Merge tag 'powerpc-4.18-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Notable changes:

   - Support for split PMD page table lock on 64-bit Book3S (Power8/9).

   - Add support for HAVE_RELIABLE_STACKTRACE, so we properly support
     live patching again.

   - Add support for patching barrier_nospec in copy_from_user() and
     syscall entry.

   - A couple of fixes for our data breakpoints on Book3S.

   - A series from Nick optimising TLB/mm handling with the Radix MMU.

   - Numerous small cleanups to squash sparse/gcc warnings from Mathieu
     Malaterre.

   - Several series optimising various parts of the 32-bit code from
     Christophe Leroy.

   - Removal of support for two old machines, "SBC834xE" and "C2K"
     ("GEFanuc,C2K"), which is why the diffstat has so many deletions.

  And many other small improvements & fixes.

  There's a few out-of-area changes. Some minor ftrace changes OK'ed by
  Steve, and a fix to our powernv cpuidle driver. Then there's a series
  touching mm, x86 and fs/proc/task_mmu.c, which cleans up some details
  around pkey support. It was ack'ed/reviewed by Ingo & Dave and has
  been in next for several weeks.

  Thanks to: Akshay Adiga, Alastair D'Silva, Alexey Kardashevskiy, Al
  Viro, Andrew Donnellan, Aneesh Kumar K.V, Anju T Sudhakar, Arnd
  Bergmann, Balbir Singh, Cédric Le Goater, Christophe Leroy, Christophe
  Lombard, Colin Ian King, Dave Hansen, Fabio Estevam, Finn Thain,
  Frederic Barrat, Gautham R. Shenoy, Haren Myneni, Hari Bathini, Ingo
  Molnar, Jonathan Neuschäfer, Josh Poimboeuf, Kamalesh Babulal,
  Madhavan Srinivasan, Mahesh Salgaonkar, Mark Greer, Mathieu Malaterre,
  Matthew Wilcox, Michael Neuling, Michal Suchanek, Naveen N. Rao,
  Nicholas Piggin, Nicolai Stange, Olof Johansson, Paul Gortmaker, Paul
  Mackerras, Peter Rosin, Pridhiviraj Paidipeddi, Ram Pai, Rashmica
  Gupta, Ravi Bangoria, Russell Currey, Sam Bobroff, Samuel
  Mendoza-Jonas, Segher Boessenkool, Shilpasri G Bhat, Simon Guo,
  Souptick Joarder, Stewart Smith, Thiago Jung Bauermann, Torsten Duwe,
  Vaibhav Jain, Wei Yongjun, Wolfram Sang, Yisheng Xie, YueHaibing"

* tag 'powerpc-4.18-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (251 commits)
  powerpc/64s/radix: Fix missing ptesync in flush_cache_vmap
  cpuidle: powernv: Fix promotion from snooze if next state disabled
  powerpc: fix build failure by disabling attribute-alias warning in pci_32
  ocxl: Fix missing unlock on error in afu_ioctl_enable_p9_wait()
  powerpc-opal: fix spelling mistake "Uniterrupted" -> "Uninterrupted"
  powerpc: fix spelling mistake: "Usupported" -> "Unsupported"
  powerpc/pkeys: Detach execute_only key on !PROT_EXEC
  powerpc/powernv: copy/paste - Mask SO bit in CR
  powerpc: Remove core support for Marvell mv64x60 hostbridges
  powerpc/boot: Remove core support for Marvell mv64x60 hostbridges
  powerpc/boot: Remove support for Marvell mv64x60 i2c controller
  powerpc/boot: Remove support for Marvell MPSC serial controller
  powerpc/embedded6xx: Remove C2K board support
  powerpc/lib: optimise PPC32 memcmp
  powerpc/lib: optimise 32 bits __clear_user()
  powerpc/time: inline arch_vtime_task_switch()
  powerpc/Makefile: set -mcpu=860 flag for the 8xx
  powerpc: Implement csum_ipv6_magic in assembly
  powerpc/32: Optimise __csum_partial()
  powerpc/lib: Adjust .balign inside string functions for PPC32
  ...

1 files changed, 37 insertions, 49 deletions

diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 705193e7192f..ef9f96742ce1 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -124,23 +124,28 @@ extern void radix__mark_rodata_ro(void);
 extern void radix__mark_initmem_nx(void);
 #endif
 
+extern void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep,
+					 pte_t entry, unsigned long address,
+					 int psize);
+
 static inline unsigned long __radix_pte_update(pte_t *ptep, unsigned long clr,
 					       unsigned long set)
 {
-	pte_t pte;
-	unsigned long old_pte, new_pte;
-
-	do {
-		pte = READ_ONCE(*ptep);
-		old_pte = pte_val(pte);
-		new_pte = (old_pte | set) & ~clr;
-
-	} while (!pte_xchg(ptep, __pte(old_pte), __pte(new_pte)));
-
-	return old_pte;
+	__be64 old_be, tmp_be;
+
+	__asm__ __volatile__(
+	"1:	ldarx	%0,0,%3		# pte_update\n"
+	"	andc	%1,%0,%5	\n"
+	"	or	%1,%1,%4	\n"
+	"	stdcx.	%1,0,%3		\n"
+	"	bne-	1b"
+	: "=&r" (old_be), "=&r" (tmp_be), "=m" (*ptep)
+	: "r" (ptep), "r" (cpu_to_be64(set)), "r" (cpu_to_be64(clr))
+	: "cc" );
+
+	return be64_to_cpu(old_be);
 }
 
-
 static inline unsigned long radix__pte_update(struct mm_struct *mm,
 					unsigned long addr,
 					pte_t *ptep, unsigned long clr,
@@ -176,48 +181,14 @@ static inline pte_t radix__ptep_get_and_clear_full(struct mm_struct *mm,
 	unsigned long old_pte;
 
 	if (full) {
-		/*
-		 * If we are trying to clear the pte, we can skip
-		 * the DD1 pte update sequence and batch the tlb flush. The
-		 * tlb flush batching is done by mmu gather code. We
-		 * still keep the cmp_xchg update to make sure we get
-		 * correct R/C bit which might be updated via Nest MMU.
-		 */
-		old_pte = __radix_pte_update(ptep, ~0ul, 0);
+		old_pte = pte_val(*ptep);
+		*ptep = __pte(0);
 	} else
 		old_pte = radix__pte_update(mm, addr, ptep, ~0ul, 0, 0);
 
 	return __pte(old_pte);
 }
 
-/*
- * Set the dirty and/or accessed bits atomically in a linux PTE, this
- * function doesn't need to invalidate tlb.
- */
-static inline void radix__ptep_set_access_flags(struct mm_struct *mm,
-						pte_t *ptep, pte_t entry,
-						unsigned long address)
-{
-
-	unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED |
-					      _PAGE_RW | _PAGE_EXEC);
-
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
-
-		unsigned long old_pte, new_pte;
-
-		old_pte = __radix_pte_update(ptep, ~0, 0);
-		/*
-		 * new value of pte
-		 */
-		new_pte = old_pte | set;
-		radix__flush_tlb_pte_p9_dd1(old_pte, mm, address);
-		__radix_pte_update(ptep, 0, new_pte);
-	} else
-		__radix_pte_update(ptep, 0, set);
-	asm volatile("ptesync" : : : "memory");
-}
-
 static inline int radix__pte_same(pte_t pte_a, pte_t pte_b)
 {
 	return ((pte_raw(pte_a) ^ pte_raw(pte_b)) == 0);
@@ -232,7 +203,24 @@ static inline void radix__set_pte_at(struct mm_struct *mm, unsigned long addr,
 				 pte_t *ptep, pte_t pte, int percpu)
 {
 	*ptep = pte;
-	asm volatile("ptesync" : : : "memory");
+
+	/*
+	 * The architecture suggests a ptesync after setting the pte, which
+	 * orders the store that updates the pte with subsequent page table
+	 * walk accesses which may load the pte. Without this it may be
+	 * possible for a subsequent access to result in spurious fault.
+	 *
+	 * This is not necessary for correctness, because a spurious fault
+	 * is tolerated by the page fault handler, and this store will
+	 * eventually be seen. In testing, there was no noticable increase
+	 * in user faults on POWER9. Avoiding ptesync here is a significant
+	 * win for things like fork. If a future microarchitecture benefits
+	 * from ptesync, it should probably go into update_mmu_cache, rather
+	 * than set_pte_at (which is used to set ptes unrelated to faults).
+	 *
+	 * Spurious faults to vmalloc region are not tolerated, so there is
+	 * a ptesync in flush_cache_vmap.
+	 */
 }
 
 static inline int radix__pmd_bad(pmd_t pmd)