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, 151 insertions, 17 deletions

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 3c5736e..612df30 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -133,6 +133,16 @@ void __msr_check_and_clear(unsigned long bits)
 EXPORT_SYMBOL(__msr_check_and_clear);
 
 #ifdef CONFIG_PPC_FPU
+void __giveup_fpu(struct task_struct *tsk)
+{
+	save_fpu(tsk);
+	tsk->thread.regs->msr &= ~MSR_FP;
+#ifdef CONFIG_VSX
+	if (cpu_has_feature(CPU_FTR_VSX))
+		tsk->thread.regs->msr &= ~MSR_VSX;
+#endif
+}
+
 void giveup_fpu(struct task_struct *tsk)
 {
 	check_if_tm_restore_required(tsk);
@@ -187,9 +197,32 @@ void enable_kernel_fp(void)
 	}
 }
 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)
+{
+	save_altivec(tsk);
+	tsk->thread.regs->msr &= ~MSR_VEC;
+#ifdef CONFIG_VSX
+	if (cpu_has_feature(CPU_FTR_VSX))
+		tsk->thread.regs->msr &= ~MSR_VSX;
+#endif
+}
+
 void giveup_altivec(struct task_struct *tsk)
 {
 	check_if_tm_restore_required(tsk);
@@ -229,22 +262,49 @@ void flush_altivec_to_thread(struct task_struct *tsk)
 	}
 }
 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
-void giveup_vsx(struct task_struct *tsk)
+static void __giveup_vsx(struct task_struct *tsk)
 {
-	check_if_tm_restore_required(tsk);
-
-	msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX);
 	if (tsk->thread.regs->msr & MSR_FP)
 		__giveup_fpu(tsk);
 	if (tsk->thread.regs->msr & MSR_VEC)
 		__giveup_altivec(tsk);
+	tsk->thread.regs->msr &= ~MSR_VSX;
+}
+
+static void giveup_vsx(struct task_struct *tsk)
+{
+	check_if_tm_restore_required(tsk);
+
+	msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX);
 	__giveup_vsx(tsk);
 	msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX);
 }
-EXPORT_SYMBOL(giveup_vsx);
+
+static void save_vsx(struct task_struct *tsk)
+{
+	if (tsk->thread.regs->msr & MSR_FP)
+		save_fpu(tsk);
+	if (tsk->thread.regs->msr & MSR_VEC)
+		save_altivec(tsk);
+}
 
 void enable_kernel_vsx(void)
 {
@@ -275,6 +335,19 @@ void flush_vsx_to_thread(struct task_struct *tsk)
 	}
 }
 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; }
+static inline void save_vsx(struct task_struct *tsk) { }
 #endif /* CONFIG_VSX */
 
 #ifdef CONFIG_SPE
@@ -374,12 +447,76 @@ void giveup_all(struct task_struct *tsk)
 }
 EXPORT_SYMBOL(giveup_all);
 
+void restore_math(struct pt_regs *regs)
+{
+	unsigned long msr;
+
+	if (!current->thread.load_fp && !loadvec(current->thread))
+		return;
+
+	msr = regs->msr;
+	msr_check_and_set(msr_all_available);
+
+	/*
+	 * Only reload if the bit is not set in the user MSR, the bit BEING set
+	 * indicates that the registers are hot
+	 */
+	if ((!(msr & MSR_FP)) && restore_fp(current))
+		msr |= MSR_FP | current->thread.fpexc_mode;
+
+	if ((!(msr & MSR_VEC)) && restore_altivec(current))
+		msr |= MSR_VEC;
+
+	if ((msr & (MSR_FP | MSR_VEC)) == (MSR_FP | MSR_VEC) &&
+			restore_vsx(current)) {
+		msr |= MSR_VSX;
+	}
+
+	msr_check_and_clear(msr_all_available);
+
+	regs->msr = msr;
+}
+
+void save_all(struct task_struct *tsk)
+{
+	unsigned long usermsr;
+
+	if (!tsk->thread.regs)
+		return;
+
+	usermsr = tsk->thread.regs->msr;
+
+	if ((usermsr & msr_all_available) == 0)
+		return;
+
+	msr_check_and_set(msr_all_available);
+
+	/*
+	 * Saving the way the register space is in hardware, save_vsx boils
+	 * down to a save_fpu() and save_altivec()
+	 */
+	if (usermsr & MSR_VSX) {
+		save_vsx(tsk);
+	} else {
+		if (usermsr & MSR_FP)
+			save_fpu(tsk);
+
+		if (usermsr & MSR_VEC)
+			save_altivec(tsk);
+	}
+
+	if (usermsr & MSR_SPE)
+		__giveup_spe(tsk);
+
+	msr_check_and_clear(msr_all_available);
+}
+
 void flush_all_to_thread(struct task_struct *tsk)
 {
 	if (tsk->thread.regs) {
 		preempt_disable();
 		BUG_ON(tsk != current);
-		giveup_all(tsk);
+		save_all(tsk);
 
 #ifdef CONFIG_SPE
 		if (tsk->thread.regs->msr & MSR_SPE)
@@ -832,17 +969,9 @@ void restore_tm_state(struct pt_regs *regs)
 
 	msr_diff = current->thread.ckpt_regs.msr & ~regs->msr;
 	msr_diff &= MSR_FP | MSR_VEC | MSR_VSX;
-	if (msr_diff & MSR_FP) {
-		msr_check_and_set(MSR_FP);
-		load_fp_state(&current->thread.fp_state);
-		msr_check_and_clear(MSR_FP);
-		regs->msr |= current->thread.fpexc_mode;
-	}
-	if (msr_diff & MSR_VEC) {
-		msr_check_and_set(MSR_VEC);
-		load_vr_state(&current->thread.vr_state);
-		msr_check_and_clear(MSR_VEC);
-	}
+
+	restore_math(regs);
+
 	regs->msr |= msr_diff;
 }
 
@@ -1006,6 +1135,10 @@ struct task_struct *__switch_to(struct task_struct *prev,
 		batch = this_cpu_ptr(&ppc64_tlb_batch);
 		batch->active = 1;
 	}
+
+	if (current_thread_info()->task->thread.regs)
+		restore_math(current_thread_info()->task->thread.regs);
+
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 	return last;
@@ -1307,6 +1440,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 
 		f = ret_from_fork;
 	}
+	childregs->msr &= ~(MSR_FP|MSR_VEC|MSR_VSX);
 	sp -= STACK_FRAME_OVERHEAD;
 
 	/*