Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Martin Schwidefsky:
 "One additional new feature for 4.1, a new PRNG based on SHA-512 for
  the zcrypt driver.

  Two memory management related changes, the page table reallocation for
  KVM is removed, and with file ptes gone the encoding of page table
  entries is improved.

  And three bug fixes"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux:
  s390/zcrypt: Introduce new SHA-512 based Pseudo Random Generator.
  s390/mm: change swap pte encoding and pgtable cleanup
  s390/mm: correct transfer of dirty & young bits in __pmd_to_pte
  s390/bpf: add dependency to z196 features
  s390/3215: free memory in error path
  s390/kvm: remove delayed reallocation of page tables for KVM
  kexec: allocate the kexec control page with KEXEC_CONTROL_MEMORY_GFP

2 files changed, 79 insertions, 129 deletions

diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 210ffede0153..e617e74b7be2 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -14,20 +14,23 @@ static inline pmd_t __pte_to_pmd(pte_t pte)
 
 	/*
 	 * Convert encoding		  pte bits	   pmd bits
-	 *				.IR...wrdytp	dy..R...I...wr
-	 * empty			.10...000000 -> 00..0...1...00
-	 * prot-none, clean, old	.11...000001 -> 00..1...1...00
-	 * prot-none, clean, young	.11...000101 -> 01..1...1...00
-	 * prot-none, dirty, old	.10...001001 -> 10..1...1...00
-	 * prot-none, dirty, young	.10...001101 -> 11..1...1...00
-	 * read-only, clean, old	.11...010001 -> 00..1...1...01
-	 * read-only, clean, young	.01...010101 -> 01..1...0...01
-	 * read-only, dirty, old	.11...011001 -> 10..1...1...01
-	 * read-only, dirty, young	.01...011101 -> 11..1...0...01
-	 * read-write, clean, old	.11...110001 -> 00..0...1...11
-	 * read-write, clean, young	.01...110101 -> 01..0...0...11
-	 * read-write, dirty, old	.10...111001 -> 10..0...1...11
-	 * read-write, dirty, young	.00...111101 -> 11..0...0...11
+	 *				lIR.uswrdy.p	dy..R...I...wr
+	 * empty			010.000000.0 -> 00..0...1...00
+	 * prot-none, clean, old	111.000000.1 -> 00..1...1...00
+	 * prot-none, clean, young	111.000001.1 -> 01..1...1...00
+	 * prot-none, dirty, old	111.000010.1 -> 10..1...1...00
+	 * prot-none, dirty, young	111.000011.1 -> 11..1...1...00
+	 * read-only, clean, old	111.000100.1 -> 00..1...1...01
+	 * read-only, clean, young	101.000101.1 -> 01..1...0...01
+	 * read-only, dirty, old	111.000110.1 -> 10..1...1...01
+	 * read-only, dirty, young	101.000111.1 -> 11..1...0...01
+	 * read-write, clean, old	111.001100.1 -> 00..1...1...11
+	 * read-write, clean, young	101.001101.1 -> 01..1...0...11
+	 * read-write, dirty, old	110.001110.1 -> 10..0...1...11
+	 * read-write, dirty, young	100.001111.1 -> 11..0...0...11
+	 * HW-bits: R read-only, I invalid
+	 * SW-bits: p present, y young, d dirty, r read, w write, s special,
+	 *	    u unused, l large
 	 */
 	if (pte_present(pte)) {
 		pmd_val(pmd) = pte_val(pte) & PAGE_MASK;
@@ -48,20 +51,23 @@ static inline pte_t __pmd_to_pte(pmd_t pmd)
 
 	/*
 	 * Convert encoding		   pmd bits	    pte bits
-	 *				dy..R...I...wr	  .IR...wrdytp
-	 * empty			00..0...1...00 -> .10...001100
-	 * prot-none, clean, old	00..0...1...00 -> .10...000001
-	 * prot-none, clean, young	01..0...1...00 -> .10...000101
-	 * prot-none, dirty, old	10..0...1...00 -> .10...001001
-	 * prot-none, dirty, young	11..0...1...00 -> .10...001101
-	 * read-only, clean, old	00..1...1...01 -> .11...010001
-	 * read-only, clean, young	01..1...1...01 -> .11...010101
-	 * read-only, dirty, old	10..1...1...01 -> .11...011001
-	 * read-only, dirty, young	11..1...1...01 -> .11...011101
-	 * read-write, clean, old	00..0...1...11 -> .10...110001
-	 * read-write, clean, young	01..0...1...11 -> .10...110101
-	 * read-write, dirty, old	10..0...1...11 -> .10...111001
-	 * read-write, dirty, young	11..0...1...11 -> .10...111101
+	 *				dy..R...I...wr	  lIR.uswrdy.p
+	 * empty			00..0...1...00 -> 010.000000.0
+	 * prot-none, clean, old	00..1...1...00 -> 111.000000.1
+	 * prot-none, clean, young	01..1...1...00 -> 111.000001.1
+	 * prot-none, dirty, old	10..1...1...00 -> 111.000010.1
+	 * prot-none, dirty, young	11..1...1...00 -> 111.000011.1
+	 * read-only, clean, old	00..1...1...01 -> 111.000100.1
+	 * read-only, clean, young	01..1...0...01 -> 101.000101.1
+	 * read-only, dirty, old	10..1...1...01 -> 111.000110.1
+	 * read-only, dirty, young	11..1...0...01 -> 101.000111.1
+	 * read-write, clean, old	00..1...1...11 -> 111.001100.1
+	 * read-write, clean, young	01..1...0...11 -> 101.001101.1
+	 * read-write, dirty, old	10..0...1...11 -> 110.001110.1
+	 * read-write, dirty, young	11..0...0...11 -> 100.001111.1
+	 * HW-bits: R read-only, I invalid
+	 * SW-bits: p present, y young, d dirty, r read, w write, s special,
+	 *	    u unused, l large
 	 */
 	if (pmd_present(pmd)) {
 		pte_val(pte) = pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN_LARGE;
@@ -70,8 +76,8 @@ static inline pte_t __pmd_to_pte(pmd_t pmd)
 		pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) << 4;
 		pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_INVALID) << 5;
 		pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT);
-		pmd_val(pmd) |= (pte_val(pte) & _PAGE_DIRTY) << 10;
-		pmd_val(pmd) |= (pte_val(pte) & _PAGE_YOUNG) << 10;
+		pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) >> 10;
+		pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) >> 10;
 	} else
 		pte_val(pte) = _PAGE_INVALID;
 	return pte;
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 33f589459113..b33f66110ca9 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -18,6 +18,7 @@
 #include <linux/rcupdate.h>
 #include <linux/slab.h>
 #include <linux/swapops.h>
+#include <linux/sysctl.h>
 #include <linux/ksm.h>
 #include <linux/mman.h>
 
@@ -920,6 +921,40 @@ unsigned long get_guest_storage_key(struct mm_struct *mm, unsigned long addr)
 }
 EXPORT_SYMBOL(get_guest_storage_key);
 
+static int page_table_allocate_pgste_min = 0;
+static int page_table_allocate_pgste_max = 1;
+int page_table_allocate_pgste = 0;
+EXPORT_SYMBOL(page_table_allocate_pgste);
+
+static struct ctl_table page_table_sysctl[] = {
+	{
+		.procname	= "allocate_pgste",
+		.data		= &page_table_allocate_pgste,
+		.maxlen		= sizeof(int),
+		.mode		= S_IRUGO | S_IWUSR,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &page_table_allocate_pgste_min,
+		.extra2		= &page_table_allocate_pgste_max,
+	},
+	{ }
+};
+
+static struct ctl_table page_table_sysctl_dir[] = {
+	{
+		.procname	= "vm",
+		.maxlen		= 0,
+		.mode		= 0555,
+		.child		= page_table_sysctl,
+	},
+	{ }
+};
+
+static int __init page_table_register_sysctl(void)
+{
+	return register_sysctl_table(page_table_sysctl_dir) ? 0 : -ENOMEM;
+}
+__initcall(page_table_register_sysctl);
+
 #else /* CONFIG_PGSTE */
 
 static inline int page_table_with_pgste(struct page *page)
@@ -963,7 +998,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
 	struct page *uninitialized_var(page);
 	unsigned int mask, bit;
 
-	if (mm_has_pgste(mm))
+	if (mm_alloc_pgste(mm))
 		return page_table_alloc_pgste(mm);
 	/* Allocate fragments of a 4K page as 1K/2K page table */
 	spin_lock_bh(&mm->context.list_lock);
@@ -1165,116 +1200,25 @@ static inline void thp_split_mm(struct mm_struct *mm)
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-static unsigned long page_table_realloc_pmd(struct mmu_gather *tlb,
-				struct mm_struct *mm, pud_t *pud,
-				unsigned long addr, unsigned long end)
-{
-	unsigned long next, *table, *new;
-	struct page *page;
-	spinlock_t *ptl;
-	pmd_t *pmd;
-
-	pmd = pmd_offset(pud, addr);
-	do {
-		next = pmd_addr_end(addr, end);
-again:
-		if (pmd_none_or_clear_bad(pmd))
-			continue;
-		table = (unsigned long *) pmd_deref(*pmd);
-		page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
-		if (page_table_with_pgste(page))
-			continue;
-		/* Allocate new page table with pgstes */
-		new = page_table_alloc_pgste(mm);
-		if (!new)
-			return -ENOMEM;
-
-		ptl = pmd_lock(mm, pmd);
-		if (likely((unsigned long *) pmd_deref(*pmd) == table)) {
-			/* Nuke pmd entry pointing to the "short" page table */
-			pmdp_flush_lazy(mm, addr, pmd);
-			pmd_clear(pmd);
-			/* Copy ptes from old table to new table */
-			memcpy(new, table, PAGE_SIZE/2);
-			clear_table(table, _PAGE_INVALID, PAGE_SIZE/2);
-			/* Establish new table */
-			pmd_populate(mm, pmd, (pte_t *) new);
-			/* Free old table with rcu, there might be a walker! */
-			page_table_free_rcu(tlb, table, addr);
-			new = NULL;
-		}
-		spin_unlock(ptl);
-		if (new) {
-			page_table_free_pgste(new);
-			goto again;
-		}
-	} while (pmd++, addr = next, addr != end);
-
-	return addr;
-}
-
-static unsigned long page_table_realloc_pud(struct mmu_gather *tlb,
-				   struct mm_struct *mm, pgd_t *pgd,
-				   unsigned long addr, unsigned long end)
-{
-	unsigned long next;
-	pud_t *pud;
-
-	pud = pud_offset(pgd, addr);
-	do {
-		next = pud_addr_end(addr, end);
-		if (pud_none_or_clear_bad(pud))
-			continue;
-		next = page_table_realloc_pmd(tlb, mm, pud, addr, next);
-		if (unlikely(IS_ERR_VALUE(next)))
-			return next;
-	} while (pud++, addr = next, addr != end);
-
-	return addr;
-}
-
-static unsigned long page_table_realloc(struct mmu_gather *tlb, struct mm_struct *mm,
-					unsigned long addr, unsigned long end)
-{
-	unsigned long next;
-	pgd_t *pgd;
-
-	pgd = pgd_offset(mm, addr);
-	do {
-		next = pgd_addr_end(addr, end);
-		if (pgd_none_or_clear_bad(pgd))
-			continue;
-		next = page_table_realloc_pud(tlb, mm, pgd, addr, next);
-		if (unlikely(IS_ERR_VALUE(next)))
-			return next;
-	} while (pgd++, addr = next, addr != end);
-
-	return 0;
-}
-
 /*
  * switch on pgstes for its userspace process (for kvm)
  */
 int s390_enable_sie(void)
 {
-	struct task_struct *tsk = current;
-	struct mm_struct *mm = tsk->mm;
-	struct mmu_gather tlb;
+	struct mm_struct *mm = current->mm;
 
 	/* Do we have pgstes? if yes, we are done */
-	if (mm_has_pgste(tsk->mm))
+	if (mm_has_pgste(mm))
 		return 0;
-
+	/* Fail if the page tables are 2K */
+	if (!mm_alloc_pgste(mm))
+		return -EINVAL;
 	down_write(&mm->mmap_sem);
+	mm->context.has_pgste = 1;
 	/* split thp mappings and disable thp for future mappings */
 	thp_split_mm(mm);
-	/* Reallocate the page tables with pgstes */
-	tlb_gather_mmu(&tlb, mm, 0, TASK_SIZE);
-	if (!page_table_realloc(&tlb, mm, 0, TASK_SIZE))
-		mm->context.has_pgste = 1;
-	tlb_finish_mmu(&tlb, 0, TASK_SIZE);
 	up_write(&mm->mmap_sem);
-	return mm->context.has_pgste ? 0 : -ENOMEM;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(s390_enable_sie);