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

Pull s390 updates from Martin Schwidefsky:
 "The most notable change for this pull request is the ftrace rework
  from Heiko.  It brings a small performance improvement and the ground
  work to support a new gcc option to replace the mcount blocks with a
  single nop.

  Two new s390 specific system calls are added to emulate user space
  mmio for PCI, an artifact of the how PCI memory is accessed.

  Two patches for the memory management with changes to common code.
  For KVM mm_forbids_zeropage is added which disables the empty zero
  page for an mm that is used by a KVM process.  And an optimization,
  pmdp_get_and_clear_full is added analog to ptep_get_and_clear_full.

  Some micro optimization for the cmpxchg and the spinlock code.

  And as usual bug fixes and cleanups"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (46 commits)
  s390/cputime: fix 31-bit compile
  s390/scm_block: make the number of reqs per HW req configurable
  s390/scm_block: handle multiple requests in one HW request
  s390/scm_block: allocate aidaw pages only when necessary
  s390/scm_block: use mempool to manage aidaw requests
  s390/eadm: change timeout value
  s390/mm: fix memory leak of ptlock in pmd_free_tlb
  s390: use local symbol names in entry[64].S
  s390/ptrace: always include vector registers in core files
  s390/simd: clear vector register pointer on fork/clone
  s390: translate cputime magic constants to macros
  s390/idle: convert open coded idle time seqcount
  s390/idle: add missing irq off lockdep annotation
  s390/debug: avoid function call for debug_sprintf_*
  s390/kprobes: fix instruction copy for out of line execution
  s390: remove diag 44 calls from cpu_relax()
  s390/dasd: retry partition detection
  s390/dasd: fix list corruption for sleep_on requests
  s390/dasd: fix infinite term I/O loop
  s390/dasd: remove unused code
  ...

2 files changed, 88 insertions, 107 deletions

diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index a2b81d6..811937b 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -261,8 +261,8 @@ static inline void report_user_fault(struct pt_regs *regs, long signr)
 		return;
 	if (!printk_ratelimit())
 		return;
-	printk(KERN_ALERT "User process fault: interruption code 0x%X ",
-	       regs->int_code);
+	printk(KERN_ALERT "User process fault: interruption code %04x ilc:%d",
+	       regs->int_code & 0xffff, regs->int_code >> 17);
 	print_vma_addr(KERN_CONT "in ", regs->psw.addr & PSW_ADDR_INSN);
 	printk(KERN_CONT "\n");
 	printk(KERN_ALERT "failing address: %016lx TEID: %016lx\n",
@@ -548,7 +548,7 @@ out:
 	return fault;
 }
 
-void __kprobes do_protection_exception(struct pt_regs *regs)
+void do_protection_exception(struct pt_regs *regs)
 {
 	unsigned long trans_exc_code;
 	int fault;
@@ -574,8 +574,9 @@ void __kprobes do_protection_exception(struct pt_regs *regs)
 	if (unlikely(fault))
 		do_fault_error(regs, fault);
 }
+NOKPROBE_SYMBOL(do_protection_exception);
 
-void __kprobes do_dat_exception(struct pt_regs *regs)
+void do_dat_exception(struct pt_regs *regs)
 {
 	int access, fault;
 
@@ -584,6 +585,7 @@ void __kprobes do_dat_exception(struct pt_regs *regs)
 	if (unlikely(fault))
 		do_fault_error(regs, fault);
 }
+NOKPROBE_SYMBOL(do_dat_exception);
 
 #ifdef CONFIG_PFAULT 
 /*
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 1b79ca6..71c7eff 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -18,6 +18,8 @@
 #include <linux/rcupdate.h>
 #include <linux/slab.h>
 #include <linux/swapops.h>
+#include <linux/ksm.h>
+#include <linux/mman.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -750,8 +752,7 @@ int gmap_ipte_notify(struct gmap *gmap, unsigned long gaddr, unsigned long len)
 			break;
 		/* Walk the process page table, lock and get pte pointer */
 		ptep = get_locked_pte(gmap->mm, addr, &ptl);
-		if (unlikely(!ptep))
-			continue;
+		VM_BUG_ON(!ptep);
 		/* Set notification bit in the pgste of the pte */
 		entry = *ptep;
 		if ((pte_val(entry) & (_PAGE_INVALID | _PAGE_PROTECT)) == 0) {
@@ -761,7 +762,7 @@ int gmap_ipte_notify(struct gmap *gmap, unsigned long gaddr, unsigned long len)
 			gaddr += PAGE_SIZE;
 			len -= PAGE_SIZE;
 		}
-		spin_unlock(ptl);
+		pte_unmap_unlock(ptep, ptl);
 	}
 	up_read(&gmap->mm->mmap_sem);
 	return rc;
@@ -834,99 +835,6 @@ static inline void page_table_free_pgste(unsigned long *table)
 	__free_page(page);
 }
 
-static inline unsigned long page_table_reset_pte(struct mm_struct *mm, pmd_t *pmd,
-			unsigned long addr, unsigned long end, bool init_skey)
-{
-	pte_t *start_pte, *pte;
-	spinlock_t *ptl;
-	pgste_t pgste;
-
-	start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
-	pte = start_pte;
-	do {
-		pgste = pgste_get_lock(pte);
-		pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK;
-		if (init_skey) {
-			unsigned long address;
-
-			pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT |
-					      PGSTE_GR_BIT | PGSTE_GC_BIT);
-
-			/* skip invalid and not writable pages */
-			if (pte_val(*pte) & _PAGE_INVALID ||
-			    !(pte_val(*pte) & _PAGE_WRITE)) {
-				pgste_set_unlock(pte, pgste);
-				continue;
-			}
-
-			address = pte_val(*pte) & PAGE_MASK;
-			page_set_storage_key(address, PAGE_DEFAULT_KEY, 1);
-		}
-		pgste_set_unlock(pte, pgste);
-	} while (pte++, addr += PAGE_SIZE, addr != end);
-	pte_unmap_unlock(start_pte, ptl);
-
-	return addr;
-}
-
-static inline unsigned long page_table_reset_pmd(struct mm_struct *mm, pud_t *pud,
-			unsigned long addr, unsigned long end, bool init_skey)
-{
-	unsigned long next;
-	pmd_t *pmd;
-
-	pmd = pmd_offset(pud, addr);
-	do {
-		next = pmd_addr_end(addr, end);
-		if (pmd_none_or_clear_bad(pmd))
-			continue;
-		next = page_table_reset_pte(mm, pmd, addr, next, init_skey);
-	} while (pmd++, addr = next, addr != end);
-
-	return addr;
-}
-
-static inline unsigned long page_table_reset_pud(struct mm_struct *mm, pgd_t *pgd,
-			unsigned long addr, unsigned long end, bool init_skey)
-{
-	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_reset_pmd(mm, pud, addr, next, init_skey);
-	} while (pud++, addr = next, addr != end);
-
-	return addr;
-}
-
-void page_table_reset_pgste(struct mm_struct *mm, unsigned long start,
-			    unsigned long end, bool init_skey)
-{
-	unsigned long addr, next;
-	pgd_t *pgd;
-
-	down_write(&mm->mmap_sem);
-	if (init_skey && mm_use_skey(mm))
-		goto out_up;
-	addr = start;
-	pgd = pgd_offset(mm, addr);
-	do {
-		next = pgd_addr_end(addr, end);
-		if (pgd_none_or_clear_bad(pgd))
-			continue;
-		next = page_table_reset_pud(mm, pgd, addr, next, init_skey);
-	} while (pgd++, addr = next, addr != end);
-	if (init_skey)
-		current->mm->context.use_skey = 1;
-out_up:
-	up_write(&mm->mmap_sem);
-}
-EXPORT_SYMBOL(page_table_reset_pgste);
-
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned long key, bool nq)
 {
@@ -992,11 +900,6 @@ static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm)
 	return NULL;
 }
 
-void page_table_reset_pgste(struct mm_struct *mm, unsigned long start,
-			    unsigned long end, bool init_skey)
-{
-}
-
 static inline void page_table_free_pgste(unsigned long *table)
 {
 }
@@ -1347,13 +1250,89 @@ EXPORT_SYMBOL_GPL(s390_enable_sie);
  * Enable storage key handling from now on and initialize the storage
  * keys with the default key.
  */
-void s390_enable_skey(void)
+static int __s390_enable_skey(pte_t *pte, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
 {
-	page_table_reset_pgste(current->mm, 0, TASK_SIZE, true);
+	unsigned long ptev;
+	pgste_t pgste;
+
+	pgste = pgste_get_lock(pte);
+	/*
+	 * Remove all zero page mappings,
+	 * after establishing a policy to forbid zero page mappings
+	 * following faults for that page will get fresh anonymous pages
+	 */
+	if (is_zero_pfn(pte_pfn(*pte))) {
+		ptep_flush_direct(walk->mm, addr, pte);
+		pte_val(*pte) = _PAGE_INVALID;
+	}
+	/* Clear storage key */
+	pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT |
+			      PGSTE_GR_BIT | PGSTE_GC_BIT);
+	ptev = pte_val(*pte);
+	if (!(ptev & _PAGE_INVALID) && (ptev & _PAGE_WRITE))
+		page_set_storage_key(ptev & PAGE_MASK, PAGE_DEFAULT_KEY, 1);
+	pgste_set_unlock(pte, pgste);
+	return 0;
+}
+
+int s390_enable_skey(void)
+{
+	struct mm_walk walk = { .pte_entry = __s390_enable_skey };
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	int rc = 0;
+
+	down_write(&mm->mmap_sem);
+	if (mm_use_skey(mm))
+		goto out_up;
+
+	mm->context.use_skey = 1;
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		if (ksm_madvise(vma, vma->vm_start, vma->vm_end,
+				MADV_UNMERGEABLE, &vma->vm_flags)) {
+			mm->context.use_skey = 0;
+			rc = -ENOMEM;
+			goto out_up;
+		}
+	}
+	mm->def_flags &= ~VM_MERGEABLE;
+
+	walk.mm = mm;
+	walk_page_range(0, TASK_SIZE, &walk);
+
+out_up:
+	up_write(&mm->mmap_sem);
+	return rc;
 }
 EXPORT_SYMBOL_GPL(s390_enable_skey);
 
 /*
+ * Reset CMMA state, make all pages stable again.
+ */
+static int __s390_reset_cmma(pte_t *pte, unsigned long addr,
+			     unsigned long next, struct mm_walk *walk)
+{
+	pgste_t pgste;
+
+	pgste = pgste_get_lock(pte);
+	pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK;
+	pgste_set_unlock(pte, pgste);
+	return 0;
+}
+
+void s390_reset_cmma(struct mm_struct *mm)
+{
+	struct mm_walk walk = { .pte_entry = __s390_reset_cmma };
+
+	down_write(&mm->mmap_sem);
+	walk.mm = mm;
+	walk_page_range(0, TASK_SIZE, &walk);
+	up_write(&mm->mmap_sem);
+}
+EXPORT_SYMBOL_GPL(s390_reset_cmma);
+
+/*
  * Test and reset if a guest page is dirty
  */
 bool gmap_test_and_clear_dirty(unsigned long address, struct gmap *gmap)