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, 273 insertions, 6 deletions

diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c
index 518518fb7c45..c1f4ca45c93a 100644
--- a/arch/powerpc/mm/pgtable-book3s64.c
+++ b/arch/powerpc/mm/pgtable-book3s64.c
@@ -9,14 +9,22 @@
 
 #include <linux/sched.h>
 #include <linux/mm_types.h>
+#include <linux/memblock.h>
 #include <misc/cxl-base.h>
 
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
+#include <asm/trace.h>
+#include <asm/powernv.h>
 
 #include "mmu_decl.h"
 #include <trace/events/thp.h>
 
+unsigned long __pmd_frag_nr;
+EXPORT_SYMBOL(__pmd_frag_nr);
+unsigned long __pmd_frag_size_shift;
+EXPORT_SYMBOL(__pmd_frag_size_shift);
+
 int (*register_process_table)(unsigned long base, unsigned long page_size,
 			      unsigned long tbl_size);
 
@@ -34,13 +42,16 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
 	int changed;
 #ifdef CONFIG_DEBUG_VM
 	WARN_ON(!pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp));
-	assert_spin_locked(&vma->vm_mm->page_table_lock);
+	assert_spin_locked(pmd_lockptr(vma->vm_mm, pmdp));
 #endif
 	changed = !pmd_same(*(pmdp), entry);
 	if (changed) {
-		__ptep_set_access_flags(vma->vm_mm, pmdp_ptep(pmdp),
-					pmd_pte(entry), address);
-		flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+		/*
+		 * We can use MMU_PAGE_2M here, because only radix
+		 * path look at the psize.
+		 */
+		__ptep_set_access_flags(vma, pmdp_ptep(pmdp),
+					pmd_pte(entry), address, MMU_PAGE_2M);
 	}
 	return changed;
 }
@@ -59,7 +70,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 {
 #ifdef CONFIG_DEBUG_VM
 	WARN_ON(pte_present(pmd_pte(*pmdp)) && !pte_protnone(pmd_pte(*pmdp)));
-	assert_spin_locked(&mm->page_table_lock);
+	assert_spin_locked(pmd_lockptr(mm, pmdp));
 	WARN_ON(!(pmd_trans_huge(pmd) || pmd_devmap(pmd)));
 #endif
 	trace_hugepage_set_pmd(addr, pmd_val(pmd));
@@ -141,7 +152,8 @@ pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
 			  pmd_t *pmd)
 {
-	return;
+	if (radix_enabled())
+		prefetch((void *)addr);
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
@@ -171,3 +183,258 @@ int __meminit remove_section_mapping(unsigned long start, unsigned long end)
 	return hash__remove_section_mapping(start, end);
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
+
+void __init mmu_partition_table_init(void)
+{
+	unsigned long patb_size = 1UL << PATB_SIZE_SHIFT;
+	unsigned long ptcr;
+
+	BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 36), "Partition table size too large.");
+	partition_tb = __va(memblock_alloc_base(patb_size, patb_size,
+						MEMBLOCK_ALLOC_ANYWHERE));
+
+	/* Initialize the Partition Table with no entries */
+	memset((void *)partition_tb, 0, patb_size);
+
+	/*
+	 * update partition table control register,
+	 * 64 K size.
+	 */
+	ptcr = __pa(partition_tb) | (PATB_SIZE_SHIFT - 12);
+	mtspr(SPRN_PTCR, ptcr);
+	powernv_set_nmmu_ptcr(ptcr);
+}
+
+void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0,
+				   unsigned long dw1)
+{
+	unsigned long old = be64_to_cpu(partition_tb[lpid].patb0);
+
+	partition_tb[lpid].patb0 = cpu_to_be64(dw0);
+	partition_tb[lpid].patb1 = cpu_to_be64(dw1);
+
+	/*
+	 * Global flush of TLBs and partition table caches for this lpid.
+	 * The type of flush (hash or radix) depends on what the previous
+	 * use of this partition ID was, not the new use.
+	 */
+	asm volatile("ptesync" : : : "memory");
+	if (old & PATB_HR) {
+		asm volatile(PPC_TLBIE_5(%0,%1,2,0,1) : :
+			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
+		asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : :
+			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
+		trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 1);
+	} else {
+		asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : :
+			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
+		trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 0);
+	}
+	/* do we need fixup here ?*/
+	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+}
+EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry);
+
+static pmd_t *get_pmd_from_cache(struct mm_struct *mm)
+{
+	void *pmd_frag, *ret;
+
+	spin_lock(&mm->page_table_lock);
+	ret = mm->context.pmd_frag;
+	if (ret) {
+		pmd_frag = ret + PMD_FRAG_SIZE;
+		/*
+		 * If we have taken up all the fragments mark PTE page NULL
+		 */
+		if (((unsigned long)pmd_frag & ~PAGE_MASK) == 0)
+			pmd_frag = NULL;
+		mm->context.pmd_frag = pmd_frag;
+	}
+	spin_unlock(&mm->page_table_lock);
+	return (pmd_t *)ret;
+}
+
+static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm)
+{
+	void *ret = NULL;
+	struct page *page;
+	gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO;
+
+	if (mm == &init_mm)
+		gfp &= ~__GFP_ACCOUNT;
+	page = alloc_page(gfp);
+	if (!page)
+		return NULL;
+	if (!pgtable_pmd_page_ctor(page)) {
+		__free_pages(page, 0);
+		return NULL;
+	}
+
+	ret = page_address(page);
+	/*
+	 * if we support only one fragment just return the
+	 * allocated page.
+	 */
+	if (PMD_FRAG_NR == 1)
+		return ret;
+
+	spin_lock(&mm->page_table_lock);
+	/*
+	 * If we find pgtable_page set, we return
+	 * the allocated page with single fragement
+	 * count.
+	 */
+	if (likely(!mm->context.pmd_frag)) {
+		set_page_count(page, PMD_FRAG_NR);
+		mm->context.pmd_frag = ret + PMD_FRAG_SIZE;
+	}
+	spin_unlock(&mm->page_table_lock);
+
+	return (pmd_t *)ret;
+}
+
+pmd_t *pmd_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr)
+{
+	pmd_t *pmd;
+
+	pmd = get_pmd_from_cache(mm);
+	if (pmd)
+		return pmd;
+
+	return __alloc_for_pmdcache(mm);
+}
+
+void pmd_fragment_free(unsigned long *pmd)
+{
+	struct page *page = virt_to_page(pmd);
+
+	if (put_page_testzero(page)) {
+		pgtable_pmd_page_dtor(page);
+		free_unref_page(page);
+	}
+}
+
+static pte_t *get_pte_from_cache(struct mm_struct *mm)
+{
+	void *pte_frag, *ret;
+
+	spin_lock(&mm->page_table_lock);
+	ret = mm->context.pte_frag;
+	if (ret) {
+		pte_frag = ret + PTE_FRAG_SIZE;
+		/*
+		 * If we have taken up all the fragments mark PTE page NULL
+		 */
+		if (((unsigned long)pte_frag & ~PAGE_MASK) == 0)
+			pte_frag = NULL;
+		mm->context.pte_frag = pte_frag;
+	}
+	spin_unlock(&mm->page_table_lock);
+	return (pte_t *)ret;
+}
+
+static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel)
+{
+	void *ret = NULL;
+	struct page *page;
+
+	if (!kernel) {
+		page = alloc_page(PGALLOC_GFP | __GFP_ACCOUNT);
+		if (!page)
+			return NULL;
+		if (!pgtable_page_ctor(page)) {
+			__free_page(page);
+			return NULL;
+		}
+	} else {
+		page = alloc_page(PGALLOC_GFP);
+		if (!page)
+			return NULL;
+	}
+
+
+	ret = page_address(page);
+	/*
+	 * if we support only one fragment just return the
+	 * allocated page.
+	 */
+	if (PTE_FRAG_NR == 1)
+		return ret;
+	spin_lock(&mm->page_table_lock);
+	/*
+	 * If we find pgtable_page set, we return
+	 * the allocated page with single fragement
+	 * count.
+	 */
+	if (likely(!mm->context.pte_frag)) {
+		set_page_count(page, PTE_FRAG_NR);
+		mm->context.pte_frag = ret + PTE_FRAG_SIZE;
+	}
+	spin_unlock(&mm->page_table_lock);
+
+	return (pte_t *)ret;
+}
+
+pte_t *pte_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel)
+{
+	pte_t *pte;
+
+	pte = get_pte_from_cache(mm);
+	if (pte)
+		return pte;
+
+	return __alloc_for_ptecache(mm, kernel);
+}
+
+void pte_fragment_free(unsigned long *table, int kernel)
+{
+	struct page *page = virt_to_page(table);
+
+	if (put_page_testzero(page)) {
+		if (!kernel)
+			pgtable_page_dtor(page);
+		free_unref_page(page);
+	}
+}
+
+static inline void pgtable_free(void *table, int index)
+{
+	switch (index) {
+	case PTE_INDEX:
+		pte_fragment_free(table, 0);
+		break;
+	case PMD_INDEX:
+		pmd_fragment_free(table);
+		break;
+	case PUD_INDEX:
+		kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), table);
+		break;
+		/* We don't free pgd table via RCU callback */
+	default:
+		BUG();
+	}
+}
+
+#ifdef CONFIG_SMP
+void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int index)
+{
+	unsigned long pgf = (unsigned long)table;
+
+	BUG_ON(index > MAX_PGTABLE_INDEX_SIZE);
+	pgf |= index;
+	tlb_remove_table(tlb, (void *)pgf);
+}
+
+void __tlb_remove_table(void *_table)
+{
+	void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
+	unsigned int index = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
+
+	return pgtable_free(table, index);
+}
+#else
+void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int index)
+{
+	return pgtable_free(table, index);
+}
+#endif