Merge tag 'kvm-s390-master-4.5-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

KVM: s390: Fixes for kvm/master (targeting 4.5)

1. Fallout of some bigger floating point/vector rework in s390
- memory leak -> stable 4.3+
- memory overwrite -> stable 4.4+

2. enable KVM-VFIO for s390

15 files changed, 177 insertions, 42 deletions

diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index d56ec0715157..e4962f04201e 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -19,7 +19,6 @@ struct alt_instr {
 
 void __init apply_alternatives_all(void);
 void apply_alternatives(void *start, size_t length);
-void free_alternatives_memory(void);
 
 #define ALTINSTR_ENTRY(feature)						      \
 	" .word 661b - .\n"				/* label           */ \
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 12eff928ef8b..bb7b72734c24 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -193,6 +193,17 @@ lr	.req	x30		// link register
 	str	\src, [\tmp, :lo12:\sym]
 	.endm
 
+	/*
+	 * @sym: The name of the per-cpu variable
+	 * @reg: Result of per_cpu(sym, smp_processor_id())
+	 * @tmp: scratch register
+	 */
+	.macro this_cpu_ptr, sym, reg, tmp
+	adr_l	\reg, \sym
+	mrs	\tmp, tpidr_el1
+	add	\reg, \reg, \tmp
+	.endm
+
 /*
  * Annotate a function as position independent, i.e., safe to be called before
  * the kernel virtual mapping is activated.
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 54efedaf331f..7fc294c3bc5b 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -68,6 +68,7 @@
 extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 extern void flush_icache_range(unsigned long start, unsigned long end);
 extern void __flush_dcache_area(void *addr, size_t len);
+extern void __clean_dcache_area_pou(void *addr, size_t len);
 extern long __flush_cache_user_range(unsigned long start, unsigned long end);
 
 static inline void flush_cache_mm(struct mm_struct *mm)
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 9ea611ea69df..510c7b404454 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -19,7 +19,6 @@
 #define __ASM_CMPXCHG_H
 
 #include <linux/bug.h>
-#include <linux/mmdebug.h>
 
 #include <asm/atomic.h>
 #include <asm/barrier.h>
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index ef572206f1c3..8e88a696c9cb 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -2,7 +2,9 @@
 #define _ASM_EFI_H
 
 #include <asm/io.h>
+#include <asm/mmu_context.h>
 #include <asm/neon.h>
+#include <asm/tlbflush.h>
 
 #ifdef CONFIG_EFI
 extern void efi_init(void);
@@ -10,6 +12,8 @@ extern void efi_init(void);
 #define efi_init()
 #endif
 
+int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md);
+
 #define efi_call_virt(f, ...)						\
 ({									\
 	efi_##f##_t *__f;						\
@@ -63,6 +67,11 @@ extern void efi_init(void);
  *   Services are enabled and the EFI_RUNTIME_SERVICES bit set.
  */
 
+static inline void efi_set_pgd(struct mm_struct *mm)
+{
+	switch_mm(NULL, mm, NULL);
+}
+
 void efi_virtmap_load(void);
 void efi_virtmap_unload(void);
 
diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h
index c5534facf941..3c60f37e48ab 100644
--- a/arch/arm64/include/asm/ftrace.h
+++ b/arch/arm64/include/asm/ftrace.h
@@ -28,6 +28,8 @@ struct dyn_arch_ftrace {
 
 extern unsigned long ftrace_graph_call;
 
+extern void return_to_handler(void);
+
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
 	/*
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index bb4052e85dba..bbc1e35aa601 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -26,36 +26,7 @@ static inline pte_t huge_ptep_get(pte_t *ptep)
 	return *ptep;
 }
 
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte_at(mm, addr, ptep, pte);
-}
-
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-					 unsigned long addr, pte_t *ptep)
-{
-	ptep_clear_flush(vma, addr, ptep);
-}
-
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
 
-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
-{
-	return ptep_get_and_clear(mm, addr, ptep);
-}
-
-static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-					     unsigned long addr, pte_t *ptep,
-					     pte_t pte, int dirty)
-{
-	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-}
 
 static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 					  unsigned long addr, unsigned long end,
@@ -97,4 +68,19 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 	clear_bit(PG_dcache_clean, &page->flags);
 }
 
+extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
+				struct page *page, int writable);
+#define arch_make_huge_pte arch_make_huge_pte
+extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+			    pte_t *ptep, pte_t pte);
+extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+				      unsigned long addr, pte_t *ptep,
+				      pte_t pte, int dirty);
+extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+				     unsigned long addr, pte_t *ptep);
+extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
+				    unsigned long addr, pte_t *ptep);
+extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
+				  unsigned long addr, pte_t *ptep);
+
 #endif /* __ASM_HUGETLB_H */
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index 8e8d30684392..b77197d941fc 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -1,10 +1,45 @@
 #ifndef __ASM_IRQ_H
 #define __ASM_IRQ_H
 
+#define IRQ_STACK_SIZE			THREAD_SIZE
+#define IRQ_STACK_START_SP		THREAD_START_SP
+
+#ifndef __ASSEMBLER__
+
+#include <linux/percpu.h>
+
 #include <asm-generic/irq.h>
+#include <asm/thread_info.h>
 
 struct pt_regs;
 
+DECLARE_PER_CPU(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack);
+
+/*
+ * The highest address on the stack, and the first to be used. Used to
+ * find the dummy-stack frame put down by el?_irq() in entry.S, which
+ * is structured as follows:
+ *
+ *       ------------
+ *       |          |  <- irq_stack_ptr
+ *   top ------------
+ *       |   x19    | <- irq_stack_ptr - 0x08
+ *       ------------
+ *       |   x29    | <- irq_stack_ptr - 0x10
+ *       ------------
+ *
+ * where x19 holds a copy of the task stack pointer where the struct pt_regs
+ * from kernel_entry can be found.
+ *
+ */
+#define IRQ_STACK_PTR(cpu) ((unsigned long)per_cpu(irq_stack, cpu) + IRQ_STACK_START_SP)
+
+/*
+ * The offset from irq_stack_ptr where entry.S will store the original
+ * stack pointer. Used by unwind_frame() and dump_backtrace().
+ */
+#define IRQ_STACK_TO_TASK_STACK(ptr) (*((unsigned long *)((ptr) - 0x08)))
+
 extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
 
 static inline int nr_legacy_irqs(void)
@@ -12,4 +47,14 @@ static inline int nr_legacy_irqs(void)
 	return 0;
 }
 
+static inline bool on_irq_stack(unsigned long sp, int cpu)
+{
+	/* variable names the same as kernel/stacktrace.c */
+	unsigned long low = (unsigned long)per_cpu(irq_stack, cpu);
+	unsigned long high = low + IRQ_STACK_START_SP;
+
+	return (low <= sp && sp <= high);
+}
+
+#endif /* !__ASSEMBLER__ */
 #endif
diff --git a/arch/arm64/include/asm/paravirt.h b/arch/arm64/include/asm/paravirt.h
new file mode 100644
index 000000000000..fd5f42886251
--- /dev/null
+++ b/arch/arm64/include/asm/paravirt.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_ARM64_PARAVIRT_H
+#define _ASM_ARM64_PARAVIRT_H
+
+#ifdef CONFIG_PARAVIRT
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
+
+struct pv_time_ops {
+	unsigned long long (*steal_clock)(int cpu);
+};
+extern struct pv_time_ops pv_time_ops;
+
+static inline u64 paravirt_steal_clock(int cpu)
+{
+	return pv_time_ops.steal_clock(cpu);
+}
+#endif
+
+#endif
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index d6739e836f7b..5c25b831273d 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -90,7 +90,23 @@
 /*
  * Contiguous page definitions.
  */
-#define CONT_PTES		(_AC(1, UL) << CONT_SHIFT)
+#ifdef CONFIG_ARM64_64K_PAGES
+#define CONT_PTE_SHIFT		5
+#define CONT_PMD_SHIFT		5
+#elif defined(CONFIG_ARM64_16K_PAGES)
+#define CONT_PTE_SHIFT		7
+#define CONT_PMD_SHIFT		5
+#else
+#define CONT_PTE_SHIFT		4
+#define CONT_PMD_SHIFT		4
+#endif
+
+#define CONT_PTES		(1 << CONT_PTE_SHIFT)
+#define CONT_PTE_SIZE		(CONT_PTES * PAGE_SIZE)
+#define CONT_PTE_MASK		(~(CONT_PTE_SIZE - 1))
+#define CONT_PMDS		(1 << CONT_PMD_SHIFT)
+#define CONT_PMD_SIZE		(CONT_PMDS * PMD_SIZE)
+#define CONT_PMD_MASK		(~(CONT_PMD_SIZE - 1))
 /* the the numerical offset of the PTE within a range of CONT_PTES */
 #define CONT_RANGE_OFFSET(addr) (((addr)>>PAGE_SHIFT)&(CONT_PTES-1))
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 63f52b55defe..69d2e2f86bce 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -167,6 +167,16 @@ extern struct page *empty_zero_page;
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
 #define pte_valid_not_user(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
+#define pte_valid_young(pte) \
+	((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF))
+
+/*
+ * Could the pte be present in the TLB? We must check mm_tlb_flush_pending
+ * so that we don't erroneously return false for pages that have been
+ * remapped as PROT_NONE but are yet to be flushed from the TLB.
+ */
+#define pte_accessible(mm, pte)	\
+	(mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte))
 
 static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot)
 {
@@ -217,7 +227,8 @@ static inline pte_t pte_mkspecial(pte_t pte)
 
 static inline pte_t pte_mkcont(pte_t pte)
 {
-	return set_pte_bit(pte, __pgprot(PTE_CONT));
+	pte = set_pte_bit(pte, __pgprot(PTE_CONT));
+	return set_pte_bit(pte, __pgprot(PTE_TYPE_PAGE));
 }
 
 static inline pte_t pte_mknoncont(pte_t pte)
@@ -225,6 +236,11 @@ static inline pte_t pte_mknoncont(pte_t pte)
 	return clear_pte_bit(pte, __pgprot(PTE_CONT));
 }
 
+static inline pmd_t pmd_mkcont(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | PMD_SECT_CONT);
+}
+
 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
 	*ptep = pte;
@@ -298,7 +314,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 /*
  * Hugetlb definitions.
  */
-#define HUGE_MAX_HSTATE		2
+#define HUGE_MAX_HSTATE		4
 #define HPAGE_SHIFT		PMD_SHIFT
 #define HPAGE_SIZE		(_AC(1, UL) << HPAGE_SHIFT)
 #define HPAGE_MASK		(~(HPAGE_SIZE - 1))
@@ -664,7 +680,8 @@ extern int kern_addr_valid(unsigned long addr);
 
 #include <asm-generic/pgtable.h>
 
-#define pgtable_cache_init() do { } while (0)
+void pgd_cache_init(void);
+#define pgtable_cache_init	pgd_cache_init
 
 /*
  * On AArch64, the cache coherency is handled via the set_pte_at() function.
diff --git a/arch/arm64/include/asm/shmparam.h b/arch/arm64/include/asm/shmparam.h
index 4df608a8459e..e368a55ebd22 100644
--- a/arch/arm64/include/asm/shmparam.h
+++ b/arch/arm64/include/asm/shmparam.h
@@ -21,7 +21,7 @@
  * alignment value. Since we don't have aliasing D-caches, the rest of
  * the time we can safely use PAGE_SIZE.
  */
-#define COMPAT_SHMLBA	0x4000
+#define COMPAT_SHMLBA	(4 * PAGE_SIZE)
 
 #include <asm-generic/shmparam.h>
 
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index c85e96d174a5..fc9682bfe002 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -26,9 +26,28 @@
  * The memory barriers are implicit with the load-acquire and store-release
  * instructions.
  */
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	unsigned int tmp;
+	arch_spinlock_t lockval;
 
-#define arch_spin_unlock_wait(lock) \
-	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
+	asm volatile(
+"	sevl\n"
+"1:	wfe\n"
+"2:	ldaxr	%w0, %2\n"
+"	eor	%w1, %w0, %w0, ror #16\n"
+"	cbnz	%w1, 1b\n"
+	ARM64_LSE_ATOMIC_INSN(
+	/* LL/SC */
+"	stxr	%w1, %w0, %2\n"
+"	cbnz	%w1, 2b\n", /* Serialise against any concurrent lockers */
+	/* LSE atomics */
+"	nop\n"
+"	nop\n")
+	: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
+	:
+	: "memory");
+}
 
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
 
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 7318f6d54aa9..801a16dbbdf6 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -16,14 +16,19 @@
 #ifndef __ASM_STACKTRACE_H
 #define __ASM_STACKTRACE_H
 
+struct task_struct;
+
 struct stackframe {
 	unsigned long fp;
 	unsigned long sp;
 	unsigned long pc;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	unsigned int graph;
+#endif
 };
 
-extern int unwind_frame(struct stackframe *frame);
-extern void walk_stackframe(struct stackframe *frame,
+extern int unwind_frame(struct task_struct *tsk, struct stackframe *frame);
+extern void walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
 			    int (*fn)(struct stackframe *, void *), void *data);
 
 #endif	/* __ASM_STACKTRACE_H */
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 90c7ff233735..abd64bd1f6d9 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -73,10 +73,16 @@ register unsigned long current_stack_pointer asm ("sp");
  */
 static inline struct thread_info *current_thread_info(void) __attribute_const__;
 
+/*
+ * struct thread_info can be accessed directly via sp_el0.
+ */
 static inline struct thread_info *current_thread_info(void)
 {
-	return (struct thread_info *)
-		(current_stack_pointer & ~(THREAD_SIZE - 1));
+	unsigned long sp_el0;
+
+	asm ("mrs %0, sp_el0" : "=r" (sp_el0));
+
+	return (struct thread_info *)sp_el0;
 }
 
 #define thread_saved_pc(tsk)	\