuf:	Kernel buffer to copy from.
+ * @ubuf:	User buffer to copy into.
+ *
+ * This function gets in transaction checkpointed VMX registers.
+ *
+ * When the transaction is active 'ckvr_state' and 'ckvrsave' hold
+ * the checkpointed values for the current transaction to fall
+ * back on if it aborts in between. The userspace interface buffer
+ * layout is as follows.
+ *
+ * struct data {
+ *	vector128	vr[32];
+ *	vector128	vscr;
+ *	vector128	vrsave;
+ *};
+ */
+int tm_cvmx_get(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	int ret;
+
+	BUILD_BUG_ON(TVSO(vscr) != TVSO(vr[32]));
+
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+		return -ENODATA;
+
+	/* Flush the state */
+	flush_tmregs_to_thread(target);
+	flush_fp_to_thread(target);
+	flush_altivec_to_thread(target);
+
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.ckvr_state,
+				  0, 33 * sizeof(vector128));
+	if (!ret) {
+		/*
+		 * Copy out only the low-order word of vrsave.
+		 */
+		union {
+			elf_vrreg_t reg;
+			u32 word;
+		} vrsave;
+		memset(&vrsave, 0, sizeof(vrsave));
+		vrsave.word = target->thread.ckvrsave;
+		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &vrsave,
+					  33 * sizeof(vector128), -1);
+	}
+
+	return ret;
+}
+
+/**
+ * tm_cvmx_set - set CMVX registers
+ * @target:	The target task.
+ * @regset:	The user regset structure.
+ * @pos:	The buffer position.
+ * @count:	Number of bytes to copy.
+ * @kbuf:	Kernel buffer to copy into.
+ * @ubuf:	User buffer to copy from.
+ *
+ * This function sets in transaction checkpointed VMX registers.
+ *
+ * When the transaction is active 'ckvr_state' and 'ckvrsave' hold
+ * the checkpointed values for the current transaction to fall
+ * back on if it aborts in between. The userspace interface buffer
+ * layout is as follows.
+ *
+ * struct data {
+ *	vector128	vr[32];
+ *	vector128	vscr;
+ *	vector128	vrsave;
+ *};
+ */
+int tm_cvmx_set(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+
+	BUILD_BUG_ON(TVSO(vscr) != TVSO(vr[32]));
+
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+		return -ENODATA;
+
+	flush_tmregs_to_thread(target);
+	flush_fp_to_thread(target);
+	flush_altivec_to_thread(target);
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.ckvr_state,
+				 0, 33 * sizeof(vector128));
+	if (!ret && count > 0) {
+		/*
+		 * We use only the low-order word of vrsave.
+		 */
+		union {
+			elf_vrreg_t reg;
+			u32 word;
+		} vrsave;
+		memset(&vrsave, 0, sizeof(vrsave));
+		vrsave.word = target->thread.ckvrsave;
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &vrsave,
+					 33 * sizeof(vector128), -1);
+		if (!ret)
+			target->thread.ckvrsave = vrsave.word;
+	}
+
+	return ret;
+}
+
+/**
+ * tm_cvsx_active - get active number of registers in CVSX
+ * @target:	The target task.
+ * @regset:	The user regset structure.
+ *
+ * This function checks for the active number of available
+ * regisers in transaction checkpointed VSX category.
+ */
+int tm_cvsx_active(struct task_struct *target, const struct user_regset *regset)
+{
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+		return 0;
+
+	flush_vsx_to_thread(target);
+	return target->thread.used_vsr ? regset->n : 0;
+}
+
+/**
+ * tm_cvsx_get - get CVSX registers
+ * @target:	The target task.
+ * @regset:	The user regset structure.
+ * @pos:	The buffer position.
+ * @count:	Number of bytes to copy.
+ * @kbuf:	Kernel buffer to copy from.
+ * @ubuf:	User buffer to copy into.
+ *
+ * This function gets in transaction checkpointed VSX registers.
+ *
+ * When the transaction is active 'ckfp_state' holds the checkpointed
+ * values for the current transaction to fall back on if it aborts
+ * in between. This function gets those checkpointed VSX registers.
+ * The userspace interface buffer layout is as follows.
+ *
+ * struct data {
+ *	u64	vsx[32];
+ *};
+ */
+int tm_cvsx_get(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	u64 buf[32];
+	int ret, i;
+
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+		return -ENODATA;
+
+	/* Flush the state */
+	flush_tmregs_to_thread(target);
+	flush_fp_to_thread(target);
+	flush_altivec_to_thread(target);
+	flush_vsx_to_thread(target);
+
+	for (i = 0; i < 32 ; i++)
+		buf[i] = target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET];
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  buf, 0, 32 * sizeof(double));
+
+	return ret;
+}
+
+/**
+ * tm_cvsx_set - set CFPR registers
+ * @target:	The target task.
+ * @regset:	The user regset structure.
+ * @pos:	The buffer position.
+ * @count:	Number of bytes to copy.
+ * @kbuf:	Kernel buffer to copy into.
+ * @ubuf:	User buffer to copy from.
+ *
+ * This function sets in transaction checkpointed VSX registers.
+ *
+ * When the transaction is active 'ckfp_state' holds the checkpointed
+ * VSX register values for the current transaction to fall back on
+ * if it aborts in between. This function sets these checkpointed
+ * FPR registers. The userspace interface buffer layout is as follows.
+ *
+ * struct data {
+ *	u64	vsx[32];
+ *};
+ */
+int tm_cvsx_set(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		const void *kbuf, const void __user *ubuf)
+{
+	u64 buf[32];
+	int ret, i;
+
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+		return -ENODATA;
+
+	/* Flush the state */
+	flush_tmregs_to_thread(target);
+	flush_fp_to_thread(target);
+	flush_altivec_to_thread(target);
+	flush_vsx_to_thread(target);
+
+	for (i = 0; i < 32 ; i++)
+		buf[i] = target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET];
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 buf, 0, 32 * sizeof(double));
+	if (!ret)
+		for (i = 0; i < 32 ; i++)
+			target->thread.ckfp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
+
+	return ret;
+}
+
+/**
+ * tm_spr_active - get active number of registers in TM SPR
+ * @target:	The target task.
+ * @regset:	The user regset structure.
+ *
+ * This function checks the active number of available
+ * regisers in the transactional memory SPR category.
+ */
+int tm_spr_active(struct task_struct *target, const struct user_regset *regset)
+{
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	return regset->n;
+}
+
+/**
+ * tm_spr_get - get the TM related SPR registers
+ * @target:	The target task.
+ * @regset:	The user regset structure.
+ * @pos:	The buffer position.
+ * @count:	Number of bytes to copy.
+ * @kbuf:	Kernel buffer to copy from.
+ * @ubuf:	User buffer to copy into.
+ *
+ * This function gets transactional memory related SPR registers.
+ * The userspace interface buffer layout is as follows.
+ *
+ * struct {
+ *	u64		tm_tfhar;
+ *	u64		tm_texasr;
+ *	u64		tm_tfiar;
+ * };
+ */
+int tm_spr_get(struct task_struct *target, const struct user_regset *regset,
+	       unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	int ret;
+
+	/* Build tests */
+	BUILD_BUG_ON(TSO(tm_tfhar) + sizeof(u64) != TSO(tm_texasr));
+	BUILD_BUG_ON(TSO(tm_texasr) + sizeof(u64) != TSO(tm_tfiar));
+	BUILD_BUG_ON(TSO(tm_tfiar) + sizeof(u64) != TSO(ckpt_regs));
+
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	/* Flush the states */
+	flush_tmregs_to_thread(target);
+	flush_fp_to_thread(target);
+	flush_altivec_to_thread(target);
+
+	/* TFHAR register */
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.tm_tfhar, 0, sizeof(u64));
+
+	/* TEXASR register */
+	if (!ret)
+		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+					  &target->thread.tm_texasr, sizeof(u64),
+					  2 * sizeof(u64));
+
+	/* TFIAR register */
+	if (!ret)
+		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+					  &target->thread.tm_tfiar,
+					  2 * sizeof(u64), 3 * sizeof(u64));
+	return ret;
+}
+
+/**
+ * tm_spr_set - set the TM related SPR registers
+ * @target:	The target task.
+ * @regset:	The user regset structure.
+ * @pos:	The buffer position.
+ * @count:	Number of bytes to copy.
+ * @kbuf:	Kernel buffer to copy into.
+ * @ubuf:	User buffer to copy from.
+ *
+ * This function sets transactional memory related SPR registers.
+ * The userspace interface buffer layout is as follows.
+ *
+ * struct {
+ *	u64		tm_tfhar;
+ *	u64		tm_texasr;
+ *	u64		tm_tfiar;
+ * };
+ */
+int tm_spr_set(struct task_struct *target, const struct user_regset *regset,
+	       unsigned int pos, unsigned int count,
+	       const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+
+	/* Build tests */
+	BUILD_BUG_ON(TSO(tm_tfhar) + sizeof(u64) != TSO(tm_texasr));
+	BUILD_BUG_ON(TSO(tm_texasr) + sizeof(u64) != TSO(tm_tfiar));
+	BUILD_BUG_ON(TSO(tm_tfiar) + sizeof(u64) != TSO(ckpt_regs));
+
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	/* Flush the states */
+	flush_tmregs_to_thread(target);
+	flush_fp_to_thread(target);
+	flush_altivec_to_thread(target);
+
+	/* TFHAR register */
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &target->thread.tm_tfhar, 0, sizeof(u64));
+
+	/* TEXASR register */
+	if (!ret)
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					 &target->thread.tm_texasr, sizeof(u64),
+					 2 * sizeof(u64));
+
+	/* TFIAR register */
+	if (!ret)
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					 &target->thread.tm_tfiar,
+					 2 * sizeof(u64), 3 * sizeof(u64));
+	return ret;
+}
+
+int tm_tar_active(struct task_struct *target, const struct user_regset *regset)
+{
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (MSR_TM_ACTIVE(target->thread.regs->msr))
+		return regset->n;
+
+	return 0;
+}
+
+int tm_tar_get(struct task_struct *target, const struct user_regset *regset,
+	       unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	int ret;
+
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+		return -ENODATA;
+
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.tm_tar, 0, sizeof(u64));
+	return ret;
+}
+
+int tm_tar_set(struct task_struct *target, const struct user_regset *regset,
+	       unsigned int pos, unsigned int count,
+	       const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+		return -ENODATA;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &target->thread.tm_tar, 0, sizeof(u64));
+	return ret;
+}
+
+int tm_ppr_active(struct task_struct *target, const struct user_regset *regset)
+{
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (MSR_TM_ACTIVE(target->thread.regs->msr))
+		return regset->n;
+
+	return 0;
+}
+
+
+int tm_ppr_get(struct task_struct *target, const struct user_regset *regset,
+	       unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	int ret;
+
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+		return -ENODATA;
+
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.tm_ppr, 0, sizeof(u64));
+	return ret;
+}
+
+int tm_ppr_set(struct task_struct *target, const struct user_regset *regset,
+	       unsigned int pos, unsigned int count,
+	       const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+		return -ENODATA;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &target->thread.tm_ppr, 0, sizeof(u64));
+	return ret;
+}
+
+int tm_dscr_active(struct task_struct *target, const struct user_regset *regset)
+{
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (MSR_TM_ACTIVE(target->thread.regs->msr))
+		return regset->n;
+
+	return 0;
+}
+
+int tm_dscr_get(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	int ret;
+
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+		return -ENODATA;
+
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.tm_dscr, 0, sizeof(u64));
+	return ret;
+}
+
+int tm_dscr_set(struct task_struct *target, const struct user_regset *regset,
+		unsigned int pos, unsigned int count,
+		const void *kbuf, const void __user *ubuf)
+{
+	int ret;
+
+	if (!cpu_has_feature(CPU_FTR_TM))
+		return -ENODEV;
+
+	if (!MSR_TM_ACTIVE(target->thread.regs->msr))
+		return -ENODATA;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &target->thread.tm_dscr, 0, sizeof(u64));
+	return ret;
+}
+
+int tm_cgpr32_get(struct task_struct *target, const struct user_regset *regset,
+		  unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	return gpr32_get_common(target, regset, pos, count, kbuf, ubuf,
+				&target->thread.ckpt_regs.gpr[0]);
+}
+
+int tm_cgpr32_set(struct task_struct *target, const struct user_regset *regset,
+		  unsigned int pos, unsigned int count,
+		  const void *kbuf, const void __user *ubuf)
+{
+	return gpr32_set_common(target, regset, pos, count, kbuf, ubuf,
+				&target->thread.ckpt_regs.gpr[0]);
+}

arch/powerpc/kernel/ptrace/ptrace-view.c

···
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+#include <linux/elf.h>
+#include <linux/nospec.h>
+#include <linux/pkeys.h>
+
+#include "ptrace-decl.h"
+
+struct pt_regs_offset {
+	const char *name;
+	int offset;
+};
+
+#define STR(s)	#s			/* convert to string */
+#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)}
+#define GPR_OFFSET_NAME(num)	\
+	{.name = STR(r##num), .offset = offsetof(struct pt_regs, gpr[num])}, \
+	{.name = STR(gpr##num), .offset = offsetof(struct pt_regs, gpr[num])}
+#define REG_OFFSET_END {.name = NULL, .offset = 0}
+
+static const struct pt_regs_offset regoffset_table[] = {
+	GPR_OFFSET_NAME(0),
+	GPR_OFFSET_NAME(1),
+	GPR_OFFSET_NAME(2),
+	GPR_OFFSET_NAME(3),
+	GPR_OFFSET_NAME(4),
+	GPR_OFFSET_NAME(5),
+	GPR_OFFSET_NAME(6),
+	GPR_OFFSET_NAME(7),
+	GPR_OFFSET_NAME(8),
+	GPR_OFFSET_NAME(9),
+	GPR_OFFSET_NAME(10),
+	GPR_OFFSET_NAME(11),
+	GPR_OFFSET_NAME(12),
+	GPR_OFFSET_NAME(13),
+	GPR_OFFSET_NAME(14),
+	GPR_OFFSET_NAME(15),
+	GPR_OFFSET_NAME(16),
+	GPR_OFFSET_NAME(17),
+	GPR_OFFSET_NAME(18),
+	GPR_OFFSET_NAME(19),
+	GPR_OFFSET_NAME(20),
+	GPR_OFFSET_NAME(21),
+	GPR_OFFSET_NAME(22),
+	GPR_OFFSET_NAME(23),
+	GPR_OFFSET_NAME(24),
+	GPR_OFFSET_NAME(25),
+	GPR_OFFSET_NAME(26),
+	GPR_OFFSET_NAME(27),
+	GPR_OFFSET_NAME(28),
+	GPR_OFFSET_NAME(29),
+	GPR_OFFSET_NAME(30),
+	GPR_OFFSET_NAME(31),
+	REG_OFFSET_NAME(nip),
+	REG_OFFSET_NAME(msr),
+	REG_OFFSET_NAME(ctr),
+	REG_OFFSET_NAME(link),
+	REG_OFFSET_NAME(xer),
+	REG_OFFSET_NAME(ccr),
+#ifdef CONFIG_PPC64
+	REG_OFFSET_NAME(softe),
+#else
+	REG_OFFSET_NAME(mq),
+#endif
+	REG_OFFSET_NAME(trap),
+	REG_OFFSET_NAME(dar),
+	REG_OFFSET_NAME(dsisr),
+	REG_OFFSET_END,
+};
+
+/**
+ * regs_query_register_offset() - query register offset from its name
+ * @name:	the name of a register
+ *
+ * regs_query_register_offset() returns the offset of a register in struct
+ * pt_regs from its name. If the name is invalid, this returns -EINVAL;
+ */
+int regs_query_register_offset(const char *name)
+{
+	const struct pt_regs_offset *roff;
+	for (roff = regoffset_table; roff->name != NULL; roff++)
+		if (!strcmp(roff->name, name))
+			return roff->offset;
+	return -EINVAL;
+}
+
+/**
+ * regs_query_register_name() - query register name from its offset
+ * @offset:	the offset of a register in struct pt_regs.
+ *
+ * regs_query_register_name() returns the name of a register from its
+ * offset in struct pt_regs. If the @offset is invalid, this returns NULL;
+ */
+const char *regs_query_register_name(unsigned int offset)
+{
+	const struct pt_regs_offset *roff;
+	for (roff = regoffset_table; roff->name != NULL; roff++)
+		if (roff->offset == offset)
+			return roff->name;
+	return NULL;
+}
+
+/*
+ * does not yet catch signals sent when the child dies.
+ * in exit.c or in signal.c.
+ */
+
+static unsigned long get_user_msr(struct task_struct *task)
+{
+	return task->thread.regs->msr | task->thread.fpexc_mode;
+}
+
+static int set_user_msr(struct task_struct *task, unsigned long msr)
+{
+	task->thread.regs->msr &= ~MSR_DEBUGCHANGE;
+	task->thread.regs->msr |= msr & MSR_DEBUGCHANGE;
+	return 0;
+}
+
+#ifdef CONFIG_PPC64
+static int get_user_dscr(struct task_struct *task, unsigned long *data)
+{
+	*data = task->thread.dscr;
+	return 0;
+}
+
+static int set_user_dscr(struct task_struct *task, unsigned long dscr)
+{
+	task->thread.dscr = dscr;
+	task->thread.dscr_inherit = 1;
+	return 0;
+}
+#else
+static int get_user_dscr(struct task_struct *task, unsigned long *data)
+{
+	return -EIO;
+}
+
+static int set_user_dscr(struct task_struct *task, unsigned long dscr)
+{
+	return -EIO;
+}
+#endif
+
+/*
+ * We prevent mucking around with the reserved area of trap
+ * which are used internally by the kernel.
+ */
+static int set_user_trap(struct task_struct *task, unsigned long trap)
+{
+	task->thread.regs->trap = trap & 0xfff0;
+	return 0;
+}
+
+/*
+ * Get contents of register REGNO in task TASK.
+ */
+int ptrace_get_reg(struct task_struct *task, int regno, unsigned long *data)
+{
+	unsigned int regs_max;
+
+	if (task->thread.regs == NULL || !data)
+		return -EIO;
+
+	if (regno == PT_MSR) {
+		*data = get_user_msr(task);
+		return 0;
+	}
+
+	if (regno == PT_DSCR)
+		return get_user_dscr(task, data);
+
+	/*
+	 * softe copies paca->irq_soft_mask variable state. Since irq_soft_mask is
+	 * no more used as a flag, lets force usr to alway see the softe value as 1
+	 * which means interrupts are not soft disabled.
+	 */
+	if (IS_ENABLED(CONFIG_PPC64) && regno == PT_SOFTE) {
+		*data = 1;
+		return  0;
+	}
+
+	regs_max = sizeof(struct user_pt_regs) / sizeof(unsigned long);
+	if (regno < regs_max) {
+		regno = array_index_nospec(regno, regs_max);
+		*data = ((unsigned long *)task->thread.regs)[regno];
+		return 0;
+	}
+
+	return -EIO;
+}
+
+/*
+ * Write contents of register REGNO in task TASK.
+ */
+int ptrace_put_reg(struct task_struct *task, int regno, unsigned long data)
+{
+	if (task->thread.regs == NULL)
+		return -EIO;
+
+	if (regno == PT_MSR)
+		return set_user_msr(task, data);
+	if (regno == PT_TRAP)
+		return set_user_trap(task, data);
+	if (regno == PT_DSCR)
+		return set_user_dscr(task, data);
+
+	if (regno <= PT_MAX_PUT_REG) {
+		regno = array_index_nospec(regno, PT_MAX_PUT_REG + 1);
+		((unsigned long *)task->thread.regs)[regno] = data;
+		return 0;
+	}
+	return -EIO;
+}
+
+static int gpr_get(struct task_struct *target, const struct user_regset *regset,
+		   unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	int i, ret;
+
+	if (target->thread.regs == NULL)
+		return -EIO;
+
+	if (!FULL_REGS(target->thread.regs)) {
+		/* We have a partial register set.  Fill 14-31 with bogus values */
+		for (i = 14; i < 32; i++)
+			target->thread.regs->gpr[i] = NV_REG_POISON;
+	}
+
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  target->thread.regs,
+				  0, offsetof(struct pt_regs, msr));
+	if (!ret) {
+		unsigned long msr = get_user_msr(target);
+		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &msr,
+					  offsetof(struct pt_regs, msr),
+					  offsetof(struct pt_regs, msr) +
+					  sizeof(msr));
+	}
+
+	BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
+		     offsetof(struct pt_regs, msr) + sizeof(long));
+
+	if (!ret)
+		ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+					  &target->thread.regs->orig_gpr3,
+					  offsetof(struct pt_regs, orig_gpr3),
+					  sizeof(struct user_pt_regs));
+	if (!ret)
+		ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+					       sizeof(struct user_pt_regs), -1);
+
+	return ret;
+}
+
+static int gpr_set(struct task_struct *target, const struct user_regset *regset,
+		   unsigned int pos, unsigned int count, const void *kbuf,
+		   const void __user *ubuf)
+{
+	unsigned long reg;
+	int ret;
+
+	if (target->thread.regs == NULL)
+		return -EIO;
+
+	CHECK_FULL_REGS(target->thread.regs);
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 target->thread.regs,
+				 0, PT_MSR * sizeof(reg));
+
+	if (!ret && count > 0) {
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &reg,
+					 PT_MSR * sizeof(reg),
+					 (PT_MSR + 1) * sizeof(reg));
+		if (!ret)
+			ret = set_user_msr(target, reg);
+	}
+
+	BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
+		     offsetof(struct pt_regs, msr) + sizeof(long));
+
+	if (!ret)
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					 &target->thread.regs->orig_gpr3,
+					 PT_ORIG_R3 * sizeof(reg),
+					 (PT_MAX_PUT_REG + 1) * sizeof(reg));
+
+	if (PT_MAX_PUT_REG + 1 < PT_TRAP && !ret)
+		ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+						(PT_MAX_PUT_REG + 1) * sizeof(reg),
+						PT_TRAP * sizeof(reg));
+
+	if (!ret && count > 0) {
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &reg,
+					 PT_TRAP * sizeof(reg),
+					 (PT_TRAP + 1) * sizeof(reg));
+		if (!ret)
+			ret = set_user_trap(target, reg);
+	}
+
+	if (!ret)
+		ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+						(PT_TRAP + 1) * sizeof(reg), -1);
+
+	return ret;
+}
+
+#ifdef CONFIG_PPC64
+static int ppr_get(struct task_struct *target, const struct user_regset *regset,
+		   unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   &target->thread.regs->ppr, 0, sizeof(u64));
+}
+
+static int ppr_set(struct task_struct *target, const struct user_regset *regset,
+		   unsigned int pos, unsigned int count, const void *kbuf,
+		   const void __user *ubuf)
+{
+	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.regs->ppr, 0, sizeof(u64));
+}
+
+static int dscr_get(struct task_struct *target, const struct user_regset *regset,
+		    unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   &target->thread.dscr, 0, sizeof(u64));
+}
+static int dscr_set(struct task_struct *target, const struct user_regset *regset,
+		    unsigned int pos, unsigned int count, const void *kbuf,
+		    const void __user *ubuf)
+{
+	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.dscr, 0, sizeof(u64));
+}
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+static int tar_get(struct task_struct *target, const struct user_regset *regset,
+		   unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				   &target->thread.tar, 0, sizeof(u64));
+}
+static int tar_set(struct task_struct *target, const struct user_regset *regset,
+		   unsigned int pos, unsigned int count, const void *kbuf,
+		   const void __user *ubuf)
+{
+	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.tar, 0, sizeof(u64));
+}
+
+static int ebb_active(struct task_struct *target, const struct user_regset *regset)
+{
+	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+		return -ENODEV;
+
+	if (target->thread.used_ebb)
+		return regset->n;
+
+	return 0;
+}
+
+static int ebb_get(struct task_struct *target, const struct user_regset *regset,
+		   unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	/* Build tests */
+	BUILD_BUG_ON(TSO(ebbrr) + sizeof(unsigned long) != TSO(ebbhr));
+	BUILD_BUG_ON(TSO(ebbhr) + sizeof(unsigned long) != TSO(bescr));
+
+	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+		return -ENODEV;
+
+	if (!target->thread.used_ebb)
+		return -ENODATA;
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.ebbrr,
+				   0, 3 * sizeof(unsigned long));
+}
+
+static int ebb_set(struct task_struct *target, const struct user_regset *regset,
+		   unsigned int pos, unsigned int count, const void *kbuf,
+		   const void __user *ubuf)
+{
+	int ret = 0;
+
+	/* Build tests */
+	BUILD_BUG_ON(TSO(ebbrr) + sizeof(unsigned long) != TSO(ebbhr));
+	BUILD_BUG_ON(TSO(ebbhr) + sizeof(unsigned long) != TSO(bescr));
+
+	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+		return -ENODEV;
+
+	if (target->thread.used_ebb)
+		return -ENODATA;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.ebbrr,
+				 0, sizeof(unsigned long));
+
+	if (!ret)
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					 &target->thread.ebbhr, sizeof(unsigned long),
+					 2 * sizeof(unsigned long));
+
+	if (!ret)
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					 &target->thread.bescr, 2 * sizeof(unsigned long),
+					 3 * sizeof(unsigned long));
+
+	return ret;
+}
+static int pmu_active(struct task_struct *target, const struct user_regset *regset)
+{
+	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+		return -ENODEV;
+
+	return regset->n;
+}
+
+static int pmu_get(struct task_struct *target, const struct user_regset *regset,
+		   unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	/* Build tests */
+	BUILD_BUG_ON(TSO(siar) + sizeof(unsigned long) != TSO(sdar));
+	BUILD_BUG_ON(TSO(sdar) + sizeof(unsigned long) != TSO(sier));
+	BUILD_BUG_ON(TSO(sier) + sizeof(unsigned long) != TSO(mmcr2));
+	BUILD_BUG_ON(TSO(mmcr2) + sizeof(unsigned long) != TSO(mmcr0));
+
+	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+		return -ENODEV;
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.siar,
+				   0, 5 * sizeof(unsigned long));
+}
+
+static int pmu_set(struct task_struct *target, const struct user_regset *regset,
+		   unsigned int pos, unsigned int count, const void *kbuf,
+		   const void __user *ubuf)
+{
+	int ret = 0;
+
+	/* Build tests */
+	BUILD_BUG_ON(TSO(siar) + sizeof(unsigned long) != TSO(sdar));
+	BUILD_BUG_ON(TSO(sdar) + sizeof(unsigned long) != TSO(sier));
+	BUILD_BUG_ON(TSO(sier) + sizeof(unsigned long) != TSO(mmcr2));
+	BUILD_BUG_ON(TSO(mmcr2) + sizeof(unsigned long) != TSO(mmcr0));
+
+	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+		return -ENODEV;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.siar,
+				 0, sizeof(unsigned long));
+
+	if (!ret)
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					 &target->thread.sdar, sizeof(unsigned long),
+					 2 * sizeof(unsigned long));
+
+	if (!ret)
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					 &target->thread.sier, 2 * sizeof(unsigned long),
+					 3 * sizeof(unsigned long));
+
+	if (!ret)
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					 &target->thread.mmcr2, 3 * sizeof(unsigned long),
+					 4 * sizeof(unsigned long));
+
+	if (!ret)
+		ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+					 &target->thread.mmcr0, 4 * sizeof(unsigned long),
+					 5 * sizeof(unsigned long));
+	return ret;
+}
+#endif
+
+#ifdef CONFIG_PPC_MEM_KEYS
+static int pkey_active(struct task_struct *target, const struct user_regset *regset)
+{
+	if (!arch_pkeys_enabled())
+		return -ENODEV;
+
+	return regset->n;
+}
+
+static int pkey_get(struct task_struct *target, const struct user_regset *regset,
+		    unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	BUILD_BUG_ON(TSO(amr) + sizeof(unsigned long) != TSO(iamr));
+	BUILD_BUG_ON(TSO(iamr) + sizeof(unsigned long) != TSO(uamor));
+
+	if (!arch_pkeys_enabled())
+		return -ENODEV;
+
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.amr,
+				   0, ELF_NPKEY * sizeof(unsigned long));
+}
+
+static int pkey_set(struct task_struct *target, const struct user_regset *regset,
+		    unsigned int pos, unsigned int count, const void *kbuf,
+		    const void __user *ubuf)
+{
+	u64 new_amr;
+	int ret;
+
+	if (!arch_pkeys_enabled())
+		return -ENODEV;
+
+	/* Only the AMR can be set from userspace */
+	if (pos != 0 || count != sizeof(new_amr))
+		return -EINVAL;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 &new_amr, 0, sizeof(new_amr));
+	if (ret)
+		return ret;
+
+	/* UAMOR determines which bits of the AMR can be set from userspace. */
+	target->thread.amr = (new_amr & target->thread.uamor) |
+			     (target->thread.amr & ~target->thread.uamor);
+
+	return 0;
+}
+#endif /* CONFIG_PPC_MEM_KEYS */
+
+static const struct user_regset native_regsets[] = {
+	[REGSET_GPR] = {
+		.core_note_type = NT_PRSTATUS, .n = ELF_NGREG,
+		.size = sizeof(long), .align = sizeof(long),
+		.get = gpr_get, .set = gpr_set
+	},
+	[REGSET_FPR] = {
+		.core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
+		.size = sizeof(double), .align = sizeof(double),
+		.get = fpr_get, .set = fpr_set
+	},
+#ifdef CONFIG_ALTIVEC
+	[REGSET_VMX] = {
+		.core_note_type = NT_PPC_VMX, .n = 34,
+		.size = sizeof(vector128), .align = sizeof(vector128),
+		.active = vr_active, .get = vr_get, .set = vr_set
+	},
+#endif
+#ifdef CONFIG_VSX
+	[REGSET_VSX] = {
+		.core_note_type = NT_PPC_VSX, .n = 32,
+		.size = sizeof(double), .align = sizeof(double),
+		.active = vsr_active, .get = vsr_get, .set = vsr_set
+	},
+#endif
+#ifdef CONFIG_SPE
+	[REGSET_SPE] = {
+		.core_note_type = NT_PPC_SPE, .n = 35,
+		.size = sizeof(u32), .align = sizeof(u32),
+		.active = evr_active, .get = evr_get, .set = evr_set
+	},
+#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	[REGSET_TM_CGPR] = {
+		.core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG,
+		.size = sizeof(long), .align = sizeof(long),
+		.active = tm_cgpr_active, .get = tm_cgpr_get, .set = tm_cgpr_set
+	},
+	[REGSET_TM_CFPR] = {
+		.core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG,
+		.size = sizeof(double), .align = sizeof(double),
+		.active = tm_cfpr_active, .get = tm_cfpr_get, .set = tm_cfpr_set
+	},
+	[REGSET_TM_CVMX] = {
+		.core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX,
+		.size = sizeof(vector128), .align = sizeof(vector128),
+		.active = tm_cvmx_active, .get = tm_cvmx_get, .set = tm_cvmx_set
+	},
+	[REGSET_TM_CVSX] = {
+		.core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX,
+		.size = sizeof(double), .align = sizeof(double),
+		.active = tm_cvsx_active, .get = tm_cvsx_get, .set = tm_cvsx_set
+	},
+	[REGSET_TM_SPR] = {
+		.core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.active = tm_spr_active, .get = tm_spr_get, .set = tm_spr_set
+	},
+	[REGSET_TM_CTAR] = {
+		.core_note_type = NT_PPC_TM_CTAR, .n = 1,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.active = tm_tar_active, .get = tm_tar_get, .set = tm_tar_set
+	},
+	[REGSET_TM_CPPR] = {
+		.core_note_type = NT_PPC_TM_CPPR, .n = 1,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.active = tm_ppr_active, .get = tm_ppr_get, .set = tm_ppr_set
+	},
+	[REGSET_TM_CDSCR] = {
+		.core_note_type = NT_PPC_TM_CDSCR, .n = 1,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.active = tm_dscr_active, .get = tm_dscr_get, .set = tm_dscr_set
+	},
+#endif
+#ifdef CONFIG_PPC64
+	[REGSET_PPR] = {
+		.core_note_type = NT_PPC_PPR, .n = 1,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.get = ppr_get, .set = ppr_set
+	},
+	[REGSET_DSCR] = {
+		.core_note_type = NT_PPC_DSCR, .n = 1,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.get = dscr_get, .set = dscr_set
+	},
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+	[REGSET_TAR] = {
+		.core_note_type = NT_PPC_TAR, .n = 1,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.get = tar_get, .set = tar_set
+	},
+	[REGSET_EBB] = {
+		.core_note_type = NT_PPC_EBB, .n = ELF_NEBB,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.active = ebb_active, .get = ebb_get, .set = ebb_set
+	},
+	[REGSET_PMR] = {
+		.core_note_type = NT_PPC_PMU, .n = ELF_NPMU,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.active = pmu_active, .get = pmu_get, .set = pmu_set
+	},
+#endif
+#ifdef CONFIG_PPC_MEM_KEYS
+	[REGSET_PKEY] = {
+		.core_note_type = NT_PPC_PKEY, .n = ELF_NPKEY,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.active = pkey_active, .get = pkey_get, .set = pkey_set
+	},
+#endif
+};
+
+const struct user_regset_view user_ppc_native_view = {
+	.name = UTS_MACHINE, .e_machine = ELF_ARCH, .ei_osabi = ELF_OSABI,
+	.regsets = native_regsets, .n = ARRAY_SIZE(native_regsets)
+};
+
+#include <linux/compat.h>
+
+int gpr32_get_common(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+			    void *kbuf, void __user *ubuf,
+			    unsigned long *regs)
+{
+	compat_ulong_t *k = kbuf;
+	compat_ulong_t __user *u = ubuf;
+	compat_ulong_t reg;
+
+	pos /= sizeof(reg);
+	count /= sizeof(reg);
+
+	if (kbuf)
+		for (; count > 0 && pos < PT_MSR; --count)
+			*k++ = regs[pos++];
+	else
+		for (; count > 0 && pos < PT_MSR; --count)
+			if (__put_user((compat_ulong_t)regs[pos++], u++))
+				return -EFAULT;
+
+	if (count > 0 && pos == PT_MSR) {
+		reg = get_user_msr(target);
+		if (kbuf)
+			*k++ = reg;
+		else if (__put_user(reg, u++))
+			return -EFAULT;
+		++pos;
+		--count;
+	}
+
+	if (kbuf)
+		for (; count > 0 && pos < PT_REGS_COUNT; --count)
+			*k++ = regs[pos++];
+	else
+		for (; count > 0 && pos < PT_REGS_COUNT; --count)
+			if (__put_user((compat_ulong_t)regs[pos++], u++))
+				return -EFAULT;
+
+	kbuf = k;
+	ubuf = u;
+	pos *= sizeof(reg);
+	count *= sizeof(reg);
+	return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
+					PT_REGS_COUNT * sizeof(reg), -1);
+}
+
+int gpr32_set_common(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     const void *kbuf, const void __user *ubuf,
+		     unsigned long *regs)
+{
+	const compat_ulong_t *k = kbuf;
+	const compat_ulong_t __user *u = ubuf;
+	compat_ulong_t reg;
+
+	pos /= sizeof(reg);
+	count /= sizeof(reg);
+
+	if (kbuf)
+		for (; count > 0 && pos < PT_MSR; --count)
+			regs[pos++] = *k++;
+	else
+		for (; count > 0 && pos < PT_MSR; --count) {
+			if (__get_user(reg, u++))
+				return -EFAULT;
+			regs[pos++] = reg;
+		}
+
+
+	if (count > 0 && pos == PT_MSR) {
+		if (kbuf)
+			reg = *k++;
+		else if (__get_user(reg, u++))
+			return -EFAULT;
+		set_user_msr(target, reg);
+		++pos;
+		--count;
+	}
+
+	if (kbuf) {
+		for (; count > 0 && pos <= PT_MAX_PUT_REG; --count)
+			regs[pos++] = *k++;
+		for (; count > 0 && pos < PT_TRAP; --count, ++pos)
+			++k;
+	} else {
+		for (; count > 0 && pos <= PT_MAX_PUT_REG; --count) {
+			if (__get_user(reg, u++))
+				return -EFAULT;
+			regs[pos++] = reg;
+		}
+		for (; count > 0 && pos < PT_TRAP; --count, ++pos)
+			if (__get_user(reg, u++))
+				return -EFAULT;
+	}
+
+	if (count > 0 && pos == PT_TRAP) {
+		if (kbuf)
+			reg = *k++;
+		else if (__get_user(reg, u++))
+			return -EFAULT;
+		set_user_trap(target, reg);
+		++pos;
+		--count;
+	}
+
+	kbuf = k;
+	ubuf = u;
+	pos *= sizeof(reg);
+	count *= sizeof(reg);
+	return user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf,
+					 (PT_TRAP + 1) * sizeof(reg), -1);
+}
+
+static int gpr32_get(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     void *kbuf, void __user *ubuf)
+{
+	int i;
+
+	if (target->thread.regs == NULL)
+		return -EIO;
+
+	if (!FULL_REGS(target->thread.regs)) {
+		/*
+		 * We have a partial register set.
+		 * Fill 14-31 with bogus values.
+		 */
+		for (i = 14; i < 32; i++)
+			target->thread.regs->gpr[i] = NV_REG_POISON;
+	}
+	return gpr32_get_common(target, regset, pos, count, kbuf, ubuf,
+			&target->thread.regs->gpr[0]);
+}
+
+static int gpr32_set(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     const void *kbuf, const void __user *ubuf)
+{
+	if (target->thread.regs == NULL)
+		return -EIO;
+
+	CHECK_FULL_REGS(target->thread.regs);
+	return gpr32_set_common(target, regset, pos, count, kbuf, ubuf,
+			&target->thread.regs->gpr[0]);
+}
+
+/*
+ * These are the regset flavors matching the CONFIG_PPC32 native set.
+ */
+static const struct user_regset compat_regsets[] = {
+	[REGSET_GPR] = {
+		.core_note_type = NT_PRSTATUS, .n = ELF_NGREG,
+		.size = sizeof(compat_long_t), .align = sizeof(compat_long_t),
+		.get = gpr32_get, .set = gpr32_set
+	},
+	[REGSET_FPR] = {
+		.core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
+		.size = sizeof(double), .align = sizeof(double),
+		.get = fpr_get, .set = fpr_set
+	},
+#ifdef CONFIG_ALTIVEC
+	[REGSET_VMX] = {
+		.core_note_type = NT_PPC_VMX, .n = 34,
+		.size = sizeof(vector128), .align = sizeof(vector128),
+		.active = vr_active, .get = vr_get, .set = vr_set
+	},
+#endif
+#ifdef CONFIG_SPE
+	[REGSET_SPE] = {
+		.core_note_type = NT_PPC_SPE, .n = 35,
+		.size = sizeof(u32), .align = sizeof(u32),
+		.active = evr_active, .get = evr_get, .set = evr_set
+	},
+#endif
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	[REGSET_TM_CGPR] = {
+		.core_note_type = NT_PPC_TM_CGPR, .n = ELF_NGREG,
+		.size = sizeof(long), .align = sizeof(long),
+		.active = tm_cgpr_active,
+		.get = tm_cgpr32_get, .set = tm_cgpr32_set
+	},
+	[REGSET_TM_CFPR] = {
+		.core_note_type = NT_PPC_TM_CFPR, .n = ELF_NFPREG,
+		.size = sizeof(double), .align = sizeof(double),
+		.active = tm_cfpr_active, .get = tm_cfpr_get, .set = tm_cfpr_set
+	},
+	[REGSET_TM_CVMX] = {
+		.core_note_type = NT_PPC_TM_CVMX, .n = ELF_NVMX,
+		.size = sizeof(vector128), .align = sizeof(vector128),
+		.active = tm_cvmx_active, .get = tm_cvmx_get, .set = tm_cvmx_set
+	},
+	[REGSET_TM_CVSX] = {
+		.core_note_type = NT_PPC_TM_CVSX, .n = ELF_NVSX,
+		.size = sizeof(double), .align = sizeof(double),
+		.active = tm_cvsx_active, .get = tm_cvsx_get, .set = tm_cvsx_set
+	},
+	[REGSET_TM_SPR] = {
+		.core_note_type = NT_PPC_TM_SPR, .n = ELF_NTMSPRREG,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.active = tm_spr_active, .get = tm_spr_get, .set = tm_spr_set
+	},
+	[REGSET_TM_CTAR] = {
+		.core_note_type = NT_PPC_TM_CTAR, .n = 1,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.active = tm_tar_active, .get = tm_tar_get, .set = tm_tar_set
+	},
+	[REGSET_TM_CPPR] = {
+		.core_note_type = NT_PPC_TM_CPPR, .n = 1,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.active = tm_ppr_active, .get = tm_ppr_get, .set = tm_ppr_set
+	},
+	[REGSET_TM_CDSCR] = {
+		.core_note_type = NT_PPC_TM_CDSCR, .n = 1,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.active = tm_dscr_active, .get = tm_dscr_get, .set = tm_dscr_set
+	},
+#endif
+#ifdef CONFIG_PPC64
+	[REGSET_PPR] = {
+		.core_note_type = NT_PPC_PPR, .n = 1,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.get = ppr_get, .set = ppr_set
+	},
+	[REGSET_DSCR] = {
+		.core_note_type = NT_PPC_DSCR, .n = 1,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.get = dscr_get, .set = dscr_set
+	},
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+	[REGSET_TAR] = {
+		.core_note_type = NT_PPC_TAR, .n = 1,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.get = tar_get, .set = tar_set
+	},
+	[REGSET_EBB] = {
+		.core_note_type = NT_PPC_EBB, .n = ELF_NEBB,
+		.size = sizeof(u64), .align = sizeof(u64),
+		.active = ebb_active, .get = ebb_get, .set = ebb_set
+	},
+#endif
+};
+
+static const struct user_regset_view user_ppc_compat_view = {
+	.name = "ppc", .e_machine = EM_PPC, .ei_osabi = ELF_OSABI,
+	.regsets = compat_regsets, .n = ARRAY_SIZE(compat_regsets)
+};
+
+const struct user_regset_view *task_user_regset_view(struct task_struct *task)
+{
+	if (IS_ENABLED(CONFIG_PPC64) && test_tsk_thread_flag(task, TIF_32BIT))
+		return &user_ppc_compat_view;
+	return &user_ppc_native_view;
+}

arch/powerpc/kernel/ptrace/ptrace-vsx.c

···
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/regset.h>
+
+#include <asm/switch_to.h>
+
+#include "ptrace-decl.h"
+
+/*
+ * Regardless of transactions, 'fp_state' holds the current running
+ * value of all FPR registers and 'ckfp_state' holds the last checkpointed
+ * value of all FPR registers for the current transaction.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ *	u64	fpr[32];
+ *	u64	fpscr;
+ * };
+ */
+int fpr_get(struct task_struct *target, const struct user_regset *regset,
+	    unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	u64 buf[33];
+	int i;
+
+	flush_fp_to_thread(target);
+
+	/* copy to local buffer then write that out */
+	for (i = 0; i < 32 ; i++)
+		buf[i] = target->thread.TS_FPR(i);
+	buf[32] = target->thread.fp_state.fpscr;
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
+}
+
+/*
+ * Regardless of transactions, 'fp_state' holds the current running
+ * value of all FPR registers and 'ckfp_state' holds the last checkpointed
+ * value of all FPR registers for the current transaction.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ *	u64	fpr[32];
+ *	u64	fpscr;
+ * };
+ *
+ */
+int fpr_set(struct task_struct *target, const struct user_regset *regset,
+	    unsigned int pos, unsigned int count,
+	    const void *kbuf, const void __user *ubuf)
+{
+	u64 buf[33];
+	int i;
+
+	flush_fp_to_thread(target);
+
+	for (i = 0; i < 32 ; i++)
+		buf[i] = target->thread.TS_FPR(i);
+	buf[32] = target->thread.fp_state.fpscr;
+
+	/* copy to local buffer then write that out */
+	i = user_regset_copyin(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
+	if (i)
+		return i;
+
+	for (i = 0; i < 32 ; i++)
+		target->thread.TS_FPR(i) = buf[i];
+	target->thread.fp_state.fpscr = buf[32];
+	return 0;
+}
+
+/*
+ * Currently to set and and get all the vsx state, you need to call
+ * the fp and VMX calls as well.  This only get/sets the lower 32
+ * 128bit VSX registers.
+ */
+
+int vsr_active(struct task_struct *target, const struct user_regset *regset)
+{
+	flush_vsx_to_thread(target);
+	return target->thread.used_vsr ? regset->n : 0;
+}
+
+/*
+ * Regardless of transactions, 'fp_state' holds the current running
+ * value of all FPR registers and 'ckfp_state' holds the last
+ * checkpointed value of all FPR registers for the current
+ * transaction.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ *	u64	vsx[32];
+ * };
+ */
+int vsr_get(struct task_struct *target, const struct user_regset *regset,
+	    unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
+{
+	u64 buf[32];
+	int ret, i;
+
+	flush_tmregs_to_thread(target);
+	flush_fp_to_thread(target);
+	flush_altivec_to_thread(target);
+	flush_vsx_to_thread(target);
+
+	for (i = 0; i < 32 ; i++)
+		buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
+
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  buf, 0, 32 * sizeof(double));
+
+	return ret;
+}
+
+/*
+ * Regardless of transactions, 'fp_state' holds the current running
+ * value of all FPR registers and 'ckfp_state' holds the last
+ * checkpointed value of all FPR registers for the current
+ * transaction.
+ *
+ * Userspace interface buffer layout:
+ *
+ * struct data {
+ *	u64	vsx[32];
+ * };
+ */
+int vsr_set(struct task_struct *target, const struct user_regset *regset,
+	    unsigned int pos, unsigned int count,
+	    const void *kbuf, const void __user *ubuf)
+{
+	u64 buf[32];
+	int ret, i;
+
+	flush_tmregs_to_thread(target);
+	flush_fp_to_thread(target);
+	flush_altivec_to_thread(target);
+	flush_vsx_to_thread(target);
+
+	for (i = 0; i < 32 ; i++)
+		buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 buf, 0, 32 * sizeof(double));
+	if (!ret)
+		for (i = 0; i < 32 ; i++)
+			target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
+
+	return ret;
+}

arch/powerpc/kernel/ptrace/ptrace.c

···
+/*
+ *  PowerPC version
+ *    Copyright (C) 1995-1996 Gary Thomas ([e-mail])
+ *
+ *  Derived from "arch/m68k/kernel/ptrace.c"
+ *  Copyright (C) 1994 by Hamish Macdonald
+ *  Taken from linux/kernel/ptrace.c and modified for M680x0.
+ *  linux/kernel/ptrace.c is by Ross Biro 1/23/92, edited by Linus Torvalds
+ *
+ * Modified by Cort Dougan ([e-mail])
+ * and Paul Mackerras ([e-mail]).
+ *
+ * This file is subject to the terms and conditions of the GNU General
+ * Public License.  See the file README.legal in the main directory of
+ * this archive for more details.
+ */
+
+#include <linux/regset.h>
+#include <linux/tracehook.h>
+#include <linux/audit.h>
+#include <linux/context_tracking.h>
+#include <linux/syscalls.h>
+
+#include <asm/switch_to.h>
+#include <asm/asm-prototypes.h>
+#include <asm/debug.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+#include "ptrace-decl.h"
+
+/*
+ * Called by kernel/ptrace.c when detaching..
+ *
+ * Make sure single step bits etc are not set.
+ */
+void ptrace_disable(struct task_struct *child)
+{
+	/* make sure the single step bit is not set. */
+	user_disable_single_step(child);
+}
+
+long arch_ptrace(struct task_struct *child, long request,
+		 unsigned long addr, unsigned long data)
+{
+	int ret = -EPERM;
+	void __user *datavp = (void __user *) data;
+	unsigned long __user *datalp = datavp;
+
+	switch (request) {
+	/* read the word at location addr in the USER area. */
+	case PTRACE_PEEKUSR: {
+		unsigned long index, tmp;
+
+		ret = -EIO;
+		/* convert to index and check */
+#ifdef CONFIG_PPC32
+		index = addr >> 2;
+		if ((addr & 3) || (index > PT_FPSCR)
+		    || (child->thread.regs == NULL))
+#else
+		index = addr >> 3;
+		if ((addr & 7) || (index > PT_FPSCR))
+#endif
+			break;
+
+		CHECK_FULL_REGS(child->thread.regs);
+		if (index < PT_FPR0) {
+			ret = ptrace_get_reg(child, (int) index, &tmp);
+			if (ret)
+				break;
+		} else {
+			unsigned int fpidx = index - PT_FPR0;
+
+			flush_fp_to_thread(child);
+			if (fpidx < (PT_FPSCR - PT_FPR0))
+				memcpy(&tmp, &child->thread.TS_FPR(fpidx),
+				       sizeof(long));
+			else
+				tmp = child->thread.fp_state.fpscr;
+		}
+		ret = put_user(tmp, datalp);
+		break;
+	}
+
+	/* write the word at location addr in the USER area */
+	case PTRACE_POKEUSR: {
+		unsigned long index;
+
+		ret = -EIO;
+		/* convert to index and check */
+#ifdef CONFIG_PPC32
+		index = addr >> 2;
+		if ((addr & 3) || (index > PT_FPSCR)
+		    || (child->thread.regs == NULL))
+#else
+		index = addr >> 3;
+		if ((addr & 7) || (index > PT_FPSCR))
+#endif
+			break;
+
+		CHECK_FULL_REGS(child->thread.regs);
+		if (index < PT_FPR0) {
+			ret = ptrace_put_reg(child, index, data);
+		} else {
+			unsigned int fpidx = index - PT_FPR0;
+
+			flush_fp_to_thread(child);
+			if (fpidx < (PT_FPSCR - PT_FPR0))
+				memcpy(&child->thread.TS_FPR(fpidx), &data,
+				       sizeof(long));
+			else
+				child->thread.fp_state.fpscr = data;
+			ret = 0;
+		}
+		break;
+	}
+
+	case PPC_PTRACE_GETHWDBGINFO: {
+		struct ppc_debug_info dbginfo;
+
+		ppc_gethwdinfo(&dbginfo);
+
+		if (copy_to_user(datavp, &dbginfo,
+				 sizeof(struct ppc_debug_info)))
+			return -EFAULT;
+		return 0;
+	}
+
+	case PPC_PTRACE_SETHWDEBUG: {
+		struct ppc_hw_breakpoint bp_info;
+
+		if (copy_from_user(&bp_info, datavp,
+				   sizeof(struct ppc_hw_breakpoint)))
+			return -EFAULT;
+		return ppc_set_hwdebug(child, &bp_info);
+	}
+
+	case PPC_PTRACE_DELHWDEBUG: {
+		ret = ppc_del_hwdebug(child, data);
+		break;
+	}
+
+	case PTRACE_GET_DEBUGREG:
+		ret = ptrace_get_debugreg(child, addr, datalp);
+		break;
+
+	case PTRACE_SET_DEBUGREG:
+		ret = ptrace_set_debugreg(child, addr, data);
+		break;
+
+#ifdef CONFIG_PPC64
+	case PTRACE_GETREGS64:
+#endif
+	case PTRACE_GETREGS:	/* Get all pt_regs from the child. */
+		return copy_regset_to_user(child, &user_ppc_native_view,
+					   REGSET_GPR,
+					   0, sizeof(struct user_pt_regs),
+					   datavp);
+
+#ifdef CONFIG_PPC64
+	case PTRACE_SETREGS64:
+#endif
+	case PTRACE_SETREGS:	/* Set all gp regs in the child. */
+		return copy_regset_from_user(child, &user_ppc_native_view,
+					     REGSET_GPR,
+					     0, sizeof(struct user_pt_regs),
+					     datavp);
+
+	case PTRACE_GETFPREGS: /* Get the child FPU state (FPR0...31 + FPSCR) */
+		return copy_regset_to_user(child, &user_ppc_native_view,
+					   REGSET_FPR,
+					   0, sizeof(elf_fpregset_t),
+					   datavp);
+
+	case PTRACE_SETFPREGS: /* Set the child FPU state (FPR0...31 + FPSCR) */
+		return copy_regset_from_user(child, &user_ppc_native_view,
+					     REGSET_FPR,
+					     0, sizeof(elf_fpregset_t),
+					     datavp);
+
+#ifdef CONFIG_ALTIVEC
+	case PTRACE_GETVRREGS:
+		return copy_regset_to_user(child, &user_ppc_native_view,
+					   REGSET_VMX,
+					   0, (33 * sizeof(vector128) +
+					       sizeof(u32)),
+					   datavp);
+
+	case PTRACE_SETVRREGS:
+		return copy_regset_from_user(child, &user_ppc_native_view,
+					     REGSET_VMX,
+					     0, (33 * sizeof(vector128) +
+						 sizeof(u32)),
+					     datavp);
+#endif
+#ifdef CONFIG_VSX
+	case PTRACE_GETVSRREGS:
+		return copy_regset_to_user(child, &user_ppc_native_view,
+					   REGSET_VSX,
+					   0, 32 * sizeof(double),
+					   datavp);
+
+	case PTRACE_SETVSRREGS:
+		return copy_regset_from_user(child, &user_ppc_native_view,
+					     REGSET_VSX,
+					     0, 32 * sizeof(double),
+					     datavp);
+#endif
+#ifdef CONFIG_SPE
+	case PTRACE_GETEVRREGS:
+		/* Get the child spe register state. */
+		return copy_regset_to_user(child, &user_ppc_native_view,
+					   REGSET_SPE, 0, 35 * sizeof(u32),
+					   datavp);
+
+	case PTRACE_SETEVRREGS:
+		/* Set the child spe register state. */
+		return copy_regset_from_user(child, &user_ppc_native_view,
+					     REGSET_SPE, 0, 35 * sizeof(u32),
+					     datavp);
+#endif
+
+	default:
+		ret = ptrace_request(child, request, addr, data);
+		break;
+	}
+	return ret;
+}
+
+#ifdef CONFIG_SECCOMP
+static int do_seccomp(struct pt_regs *regs)
+{
+	if (!test_thread_flag(TIF_SECCOMP))
+		return 0;
+
+	/*
+	 * The ABI we present to seccomp tracers is that r3 contains
+	 * the syscall return value and orig_gpr3 contains the first
+	 * syscall parameter. This is different to the ptrace ABI where
+	 * both r3 and orig_gpr3 contain the first syscall parameter.
+	 */
+	regs->gpr[3] = -ENOSYS;
+
+	/*
+	 * We use the __ version here because we have already checked
+	 * TIF_SECCOMP. If this fails, there is nothing left to do, we
+	 * have already loaded -ENOSYS into r3, or seccomp has put
+	 * something else in r3 (via SECCOMP_RET_ERRNO/TRACE).
+	 */
+	if (__secure_computing(NULL))
+		return -1;
+
+	/*
+	 * The syscall was allowed by seccomp, restore the register
+	 * state to what audit expects.
+	 * Note that we use orig_gpr3, which means a seccomp tracer can
+	 * modify the first syscall parameter (in orig_gpr3) and also
+	 * allow the syscall to proceed.
+	 */
+	regs->gpr[3] = regs->orig_gpr3;
+
+	return 0;
+}
+#else
+static inline int do_seccomp(struct pt_regs *regs) { return 0; }
+#endif /* CONFIG_SECCOMP */
+
+/**
+ * do_syscall_trace_enter() - Do syscall tracing on kernel entry.
+ * @regs: the pt_regs of the task to trace (current)
+ *
+ * Performs various types of tracing on syscall entry. This includes seccomp,
+ * ptrace, syscall tracepoints and audit.
+ *
+ * The pt_regs are potentially visible to userspace via ptrace, so their
+ * contents is ABI.
+ *
+ * One or more of the tracers may modify the contents of pt_regs, in particular
+ * to modify arguments or even the syscall number itself.
+ *
+ * It's also possible that a tracer can choose to reject the system call. In
+ * that case this function will return an illegal syscall number, and will put
+ * an appropriate return value in regs->r3.
+ *
+ * Return: the (possibly changed) syscall number.
+ */
+long do_syscall_trace_enter(struct pt_regs *regs)
+{
+	u32 flags;
+
+	user_exit();
+
+	flags = READ_ONCE(current_thread_info()->flags) &
+		(_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE);
+
+	if (flags) {
+		int rc = tracehook_report_syscall_entry(regs);
+
+		if (unlikely(flags & _TIF_SYSCALL_EMU)) {
+			/*
+			 * A nonzero return code from
+			 * tracehook_report_syscall_entry() tells us to prevent
+			 * the syscall execution, but we are not going to
+			 * execute it anyway.
+			 *
+			 * Returning -1 will skip the syscall execution. We want
+			 * to avoid clobbering any registers, so we don't goto
+			 * the skip label below.
+			 */
+			return -1;
+		}
+
+		if (rc) {
+			/*
+			 * The tracer decided to abort the syscall. Note that
+			 * the tracer may also just change regs->gpr[0] to an
+			 * invalid syscall number, that is handled below on the
+			 * exit path.
+			 */
+			goto skip;
+		}
+	}
+
+	/* Run seccomp after ptrace; allow it to set gpr[3]. */
+	if (do_seccomp(regs))
+		return -1;
+
+	/* Avoid trace and audit when syscall is invalid. */
+	if (regs->gpr[0] >= NR_syscalls)
+		goto skip;
+
+	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+		trace_sys_enter(regs, regs->gpr[0]);
+
+	if (!is_32bit_task())
+		audit_syscall_entry(regs->gpr[0], regs->gpr[3], regs->gpr[4],
+				    regs->gpr[5], regs->gpr[6]);
+	else
+		audit_syscall_entry(regs->gpr[0],
+				    regs->gpr[3] & 0xffffffff,
+				    regs->gpr[4] & 0xffffffff,
+				    regs->gpr[5] & 0xffffffff,
+				    regs->gpr[6] & 0xffffffff);
+
+	/* Return the possibly modified but valid syscall number */
+	return regs->gpr[0];
+
+skip:
+	/*
+	 * If we are aborting explicitly, or if the syscall number is
+	 * now invalid, set the return value to -ENOSYS.
+	 */
+	regs->gpr[3] = -ENOSYS;
+	return -1;
+}
+
+void do_syscall_trace_leave(struct pt_regs *regs)
+{
+	int step;
+
+	audit_syscall_exit(regs);
+
+	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+		trace_sys_exit(regs, regs->result);
+
+	step = test_thread_flag(TIF_SINGLESTEP);
+	if (step || test_thread_flag(TIF_SYSCALL_TRACE))
+		tracehook_report_syscall_exit(regs, step);
+
+	user_enter();
+}
+
+void __init pt_regs_check(void);
+
+/*
+ * Dummy function, its purpose is to break the build if struct pt_regs and
+ * struct user_pt_regs don't match.
+ */
+void __init pt_regs_check(void)
+{
+	BUILD_BUG_ON(offsetof(struct pt_regs, gpr) !=
+		     offsetof(struct user_pt_regs, gpr));
+	BUILD_BUG_ON(offsetof(struct pt_regs, nip) !=
+		     offsetof(struct user_pt_regs, nip));
+	BUILD_BUG_ON(offsetof(struct pt_regs, msr) !=
+		     offsetof(struct user_pt_regs, msr));
+	BUILD_BUG_ON(offsetof(struct pt_regs, msr) !=
+		     offsetof(struct user_pt_regs, msr));
+	BUILD_BUG_ON(offsetof(struct pt_regs, orig_gpr3) !=
+		     offsetof(struct user_pt_regs, orig_gpr3));
+	BUILD_BUG_ON(offsetof(struct pt_regs, ctr) !=
+		     offsetof(struct user_pt_regs, ctr));
+	BUILD_BUG_ON(offsetof(struct pt_regs, link) !=
+		     offsetof(struct user_pt_regs, link));
+	BUILD_BUG_ON(offsetof(struct pt_regs, xer) !=
+		     offsetof(struct user_pt_regs, xer));
+	BUILD_BUG_ON(offsetof(struct pt_regs, ccr) !=
+		     offsetof(struct user_pt_regs, ccr));
+#ifdef __powerpc64__
+	BUILD_BUG_ON(offsetof(struct pt_regs, softe) !=
+		     offsetof(struct user_pt_regs, softe));
+#else
+	BUILD_BUG_ON(offsetof(struct pt_regs, mq) !=
+		     offsetof(struct user_pt_regs, mq));
+#endif
+	BUILD_BUG_ON(offsetof(struct pt_regs, trap) !=
+		     offsetof(struct user_pt_regs, trap));
+	BUILD_BUG_ON(offsetof(struct pt_regs, dar) !=
+		     offsetof(struct user_pt_regs, dar));
+	BUILD_BUG_ON(offsetof(struct pt_regs, dsisr) !=
+		     offsetof(struct user_pt_regs, dsisr));
+	BUILD_BUG_ON(offsetof(struct pt_regs, result) !=
+		     offsetof(struct user_pt_regs, result));
+
+	BUILD_BUG_ON(sizeof(struct user_pt_regs) > sizeof(struct pt_regs));
+
+	// Now check that the pt_regs offsets match the uapi #defines
+	#define CHECK_REG(_pt, _reg) \
+		BUILD_BUG_ON(_pt != (offsetof(struct user_pt_regs, _reg) / \
+				     sizeof(unsigned long)));
+
+	CHECK_REG(PT_R0,  gpr[0]);
+	CHECK_REG(PT_R1,  gpr[1]);
+	CHECK_REG(PT_R2,  gpr[2]);
+	CHECK_REG(PT_R3,  gpr[3]);
+	CHECK_REG(PT_R4,  gpr[4]);
+	CHECK_REG(PT_R5,  gpr[5]);
+	CHECK_REG(PT_R6,  gpr[6]);
+	CHECK_REG(PT_R7,  gpr[7]);
+	CHECK_REG(PT_R8,  gpr[8]);
+	CHECK_REG(PT_R9,  gpr[9]);
+	CHECK_REG(PT_R10, gpr[10]);
+	CHECK_REG(PT_R11, gpr[11]);
+	CHECK_REG(PT_R12, gpr[12]);
+	CHECK_REG(PT_R13, gpr[13]);
+	CHECK_REG(PT_R14, gpr[14]);
+	CHECK_REG(PT_R15, gpr[15]);
+	CHECK_REG(PT_R16, gpr[16]);
+	CHECK_REG(PT_R17, gpr[17]);
+	CHECK_REG(PT_R18, gpr[18]);
+	CHECK_REG(PT_R19, gpr[19]);
+	CHECK_REG(PT_R20, gpr[20]);
+	CHECK_REG(PT_R21, gpr[21]);
+	CHECK_REG(PT_R22, gpr[22]);
+	CHECK_REG(PT_R23, gpr[23]);
+	CHECK_REG(PT_R24, gpr[24]);
+	CHECK_REG(PT_R25, gpr[25]);
+	CHECK_REG(PT_R26, gpr[26]);
+	CHECK_REG(PT_R27, gpr[27]);
+	CHECK_REG(PT_R28, gpr[28]);
+	CHECK_REG(PT_R29, gpr[29]);
+	CHECK_REG(PT_R30, gpr[30]);
+	CHECK_REG(PT_R31, gpr[31]);
+	CHECK_REG(PT_NIP, nip);
+	CHECK_REG(PT_MSR, msr);
+	CHECK_REG(PT_ORIG_R3, orig_gpr3);
+	CHECK_REG(PT_CTR, ctr);
+	CHECK_REG(PT_LNK, link);
+	CHECK_REG(PT_XER, xer);
+	CHECK_REG(PT_CCR, ccr);
+#ifdef CONFIG_PPC64
+	CHECK_REG(PT_SOFTE, softe);
+#else
+	CHECK_REG(PT_MQ, mq);
+#endif
+	CHECK_REG(PT_TRAP, trap);
+	CHECK_REG(PT_DAR, dar);
+	CHECK_REG(PT_DSISR, dsisr);
+	CHECK_REG(PT_RESULT, result);
+	#undef CHECK_REG
+
+	BUILD_BUG_ON(PT_REGS_COUNT != sizeof(struct user_pt_regs) / sizeof(unsigned long));
+
+	/*
+	 * PT_DSCR isn't a real reg, but it's important that it doesn't overlap the
+	 * real registers.
+	 */
+	BUILD_BUG_ON(PT_DSCR < sizeof(struct user_pt_regs) / sizeof(unsigned long));
+}

arch/powerpc/kernel/ptrace32.c arch/powerpc/kernel/ptrace/ptrace32.c

···
  * this archive for more details.
  */
 
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/errno.h>
 #include <linux/ptrace.h>
 #include <linux/regset.h>
-#include <linux/user.h>
-#include <linux/security.h>
-#include <linux/signal.h>
 #include <linux/compat.h>
 
-#include <linux/uaccess.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
 #include <asm/switch_to.h>
 
 /*

arch/powerpc/kernel/setup-common.c

···
 static int powerpc_debugfs_init(void)
 {
 	powerpc_debugfs_root = debugfs_create_dir("powerpc", NULL);
-
-	return powerpc_debugfs_root == NULL;
+	return 0;
 }
 arch_initcall(powerpc_debugfs_init);
 #endif

arch/powerpc/kernel/setup.h

···
 #ifndef __ARCH_POWERPC_KERNEL_SETUP_H
 #define __ARCH_POWERPC_KERNEL_SETUP_H
 
+#ifdef CONFIG_CC_IS_CLANG
+#define __nostackprotector
+#else
+#define __nostackprotector __attribute__((__optimize__("no-stack-protector")))
+#endif
+
 void initialize_cache_info(void);
 void irqstack_early_init(void);
 

arch/powerpc/kernel/setup_32.c

···
 int smp_hw_index[NR_CPUS];
 EXPORT_SYMBOL(smp_hw_index);
 
-unsigned long ISA_DMA_THRESHOLD;
 unsigned int DMA_MODE_READ;
 unsigned int DMA_MODE_WRITE;
 

arch/powerpc/kernel/setup_64.c

···
  * device-tree is not accessible via normal means at this point.
  */
 
-void __init early_setup(unsigned long dt_ptr)
+void __init __nostackprotector early_setup(unsigned long dt_ptr)
 {
 	static __initdata struct paca_struct boot_paca;
 
 	/* -------- printk is _NOT_ safe to use here ! ------- */
 
-	/* Try new device tree based feature discovery ... */
-	if (!dt_cpu_ftrs_init(__va(dt_ptr)))
-		/* Otherwise use the old style CPU table */
-		identify_cpu(0, mfspr(SPRN_PVR));
-
-	/* Assume we're on cpu 0 for now. Don't write to the paca yet! */
+	/*
+	 * Assume we're on cpu 0 for now.
+	 *
+	 * We need to load a PACA very early for a few reasons.
+	 *
+	 * The stack protector canary is stored in the paca, so as soon as we
+	 * call any stack protected code we need r13 pointing somewhere valid.
+	 *
+	 * If we are using kcov it will call in_task() in its instrumentation,
+	 * which relies on the current task from the PACA.
+	 *
+	 * dt_cpu_ftrs_init() calls into generic OF/fdt code, as well as
+	 * printk(), which can trigger both stack protector and kcov.
+	 *
+	 * percpu variables and spin locks also use the paca.
+	 *
+	 * So set up a temporary paca. It will be replaced below once we know
+	 * what CPU we are on.
+	 */
 	initialise_paca(&boot_paca, 0);
 	setup_paca(&boot_paca);
 	fixup_boot_paca();
 
 	/* -------- printk is now safe to use ------- */
+
+	/* Try new device tree based feature discovery ... */
+	if (!dt_cpu_ftrs_init(__va(dt_ptr)))
+		/* Otherwise use the old style CPU table */
+		identify_cpu(0, mfspr(SPRN_PVR));
 
 	/* Enable early debugging if any specified (see udbg.h) */
 	udbg_early_init();

arch/powerpc/kernel/signal.h

···
 #ifndef _POWERPC_ARCH_SIGNAL_H
 #define _POWERPC_ARCH_SIGNAL_H
 
-extern void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags);
-
 extern void __user *get_sigframe(struct ksignal *ksig, unsigned long sp,
 				  size_t frame_size, int is_32);
 

arch/powerpc/kernel/signal_64.c

···
 	err |= __get_user(tsk->thread.ckpt_regs.ccr,
 			  &sc->gp_regs[PT_CCR]);
 
+	/* Don't allow userspace to set the trap value */
+	regs->trap = 0;
+
 	/* These regs are not checkpointed; they can go in 'regs'. */
-	err |= __get_user(regs->trap, &sc->gp_regs[PT_TRAP]);
 	err |= __get_user(regs->dar, &sc->gp_regs[PT_DAR]);
 	err |= __get_user(regs->dsisr, &sc->gp_regs[PT_DSISR]);
 	err |= __get_user(regs->result, &sc->gp_regs[PT_RESULT]);

arch/powerpc/kernel/smp.c

···
 	}
 }
 
+int get_physical_package_id(int cpu)
+{
+	int pkg_id = cpu_to_chip_id(cpu);
+
+	/*
+	 * If the platform is PowerNV or Guest on KVM, ibm,chip-id is
+	 * defined. Hence we would return the chip-id as the result of
+	 * get_physical_package_id.
+	 */
+	if (pkg_id == -1 && firmware_has_feature(FW_FEATURE_LPAR) &&
+	    IS_ENABLED(CONFIG_PPC_SPLPAR)) {
+		struct device_node *np = of_get_cpu_node(cpu, NULL);
+		pkg_id = of_node_to_nid(np);
+		of_node_put(np);
+	}
+
+	return pkg_id;
+}
+EXPORT_SYMBOL_GPL(get_physical_package_id);
+
 static void add_cpu_to_masks(int cpu)
 {
 	int first_thread = cpu_first_thread_sibling(cpu);
-	int chipid = cpu_to_chip_id(cpu);
+	int pkg_id = get_physical_package_id(cpu);
 	int i;
 
 	/*
···
 	for_each_cpu(i, cpu_l2_cache_mask(cpu))
 		set_cpus_related(cpu, i, cpu_core_mask);
 
-	if (chipid == -1)
+	if (pkg_id == -1)
 		return;
 
 	for_each_cpu(i, cpu_online_mask)
-		if (cpu_to_chip_id(i) == chipid)
+		if (get_physical_package_id(i) == pkg_id)
 			set_cpus_related(cpu, i, cpu_core_mask);
 }
 
···
 	if (smp_ops && smp_ops->bringup_done)
 		smp_ops->bringup_done();
 
-	/*
-	 * On a shared LPAR, associativity needs to be requested.
-	 * Hence, get numa topology before dumping cpu topology
-	 */
-	shared_proc_topology_init();
 	dump_numa_cpu_topology();
 
 #ifdef CONFIG_SCHED_SMT

arch/powerpc/kernel/stacktrace.c

···
 {
 	unsigned long sp;
 
-	sp = current_stack_pointer();
+	sp = current_stack_frame();
 
 	save_context_stack(trace, sp, current, 1);
 }
···
 		return;
 
 	if (tsk == current)
-		sp = current_stack_pointer();
+		sp = current_stack_frame();
 	else
 		sp = tsk->thread.ksp;
 
···
 	}
 
 	if (tsk == current)
-		sp = current_stack_pointer();
+		sp = current_stack_frame();
 	else
 		sp = tsk->thread.ksp;
 

arch/powerpc/kernel/syscall_64.c

···
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/err.h>
+#include <asm/asm-prototypes.h>
+#include <asm/book3s/64/kup-radix.h>
+#include <asm/cputime.h>
+#include <asm/hw_irq.h>
+#include <asm/kprobes.h>
+#include <asm/paca.h>
+#include <asm/ptrace.h>
+#include <asm/reg.h>
+#include <asm/signal.h>
+#include <asm/switch_to.h>
+#include <asm/syscall.h>
+#include <asm/time.h>
+#include <asm/unistd.h>
+
+typedef long (*syscall_fn)(long, long, long, long, long, long);
+
+/* Has to run notrace because it is entered not completely "reconciled" */
+notrace long system_call_exception(long r3, long r4, long r5,
+				   long r6, long r7, long r8,
+				   unsigned long r0, struct pt_regs *regs)
+{
+	unsigned long ti_flags;
+	syscall_fn f;
+
+	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+		BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED);
+
+	trace_hardirqs_off(); /* finish reconciling */
+
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S))
+		BUG_ON(!(regs->msr & MSR_RI));
+	BUG_ON(!(regs->msr & MSR_PR));
+	BUG_ON(!FULL_REGS(regs));
+	BUG_ON(regs->softe != IRQS_ENABLED);
+
+	account_cpu_user_entry();
+
+#ifdef CONFIG_PPC_SPLPAR
+	if (IS_ENABLED(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) &&
+	    firmware_has_feature(FW_FEATURE_SPLPAR)) {
+		struct lppaca *lp = local_paca->lppaca_ptr;
+
+		if (unlikely(local_paca->dtl_ridx != be64_to_cpu(lp->dtl_idx)))
+			accumulate_stolen_time();
+	}
+#endif
+
+	kuap_check_amr();
+
+	/*
+	 * This is not required for the syscall exit path, but makes the
+	 * stack frame look nicer. If this was initialised in the first stack
+	 * frame, or if the unwinder was taught the first stack frame always
+	 * returns to user with IRQS_ENABLED, this store could be avoided!
+	 */
+	regs->softe = IRQS_ENABLED;
+
+	local_irq_enable();
+
+	ti_flags = current_thread_info()->flags;
+	if (unlikely(ti_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
+		 * do_syscall_trace_enter() returns an invalid syscall number
+		 * and the test against NR_syscalls will fail and the return
+		 * value to be used is in regs->gpr[3].
+		 */
+		r0 = do_syscall_trace_enter(regs);
+		if (unlikely(r0 >= NR_syscalls))
+			return regs->gpr[3];
+		r3 = regs->gpr[3];
+		r4 = regs->gpr[4];
+		r5 = regs->gpr[5];
+		r6 = regs->gpr[6];
+		r7 = regs->gpr[7];
+		r8 = regs->gpr[8];
+
+	} else if (unlikely(r0 >= NR_syscalls)) {
+		return -ENOSYS;
+	}
+
+	/* May be faster to do array_index_nospec? */
+	barrier_nospec();
+
+	if (unlikely(ti_flags & _TIF_32BIT)) {
+		f = (void *)compat_sys_call_table[r0];
+
+		r3 &= 0x00000000ffffffffULL;
+		r4 &= 0x00000000ffffffffULL;
+		r5 &= 0x00000000ffffffffULL;
+		r6 &= 0x00000000ffffffffULL;
+		r7 &= 0x00000000ffffffffULL;
+		r8 &= 0x00000000ffffffffULL;
+
+	} else {
+		f = (void *)sys_call_table[r0];
+	}
+
+	return f(r3, r4, r5, r6, r7, r8);
+}
+
+/*
+ * This should be called after a syscall returns, with r3 the return value
+ * from the syscall. If this function returns non-zero, the system call
+ * exit assembly should additionally load all GPR registers and CTR and XER
+ * from the interrupt frame.
+ *
+ * The function graph tracer can not trace the return side of this function,
+ * because RI=0 and soft mask state is "unreconciled", so it is marked notrace.
+ */
+notrace unsigned long syscall_exit_prepare(unsigned long r3,
+					   struct pt_regs *regs)
+{
+	unsigned long *ti_flagsp = &current_thread_info()->flags;
+	unsigned long ti_flags;
+	unsigned long ret = 0;
+
+	regs->result = r3;
+
+	/* Check whether the syscall is issued inside a restartable sequence */
+	rseq_syscall(regs);
+
+	ti_flags = *ti_flagsp;
+
+	if (unlikely(r3 >= (unsigned long)-MAX_ERRNO)) {
+		if (likely(!(ti_flags & (_TIF_NOERROR | _TIF_RESTOREALL)))) {
+			r3 = -r3;
+			regs->ccr |= 0x10000000; /* Set SO bit in CR */
+		}
+	}
+
+	if (unlikely(ti_flags & _TIF_PERSYSCALL_MASK)) {
+		if (ti_flags & _TIF_RESTOREALL)
+			ret = _TIF_RESTOREALL;
+		else
+			regs->gpr[3] = r3;
+		clear_bits(_TIF_PERSYSCALL_MASK, ti_flagsp);
+	} else {
+		regs->gpr[3] = r3;
+	}
+
+	if (unlikely(ti_flags & _TIF_SYSCALL_DOTRACE)) {
+		do_syscall_trace_leave(regs);
+		ret |= _TIF_RESTOREALL;
+	}
+
+again:
+	local_irq_disable();
+	ti_flags = READ_ONCE(*ti_flagsp);
+	while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
+		local_irq_enable();
+		if (ti_flags & _TIF_NEED_RESCHED) {
+			schedule();
+		} else {
+			/*
+			 * SIGPENDING must restore signal handler function
+			 * argument GPRs, and some non-volatiles (e.g., r1).
+			 * Restore all for now. This could be made lighter.
+			 */
+			if (ti_flags & _TIF_SIGPENDING)
+				ret |= _TIF_RESTOREALL;
+			do_notify_resume(regs, ti_flags);
+		}
+		local_irq_disable();
+		ti_flags = READ_ONCE(*ti_flagsp);
+	}
+
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S) && IS_ENABLED(CONFIG_PPC_FPU)) {
+		if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
+				unlikely((ti_flags & _TIF_RESTORE_TM))) {
+			restore_tm_state(regs);
+		} else {
+			unsigned long mathflags = MSR_FP;
+
+			if (cpu_has_feature(CPU_FTR_VSX))
+				mathflags |= MSR_VEC | MSR_VSX;
+			else if (cpu_has_feature(CPU_FTR_ALTIVEC))
+				mathflags |= MSR_VEC;
+
+			if ((regs->msr & mathflags) != mathflags)
+				restore_math(regs);
+		}
+	}
+
+	/* This must be done with RI=1 because tracing may touch vmaps */
+	trace_hardirqs_on();
+
+	/* This pattern matches prep_irq_for_idle */
+	__hard_EE_RI_disable();
+	if (unlikely(lazy_irq_pending())) {
+		__hard_RI_enable();
+		trace_hardirqs_off();
+		local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+		local_irq_enable();
+		/* Took an interrupt, may have more exit work to do. */
+		goto again;
+	}
+	local_paca->irq_happened = 0;
+	irq_soft_mask_set(IRQS_ENABLED);
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	local_paca->tm_scratch = regs->msr;
+#endif
+
+	kuap_check_amr();
+
+	account_cpu_user_exit();
+
+	return ret;
+}
+
+#ifdef CONFIG_PPC_BOOK3S /* BOOK3E not yet using this */
+notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned long msr)
+{
+#ifdef CONFIG_PPC_BOOK3E
+	struct thread_struct *ts = &current->thread;
+#endif
+	unsigned long *ti_flagsp = &current_thread_info()->flags;
+	unsigned long ti_flags;
+	unsigned long flags;
+	unsigned long ret = 0;
+
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S))
+		BUG_ON(!(regs->msr & MSR_RI));
+	BUG_ON(!(regs->msr & MSR_PR));
+	BUG_ON(!FULL_REGS(regs));
+	BUG_ON(regs->softe != IRQS_ENABLED);
+
+	local_irq_save(flags);
+
+again:
+	ti_flags = READ_ONCE(*ti_flagsp);
+	while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
+		local_irq_enable(); /* returning to user: may enable */
+		if (ti_flags & _TIF_NEED_RESCHED) {
+			schedule();
+		} else {
+			if (ti_flags & _TIF_SIGPENDING)
+				ret |= _TIF_RESTOREALL;
+			do_notify_resume(regs, ti_flags);
+		}
+		local_irq_disable();
+		ti_flags = READ_ONCE(*ti_flagsp);
+	}
+
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S) && IS_ENABLED(CONFIG_PPC_FPU)) {
+		if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
+				unlikely((ti_flags & _TIF_RESTORE_TM))) {
+			restore_tm_state(regs);
+		} else {
+			unsigned long mathflags = MSR_FP;
+
+			if (cpu_has_feature(CPU_FTR_VSX))
+				mathflags |= MSR_VEC | MSR_VSX;
+			else if (cpu_has_feature(CPU_FTR_ALTIVEC))
+				mathflags |= MSR_VEC;
+
+			if ((regs->msr & mathflags) != mathflags)
+				restore_math(regs);
+		}
+	}
+
+	trace_hardirqs_on();
+	__hard_EE_RI_disable();
+	if (unlikely(lazy_irq_pending())) {
+		__hard_RI_enable();
+		trace_hardirqs_off();
+		local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+		local_irq_enable();
+		local_irq_disable();
+		/* Took an interrupt, may have more exit work to do. */
+		goto again;
+	}
+	local_paca->irq_happened = 0;
+	irq_soft_mask_set(IRQS_ENABLED);
+
+#ifdef CONFIG_PPC_BOOK3E
+	if (unlikely(ts->debug.dbcr0 & DBCR0_IDM)) {
+		/*
+		 * Check to see if the dbcr0 register is set up to debug.
+		 * Use the internal debug mode bit to do this.
+		 */
+		mtmsr(mfmsr() & ~MSR_DE);
+		mtspr(SPRN_DBCR0, ts->debug.dbcr0);
+		mtspr(SPRN_DBSR, -1);
+	}
+#endif
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	local_paca->tm_scratch = regs->msr;
+#endif
+
+	kuap_check_amr();
+
+	account_cpu_user_exit();
+
+	return ret;
+}
+
+void unrecoverable_exception(struct pt_regs *regs);
+void preempt_schedule_irq(void);
+
+notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsigned long msr)
+{
+	unsigned long *ti_flagsp = &current_thread_info()->flags;
+	unsigned long flags;
+	unsigned long ret = 0;
+
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S) && unlikely(!(regs->msr & MSR_RI)))
+		unrecoverable_exception(regs);
+	BUG_ON(regs->msr & MSR_PR);
+	BUG_ON(!FULL_REGS(regs));
+
+	if (unlikely(*ti_flagsp & _TIF_EMULATE_STACK_STORE)) {
+		clear_bits(_TIF_EMULATE_STACK_STORE, ti_flagsp);
+		ret = 1;
+	}
+
+	local_irq_save(flags);
+
+	if (regs->softe == IRQS_ENABLED) {
+		/* Returning to a kernel context with local irqs enabled. */
+		WARN_ON_ONCE(!(regs->msr & MSR_EE));
+again:
+		if (IS_ENABLED(CONFIG_PREEMPT)) {
+			/* Return to preemptible kernel context */
+			if (unlikely(*ti_flagsp & _TIF_NEED_RESCHED)) {
+				if (preempt_count() == 0)
+					preempt_schedule_irq();
+			}
+		}
+
+		trace_hardirqs_on();
+		__hard_EE_RI_disable();
+		if (unlikely(lazy_irq_pending())) {
+			__hard_RI_enable();
+			irq_soft_mask_set(IRQS_ALL_DISABLED);
+			trace_hardirqs_off();
+			local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+			/*
+			 * Can't local_irq_restore to replay if we were in
+			 * interrupt context. Must replay directly.
+			 */
+			if (irqs_disabled_flags(flags)) {
+				replay_soft_interrupts();
+			} else {
+				local_irq_restore(flags);
+				local_irq_save(flags);
+			}
+			/* Took an interrupt, may have more exit work to do. */
+			goto again;
+		}
+		local_paca->irq_happened = 0;
+		irq_soft_mask_set(IRQS_ENABLED);
+	} else {
+		/* Returning to a kernel context with local irqs disabled. */
+		__hard_EE_RI_disable();
+		if (regs->msr & MSR_EE)
+			local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+	}
+
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	local_paca->tm_scratch = regs->msr;
+#endif
+
+	/*
+	 * We don't need to restore AMR on the way back to userspace for KUAP.
+	 * The value of AMR only matters while we're in the kernel.
+	 */
+	kuap_restore_amr(regs);
+
+	return ret;
+}
+#endif

arch/powerpc/kernel/syscalls/syscall.tbl

···
 #
 0	nospu	restart_syscall			sys_restart_syscall
 1	nospu	exit				sys_exit
-2	nospu	fork				ppc_fork
+2	32	fork				ppc_fork			sys_fork
+2	64	fork				sys_fork
+2	spu	fork				sys_ni_syscall
 3	common	read				sys_read
 4	common	write				sys_write
 5	common	open				sys_open			compat_sys_open
···
 119	32	sigreturn			sys_sigreturn			compat_sys_sigreturn
 119	64	sigreturn			sys_ni_syscall
 119	spu	sigreturn			sys_ni_syscall
-120	nospu	clone				ppc_clone
+120	32	clone				ppc_clone			sys_clone
+120	64	clone				sys_clone
+120	spu	clone				sys_ni_syscall
 121	common	setdomainname			sys_setdomainname
 122	common	uname				sys_newuname
 123	common	modify_ldt			sys_ni_syscall
···
 186	spu	sendfile			sys_sendfile64
 187	common	getpmsg				sys_ni_syscall
 188	common 	putpmsg				sys_ni_syscall
-189	nospu	vfork				ppc_vfork
+189	32	vfork				ppc_vfork			sys_vfork
+189	64	vfork				sys_vfork
+189	spu	vfork				sys_ni_syscall
 190	common	ugetrlimit			sys_getrlimit			compat_sys_getrlimit
 191	common	readahead			sys_readahead			compat_sys_readahead
 192	32	mmap2				sys_mmap2			compat_sys_mmap2
···
 248	32	clock_nanosleep			sys_clock_nanosleep_time32
 248	64	clock_nanosleep			sys_clock_nanosleep
 248	spu	clock_nanosleep			sys_clock_nanosleep
-249	32	swapcontext			ppc_swapcontext			ppc32_swapcontext
-249	64	swapcontext			ppc64_swapcontext
+249	32	swapcontext			ppc_swapcontext			compat_sys_swapcontext
+249	64	swapcontext			sys_swapcontext
 249	spu	swapcontext			sys_ni_syscall
 250	common	tgkill				sys_tgkill
 251	32	utimes				sys_utimes_time32
···
 361	common	bpf				sys_bpf
 362	nospu	execveat			sys_execveat			compat_sys_execveat
 363	32	switch_endian			sys_ni_syscall
-363	64	switch_endian			ppc_switch_endian
+363	64	switch_endian			sys_switch_endian
 363	spu	switch_endian			sys_ni_syscall
 364	common	userfaultfd			sys_userfaultfd
 365	common	membarrier			sys_membarrier
···
 432	common	fsmount				sys_fsmount
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
-435	nospu	clone3				ppc_clone3
+435	32	clone3				ppc_clone3			sys_clone3
+435	64	clone3				sys_clone3
+435	spu	clone3				sys_ni_syscall
 437	common	openat2				sys_openat2
 438	common	pidfd_getfd			sys_pidfd_getfd

arch/powerpc/kernel/sysfs.c

···
 
 #endif /* CONFIG_PPC64 */
 
+#define __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, EXTRA) \
+static void read_##NAME(void *val) \
+{ \
+	*(unsigned long *)val = mfspr(ADDRESS);	\
+} \
+static void write_##NAME(void *val) \
+{ \
+	EXTRA; \
+	mtspr(ADDRESS, *(unsigned long *)val);	\
+}
+
+#define __SYSFS_SPRSETUP_SHOW_STORE(NAME) \
+static ssize_t show_##NAME(struct device *dev, \
+			struct device_attribute *attr, \
+			char *buf) \
+{ \
+	struct cpu *cpu = container_of(dev, struct cpu, dev); \
+	unsigned long val; \
+	smp_call_function_single(cpu->dev.id, read_##NAME, &val, 1);	\
+	return sprintf(buf, "%lx\n", val); \
+} \
+static ssize_t __used \
+	store_##NAME(struct device *dev, struct device_attribute *attr, \
+			const char *buf, size_t count) \
+{ \
+	struct cpu *cpu = container_of(dev, struct cpu, dev); \
+	unsigned long val; \
+	int ret = sscanf(buf, "%lx", &val); \
+	if (ret != 1) \
+		return -EINVAL; \
+	smp_call_function_single(cpu->dev.id, write_##NAME, &val, 1); \
+	return count; \
+}
+
+#define SYSFS_PMCSETUP(NAME, ADDRESS) \
+	__SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, ppc_enable_pmcs()) \
+	__SYSFS_SPRSETUP_SHOW_STORE(NAME)
+#define SYSFS_SPRSETUP(NAME, ADDRESS) \
+	__SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, ) \
+	__SYSFS_SPRSETUP_SHOW_STORE(NAME)
+
+#define SYSFS_SPRSETUP_SHOW_STORE(NAME) \
+	__SYSFS_SPRSETUP_SHOW_STORE(NAME)
+
+#ifdef CONFIG_PPC64
+
+/*
+ * This is the system wide DSCR register default value. Any
+ * change to this default value through the sysfs interface
+ * will update all per cpu DSCR default values across the
+ * system stored in their respective PACA structures.
+ */
+static unsigned long dscr_default;
+
+/**
+ * read_dscr() - Fetch the cpu specific DSCR default
+ * @val:	Returned cpu specific DSCR default value
+ *
+ * This function returns the per cpu DSCR default value
+ * for any cpu which is contained in it's PACA structure.
+ */
+static void read_dscr(void *val)
+{
+	*(unsigned long *)val = get_paca()->dscr_default;
+}
+
+
+/**
+ * write_dscr() - Update the cpu specific DSCR default
+ * @val:	New cpu specific DSCR default value to update
+ *
+ * This function updates the per cpu DSCR default value
+ * for any cpu which is contained in it's PACA structure.
+ */
+static void write_dscr(void *val)
+{
+	get_paca()->dscr_default = *(unsigned long *)val;
+	if (!current->thread.dscr_inherit) {
+		current->thread.dscr = *(unsigned long *)val;
+		mtspr(SPRN_DSCR, *(unsigned long *)val);
+	}
+}
+
+SYSFS_SPRSETUP_SHOW_STORE(dscr);
+static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr);
+
+static void add_write_permission_dev_attr(struct device_attribute *attr)
+{
+	attr->attr.mode |= 0200;
+}
+
+/**
+ * show_dscr_default() - Fetch the system wide DSCR default
+ * @dev:	Device structure
+ * @attr:	Device attribute structure
+ * @buf:	Interface buffer
+ *
+ * This function returns the system wide DSCR default value.
+ */
+static ssize_t show_dscr_default(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%lx\n", dscr_default);
+}
+
+/**
+ * store_dscr_default() - Update the system wide DSCR default
+ * @dev:	Device structure
+ * @attr:	Device attribute structure
+ * @buf:	Interface buffer
+ * @count:	Size of the update
+ *
+ * This function updates the system wide DSCR default value.
+ */
+static ssize_t __used store_dscr_default(struct device *dev,
+		struct device_attribute *attr, const char *buf,
+		size_t count)
+{
+	unsigned long val;
+	int ret = 0;
+
+	ret = sscanf(buf, "%lx", &val);
+	if (ret != 1)
+		return -EINVAL;
+	dscr_default = val;
+
+	on_each_cpu(write_dscr, &val, 1);
+
+	return count;
+}
+
+static DEVICE_ATTR(dscr_default, 0600,
+		show_dscr_default, store_dscr_default);
+
+static void sysfs_create_dscr_default(void)
+{
+	if (cpu_has_feature(CPU_FTR_DSCR)) {
+		int err = 0;
+		int cpu;
+
+		dscr_default = spr_default_dscr;
+		for_each_possible_cpu(cpu)
+			paca_ptrs[cpu]->dscr_default = dscr_default;
+
+		err = device_create_file(cpu_subsys.dev_root, &dev_attr_dscr_default);
+	}
+}
+#endif /* CONFIG_PPC64 */
+
 #ifdef CONFIG_PPC_FSL_BOOK3E
 #define MAX_BIT				63
 
···
 }
 EXPORT_SYMBOL(ppc_enable_pmcs);
 
-#define __SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, EXTRA) \
-static void read_##NAME(void *val) \
-{ \
-	*(unsigned long *)val = mfspr(ADDRESS);	\
-} \
-static void write_##NAME(void *val) \
-{ \
-	EXTRA; \
-	mtspr(ADDRESS, *(unsigned long *)val);	\
-}
 
-#define __SYSFS_SPRSETUP_SHOW_STORE(NAME) \
-static ssize_t show_##NAME(struct device *dev, \
-			struct device_attribute *attr, \
-			char *buf) \
-{ \
-	struct cpu *cpu = container_of(dev, struct cpu, dev); \
-	unsigned long val; \
-	smp_call_function_single(cpu->dev.id, read_##NAME, &val, 1);	\
-	return sprintf(buf, "%lx\n", val); \
-} \
-static ssize_t __used \
-	store_##NAME(struct device *dev, struct device_attribute *attr, \
-			const char *buf, size_t count) \
-{ \
-	struct cpu *cpu = container_of(dev, struct cpu, dev); \
-	unsigned long val; \
-	int ret = sscanf(buf, "%lx", &val); \
-	if (ret != 1) \
-		return -EINVAL; \
-	smp_call_function_single(cpu->dev.id, write_##NAME, &val, 1); \
-	return count; \
-}
-
-#define SYSFS_PMCSETUP(NAME, ADDRESS) \
-	__SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, ppc_enable_pmcs()) \
-	__SYSFS_SPRSETUP_SHOW_STORE(NAME)
-#define SYSFS_SPRSETUP(NAME, ADDRESS) \
-	__SYSFS_SPRSETUP_READ_WRITE(NAME, ADDRESS, ) \
-	__SYSFS_SPRSETUP_SHOW_STORE(NAME)
-
-#define SYSFS_SPRSETUP_SHOW_STORE(NAME) \
-	__SYSFS_SPRSETUP_SHOW_STORE(NAME)
 
 /* Let's define all possible registers, we'll only hook up the ones
  * that are implemented on the current processor
  */
 
-#if defined(CONFIG_PPC64)
+#ifdef CONFIG_PMU_SYSFS
+#if defined(CONFIG_PPC64) || defined(CONFIG_PPC_BOOK3S_32)
 #define HAS_PPC_PMC_CLASSIC	1
 #define HAS_PPC_PMC_IBM		1
-#define HAS_PPC_PMC_PA6T	1
-#elif defined(CONFIG_PPC_BOOK3S_32)
-#define HAS_PPC_PMC_CLASSIC	1
-#define HAS_PPC_PMC_IBM		1
-#define HAS_PPC_PMC_G4		1
-#endif
-
-
-#ifdef HAS_PPC_PMC_CLASSIC
-SYSFS_PMCSETUP(mmcr0, SPRN_MMCR0);
-SYSFS_PMCSETUP(mmcr1, SPRN_MMCR1);
-SYSFS_PMCSETUP(pmc1, SPRN_PMC1);
-SYSFS_PMCSETUP(pmc2, SPRN_PMC2);
-SYSFS_PMCSETUP(pmc3, SPRN_PMC3);
-SYSFS_PMCSETUP(pmc4, SPRN_PMC4);
-SYSFS_PMCSETUP(pmc5, SPRN_PMC5);
-SYSFS_PMCSETUP(pmc6, SPRN_PMC6);
-
-#ifdef HAS_PPC_PMC_G4
-SYSFS_PMCSETUP(mmcr2, SPRN_MMCR2);
 #endif
 
 #ifdef CONFIG_PPC64
-SYSFS_PMCSETUP(pmc7, SPRN_PMC7);
-SYSFS_PMCSETUP(pmc8, SPRN_PMC8);
+#define HAS_PPC_PMC_PA6T	1
+#define HAS_PPC_PMC56          1
+#endif
 
-SYSFS_PMCSETUP(mmcra, SPRN_MMCRA);
+#ifdef CONFIG_PPC_BOOK3S_32
+#define HAS_PPC_PMC_G4		1
+#endif
+#endif /* CONFIG_PMU_SYSFS */
+
+#if defined(CONFIG_PPC64) && defined(CONFIG_DEBUG_MISC)
+#define HAS_PPC_PA6T
+#endif
+/*
+ * SPRs which are not related to PMU.
+ */
+#ifdef CONFIG_PPC64
 SYSFS_SPRSETUP(purr, SPRN_PURR);
 SYSFS_SPRSETUP(spurr, SPRN_SPURR);
 SYSFS_SPRSETUP(pir, SPRN_PIR);
···
   enable write when needed with a separate function.
   Lets be conservative and default to pseries.
 */
-static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
 static DEVICE_ATTR(spurr, 0400, show_spurr, NULL);
 static DEVICE_ATTR(purr, 0400, show_purr, store_purr);
 static DEVICE_ATTR(pir, 0400, show_pir, NULL);
 static DEVICE_ATTR(tscr, 0600, show_tscr, store_tscr);
-
-/*
- * This is the system wide DSCR register default value. Any
- * change to this default value through the sysfs interface
- * will update all per cpu DSCR default values across the
- * system stored in their respective PACA structures.
- */
-static unsigned long dscr_default;
-
-/**
- * read_dscr() - Fetch the cpu specific DSCR default
- * @val:	Returned cpu specific DSCR default value
- *
- * This function returns the per cpu DSCR default value
- * for any cpu which is contained in it's PACA structure.
- */
-static void read_dscr(void *val)
-{
-	*(unsigned long *)val = get_paca()->dscr_default;
-}
-
-
-/**
- * write_dscr() - Update the cpu specific DSCR default
- * @val:	New cpu specific DSCR default value to update
- *
- * This function updates the per cpu DSCR default value
- * for any cpu which is contained in it's PACA structure.
- */
-static void write_dscr(void *val)
-{
-	get_paca()->dscr_default = *(unsigned long *)val;
-	if (!current->thread.dscr_inherit) {
-		current->thread.dscr = *(unsigned long *)val;
-		mtspr(SPRN_DSCR, *(unsigned long *)val);
-	}
-}
-
-SYSFS_SPRSETUP_SHOW_STORE(dscr);
-static DEVICE_ATTR(dscr, 0600, show_dscr, store_dscr);
-
-static void add_write_permission_dev_attr(struct device_attribute *attr)
-{
-	attr->attr.mode |= 0200;
-}
-
-/**
- * show_dscr_default() - Fetch the system wide DSCR default
- * @dev:	Device structure
- * @attr:	Device attribute structure
- * @buf:	Interface buffer
- *
- * This function returns the system wide DSCR default value.
- */
-static ssize_t show_dscr_default(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	return sprintf(buf, "%lx\n", dscr_default);
-}
-
-/**
- * store_dscr_default() - Update the system wide DSCR default
- * @dev:	Device structure
- * @attr:	Device attribute structure
- * @buf:	Interface buffer
- * @count:	Size of the update
- *
- * This function updates the system wide DSCR default value.
- */
-static ssize_t __used store_dscr_default(struct device *dev,
-		struct device_attribute *attr, const char *buf,
-		size_t count)
-{
-	unsigned long val;
-	int ret = 0;
-	
-	ret = sscanf(buf, "%lx", &val);
-	if (ret != 1)
-		return -EINVAL;
-	dscr_default = val;
-
-	on_each_cpu(write_dscr, &val, 1);
-
-	return count;
-}
-
-static DEVICE_ATTR(dscr_default, 0600,
-		show_dscr_default, store_dscr_default);
-
-static void sysfs_create_dscr_default(void)
-{
-	if (cpu_has_feature(CPU_FTR_DSCR)) {
-		int err = 0;
-		int cpu;
-
-		dscr_default = spr_default_dscr;
-		for_each_possible_cpu(cpu)
-			paca_ptrs[cpu]->dscr_default = dscr_default;
-
-		err = device_create_file(cpu_subsys.dev_root, &dev_attr_dscr_default);
-	}
-}
-
 #endif /* CONFIG_PPC64 */
+
+#ifdef HAS_PPC_PMC_CLASSIC
+SYSFS_PMCSETUP(mmcr0, SPRN_MMCR0);
+SYSFS_PMCSETUP(mmcr1, SPRN_MMCR1);
+SYSFS_PMCSETUP(pmc1, SPRN_PMC1);
+SYSFS_PMCSETUP(pmc2, SPRN_PMC2);
+SYSFS_PMCSETUP(pmc3, SPRN_PMC3);
+SYSFS_PMCSETUP(pmc4, SPRN_PMC4);
+SYSFS_PMCSETUP(pmc5, SPRN_PMC5);
+SYSFS_PMCSETUP(pmc6, SPRN_PMC6);
+#endif
+
+#ifdef HAS_PPC_PMC_G4
+SYSFS_PMCSETUP(mmcr2, SPRN_MMCR2);
+#endif
+
+#ifdef HAS_PPC_PMC56
+SYSFS_PMCSETUP(pmc7, SPRN_PMC7);
+SYSFS_PMCSETUP(pmc8, SPRN_PMC8);
+
+SYSFS_PMCSETUP(mmcra, SPRN_MMCRA);
+
+static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
+#endif /* HAS_PPC_PMC56 */
+
+
+
 
 #ifdef HAS_PPC_PMC_PA6T
 SYSFS_PMCSETUP(pa6t_pmc0, SPRN_PA6T_PMC0);
···
 SYSFS_PMCSETUP(pa6t_pmc3, SPRN_PA6T_PMC3);
 SYSFS_PMCSETUP(pa6t_pmc4, SPRN_PA6T_PMC4);
 SYSFS_PMCSETUP(pa6t_pmc5, SPRN_PA6T_PMC5);
-#ifdef CONFIG_DEBUG_MISC
+#endif
+
+#ifdef HAS_PPC_PA6T
 SYSFS_SPRSETUP(hid0, SPRN_HID0);
 SYSFS_SPRSETUP(hid1, SPRN_HID1);
 SYSFS_SPRSETUP(hid4, SPRN_HID4);
···
 SYSFS_SPRSETUP(tsr1, SPRN_PA6T_TSR1);
 SYSFS_SPRSETUP(tsr2, SPRN_PA6T_TSR2);
 SYSFS_SPRSETUP(tsr3, SPRN_PA6T_TSR3);
-#endif /* CONFIG_DEBUG_MISC */
-#endif /* HAS_PPC_PMC_PA6T */
+#endif /* HAS_PPC_PA6T */
 
 #ifdef HAS_PPC_PMC_IBM
 static struct device_attribute ibm_common_attrs[] = {
 	__ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0),
 	__ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1),
 };
-#endif /* HAS_PPC_PMC_G4 */
+#endif /* HAS_PPC_PMC_IBM */
 
 #ifdef HAS_PPC_PMC_G4
 static struct device_attribute g4_common_attrs[] = {
···
 };
 #endif /* HAS_PPC_PMC_G4 */
 
+#ifdef HAS_PPC_PMC_CLASSIC
 static struct device_attribute classic_pmc_attrs[] = {
 	__ATTR(pmc1, 0600, show_pmc1, store_pmc1),
 	__ATTR(pmc2, 0600, show_pmc2, store_pmc2),
···
 	__ATTR(pmc4, 0600, show_pmc4, store_pmc4),
 	__ATTR(pmc5, 0600, show_pmc5, store_pmc5),
 	__ATTR(pmc6, 0600, show_pmc6, store_pmc6),
-#ifdef CONFIG_PPC64
+#ifdef HAS_PPC_PMC56
 	__ATTR(pmc7, 0600, show_pmc7, store_pmc7),
 	__ATTR(pmc8, 0600, show_pmc8, store_pmc8),
 #endif
 };
+#endif
 
-#ifdef HAS_PPC_PMC_PA6T
+#if defined(HAS_PPC_PMC_PA6T) || defined(HAS_PPC_PA6T)
 static struct device_attribute pa6t_attrs[] = {
+#ifdef HAS_PPC_PMC_PA6T
 	__ATTR(mmcr0, 0600, show_mmcr0, store_mmcr0),
 	__ATTR(mmcr1, 0600, show_mmcr1, store_mmcr1),
 	__ATTR(pmc0, 0600, show_pa6t_pmc0, store_pa6t_pmc0),
···
 	__ATTR(pmc3, 0600, show_pa6t_pmc3, store_pa6t_pmc3),
 	__ATTR(pmc4, 0600, show_pa6t_pmc4, store_pa6t_pmc4),
 	__ATTR(pmc5, 0600, show_pa6t_pmc5, store_pa6t_pmc5),
-#ifdef CONFIG_DEBUG_MISC
+#endif
+#ifdef HAS_PPC_PA6T
 	__ATTR(hid0, 0600, show_hid0, store_hid0),
 	__ATTR(hid1, 0600, show_hid1, store_hid1),
 	__ATTR(hid4, 0600, show_hid4, store_hid4),
···
 	__ATTR(tsr1, 0600, show_tsr1, store_tsr1),
 	__ATTR(tsr2, 0600, show_tsr2, store_tsr2),
 	__ATTR(tsr3, 0600, show_tsr3, store_tsr3),
-#endif /* CONFIG_DEBUG_MISC */
+#endif /* HAS_PPC_PA6T */
 };
-#endif /* HAS_PPC_PMC_PA6T */
-#endif /* HAS_PPC_PMC_CLASSIC */
+#endif
 
 #ifdef CONFIG_PPC_SVM
 static ssize_t show_svm(struct device *dev, struct device_attribute *attr, char *buf)
···
 		pmc_attrs = classic_pmc_attrs;
 		break;
 #endif /* HAS_PPC_PMC_G4 */
-#ifdef HAS_PPC_PMC_PA6T
+#if defined(HAS_PPC_PMC_PA6T) || defined(HAS_PPC_PA6T)
 	case PPC_PMC_PA6T:
 		/* PA Semi starts counting at PMC0 */
 		attrs = pa6t_attrs;
 		nattrs = sizeof(pa6t_attrs) / sizeof(struct device_attribute);
 		pmc_attrs = NULL;
 		break;
-#endif /* HAS_PPC_PMC_PA6T */
+#endif
 	default:
 		attrs = NULL;
 		nattrs = 0;
···
 			device_create_file(s, &pmc_attrs[i]);
 
 #ifdef CONFIG_PPC64
+#ifdef	CONFIG_PMU_SYSFS
 	if (cpu_has_feature(CPU_FTR_MMCRA))
 		device_create_file(s, &dev_attr_mmcra);
+#endif /* CONFIG_PMU_SYSFS */
 
 	if (cpu_has_feature(CPU_FTR_PURR)) {
 		if (!firmware_has_feature(FW_FEATURE_LPAR))
···
 		pmc_attrs = classic_pmc_attrs;
 		break;
 #endif /* HAS_PPC_PMC_G4 */
-#ifdef HAS_PPC_PMC_PA6T
+#if defined(HAS_PPC_PMC_PA6T) || defined(HAS_PPC_PA6T)
 	case PPC_PMC_PA6T:
 		/* PA Semi starts counting at PMC0 */
 		attrs = pa6t_attrs;
 		nattrs = sizeof(pa6t_attrs) / sizeof(struct device_attribute);
 		pmc_attrs = NULL;
 		break;
-#endif /* HAS_PPC_PMC_PA6T */
+#endif
 	default:
 		attrs = NULL;
 		nattrs = 0;
···
 			device_remove_file(s, &pmc_attrs[i]);
 
 #ifdef CONFIG_PPC64
+#ifdef CONFIG_PMU_SYSFS
 	if (cpu_has_feature(CPU_FTR_MMCRA))
 		device_remove_file(s, &dev_attr_mmcra);
+#endif /* CONFIG_PMU_SYSFS */
 
 	if (cpu_has_feature(CPU_FTR_PURR))
 		device_remove_file(s, &dev_attr_purr);

arch/powerpc/kernel/systbl.S

···
 
 #ifdef CONFIG_PPC64
 	.p2align	3
+#define __SYSCALL(nr, entry)	.8byte entry
+#else
+#define __SYSCALL(nr, entry)	.long entry
 #endif
 
 .globl sys_call_table
 sys_call_table:
 #ifdef CONFIG_PPC64
-#define __SYSCALL(nr, entry)	.8byte DOTSYM(entry)
 #include <asm/syscall_table_64.h>
-#undef __SYSCALL
 #else
-#define __SYSCALL(nr, entry)	.long entry
 #include <asm/syscall_table_32.h>
-#undef __SYSCALL
 #endif
 
 #ifdef CONFIG_COMPAT
 .globl compat_sys_call_table
 compat_sys_call_table:
 #define compat_sys_sigsuspend	sys_sigsuspend
-#define __SYSCALL(nr, entry)	.8byte DOTSYM(entry)
 #include <asm/syscall_table_c32.h>
-#undef __SYSCALL
 #endif

arch/powerpc/kernel/time.c

···
 }
 #endif
 
-/*
- * Hypervisor decrementer interrupts shouldn't occur but are sometimes
- * left pending on exit from a KVM guest.  We don't need to do anything
- * to clear them, as they are edge-triggered.
- */
-void hdec_interrupt(struct pt_regs *regs)
-{
-}
-
 #ifdef CONFIG_SUSPEND
 static void generic_suspend_disable_irqs(void)
 {

arch/powerpc/kernel/traps.c

···
 
 static int __init ppc_warn_emulated_init(void)
 {
-	struct dentry *dir, *d;
+	struct dentry *dir;
 	unsigned int i;
 	struct ppc_emulated_entry *entries = (void *)&ppc_emulated;
 
-	if (!powerpc_debugfs_root)
-		return -ENODEV;
-
 	dir = debugfs_create_dir("emulated_instructions",
 				 powerpc_debugfs_root);
-	if (!dir)
-		return -ENOMEM;
 
-	d = debugfs_create_u32("do_warn", 0644, dir,
-			       &ppc_warn_emulated);
-	if (!d)
-		goto fail;
+	debugfs_create_u32("do_warn", 0644, dir, &ppc_warn_emulated);
 
-	for (i = 0; i < sizeof(ppc_emulated)/sizeof(*entries); i++) {
-		d = debugfs_create_u32(entries[i].name, 0644, dir,
-				       (u32 *)&entries[i].val.counter);
-		if (!d)
-			goto fail;
-	}
+	for (i = 0; i < sizeof(ppc_emulated)/sizeof(*entries); i++)
+		debugfs_create_u32(entries[i].name, 0644, dir,
+				   (u32 *)&entries[i].val.counter);
 
 	return 0;
-
-fail:
-	debugfs_remove_recursive(dir);
-	return -ENOMEM;
 }
 
 device_initcall(ppc_warn_emulated_init);

arch/powerpc/kernel/vdso.c

···
 		       symname);
 		return 0;
 	}
-#ifdef VDS64_HAS_DESCRIPTORS
-	return *((u64 *)(vdso64_kbase + sym->st_value - VDSO64_LBASE)) -
-		VDSO64_LBASE;
-#else
 	return sym->st_value - VDSO64_LBASE;
-#endif
 }
 
 static int __init vdso_do_func_patch64(struct lib32_elfinfo *v32,

arch/powerpc/kernel/vector.S

···
 	/* enable use of VSX after return */
 	oris	r12,r12,MSR_VSX@h
 	std	r12,_MSR(r1)
-	b	fast_exception_return
+	b	fast_interrupt_return
 
 #endif /* CONFIG_VSX */
 

arch/powerpc/kernel/vmlinux.lds.S

···
 		*(.dynamic)
 	}
 	.hash : AT(ADDR(.hash) - LOAD_OFFSET) { *(.hash) }
+	.gnu.hash : AT(ADDR(.gnu.hash) - LOAD_OFFSET) { *(.gnu.hash) }
 	.interp : AT(ADDR(.interp) - LOAD_OFFSET) { *(.interp) }
 	.rela.dyn : AT(ADDR(.rela.dyn) - LOAD_OFFSET)
 	{

arch/powerpc/kexec/Makefile

···
 # Makefile for the linux kernel.
 #
 
-# Avoid clang warnings around longjmp/setjmp declarations
-CFLAGS_crash.o += -ffreestanding
-
 obj-y				+= core.o crash.o core_$(BITS).o
 
 obj-$(CONFIG_PPC32)		+= relocate_32.o

arch/powerpc/kvm/book3s_64_mmu_hv.c

···
 
 void kvmppc_mmu_debugfs_init(struct kvm *kvm)
 {
-	kvm->arch.htab_dentry = debugfs_create_file("htab", 0400,
-						    kvm->arch.debugfs_dir, kvm,
-						    &debugfs_htab_fops);
+	debugfs_create_file("htab", 0400, kvm->arch.debugfs_dir, kvm,
+			    &debugfs_htab_fops);
 }
 
 void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu)

arch/powerpc/kvm/book3s_64_mmu_radix.c

···
 
 void kvmhv_radix_debugfs_init(struct kvm *kvm)
 {
-	kvm->arch.radix_dentry = debugfs_create_file("radix", 0400,
-						     kvm->arch.debugfs_dir, kvm,
-						     &debugfs_radix_fops);
+	debugfs_create_file("radix", 0400, kvm->arch.debugfs_dir, kvm,
+			    &debugfs_radix_fops);
 }
 
 int kvmppc_radix_init(void)

arch/powerpc/kvm/book3s_hv.c

···
 	struct kvm *kvm = vcpu->kvm;
 
 	snprintf(buf, sizeof(buf), "vcpu%u", id);
-	if (IS_ERR_OR_NULL(kvm->arch.debugfs_dir))
-		return;
 	vcpu->arch.debugfs_dir = debugfs_create_dir(buf, kvm->arch.debugfs_dir);
-	if (IS_ERR_OR_NULL(vcpu->arch.debugfs_dir))
-		return;
-	vcpu->arch.debugfs_timings =
-		debugfs_create_file("timings", 0444, vcpu->arch.debugfs_dir,
-				    vcpu, &debugfs_timings_ops);
+	debugfs_create_file("timings", 0444, vcpu->arch.debugfs_dir, vcpu,
+			    &debugfs_timings_ops);
 }
 
 #else /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */

arch/powerpc/kvm/book3s_hv_rmhandlers.S

···
 	 * R12		= (guest CR << 32) | interrupt vector
 	 * R13		= PACA
 	 * guest R12 saved in shadow VCPU SCRATCH0
-	 * guest CTR saved in shadow VCPU SCRATCH1 if RELOCATABLE
 	 * guest R13 saved in SPRN_SCRATCH0
 	 */
 	std	r9, HSTATE_SCRATCH2(r13)
···
 11:	stw	r3,VCPU_HEIR(r9)
 
 	/* these are volatile across C function calls */
-#ifdef CONFIG_RELOCATABLE
-	ld	r3, HSTATE_SCRATCH1(r13)
-	mtctr	r3
-#else
 	mfctr	r3
-#endif
 	mfxer	r4
 	std	r3, VCPU_CTR(r9)
 	std	r4, VCPU_XER(r9)
···
  * r12 is (CR << 32) | vector
  * r13 points to our PACA
  * r12 is saved in HSTATE_SCRATCH0(r13)
- * ctr is saved in HSTATE_SCRATCH1(r13) if RELOCATABLE
  * r9 is saved in HSTATE_SCRATCH2(r13)
  * r13 is saved in HSPRG1
  * cfar is saved in HSTATE_CFAR(r13)
···
 	ld	r5, HSTATE_CFAR(r13)
 	std	r5, ORIG_GPR3(r1)
 	mflr	r3
-#ifdef CONFIG_RELOCATABLE
-	ld	r4, HSTATE_SCRATCH1(r13)
-#else
 	mfctr	r4
-#endif
 	mfxer	r5
 	lbz	r6, PACAIRQSOFTMASK(r13)
 	std	r3, _LINK(r1)

arch/powerpc/kvm/book3s_segment.S

···
 	 * R12             = (guest CR << 32) | exit handler id
 	 * R13             = PACA
 	 * HSTATE.SCRATCH0 = guest R12
-	 * HSTATE.SCRATCH1 = guest CTR if RELOCATABLE
 	 */
 #ifdef CONFIG_PPC64
 	/* Match 32-bit entry */
-#ifdef CONFIG_RELOCATABLE
-	std	r9, HSTATE_SCRATCH2(r13)
-	ld	r9, HSTATE_SCRATCH1(r13)
-	mtctr	r9
-	ld	r9, HSTATE_SCRATCH2(r13)
-#endif
 	rotldi	r12, r12, 32		  /* Flip R12 halves for stw */
 	stw	r12, HSTATE_SCRATCH1(r13) /* CR is now in the low half */
 	srdi	r12, r12, 32		  /* shift trap into low half */

arch/powerpc/kvm/timing.c

···
 
 	snprintf(dbg_fname, sizeof(dbg_fname), "vm%u_vcpu%u_timing",
 		 current->pid, id);
-	debugfs_file = debugfs_create_file(dbg_fname, 0666,
-					kvm_debugfs_dir, vcpu,
-					&kvmppc_exit_timing_fops);
-
-	if (!debugfs_file) {
-		printk(KERN_ERR"%s: error creating debugfs file %s\n",
-			__func__, dbg_fname);
-		return;
-	}
+	debugfs_file = debugfs_create_file(dbg_fname, 0666, kvm_debugfs_dir,
+						vcpu, &kvmppc_exit_timing_fops);
 
 	vcpu->arch.debugfs_exit_timing = debugfs_file;
 }
 
 void kvmppc_remove_vcpu_debugfs(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->arch.debugfs_exit_timing) {
-		debugfs_remove(vcpu->arch.debugfs_exit_timing);
-		vcpu->arch.debugfs_exit_timing = NULL;
-	}
+	debugfs_remove(vcpu->arch.debugfs_exit_timing);
+	vcpu->arch.debugfs_exit_timing = NULL;
 }

arch/powerpc/lib/sstep.c

···
 		 * entry code works.  If that is changed, this will
 		 * need to be changed also.
 		 */
-		if (regs->gpr[0] == 0x1ebe &&
-		    cpu_has_feature(CPU_FTR_REAL_LE)) {
+		if (IS_ENABLED(CONFIG_PPC_FAST_ENDIAN_SWITCH) &&
+				cpu_has_feature(CPU_FTR_REAL_LE) &&
+				regs->gpr[0] == 0x1ebe) {
 			regs->msr ^= MSR_LE;
 			goto instr_done;
 		}

arch/powerpc/lib/test_emulate_step.c

···
 #include <asm/code-patching.h>
 
 #define IMM_L(i)		((uintptr_t)(i) & 0xffff)
+#define IMM_DS(i)		((uintptr_t)(i) & 0xfffc)
 
 /*
  * Defined with TEST_ prefix so it does not conflict with other
  * definitions.
  */
 #define TEST_LD(r, base, i)	(PPC_INST_LD | ___PPC_RT(r) |		\
-					___PPC_RA(base) | IMM_L(i))
+					___PPC_RA(base) | IMM_DS(i))
 #define TEST_LWZ(r, base, i)	(PPC_INST_LWZ | ___PPC_RT(r) |		\
 					___PPC_RA(base) | IMM_L(i))
 #define TEST_LWZX(t, a, b)	(PPC_INST_LWZX | ___PPC_RT(t) |		\
 					___PPC_RA(a) | ___PPC_RB(b))
 #define TEST_STD(r, base, i)	(PPC_INST_STD | ___PPC_RS(r) |		\
-					___PPC_RA(base) | ((i) & 0xfffc))
+					___PPC_RA(base) | IMM_DS(i))
 #define TEST_LDARX(t, a, b, eh)	(PPC_INST_LDARX | ___PPC_RT(t) |	\
 					___PPC_RA(a) | ___PPC_RB(b) |	\
 					__PPC_EH(eh))
···
 
 	/* std r5, 0(r3) */
 	stepped = emulate_step(&regs, TEST_STD(5, 3, 0));
-	if (stepped == 1 || regs.gpr[5] == a)
+	if (stepped == 1 && regs.gpr[5] == a)
 		show_result("std", "PASS");
 	else
 		show_result("std", "FAIL");

arch/powerpc/mm/book3s32/hash_low.S

···
 /*
  * Load a PTE into the hash table, if possible.
  * The address is in r4, and r3 contains an access flag:
- * _PAGE_RW (0x400) if a write.
+ * _PAGE_RW (0x002) if a write.
  * r9 contains the SRR1 value, from which we use the MSR_PR bit.
  * SPRG_THREAD contains the physical address of the current task's thread.
  *
···
 	blt+	112f			/* assume user more likely */
 	lis	r5, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
 	addi	r5 ,r5 ,(swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
-	rlwimi	r3,r9,32-12,29,29	/* MSR_PR -> _PAGE_USER */
+	rlwimi	r3,r9,32-14,31,31	/* MSR_PR -> _PAGE_USER */
 112:
 #ifndef CONFIG_PTE_64BIT
 	rlwimi	r5,r4,12,20,29		/* insert top 10 bits of address */
···
 #else
 	rlwimi	r8,r4,23,20,28		/* compute pte address */
 #endif
-	rlwinm	r0,r3,32-3,24,24	/* _PAGE_RW access -> _PAGE_DIRTY */
+	rlwinm	r0,r3,6,24,24		/* _PAGE_RW access -> _PAGE_DIRTY */
 	ori	r0,r0,_PAGE_ACCESSED|_PAGE_HASHPTE
 
 	/*
···
 
 _GLOBAL(create_hpte)
 	/* Convert linux-style PTE (r5) to low word of PPC-style PTE (r8) */
-	rlwinm	r8,r5,32-9,30,30	/* _PAGE_RW -> PP msb */
 	rlwinm	r0,r5,32-6,30,30	/* _PAGE_DIRTY -> PP msb */
-	and	r8,r8,r0		/* writable if _RW & _DIRTY */
-	rlwimi	r5,r5,32-1,30,30	/* _PAGE_USER -> PP msb */
-	rlwimi	r5,r5,32-2,31,31	/* _PAGE_USER -> PP lsb */
+	and	r8,r5,r0		/* writable if _RW & _DIRTY */
+	rlwimi	r5,r5,1,30,30		/* _PAGE_USER -> PP msb */
 	ori	r8,r8,0xe04		/* clear out reserved bits */
 	andc	r8,r5,r8		/* PP = user? (rw&dirty? 1: 3): 0 */
 BEGIN_FTR_SECTION
···
 33:	lwarx	r8,0,r5			/* fetch the pte flags word */
 	andi.	r0,r8,_PAGE_HASHPTE
 	beq	8f			/* done if HASHPTE is already clear */
-	rlwinm	r8,r8,0,31,29		/* clear HASHPTE bit */
+	rlwinm	r8,r8,0,~_PAGE_HASHPTE	/* clear HASHPTE bit */
 	stwcx.	r8,0,r5			/* update the pte */
 	bne-	33b
 
···
 	bne-	10b
 	stwcx.	r8,0,r9
 	bne-	10b
+#endif /* CONFIG_SMP */
+	li	r5, 32
+	lis	r4, KERNELBASE@h
+	mtctr	r5
 	sync
-	tlbia
+0:	tlbie	r4
+	addi	r4, r4, 0x1000
+	bdnz	0b
 	sync
+#ifdef CONFIG_SMP
 	TLBSYNC
 	li	r0,0
 	stw	r0,0(r9)		/* clear mmu_hash_lock */
 	mtmsr	r10
 	SYNC_601
 	isync
-#else /* CONFIG_SMP */
-	sync
-	tlbia
-	sync
 #endif /* CONFIG_SMP */
 	blr

arch/powerpc/mm/book3s32/mmu.c

···
 
 	if (!Hash)
 		return;
-	pmd = pmd_offset(pud_offset(pgd_offset(mm, ea), ea), ea);
+	pmd = pmd_ptr(mm, ea);
 	if (!pmd_none(*pmd))
 		add_hash_page(mm->context.id, ea, pmd_val(*pmd));
 }

arch/powerpc/mm/book3s32/tlb.c

···
 	int count;
 	unsigned int ctx = mm->context.id;
 
+	start &= PAGE_MASK;
 	if (!Hash) {
-		_tlbia();
+		if (end - start <= PAGE_SIZE)
+			_tlbie(start);
+		else
+			_tlbia();
 		return;
 	}
-	start &= PAGE_MASK;
 	if (start >= end)
 		return;
 	end = (end - 1) | ~PAGE_MASK;
-	pmd = pmd_offset(pud_offset(pgd_offset(mm, start), start), start);
+	pmd = pmd_ptr(mm, start);
 	for (;;) {
 		pmd_end = ((start + PGDIR_SIZE) & PGDIR_MASK) - 1;
 		if (pmd_end > end)
···
 		return;
 	}
 	mm = (vmaddr < TASK_SIZE)? vma->vm_mm: &init_mm;
-	pmd = pmd_offset(pud_offset(pgd_offset(mm, vmaddr), vmaddr), vmaddr);
+	pmd = pmd_ptr(mm, vmaddr);
 	if (!pmd_none(*pmd))
 		flush_hash_pages(mm->context.id, vmaddr, pmd_val(*pmd), 1);
 }

arch/powerpc/mm/book3s64/hash_utils.c

···
 
 static int __init hash64_debugfs(void)
 {
-	if (!debugfs_create_file_unsafe("hpt_order", 0600, powerpc_debugfs_root,
-					NULL, &fops_hpt_order)) {
-		pr_err("lpar: unable to create hpt_order debugsfs file\n");
-	}
-
+	debugfs_create_file("hpt_order", 0600, powerpc_debugfs_root, NULL,
+			    &fops_hpt_order);
 	return 0;
 }
 machine_device_initcall(pseries, hash64_debugfs);

arch/powerpc/mm/book3s64/iommu_api.c

···
 		goto free_exit;
 	}
 
-	pageshift = PAGE_SHIFT;
-	for (i = 0; i < entries; ++i) {
-		struct page *page = mem->hpages[i];
-
-		/*
-		 * Allow to use larger than 64k IOMMU pages. Only do that
-		 * if we are backed by hugetlb.
-		 */
-		if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page))
-			pageshift = page_shift(compound_head(page));
-		mem->pageshift = min(mem->pageshift, pageshift);
-		/*
-		 * We don't need struct page reference any more, switch
-		 * to physical address.
-		 */
-		mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
-	}
-
 good_exit:
 	atomic64_set(&mem->mapped, 1);
 	mem->used = 1;
···
 			ret = -EINVAL;
 			mutex_unlock(&mem_list_mutex);
 			goto free_exit;
+		}
+	}
+
+	if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) {
+		/*
+		 * Allow to use larger than 64k IOMMU pages. Only do that
+		 * if we are backed by hugetlb. Skip device memory as it is not
+		 * backed with page structs.
+		 */
+		pageshift = PAGE_SHIFT;
+		for (i = 0; i < entries; ++i) {
+			struct page *page = mem->hpages[i];
+
+			if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page))
+				pageshift = page_shift(compound_head(page));
+			mem->pageshift = min(mem->pageshift, pageshift);
+			/*
+			 * We don't need struct page reference any more, switch
+			 * to physical address.
+			 */
+			mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
 		}
 	}
 

arch/powerpc/mm/book3s64/radix_pgtable.c

···
 #include <asm/firmware.h>
 #include <asm/powernv.h>
 #include <asm/sections.h>
+#include <asm/smp.h>
 #include <asm/trace.h>
 #include <asm/uaccess.h>
 #include <asm/ultravisor.h>

arch/powerpc/mm/book3s64/radix_tlb.c

···
 	preempt_enable();
 }
 EXPORT_SYMBOL(radix__local_flush_all_mm);
+
+static void __flush_all_mm(struct mm_struct *mm, bool fullmm)
+{
+	radix__local_flush_all_mm(mm);
+}
 #endif /* CONFIG_SMP */
 
 void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
···
 EXPORT_SYMBOL(radix__flush_tlb_page);
 
 #else /* CONFIG_SMP */
-#define radix__flush_all_mm radix__local_flush_all_mm
+static inline void exit_flush_lazy_tlbs(struct mm_struct *mm) { }
 #endif /* CONFIG_SMP */
 
 static void do_tlbiel_kernel(void *info)

arch/powerpc/mm/kasan/kasan_init_32.c

···
 	unsigned long k_cur, k_next;
 	pte_t *new = NULL;
 
-	pmd = pmd_offset(pud_offset(pgd_offset_k(k_start), k_start), k_start);
+	pmd = pmd_ptr_k(k_start);
 
 	for (k_cur = k_start; k_cur != k_end; k_cur = k_next, pmd++) {
 		k_next = pgd_addr_end(k_cur, k_end);
···
 	block = memblock_alloc(k_end - k_start, PAGE_SIZE);
 
 	for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) {
-		pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur);
+		pmd_t *pmd = pmd_ptr_k(k_cur);
 		void *va = block + k_cur - k_start;
 		pte_t pte = pfn_pte(PHYS_PFN(__pa(va)), PAGE_KERNEL);
 
···
 
 	kasan_populate_pte(kasan_early_shadow_pte, prot);
 
-	for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) {
-		pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur);
+	for (k_cur = k_start & PAGE_MASK; k_cur != k_end; k_cur += PAGE_SIZE) {
+		pmd_t *pmd = pmd_ptr_k(k_cur);
 		pte_t *ptep = pte_offset_kernel(pmd, k_cur);
 
 		if ((pte_val(*ptep) & PTE_RPN_MASK) != pa)
···
 	unsigned long addr = KASAN_SHADOW_START;
 	unsigned long end = KASAN_SHADOW_END;
 	unsigned long next;
-	pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(addr), addr), addr);
+	pmd_t *pmd = pmd_ptr_k(addr);
 
 	BUILD_BUG_ON(KASAN_SHADOW_START & ~PGDIR_MASK);
 

arch/powerpc/mm/mem.c

···
 EXPORT_SYMBOL(kmap_pte);
 pgprot_t kmap_prot;
 EXPORT_SYMBOL(kmap_prot);
-
-static inline pte_t *virt_to_kpte(unsigned long vaddr)
-{
-	return pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr),
-			vaddr), vaddr), vaddr);
-}
 #endif
 
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,

arch/powerpc/mm/nohash/40x.c

···
 		pmd_t *pmdp;
 		unsigned long val = p | _PMD_SIZE_16M | _PAGE_EXEC | _PAGE_HWWRITE;
 
-		pmdp = pmd_offset(pud_offset(pgd_offset_k(v), v), v);
+		pmdp = pmd_ptr_k(v);
 		*pmdp++ = __pmd(val);
 		*pmdp++ = __pmd(val);
 		*pmdp++ = __pmd(val);
···
 		pmd_t *pmdp;
 		unsigned long val = p | _PMD_SIZE_4M | _PAGE_EXEC | _PAGE_HWWRITE;
 
-		pmdp = pmd_offset(pud_offset(pgd_offset_k(v), v), v);
+		pmdp = pmd_ptr_k(v);
 		*pmdp = __pmd(val);
 
 		v += LARGE_PAGE_SIZE_4M;

arch/powerpc/mm/nohash/tlb_low.S

···
  * extern void loadcam_entry(unsigned int index)
  *
  * Load TLBCAM[index] entry in to the L2 CAM MMU
- * Must preserve r7, r8, r9, and r10
+ * Must preserve r7, r8, r9, r10 and r11
  */
 _GLOBAL(loadcam_entry)
 	mflr	r5
···
  */
 _GLOBAL(loadcam_multi)
 	mflr	r8
+	/* Don't switch to AS=1 if already there */
+	mfmsr	r11
+	andi.	r11,r11,MSR_IS
+	bne	10f
 
 	/*
 	 * Set up temporary TLB entry that is the same as what we're
···
 	mtmsr	r6
 	isync
 
+10:
 	mr	r9,r3
 	add	r10,r3,r4
 2:	bl	loadcam_entry
···
 	cmpw	r9,r10
 	mr	r3,r9
 	blt	2b
+
+	/* Don't return to AS=0 if we were in AS=1 at function start */
+	andi.	r11,r11,MSR_IS
+	bne	3f
 
 	/* Return to AS=0 and clear the temporary entry */
 	mfmsr	r6
···
 	tlbwe
 	isync
 
+3:
 	mtlr	r8
 	blr
 #endif

arch/powerpc/mm/numa.c

···
 	return nid;
 }
 
+#ifdef CONFIG_PPC_SPLPAR
+static int vphn_get_nid(long lcpu)
+{
+	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
+	long rc, hwid;
+
+	/*
+	 * On a shared lpar, device tree will not have node associativity.
+	 * At this time lppaca, or its __old_status field may not be
+	 * updated. Hence kernel cannot detect if its on a shared lpar. So
+	 * request an explicit associativity irrespective of whether the
+	 * lpar is shared or dedicated. Use the device tree property as a
+	 * fallback. cpu_to_phys_id is only valid between
+	 * smp_setup_cpu_maps() and smp_setup_pacas().
+	 */
+	if (firmware_has_feature(FW_FEATURE_VPHN)) {
+		if (cpu_to_phys_id)
+			hwid = cpu_to_phys_id[lcpu];
+		else
+			hwid = get_hard_smp_processor_id(lcpu);
+
+		rc = hcall_vphn(hwid, VPHN_FLAG_VCPU, associativity);
+		if (rc == H_SUCCESS)
+			return associativity_to_nid(associativity);
+	}
+
+	return NUMA_NO_NODE;
+}
+#else
+static int vphn_get_nid(long unused)
+{
+	return NUMA_NO_NODE;
+}
+#endif  /* CONFIG_PPC_SPLPAR */
+
 /*
  * Figure out to which domain a cpu belongs and stick it there.
  * Return the id of the domain used.
  */
 static int numa_setup_cpu(unsigned long lcpu)
 {
-	int nid = NUMA_NO_NODE;
 	struct device_node *cpu;
+	int fcpu = cpu_first_thread_sibling(lcpu);
+	int nid = NUMA_NO_NODE;
 
 	/*
 	 * If a valid cpu-to-node mapping is already available, use it
 	 * directly instead of querying the firmware, since it represents
 	 * the most recent mapping notified to us by the platform (eg: VPHN).
+	 * Since cpu_to_node binding remains the same for all threads in the
+	 * core. If a valid cpu-to-node mapping is already available, for
+	 * the first thread in the core, use it.
 	 */
-	if ((nid = numa_cpu_lookup_table[lcpu]) >= 0) {
+	nid = numa_cpu_lookup_table[fcpu];
+	if (nid >= 0) {
 		map_cpu_to_node(lcpu, nid);
 		return nid;
 	}
+
+	nid = vphn_get_nid(lcpu);
+	if (nid != NUMA_NO_NODE)
+		goto out_present;
 
 	cpu = of_get_cpu_node(lcpu, NULL);
 
···
 	}
 
 	nid = of_node_to_nid_single(cpu);
+	of_node_put(cpu);
 
 out_present:
 	if (nid < 0 || !node_possible(nid))
 		nid = first_online_node;
 
+	/*
+	 * Update for the first thread of the core. All threads of a core
+	 * have to be part of the same node. This not only avoids querying
+	 * for every other thread in the core, but always avoids a case
+	 * where virtual node associativity change causes subsequent threads
+	 * of a core to be associated with different nid. However if first
+	 * thread is already online, expect it to have a valid mapping.
+	 */
+	if (fcpu != lcpu) {
+		WARN_ON(cpu_online(fcpu));
+		map_cpu_to_node(fcpu, nid);
+	}
+
 	map_cpu_to_node(lcpu, nid);
-	of_node_put(cpu);
 out:
 	return nid;
 }
···
 				VPHN_FLAG_VCPU, associativity);
 
 	switch (rc) {
-	case H_FUNCTION:
-		printk_once(KERN_INFO
-			"VPHN is not supported. Disabling polling...\n");
-		stop_topology_update();
-		break;
-	case H_HARDWARE:
-		printk(KERN_ERR
-			"hcall_vphn() experienced a hardware fault "
-			"preventing VPHN. Disabling polling...\n");
-		stop_topology_update();
-		break;
 	case H_SUCCESS:
 		dbg("VPHN hcall succeeded. Reset polling...\n");
 		timed_topology_update(0);
+		goto out;
+
+	case H_FUNCTION:
+		pr_err_ratelimited("VPHN unsupported. Disabling polling...\n");
+		break;
+	case H_HARDWARE:
+		pr_err_ratelimited("hcall_vphn() experienced a hardware fault "
+			"preventing VPHN. Disabling polling...\n");
+		break;
+	case H_PARAMETER:
+		pr_err_ratelimited("hcall_vphn() was passed an invalid parameter. "
+			"Disabling polling...\n");
+		break;
+	default:
+		pr_err_ratelimited("hcall_vphn() returned %ld. Disabling polling...\n"
+			, rc);
 		break;
 	}
 
+	stop_topology_update();
+out:
 	return rc;
 }
 
···
 int prrn_is_enabled(void)
 {
 	return prrn_enabled;
-}
-
-void __init shared_proc_topology_init(void)
-{
-	if (lppaca_shared_proc(get_lppaca())) {
-		bitmap_fill(cpumask_bits(&cpu_associativity_changes_mask),
-			    nr_cpumask_bits);
-		numa_update_cpu_topology(false);
-	}
 }
 
 static int topology_read(struct seq_file *file, void *v)

arch/powerpc/mm/pgtable_32.c

···
 	int err = -ENOMEM;
 
 	/* Use upper 10 bits of VA to index the first level map */
-	pd = pmd_offset(pud_offset(pgd_offset_k(va), va), va);
+	pd = pmd_ptr_k(va);
 	/* Use middle 10 bits of VA to index the second-level map */
 	if (likely(slab_is_available()))
 		pg = pte_alloc_kernel(pd, va);
···
 	}
 }
 
-/* Scan the real Linux page tables and return a PTE pointer for
- * a virtual address in a context.
- * Returns true (1) if PTE was found, zero otherwise.  The pointer to
- * the PTE pointer is unmodified if PTE is not found.
- */
-static int
-get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep, pmd_t **pmdp)
-{
-        pgd_t	*pgd;
-	pud_t	*pud;
-        pmd_t	*pmd;
-        pte_t	*pte;
-        int     retval = 0;
-
-        pgd = pgd_offset(mm, addr & PAGE_MASK);
-        if (pgd) {
-		pud = pud_offset(pgd, addr & PAGE_MASK);
-		if (pud && pud_present(*pud)) {
-			pmd = pmd_offset(pud, addr & PAGE_MASK);
-			if (pmd_present(*pmd)) {
-				pte = pte_offset_map(pmd, addr & PAGE_MASK);
-				if (pte) {
-					retval = 1;
-					*ptep = pte;
-					if (pmdp)
-						*pmdp = pmd;
-					/* XXX caller needs to do pte_unmap, yuck */
-				}
-			}
-		}
-        }
-        return(retval);
-}
-
 static int __change_page_attr_noflush(struct page *page, pgprot_t prot)
 {
 	pte_t *kpte;
-	pmd_t *kpmd;
 	unsigned long address;
 
 	BUG_ON(PageHighMem(page));
···
 
 	if (v_block_mapped(address))
 		return 0;
-	if (!get_pteptr(&init_mm, address, &kpte, &kpmd))
+	kpte = virt_to_kpte(address);
+	if (!kpte)
 		return -EINVAL;
 	__set_pte_at(&init_mm, address, kpte, mk_pte(page, prot), 0);
-	pte_unmap(kpte);
 
 	return 0;
 }

arch/powerpc/mm/ptdump/bats.c

···
 
 static int __init bats_init(void)
 {
-	struct dentry *debugfs_file;
-
-	debugfs_file = debugfs_create_file("block_address_translation", 0400,
-					   powerpc_debugfs_root, NULL, &bats_fops);
-	return debugfs_file ? 0 : -ENOMEM;
+	debugfs_create_file("block_address_translation", 0400,
+			    powerpc_debugfs_root, NULL, &bats_fops);
+	return 0;
 }
 device_initcall(bats_init);

arch/powerpc/mm/ptdump/hashpagetable.c

···
 
 static int ptdump_init(void)
 {
-	struct dentry *debugfs_file;
-
 	if (!radix_enabled()) {
 		populate_markers();
-		debugfs_file = debugfs_create_file("kernel_hash_pagetable",
-				0400, NULL, NULL, &ptdump_fops);
-		return debugfs_file ? 0 : -ENOMEM;
+		debugfs_create_file("kernel_hash_pagetable", 0400, NULL, NULL,
+				    &ptdump_fops);
 	}
 	return 0;
 }

arch/powerpc/mm/ptdump/ptdump.c

···
 
 static int ptdump_init(void)
 {
-	struct dentry *debugfs_file;
-
 	populate_markers();
 	build_pgtable_complete_mask();
-	debugfs_file = debugfs_create_file("kernel_page_tables", 0400, NULL,
-			NULL, &ptdump_fops);
-	return debugfs_file ? 0 : -ENOMEM;
+	debugfs_create_file("kernel_page_tables", 0400, NULL, NULL,
+			    &ptdump_fops);
+	return 0;
 }
 device_initcall(ptdump_init);

arch/powerpc/mm/ptdump/segment_regs.c

···
 
 static int __init sr_init(void)
 {
-	struct dentry *debugfs_file;
-
-	debugfs_file = debugfs_create_file("segment_registers", 0400,
-					   powerpc_debugfs_root, NULL, &sr_fops);
-	return debugfs_file ? 0 : -ENOMEM;
+	debugfs_create_file("segment_registers", 0400, powerpc_debugfs_root,
+			    NULL, &sr_fops);
+	return 0;
 }
 device_initcall(sr_init);

arch/powerpc/platforms/44x/warp.c

···
 	if (!of_machine_is_compatible("pika,warp"))
 		return 0;
 
-	/* For arch_dma_alloc */
-	ISA_DMA_THRESHOLD = ~0L;
-
 	return 1;
 }
 

arch/powerpc/platforms/52xx/efika.c

···
 	if (strcmp(model, "EFIKA5K2"))
 		return 0;
 
-	ISA_DMA_THRESHOLD = ~0L;
 	DMA_MODE_READ = 0x44;
 	DMA_MODE_WRITE = 0x48;
 

arch/powerpc/platforms/83xx/km83xx.c

···
 
 	np_par = of_find_node_by_name(NULL, "par_io");
 	if (np_par == NULL) {
-		pr_warn("%s couldn;t find par_io node\n", __func__);
+		pr_warn("%s couldn't find par_io node\n", __func__);
 		return;
 	}
 	/* Map Parallel I/O ports registers */
 	ret = of_address_to_resource(np_par, 0, &res);
 	if (ret) {
-		pr_warn("%s couldn;t map par_io registers\n", __func__);
-		return;
+		pr_warn("%s couldn't map par_io registers\n", __func__);
+		goto out;
 	}
 
 	base = ioremap(res.start, resource_size(&res));
+	if (!base)
+		goto out;
 
 	/*
 	 * set output delay adjustments to default values according
···
 		setbits32((base + 0xac), 0x0000c000);
 	}
 	iounmap(base);
+out:
 	of_node_put(np_par);
 }
 

arch/powerpc/platforms/85xx/mpc85xx_cds.c

···
 {
 	return IRQ_HANDLED;
 }
-
-static struct irqaction mpc85xxcds_8259_irqaction = {
-	.handler = mpc85xx_8259_cascade_action,
-	.flags = IRQF_SHARED | IRQF_NO_THREAD,
-	.name = "8259 cascade",
-};
 #endif /* PPC_I8259 */
 #endif /* CONFIG_PCI */
 
···
 	 *  disabled when the last user of the shared IRQ line frees their
 	 *  interrupt.
 	 */
-	if ((ret = setup_irq(cascade_irq, &mpc85xxcds_8259_irqaction))) {
+	ret = request_irq(cascade_irq, mpc85xx_8259_cascade_action,
+			  IRQF_SHARED | IRQF_NO_THREAD, "8259 cascade",
+			  cascade_node);
+	if (ret) {
 		printk(KERN_ERR "Failed to setup cascade interrupt\n");
 		return ret;
 	}

arch/powerpc/platforms/8xx/cpm1.c

···
 	return IRQ_HANDLED;
 }
 
-static struct irqaction cpm_error_irqaction = {
-	.handler = cpm_error_interrupt,
-	.flags = IRQF_NO_THREAD,
-	.name = "error",
-};
-
 static const struct irq_domain_ops cpm_pic_host_ops = {
 	.map = cpm_pic_host_map,
 };
···
 	if (!eirq)
 		goto end;
 
-	if (setup_irq(eirq, &cpm_error_irqaction))
+	if (request_irq(eirq, cpm_error_interrupt, IRQF_NO_THREAD, "error",
+			NULL))
 		printk(KERN_ERR "Could not allocate CPM error IRQ!");
 
 	setbits32(&cpic_reg->cpic_cicr, CICR_IEN);

arch/powerpc/platforms/8xx/m8xx_setup.c

···
 	return IRQ_HANDLED;
 }
 
-static struct irqaction tbint_irqaction = {
-	.handler = timebase_interrupt,
-	.flags = IRQF_NO_THREAD,
-	.name = "tbint",
-};
-
 /* per-board overridable init_internal_rtc() function. */
 void __init __attribute__ ((weak))
 init_internal_rtc(void)
···
 					(TBSCR_TBF | TBSCR_TBE));
 	immr_unmap(sys_tmr2);
 
-	if (setup_irq(virq, &tbint_irqaction))
+	if (request_irq(virq, timebase_interrupt, IRQF_NO_THREAD, "tbint",
+			NULL))
 		panic("Could not allocate timer IRQ!");
 }
 

arch/powerpc/platforms/Kconfig.cputype

···
 
 config PPC_KUAP_DEBUG
 	bool "Extra debugging for Kernel Userspace Access Protection"
-	depends on PPC_HAVE_KUAP && (PPC_RADIX_MMU || PPC_32)
+	depends on PPC_KUAP && (PPC_RADIX_MMU || PPC_32)
 	help
 	  Add extra debugging for Kernel Userspace Access Protection (KUAP)
 	  If you're unsure, say N.
···
 
 config PPC_HAVE_PMU_SUPPORT
 	bool
+
+config PMU_SYSFS
+	bool "Create PMU SPRs sysfs file"
+	default n
+	help
+	  This option enables sysfs file creation for PMU SPRs like MMCR* and PMC*.
 
 config PPC_PERF_CTRS
 	def_bool y

arch/powerpc/platforms/amigaone/setup.c

···
 		 */
 		cur_cpu_spec->cpu_features &= ~CPU_FTR_NEED_COHERENT;
 
-		ISA_DMA_THRESHOLD = 0x00ffffff;
 		DMA_MODE_READ = 0x44;
 		DMA_MODE_WRITE = 0x48;
 

arch/powerpc/platforms/cell/axon_msi.c

···
 
 	snprintf(name, sizeof(name), "msic_%d", of_node_to_nid(dn));
 
-	if (!debugfs_create_file(name, 0600, powerpc_debugfs_root,
-				 msic, &fops_msic)) {
-		pr_devel("axon_msi: debugfs_create_file failed!\n");
-		return;
-	}
+	debugfs_create_file(name, 0600, powerpc_debugfs_root, msic, &fops_msic);
 }
 #endif /* DEBUG */

arch/powerpc/platforms/cell/spufs/switch.c

···
 		POLL_WHILE_FALSE((in_be64(&priv2->mfc_control_RW) &
 				  MFC_CNTL_SUSPEND_DMA_STATUS_MASK) ==
 				 MFC_CNTL_SUSPEND_COMPLETE);
-		/* fall through */
+		fallthrough;
 	case MFC_CNTL_SUSPEND_COMPLETE:
 		if (csa)
 			csa->priv2.mfc_control_RW =

arch/powerpc/platforms/chrp/setup.c

···
 	of_node_put(np);
 }
 
-#if defined(CONFIG_VT) && defined(CONFIG_INPUT_ADBHID) && defined(CONFIG_XMON)
-static struct irqaction xmon_irqaction = {
-	.handler = xmon_irq,
-	.name = "XMON break",
-};
-#endif
-
 static void __init chrp_find_8259(void)
 {
 	struct device_node *np, *pic = NULL;
···
 		if (of_node_is_type(kbd->parent, "adb"))
 			break;
 	of_node_put(kbd);
-	if (kbd)
-		setup_irq(HYDRA_INT_ADB_NMI, &xmon_irqaction);
+	if (kbd) {
+		if (request_irq(HYDRA_INT_ADB_NMI, xmon_irq, 0, "XMON break",
+				NULL))
+			pr_err("Failed to register XMON break interrupt\n");
+	}
 #endif
 }
 
···
  	if (strcmp(dtype, "chrp"))
 		return 0;
 
-	ISA_DMA_THRESHOLD = ~0L;
 	DMA_MODE_READ = 0x44;
 	DMA_MODE_WRITE = 0x48;
 

arch/powerpc/platforms/maple/setup.c

···
 	return 1;
 }
 
-define_machine(maple) {
-	.name			= "Maple",
-	.probe			= maple_probe,
-	.setup_arch		= maple_setup_arch,
-	.init_IRQ		= maple_init_IRQ,
-	.pci_irq_fixup		= maple_pci_irq_fixup,
-	.pci_get_legacy_ide_irq	= maple_pci_get_legacy_ide_irq,
-	.restart		= maple_restart,
-	.halt			= maple_halt,
-       	.get_boot_time		= maple_get_boot_time,
-       	.set_rtc_time		= maple_set_rtc_time,
-       	.get_rtc_time		= maple_get_rtc_time,
-      	.calibrate_decr		= generic_calibrate_decr,
-	.progress		= maple_progress,
-	.power_save		= power4_idle,
-};
-
 #ifdef CONFIG_EDAC
 /*
  * Register a platform device for CPC925 memory controller on
···
 }
 machine_device_initcall(maple, maple_cpc925_edac_setup);
 #endif
+
+define_machine(maple) {
+	.name			= "Maple",
+	.probe			= maple_probe,
+	.setup_arch		= maple_setup_arch,
+	.init_IRQ		= maple_init_IRQ,
+	.pci_irq_fixup		= maple_pci_irq_fixup,
+	.pci_get_legacy_ide_irq	= maple_pci_get_legacy_ide_irq,
+	.restart		= maple_restart,
+	.halt			= maple_halt,
+	.get_boot_time		= maple_get_boot_time,
+	.set_rtc_time		= maple_set_rtc_time,
+	.get_rtc_time		= maple_get_rtc_time,
+	.calibrate_decr		= generic_calibrate_decr,
+	.progress		= maple_progress,
+	.power_save		= power4_idle,
+};

arch/powerpc/platforms/powermac/pic.c

···
 	return irq_linear_revmap(pmac_pic_host, irq);
 }
 
-#ifdef CONFIG_XMON
-static struct irqaction xmon_action = {
-	.handler	= xmon_irq,
-	.flags		= IRQF_NO_THREAD,
-	.name		= "NMI - XMON"
-};
-#endif
-
-static struct irqaction gatwick_cascade_action = {
-	.handler	= gatwick_action,
-	.flags		= IRQF_NO_THREAD,
-	.name		= "cascade",
-};
-
 static int pmac_pic_host_match(struct irq_domain *h, struct device_node *node,
 			       enum irq_domain_bus_token bus_token)
 {
···
 		out_le32(&pmac_irq_hw[i]->enable, 0);
 
 	/* Hookup cascade irq */
-	if (slave && pmac_irq_cascade)
-		setup_irq(pmac_irq_cascade, &gatwick_cascade_action);
+	if (slave && pmac_irq_cascade) {
+		if (request_irq(pmac_irq_cascade, gatwick_action,
+				IRQF_NO_THREAD, "cascade", NULL))
+			pr_err("Failed to register cascade interrupt\n");
+	}
 
 	printk(KERN_INFO "irq: System has %d possible interrupts\n", max_irqs);
 #ifdef CONFIG_XMON
-	setup_irq(irq_create_mapping(NULL, 20), &xmon_action);
+	i = irq_create_mapping(NULL, 20);
+	if (request_irq(i, xmon_irq, IRQF_NO_THREAD, "NMI - XMON", NULL))
+		pr_err("Failed to register NMI-XMON interrupt\n");
 #endif
 }
 
···
 		nmi_irq = irq_of_parse_and_map(pswitch, 0);
 		if (nmi_irq) {
 			mpic_irq_set_priority(nmi_irq, 9);
-			setup_irq(nmi_irq, &xmon_action);
+			if (request_irq(nmi_irq, xmon_irq, IRQF_NO_THREAD,
+					"NMI - XMON", NULL))
+				pr_err("Failed to register NMI-XMON interrupt\n");
 		}
 		of_node_put(pswitch);
 	}

arch/powerpc/platforms/powermac/setup.c

···
 
 #ifdef CONFIG_PPC32
 	/* isa_io_base gets set in pmac_pci_init */
-	ISA_DMA_THRESHOLD = ~0L;
 	DMA_MODE_READ = 1;
 	DMA_MODE_WRITE = 2;
 #endif /* CONFIG_PPC32 */

arch/powerpc/platforms/powermac/smp.c

···
 	return 0;
 }
 
-static struct irqaction psurge_irqaction = {
-	.handler = psurge_ipi_intr,
-	.flags = IRQF_PERCPU | IRQF_NO_THREAD,
-	.name = "primary IPI",
-};
-
 static void __init smp_psurge_setup_cpu(int cpu_nr)
 {
+	unsigned long flags = IRQF_PERCPU | IRQF_NO_THREAD;
+	int irq;
+
 	if (cpu_nr != 0 || !psurge_start)
 		return;
 
 	/* reset the entry point so if we get another intr we won't
 	 * try to startup again */
 	out_be32(psurge_start, 0x100);
-	if (setup_irq(irq_create_mapping(NULL, 30), &psurge_irqaction))
+	irq = irq_create_mapping(NULL, 30);
+	if (request_irq(irq, psurge_ipi_intr, flags, "primary IPI", NULL))
 		printk(KERN_ERR "Couldn't get primary IPI interrupt");
 }
 
···
 
 #endif /* !CONFIG_PPC64 */
 
-/* L2 and L3 cache settings to pass from CPU0 to CPU1 on G4 cpus */
-volatile static long int core99_l2_cache;
-volatile static long int core99_l3_cache;
-
 static void core99_init_caches(int cpu)
 {
 #ifndef CONFIG_PPC64
+	/* L2 and L3 cache settings to pass from CPU0 to CPU1 on G4 cpus */
+	static long int core99_l2_cache;
+	static long int core99_l3_cache;
+
 	if (!cpu_has_feature(CPU_FTR_L2CR))
 		return;
 

arch/powerpc/platforms/powernv/eeh-powernv.c

···
 
 void pnv_pcibios_bus_add_device(struct pci_dev *pdev)
 {
-	struct pci_dn *pdn = pci_get_pdn(pdev);
-
-	if (!pdn || eeh_has_flag(EEH_FORCE_DISABLED))
-		return;
-
 	dev_dbg(&pdev->dev, "EEH: Setting up device\n");
-	eeh_add_device_early(pdn);
-	eeh_add_device_late(pdev);
-	eeh_sysfs_add_device(pdev);
+	eeh_probe_device(pdev);
 }
 
 static int pnv_eeh_init(void)
···
 
 /**
  * pnv_eeh_probe - Do probe on PCI device
- * @pdn: PCI device node
- * @data: unused
+ * @pdev: pci_dev to probe
  *
- * When EEH module is installed during system boot, all PCI devices
- * are checked one by one to see if it supports EEH. The function
- * is introduced for the purpose. By default, EEH has been enabled
- * on all PCI devices. That's to say, we only need do necessary
- * initialization on the corresponding eeh device and create PE
- * accordingly.
- *
- * It's notable that's unsafe to retrieve the EEH device through
- * the corresponding PCI device. During the PCI device hotplug, which
- * was possiblly triggered by EEH core, the binding between EEH device
- * and the PCI device isn't built yet.
+ * Create, or find the existing, eeh_dev for this pci_dev.
  */
-static void *pnv_eeh_probe(struct pci_dn *pdn, void *data)
+static struct eeh_dev *pnv_eeh_probe(struct pci_dev *pdev)
 {
+	struct pci_dn *pdn = pci_get_pdn(pdev);
 	struct pci_controller *hose = pdn->phb;
 	struct pnv_phb *phb = hose->private_data;
 	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
···
 	 */
 	if (!edev || edev->pe)
 		return NULL;
+
+	/* already configured? */
+	if (edev->pdev) {
+		pr_debug("%s: found existing edev for %04x:%02x:%02x.%01x\n",
+			__func__, hose->global_number, config_addr >> 8,
+			PCI_SLOT(config_addr), PCI_FUNC(config_addr));
+		return edev;
+	}
 
 	/* Skip for PCI-ISA bridge */
 	if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA)
···
 
 	eeh_edev_dbg(edev, "EEH enabled on device\n");
 
-	return NULL;
+	return edev;
 }
 
 /**

arch/powerpc/platforms/powernv/memtrace.c

···
 
 		snprintf(ent->name, 16, "%08x", ent->nid);
 		dir = debugfs_create_dir(ent->name, memtrace_debugfs_dir);
-		if (!dir) {
-			pr_err("Failed to create debugfs directory for node %d\n",
-				ent->nid);
-			return -1;
-		}
 
 		ent->dir = dir;
 		debugfs_create_file("trace", 0400, dir, ent, &memtrace_fops);
···
 {
 	memtrace_debugfs_dir = debugfs_create_dir("memtrace",
 						  powerpc_debugfs_root);
-	if (!memtrace_debugfs_dir)
-		return -1;
 
 	debugfs_create_file("enable", 0600, memtrace_debugfs_dir,
 			    NULL, &memtrace_init_fops);

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

···
 static struct opalcore_config *oc_conf;
 static const struct opal_mpipl_fadump *opalc_metadata;
 static const struct opal_mpipl_fadump *opalc_cpu_metadata;
+struct kobject *mpipl_kobj;
 
 /*
  * Set crashing CPU's signal to SIGUSR1. if the kernel is triggered
···
 		return;
 
 	/* Remove OPAL core sysfs file */
-	sysfs_remove_bin_file(opal_kobj, &opal_core_attr);
+	sysfs_remove_bin_file(mpipl_kobj, &opal_core_attr);
 	oc_conf->ptload_phdr = NULL;
 	oc_conf->ptload_cnt = 0;
 
···
 	of_node_put(np);
 }
 
-static ssize_t fadump_release_opalcore_store(struct kobject *kobj,
-					     struct kobj_attribute *attr,
-					     const char *buf, size_t count)
+static ssize_t release_core_store(struct kobject *kobj,
+				  struct kobj_attribute *attr,
+				  const char *buf, size_t count)
 {
 	int input = -1;
 
···
 	return count;
 }
 
-static struct kobj_attribute opalcore_rel_attr = __ATTR(fadump_release_opalcore,
-						0200, NULL,
-						fadump_release_opalcore_store);
+static struct kobj_attribute opalcore_rel_attr = __ATTR_WO(release_core);
+
+static struct attribute *mpipl_attr[] = {
+	&opalcore_rel_attr.attr,
+	NULL,
+};
+
+static struct bin_attribute *mpipl_bin_attr[] = {
+	&opal_core_attr,
+	NULL,
+
+};
+
+static struct attribute_group mpipl_group = {
+	.attrs = mpipl_attr,
+	.bin_attrs =  mpipl_bin_attr,
+};
 
 static int __init opalcore_init(void)
 {
···
 	 * then capture the dump.
 	 */
 	if (!(is_opalcore_usable())) {
-		pr_err("Failed to export /sys/firmware/opal/core\n");
+		pr_err("Failed to export /sys/firmware/opal/mpipl/core\n");
 		opalcore_cleanup();
 		return rc;
 	}
···
 	/* Set OPAL core file size */
 	opal_core_attr.size = oc_conf->opalcore_size;
 
+	mpipl_kobj = kobject_create_and_add("mpipl", opal_kobj);
+	if (!mpipl_kobj) {
+		pr_err("unable to create mpipl kobject\n");
+		return -ENOMEM;
+	}
+
 	/* Export OPAL core sysfs file */
-	rc = sysfs_create_bin_file(opal_kobj, &opal_core_attr);
-	if (rc != 0) {
-		pr_err("Failed to export /sys/firmware/opal/core\n");
+	rc = sysfs_create_group(mpipl_kobj, &mpipl_group);
+	if (rc) {
+		pr_err("mpipl sysfs group creation failed (%d)", rc);
 		opalcore_cleanup();
 		return rc;
 	}
-
-	rc = sysfs_create_file(kernel_kobj, &opalcore_rel_attr.attr);
+	/* The /sys/firmware/opal/core is moved to /sys/firmware/opal/mpipl/
+	 * directory, need to create symlink at old location to maintain
+	 * backward compatibility.
+	 */
+	rc = compat_only_sysfs_link_entry_to_kobj(opal_kobj, mpipl_kobj,
+						  "core", NULL);
 	if (rc) {
-		pr_warn("unable to create sysfs file fadump_release_opalcore (%d)\n",
-			rc);
+		pr_err("unable to create core symlink (%d)\n", rc);
+		return rc;
 	}
 
 	return 0;

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

···
 }
 DEFINE_DEBUGFS_ATTRIBUTE(fops_imc_x64, imc_mem_get, imc_mem_set, "0x%016llx\n");
 
-static struct dentry *imc_debugfs_create_x64(const char *name, umode_t mode,
-					     struct dentry *parent, u64  *value)
+static void imc_debugfs_create_x64(const char *name, umode_t mode,
+				   struct dentry *parent, u64  *value)
 {
-	return debugfs_create_file_unsafe(name, mode, parent,
-					  value, &fops_imc_x64);
+	debugfs_create_file_unsafe(name, mode, parent, value, &fops_imc_x64);
 }
 
 /*
···
 
 	imc_debugfs_parent = debugfs_create_dir("imc", powerpc_debugfs_root);
 
-	if (!imc_debugfs_parent)
-		return;
-
 	if (of_property_read_u32(node, "cb_offset", &cb_offset))
 		cb_offset = IMC_CNTL_BLK_OFFSET;
 
···
 		loc = (u64)(ptr->vbase) + cb_offset;
 		imc_mode_addr = (u64 *)(loc + IMC_CNTL_BLK_MODE_OFFSET);
 		sprintf(mode, "imc_mode_%d", (u32)(ptr->id));
-		if (!imc_debugfs_create_x64(mode, 0600, imc_debugfs_parent,
-					    imc_mode_addr))
-			goto err;
+		imc_debugfs_create_x64(mode, 0600, imc_debugfs_parent,
+				       imc_mode_addr);
 
 		imc_cmd_addr = (u64 *)(loc + IMC_CNTL_BLK_CMD_OFFSET);
 		sprintf(cmd, "imc_cmd_%d", (u32)(ptr->id));
-		if (!imc_debugfs_create_x64(cmd, 0600, imc_debugfs_parent,
-					    imc_cmd_addr))
-			goto err;
+		imc_debugfs_create_x64(cmd, 0600, imc_debugfs_parent,
+				       imc_cmd_addr);
 		ptr++;
 	}
-	return;
-
-err:
-	debugfs_remove_recursive(imc_debugfs_parent);
 }
 
 /*

arch/powerpc/platforms/powernv/pci-ioda.c

···
 
 		sprintf(name, "PCI%04x", hose->global_number);
 		phb->dbgfs = debugfs_create_dir(name, powerpc_debugfs_root);
-		if (!phb->dbgfs) {
-			pr_warn("%s: Error on creating debugfs on PHB#%x\n",
-				__func__, hose->global_number);
-			continue;
-		}
 
 		debugfs_create_file_unsafe("dump_diag_regs", 0200, phb->dbgfs,
 					   phb, &pnv_pci_diag_data_fops);

arch/powerpc/platforms/powernv/setup.c

···
 	pnv_prepare_going_down();
 
 	do {
-		if (!cmd)
+		if (!cmd || !strlen(cmd))
 			rc = opal_cec_reboot();
 		else if (strcmp(cmd, "full") == 0)
 			rc = opal_cec_reboot2(OPAL_REBOOT_FULL_IPL, NULL);
···
 			rc = opal_cec_reboot2(OPAL_REBOOT_MPIPL, NULL);
 		else if (strcmp(cmd, "error") == 0)
 			rc = opal_cec_reboot2(OPAL_REBOOT_PLATFORM_ERROR, NULL);
+		else if (strcmp(cmd, "fast") == 0)
+			rc = opal_cec_reboot2(OPAL_REBOOT_FAST, NULL);
 		else
 			rc = OPAL_UNSUPPORTED;
 

arch/powerpc/platforms/powernv/vas-debug.c

···
 
 void vas_window_init_dbgdir(struct vas_window *window)
 {
-	struct dentry *f, *d;
+	struct dentry *d;
 
 	if (!window->vinst->dbgdir)
 		return;
···
 	snprintf(window->dbgname, 16, "w%d", window->winid);
 
 	d = debugfs_create_dir(window->dbgname, window->vinst->dbgdir);
-	if (IS_ERR(d))
-		goto free_name;
-
 	window->dbgdir = d;
 
-	f = debugfs_create_file("info", 0444, d, window, &info_fops);
-	if (IS_ERR(f))
-		goto remove_dir;
-
-	f = debugfs_create_file("hvwc", 0444, d, window, &hvwc_fops);
-	if (IS_ERR(f))
-		goto remove_dir;
-
-	return;
-
-remove_dir:
-	debugfs_remove_recursive(window->dbgdir);
-	window->dbgdir = NULL;
-
-free_name:
-	kfree(window->dbgname);
-	window->dbgname = NULL;
+	debugfs_create_file("info", 0444, d, window, &info_fops);
+	debugfs_create_file("hvwc", 0444, d, window, &hvwc_fops);
 }
 
 void vas_instance_init_dbgdir(struct vas_instance *vinst)
···
 	struct dentry *d;
 
 	vas_init_dbgdir();
-	if (!vas_debugfs)
-		return;
 
 	vinst->dbgname = kzalloc(16, GFP_KERNEL);
 	if (!vinst->dbgname)
···
 	snprintf(vinst->dbgname, 16, "v%d", vinst->vas_id);
 
 	d = debugfs_create_dir(vinst->dbgname, vas_debugfs);
-	if (IS_ERR(d))
-		goto free_name;
-
 	vinst->dbgdir = d;
-	return;
-
-free_name:
-	kfree(vinst->dbgname);
-	vinst->dbgname = NULL;
-	vinst->dbgdir = NULL;
 }
 
 /*
···
 
 	first_time = false;
 	vas_debugfs = debugfs_create_dir("vas", NULL);
-	if (IS_ERR(vas_debugfs))
-		vas_debugfs = NULL;
 }

arch/powerpc/platforms/pseries/Makefile

···
 obj-$(CONFIG_PPC_SVM)		+= svm.o
 obj-$(CONFIG_FA_DUMP)		+= rtas-fadump.o
 
-ifdef CONFIG_PPC_PSERIES
 obj-$(CONFIG_SUSPEND)		+= suspend.o
-endif

arch/powerpc/platforms/pseries/eeh_pseries.c

···
 		pdn->pe_number  =  physfn_pdn->pe_num_map[pdn->vf_index];
 	}
 #endif
-	eeh_add_device_early(pdn);
-	eeh_add_device_late(pdev);
+	pseries_eeh_init_edev(pdn);
 #ifdef CONFIG_PCI_IOV
 	if (pdev->is_virtfn) {
 		struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
···
 		eeh_add_to_parent_pe(edev);   /* Add as VF PE type */
 	}
 #endif
-	eeh_sysfs_add_device(pdev);
+	eeh_probe_device(pdev);
 }
 
 /*
···
 }
 
 /**
- * pseries_eeh_probe - EEH probe on the given device
- * @pdn: PCI device node
- * @data: Unused
+ * pseries_eeh_init_edev - initialise the eeh_dev and eeh_pe for a pci_dn
  *
- * When EEH module is installed during system boot, all PCI devices
- * are checked one by one to see if it supports EEH. The function
- * is introduced for the purpose.
+ * @pdn: PCI device node
+ *
+ * When we discover a new PCI device via the device-tree we create a
+ * corresponding pci_dn and we allocate, but don't initialise, an eeh_dev.
+ * This function takes care of the initialisation and inserts the eeh_dev
+ * into the correct eeh_pe. If no eeh_pe exists we'll allocate one.
  */
-static void *pseries_eeh_probe(struct pci_dn *pdn, void *data)
+void pseries_eeh_init_edev(struct pci_dn *pdn)
 {
 	struct eeh_dev *edev;
 	struct eeh_pe pe;
···
 	int enable = 0;
 	int ret;
 
-	/* Retrieve OF node and eeh device */
+	if (WARN_ON_ONCE(!eeh_has_flag(EEH_PROBE_MODE_DEVTREE)))
+		return;
+
+	/*
+	 * Find the eeh_dev for this pdn. The storage for the eeh_dev was
+	 * allocated at the same time as the pci_dn.
+	 *
+	 * XXX: We should probably re-visit that.
+	 */
 	edev = pdn_to_eeh_dev(pdn);
-	if (!edev || edev->pe)
-		return NULL;
+	if (!edev)
+		return;
+
+	/*
+	 * If ->pe is set then we've already probed this device. We hit
+	 * this path when a pci_dev is removed and rescanned while recovering
+	 * a PE (i.e. for devices where the driver doesn't support error
+	 * recovery).
+	 */
+	if (edev->pe)
+		return;
 
 	/* Check class/vendor/device IDs */
 	if (!pdn->vendor_id || !pdn->device_id || !pdn->class_code)
-		return NULL;
+		return;
 
 	/* Skip for PCI-ISA bridge */
         if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA)
-		return NULL;
+		return;
 
 	eeh_edev_dbg(edev, "Probing device\n");
 
···
 
 	/* Save memory bars */
 	eeh_save_bars(edev);
-
-	return NULL;
 }
+
+static struct eeh_dev *pseries_eeh_probe(struct pci_dev *pdev)
+{
+	struct eeh_dev *edev;
+	struct pci_dn *pdn;
+
+	pdn = pci_get_pdn_by_devfn(pdev->bus, pdev->devfn);
+	if (!pdn)
+		return NULL;
+
+	/*
+	 * If the system supports EEH on this device then the eeh_dev was
+	 * configured and inserted into a PE in pseries_eeh_init_edev()
+	 */
+	edev = pdn_to_eeh_dev(pdn);
+	if (!edev || !edev->pe)
+		return NULL;
+
+	return edev;
+}
+
+/**
+ * pseries_eeh_init_edev_recursive - Enable EEH for the indicated device
+ * @pdn: PCI device node
+ *
+ * This routine must be used to perform EEH initialization for the
+ * indicated PCI device that was added after system boot (e.g.
+ * hotplug, dlpar).
+ */
+void pseries_eeh_init_edev_recursive(struct pci_dn *pdn)
+{
+	struct pci_dn *n;
+
+	if (!pdn)
+		return;
+
+	list_for_each_entry(n, &pdn->child_list, list)
+		pseries_eeh_init_edev_recursive(n);
+
+	pseries_eeh_init_edev(pdn);
+}
+EXPORT_SYMBOL_GPL(pseries_eeh_init_edev_recursive);
 
 /**
  * pseries_eeh_set_option - Initialize EEH or MMIO/DMA reenable

arch/powerpc/platforms/pseries/hotplug-memory.c

···
 			 struct drmem_lmb **end_lmb)
 {
 	struct drmem_lmb *lmb, *start, *end;
-	struct drmem_lmb *last_lmb;
+	struct drmem_lmb *limit;
 
 	start = NULL;
 	for_each_drmem_lmb(lmb) {
···
 	if (!start)
 		return -EINVAL;
 
-	end = &start[n_lmbs - 1];
+	end = &start[n_lmbs];
 
-	last_lmb = &drmem_info->lmbs[drmem_info->n_lmbs - 1];
-	if (end > last_lmb)
+	limit = &drmem_info->lmbs[drmem_info->n_lmbs];
+	if (end > limit)
 		return -EINVAL;
 
 	*start_lmb = start;

arch/powerpc/platforms/pseries/lpar.c

···
 
 static int __init vcpudispatch_stats_procfs_init(void)
 {
-	if (!lppaca_shared_proc(get_lppaca()))
+	/*
+	 * Avoid smp_processor_id while preemptible. All CPUs should have
+	 * the same value for lppaca_shared_proc.
+	 */
+	preempt_disable();
+	if (!lppaca_shared_proc(get_lppaca())) {
+		preempt_enable();
 		return 0;
+	}
+	preempt_enable();
 
 	if (!proc_create("powerpc/vcpudispatch_stats", 0600, NULL,
 					&vcpudispatch_stats_proc_ops))

arch/powerpc/platforms/pseries/of_helpers.c

···
 		return -EINVAL;
 
 	/* Should now know end of current entry */
-	(*curval) = (void *)p2;
+	(*curval) = (void *)(++p2);
 	data->last_drc_index = data->drc_index_start +
 		((data->num_sequential_elems - 1) * data->sequential_inc);
 

arch/powerpc/platforms/pseries/papr_scm.c

···
 	return 0;
 }
 
-int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
-		unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc)
+static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc,
+			  struct nvdimm *nvdimm, unsigned int cmd, void *buf,
+			  unsigned int buf_len, int *cmd_rc)
 {
 	struct nd_cmd_get_config_size *get_size_hdr;
 	struct papr_scm_priv *p;

arch/powerpc/platforms/pseries/pci_dlpar.c

···
 	eeh_dev_phb_init_dynamic(phb);
 
 	if (dn->child)
-		eeh_add_device_tree_early(PCI_DN(dn));
+		pseries_eeh_init_edev_recursive(PCI_DN(dn));
 
 	pcibios_scan_phb(phb);
 	pcibios_finish_adding_to_bus(phb->bus);

arch/powerpc/platforms/pseries/ras.c

···
 	switch (mce_log->error_type) {
 	case MC_ERROR_TYPE_UE:
 		mce_err.error_type = MCE_ERROR_TYPE_UE;
+		mce_common_process_ue(regs, &mce_err);
+		if (mce_err.ignore_event)
+			disposition = RTAS_DISP_FULLY_RECOVERED;
 		switch (err_sub_type) {
 		case MC_ERROR_UE_IFETCH:
 			mce_err.u.ue_error_type = MCE_UE_ERROR_IFETCH;

arch/powerpc/platforms/pseries/vio.c

···
 }
 EXPORT_SYMBOL(vio_get_attribute);
 
-#ifdef CONFIG_PPC_PSERIES
 /* vio_find_name() - internal because only vio.c knows how we formatted the
  * kobject name
  */
···
 	return rc;
 }
 EXPORT_SYMBOL(vio_disable_interrupts);
-#endif /* CONFIG_PPC_PSERIES */
 
 static int __init vio_init(void)
 {

arch/powerpc/platforms/pseries/vphn.c

···
 	long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
 
 	rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, cpu);
-	vphn_unpack_associativity(retbuf, associativity);
+	if (rc == H_SUCCESS)
+		vphn_unpack_associativity(retbuf, associativity);
 
 	return rc;
 }

arch/powerpc/sysdev/xive/common.c

···
 #include <linux/spinlock.h>
 #include <linux/msi.h>
 
+#include <asm/debugfs.h>
 #include <asm/prom.h>
 #include <asm/io.h>
 #include <asm/smp.h>
···
 
 /* Xive state for each CPU */
 static DEFINE_PER_CPU(struct xive_cpu *, xive_cpu);
-
-/*
- * A "disabled" interrupt should never fire, to catch problems
- * we set its logical number to this
- */
-#define XIVE_BAD_IRQ		0x7fffffff
-#define XIVE_MAX_IRQ		(XIVE_BAD_IRQ - 1)
 
 /* An invalid CPU target */
 #define XIVE_INVALID_TARGET	(-1)
···
 
 int xmon_xive_get_irq_config(u32 hw_irq, struct irq_data *d)
 {
+	struct irq_chip *chip = irq_data_get_irq_chip(d);
 	int rc;
 	u32 target;
 	u8 prio;
 	u32 lirq;
+
+	if (!is_xive_irq(chip))
+		return -EINVAL;
 
 	rc = xive_ops->get_irq_config(hw_irq, &target, &prio, &lirq);
 	if (rc) {
···
 		struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
 		u64 val = xive_esb_read(xd, XIVE_ESB_GET);
 
-		xmon_printf("PQ=%c%c",
+		xmon_printf("flags=%c%c%c PQ=%c%c",
+			    xd->flags & XIVE_IRQ_FLAG_STORE_EOI ? 'S' : ' ',
+			    xd->flags & XIVE_IRQ_FLAG_LSI ? 'L' : ' ',
+			    xd->flags & XIVE_IRQ_FLAG_H_INT_ESB ? 'H' : ' ',
 			    val & XIVE_ESB_VAL_P ? 'P' : '-',
 			    val & XIVE_ESB_VAL_Q ? 'Q' : '-');
 	}
···
 	xc = per_cpu(xive_cpu, cpu);
 
 	/* Check if we are already setup */
-	if (xc->hw_ipi != 0)
+	if (xc->hw_ipi != XIVE_BAD_IRQ)
 		return 0;
 
 	/* Grab an IPI from the backend, this will populate xc->hw_ipi */
···
 	/* Disable the IPI and free the IRQ data */
 
 	/* Already cleaned up ? */
-	if (xc->hw_ipi == 0)
+	if (xc->hw_ipi == XIVE_BAD_IRQ)
 		return;
 
 	/* Mask the IPI */
···
 		if (np)
 			xc->chip_id = of_get_ibm_chip_id(np);
 		of_node_put(np);
+		xc->hw_ipi = XIVE_BAD_IRQ;
 
 		per_cpu(xive_cpu, cpu) = xc;
 	}
···
 	return 0;
 }
 __setup("xive=off", xive_off);
+
+void xive_debug_show_cpu(struct seq_file *m, int cpu)
+{
+	struct xive_cpu *xc = per_cpu(xive_cpu, cpu);
+
+	seq_printf(m, "CPU %d:", cpu);
+	if (xc) {
+		seq_printf(m, "pp=%02x CPPR=%02x ", xc->pending_prio, xc->cppr);
+
+#ifdef CONFIG_SMP
+		{
+			u64 val = xive_esb_read(&xc->ipi_data, XIVE_ESB_GET);
+
+			seq_printf(m, "IPI=0x%08x PQ=%c%c ", xc->hw_ipi,
+				   val & XIVE_ESB_VAL_P ? 'P' : '-',
+				   val & XIVE_ESB_VAL_Q ? 'Q' : '-');
+		}
+#endif
+		{
+			struct xive_q *q = &xc->queue[xive_irq_priority];
+			u32 i0, i1, idx;
+
+			if (q->qpage) {
+				idx = q->idx;
+				i0 = be32_to_cpup(q->qpage + idx);
+				idx = (idx + 1) & q->msk;
+				i1 = be32_to_cpup(q->qpage + idx);
+				seq_printf(m, "EQ idx=%d T=%d %08x %08x ...",
+					   q->idx, q->toggle, i0, i1);
+			}
+		}
+	}
+	seq_puts(m, "\n");
+}
+
+void xive_debug_show_irq(struct seq_file *m, u32 hw_irq, struct irq_data *d)
+{
+	struct irq_chip *chip = irq_data_get_irq_chip(d);
+	int rc;
+	u32 target;
+	u8 prio;
+	u32 lirq;
+
+	if (!is_xive_irq(chip))
+		return;
+
+	rc = xive_ops->get_irq_config(hw_irq, &target, &prio, &lirq);
+	if (rc) {
+		seq_printf(m, "IRQ 0x%08x : no config rc=%d\n", hw_irq, rc);
+		return;
+	}
+
+	seq_printf(m, "IRQ 0x%08x : target=0x%x prio=%02x lirq=0x%x ",
+		   hw_irq, target, prio, lirq);
+
+	if (d) {
+		struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+		u64 val = xive_esb_read(xd, XIVE_ESB_GET);
+
+		seq_printf(m, "flags=%c%c%c PQ=%c%c",
+			   xd->flags & XIVE_IRQ_FLAG_STORE_EOI ? 'S' : ' ',
+			   xd->flags & XIVE_IRQ_FLAG_LSI ? 'L' : ' ',
+			   xd->flags & XIVE_IRQ_FLAG_H_INT_ESB ? 'H' : ' ',
+			   val & XIVE_ESB_VAL_P ? 'P' : '-',
+			   val & XIVE_ESB_VAL_Q ? 'Q' : '-');
+	}
+	seq_puts(m, "\n");
+}
+
+static int xive_core_debug_show(struct seq_file *m, void *private)
+{
+	unsigned int i;
+	struct irq_desc *desc;
+	int cpu;
+
+	if (xive_ops->debug_show)
+		xive_ops->debug_show(m, private);
+
+	for_each_possible_cpu(cpu)
+		xive_debug_show_cpu(m, cpu);
+
+	for_each_irq_desc(i, desc) {
+		struct irq_data *d = irq_desc_get_irq_data(desc);
+		unsigned int hw_irq;
+
+		if (!d)
+			continue;
+
+		hw_irq = (unsigned int)irqd_to_hwirq(d);
+
+		/* IPIs are special (HW number 0) */
+		if (hw_irq)
+			xive_debug_show_irq(m, hw_irq, d);
+	}
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(xive_core_debug);
+
+int xive_core_debug_init(void)
+{
+	debugfs_create_file("xive", 0400, powerpc_debugfs_root,
+			    NULL, &xive_core_debug_fops);
+	return 0;
+}

arch/powerpc/sysdev/xive/native.c

···
 #include <linux/cpumask.h>
 #include <linux/mm.h>
 
+#include <asm/machdep.h>
 #include <asm/prom.h>
 #include <asm/io.h>
 #include <asm/smp.h>
···
 	s64 rc;
 
 	/* Free the IPI */
-	if (!xc->hw_ipi)
+	if (xc->hw_ipi == XIVE_BAD_IRQ)
 		return;
 	for (;;) {
 		rc = opal_xive_free_irq(xc->hw_ipi);
···
 			msleep(OPAL_BUSY_DELAY_MS);
 			continue;
 		}
-		xc->hw_ipi = 0;
+		xc->hw_ipi = XIVE_BAD_IRQ;
 		break;
 	}
 }
···
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xive_native_get_vp_state);
+
+machine_arch_initcall(powernv, xive_core_debug_init);

arch/powerpc/sysdev/xive/spapr.c

···
 #include <linux/delay.h>
 #include <linux/libfdt.h>
 
+#include <asm/machdep.h>
 #include <asm/prom.h>
 #include <asm/io.h>
 #include <asm/smp.h>
···
 
 static void xive_spapr_put_ipi(unsigned int cpu, struct xive_cpu *xc)
 {
-	if (!xc->hw_ipi)
+	if (xc->hw_ipi == XIVE_BAD_IRQ)
 		return;
 
 	xive_irq_bitmap_free(xc->hw_ipi);
-	xc->hw_ipi = 0;
+	xc->hw_ipi = XIVE_BAD_IRQ;
 }
 #endif /* CONFIG_SMP */
 
···
 	plpar_int_sync(0, hw_irq);
 }
 
+static int xive_spapr_debug_show(struct seq_file *m, void *private)
+{
+	struct xive_irq_bitmap *xibm;
+	char *buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+
+	list_for_each_entry(xibm, &xive_irq_bitmaps, list) {
+		memset(buf, 0, PAGE_SIZE);
+		bitmap_print_to_pagebuf(true, buf, xibm->bitmap, xibm->count);
+		seq_printf(m, "bitmap #%d: %s", xibm->count, buf);
+	}
+	kfree(buf);
+
+	return 0;
+}
+
 static const struct xive_ops xive_spapr_ops = {
 	.populate_irq_data	= xive_spapr_populate_irq_data,
 	.configure_irq		= xive_spapr_configure_irq,
···
 #ifdef CONFIG_SMP
 	.get_ipi		= xive_spapr_get_ipi,
 	.put_ipi		= xive_spapr_put_ipi,
+	.debug_show		= xive_spapr_debug_show,
 #endif /* CONFIG_SMP */
 	.name			= "spapr",
 };
···
 	pr_info("Using %dkB queues\n", 1 << (xive_queue_shift - 10));
 	return true;
 }
+
+machine_arch_initcall(pseries, xive_core_debug_init);

arch/powerpc/sysdev/xive/xive-internal.h

···
 #ifndef __XIVE_INTERNAL_H
 #define __XIVE_INTERNAL_H
 
+/*
+ * A "disabled" interrupt should never fire, to catch problems
+ * we set its logical number to this
+ */
+#define XIVE_BAD_IRQ		0x7fffffff
+#define XIVE_MAX_IRQ		(XIVE_BAD_IRQ - 1)
+
 /* Each CPU carry one of these with various per-CPU state */
 struct xive_cpu {
 #ifdef CONFIG_SMP
···
 	int	(*get_ipi)(unsigned int cpu, struct xive_cpu *xc);
 	void	(*put_ipi)(unsigned int cpu, struct xive_cpu *xc);
 #endif
+	int	(*debug_show)(struct seq_file *m, void *private);
 	const char *name;
 };
 
 bool xive_core_init(const struct xive_ops *ops, void __iomem *area, u32 offset,
 		    u8 max_prio);
 __be32 *xive_queue_page_alloc(unsigned int cpu, u32 queue_shift);
+int xive_core_debug_init(void);
 
 static inline u32 xive_alloc_order(u32 queue_shift)
 {

arch/powerpc/xmon/Makefile

···
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for xmon
 
-# Avoid clang warnings around longjmp/setjmp declarations
-subdir-ccflags-y := -ffreestanding
-
 GCOV_PROFILE := n
 KCOV_INSTRUMENT := n
 UBSAN_SANITIZE := n

arch/powerpc/xmon/xmon.c

···
 
 static unsigned long adrs;
 static int size = 1;
-#define MAX_DUMP (128 * 1024)
+#define MAX_DUMP (64 * 1024)
 static unsigned long ndump = 64;
+#define MAX_IDUMP (MAX_DUMP >> 2)
 static unsigned long nidump = 16;
 static unsigned long ncsum = 4096;
 static int termch;
···
 
 			printf("%0*llx", size * 2, val);
 		}
-		printf("\n");
+		printf("  |");
+		for (j = 0; j < 16; ++j) {
+			val = temp[j];
+			putchar(' ' <= val && val <= '~' ? val : '.');
+		}
+		printf("|\n");
 	}
 }
 
···
 		scanhex(&nidump);
 		if (nidump == 0)
 			nidump = 16;
-		else if (nidump > MAX_DUMP)
-			nidump = MAX_DUMP;
+		else if (nidump > MAX_IDUMP)
+			nidump = MAX_IDUMP;
 		adrs += ppc_inst_dump(adrs, nidump, 1);
 		last_cmd = "di\n";
 	} else if (c == 'l') {

drivers/cpufreq/powernv-cpufreq.c

···
 void powernv_cpufreq_work_fn(struct work_struct *work)
 {
 	struct chip *chip = container_of(work, struct chip, throttle);
+	struct cpufreq_policy *policy;
 	unsigned int cpu;
 	cpumask_t mask;
 
···
 	chip->restore = false;
 	for_each_cpu(cpu, &mask) {
 		int index;
-		struct cpufreq_policy policy;
 
-		cpufreq_get_policy(&policy, cpu);
-		index = cpufreq_table_find_index_c(&policy, policy.cur);
-		powernv_cpufreq_target_index(&policy, index);
-		cpumask_andnot(&mask, &mask, policy.cpus);
+		policy = cpufreq_cpu_get(cpu);
+		if (!policy)
+			continue;
+		index = cpufreq_table_find_index_c(policy, policy->cur);
+		powernv_cpufreq_target_index(policy, index);
+		cpumask_andnot(&mask, &mask, policy->cpus);
+		cpufreq_cpu_put(policy);
 	}
 out:
 	put_online_cpus();
···
 
 static inline void clean_chip_info(void)
 {
+	int i;
+
+	/* flush any pending work items */
+	if (chips)
+		for (i = 0; i < nr_chips; i++)
+			cancel_work_sync(&chips[i].throttle);
 	kfree(chips);
 }
 
···
 	if (rc)
 		goto out;
 
-	register_reboot_notifier(&powernv_cpufreq_reboot_nb);
-	opal_message_notifier_register(OPAL_MSG_OCC, &powernv_cpufreq_opal_nb);
-
 	if (powernv_pstate_info.wof_enabled)
 		powernv_cpufreq_driver.boost_enabled = true;
 	else
···
 	rc = cpufreq_register_driver(&powernv_cpufreq_driver);
 	if (rc) {
 		pr_info("Failed to register the cpufreq driver (%d)\n", rc);
-		goto cleanup_notifiers;
+		goto cleanup;
 	}
 
 	if (powernv_pstate_info.wof_enabled)
 		cpufreq_enable_boost_support();
 
+	register_reboot_notifier(&powernv_cpufreq_reboot_nb);
+	opal_message_notifier_register(OPAL_MSG_OCC, &powernv_cpufreq_opal_nb);
+
 	return 0;
-cleanup_notifiers:
-	unregister_all_notifiers();
+cleanup:
 	clean_chip_info();
 out:
 	pr_info("Platform driver disabled. System does not support PState control\n");

drivers/pci/hotplug/rpadlpar_core.c

···
 	struct pci_controller *phb = pdn->phb;
 	struct pci_dev *dev = NULL;
 
-	eeh_add_device_tree_early(pdn);
+	pseries_eeh_init_edev_recursive(pdn);
 
 	/* Add EADS device to PHB bus, adding new entry to bus->devices */
 	dev = of_create_pci_dev(dn, phb->bus, pdn->devfn);

drivers/pci/hotplug/rpaphp_core.c

···
 
 static int is_php_type(char *drc_type)
 {
-	unsigned long value;
 	char *endptr;
 
 	/* PCI Hotplug nodes have an integer for drc_type */
-	value = simple_strtoul(drc_type, &endptr, 10);
+	simple_strtoul(drc_type, &endptr, 10);
 	if (endptr == drc_type)
 		return 0;
 
···
 		return retval;
 
 	if (state == PRESENT) {
+		pseries_eeh_init_edev_recursive(PCI_DN(slot->dn));
+
 		pci_lock_rescan_remove();
 		pci_hp_add_devices(slot->bus);
 		pci_unlock_rescan_remove();

drivers/pci/hotplug/rpaphp_pci.c

···
 			return -EINVAL;
 		}
 
-		if (list_empty(&bus->devices))
+		if (list_empty(&bus->devices)) {
+			pseries_eeh_init_edev_recursive(PCI_DN(slot->dn));
 			pci_hp_add_devices(bus);
+		}
 
 		if (!list_empty(&bus->devices)) {
 			slot->state = CONFIGURED;

drivers/tty/ehv_bytechan.c

···
 	return 1;
 }
 
+static unsigned int local_ev_byte_channel_send(unsigned int handle,
+					       unsigned int *count,
+					       const char *p)
+{
+	char buffer[EV_BYTE_CHANNEL_MAX_BYTES];
+	unsigned int c = *count;
+
+	if (c < sizeof(buffer)) {
+		memcpy(buffer, p, c);
+		memset(&buffer[c], 0, sizeof(buffer) - c);
+		p = buffer;
+	}
+	return ev_byte_channel_send(handle, count, p);
+}
+
 /*************************** EARLY CONSOLE DRIVER ***************************/
 
 #ifdef CONFIG_PPC_EARLY_DEBUG_EHV_BC
···
 
 	do {
 		count = 1;
-		ret = ev_byte_channel_send(CONFIG_PPC_EARLY_DEBUG_EHV_BC_HANDLE,
+		ret = local_ev_byte_channel_send(CONFIG_PPC_EARLY_DEBUG_EHV_BC_HANDLE,
 					   &count, &data);
 	} while (ret == EV_EAGAIN);
 }
···
 	while (count) {
 		len = min_t(unsigned int, count, EV_BYTE_CHANNEL_MAX_BYTES);
 		do {
-			ret = ev_byte_channel_send(handle, &len, s);
+			ret = local_ev_byte_channel_send(handle, &len, s);
 		} while (ret == EV_EAGAIN);
 		count -= len;
 		s += len;
···
 			    CIRC_CNT_TO_END(bc->head, bc->tail, BUF_SIZE),
 			    EV_BYTE_CHANNEL_MAX_BYTES);
 
-		ret = ev_byte_channel_send(bc->handle, &len, bc->buf + bc->tail);
+		ret = local_ev_byte_channel_send(bc->handle, &len, bc->buf + bc->tail);
 
 		/* 'len' is valid only if the return code is 0 or EV_EAGAIN */
 		if (!ret || (ret == EV_EAGAIN))

fs/sysfs/group.c

···
 				      struct kobject *target_kobj,
 				      const char *target_name)
 {
+	return compat_only_sysfs_link_entry_to_kobj(kobj, target_kobj,
+						    target_name, NULL);
+}
+EXPORT_SYMBOL_GPL(__compat_only_sysfs_link_entry_to_kobj);
+
+/**
+ * compat_only_sysfs_link_entry_to_kobj - add a symlink to a kobject pointing
+ * to a group or an attribute
+ * @kobj:		The kobject containing the group.
+ * @target_kobj:	The target kobject.
+ * @target_name:	The name of the target group or attribute.
+ * @symlink_name:	The name of the symlink file (target_name will be
+ *			considered if symlink_name is NULL).
+ */
+int compat_only_sysfs_link_entry_to_kobj(struct kobject *kobj,
+					 struct kobject *target_kobj,
+					 const char *target_name,
+					 const char *symlink_name)
+{
 	struct kernfs_node *target;
 	struct kernfs_node *entry;
 	struct kernfs_node *link;
···
 		return -ENOENT;
 	}
 
-	link = kernfs_create_link(kobj->sd, target_name, entry);
+	if (!symlink_name)
+		symlink_name = target_name;
+
+	link = kernfs_create_link(kobj->sd, symlink_name, entry);
 	if (PTR_ERR(link) == -EEXIST)
-		sysfs_warn_dup(kobj->sd, target_name);
+		sysfs_warn_dup(kobj->sd, symlink_name);
 
 	kernfs_put(entry);
 	kernfs_put(target);
 	return PTR_ERR_OR_ZERO(link);
 }
-EXPORT_SYMBOL_GPL(__compat_only_sysfs_link_entry_to_kobj);
+EXPORT_SYMBOL_GPL(compat_only_sysfs_link_entry_to_kobj);
 
 static int sysfs_group_attrs_change_owner(struct kernfs_node *grp_kn,
 					  const struct attribute_group *grp,

include/linux/sysfs.h

···
 int __compat_only_sysfs_link_entry_to_kobj(struct kobject *kobj,
 				      struct kobject *target_kobj,
 				      const char *target_name);
+int compat_only_sysfs_link_entry_to_kobj(struct kobject *kobj,
+					 struct kobject *target_kobj,
+					 const char *target_name,
+					 const char *symlink_name);
 
 void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr);
 
···
 	struct kobject *kobj,
 	struct kobject *target_kobj,
 	const char *target_name)
+{
+	return 0;
+}
+
+static inline int compat_only_sysfs_link_entry_to_kobj(struct kobject *kobj,
+						       struct kobject *target_kobj,
+						       const char *target_name,
+						       const char *symlink_name)
 {
 	return 0;
 }

tools/testing/selftests/powerpc/benchmarks/Makefile

···
 TEST_GEN_PROGS := gettimeofday context_switch fork mmap_bench futex_bench null_syscall
 TEST_GEN_FILES := exec_target
 
+TEST_FILES := settings
+
 CFLAGS += -O2
 
 top_srcdir = ../../../../..

tools/testing/selftests/powerpc/benchmarks/settings

···
+timeout=0

tools/testing/selftests/powerpc/dscr/Makefile

···
 	      dscr_inherit_test dscr_inherit_exec_test dscr_sysfs_test	\
 	      dscr_sysfs_thread_test
 
+TEST_FILES := settings
+
 top_srcdir = ../../../../..
 include ../../lib.mk
 

tools/testing/selftests/powerpc/dscr/settings

···
+timeout=0

tools/testing/selftests/powerpc/mm/.gitignore

···
 wild_bctr
 large_vm_fork_separation
 bad_accesses
+tlbie_test

tools/testing/selftests/powerpc/pmu/ebb/Makefile

···
 # The EBB handler is 64-bit code and everything links against it
 CFLAGS += -m64
 
+TMPOUT = $(OUTPUT)/
 # Toolchains may build PIE by default which breaks the assembly
 no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
         $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)

tools/testing/selftests/powerpc/signal/.gitignore

···
 signal
 signal_tm
 sigfuz
+sigreturn_vdso

tools/testing/selftests/powerpc/signal/Makefile

···
 # SPDX-License-Identifier: GPL-2.0
-TEST_GEN_PROGS := signal signal_tm sigfuz
+TEST_GEN_PROGS := signal signal_tm sigfuz sigreturn_vdso
 
 CFLAGS += -maltivec
 $(OUTPUT)/signal_tm: CFLAGS += -mhtm
 $(OUTPUT)/sigfuz: CFLAGS += -pthread -m64
+
+TEST_FILES := settings
 
 top_srcdir = ../../../../..
 include ../../lib.mk

tools/testing/selftests/powerpc/signal/settings

···
+timeout=0

tools/testing/selftests/powerpc/signal/sigreturn_vdso.c

···
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test that we can take signals with and without the VDSO mapped, which trigger
+ * different paths in the signal handling code.
+ *
+ * See handle_rt_signal64() and setup_trampoline() in signal_64.c
+ */
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <stdio.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+// Ensure assert() is not compiled out
+#undef NDEBUG
+#include <assert.h>
+
+#include "utils.h"
+
+static int search_proc_maps(char *needle, unsigned long *low, unsigned long *high)
+{
+	unsigned long start, end;
+	static char buf[4096];
+	char name[128];
+	FILE *f;
+	int rc = -1;
+
+	f = fopen("/proc/self/maps", "r");
+	if (!f) {
+		perror("fopen");
+		return -1;
+	}
+
+	while (fgets(buf, sizeof(buf), f)) {
+		rc = sscanf(buf, "%lx-%lx %*c%*c%*c%*c %*x %*d:%*d %*d %127s\n",
+			    &start, &end, name);
+		if (rc == 2)
+			continue;
+
+		if (rc != 3) {
+			printf("sscanf errored\n");
+			rc = -1;
+			break;
+		}
+
+		if (strstr(name, needle)) {
+			*low = start;
+			*high = end - 1;
+			rc = 0;
+			break;
+		}
+	}
+
+	fclose(f);
+
+	return rc;
+}
+
+static volatile sig_atomic_t took_signal = 0;
+
+static void sigusr1_handler(int sig)
+{
+	took_signal++;
+}
+
+int test_sigreturn_vdso(void)
+{
+	unsigned long low, high, size;
+	struct sigaction act;
+	char *p;
+
+	act.sa_handler = sigusr1_handler;
+	act.sa_flags = 0;
+	sigemptyset(&act.sa_mask);
+
+	assert(sigaction(SIGUSR1, &act, NULL) == 0);
+
+	// Confirm the VDSO is mapped, and work out where it is
+	assert(search_proc_maps("[vdso]", &low, &high) == 0);
+	size = high - low + 1;
+	printf("VDSO is at 0x%lx-0x%lx (%lu bytes)\n", low, high, size);
+
+	kill(getpid(), SIGUSR1);
+	assert(took_signal == 1);
+	printf("Signal delivered OK with VDSO mapped\n");
+
+	// Remap the VDSO somewhere else
+	p = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
+	assert(p != MAP_FAILED);
+	assert(mremap((void *)low, size, size, MREMAP_MAYMOVE|MREMAP_FIXED, p) != MAP_FAILED);
+	assert(search_proc_maps("[vdso]", &low, &high) == 0);
+	size = high - low + 1;
+	printf("VDSO moved to 0x%lx-0x%lx (%lu bytes)\n", low, high, size);
+
+	kill(getpid(), SIGUSR1);
+	assert(took_signal == 2);
+	printf("Signal delivered OK with VDSO moved\n");
+
+	assert(munmap((void *)low, size) == 0);
+	printf("Unmapped VDSO\n");
+
+	// Confirm the VDSO is not mapped anymore
+	assert(search_proc_maps("[vdso]", &low, &high) != 0);
+
+	// Make the stack executable
+	assert(search_proc_maps("[stack]", &low, &high) == 0);
+	size = high - low + 1;
+	mprotect((void *)low, size, PROT_READ|PROT_WRITE|PROT_EXEC);
+	printf("Remapped the stack executable\n");
+
+	kill(getpid(), SIGUSR1);
+	assert(took_signal == 3);
+	printf("Signal delivered OK with VDSO unmapped\n");
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(test_sigreturn_vdso, "sigreturn_vdso");
+}

tools/testing/selftests/powerpc/tm/.gitignore

···
 tm-signal-context-chk-vsx
 tm-signal-context-force-tm
 tm-signal-sigreturn-nt
+tm-signal-pagefault
 tm-vmx-unavail
 tm-unavailable
 tm-trap

tools/testing/selftests/powerpc/tm/Makefile

···
 TEST_GEN_PROGS := tm-resched-dscr tm-syscall tm-signal-msr-resv tm-signal-stack \
 	tm-vmxcopy tm-fork tm-tar tm-tmspr tm-vmx-unavail tm-unavailable tm-trap \
 	$(SIGNAL_CONTEXT_CHK_TESTS) tm-sigreturn tm-signal-sigreturn-nt \
-	tm-signal-context-force-tm tm-poison
+	tm-signal-context-force-tm tm-poison tm-signal-pagefault
+
+TEST_FILES := settings
 
 top_srcdir = ../../../../..
 include ../../lib.mk
···
 $(OUTPUT)/tm-unavailable: CFLAGS += -O0 -pthread -m64 -Wno-error=uninitialized -mvsx
 $(OUTPUT)/tm-trap: CFLAGS += -O0 -pthread -m64
 $(OUTPUT)/tm-signal-context-force-tm: CFLAGS += -pthread -m64
+$(OUTPUT)/tm-signal-pagefault: CFLAGS += -pthread -m64
 
 SIGNAL_CONTEXT_CHK_TESTS := $(patsubst %,$(OUTPUT)/%,$(SIGNAL_CONTEXT_CHK_TESTS))
 $(SIGNAL_CONTEXT_CHK_TESTS): tm-signal.S

tools/testing/selftests/powerpc/tm/settings

···
+timeout=0

tools/testing/selftests/powerpc/tm/tm-signal-context-force-tm.c

···
 #endif
 
 /* Setting contexts because the test will crash and we want to recover */
-ucontext_t init_context, main_context;
+ucontext_t init_context;
 
-static int count, first_time;
+/* count is changed in the signal handler, so it must be volatile */
+static volatile int count;
 
 void usr_signal_handler(int signo, siginfo_t *si, void *uc)
 {
···
 
 void seg_signal_handler(int signo, siginfo_t *si, void *uc)
 {
-	if (count == COUNT_MAX) {
-		/* Return to tm_signal_force_msr() and exit */
-		setcontext(&main_context);
-	}
-
 	count++;
 
 	/* Reexecute the test */
···
 	 */
 	getcontext(&init_context);
 
-	/* Allocated an alternative signal stack area */
-	ss.ss_sp = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE,
-			MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
-	ss.ss_size = SIGSTKSZ;
-	ss.ss_flags = 0;
+	while (count < COUNT_MAX) {
+		/* Allocated an alternative signal stack area */
+		ss.ss_sp = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE,
+				MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
+		ss.ss_size = SIGSTKSZ;
+		ss.ss_flags = 0;
 
-	if (ss.ss_sp == (void *)-1) {
-		perror("mmap error\n");
-		exit(-1);
+		if (ss.ss_sp == (void *)-1) {
+			perror("mmap error\n");
+			exit(-1);
+		}
+
+		/* Force the allocation through a page fault */
+		if (madvise(ss.ss_sp, SIGSTKSZ, MADV_DONTNEED)) {
+			perror("madvise\n");
+			exit(-1);
+		}
+
+		/*
+		 * Setting an alternative stack to generate a page fault when
+		 * the signal is raised.
+		 */
+		if (sigaltstack(&ss, NULL)) {
+			perror("sigaltstack\n");
+			exit(-1);
+		}
+
+		/* The signal handler will enable MSR_TS */
+		sigaction(SIGUSR1, &usr_sa, NULL);
+		/* If it does not crash, it might segfault, avoid it to retest */
+		sigaction(SIGSEGV, &seg_sa, NULL);
+
+		raise(SIGUSR1);
+		count++;
 	}
-
-	/* Force the allocation through a page fault */
-	if (madvise(ss.ss_sp, SIGSTKSZ, MADV_DONTNEED)) {
-		perror("madvise\n");
-		exit(-1);
-	}
-
-	/* Setting an alternative stack to generate a page fault when
-	 * the signal is raised.
-	 */
-	if (sigaltstack(&ss, NULL)) {
-		perror("sigaltstack\n");
-		exit(-1);
-	}
-
-	/* The signal handler will enable MSR_TS */
-	sigaction(SIGUSR1, &usr_sa, NULL);
-	/* If it does not crash, it will segfault, avoid it to retest */
-	sigaction(SIGSEGV, &seg_sa, NULL);
-
-	raise(SIGUSR1);
 }
 
 int tm_signal_context_force_tm(void)
···
 	 */
 	SKIP_IF(!is_ppc64le());
 
-	/* Will get back here after COUNT_MAX interactions */
-	getcontext(&main_context);
-
-	if (!first_time++)
-		tm_trap_test();
+	tm_trap_test();
 
 	return EXIT_SUCCESS;
 }

tools/testing/selftests/powerpc/tm/tm-signal-pagefault.c

···
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2020, Gustavo Luiz Duarte, IBM Corp.
+ *
+ * This test starts a transaction and triggers a signal, forcing a pagefault to
+ * happen when the kernel signal handling code touches the user signal stack.
+ *
+ * In order to avoid pre-faulting the signal stack memory and to force the
+ * pagefault to happen precisely in the kernel signal handling code, the
+ * pagefault handling is done in userspace using the userfaultfd facility.
+ *
+ * Further pagefaults are triggered by crafting the signal handler's ucontext
+ * to point to additional memory regions managed by the userfaultfd, so using
+ * the same mechanism used to avoid pre-faulting the signal stack memory.
+ *
+ * On failure (bug is present) kernel crashes or never returns control back to
+ * userspace. If bug is not present, tests completes almost immediately.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/userfaultfd.h>
+#include <poll.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+#include <fcntl.h>
+#include <sys/mman.h>
+#include <pthread.h>
+#include <signal.h>
+#include <errno.h>
+
+#include "tm.h"
+
+
+#define UF_MEM_SIZE 655360	/* 10 x 64k pages */
+
+/* Memory handled by userfaultfd */
+static char *uf_mem;
+static size_t uf_mem_offset = 0;
+
+/*
+ * Data that will be copied into the faulting pages (instead of zero-filled
+ * pages). This is used to make the test more reliable and avoid segfaulting
+ * when we return from the signal handler. Since we are making the signal
+ * handler's ucontext point to newly allocated memory, when that memory is
+ * paged-in it will contain the expected content.
+ */
+static char backing_mem[UF_MEM_SIZE];
+
+static size_t pagesize;
+
+/*
+ * Return a chunk of at least 'size' bytes of memory that will be handled by
+ * userfaultfd. If 'backing_data' is not NULL, its content will be save to
+ * 'backing_mem' and then copied into the faulting pages when the page fault
+ * is handled.
+ */
+void *get_uf_mem(size_t size, void *backing_data)
+{
+	void *ret;
+
+	if (uf_mem_offset + size > UF_MEM_SIZE) {
+		fprintf(stderr, "Requesting more uf_mem than expected!\n");
+		exit(EXIT_FAILURE);
+	}
+
+	ret = &uf_mem[uf_mem_offset];
+
+	/* Save the data that will be copied into the faulting page */
+	if (backing_data != NULL)
+		memcpy(&backing_mem[uf_mem_offset], backing_data, size);
+
+	/* Reserve the requested amount of uf_mem */
+	uf_mem_offset += size;
+	/* Keep uf_mem_offset aligned to the page size (round up) */
+	uf_mem_offset = (uf_mem_offset + pagesize - 1) & ~(pagesize - 1);
+
+	return ret;
+}
+
+void *fault_handler_thread(void *arg)
+{
+	struct uffd_msg msg;	/* Data read from userfaultfd */
+	long uffd;		/* userfaultfd file descriptor */
+	struct uffdio_copy uffdio_copy;
+	struct pollfd pollfd;
+	ssize_t nread, offset;
+
+	uffd = (long) arg;
+
+	for (;;) {
+		pollfd.fd = uffd;
+		pollfd.events = POLLIN;
+		if (poll(&pollfd, 1, -1) == -1) {
+			perror("poll() failed");
+			exit(EXIT_FAILURE);
+		}
+
+		nread = read(uffd, &msg, sizeof(msg));
+		if (nread == 0) {
+			fprintf(stderr, "read(): EOF on userfaultfd\n");
+			exit(EXIT_FAILURE);
+		}
+
+		if (nread == -1) {
+			perror("read() failed");
+			exit(EXIT_FAILURE);
+		}
+
+		/* We expect only one kind of event */
+		if (msg.event != UFFD_EVENT_PAGEFAULT) {
+			fprintf(stderr, "Unexpected event on userfaultfd\n");
+			exit(EXIT_FAILURE);
+		}
+
+		/*
+		 * We need to handle page faults in units of pages(!).
+		 * So, round faulting address down to page boundary.
+		 */
+		uffdio_copy.dst = msg.arg.pagefault.address & ~(pagesize-1);
+
+		offset = (char *) uffdio_copy.dst - uf_mem;
+		uffdio_copy.src = (unsigned long) &backing_mem[offset];
+
+		uffdio_copy.len = pagesize;
+		uffdio_copy.mode = 0;
+		uffdio_copy.copy = 0;
+		if (ioctl(uffd, UFFDIO_COPY, &uffdio_copy) == -1) {
+			perror("ioctl-UFFDIO_COPY failed");
+			exit(EXIT_FAILURE);
+		}
+	}
+}
+
+void setup_uf_mem(void)
+{
+	long uffd;		/* userfaultfd file descriptor */
+	pthread_t thr;
+	struct uffdio_api uffdio_api;
+	struct uffdio_register uffdio_register;
+	int ret;
+
+	pagesize = sysconf(_SC_PAGE_SIZE);
+
+	/* Create and enable userfaultfd object */
+	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
+	if (uffd == -1) {
+		perror("userfaultfd() failed");
+		exit(EXIT_FAILURE);
+	}
+	uffdio_api.api = UFFD_API;
+	uffdio_api.features = 0;
+	if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) {
+		perror("ioctl-UFFDIO_API failed");
+		exit(EXIT_FAILURE);
+	}
+
+	/*
+	 * Create a private anonymous mapping. The memory will be demand-zero
+	 * paged, that is, not yet allocated. When we actually touch the memory
+	 * the related page will be allocated via the userfaultfd mechanism.
+	 */
+	uf_mem = mmap(NULL, UF_MEM_SIZE, PROT_READ | PROT_WRITE,
+		      MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	if (uf_mem == MAP_FAILED) {
+		perror("mmap() failed");
+		exit(EXIT_FAILURE);
+	}
+
+	/*
+	 * Register the memory range of the mapping we've just mapped to be
+	 * handled by the userfaultfd object. In 'mode' we request to track
+	 * missing pages (i.e. pages that have not yet been faulted-in).
+	 */
+	uffdio_register.range.start = (unsigned long) uf_mem;
+	uffdio_register.range.len = UF_MEM_SIZE;
+	uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
+	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) {
+		perror("ioctl-UFFDIO_REGISTER");
+		exit(EXIT_FAILURE);
+	}
+
+	/* Create a thread that will process the userfaultfd events */
+	ret = pthread_create(&thr, NULL, fault_handler_thread, (void *) uffd);
+	if (ret != 0) {
+		fprintf(stderr, "pthread_create(): Error. Returned %d\n", ret);
+		exit(EXIT_FAILURE);
+	}
+}
+
+/*
+ * Assumption: the signal was delivered while userspace was in transactional or
+ * suspended state, i.e. uc->uc_link != NULL.
+ */
+void signal_handler(int signo, siginfo_t *si, void *uc)
+{
+	ucontext_t *ucp = uc;
+
+	/* Skip 'trap' after returning, otherwise we get a SIGTRAP again */
+	ucp->uc_link->uc_mcontext.regs->nip += 4;
+
+	ucp->uc_mcontext.v_regs =
+		get_uf_mem(sizeof(elf_vrreg_t), ucp->uc_mcontext.v_regs);
+
+	ucp->uc_link->uc_mcontext.v_regs =
+		get_uf_mem(sizeof(elf_vrreg_t), ucp->uc_link->uc_mcontext.v_regs);
+
+	ucp->uc_link = get_uf_mem(sizeof(ucontext_t), ucp->uc_link);
+}
+
+bool have_userfaultfd(void)
+{
+	long rc;
+
+	errno = 0;
+	rc = syscall(__NR_userfaultfd, -1);
+
+	return rc == 0 || errno != ENOSYS;
+}
+
+int tm_signal_pagefault(void)
+{
+	struct sigaction sa;
+	stack_t ss;
+
+	SKIP_IF(!have_htm());
+	SKIP_IF(!have_userfaultfd());
+
+	setup_uf_mem();
+
+	/*
+	 * Set an alternative stack that will generate a page fault when the
+	 * signal is raised. The page fault will be treated via userfaultfd,
+	 * i.e. via fault_handler_thread.
+	 */
+	ss.ss_sp = get_uf_mem(SIGSTKSZ, NULL);
+	ss.ss_size = SIGSTKSZ;
+	ss.ss_flags = 0;
+	if (sigaltstack(&ss, NULL) == -1) {
+		perror("sigaltstack() failed");
+		exit(EXIT_FAILURE);
+	}
+
+	sa.sa_flags = SA_SIGINFO | SA_ONSTACK;
+	sa.sa_sigaction = signal_handler;
+	if (sigaction(SIGTRAP, &sa, NULL) == -1) {
+		perror("sigaction() failed");
+		exit(EXIT_FAILURE);
+	}
+
+	/* Trigger a SIGTRAP in transactional state */
+	asm __volatile__(
+			"tbegin.;"
+			"beq    1f;"
+			"trap;"
+			"1: ;"
+			: : : "memory");
+
+	/* Trigger a SIGTRAP in suspended state */
+	asm __volatile__(
+			"tbegin.;"
+			"beq    1f;"
+			"tsuspend.;"
+			"trap;"
+			"tresume.;"
+			"1: ;"
+			: : : "memory");
+
+	return EXIT_SUCCESS;
+}
+
+int main(int argc, char **argv)
+{
+	/*
+	 * Depending on kernel config, the TM Bad Thing might not result in a
+	 * crash, instead the kernel never returns control back to userspace, so
+	 * set a tight timeout. If the test passes it completes almost
+	 * immediately.
+	 */
+	test_harness_set_timeout(2);
+	return test_harness(tm_signal_pagefault, "tm_signal_pagefault");
+}