Merge tag 'powerpc-4.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "A bit of a small release, I suspect in part due to me travelling for
  KS. But my backlog of patches to review is smaller than usual, so I
  think in part folks just didn't send as much this cycle.

  Non-highlights:

   - Five fixes for the >128T address space handling, both to fix bugs
     in our implementation and to bring the semantics exactly into line
     with x86.

  Highlights:

   - Support for a new OPAL call on bare metal machines which gives us a
     true NMI (ie. is not masked by MSR[EE]=0) for debugging etc.

   - Support for Power9 DD2 in the CXL driver.

   - Improvements to machine check handling so that uncorrectable errors
     can be reported into the generic memory_failure() machinery.

   - Some fixes and improvements for VPHN, which is used under PowerVM
     to notify the Linux partition of topology changes.

   - Plumbing to enable TM (transactional memory) without suspend on
     some Power9 processors (PPC_FEATURE2_HTM_NO_SUSPEND).

   - Support for emulating vector loads form cache-inhibited memory, on
     some Power9 revisions.

   - Disable the fast-endian switch "syscall" by default (behind a
     CONFIG), we believe it has never had any users.

   - A major rework of the API drivers use when initiating and waiting
     for long running operations performed by OPAL firmware, and changes
     to the powernv_flash driver to use the new API.

   - Several fixes for the handling of FP/VMX/VSX while processes are
     using transactional memory.

   - Optimisations of TLB range flushes when using the radix MMU on
     Power9.

   - Improvements to the VAS facility used to access coprocessors on
     Power9, and related improvements to the way the NX crypto driver
     handles requests.

   - Implementation of PMEM_API and UACCESS_FLUSHCACHE for 64-bit.

  Thanks to: Alexey Kardashevskiy, Alistair Popple, Allen Pais, Andrew
  Donnellan, Aneesh Kumar K.V, Arnd Bergmann, Balbir Singh, Benjamin
  Herrenschmidt, Breno Leitao, Christophe Leroy, Christophe Lombard,
  Cyril Bur, Frederic Barrat, Gautham R. Shenoy, Geert Uytterhoeven,
  Guilherme G. Piccoli, Gustavo Romero, Haren Myneni, Joel Stanley,
  Kamalesh Babulal, Kautuk Consul, Markus Elfring, Masami Hiramatsu,
  Michael Bringmann, Michael Neuling, Michal Suchanek, Naveen N. Rao,
  Nicholas Piggin, Oliver O'Halloran, Paul Mackerras, Pedro Miraglia
  Franco de Carvalho, Philippe Bergheaud, Sandipan Das, Seth Forshee,
  Shriya, Stephen Rothwell, Stewart Smith, Sukadev Bhattiprolu, Tyrel
  Datwyler, Vaibhav Jain, Vaidyanathan Srinivasan, and William A.
  Kennington III"

* tag 'powerpc-4.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (151 commits)
  powerpc/64s: Fix Power9 DD2.0 workarounds by adding DD2.1 feature
  powerpc/64s: Fix masking of SRR1 bits on instruction fault
  powerpc/64s: mm_context.addr_limit is only used on hash
  powerpc/64s/radix: Fix 128TB-512TB virtual address boundary case allocation
  powerpc/64s/hash: Allow MAP_FIXED allocations to cross 128TB boundary
  powerpc/64s/hash: Fix fork() with 512TB process address space
  powerpc/64s/hash: Fix 128TB-512TB virtual address boundary case allocation
  powerpc/64s/hash: Fix 512T hint detection to use >= 128T
  powerpc: Fix DABR match on hash based systems
  powerpc/signal: Properly handle return value from uprobe_deny_signal()
  powerpc/fadump: use kstrtoint to handle sysfs store
  powerpc/lib: Implement UACCESS_FLUSHCACHE API
  powerpc/lib: Implement PMEM API
  powerpc/powernv/npu: Don't explicitly flush nmmu tlb
  powerpc/powernv/npu: Use flush_all_mm() instead of flush_tlb_mm()
  powerpc/powernv/idle: Round up latency and residency values
  powerpc/kprobes: refactor kprobe_lookup_name for safer string operations
  powerpc/kprobes: Blacklist emulate_update_regs() from kprobes
  powerpc/kprobes: Do not disable interrupts for optprobes and kprobes_on_ftrace
  powerpc/kprobes: Disable preemption before invoking probe handler for optprobes
  ...

arch/powerpc/lib/Makefile

@@ -24,7 +24,7 @@ endif
 
 obj64-y	+= copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
 	   copyuser_power7.o string_64.o copypage_power7.o memcpy_power7.o \
-	   memcpy_64.o memcmp_64.o
+	   memcpy_64.o memcmp_64.o pmem.o
 
 obj64-$(CONFIG_SMP)	+= locks.o
 obj64-$(CONFIG_ALTIVEC)	+= vmx-helper.o

arch/powerpc/lib/pmem.c

@@ -0,0 +1,67 @@
+/*
+ * Copyright(c) 2017 IBM Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/string.h>
+#include <linux/export.h>
+#include <linux/uaccess.h>
+
+#include <asm/cacheflush.h>
+
+/*
+ * CONFIG_ARCH_HAS_PMEM_API symbols
+ */
+void arch_wb_cache_pmem(void *addr, size_t size)
+{
+	unsigned long start = (unsigned long) addr;
+	flush_inval_dcache_range(start, start + size);
+}
+EXPORT_SYMBOL(arch_wb_cache_pmem);
+
+void arch_invalidate_pmem(void *addr, size_t size)
+{
+	unsigned long start = (unsigned long) addr;
+	flush_inval_dcache_range(start, start + size);
+}
+EXPORT_SYMBOL(arch_invalidate_pmem);
+
+/*
+ * CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE symbols
+ */
+long __copy_from_user_flushcache(void *dest, const void __user *src,
+		unsigned size)
+{
+	unsigned long copied, start = (unsigned long) dest;
+
+	copied = __copy_from_user(dest, src, size);
+	flush_inval_dcache_range(start, start + size);
+
+	return copied;
+}
+
+void *memcpy_flushcache(void *dest, const void *src, size_t size)
+{
+	unsigned long start = (unsigned long) dest;
+
+	memcpy(dest, src, size);
+	flush_inval_dcache_range(start, start + size);
+
+	return dest;
+}
+EXPORT_SYMBOL(memcpy_flushcache);
+
+void memcpy_page_flushcache(char *to, struct page *page, size_t offset,
+	size_t len)
+{
+	memcpy_flushcache(to, page_to_virt(page) + offset, len);
+}
+EXPORT_SYMBOL(memcpy_page_flushcache);

arch/powerpc/lib/sstep.c

@@ -31,6 +31,8 @@ extern char system_call_common[];
 #define XER_SO		0x80000000U
 #define XER_OV		0x40000000U
 #define XER_CA		0x20000000U
+#define XER_OV32	0x00080000U
+#define XER_CA32	0x00040000U
 
 #ifdef CONFIG_PPC_FPU
 /*
@@ -962,6 +964,16 @@ static nokprobe_inline void set_cr0(const struct pt_regs *regs,
 		op->ccval |= 0x20000000;
 }
 
+static nokprobe_inline void set_ca32(struct instruction_op *op, bool val)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		if (val)
+			op->xerval |= XER_CA32;
+		else
+			op->xerval &= ~XER_CA32;
+	}
+}
+
 static nokprobe_inline void add_with_carry(const struct pt_regs *regs,
 				     struct instruction_op *op, int rd,
 				     unsigned long val1, unsigned long val2,
@@ -985,6 +997,9 @@ static nokprobe_inline void add_with_carry(const struct pt_regs *regs,
 		op->xerval |= XER_CA;
 	else
 		op->xerval &= ~XER_CA;
+
+	set_ca32(op, (unsigned int)val < (unsigned int)val1 ||
+			(carry_in && (unsigned int)val == (unsigned int)val1));
 }
 
 static nokprobe_inline void do_cmp_signed(const struct pt_regs *regs,
@@ -1791,6 +1806,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 				op->xerval |= XER_CA;
 			else
 				op->xerval &= ~XER_CA;
+			set_ca32(op, op->xerval & XER_CA);
 			goto logical_done;
 
 		case 824:	/* srawi */
@@ -1803,6 +1819,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 				op->xerval |= XER_CA;
 			else
 				op->xerval &= ~XER_CA;
+			set_ca32(op, op->xerval & XER_CA);
 			goto logical_done;
 
 #ifdef __powerpc64__
@@ -1832,6 +1849,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 				op->xerval |= XER_CA;
 			else
 				op->xerval &= ~XER_CA;
+			set_ca32(op, op->xerval & XER_CA);
 			goto logical_done;
 
 		case 826:	/* sradi with sh_5 = 0 */
@@ -1845,6 +1863,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs,
 				op->xerval |= XER_CA;
 			else
 				op->xerval &= ~XER_CA;
+			set_ca32(op, op->xerval & XER_CA);
 			goto logical_done;
 #endif /* __powerpc64__ */
 
@@ -2698,6 +2717,7 @@ void emulate_update_regs(struct pt_regs *regs, struct instruction_op *op)
 	}
 	regs->nip = next_pc;
 }
+NOKPROBE_SYMBOL(emulate_update_regs);
 
 /*
  * Emulate a previously-analysed load or store instruction.