summaryrefslogtreecommitdiffstats
path: root/arch/s390/include
diff options
context:
space:
mode:
Diffstat (limited to 'arch/s390/include')
-rw-r--r--arch/s390/include/asm/Kbuild5
-rw-r--r--arch/s390/include/asm/airq.h14
-rw-r--r--arch/s390/include/asm/atomic.h70
-rw-r--r--arch/s390/include/asm/bitops.h49
-rw-r--r--arch/s390/include/asm/ccwdev.h4
-rw-r--r--arch/s390/include/asm/ccwgroup.h1
-rw-r--r--arch/s390/include/asm/checksum.h11
-rw-r--r--arch/s390/include/asm/cio.h2
-rw-r--r--arch/s390/include/asm/compat.h6
-rw-r--r--arch/s390/include/asm/futex.h63
-rw-r--r--arch/s390/include/asm/irq.h19
-rw-r--r--arch/s390/include/asm/kvm_host.h101
-rw-r--r--arch/s390/include/asm/mmu.h2
-rw-r--r--arch/s390/include/asm/mmu_context.h78
-rw-r--r--arch/s390/include/asm/pgalloc.h18
-rw-r--r--arch/s390/include/asm/pgtable.h229
-rw-r--r--arch/s390/include/asm/processor.h1
-rw-r--r--arch/s390/include/asm/ptrace.h1
-rw-r--r--arch/s390/include/asm/sclp.h1
-rw-r--r--arch/s390/include/asm/setup.h6
-rw-r--r--arch/s390/include/asm/switch_to.h1
-rw-r--r--arch/s390/include/asm/thread_info.h5
-rw-r--r--arch/s390/include/asm/tlb.h14
-rw-r--r--arch/s390/include/asm/tlbflush.h115
-rw-r--r--arch/s390/include/asm/uaccess.h169
-rw-r--r--arch/s390/include/uapi/asm/kvm.h43
-rw-r--r--arch/s390/include/uapi/asm/ptrace.h6
27 files changed, 708 insertions, 326 deletions
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 8386a4a1f19..57892a8a905 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -1,6 +1,7 @@
generic-y += clkdev.h
-generic-y += trace_clock.h
-generic-y += preempt.h
generic-y += hash.h
+generic-y += mcs_spinlock.h
+generic-y += preempt.h
+generic-y += trace_clock.h
diff --git a/arch/s390/include/asm/airq.h b/arch/s390/include/asm/airq.h
index 4bbb5957ed1..bd93ff6661b 100644
--- a/arch/s390/include/asm/airq.h
+++ b/arch/s390/include/asm/airq.h
@@ -44,11 +44,21 @@ struct airq_iv {
struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags);
void airq_iv_release(struct airq_iv *iv);
-unsigned long airq_iv_alloc_bit(struct airq_iv *iv);
-void airq_iv_free_bit(struct airq_iv *iv, unsigned long bit);
+unsigned long airq_iv_alloc(struct airq_iv *iv, unsigned long num);
+void airq_iv_free(struct airq_iv *iv, unsigned long bit, unsigned long num);
unsigned long airq_iv_scan(struct airq_iv *iv, unsigned long start,
unsigned long end);
+static inline unsigned long airq_iv_alloc_bit(struct airq_iv *iv)
+{
+ return airq_iv_alloc(iv, 1);
+}
+
+static inline void airq_iv_free_bit(struct airq_iv *iv, unsigned long bit)
+{
+ airq_iv_free(iv, bit, 1);
+}
+
static inline unsigned long airq_iv_end(struct airq_iv *iv)
{
return iv->end;
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index fa9aaf7144b..1d4706114a4 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -15,23 +15,29 @@
#include <linux/compiler.h>
#include <linux/types.h>
+#include <asm/barrier.h>
#include <asm/cmpxchg.h>
#define ATOMIC_INIT(i) { (i) }
+#define __ATOMIC_NO_BARRIER "\n"
+
#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
#define __ATOMIC_OR "lao"
#define __ATOMIC_AND "lan"
#define __ATOMIC_ADD "laa"
+#define __ATOMIC_BARRIER "bcr 14,0\n"
-#define __ATOMIC_LOOP(ptr, op_val, op_string) \
+#define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier) \
({ \
int old_val; \
\
typecheck(atomic_t *, ptr); \
asm volatile( \
+ __barrier \
op_string " %0,%2,%1\n" \
+ __barrier \
: "=d" (old_val), "+Q" ((ptr)->counter) \
: "d" (op_val) \
: "cc", "memory"); \
@@ -43,8 +49,9 @@
#define __ATOMIC_OR "or"
#define __ATOMIC_AND "nr"
#define __ATOMIC_ADD "ar"
+#define __ATOMIC_BARRIER "\n"
-#define __ATOMIC_LOOP(ptr, op_val, op_string) \
+#define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier) \
({ \
int old_val, new_val; \
\
@@ -82,7 +89,7 @@ static inline void atomic_set(atomic_t *v, int i)
static inline int atomic_add_return(int i, atomic_t *v)
{
- return __ATOMIC_LOOP(v, i, __ATOMIC_ADD) + i;
+ return __ATOMIC_LOOP(v, i, __ATOMIC_ADD, __ATOMIC_BARRIER) + i;
}
static inline void atomic_add(int i, atomic_t *v)
@@ -94,12 +101,10 @@ static inline void atomic_add(int i, atomic_t *v)
: "+Q" (v->counter)
: "i" (i)
: "cc", "memory");
- } else {
- atomic_add_return(i, v);
+ return;
}
-#else
- atomic_add_return(i, v);
#endif
+ __ATOMIC_LOOP(v, i, __ATOMIC_ADD, __ATOMIC_NO_BARRIER);
}
#define atomic_add_negative(_i, _v) (atomic_add_return(_i, _v) < 0)
@@ -115,12 +120,12 @@ static inline void atomic_add(int i, atomic_t *v)
static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
{
- __ATOMIC_LOOP(v, ~mask, __ATOMIC_AND);
+ __ATOMIC_LOOP(v, ~mask, __ATOMIC_AND, __ATOMIC_NO_BARRIER);
}
static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
{
- __ATOMIC_LOOP(v, mask, __ATOMIC_OR);
+ __ATOMIC_LOOP(v, mask, __ATOMIC_OR, __ATOMIC_NO_BARRIER);
}
#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
@@ -157,19 +162,24 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
#ifdef CONFIG_64BIT
+#define __ATOMIC64_NO_BARRIER "\n"
+
#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
#define __ATOMIC64_OR "laog"
#define __ATOMIC64_AND "lang"
#define __ATOMIC64_ADD "laag"
+#define __ATOMIC64_BARRIER "bcr 14,0\n"
-#define __ATOMIC64_LOOP(ptr, op_val, op_string) \
+#define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier) \
({ \
long long old_val; \
\
typecheck(atomic64_t *, ptr); \
asm volatile( \
+ __barrier \
op_string " %0,%2,%1\n" \
+ __barrier \
: "=d" (old_val), "+Q" ((ptr)->counter) \
: "d" (op_val) \
: "cc", "memory"); \
@@ -181,8 +191,9 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
#define __ATOMIC64_OR "ogr"
#define __ATOMIC64_AND "ngr"
#define __ATOMIC64_ADD "agr"
+#define __ATOMIC64_BARRIER "\n"
-#define __ATOMIC64_LOOP(ptr, op_val, op_string) \
+#define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier) \
({ \
long long old_val, new_val; \
\
@@ -220,17 +231,32 @@ static inline void atomic64_set(atomic64_t *v, long long i)
static inline long long atomic64_add_return(long long i, atomic64_t *v)
{
- return __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD) + i;
+ return __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_BARRIER) + i;
+}
+
+static inline void atomic64_add(long long i, atomic64_t *v)
+{
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+ if (__builtin_constant_p(i) && (i > -129) && (i < 128)) {
+ asm volatile(
+ "agsi %0,%1\n"
+ : "+Q" (v->counter)
+ : "i" (i)
+ : "cc", "memory");
+ return;
+ }
+#endif
+ __ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_NO_BARRIER);
}
static inline void atomic64_clear_mask(unsigned long mask, atomic64_t *v)
{
- __ATOMIC64_LOOP(v, ~mask, __ATOMIC64_AND);
+ __ATOMIC64_LOOP(v, ~mask, __ATOMIC64_AND, __ATOMIC64_NO_BARRIER);
}
static inline void atomic64_set_mask(unsigned long mask, atomic64_t *v)
{
- __ATOMIC64_LOOP(v, mask, __ATOMIC64_OR);
+ __ATOMIC64_LOOP(v, mask, __ATOMIC64_OR, __ATOMIC64_NO_BARRIER);
}
#define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
@@ -334,25 +360,13 @@ static inline void atomic64_clear_mask(unsigned long long mask, atomic64_t *v)
} while (atomic64_cmpxchg(v, old, new) != old);
}
-#endif /* CONFIG_64BIT */
-
static inline void atomic64_add(long long i, atomic64_t *v)
{
-#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
- if (__builtin_constant_p(i) && (i > -129) && (i < 128)) {
- asm volatile(
- "agsi %0,%1\n"
- : "+Q" (v->counter)
- : "i" (i)
- : "cc", "memory");
- } else {
- atomic64_add_return(i, v);
- }
-#else
atomic64_add_return(i, v);
-#endif
}
+#endif /* CONFIG_64BIT */
+
static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u)
{
long long c, old;
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 6e6ad068082..52054247767 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -13,9 +13,9 @@
*
* The bitop functions are defined to work on unsigned longs, so for an
* s390x system the bits end up numbered:
- * |63..............0|127............64|191...........128|255...........196|
+ * |63..............0|127............64|191...........128|255...........192|
* and on s390:
- * |31.....0|63....31|95....64|127...96|159..128|191..160|223..192|255..224|
+ * |31.....0|63....32|95....64|127...96|159..128|191..160|223..192|255..224|
*
* There are a few little-endian macros used mostly for filesystem
* bitmaps, these work on similar bit arrays layouts, but
@@ -30,7 +30,7 @@
* on an s390x system the bits are numbered:
* |0..............63|64............127|128...........191|192...........255|
* and on s390:
- * |0.....31|31....63|64....95|96...127|128..159|160..191|192..223|224..255|
+ * |0.....31|32....63|64....95|96...127|128..159|160..191|192..223|224..255|
*
* The main difference is that bit 0-63 (64b) or 0-31 (32b) in the bit
* number field needs to be reversed compared to the LSB0 encoded bit
@@ -47,14 +47,18 @@
#include <linux/typecheck.h>
#include <linux/compiler.h>
+#include <asm/barrier.h>
+
+#define __BITOPS_NO_BARRIER "\n"
#ifndef CONFIG_64BIT
#define __BITOPS_OR "or"
#define __BITOPS_AND "nr"
#define __BITOPS_XOR "xr"
+#define __BITOPS_BARRIER "\n"
-#define __BITOPS_LOOP(__addr, __val, __op_string) \
+#define __BITOPS_LOOP(__addr, __val, __op_string, __barrier) \
({ \
unsigned long __old, __new; \
\
@@ -67,7 +71,7 @@
" jl 0b" \
: "=&d" (__old), "=&d" (__new), "+Q" (*(__addr))\
: "d" (__val) \
- : "cc"); \
+ : "cc", "memory"); \
__old; \
})
@@ -78,17 +82,20 @@
#define __BITOPS_OR "laog"
#define __BITOPS_AND "lang"
#define __BITOPS_XOR "laxg"
+#define __BITOPS_BARRIER "bcr 14,0\n"
-#define __BITOPS_LOOP(__addr, __val, __op_string) \
+#define __BITOPS_LOOP(__addr, __val, __op_string, __barrier) \
({ \
unsigned long __old; \
\
typecheck(unsigned long *, (__addr)); \
asm volatile( \
+ __barrier \
__op_string " %0,%2,%1\n" \
+ __barrier \
: "=d" (__old), "+Q" (*(__addr)) \
: "d" (__val) \
- : "cc"); \
+ : "cc", "memory"); \
__old; \
})
@@ -97,8 +104,9 @@
#define __BITOPS_OR "ogr"
#define __BITOPS_AND "ngr"
#define __BITOPS_XOR "xgr"
+#define __BITOPS_BARRIER "\n"
-#define __BITOPS_LOOP(__addr, __val, __op_string) \
+#define __BITOPS_LOOP(__addr, __val, __op_string, __barrier) \
({ \
unsigned long __old, __new; \
\
@@ -111,7 +119,7 @@
" jl 0b" \
: "=&d" (__old), "=&d" (__new), "+Q" (*(__addr))\
: "d" (__val) \
- : "cc"); \
+ : "cc", "memory"); \
__old; \
})
@@ -149,12 +157,12 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *ptr)
"oi %0,%b1\n"
: "+Q" (*caddr)
: "i" (1 << (nr & 7))
- : "cc");
+ : "cc", "memory");
return;
}
#endif
mask = 1UL << (nr & (BITS_PER_LONG - 1));
- __BITOPS_LOOP(addr, mask, __BITOPS_OR);
+ __BITOPS_LOOP(addr, mask, __BITOPS_OR, __BITOPS_NO_BARRIER);
}
static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr)
@@ -170,12 +178,12 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr)
"ni %0,%b1\n"
: "+Q" (*caddr)
: "i" (~(1 << (nr & 7)))
- : "cc");
+ : "cc", "memory");
return;
}
#endif
mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
- __BITOPS_LOOP(addr, mask, __BITOPS_AND);
+ __BITOPS_LOOP(addr, mask, __BITOPS_AND, __BITOPS_NO_BARRIER);
}
static inline void change_bit(unsigned long nr, volatile unsigned long *ptr)
@@ -191,12 +199,12 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *ptr)
"xi %0,%b1\n"
: "+Q" (*caddr)
: "i" (1 << (nr & 7))
- : "cc");
+ : "cc", "memory");
return;
}
#endif
mask = 1UL << (nr & (BITS_PER_LONG - 1));
- __BITOPS_LOOP(addr, mask, __BITOPS_XOR);
+ __BITOPS_LOOP(addr, mask, __BITOPS_XOR, __BITOPS_NO_BARRIER);
}
static inline int
@@ -206,8 +214,7 @@ test_and_set_bit(unsigned long nr, volatile unsigned long *ptr)
unsigned long old, mask;
mask = 1UL << (nr & (BITS_PER_LONG - 1));
- old = __BITOPS_LOOP(addr, mask, __BITOPS_OR);
- barrier();
+ old = __BITOPS_LOOP(addr, mask, __BITOPS_OR, __BITOPS_BARRIER);
return (old & mask) != 0;
}
@@ -218,8 +225,7 @@ test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr)
unsigned long old, mask;
mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
- old = __BITOPS_LOOP(addr, mask, __BITOPS_AND);
- barrier();
+ old = __BITOPS_LOOP(addr, mask, __BITOPS_AND, __BITOPS_BARRIER);
return (old & ~mask) != 0;
}
@@ -230,8 +236,7 @@ test_and_change_bit(unsigned long nr, volatile unsigned long *ptr)
unsigned long old, mask;
mask = 1UL << (nr & (BITS_PER_LONG - 1));
- old = __BITOPS_LOOP(addr, mask, __BITOPS_XOR);
- barrier();
+ old = __BITOPS_LOOP(addr, mask, __BITOPS_XOR, __BITOPS_BARRIER);
return (old & mask) != 0;
}
@@ -304,7 +309,7 @@ static inline int test_bit(unsigned long nr, const volatile unsigned long *ptr)
* On an s390x system the bits are numbered:
* |0..............63|64............127|128...........191|192...........255|
* and on s390:
- * |0.....31|31....63|64....95|96...127|128..159|160..191|192..223|224..255|
+ * |0.....31|32....63|64....95|96...127|128..159|160..191|192..223|224..255|
*/
unsigned long find_first_bit_inv(const unsigned long *addr, unsigned long size);
unsigned long find_next_bit_inv(const unsigned long *addr, unsigned long size,
diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h
index f201af8be58..a9c2c068617 100644
--- a/arch/s390/include/asm/ccwdev.h
+++ b/arch/s390/include/asm/ccwdev.h
@@ -219,7 +219,9 @@ extern void ccw_device_get_id(struct ccw_device *, struct ccw_dev_id *);
#define to_ccwdev(n) container_of(n, struct ccw_device, dev)
#define to_ccwdrv(n) container_of(n, struct ccw_driver, driver)
-extern struct ccw_device *ccw_device_probe_console(void);
+extern struct ccw_device *ccw_device_create_console(struct ccw_driver *);
+extern void ccw_device_destroy_console(struct ccw_device *);
+extern int ccw_device_enable_console(struct ccw_device *);
extern void ccw_device_wait_idle(struct ccw_device *);
extern int ccw_device_force_console(struct ccw_device *);
diff --git a/arch/s390/include/asm/ccwgroup.h b/arch/s390/include/asm/ccwgroup.h
index 23723ce5ca7..6e670f88d12 100644
--- a/arch/s390/include/asm/ccwgroup.h
+++ b/arch/s390/include/asm/ccwgroup.h
@@ -23,6 +23,7 @@ struct ccwgroup_device {
unsigned int count;
struct device dev;
struct ccw_device *cdev[0];
+ struct work_struct ungroup_work;
};
/**
diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h
index 4f57a4f3909..74036485635 100644
--- a/arch/s390/include/asm/checksum.h
+++ b/arch/s390/include/asm/checksum.h
@@ -44,22 +44,15 @@ csum_partial(const void *buff, int len, __wsum sum)
* here even more important to align src and dst on a 32-bit (or even
* better 64-bit) boundary
*
- * Copy from userspace and compute checksum. If we catch an exception
- * then zero the rest of the buffer.
+ * Copy from userspace and compute checksum.
*/
static inline __wsum
csum_partial_copy_from_user(const void __user *src, void *dst,
int len, __wsum sum,
int *err_ptr)
{
- int missing;
-
- missing = copy_from_user(dst, src, len);
- if (missing) {
- memset(dst + len - missing, 0, missing);
+ if (unlikely(copy_from_user(dst, src, len)))
*err_ptr = -EFAULT;
- }
-
return csum_partial(dst, len, sum);
}
diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h
index d42625053c3..09633920776 100644
--- a/arch/s390/include/asm/cio.h
+++ b/arch/s390/include/asm/cio.h
@@ -199,7 +199,7 @@ struct esw_eadm {
/**
* struct irb - interruption response block
* @scsw: subchannel status word
- * @esw: extened status word
+ * @esw: extended status word
* @ecw: extended control word
*
* The irb that is handed to the device driver when an interrupt occurs. For
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 5d7e8cf83bd..d350ed9d0fb 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -8,7 +8,11 @@
#include <linux/thread_info.h>
#define __TYPE_IS_PTR(t) (!__builtin_types_compatible_p(typeof(0?(t)0:0ULL), u64))
-#define __SC_DELOUSE(t,v) (t)(__TYPE_IS_PTR(t) ? ((v) & 0x7fffffff) : (v))
+
+#define __SC_DELOUSE(t,v) ({ \
+ BUILD_BUG_ON(sizeof(t) > 4 && !__TYPE_IS_PTR(t)); \
+ (t)(__TYPE_IS_PTR(t) ? ((v) & 0x7fffffff) : (v)); \
+})
#define PSW32_MASK_PER 0x40000000UL
#define PSW32_MASK_DAT 0x04000000UL
diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h
index 51bcaa0fdee..69cf5b5eddc 100644
--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -1,23 +1,63 @@
#ifndef _ASM_S390_FUTEX_H
#define _ASM_S390_FUTEX_H
-#include <linux/futex.h>
#include <linux/uaccess.h>
+#include <linux/futex.h>
+#include <asm/mmu_context.h>
#include <asm/errno.h>
-static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
+#define __futex_atomic_op(insn, ret, oldval, newval, uaddr, oparg) \
+ asm volatile( \
+ " sacf 256\n" \
+ "0: l %1,0(%6)\n" \
+ "1:"insn \
+ "2: cs %1,%2,0(%6)\n" \
+ "3: jl 1b\n" \
+ " lhi %0,0\n" \
+ "4: sacf 768\n" \
+ EX_TABLE(0b,4b) EX_TABLE(2b,4b) EX_TABLE(3b,4b) \
+ : "=d" (ret), "=&d" (oldval), "=&d" (newval), \
+ "=m" (*uaddr) \
+ : "0" (-EFAULT), "d" (oparg), "a" (uaddr), \
+ "m" (*uaddr) : "cc");
+
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
{
int op = (encoded_op >> 28) & 7;
int cmp = (encoded_op >> 24) & 15;
int oparg = (encoded_op << 8) >> 20;
int cmparg = (encoded_op << 20) >> 20;
- int oldval, ret;
+ int oldval = 0, newval, ret;
+ update_primary_asce(current);
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
oparg = 1 << oparg;
pagefault_disable();
- ret = uaccess.futex_atomic_op(op, uaddr, oparg, &oldval);
+ switch (op) {
+ case FUTEX_OP_SET:
+ __futex_atomic_op("lr %2,%5\n",
+ ret, oldval, newval, uaddr, oparg);
+ break;
+ case FUTEX_OP_ADD:
+ __futex_atomic_op("lr %2,%1\nar %2,%5\n",
+ ret, oldval, newval, uaddr, oparg);
+ break;
+ case FUTEX_OP_OR:
+ __futex_atomic_op("lr %2,%1\nor %2,%5\n",
+ ret, oldval, newval, uaddr, oparg);
+ break;
+ case FUTEX_OP_ANDN:
+ __futex_atomic_op("lr %2,%1\nnr %2,%5\n",
+ ret, oldval, newval, uaddr, oparg);
+ break;
+ case FUTEX_OP_XOR:
+ __futex_atomic_op("lr %2,%1\nxr %2,%5\n",
+ ret, oldval, newval, uaddr, oparg);
+ break;
+ default:
+ ret = -ENOSYS;
+ }
pagefault_enable();
if (!ret) {
@@ -37,7 +77,20 @@ static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
u32 oldval, u32 newval)
{
- return uaccess.futex_atomic_cmpxchg(uval, uaddr, oldval, newval);
+ int ret;
+
+ update_primary_asce(current);
+ asm volatile(
+ " sacf 256\n"
+ "0: cs %1,%4,0(%5)\n"
+ "1: la %0,0\n"
+ "2: sacf 768\n"
+ EX_TABLE(0b,2b) EX_TABLE(1b,2b)
+ : "=d" (ret), "+d" (oldval), "=m" (*uaddr)
+ : "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr)
+ : "cc", "memory");
+ *uval = oldval;
+ return ret;
}
#endif /* _ASM_S390_FUTEX_H */
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index 5f8bcc5fe42..c4dd400a279 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -16,6 +16,20 @@
/* This number is used when no interrupt has been assigned */
#define NO_IRQ 0
+/* External interruption codes */
+#define EXT_IRQ_INTERRUPT_KEY 0x0040
+#define EXT_IRQ_CLK_COMP 0x1004
+#define EXT_IRQ_CPU_TIMER 0x1005
+#define EXT_IRQ_WARNING_TRACK 0x1007
+#define EXT_IRQ_MALFUNC_ALERT 0x1200
+#define EXT_IRQ_EMERGENCY_SIG 0x1201
+#define EXT_IRQ_EXTERNAL_CALL 0x1202
+#define EXT_IRQ_TIMING_ALERT 0x1406
+#define EXT_IRQ_MEASURE_ALERT 0x1407
+#define EXT_IRQ_SERVICE_SIG 0x2401
+#define EXT_IRQ_CP_SERVICE 0x2603
+#define EXT_IRQ_IUCV 0x4000
+
#ifndef __ASSEMBLY__
#include <linux/hardirq.h>
@@ -53,6 +67,7 @@ enum interruption_class {
IRQIO_PCI,
IRQIO_MSI,
IRQIO_VIR,
+ IRQIO_VAI,
NMI_NMI,
CPU_RST,
NR_ARCH_IRQS
@@ -76,8 +91,8 @@ struct ext_code {
typedef void (*ext_int_handler_t)(struct ext_code, unsigned int, unsigned long);
-int register_external_interrupt(u16 code, ext_int_handler_t handler);
-int unregister_external_interrupt(u16 code, ext_int_handler_t handler);
+int register_external_irq(u16 code, ext_int_handler_t handler);
+int unregister_external_irq(u16 code, ext_int_handler_t handler);
enum irq_subclass {
IRQ_SUBCLASS_MEASUREMENT_ALERT = 5,
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index eef3dd3fd9a..154b60089be 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -16,12 +16,22 @@
#include <linux/hrtimer.h>
#include <linux/interrupt.h>
#include <linux/kvm_host.h>
+#include <linux/kvm.h>
#include <asm/debug.h>
#include <asm/cpu.h>
+#include <asm/isc.h>
#define KVM_MAX_VCPUS 64
#define KVM_USER_MEM_SLOTS 32
+/*
+ * These seem to be used for allocating ->chip in the routing table,
+ * which we don't use. 4096 is an out-of-thin-air value. If we need
+ * to look at ->chip later on, we'll need to revisit this.
+ */
+#define KVM_NR_IRQCHIPS 1
+#define KVM_IRQCHIP_NUM_PINS 4096
+
struct sca_entry {
atomic_t scn;
__u32 reserved;
@@ -106,7 +116,11 @@ struct kvm_s390_sie_block {
__u64 gbea; /* 0x0180 */
__u8 reserved188[24]; /* 0x0188 */
__u32 fac; /* 0x01a0 */
- __u8 reserved1a4[68]; /* 0x01a4 */
+ __u8 reserved1a4[20]; /* 0x01a4 */
+ __u64 cbrlo; /* 0x01b8 */
+ __u8 reserved1c0[30]; /* 0x01c0 */
+ __u64 pp; /* 0x01de */
+ __u8 reserved1e6[2]; /* 0x01e6 */
__u64 itdba; /* 0x01e8 */
__u8 reserved1f0[16]; /* 0x01f0 */
} __attribute__((packed));
@@ -155,6 +169,7 @@ struct kvm_vcpu_stat {
u32 instruction_stsi;
u32 instruction_stfl;
u32 instruction_tprot;
+ u32 instruction_essa;
u32 instruction_sigp_sense;
u32 instruction_sigp_sense_running;
u32 instruction_sigp_external_call;
@@ -168,18 +183,6 @@ struct kvm_vcpu_stat {
u32 diagnose_9c;
};
-struct kvm_s390_io_info {
- __u16 subchannel_id; /* 0x0b8 */
- __u16 subchannel_nr; /* 0x0ba */
- __u32 io_int_parm; /* 0x0bc */
- __u32 io_int_word; /* 0x0c0 */
-};
-
-struct kvm_s390_ext_info {
- __u32 ext_params;
- __u64 ext_params2;
-};
-
#define PGM_OPERATION 0x01
#define PGM_PRIVILEGED_OP 0x02
#define PGM_EXECUTE 0x03
@@ -188,27 +191,6 @@ struct kvm_s390_ext_info {
#define PGM_SPECIFICATION 0x06
#define PGM_DATA 0x07
-struct kvm_s390_pgm_info {
- __u16 code;
-};
-
-struct kvm_s390_prefix_info {
- __u32 address;
-};
-
-struct kvm_s390_extcall_info {
- __u16 code;
-};
-
-struct kvm_s390_emerg_info {
- __u16 code;
-};
-
-struct kvm_s390_mchk_info {
- __u64 cr14;
- __u64 mcic;
-};
-
struct kvm_s390_interrupt_info {
struct list_head list;
u64 type;
@@ -243,9 +225,8 @@ struct kvm_s390_float_interrupt {
struct list_head list;
atomic_t active;
int next_rr_cpu;
- unsigned long idle_mask[(KVM_MAX_VCPUS + sizeof(long) - 1)
- / sizeof(long)];
- struct kvm_s390_local_interrupt *local_int[KVM_MAX_VCPUS];
+ unsigned long idle_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)];
+ unsigned int irq_count;
};
@@ -262,6 +243,10 @@ struct kvm_vcpu_arch {
u64 stidp_data;
};
struct gmap *gmap;
+#define KVM_S390_PFAULT_TOKEN_INVALID (-1UL)
+ unsigned long pfault_token;
+ unsigned long pfault_select;
+ unsigned long pfault_compare;
};
struct kvm_vm_stat {
@@ -271,12 +256,36 @@ struct kvm_vm_stat {
struct kvm_arch_memory_slot {
};
+struct s390_map_info {
+ struct list_head list;
+ __u64 guest_addr;
+ __u64 addr;
+ struct page *page;
+};
+
+struct s390_io_adapter {
+ unsigned int id;
+ int isc;
+ bool maskable;
+ bool masked;
+ bool swap;
+ struct rw_semaphore maps_lock;
+ struct list_head maps;
+ atomic_t nr_maps;
+};
+
+#define MAX_S390_IO_ADAPTERS ((MAX_ISC + 1) * 8)
+#define MAX_S390_ADAPTER_MAPS 256
+
struct kvm_arch{
struct sca_block *sca;
debug_info_t *dbf;
struct kvm_s390_float_interrupt float_int;
+ struct kvm_device *flic;
struct gmap *gmap;
int css_support;
+ int use_irqchip;
+ struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
};
#define KVM_HVA_ERR_BAD (-1UL)
@@ -287,6 +296,24 @@ static inline bool kvm_is_error_hva(unsigned long addr)
return IS_ERR_VALUE(addr);
}
+#define ASYNC_PF_PER_VCPU 64
+struct kvm_vcpu;
+struct kvm_async_pf;
+struct kvm_arch_async_pf {
+ unsigned long pfault_token;
+};
+
+bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu);
+
+void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work);
+
+void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work);
+
+void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work);
+
extern int sie64a(struct kvm_s390_sie_block *, u64 *);
extern char sie_exit;
#endif
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index ff132ac64dd..f77695a82f6 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -1,9 +1,11 @@
#ifndef __MMU_H
#define __MMU_H
+#include <linux/cpumask.h>
#include <linux/errno.h>
typedef struct {
+ cpumask_t cpu_attach_mask;
atomic_t attach_count;
unsigned int flush_mm;
spinlock_t list_lock;
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 5d1f950704d..71be346d0e3 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -15,6 +15,7 @@
static inline int init_new_context(struct task_struct *tsk,
struct mm_struct *mm)
{
+ cpumask_clear(&mm->context.cpu_attach_mask);
atomic_set(&mm->context.attach_count, 0);
mm->context.flush_mm = 0;
mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS;
@@ -29,32 +30,81 @@ static inline int init_new_context(struct task_struct *tsk,
#define destroy_context(mm) do { } while (0)
-#ifndef CONFIG_64BIT
-#define LCTL_OPCODE "lctl"
-#else
-#define LCTL_OPCODE "lctlg"
-#endif
-
-static inline void update_mm(struct mm_struct *mm, struct task_struct *tsk)
+static inline void update_user_asce(struct mm_struct *mm, int load_primary)
{
pgd_t *pgd = mm->pgd;
S390_lowcore.user_asce = mm->context.asce_bits | __pa(pgd);
- /* Load primary space page table origin. */
- asm volatile(LCTL_OPCODE" 1,1,%0\n" : : "m" (S390_lowcore.user_asce));
+ if (load_primary)
+ __ctl_load(S390_lowcore.user_asce, 1, 1);
set_fs(current->thread.mm_segment);
}
+static inline void clear_user_asce(struct mm_struct *mm, int load_primary)
+{
+ S390_lowcore.user_asce = S390_lowcore.kernel_asce;
+
+ if (load_primary)
+ __ctl_load(S390_lowcore.user_asce, 1, 1);
+ __ctl_load(S390_lowcore.user_asce, 7, 7);
+}
+
+static inline void update_primary_asce(struct task_struct *tsk)
+{
+ unsigned long asce;
+
+ __ctl_store(asce, 1, 1);
+ if (asce != S390_lowcore.kernel_asce)
+ __ctl_load(S390_lowcore.kernel_asce, 1, 1);
+ set_tsk_thread_flag(tsk, TIF_ASCE);
+}
+
static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk)
{
- cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
- update_mm(next, tsk);
+ int cpu = smp_processor_id();
+
+ update_primary_asce(tsk);
+ if (prev == next)
+ return;
+ if (MACHINE_HAS_TLB_LC)
+ cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
+ if (atomic_inc_return(&next->context.attach_count) >> 16) {
+ /* Delay update_user_asce until all TLB flushes are done. */
+ set_tsk_thread_flag(tsk, TIF_TLB_WAIT);
+ /* Clear old ASCE by loading the kernel ASCE. */
+ clear_user_asce(next, 0);
+ } else {
+ cpumask_set_cpu(cpu, mm_cpumask(next));
+ update_user_asce(next, 0);
+ if (next->context.flush_mm)
+ /* Flush pending TLBs */
+ __tlb_flush_mm(next);
+ }
atomic_dec(&prev->context.attach_count);
WARN_ON(atomic_read(&prev->context.attach_count) < 0);
- atomic_inc(&next->context.attach_count);
- /* Check for TLBs not flushed yet */
- __tlb_flush_mm_lazy(next);
+ if (MACHINE_HAS_TLB_LC)
+ cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
+}
+
+#define finish_arch_post_lock_switch finish_arch_post_lock_switch
+static inline void finish_arch_post_lock_switch(void)
+{
+ struct task_struct *tsk = current;
+ struct mm_struct *mm = tsk->mm;
+
+ if (!test_tsk_thread_flag(tsk, TIF_TLB_WAIT))
+ return;
+ preempt_disable();
+ clear_tsk_thread_flag(tsk, TIF_TLB_WAIT);
+ while (atomic_read(&mm->context.attach_count) >> 16)
+ cpu_relax();
+
+ cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
+ update_user_asce(mm, 0);
+ if (mm->context.flush_mm)
+ __tlb_flush_mm(mm);
+ preempt_enable();
}
#define enter_lazy_tlb(mm,tsk) do { } while (0)
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index e1408ddb94f..884017cbfa9 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -22,6 +22,7 @@ unsigned long *page_table_alloc(struct mm_struct *, unsigned long);
void page_table_free(struct mm_struct *, unsigned long *);
void page_table_free_rcu(struct mmu_gather *, unsigned long *);
+void page_table_reset_pgste(struct mm_struct *, unsigned long, unsigned long);
int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
unsigned long key, bool nq);
@@ -91,11 +92,22 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
{
unsigned long *table = crst_table_alloc(mm);
- if (table)
- crst_table_init(table, _SEGMENT_ENTRY_EMPTY);
+
+ if (!table)
+ return NULL;
+ crst_table_init(table, _SEGMENT_ENTRY_EMPTY);
+ if (!pgtable_pmd_page_ctor(virt_to_page(table))) {
+ crst_table_free(mm, table);
+ return NULL;
+ }
return (pmd_t *) table;
}
-#define pmd_free(mm, pmd) crst_table_free(mm, (unsigned long *) pmd)
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+ pgtable_pmd_page_dtor(virt_to_page(pmd));
+ crst_table_free(mm, (unsigned long *) pmd);
+}
static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
{
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 2204400d0bd..12f75313e08 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -229,6 +229,7 @@ extern unsigned long MODULES_END;
#define _PAGE_READ 0x010 /* SW pte read bit */
#define _PAGE_WRITE 0x020 /* SW pte write bit */
#define _PAGE_SPECIAL 0x040 /* SW associated with special page */
+#define _PAGE_UNUSED 0x080 /* SW bit for pgste usage state */
#define __HAVE_ARCH_PTE_SPECIAL
/* Set of bits not changed in pte_modify */
@@ -394,6 +395,12 @@ extern unsigned long MODULES_END;
#endif /* CONFIG_64BIT */
+/* Guest Page State used for virtualization */
+#define _PGSTE_GPS_ZERO 0x0000000080000000UL
+#define _PGSTE_GPS_USAGE_MASK 0x0000000003000000UL
+#define _PGSTE_GPS_USAGE_STABLE 0x0000000000000000UL
+#define _PGSTE_GPS_USAGE_UNUSED 0x0000000001000000UL
+
/*
* A user page table pointer has the space-switch-event bit, the
* private-space-control bit and the storage-alteration-event-control
@@ -617,6 +624,14 @@ static inline int pte_none(pte_t pte)
return pte_val(pte) == _PAGE_INVALID;
}
+static inline int pte_swap(pte_t pte)
+{
+ /* Bit pattern: (pte & 0x603) == 0x402 */
+ return (pte_val(pte) & (_PAGE_INVALID | _PAGE_PROTECT |
+ _PAGE_TYPE | _PAGE_PRESENT))
+ == (_PAGE_INVALID | _PAGE_TYPE);
+}
+
static inline int pte_file(pte_t pte)
{
/* Bit pattern: (pte & 0x601) == 0x600 */
@@ -767,6 +782,7 @@ static inline void pgste_set_pte(pte_t *ptep, pte_t entry)
* @table: pointer to the page directory
* @asce: address space control element for gmap page table
* @crst_list: list of all crst tables used in the guest address space
+ * @pfault_enabled: defines if pfaults are applicable for the guest
*/
struct gmap {
struct list_head list;
@@ -775,6 +791,7 @@ struct gmap {
unsigned long asce;
void *private;
struct list_head crst_list;
+ bool pfault_enabled;
};
/**
@@ -821,20 +838,20 @@ unsigned long gmap_translate(unsigned long address, struct gmap *);
unsigned long __gmap_fault(unsigned long address, struct gmap *);
unsigned long gmap_fault(unsigned long address, struct gmap *);
void gmap_discard(unsigned long from, unsigned long to, struct gmap *);
+void __gmap_zap(unsigned long address, struct gmap *);
void gmap_register_ipte_notifier(struct gmap_notifier *);
void gmap_unregister_ipte_notifier(struct gmap_notifier *);
int gmap_ipte_notify(struct gmap *, unsigned long start, unsigned long len);
-void gmap_do_ipte_notify(struct mm_struct *, unsigned long addr, pte_t *);
+void gmap_do_ipte_notify(struct mm_struct *, pte_t *);
static inline pgste_t pgste_ipte_notify(struct mm_struct *mm,
- unsigned long addr,
pte_t *ptep, pgste_t pgste)
{
#ifdef CONFIG_PGSTE
if (pgste_val(pgste) & PGSTE_IN_BIT) {
pgste_val(pgste) &= ~PGSTE_IN_BIT;
- gmap_do_ipte_notify(mm, addr, ptep);
+ gmap_do_ipte_notify(mm, ptep);
}
#endif
return pgste;
@@ -852,6 +869,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
if (mm_has_pgste(mm)) {
pgste = pgste_get_lock(ptep);
+ pgste_val(pgste) &= ~_PGSTE_GPS_ZERO;
pgste_set_key(ptep, pgste, entry);
pgste_set_pte(ptep, entry);
pgste_set_unlock(ptep, pgste);
@@ -881,6 +899,12 @@ static inline int pte_young(pte_t pte)
return (pte_val(pte) & _PAGE_YOUNG) != 0;
}
+#define __HAVE_ARCH_PTE_UNUSED
+static inline int pte_unused(pte_t pte)
+{
+ return pte_val(pte) & _PAGE_UNUSED;
+}
+
/*
* pgd/pmd/pte modification functions
*/
@@ -1034,30 +1058,64 @@ static inline int ptep_test_and_clear_user_young(struct mm_struct *mm,
static inline void __ptep_ipte(unsigned long address, pte_t *ptep)
{
- if (!(pte_val(*ptep) & _PAGE_INVALID)) {
+ unsigned long pto = (unsigned long) ptep;
+
#ifndef CONFIG_64BIT
- /* pto must point to the start of the segment table */
- pte_t *pto = (pte_t *) (((unsigned long) ptep) & 0x7ffffc00);
-#else
- /* ipte in zarch mode can do the math */
- pte_t *pto = ptep;
+ /* pto in ESA mode must point to the start of the segment table */
+ pto &= 0x7ffffc00;
#endif
- asm volatile(
- " ipte %2,%3"
- : "=m" (*ptep) : "m" (*ptep),
- "a" (pto), "a" (address));
- }
+ /* Invalidation + global TLB flush for the pte */
+ asm volatile(
+ " ipte %2,%3"
+ : "=m" (*ptep) : "m" (*ptep), "a" (pto), "a" (address));
+}
+
+static inline void __ptep_ipte_local(unsigned long address, pte_t *ptep)
+{
+ unsigned long pto = (unsigned long) ptep;
+
+#ifndef CONFIG_64BIT
+ /* pto in ESA mode must point to the start of the segment table */
+ pto &= 0x7ffffc00;
+#endif
+ /* Invalidation + local TLB flush for the pte */
+ asm volatile(
+ " .insn rrf,0xb2210000,%2,%3,0,1"
+ : "=m" (*ptep) : "m" (*ptep), "a" (pto), "a" (address));
+}
+
+static inline void ptep_flush_direct(struct mm_struct *mm,
+ unsigned long address, pte_t *ptep)
+{
+ int active, count;
+
+ if (pte_val(*ptep) & _PAGE_INVALID)
+ return;
+ active = (mm == current->active_mm) ? 1 : 0;
+ count = atomic_add_return(0x10000, &mm->context.attach_count);
+ if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
+ cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
+ __ptep_ipte_local(address, ptep);
+ else
+ __ptep_ipte(address, ptep);
+ atomic_sub(0x10000, &mm->context.attach_count);
}
static inline void ptep_flush_lazy(struct mm_struct *mm,
unsigned long address, pte_t *ptep)
{
- int active = (mm == current->active_mm) ? 1 : 0;
+ int active, count;
- if (atomic_read(&mm->context.attach_count) > active)
- __ptep_ipte(address, ptep);
- else
+ if (pte_val(*ptep) & _PAGE_INVALID)
+ return;
+ active = (mm == current->active_mm) ? 1 : 0;
+ count = atomic_add_return(0x10000, &mm->context.attach_count);
+ if ((count & 0xffff) <= active) {
+ pte_val(*ptep) |= _PAGE_INVALID;
mm->context.flush_mm = 1;
+ } else
+ __ptep_ipte(address, ptep);
+ atomic_sub(0x10000, &mm->context.attach_count);
}
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
@@ -1070,11 +1128,11 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
if (mm_has_pgste(vma->vm_mm)) {
pgste = pgste_get_lock(ptep);
- pgste = pgste_ipte_notify(vma->vm_mm, addr, ptep, pgste);
+ pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste);
}
pte = *ptep;
- __ptep_ipte(addr, ptep);
+ ptep_flush_direct(vma->vm_mm, addr, ptep);
young = pte_young(pte);
pte = pte_mkold(pte);
@@ -1116,7 +1174,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
if (mm_has_pgste(mm)) {
pgste = pgste_get_lock(ptep);
- pgste = pgste_ipte_notify(mm, address, ptep, pgste);
+ pgste = pgste_ipte_notify(mm, ptep, pgste);
}
pte = *ptep;
@@ -1140,12 +1198,11 @@ static inline pte_t ptep_modify_prot_start(struct mm_struct *mm,
if (mm_has_pgste(mm)) {
pgste = pgste_get_lock(ptep);
- pgste_ipte_notify(mm, address, ptep, pgste);
+ pgste_ipte_notify(mm, ptep, pgste);
}
pte = *ptep;
ptep_flush_lazy(mm, address, ptep);
- pte_val(*ptep) |= _PAGE_INVALID;
if (mm_has_pgste(mm)) {
pgste = pgste_update_all(&pte, pgste);
@@ -1178,14 +1235,17 @@ static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,
if (mm_has_pgste(vma->vm_mm)) {
pgste = pgste_get_lock(ptep);
- pgste = pgste_ipte_notify(vma->vm_mm, address, ptep, pgste);
+ pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste);
}
pte = *ptep;
- __ptep_ipte(address, ptep);
+ ptep_flush_direct(vma->vm_mm, address, ptep);
pte_val(*ptep) = _PAGE_INVALID;
if (mm_has_pgste(vma->vm_mm)) {
+ if ((pgste_val(pgste) & _PGSTE_GPS_USAGE_MASK) ==
+ _PGSTE_GPS_USAGE_UNUSED)
+ pte_val(pte) |= _PAGE_UNUSED;
pgste = pgste_update_all(&pte, pgste);
pgste_set_unlock(ptep, pgste);
}
@@ -1209,7 +1269,7 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
if (!full && mm_has_pgste(mm)) {
pgste = pgste_get_lock(ptep);
- pgste = pgste_ipte_notify(mm, address, ptep, pgste);
+ pgste = pgste_ipte_notify(mm, ptep, pgste);
}
pte = *ptep;
@@ -1234,7 +1294,7 @@ static inline pte_t ptep_set_wrprotect(struct mm_struct *mm,
if (pte_write(pte)) {
if (mm_has_pgste(mm)) {
pgste = pgste_get_lock(ptep);
- pgste = pgste_ipte_notify(mm, address, ptep, pgste);
+ pgste = pgste_ipte_notify(mm, ptep, pgste);
}
ptep_flush_lazy(mm, address, ptep);
@@ -1260,10 +1320,10 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
return 0;
if (mm_has_pgste(vma->vm_mm)) {
pgste = pgste_get_lock(ptep);
- pgste = pgste_ipte_notify(vma->vm_mm, address, ptep, pgste);
+ pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste);
}
- __ptep_ipte(address, ptep);
+ ptep_flush_direct(vma->vm_mm, address, ptep);
if (mm_has_pgste(vma->vm_mm)) {
pgste_set_pte(ptep, entry);
@@ -1347,35 +1407,6 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
#define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
#define pte_unmap(pte) do { } while (0)
-static inline void __pmd_idte(unsigned long address, pmd_t *pmdp)
-{
- unsigned long sto = (unsigned long) pmdp -
- pmd_index(address) * sizeof(pmd_t);
-
- if (!(pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)) {
- asm volatile(
- " .insn rrf,0xb98e0000,%2,%3,0,0"
- : "=m" (*pmdp)
- : "m" (*pmdp), "a" (sto),
- "a" ((address & HPAGE_MASK))
- : "cc"
- );
- }
-}
-
-static inline void __pmd_csp(pmd_t *pmdp)
-{
- register unsigned long reg2 asm("2") = pmd_val(*pmdp);
- register unsigned long reg3 asm("3") = pmd_val(*pmdp) |
- _SEGMENT_ENTRY_INVALID;
- register unsigned long reg4 asm("4") = ((unsigned long) pmdp) + 5;
-
- asm volatile(
- " csp %1,%3"
- : "=m" (*pmdp)
- : "d" (reg2), "d" (reg3), "d" (reg4), "m" (*pmdp) : "cc");
-}
-
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)
static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot)
{
@@ -1444,15 +1475,81 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd)
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLB_PAGE */
+static inline void __pmdp_csp(pmd_t *pmdp)
+{
+ register unsigned long reg2 asm("2") = pmd_val(*pmdp);
+ register unsigned long reg3 asm("3") = pmd_val(*pmdp) |
+ _SEGMENT_ENTRY_INVALID;
+ register unsigned long reg4 asm("4") = ((unsigned long) pmdp) + 5;
+
+ asm volatile(
+ " csp %1,%3"
+ : "=m" (*pmdp)
+ : "d" (reg2), "d" (reg3), "d" (reg4), "m" (*pmdp) : "cc");
+}
+
+static inline void __pmdp_idte(unsigned long address, pmd_t *pmdp)
+{
+ unsigned long sto;
+
+ sto = (unsigned long) pmdp - pmd_index(address) * sizeof(pmd_t);
+ asm volatile(
+ " .insn rrf,0xb98e0000,%2,%3,0,0"
+ : "=m" (*pmdp)
+ : "m" (*pmdp), "a" (sto), "a" ((address & HPAGE_MASK))
+ : "cc" );
+}
+
+static inline void __pmdp_idte_local(unsigned long address, pmd_t *pmdp)
+{
+ unsigned long sto;
+
+ sto = (unsigned long) pmdp - pmd_index(address) * sizeof(pmd_t);
+ asm volatile(
+ " .insn rrf,0xb98e0000,%2,%3,0,1"
+ : "=m" (*pmdp)
+ : "m" (*pmdp), "a" (sto), "a" ((address & HPAGE_MASK))
+ : "cc" );
+}
+
+static inline void pmdp_flush_direct(struct mm_struct *mm,
+ unsigned long address, pmd_t *pmdp)
+{
+ int active, count;
+
+ if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
+ return;
+ if (!MACHINE_HAS_IDTE) {
+ __pmdp_csp(pmdp);
+ return;
+ }
+ active = (mm == current->active_mm) ? 1 : 0;
+ count = atomic_add_return(0x10000, &mm->context.attach_count);
+ if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
+ cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
+ __pmdp_idte_local(address, pmdp);
+ else
+ __pmdp_idte(address, pmdp);
+ atomic_sub(0x10000, &mm->context.attach_count);
+}
+
static inline void pmdp_flush_lazy(struct mm_struct *mm,
unsigned long address, pmd_t *pmdp)
{
- int active = (mm == current->active_mm) ? 1 : 0;
+ int active, count;
- if ((atomic_read(&mm->context.attach_count) & 0xffff) > active)
- __pmd_idte(address, pmdp);
- else
+ if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
+ return;
+ active = (mm == current->active_mm) ? 1 : 0;
+ count = atomic_add_return(0x10000, &mm->context.attach_count);
+ if ((count & 0xffff) <= active) {
+ pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID;
mm->context.flush_mm = 1;
+ } else if (MACHINE_HAS_IDTE)
+ __pmdp_idte(address, pmdp);
+ else
+ __pmdp_csp(pmdp);
+ atomic_sub(0x10000, &mm->context.attach_count);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -1504,7 +1601,7 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
pmd_t pmd;
pmd = *pmdp;
- __pmd_idte(address, pmdp);
+ pmdp_flush_direct(vma->vm_mm, address, pmdp);
*pmdp = pmd_mkold(pmd);
return pmd_young(pmd);
}
@@ -1515,7 +1612,7 @@ static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
{
pmd_t pmd = *pmdp;
- __pmd_idte(address, pmdp);
+ pmdp_flush_direct(mm, address, pmdp);
pmd_clear(pmdp);
return pmd;
}
@@ -1531,7 +1628,7 @@ static inline pmd_t pmdp_clear_flush(struct vm_area_struct *vma,
static inline void pmdp_invalidate(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp)
{
- __pmd_idte(address, pmdp);
+ pmdp_flush_direct(vma->vm_mm, address, pmdp);
}
#define __HAVE_ARCH_PMDP_SET_WRPROTECT
@@ -1541,7 +1638,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
pmd_t pmd = *pmdp;
if (pmd_write(pmd)) {
- __pmd_idte(address, pmdp);
+ pmdp_flush_direct(mm, address, pmdp);
set_pmd_at(mm, address, pmdp, pmd_wrprotect(pmd));
}
}
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 0a876bc543d..dc5fc4f90e5 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -79,6 +79,7 @@ struct thread_struct {
unsigned long ksp; /* kernel stack pointer */
mm_segment_t mm_segment;
unsigned long gmap_addr; /* address of last gmap fault. */
+ unsigned int gmap_pfault; /* signal of a pending guest pfault */
struct per_regs per_user; /* User specified PER registers */
struct per_event per_event; /* Cause of the last PER trap */
unsigned long per_flags; /* Flags to control debug behavior */
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index 9c82cebddab..f4783c0b7b4 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -83,6 +83,7 @@ struct per_struct_kernel {
* These are defined as per linux/ptrace.h, which see.
*/
#define arch_has_single_step() (1)
+#define arch_has_block_step() (1)
#define user_mode(regs) (((regs)->psw.mask & PSW_MASK_PSTATE) != 0)
#define instruction_pointer(regs) ((regs)->psw.addr & PSW_ADDR_INSN)
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index abaca2275c7..2f5e9932b4d 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -46,6 +46,7 @@ int sclp_cpu_configure(u8 cpu);
int sclp_cpu_deconfigure(u8 cpu);
unsigned long long sclp_get_rnmax(void);
unsigned long long sclp_get_rzm(void);
+unsigned int sclp_get_max_cpu(void);
int sclp_sdias_blk_count(void);
int sclp_sdias_copy(void *dest, int blk_num, int nr_blks);
int sclp_chp_configure(struct chp_id chpid);
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 94cfbe442f1..b31b22dba94 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -59,7 +59,6 @@ void create_mem_hole(struct mem_chunk mem_chunk[], unsigned long addr,
#define MACHINE_FLAG_DIAG44 (1UL << 4)
#define MACHINE_FLAG_IDTE (1UL << 5)
#define MACHINE_FLAG_DIAG9C (1UL << 6)
-#define MACHINE_FLAG_MVCOS (1UL << 7)
#define MACHINE_FLAG_KVM (1UL << 8)
#define MACHINE_FLAG_ESOP (1UL << 9)
#define MACHINE_FLAG_EDAT1 (1UL << 10)
@@ -69,6 +68,7 @@ void create_mem_hole(struct mem_chunk mem_chunk[], unsigned long addr,
#define MACHINE_FLAG_TOPOLOGY (1UL << 14)
#define MACHINE_FLAG_TE (1UL << 15)
#define MACHINE_FLAG_RRBM (1UL << 16)
+#define MACHINE_FLAG_TLB_LC (1UL << 17)
#define MACHINE_IS_VM (S390_lowcore.machine_flags & MACHINE_FLAG_VM)
#define MACHINE_IS_KVM (S390_lowcore.machine_flags & MACHINE_FLAG_KVM)
@@ -85,26 +85,26 @@ void create_mem_hole(struct mem_chunk mem_chunk[], unsigned long addr,
#define MACHINE_HAS_IDTE (0)
#define MACHINE_HAS_DIAG44 (1)
#define MACHINE_HAS_MVPG (S390_lowcore.machine_flags & MACHINE_FLAG_MVPG)
-#define MACHINE_HAS_MVCOS (0)
#define MACHINE_HAS_EDAT1 (0)
#define MACHINE_HAS_EDAT2 (0)
#define MACHINE_HAS_LPP (0)
#define MACHINE_HAS_TOPOLOGY (0)
#define MACHINE_HAS_TE (0)
#define MACHINE_HAS_RRBM (0)
+#define MACHINE_HAS_TLB_LC (0)
#else /* CONFIG_64BIT */
#define MACHINE_HAS_IEEE (1)
#define MACHINE_HAS_CSP (1)
#define MACHINE_HAS_IDTE (S390_lowcore.machine_flags & MACHINE_FLAG_IDTE)
#define MACHINE_HAS_DIAG44 (S390_lowcore.machine_flags & MACHINE_FLAG_DIAG44)
#define MACHINE_HAS_MVPG (1)
-#define MACHINE_HAS_MVCOS (S390_lowcore.machine_flags & MACHINE_FLAG_MVCOS)
#define MACHINE_HAS_EDAT1 (S390_lowcore.machine_flags & MACHINE_FLAG_EDAT1)
#define MACHINE_HAS_EDAT2 (S390_lowcore.machine_flags & MACHINE_FLAG_EDAT2)
#define MACHINE_HAS_LPP (S390_lowcore.machine_flags & MACHINE_FLAG_LPP)
#define MACHINE_HAS_TOPOLOGY (S390_lowcore.machine_flags & MACHINE_FLAG_TOPOLOGY)
#define MACHINE_HAS_TE (S390_lowcore.machine_flags & MACHINE_FLAG_TE)
#define MACHINE_HAS_RRBM (S390_lowcore.machine_flags & MACHINE_FLAG_RRBM)
+#define MACHINE_HAS_TLB_LC (S390_lowcore.machine_flags & MACHINE_FLAG_TLB_LC)
#endif /* CONFIG_64BIT */
/*
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index 29c81f82705..e759181357f 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -132,6 +132,7 @@ static inline void restore_access_regs(unsigned int *acrs)
update_cr_regs(next); \
} \
prev = __switch_to(prev,next); \
+ update_primary_asce(current); \
} while (0)
#define finish_arch_switch(prev) do { \
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 10e0fcd3633..50630e6a35d 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -81,6 +81,8 @@ static inline struct thread_info *current_thread_info(void)
#define TIF_NOTIFY_RESUME 1 /* callback before returning to user */
#define TIF_SIGPENDING 2 /* signal pending */
#define TIF_NEED_RESCHED 3 /* rescheduling necessary */
+#define TIF_TLB_WAIT 4 /* wait for TLB flush completion */
+#define TIF_ASCE 5 /* primary asce needs fixup / uaccess */
#define TIF_PER_TRAP 6 /* deliver sigtrap on return to user */
#define TIF_MCCK_PENDING 7 /* machine check handling is pending */
#define TIF_SYSCALL_TRACE 8 /* syscall trace active */
@@ -91,11 +93,14 @@ static inline struct thread_info *current_thread_info(void)
#define TIF_MEMDIE 18 /* is terminating due to OOM killer */
#define TIF_RESTORE_SIGMASK 19 /* restore signal mask in do_signal() */
#define TIF_SINGLE_STEP 20 /* This task is single stepped */
+#define TIF_BLOCK_STEP 21 /* This task is block stepped */
#define _TIF_SYSCALL (1<<TIF_SYSCALL)
#define _TIF_NOTIFY_RESUME (1<<TIF_NOTIFY_RESUME)
#define _TIF_SIGPENDING (1<<TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1<<TIF_NEED_RESCHED)
+#define _TIF_TLB_WAIT (1<<TIF_TLB_WAIT)
+#define _TIF_ASCE (1<<TIF_ASCE)
#define _TIF_PER_TRAP (1<<TIF_PER_TRAP)
#define _TIF_MCCK_PENDING (1<<TIF_MCCK_PENDING)
#define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE)
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 2cb846c4b37..c544b6f05d9 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -57,8 +57,6 @@ static inline void tlb_gather_mmu(struct mmu_gather *tlb,
tlb->end = end;
tlb->fullmm = !(start | (end+1));
tlb->batch = NULL;
- if (tlb->fullmm)
- __tlb_flush_mm(mm);
}
static inline void tlb_flush_mmu(struct mmu_gather *tlb)
@@ -96,9 +94,7 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
unsigned long address)
{
- if (!tlb->fullmm)
- return page_table_free_rcu(tlb, (unsigned long *) pte);
- page_table_free(tlb->mm, (unsigned long *) pte);
+ page_table_free_rcu(tlb, (unsigned long *) pte);
}
/*
@@ -114,9 +110,7 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
#ifdef CONFIG_64BIT
if (tlb->mm->context.asce_limit <= (1UL << 31))
return;
- if (!tlb->fullmm)
- return tlb_remove_table(tlb, pmd);
- crst_table_free(tlb->mm, (unsigned long *) pmd);
+ tlb_remove_table(tlb, pmd);
#endif
}
@@ -133,9 +127,7 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
#ifdef CONFIG_64BIT
if (tlb->mm->context.asce_limit <= (1UL << 42))
return;
- if (!tlb->fullmm)
- return tlb_remove_table(tlb, pud);
- crst_table_free(tlb->mm, (unsigned long *) pud);
+ tlb_remove_table(tlb, pud);
#endif
}
diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h
index f9fef0425fe..16c9c88658c 100644
--- a/arch/s390/include/asm/tlbflush.h
+++ b/arch/s390/include/asm/tlbflush.h
@@ -7,19 +7,41 @@
#include <asm/pgalloc.h>
/*
- * Flush all tlb entries on the local cpu.
+ * Flush all TLB entries on the local CPU.
*/
static inline void __tlb_flush_local(void)
{
asm volatile("ptlb" : : : "memory");
}
-#ifdef CONFIG_SMP
/*
- * Flush all tlb entries on all cpus.
+ * Flush TLB entries for a specific ASCE on all CPUs
*/
+static inline void __tlb_flush_idte(unsigned long asce)
+{
+ /* Global TLB flush for the mm */
+ asm volatile(
+ " .insn rrf,0xb98e0000,0,%0,%1,0"
+ : : "a" (2048), "a" (asce) : "cc");
+}
+
+/*
+ * Flush TLB entries for a specific ASCE on the local CPU
+ */
+static inline void __tlb_flush_idte_local(unsigned long asce)
+{
+ /* Local TLB flush for the mm */
+ asm volatile(
+ " .insn rrf,0xb98e0000,0,%0,%1,1"
+ : : "a" (2048), "a" (asce) : "cc");
+}
+
+#ifdef CONFIG_SMP
void smp_ptlb_all(void);
+/*
+ * Flush all TLB entries on all CPUs.
+ */
static inline void __tlb_flush_global(void)
{
register unsigned long reg2 asm("2");
@@ -42,36 +64,89 @@ static inline void __tlb_flush_global(void)
: : "d" (reg2), "d" (reg3), "d" (reg4), "m" (dummy) : "cc" );
}
+/*
+ * Flush TLB entries for a specific mm on all CPUs (in case gmap is used
+ * this implicates multiple ASCEs!).
+ */
static inline void __tlb_flush_full(struct mm_struct *mm)
{
- cpumask_t local_cpumask;
-
preempt_disable();
- /*
- * If the process only ran on the local cpu, do a local flush.
- */
- cpumask_copy(&local_cpumask, cpumask_of(smp_processor_id()));
- if (cpumask_equal(mm_cpumask(mm), &local_cpumask))
+ atomic_add(0x10000, &mm->context.attach_count);
+ if (cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
+ /* Local TLB flush */
__tlb_flush_local();
- else
+ } else {
+ /* Global TLB flush */
__tlb_flush_global();
+ /* Reset TLB flush mask */
+ if (MACHINE_HAS_TLB_LC)
+ cpumask_copy(mm_cpumask(mm),
+ &mm->context.cpu_attach_mask);
+ }
+ atomic_sub(0x10000, &mm->context.attach_count);
preempt_enable();
}
+
+/*
+ * Flush TLB entries for a specific ASCE on all CPUs.
+ */
+static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce)
+{
+ int active, count;
+
+ preempt_disable();
+ active = (mm == current->active_mm) ? 1 : 0;
+ count = atomic_add_return(0x10000, &mm->context.attach_count);
+ if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
+ cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
+ __tlb_flush_idte_local(asce);
+ } else {
+ if (MACHINE_HAS_IDTE)
+ __tlb_flush_idte(asce);
+ else
+ __tlb_flush_global();
+ /* Reset TLB flush mask */
+ if (MACHINE_HAS_TLB_LC)
+ cpumask_copy(mm_cpumask(mm),
+ &mm->context.cpu_attach_mask);
+ }
+ atomic_sub(0x10000, &mm->context.attach_count);
+ preempt_enable();
+}
+
+static inline void __tlb_flush_kernel(void)
+{
+ if (MACHINE_HAS_IDTE)
+ __tlb_flush_idte((unsigned long) init_mm.pgd |
+ init_mm.context.asce_bits);
+ else
+ __tlb_flush_global();
+}
#else
-#define __tlb_flush_full(mm) __tlb_flush_local()
#define __tlb_flush_global() __tlb_flush_local()
-#endif
+#define __tlb_flush_full(mm) __tlb_flush_local()
/*
- * Flush all tlb entries of a page table on all cpus.
+ * Flush TLB entries for a specific ASCE on all CPUs.
*/
-static inline void __tlb_flush_idte(unsigned long asce)
+static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce)
{
- asm volatile(
- " .insn rrf,0xb98e0000,0,%0,%1,0"
- : : "a" (2048), "a" (asce) : "cc" );
+ if (MACHINE_HAS_TLB_LC)
+ __tlb_flush_idte_local(asce);
+ else
+ __tlb_flush_local();
}
+static inline void __tlb_flush_kernel(void)
+{
+ if (MACHINE_HAS_TLB_LC)
+ __tlb_flush_idte_local((unsigned long) init_mm.pgd |
+ init_mm.context.asce_bits);
+ else
+ __tlb_flush_local();
+}
+#endif
+
static inline void __tlb_flush_mm(struct mm_struct * mm)
{
/*
@@ -80,7 +155,7 @@ static inline void __tlb_flush_mm(struct mm_struct * mm)
* only ran on the local cpu.
*/
if (MACHINE_HAS_IDTE && list_empty(&mm->context.gmap_list))
- __tlb_flush_idte((unsigned long) mm->pgd |
+ __tlb_flush_asce(mm, (unsigned long) mm->pgd |
mm->context.asce_bits);
else
__tlb_flush_full(mm);
@@ -130,7 +205,7 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
static inline void flush_tlb_kernel_range(unsigned long start,
unsigned long end)
{
- __tlb_flush_mm(&init_mm);
+ __tlb_flush_kernel();
}
#endif /* _S390_TLBFLUSH_H */
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 79330af9a5f..1be64a1506d 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -92,33 +92,56 @@ static inline unsigned long extable_fixup(const struct exception_table_entry *x)
#define ARCH_HAS_SORT_EXTABLE
#define ARCH_HAS_SEARCH_EXTABLE
-struct uaccess_ops {
- size_t (*copy_from_user)(size_t, const void __user *, void *);
- size_t (*copy_to_user)(size_t, void __user *, const void *);
- size_t (*copy_in_user)(size_t, void __user *, const void __user *);
- size_t (*clear_user)(size_t, void __user *);
- size_t (*strnlen_user)(size_t, const char __user *);
- size_t (*strncpy_from_user)(size_t, const char __user *, char *);
- int (*futex_atomic_op)(int op, u32 __user *, int oparg, int *old);
- int (*futex_atomic_cmpxchg)(u32 *, u32 __user *, u32 old, u32 new);
-};
+/**
+ * __copy_from_user: - Copy a block of data from user space, with less checking.
+ * @to: Destination address, in kernel space.
+ * @from: Source address, in user space.
+ * @n: Number of bytes to copy.
+ *
+ * Context: User context only. This function may sleep.
+ *
+ * Copy data from user space to kernel space. Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be copied.
+ * On success, this will be zero.
+ *
+ * If some data could not be copied, this function will pad the copied
+ * data to the requested size using zero bytes.
+ */
+unsigned long __must_check __copy_from_user(void *to, const void __user *from,
+ unsigned long n);
-extern struct uaccess_ops uaccess;
-extern struct uaccess_ops uaccess_mvcos;
-extern struct uaccess_ops uaccess_pt;
+/**
+ * __copy_to_user: - Copy a block of data into user space, with less checking.
+ * @to: Destination address, in user space.
+ * @from: Source address, in kernel space.
+ * @n: Number of bytes to copy.
+ *
+ * Context: User context only. This function may sleep.
+ *
+ * Copy data from kernel space to user space. Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be copied.
+ * On success, this will be zero.
+ */
+unsigned long __must_check __copy_to_user(void __user *to, const void *from,
+ unsigned long n);
-extern int __handle_fault(unsigned long, unsigned long, int);
+#define __copy_to_user_inatomic __copy_to_user
+#define __copy_from_user_inatomic __copy_from_user
-static inline int __put_user_fn(size_t size, void __user *ptr, void *x)
+static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
{
- size = uaccess.copy_to_user(size, ptr, x);
- return size ? -EFAULT : size;
+ size = __copy_to_user(ptr, x, size);
+ return size ? -EFAULT : 0;
}
-static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
+static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size)
{
- size = uaccess.copy_from_user(size, ptr, x);
- return size ? -EFAULT : size;
+ size = __copy_from_user(x, ptr, size);
+ return size ? -EFAULT : 0;
}
/*
@@ -135,8 +158,8 @@ static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
case 2: \
case 4: \
case 8: \
- __pu_err = __put_user_fn(sizeof (*(ptr)), \
- ptr, &__x); \
+ __pu_err = __put_user_fn(&__x, ptr, \
+ sizeof(*(ptr))); \
break; \
default: \
__put_user_bad(); \
@@ -152,7 +175,7 @@ static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
})
-extern int __put_user_bad(void) __attribute__((noreturn));
+int __put_user_bad(void) __attribute__((noreturn));
#define __get_user(x, ptr) \
({ \
@@ -161,29 +184,29 @@ extern int __put_user_bad(void) __attribute__((noreturn));
switch (sizeof(*(ptr))) { \
case 1: { \
unsigned char __x; \
- __gu_err = __get_user_fn(sizeof (*(ptr)), \
- ptr, &__x); \
+ __gu_err = __get_user_fn(&__x, ptr, \
+ sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 2: { \
unsigned short __x; \
- __gu_err = __get_user_fn(sizeof (*(ptr)), \
- ptr, &__x); \
+ __gu_err = __get_user_fn(&__x, ptr, \
+ sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 4: { \
unsigned int __x; \
- __gu_err = __get_user_fn(sizeof (*(ptr)), \
- ptr, &__x); \
+ __gu_err = __get_user_fn(&__x, ptr, \
+ sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 8: { \
unsigned long long __x; \
- __gu_err = __get_user_fn(sizeof (*(ptr)), \
- ptr, &__x); \
+ __gu_err = __get_user_fn(&__x, ptr, \
+ sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
@@ -200,35 +223,12 @@ extern int __put_user_bad(void) __attribute__((noreturn));
__get_user(x, ptr); \
})
-extern int __get_user_bad(void) __attribute__((noreturn));
+int __get_user_bad(void) __attribute__((noreturn));
#define __put_user_unaligned __put_user
#define __get_user_unaligned __get_user
/**
- * __copy_to_user: - Copy a block of data into user space, with less checking.
- * @to: Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep.
- *
- * Copy data from kernel space to user space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-static inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- return uaccess.copy_to_user(n, to, from);
-}
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
-/**
* copy_to_user: - Copy a block of data into user space.
* @to: Destination address, in user space.
* @from: Source address, in kernel space.
@@ -248,30 +248,7 @@ copy_to_user(void __user *to, const void *from, unsigned long n)
return __copy_to_user(to, from, n);
}
-/**
- * __copy_from_user: - Copy a block of data from user space, with less checking.
- * @to: Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n: Number of bytes to copy.
- *
- * Context: User context only. This function may sleep.
- *
- * Copy data from user space to kernel space. Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-static inline unsigned long __must_check
-__copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- return uaccess.copy_from_user(n, from, to);
-}
-
-extern void copy_from_user_overflow(void)
+void copy_from_user_overflow(void)
#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
__compiletime_warning("copy_from_user() buffer size is not provably correct")
#endif
@@ -306,11 +283,8 @@ copy_from_user(void *to, const void __user *from, unsigned long n)
return __copy_from_user(to, from, n);
}
-static inline unsigned long __must_check
-__copy_in_user(void __user *to, const void __user *from, unsigned long n)
-{
- return uaccess.copy_in_user(n, to, from);
-}
+unsigned long __must_check
+__copy_in_user(void __user *to, const void __user *from, unsigned long n);
static inline unsigned long __must_check
copy_in_user(void __user *to, const void __user *from, unsigned long n)
@@ -322,18 +296,22 @@ copy_in_user(void __user *to, const void __user *from, unsigned long n)
/*
* Copy a null terminated string from userspace.
*/
+
+long __strncpy_from_user(char *dst, const char __user *src, long count);
+
static inline long __must_check
strncpy_from_user(char *dst, const char __user *src, long count)
{
might_fault();
- return uaccess.strncpy_from_user(count, src, dst);
+ return __strncpy_from_user(dst, src, count);
}
-static inline unsigned long
-strnlen_user(const char __user * src, unsigned long n)
+unsigned long __must_check __strnlen_user(const char __user *src, unsigned long count);
+
+static inline unsigned long strnlen_user(const char __user *src, unsigned long n)
{
might_fault();
- return uaccess.strnlen_user(n, src);
+ return __strnlen_user(src, n);
}
/**
@@ -355,21 +333,14 @@ strnlen_user(const char __user * src, unsigned long n)
/*
* Zero Userspace
*/
+unsigned long __must_check __clear_user(void __user *to, unsigned long size);
-static inline unsigned long __must_check
-__clear_user(void __user *to, unsigned long n)
-{
- return uaccess.clear_user(n, to);
-}
-
-static inline unsigned long __must_check
-clear_user(void __user *to, unsigned long n)
+static inline unsigned long __must_check clear_user(void __user *to, unsigned long n)
{
might_fault();
- return uaccess.clear_user(n, to);
+ return __clear_user(to, n);
}
-extern int copy_to_user_real(void __user *dest, void *src, size_t count);
-extern int copy_from_user_real(void *dest, void __user *src, size_t count);
+int copy_to_user_real(void __user *dest, void *src, unsigned long count);
#endif /* __S390_UACCESS_H */
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index d25da598ec6..c003c6a73b1 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -16,6 +16,44 @@
#define __KVM_S390
+/* Device control API: s390-specific devices */
+#define KVM_DEV_FLIC_GET_ALL_IRQS 1
+#define KVM_DEV_FLIC_ENQUEUE 2
+#define KVM_DEV_FLIC_CLEAR_IRQS 3
+#define KVM_DEV_FLIC_APF_ENABLE 4
+#define KVM_DEV_FLIC_APF_DISABLE_WAIT 5
+#define KVM_DEV_FLIC_ADAPTER_REGISTER 6
+#define KVM_DEV_FLIC_ADAPTER_MODIFY 7
+/*
+ * We can have up to 4*64k pending subchannels + 8 adapter interrupts,
+ * as well as up to ASYNC_PF_PER_VCPU*KVM_MAX_VCPUS pfault done interrupts.
+ * There are also sclp and machine checks. This gives us
+ * sizeof(kvm_s390_irq)*(4*65536+8+64*64+1+1) = 72 * 266250 = 19170000
+ * Lets round up to 8192 pages.
+ */
+#define KVM_S390_MAX_FLOAT_IRQS 266250
+#define KVM_S390_FLIC_MAX_BUFFER 0x2000000
+
+struct kvm_s390_io_adapter {
+ __u32 id;
+ __u8 isc;
+ __u8 maskable;
+ __u8 swap;
+ __u8 pad;
+};
+
+#define KVM_S390_IO_ADAPTER_MASK 1
+#define KVM_S390_IO_ADAPTER_MAP 2
+#define KVM_S390_IO_ADAPTER_UNMAP 3
+
+struct kvm_s390_io_adapter_req {
+ __u32 id;
+ __u8 type;
+ __u8 mask;
+ __u16 pad0;
+ __u64 addr;
+};
+
/* for KVM_GET_REGS and KVM_SET_REGS */
struct kvm_regs {
/* general purpose regs for s390 */
@@ -57,4 +95,9 @@ struct kvm_sync_regs {
#define KVM_REG_S390_EPOCHDIFF (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x2)
#define KVM_REG_S390_CPU_TIMER (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x3)
#define KVM_REG_S390_CLOCK_COMP (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x4)
+#define KVM_REG_S390_PFTOKEN (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x5)
+#define KVM_REG_S390_PFCOMPARE (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x6)
+#define KVM_REG_S390_PFSELECT (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x7)
+#define KVM_REG_S390_PP (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x8)
+#define KVM_REG_S390_GBEA (KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x9)
#endif
diff --git a/arch/s390/include/uapi/asm/ptrace.h b/arch/s390/include/uapi/asm/ptrace.h
index 7e0b498a2c2..a150f4fabe4 100644
--- a/arch/s390/include/uapi/asm/ptrace.h
+++ b/arch/s390/include/uapi/asm/ptrace.h
@@ -403,6 +403,12 @@ typedef struct
#define PTRACE_TE_ABORT_RAND 0x5011
/*
+ * The numbers chosen here are somewhat arbitrary but absolutely MUST
+ * not overlap with any of the number assigned in <linux/ptrace.h>.
+ */
+#define PTRACE_SINGLEBLOCK 12 /* resume execution until next branch */
+
+/*
* PT_PROT definition is loosely based on hppa bsd definition in
* gdb/hppab-nat.c
*/