Merge tag 'powerpc-4.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "This was delayed a day or two by some build-breakage on old toolchains
  which we've now fixed.

  There's two PCI commits both acked by Bjorn.

  There's one commit to mm/hugepage.c which is (co)authored by Kirill.

  Highlights:
   - Restructure Linux PTE on Book3S/64 to Radix format from Paul
     Mackerras
   - Book3s 64 MMU cleanup in preparation for Radix MMU from Aneesh
     Kumar K.V
   - Add POWER9 cputable entry from Michael Neuling
   - FPU/Altivec/VSX save/restore optimisations from Cyril Bur
   - Add support for new ftrace ABI on ppc64le from Torsten Duwe

  Various cleanups & minor fixes from:
   - Adam Buchbinder, Andrew Donnellan, Balbir Singh, Christophe Leroy,
     Cyril Bur, Luis Henriques, Madhavan Srinivasan, Pan Xinhui, Russell
     Currey, Sukadev Bhattiprolu, Suraj Jitindar Singh.

  General:
   - atomics: Allow architectures to define their own __atomic_op_*
     helpers from Boqun Feng
   - Implement atomic{, 64}_*_return_* variants and acquire/release/
     relaxed variants for (cmp)xchg from Boqun Feng
   - Add powernv_defconfig from Jeremy Kerr
   - Fix BUG_ON() reporting in real mode from Balbir Singh
   - Add xmon command to dump OPAL msglog from Andrew Donnellan
   - Add xmon command to dump process/task similar to ps(1) from Douglas
     Miller
   - Clean up memory hotplug failure paths from David Gibson

  pci/eeh:
   - Redesign SR-IOV on PowerNV to give absolute isolation between VFs
     from Wei Yang.
   - EEH Support for SRIOV VFs from Wei Yang and Gavin Shan.
   - PCI/IOV: Rename and export virtfn_{add, remove} from Wei Yang
   - PCI: Add pcibios_bus_add_device() weak function from Wei Yang
   - MAINTAINERS: Update EEH details and maintainership from Russell
     Currey

  cxl:
   - Support added to the CXL driver for running on both bare-metal and
     hypervisor systems, from Christophe Lombard and Frederic Barrat.
   - Ignore probes for virtual afu pci devices from Vaibhav Jain

  perf:
   - Export Power8 generic and cache events to sysfs from Sukadev
     Bhattiprolu
   - hv-24x7: Fix usage with chip events, display change in counter
     values, display domain indices in sysfs, eliminate domain suffix in
     event names, from Sukadev Bhattiprolu

  Freescale:
   - Updates from Scott: "Highlights include 8xx optimizations, 32-bit
     checksum optimizations, 86xx consolidation, e5500/e6500 cpu
     hotplug, more fman and other dt bits, and minor fixes/cleanup"

* tag 'powerpc-4.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (179 commits)
  powerpc: Fix unrecoverable SLB miss during restore_math()
  powerpc/8xx: Fix do_mtspr_cpu6() build on older compilers
  powerpc/rcpm: Fix build break when SMP=n
  powerpc/book3e-64: Use hardcoded mttmr opcode
  powerpc/fsl/dts: Add "jedec,spi-nor" flash compatible
  powerpc/T104xRDB: add tdm riser card node to device tree
  powerpc32: PAGE_EXEC required for inittext
  powerpc/mpc85xx: Add pcsphy nodes to FManV3 device tree
  powerpc/mpc85xx: Add MDIO bus muxing support to the board device tree(s)
  powerpc/86xx: Introduce and use common dtsi
  powerpc/86xx: Update device tree
  powerpc/86xx: Move dts files to fsl directory
  powerpc/86xx: Switch to kconfig fragments approach
  powerpc/86xx: Update defconfigs
  powerpc/86xx: Consolidate common platform code
  powerpc32: Remove one insn in mulhdu
  powerpc32: small optimisation in flush_icache_range()
  powerpc: Simplify test in __dma_sync()
  powerpc32: move xxxxx_dcache_range() functions inline
  powerpc32: Remove clear_pages() and define clear_page() inline
  ...

1 files changed, 95 insertions, 37 deletions

diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 44d4d8e..9dac18da 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -61,8 +61,11 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new)
 		return -EFAULT;
 
 	/* Make sure it is what we expect it to be */
-	if (replaced != old)
+	if (replaced != old) {
+		pr_err("%p: replaced (%#x) != old (%#x)",
+		(void *)ip, replaced, old);
 		return -EINVAL;
+	}
 
 	/* replace the text with the new text */
 	if (patch_instruction((unsigned int *)ip, new))
@@ -106,14 +109,15 @@ static int
 __ftrace_make_nop(struct module *mod,
 		  struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned int op;
-	unsigned long entry, ptr;
+	unsigned long entry, ptr, tramp;
 	unsigned long ip = rec->ip;
-	void *tramp;
+	unsigned int op, pop;
 
 	/* read where this goes */
-	if (probe_kernel_read(&op, (void *)ip, sizeof(int)))
+	if (probe_kernel_read(&op, (void *)ip, sizeof(int))) {
+		pr_err("Fetching opcode failed.\n");
 		return -EFAULT;
+	}
 
 	/* Make sure that that this is still a 24bit jump */
 	if (!is_bl_op(op)) {
@@ -122,14 +126,9 @@ __ftrace_make_nop(struct module *mod,
 	}
 
 	/* lets find where the pointer goes */
-	tramp = (void *)find_bl_target(ip, op);
-
-	pr_devel("ip:%lx jumps to %p", ip, tramp);
+	tramp = find_bl_target(ip, op);
 
-	if (!is_module_trampoline(tramp)) {
-		pr_err("Not a trampoline\n");
-		return -EINVAL;
-	}
+	pr_devel("ip:%lx jumps to %lx", ip, tramp);
 
 	if (module_trampoline_target(mod, tramp, &ptr)) {
 		pr_err("Failed to get trampoline target\n");
@@ -158,10 +157,42 @@ __ftrace_make_nop(struct module *mod,
 	 *
 	 * Use a b +8 to jump over the load.
 	 */
-	op = 0x48000008;	/* b +8 */
 
-	if (patch_instruction((unsigned int *)ip, op))
+	pop = PPC_INST_BRANCH | 8;	/* b +8 */
+
+	/*
+	 * Check what is in the next instruction. We can see ld r2,40(r1), but
+	 * on first pass after boot we will see mflr r0.
+	 */
+	if (probe_kernel_read(&op, (void *)(ip+4), MCOUNT_INSN_SIZE)) {
+		pr_err("Fetching op failed.\n");
+		return -EFAULT;
+	}
+
+	if (op != PPC_INST_LD_TOC) {
+		unsigned int inst;
+
+		if (probe_kernel_read(&inst, (void *)(ip - 4), 4)) {
+			pr_err("Fetching instruction at %lx failed.\n", ip - 4);
+			return -EFAULT;
+		}
+
+		/* We expect either a mlfr r0, or a std r0, LRSAVE(r1) */
+		if (inst != PPC_INST_MFLR && inst != PPC_INST_STD_LR) {
+			pr_err("Unexpected instructions around bl _mcount\n"
+			       "when enabling dynamic ftrace!\t"
+			       "(%08x,bl,%08x)\n", inst, op);
+			return -EINVAL;
+		}
+
+		/* When using -mkernel_profile there is no load to jump over */
+		pop = PPC_INST_NOP;
+	}
+
+	if (patch_instruction((unsigned int *)ip, pop)) {
+		pr_err("Patching NOP failed.\n");
 		return -EPERM;
+	}
 
 	return 0;
 }
@@ -287,16 +318,15 @@ int ftrace_make_nop(struct module *mod,
 
 #ifdef CONFIG_MODULES
 #ifdef CONFIG_PPC64
+/*
+ * Examine the existing instructions for __ftrace_make_call.
+ * They should effectively be a NOP, and follow formal constraints,
+ * depending on the ABI. Return false if they don't.
+ */
+#ifndef CC_USING_MPROFILE_KERNEL
 static int
-__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+expected_nop_sequence(void *ip, unsigned int op0, unsigned int op1)
 {
-	unsigned int op[2];
-	void *ip = (void *)rec->ip;
-
-	/* read where this goes */
-	if (probe_kernel_read(op, ip, sizeof(op)))
-		return -EFAULT;
-
 	/*
 	 * We expect to see:
 	 *
@@ -306,8 +336,34 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	 * The load offset is different depending on the ABI. For simplicity
 	 * just mask it out when doing the compare.
 	 */
-	if ((op[0] != 0x48000008) || ((op[1] & 0xffff0000) != 0xe8410000)) {
-		pr_err("Unexpected call sequence: %x %x\n", op[0], op[1]);
+	if ((op0 != 0x48000008) || ((op1 & 0xffff0000) != 0xe8410000))
+		return 0;
+	return 1;
+}
+#else
+static int
+expected_nop_sequence(void *ip, unsigned int op0, unsigned int op1)
+{
+	/* look for patched "NOP" on ppc64 with -mprofile-kernel */
+	if (op0 != PPC_INST_NOP)
+		return 0;
+	return 1;
+}
+#endif
+
+static int
+__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned int op[2];
+	void *ip = (void *)rec->ip;
+
+	/* read where this goes */
+	if (probe_kernel_read(op, ip, sizeof(op)))
+		return -EFAULT;
+
+	if (!expected_nop_sequence(ip, op[0], op[1])) {
+		pr_err("Unexpected call sequence at %p: %x %x\n",
+		ip, op[0], op[1]);
 		return -EINVAL;
 	}
 
@@ -330,7 +386,16 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	return 0;
 }
-#else
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+			unsigned long addr)
+{
+	return ftrace_make_call(rec, addr);
+}
+#endif
+
+#else  /* !CONFIG_PPC64: */
 static int
 __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
@@ -455,20 +520,13 @@ void ftrace_replace_code(int enable)
 	}
 }
 
+/*
+ * Use the default ftrace_modify_all_code, but without
+ * stop_machine().
+ */
 void arch_ftrace_update_code(int command)
 {
-	if (command & FTRACE_UPDATE_CALLS)
-		ftrace_replace_code(1);
-	else if (command & FTRACE_DISABLE_CALLS)
-		ftrace_replace_code(0);
-
-	if (command & FTRACE_UPDATE_TRACE_FUNC)
-		ftrace_update_ftrace_func(ftrace_trace_function);
-
-	if (command & FTRACE_START_FUNC_RET)
-		ftrace_enable_ftrace_graph_caller();
-	else if (command & FTRACE_STOP_FUNC_RET)
-		ftrace_disable_ftrace_graph_caller();
+	ftrace_modify_all_code(command);
 }
 
 int __init ftrace_dyn_arch_init(void)