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
  ...

56 files changed, 6565 insertions, 5516 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 78a1b22d4fd8..570660efbb3d 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -3,8 +3,6 @@
 # Makefile for the linux kernel.
 #
 
-CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
-
 ifdef CONFIG_PPC64
 CFLAGS_prom_init.o	+= $(NO_MINIMAL_TOC)
 endif
@@ -41,16 +39,17 @@ CFLAGS_cputable.o += -DDISABLE_BRANCH_PROFILING
 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
diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c
index 6dfceaa820e4..f57712a55815 100644
--- a/arch/powerpc/kernel/btext.c
+++ b/arch/powerpc/kernel/btext.c
@@ -26,7 +26,7 @@
 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;
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 245be4fafe13..13eba2eb46fe 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -2198,7 +2198,6 @@ static struct cpu_spec * __init setup_cpu_spec(unsigned long offset,
 		 */
 		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;
 		}
 	}
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 182b4047c1ef..36bc0d5c4f3a 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -139,7 +139,6 @@ static void __init cpufeatures_setup_cpu(void)
 	/* 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);
 	}
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 17cb3e9b5697..7cdcb413bb44 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1107,87 +1107,43 @@ static int eeh_init(void)
 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)
+	pr_debug("EEH: Adding device %s\n", pci_name(dev));
+
+	/*
+	 * 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;
+	}
 
-	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");
+	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);
@@ -1198,69 +1154,16 @@ void eeh_add_device_late(struct pci_dev *dev)
 		 * 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
  * @dev: pci device to be removed
  *
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 16af0d8d90a8..a6371fb8f761 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -246,9 +246,8 @@ reenable_mmu:
 	 * 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)
@@ -262,16 +261,12 @@ reenable_mmu:
 	 * 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 */
@@ -575,6 +570,33 @@ syscall_exit_work:
 	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
  * the child process. Therefore we need to save all the nonvolatile
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 6ba675b0cf7d..63f0a4414618 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -16,6 +16,7 @@
 
 #include <linux/errno.h>
 #include <linux/err.h>
+#include <asm/cache.h>
 #include <asm/unistd.h>
 #include <asm/processor.h>
 #include <asm/page.h>
@@ -69,6 +70,7 @@ BEGIN_FTR_SECTION
 	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)
@@ -76,342 +78,122 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
 	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 */
-
-	/*
-	 * 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
-	 */
-#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
-
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	1
-#else
-	li	r11,MSR_RI
-	ori	r11,r11,MSR_EE
-	mtmsrd	r11,1
-#endif /* CONFIG_PPC_BOOK3E */
-
-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
+	std	r11,-16(r10)		/* "regshere" marker */
 
-.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.
+	 * 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().
 	 */
+	li	r11,IRQS_ALL_DISABLED
+	li	r12,PACA_IRQ_HARD_DIS
+	stb	r11,PACAIRQSOFTMASK(r13)
+	stb	r12,PACAIRQHAPPENED(r13)
 
-	ldx	r12,r11,r0	/* Fetch system call handler [ptr] */
-	mtctr   r12
-	bctrl			/* Call handler */
+	/* Calling convention has r9 = orig r0, r10 = regs */
+	mr	r9,r0
+	bl	system_call_exception
 
-	/* syscall_exit can exit to kernel mode, via ret_from_kernel_thread */
 .Lsyscall_exit:
-	std	r3,RESULT(r1)
-
-#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	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 */
+	addi    r4,r1,STACK_FRAME_OVERHEAD
+	bl	syscall_exit_prepare
 
-	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
+	ld	r2,_CCR(r1)
+	ld	r4,_NIP(r1)
+	ld	r5,_MSR(r1)
+	ld	r6,_LINK(r1)
 
-	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)