diff options
Diffstat (limited to 'arch/s390')
73 files changed, 2272 insertions, 1620 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index f2cf1f90295b..68b68d755fdf 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -65,6 +65,7 @@ config S390 def_bool y select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS + select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_INLINE_READ_LOCK select ARCH_INLINE_READ_LOCK_BH diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index 47c8630c93cd..15c94246b600 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -511,7 +511,6 @@ static const struct dev_pm_ops appldata_pm_ops = { static struct platform_driver appldata_pdrv = { .driver = { .name = "appldata", - .owner = THIS_MODULE, .pm = &appldata_pm_ops, }, }; diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c index 23223cd63e54..1f272b24fc0b 100644 --- a/arch/s390/crypto/aes_s390.c +++ b/arch/s390/crypto/aes_s390.c @@ -979,7 +979,7 @@ static void __exit aes_s390_fini(void) module_init(aes_s390_init); module_exit(aes_s390_fini); -MODULE_ALIAS("aes-all"); +MODULE_ALIAS_CRYPTO("aes-all"); MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm"); MODULE_LICENSE("GPL"); diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c index 7acb77f7ef1a..9e05cc453a40 100644 --- a/arch/s390/crypto/des_s390.c +++ b/arch/s390/crypto/des_s390.c @@ -619,8 +619,8 @@ static void __exit des_s390_exit(void) module_init(des_s390_init); module_exit(des_s390_exit); -MODULE_ALIAS("des"); -MODULE_ALIAS("des3_ede"); +MODULE_ALIAS_CRYPTO("des"); +MODULE_ALIAS_CRYPTO("des3_ede"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("DES & Triple DES EDE Cipher Algorithms"); diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c index d43485d142e9..7940dc90e80b 100644 --- a/arch/s390/crypto/ghash_s390.c +++ b/arch/s390/crypto/ghash_s390.c @@ -160,7 +160,7 @@ static void __exit ghash_mod_exit(void) module_init(ghash_mod_init); module_exit(ghash_mod_exit); -MODULE_ALIAS("ghash"); +MODULE_ALIAS_CRYPTO("ghash"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("GHASH Message Digest Algorithm, s390 implementation"); diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c index a1b3a9dc9d8a..5b2bee323694 100644 --- a/arch/s390/crypto/sha1_s390.c +++ b/arch/s390/crypto/sha1_s390.c @@ -103,6 +103,6 @@ static void __exit sha1_s390_fini(void) module_init(sha1_s390_init); module_exit(sha1_s390_fini); -MODULE_ALIAS("sha1"); +MODULE_ALIAS_CRYPTO("sha1"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm"); diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c index 9b853809a492..b74ff158108c 100644 --- a/arch/s390/crypto/sha256_s390.c +++ b/arch/s390/crypto/sha256_s390.c @@ -143,7 +143,7 @@ static void __exit sha256_s390_fini(void) module_init(sha256_s390_init); module_exit(sha256_s390_fini); -MODULE_ALIAS("sha256"); -MODULE_ALIAS("sha224"); +MODULE_ALIAS_CRYPTO("sha256"); +MODULE_ALIAS_CRYPTO("sha224"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA256 and SHA224 Secure Hash Algorithm"); diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c index 32a81383b69c..0c36989ba182 100644 --- a/arch/s390/crypto/sha512_s390.c +++ b/arch/s390/crypto/sha512_s390.c @@ -86,7 +86,7 @@ static struct shash_alg sha512_alg = { } }; -MODULE_ALIAS("sha512"); +MODULE_ALIAS_CRYPTO("sha512"); static int sha384_init(struct shash_desc *desc) { @@ -126,7 +126,7 @@ static struct shash_alg sha384_alg = { } }; -MODULE_ALIAS("sha384"); +MODULE_ALIAS_CRYPTO("sha384"); static int __init init(void) { diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c index 2badf2bf9cd7..47fe1055c714 100644 --- a/arch/s390/hypfs/hypfs_dbfs.c +++ b/arch/s390/hypfs/hypfs_dbfs.c @@ -83,10 +83,9 @@ static ssize_t dbfs_read(struct file *file, char __user *buf, static long dbfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - struct hypfs_dbfs_file *df; + struct hypfs_dbfs_file *df = file_inode(file)->i_private; long rc; - df = file->f_path.dentry->d_inode->i_private; mutex_lock(&df->lock); if (df->unlocked_ioctl) rc = df->unlocked_ioctl(file, cmd, arg); diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index 773f86676588..c631f98fd524 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -1,7 +1,6 @@ generic-y += clkdev.h -generic-y += hash.h generic-y += irq_work.h generic-y += mcs_spinlock.h generic-y += preempt.h diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h index b5dce6544d76..8d724718ec21 100644 --- a/arch/s390/include/asm/barrier.h +++ b/arch/s390/include/asm/barrier.h @@ -24,11 +24,14 @@ #define rmb() mb() #define wmb() mb() -#define read_barrier_depends() do { } while(0) +#define dma_rmb() rmb() +#define dma_wmb() wmb() #define smp_mb() mb() #define smp_rmb() rmb() #define smp_wmb() wmb() -#define smp_read_barrier_depends() read_barrier_depends() + +#define read_barrier_depends() do { } while (0) +#define smp_read_barrier_depends() do { } while (0) #define smp_mb__before_atomic() smp_mb() #define smp_mb__after_atomic() smp_mb() diff --git a/arch/s390/include/asm/cmpxchg.h b/arch/s390/include/asm/cmpxchg.h index 4236408070e5..6259895fcd97 100644 --- a/arch/s390/include/asm/cmpxchg.h +++ b/arch/s390/include/asm/cmpxchg.h @@ -11,200 +11,28 @@ #include <linux/types.h> #include <linux/bug.h> -extern void __xchg_called_with_bad_pointer(void); - -static inline unsigned long __xchg(unsigned long x, void *ptr, int size) -{ - unsigned long addr, old; - int shift; - - switch (size) { - case 1: - addr = (unsigned long) ptr; - shift = (3 ^ (addr & 3)) << 3; - addr ^= addr & 3; - asm volatile( - " l %0,%4\n" - "0: lr 0,%0\n" - " nr 0,%3\n" - " or 0,%2\n" - " cs %0,0,%4\n" - " jl 0b\n" - : "=&d" (old), "=Q" (*(int *) addr) - : "d" ((x & 0xff) << shift), "d" (~(0xff << shift)), - "Q" (*(int *) addr) : "memory", "cc", "0"); - return old >> shift; - case 2: - addr = (unsigned long) ptr; - shift = (2 ^ (addr & 2)) << 3; - addr ^= addr & 2; - asm volatile( - " l %0,%4\n" - "0: lr 0,%0\n" - " nr 0,%3\n" - " or 0,%2\n" - " cs %0,0,%4\n" - " jl 0b\n" - : "=&d" (old), "=Q" (*(int *) addr) - : "d" ((x & 0xffff) << shift), "d" (~(0xffff << shift)), - "Q" (*(int *) addr) : "memory", "cc", "0"); - return old >> shift; - case 4: - asm volatile( - " l %0,%3\n" - "0: cs %0,%2,%3\n" - " jl 0b\n" - : "=&d" (old), "=Q" (*(int *) ptr) - : "d" (x), "Q" (*(int *) ptr) - : "memory", "cc"); - return old; -#ifdef CONFIG_64BIT - case 8: - asm volatile( - " lg %0,%3\n" - "0: csg %0,%2,%3\n" - " jl 0b\n" - : "=&d" (old), "=m" (*(long *) ptr) - : "d" (x), "Q" (*(long *) ptr) - : "memory", "cc"); - return old; -#endif /* CONFIG_64BIT */ - } - __xchg_called_with_bad_pointer(); - return x; -} - -#define xchg(ptr, x) \ -({ \ - __typeof__(*(ptr)) __ret; \ - __ret = (__typeof__(*(ptr))) \ - __xchg((unsigned long)(x), (void *)(ptr), sizeof(*(ptr)));\ - __ret; \ +#define cmpxchg(ptr, o, n) \ +({ \ + __typeof__(*(ptr)) __o = (o); \ + __typeof__(*(ptr)) __n = (n); \ + (__typeof__(*(ptr))) __sync_val_compare_and_swap((ptr),__o,__n);\ }) -/* - * Atomic compare and exchange. Compare OLD with MEM, if identical, - * store NEW in MEM. Return the initial value in MEM. Success is - * indicated by comparing RETURN with OLD. - */ - -#define __HAVE_ARCH_CMPXCHG - -extern void __cmpxchg_called_with_bad_pointer(void); - -static inline unsigned long __cmpxchg(void *ptr, unsigned long old, - unsigned long new, int size) -{ - unsigned long addr, prev, tmp; - int shift; - - switch (size) { - case 1: - addr = (unsigned long) ptr; - shift = (3 ^ (addr & 3)) << 3; - addr ^= addr & 3; - asm volatile( - " l %0,%2\n" - "0: nr %0,%5\n" - " lr %1,%0\n" - " or %0,%3\n" - " or %1,%4\n" - " cs %0,%1,%2\n" - " jnl 1f\n" - " xr %1,%0\n" - " nr %1,%5\n" - " jnz 0b\n" - "1:" - : "=&d" (prev), "=&d" (tmp), "+Q" (*(int *) addr) - : "d" ((old & 0xff) << shift), - "d" ((new & 0xff) << shift), - "d" (~(0xff << shift)) - : "memory", "cc"); - return prev >> shift; - case 2: - addr = (unsigned long) ptr; - shift = (2 ^ (addr & 2)) << 3; - addr ^= addr & 2; - asm volatile( - " l %0,%2\n" - "0: nr %0,%5\n" - " lr %1,%0\n" - " or %0,%3\n" - " or %1,%4\n" - " cs %0,%1,%2\n" - " jnl 1f\n" - " xr %1,%0\n" - " nr %1,%5\n" - " jnz 0b\n" - "1:" - : "=&d" (prev), "=&d" (tmp), "+Q" (*(int *) addr) - : "d" ((old & 0xffff) << shift), - "d" ((new & 0xffff) << shift), - "d" (~(0xffff << shift)) - : "memory", "cc"); - return prev >> shift; - case 4: - asm volatile( - " cs %0,%3,%1\n" - : "=&d" (prev), "=Q" (*(int *) ptr) - : "0" (old), "d" (new), "Q" (*(int *) ptr) - : "memory", "cc"); - return prev; -#ifdef CONFIG_64BIT - case 8: - asm volatile( - " csg %0,%3,%1\n" - : "=&d" (prev), "=Q" (*(long *) ptr) - : "0" (old), "d" (new), "Q" (*(long *) ptr) - : "memory", "cc"); - return prev; -#endif /* CONFIG_64BIT */ - } - __cmpxchg_called_with_bad_pointer(); - return old; -} - -#define cmpxchg(ptr, o, n) \ -({ \ - __typeof__(*(ptr)) __ret; \ - __ret = (__typeof__(*(ptr))) \ - __cmpxchg((ptr), (unsigned long)(o), (unsigned long)(n), \ - sizeof(*(ptr))); \ - __ret; \ -}) +#define cmpxchg64 cmpxchg +#define cmpxchg_local cmpxchg +#define cmpxchg64_local cmpxchg -#ifdef CONFIG_64BIT -#define cmpxchg64(ptr, o, n) \ +#define xchg(ptr, x) \ ({ \ - cmpxchg((ptr), (o), (n)); \ + __typeof__(ptr) __ptr = (ptr); \ + __typeof__(*(ptr)) __old; \ + do { \ + __old = *__ptr; \ + } while (!__sync_bool_compare_and_swap(__ptr, __old, x)); \ + __old; \ }) -#else /* CONFIG_64BIT */ -static inline unsigned long long __cmpxchg64(void *ptr, - unsigned long long old, - unsigned long long new) -{ - register_pair rp_old = {.pair = old}; - register_pair rp_new = {.pair = new}; - unsigned long long *ullptr = ptr; - asm volatile( - " cds %0,%2,%1" - : "+d" (rp_old), "+Q" (*ullptr) - : "d" (rp_new) - : "memory", "cc"); - return rp_old.pair; -} - -#define cmpxchg64(ptr, o, n) \ -({ \ - __typeof__(*(ptr)) __ret; \ - __ret = (__typeof__(*(ptr))) \ - __cmpxchg64((ptr), \ - (unsigned long long)(o), \ - (unsigned long long)(n)); \ - __ret; \ -}) -#endif /* CONFIG_64BIT */ +#define __HAVE_ARCH_CMPXCHG #define __cmpxchg_double_op(p1, p2, o1, o2, n1, n2, insn) \ ({ \ @@ -265,40 +93,4 @@ extern void __cmpxchg_double_called_with_bad_pointer(void); #define system_has_cmpxchg_double() 1 -#include <asm-generic/cmpxchg-local.h> - -static inline unsigned long __cmpxchg_local(void *ptr, - unsigned long old, - unsigned long new, int size) -{ - switch (size) { - case 1: - case 2: - case 4: -#ifdef CONFIG_64BIT - case 8: -#endif - return __cmpxchg(ptr, old, new, size); - default: - return __cmpxchg_local_generic(ptr, old, new, size); - } - - return old; -} - -/* - * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make - * them available. - */ -#define cmpxchg_local(ptr, o, n) \ -({ \ - __typeof__(*(ptr)) __ret; \ - __ret = (__typeof__(*(ptr))) \ - __cmpxchg_local((ptr), (unsigned long)(o), \ - (unsigned long)(n), sizeof(*(ptr))); \ - __ret; \ -}) - -#define cmpxchg64_local(ptr, o, n) cmpxchg64((ptr), (o), (n)) - #endif /* __ASM_CMPXCHG_H */ diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h index f8c196984853..b91e960e4045 100644 --- a/arch/s390/include/asm/cputime.h +++ b/arch/s390/include/asm/cputime.h @@ -10,6 +10,8 @@ #include <linux/types.h> #include <asm/div64.h> +#define CPUTIME_PER_USEC 4096ULL +#define CPUTIME_PER_SEC (CPUTIME_PER_USEC * USEC_PER_SEC) /* We want to use full resolution of the CPU timer: 2**-12 micro-seconds. */ @@ -38,24 +40,24 @@ static inline unsigned long __div(unsigned long long n, unsigned long base) */ static inline unsigned long cputime_to_jiffies(const cputime_t cputime) { - return __div((__force unsigned long long) cputime, 4096000000ULL / HZ); + return __div((__force unsigned long long) cputime, CPUTIME_PER_SEC / HZ); } static inline cputime_t jiffies_to_cputime(const unsigned int jif) { - return (__force cputime_t)(jif * (4096000000ULL / HZ)); + return (__force cputime_t)(jif * (CPUTIME_PER_SEC / HZ)); } static inline u64 cputime64_to_jiffies64(cputime64_t cputime) { unsigned long long jif = (__force unsigned long long) cputime; - do_div(jif, 4096000000ULL / HZ); + do_div(jif, CPUTIME_PER_SEC / HZ); return jif; } static inline cputime64_t jiffies64_to_cputime64(const u64 jif) { - return (__force cputime64_t)(jif * (4096000000ULL / HZ)); + return (__force cputime64_t)(jif * (CPUTIME_PER_SEC / HZ)); } /* @@ -68,7 +70,7 @@ static inline unsigned int cputime_to_usecs(const cputime_t cputime) static inline cputime_t usecs_to_cputime(const unsigned int m) { - return (__force cputime_t)(m * 4096ULL); + return (__force cputime_t)(m * CPUTIME_PER_USEC); } #define usecs_to_cputime64(m) usecs_to_cputime(m) @@ -78,12 +80,12 @@ static inline cputime_t usecs_to_cputime(const unsigned int m) */ static inline unsigned int cputime_to_secs(const cputime_t cputime) { - return __div((__force unsigned long long) cputime, 2048000000) >> 1; + return __div((__force unsigned long long) cputime, CPUTIME_PER_SEC / 2) >> 1; } static inline cputime_t secs_to_cputime(const unsigned int s) { - return (__force cputime_t)(s * 4096000000ULL); + return (__force cputime_t)(s * CPUTIME_PER_SEC); } /* @@ -91,8 +93,8 @@ static inline cputime_t secs_to_cputime(const unsigned int s) */ static inline cputime_t timespec_to_cputime(const struct timespec *value) { - unsigned long long ret = value->tv_sec * 4096000000ULL; - return (__force cputime_t)(ret + value->tv_nsec * 4096 / 1000); + unsigned long long ret = value->tv_sec * CPUTIME_PER_SEC; + return (__force cputime_t)(ret + __div(value->tv_nsec * CPUTIME_PER_USEC, NSEC_PER_USEC)); } static inline void cputime_to_timespec(const cputime_t cputime, @@ -103,12 +105,12 @@ static inline void cputime_to_timespec(const cputime_t cputime, register_pair rp; rp.pair = __cputime >> 1; - asm ("dr %0,%1" : "+d" (rp) : "d" (2048000000UL)); - value->tv_nsec = rp.subreg.even * 1000 / 4096; + asm ("dr %0,%1" : "+d" (rp) : "d" (CPUTIME_PER_SEC / 2)); + value->tv_nsec = rp.subreg.even * NSEC_PER_USEC / CPUTIME_PER_USEC; value->tv_sec = rp.subreg.odd; #else - value->tv_nsec = (__cputime % 4096000000ULL) * 1000 / 4096; - value->tv_sec = __cputime / 4096000000ULL; + value->tv_nsec = (__cputime % CPUTIME_PER_SEC) * NSEC_PER_USEC / CPUTIME_PER_USEC; + value->tv_sec = __cputime / CPUTIME_PER_SEC; #endif } @@ -119,8 +121,8 @@ static inline void cputime_to_timespec(const cputime_t cputime, */ static inline cputime_t timeval_to_cputime(const struct timeval *value) { - unsigned long long ret = value->tv_sec * 4096000000ULL; - return (__force cputime_t)(ret + value->tv_usec * 4096ULL); + unsigned long long ret = value->tv_sec * CPUTIME_PER_SEC; + return (__force cputime_t)(ret + value->tv_usec * CPUTIME_PER_USEC); } static inline void cputime_to_timeval(const cputime_t cputime, @@ -131,12 +133,12 @@ static inline void cputime_to_timeval(const cputime_t cputime, register_pair rp; rp.pair = __cputime >> 1; - asm ("dr %0,%1" : "+d" (rp) : "d" (2048000000UL)); - value->tv_usec = rp.subreg.even / 4096; + asm ("dr %0,%1" : "+d" (rp) : "d" (CPUTIME_PER_USEC / 2)); + value->tv_usec = rp.subreg.even / CPUTIME_PER_USEC; value->tv_sec = rp.subreg.odd; #else - value->tv_usec = (__cputime % 4096000000ULL) / 4096; - value->tv_sec = __cputime / 4096000000ULL; + value->tv_usec = (__cputime % CPUTIME_PER_SEC) / CPUTIME_PER_USEC; + value->tv_sec = __cputime / CPUTIME_PER_SEC; #endif } @@ -146,13 +148,13 @@ static inline void cputime_to_timeval(const cputime_t cputime, static inline clock_t cputime_to_clock_t(cputime_t cputime) { unsigned long long clock = (__force unsigned long long) cputime; - do_div(clock, 4096000000ULL / USER_HZ); + do_div(clock, CPUTIME_PER_SEC / USER_HZ); return clock; } static inline cputime_t clock_t_to_cputime(unsigned long x) { - return (__force cputime_t)(x * (4096000000ULL / USER_HZ)); + return (__force cputime_t)(x * (CPUTIME_PER_SEC / USER_HZ)); } /* @@ -161,7 +163,7 @@ static inline cputime_t clock_t_to_cputime(unsigned long x) static inline clock_t cputime64_to_clock_t(cputime64_t cputime) { unsigned long long clock = (__force unsigned long long) cputime; - do_div(clock, 4096000000ULL / USER_HZ); + do_div(clock, CPUTIME_PER_SEC / USER_HZ); return clock; } diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h index 530c15eb01e9..0206c8052328 100644 --- a/arch/s390/include/asm/debug.h +++ b/arch/s390/include/asm/debug.h @@ -151,9 +151,21 @@ debug_text_event(debug_info_t* id, int level, const char* txt) * stored in the s390dbf. See Documentation/s390/s390dbf.txt for more details! */ extern debug_entry_t * -debug_sprintf_event(debug_info_t* id,int level,char *string,...) +__debug_sprintf_event(debug_info_t *id, int level, char *string, ...) __attribute__ ((format(printf, 3, 4))); +#define debug_sprintf_event(_id, _level, _fmt, ...) \ +({ \ + debug_entry_t *__ret; \ + debug_info_t *__id = _id; \ + int __level = _level; \ + if ((!__id) || (__level > __id->level)) \ + __ret = NULL; \ + else \ + __ret = __debug_sprintf_event(__id, __level, \ + _fmt, ## __VA_ARGS__); \ + __ret; \ +}) static inline debug_entry_t* debug_exception(debug_info_t* id, int level, void* data, int length) @@ -194,9 +206,22 @@ debug_text_exception(debug_info_t* id, int level, const char* txt) * stored in the s390dbf. See Documentation/s390/s390dbf.txt for more details! */ extern debug_entry_t * -debug_sprintf_exception(debug_info_t* id,int level,char *string,...) +__debug_sprintf_exception(debug_info_t *id, int level, char *string, ...) __attribute__ ((format(printf, 3, 4))); +#define debug_sprintf_exception(_id, _level, _fmt, ...) \ +({ \ + debug_entry_t *__ret; \ + debug_info_t *__id = _id; \ + int __level = _level; \ + if ((!__id) || (__level > __id->level)) \ + __ret = NULL; \ + else \ + __ret = __debug_sprintf_exception(__id, __level, \ + _fmt, ## __VA_ARGS__);\ + __ret; \ +}) + int debug_register_view(debug_info_t* id, struct debug_view* view); int debug_unregister_view(debug_info_t* id, struct debug_view* view); diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index 3aef8afec336..abb618f1ead2 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -1,25 +1,69 @@ #ifndef _ASM_S390_FTRACE_H #define _ASM_S390_FTRACE_H +#define ARCH_SUPPORTS_FTRACE_OPS 1 + +#define MCOUNT_INSN_SIZE 24 +#define MCOUNT_RETURN_FIXUP 18 + #ifndef __ASSEMBLY__ -extern void _mcount(void); +#define ftrace_return_address(n) __builtin_return_address(n) + +void _mcount(void); +void ftrace_caller(void); + extern char ftrace_graph_caller_end; +extern unsigned long ftrace_plt; struct dyn_arch_ftrace { }; -#define MCOUNT_ADDR ((long)_mcount) +#define MCOUNT_ADDR ((unsigned long)_mcount) +#define FTRACE_ADDR ((unsigned long)ftrace_caller) +#define KPROBE_ON_FTRACE_NOP 0 +#define KPROBE_ON_FTRACE_CALL 1 static inline unsigned long ftrace_call_adjust(unsigned long addr) { return addr; } -#endif /* __ASSEMBLY__ */ +struct ftrace_insn { + u16 opc; + s32 disp; +} __packed; + +static inline void ftrace_generate_nop_insn(struct ftrace_insn *insn) +{ +#ifdef CONFIG_FUNCTION_TRACER + /* jg .+24 */ + insn->opc = 0xc0f4; + insn->disp = MCOUNT_INSN_SIZE / 2; +#endif +} -#define MCOUNT_INSN_SIZE 18 +static inline int is_ftrace_nop(struct ftrace_insn *insn) +{ +#ifdef CONFIG_FUNCTION_TRACER + if (insn->disp == MCOUNT_INSN_SIZE / 2) + return 1; +#endif + return 0; +} -#define ARCH_SUPPORTS_FTRACE_OPS 1 +static inline void ftrace_generate_call_insn(struct ftrace_insn *insn, + unsigned long ip) +{ +#ifdef CONFIG_FUNCTION_TRACER + unsigned long target; + + /* brasl r0,ftrace_caller */ + target = is_module_addr((void *) ip) ? ftrace_plt : FTRACE_ADDR; + insn->opc = 0xc005; + insn->disp = (target - ip) / 2; +#endif +} +#endif /* __ASSEMBLY__ */ #endif /* _ASM_S390_FTRACE_H */ diff --git a/arch/s390/include/asm/idle.h b/arch/s390/include/asm/idle.h index 6af037f574b8..113cd963dbbe 100644 --- a/arch/s390/include/asm/idle.h +++ b/arch/s390/include/asm/idle.h @@ -9,9 +9,10 @@ #include <linux/types.h> #include <linux/device.h> +#include <linux/seqlock.h> struct s390_idle_data { - unsigned int sequence; + seqcount_t seqcount; unsigned long long idle_count; unsigned long long idle_time; unsigned long long clock_idle_enter; diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h index cd6b9ee7b69c..30fd5c84680e 100644 --- a/arch/s390/include/asm/io.h +++ b/arch/s390/include/asm/io.h @@ -13,9 +13,10 @@ #include <asm/page.h> #include <asm/pci_io.h> -void *xlate_dev_mem_ptr(unsigned long phys); #define xlate_dev_mem_ptr xlate_dev_mem_ptr -void unxlate_dev_mem_ptr(unsigned long phys, void *addr); +void *xlate_dev_mem_ptr(phys_addr_t phys); +#define unxlate_dev_mem_ptr unxlate_dev_mem_ptr +void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr); /* * Convert a virtual cached pointer to an uncached pointer @@ -38,6 +39,15 @@ static inline void iounmap(volatile void __iomem *addr) { } +static inline void __iomem *ioport_map(unsigned long port, unsigned int nr) +{ + return NULL; +} + +static inline void ioport_unmap(void __iomem *p) +{ +} + /* * s390 needs a private implementation of pci_iomap since ioremap with its * offset parameter isn't sufficient. That's because BAR spaces are not @@ -60,11 +70,6 @@ static inline void iounmap(volatile void __iomem *addr) #define __raw_writel zpci_write_u32 #define __raw_writeq zpci_write_u64 -#define readb_relaxed readb -#define readw_relaxed readw -#define readl_relaxed readl -#define readq_relaxed readq - #endif /* CONFIG_PCI */ #include <asm-generic/io.h> diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h index b0d5f0a97a01..343ea7c987aa 100644 --- a/arch/s390/include/asm/irq.h +++ b/arch/s390/include/asm/irq.h @@ -1,11 +1,11 @@ #ifndef _ASM_IRQ_H #define _ASM_IRQ_H -#define EXT_INTERRUPT 1 -#define IO_INTERRUPT 2 -#define THIN_INTERRUPT 3 +#define EXT_INTERRUPT 0 +#define IO_INTERRUPT 1 +#define THIN_INTERRUPT 2 -#define NR_IRQS_BASE 4 +#define NR_IRQS_BASE 3 #ifdef CONFIG_PCI_NR_MSI # define NR_IRQS (NR_IRQS_BASE + CONFIG_PCI_NR_MSI) @@ -13,9 +13,6 @@ # define NR_IRQS NR_IRQS_BASE #endif -/* 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 diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h index 98629173ce3b..b47ad3b642cc 100644 --- a/arch/s390/include/asm/kprobes.h +++ b/arch/s390/include/asm/kprobes.h @@ -60,6 +60,7 @@ typedef u16 kprobe_opcode_t; struct arch_specific_insn { /* copy of original instruction */ kprobe_opcode_t *insn; + unsigned int is_ftrace_insn : 1; }; struct prev_kprobe { diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 2175f911a73a..9cba74d5d853 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -123,7 +123,7 @@ struct kvm_s390_sie_block { #define ICPT_PARTEXEC 0x38 #define ICPT_IOINST 0x40 __u8 icptcode; /* 0x0050 */ - __u8 reserved51; /* 0x0051 */ + __u8 icptstatus; /* 0x0051 */ __u16 ihcpu; /* 0x0052 */ __u8 reserved54[2]; /* 0x0054 */ __u16 ipa; /* 0x0056 */ @@ -226,10 +226,17 @@ struct kvm_vcpu_stat { u32 instruction_sigp_sense_running; u32 instruction_sigp_external_call; u32 instruction_sigp_emergency; + u32 instruction_sigp_cond_emergency; + u32 instruction_sigp_start; u32 instruction_sigp_stop; + u32 instruction_sigp_stop_store_status; + u32 instruction_sigp_store_status; u32 instruction_sigp_arch; u32 instruction_sigp_prefix; u32 instruction_sigp_restart; + u32 instruction_sigp_init_cpu_reset; + u32 instruction_sigp_cpu_reset; + u32 instruction_sigp_unknown; u32 diagnose_10; u32 diagnose_44; u32 diagnose_9c; @@ -288,6 +295,79 @@ struct kvm_vcpu_stat { #define PGM_PER 0x80 #define PGM_CRYPTO_OPERATION 0x119 +/* irq types in order of priority */ +enum irq_types { + IRQ_PEND_MCHK_EX = 0, + IRQ_PEND_SVC, + IRQ_PEND_PROG, + IRQ_PEND_MCHK_REP, + IRQ_PEND_EXT_IRQ_KEY, + IRQ_PEND_EXT_MALFUNC, + IRQ_PEND_EXT_EMERGENCY, + IRQ_PEND_EXT_EXTERNAL, + IRQ_PEND_EXT_CLOCK_COMP, + IRQ_PEND_EXT_CPU_TIMER, + IRQ_PEND_EXT_TIMING, + IRQ_PEND_EXT_SERVICE, + IRQ_PEND_EXT_HOST, + IRQ_PEND_PFAULT_INIT, + IRQ_PEND_PFAULT_DONE, + IRQ_PEND_VIRTIO, + IRQ_PEND_IO_ISC_0, + IRQ_PEND_IO_ISC_1, + IRQ_PEND_IO_ISC_2, + IRQ_PEND_IO_ISC_3, + IRQ_PEND_IO_ISC_4, + IRQ_PEND_IO_ISC_5, + IRQ_PEND_IO_ISC_6, + IRQ_PEND_IO_ISC_7, + IRQ_PEND_SIGP_STOP, + IRQ_PEND_RESTART, + IRQ_PEND_SET_PREFIX, + IRQ_PEND_COUNT +}; + +/* + * Repressible (non-floating) machine check interrupts + * subclass bits in MCIC + */ +#define MCHK_EXTD_BIT 58 +#define MCHK_DEGR_BIT 56 +#define MCHK_WARN_BIT 55 +#define MCHK_REP_MASK ((1UL << MCHK_DEGR_BIT) | \ + (1UL << MCHK_EXTD_BIT) | \ + (1UL << MCHK_WARN_BIT)) + +/* Exigent machine check interrupts subclass bits in MCIC */ +#define MCHK_SD_BIT 63 +#define MCHK_PD_BIT 62 +#define MCHK_EX_MASK ((1UL << MCHK_SD_BIT) | (1UL << MCHK_PD_BIT)) + +#define IRQ_PEND_EXT_MASK ((1UL << IRQ_PEND_EXT_IRQ_KEY) | \ + (1UL << IRQ_PEND_EXT_CLOCK_COMP) | \ + (1UL << IRQ_PEND_EXT_CPU_TIMER) | \ + (1UL << IRQ_PEND_EXT_MALFUNC) | \ + (1UL << IRQ_PEND_EXT_EMERGENCY) | \ + (1UL << IRQ_PEND_EXT_EXTERNAL) | \ + (1UL << IRQ_PEND_EXT_TIMING) | \ + (1UL << IRQ_PEND_EXT_HOST) | \ + (1UL << IRQ_PEND_EXT_SERVICE) | \ + (1UL << IRQ_PEND_VIRTIO) | \ + (1UL << IRQ_PEND_PFAULT_INIT) | \ + (1UL << IRQ_PEND_PFAULT_DONE)) + +#define IRQ_PEND_IO_MASK ((1UL << IRQ_PEND_IO_ISC_0) | \ + (1UL << IRQ_PEND_IO_ISC_1) | \ + (1UL << IRQ_PEND_IO_ISC_2) | \ + (1UL << IRQ_PEND_IO_ISC_3) | \ + (1UL << IRQ_PEND_IO_ISC_4) | \ + (1UL << IRQ_PEND_IO_ISC_5) | \ + (1UL << IRQ_PEND_IO_ISC_6) | \ + (1UL << IRQ_PEND_IO_ISC_7)) + +#define IRQ_PEND_MCHK_MASK ((1UL << IRQ_PEND_MCHK_REP) | \ + (1UL << IRQ_PEND_MCHK_EX)) + struct kvm_s390_interrupt_info { struct list_head list; u64 type; @@ -306,14 +386,25 @@ struct kvm_s390_interrupt_info { #define ACTION_STORE_ON_STOP (1<<0) #define ACTION_STOP_ON_STOP (1<<1) +struct kvm_s390_irq_payload { + struct kvm_s390_io_info io; + struct kvm_s390_ext_info ext; + struct kvm_s390_pgm_info pgm; + struct kvm_s390_emerg_info emerg; + struct kvm_s390_extcall_info extcall; + struct kvm_s390_prefix_info prefix; + struct kvm_s390_mchk_info mchk; +}; + struct kvm_s390_local_interrupt { spinlock_t lock; - struct list_head list; - atomic_t active; struct kvm_s390_float_interrupt *float_int; wait_queue_head_t *wq; atomic_t *cpuflags; unsigned int action_bits; + DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS); + struct kvm_s390_irq_payload irq; + unsigned long pending_irqs; }; struct kvm_s390_float_interrupt { @@ -434,6 +525,8 @@ struct kvm_arch{ int user_cpu_state_ctrl; struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS]; wait_queue_head_t ipte_wq; + int ipte_lock_count; + struct mutex ipte_mutex; spinlock_t start_stop_lock; struct kvm_s390_crypto crypto; }; diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index 6cc51fe84410..34fbcac61133 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -147,7 +147,7 @@ struct _lowcore { __u32 softirq_pending; /* 0x02ec */ __u32 percpu_offset; /* 0x02f0 */ __u32 machine_flags; /* 0x02f4 */ - __u32 ftrace_func; /* 0x02f8 */ + __u8 pad_0x02f8[0x02fc-0x02f8]; /* 0x02f8 */ __u32 spinlock_lockval; /* 0x02fc */ __u8 pad_0x0300[0x0e00-0x0300]; /* 0x0300 */ @@ -297,7 +297,7 @@ struct _lowcore { __u64 percpu_offset; /* 0x0378 */ __u64 vdso_per_cpu_data; /* 0x0380 */ __u64 machine_flags; /* 0x0388 */ - __u64 ftrace_func; /* 0x0390 */ + __u8 pad_0x0390[0x0398-0x0390]; /* 0x0390 */ __u64 gmap; /* 0x0398 */ __u32 spinlock_lockval; /* 0x03a0 */ __u8 pad_0x03a0[0x0400-0x03a4]; /* 0x03a4 */ diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 3815bfea1b2d..f49b71954654 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -120,4 +120,15 @@ static inline void arch_exit_mmap(struct mm_struct *mm) { } +static inline void arch_unmap(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ +} + +static inline void arch_bprm_mm_init(struct mm_struct *mm, + struct vm_area_struct *vma) +{ +} + #endif /* __S390_MMU_CONTEXT_H */ diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index c030900320e0..ef803c202d42 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -50,10 +50,6 @@ struct zpci_fmb { atomic64_t unmapped_pages; } __packed __aligned(16); -#define ZPCI_MSI_VEC_BITS 11 -#define ZPCI_MSI_VEC_MAX (1 << ZPCI_MSI_VEC_BITS) -#define ZPCI_MSI_VEC_MASK (ZPCI_MSI_VEC_MAX - 1) - enum zpci_state { ZPCI_FN_STATE_RESERVED, ZPCI_FN_STATE_STANDBY, @@ -90,6 +86,7 @@ struct zpci_dev { /* IRQ stuff */ u64 msi_addr; /* MSI address */ + unsigned int max_msi; /* maximum number of MSI's */ struct airq_iv *aibv; /* adapter interrupt bit vector */ unsigned int aisb; /* number of the summary bit */ diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h index d194d544d694..f664e96f48c7 100644 --- a/arch/s390/include/asm/pci_io.h +++ b/arch/s390/include/asm/pci_io.h @@ -139,7 +139,8 @@ static inline int zpci_memcpy_fromio(void *dst, int size, rc = 0; while (n > 0) { - size = zpci_get_max_write_size((u64) src, (u64) dst, n, 8); + size = zpci_get_max_write_size((u64 __force) src, + (u64) dst, n, 8); req = ZPCI_CREATE_REQ(entry->fh, entry->bar, size); rc = zpci_read_single(req, dst, offset, size); if (rc) @@ -162,7 +163,8 @@ static inline int zpci_memcpy_toio(volatile void __iomem *dst, return -EINVAL; while (n > 0) { - size = zpci_get_max_write_size((u64) dst, (u64) src, n, 128); + size = zpci_get_max_write_size((u64 __force) dst, + (u64) src, n, 128); req = ZPCI_CREATE_REQ(entry->fh, entry->bar, size); if (size > 8) /* main path */ diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index d39a31c3cdf2..3009c2ba46d2 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -22,10 +22,9 @@ unsigned long *page_table_alloc(struct mm_struct *); void page_table_free(struct mm_struct *, unsigned long *); void page_table_free_rcu(struct mmu_gather *, unsigned long *, unsigned long); -void page_table_reset_pgste(struct mm_struct *, unsigned long, unsigned long, - bool init_skey); int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, unsigned long key, bool nq); +unsigned long get_guest_storage_key(struct mm_struct *mm, unsigned long addr); static inline void clear_table(unsigned long *s, unsigned long val, size_t n) { diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 57c882761dea..5e102422c9ab 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -133,6 +133,18 @@ extern unsigned long MODULES_END; #define MODULES_LEN (1UL << 31) #endif +static inline int is_module_addr(void *addr) +{ +#ifdef CONFIG_64BIT + BUILD_BUG_ON(MODULES_LEN > (1UL << 31)); + if (addr < (void *)MODULES_VADDR) + return 0; + if (addr > (void *)MODULES_END) + return 0; +#endif + return 1; +} + /* * A 31 bit pagetable entry of S390 has following format: * | PFRA | | OS | @@ -479,6 +491,11 @@ static inline int mm_has_pgste(struct mm_struct *mm) return 0; } +/* + * In the case that a guest uses storage keys + * faults should no longer be backed by zero pages + */ +#define mm_forbids_zeropage mm_use_skey static inline int mm_use_skey(struct mm_struct *mm) { #ifdef CONFIG_PGSTE @@ -1634,6 +1651,19 @@ static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, return pmd; } +#define __HAVE_ARCH_PMDP_GET_AND_CLEAR_FULL +static inline pmd_t pmdp_get_and_clear_full(struct mm_struct *mm, + unsigned long address, + pmd_t *pmdp, int full) +{ + pmd_t pmd = *pmdp; + + if (!full) + pmdp_flush_lazy(mm, address, pmdp); + pmd_clear(pmdp); + return pmd; +} + #define __HAVE_ARCH_PMDP_CLEAR_FLUSH static inline pmd_t pmdp_clear_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) @@ -1746,7 +1776,8 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) extern int vmem_add_mapping(unsigned long start, unsigned long size); extern int vmem_remove_mapping(unsigned long start, unsigned long size); extern int s390_enable_sie(void); -extern void s390_enable_skey(void); +extern int s390_enable_skey(void); +extern void s390_reset_cmma(struct mm_struct *mm); /* * No page table caches to initialise diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index d559bdb03d18..bed05ea7ec27 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -217,8 +217,6 @@ static inline unsigned short stap(void) */ static inline void cpu_relax(void) { - if (MACHINE_HAS_DIAG44) - asm volatile("diag 0,0,68"); barrier(); } diff --git a/arch/s390/include/asm/sigp.h b/arch/s390/include/asm/sigp.h index 49576115dbb7..fad4ae23ece0 100644 --- a/arch/s390/include/asm/sigp.h +++ b/arch/s390/include/asm/sigp.h @@ -10,6 +10,7 @@ #define SIGP_RESTART 6 #define SIGP_STOP_AND_STORE_STATUS 9 #define SIGP_INITIAL_CPU_RESET 11 +#define SIGP_CPU_RESET 12 #define SIGP_SET_PREFIX 13 #define SIGP_STORE_STATUS_AT_ADDRESS 14 #define SIGP_SET_ARCHITECTURE 18 diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index d6bdf906caa5..0e37cd041241 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -18,14 +18,7 @@ extern int spin_retry; static inline int _raw_compare_and_swap(unsigned int *lock, unsigned int old, unsigned int new) { - unsigned int old_expected = old; - - asm volatile( - " cs %0,%3,%1" - : "=d" (old), "=Q" (*lock) - : "0" (old), "d" (new), "Q" (*lock) - : "cc", "memory" ); - return old == old_expected; + return __sync_bool_compare_and_swap(lock, old, new); } /* diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 572c59949004..06d8741ad6f4 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -121,6 +121,7 @@ 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; + pgtable_pmd_page_dtor(virt_to_page(pmd)); tlb_remove_table(tlb, pmd); #endif } diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index e031332096d7..296942d56e6a 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -86,4 +86,9 @@ #define SO_BPF_EXTENSIONS 48 +#define SO_INCOMING_CPU 49 + +#define SO_ATTACH_BPF 50 +#define SO_DETACH_BPF SO_DETACH_FILTER + #endif /* _ASM_SOCKET_H */ diff --git a/arch/s390/include/uapi/asm/unistd.h b/arch/s390/include/uapi/asm/unistd.h index 4197c89c52d4..2b446cf0cc65 100644 --- a/arch/s390/include/uapi/asm/unistd.h +++ b/arch/s390/include/uapi/asm/unistd.h @@ -287,7 +287,9 @@ #define __NR_getrandom 349 #define __NR_memfd_create 350 #define __NR_bpf 351 -#define NR_syscalls 352 +#define __NR_s390_pci_mmio_write 352 +#define __NR_s390_pci_mmio_read 353 +#define NR_syscalls 354 /* * There are some system calls that are not present on 64 bit, some diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index ef279a136801..e07e91605353 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -17,8 +17,8 @@ * Make sure that the compiler is new enough. We want a compiler that * is known to work with the "Q" assembler constraint. */ -#if __GNUC__ < 3 || (__GNUC__ == 3 && __GNUC_MINOR__ < 3) -#error Your compiler is too old; please use version 3.3.3 or newer +#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 3) +#error Your compiler is too old; please use version 4.3 or newer #endif int main(void) @@ -156,7 +156,6 @@ int main(void) DEFINE(__LC_INT_CLOCK, offsetof(struct _lowcore, int_clock)); DEFINE(__LC_MCCK_CLOCK, offsetof(struct _lowcore, mcck_clock)); DEFINE(__LC_MACHINE_FLAGS, offsetof(struct _lowcore, machine_flags)); - DEFINE(__LC_FTRACE_FUNC, offsetof(struct _lowcore, ftrace_func)); DEFINE(__LC_DUMP_REIPL, offsetof(struct _lowcore, ipib)); BLANK(); DEFINE(__LC_CPU_TIMER_SAVE_AREA, offsetof(struct _lowcore, cpu_timer_save_area)); diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index ca38139423ae..437e61159279 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -249,7 +249,7 @@ COMPAT_SYSCALL_DEFINE2(s390_setgroups16, int, gidsetsize, u16 __user *, grouplis struct group_info *group_info; int retval; - if (!capable(CAP_SETGID)) + if (!may_setgroups()) return -EPERM; if ((unsigned)gidsetsize > NGROUPS_MAX) return -EINVAL; diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index 009f5eb11125..34d5fa7b01b5 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -434,7 +434,7 @@ static int setup_frame32(struct ksignal *ksig, sigset_t *set, ksig->ka.sa.sa_restorer | PSW32_ADDR_AMODE; } else { /* Signal frames without vectors registers are short ! */ - __u16 __user *svc = (void *) frame + frame_size - 2; + __u16 __user *svc = (void __user *) frame + frame_size - 2; if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, svc)) return -EFAULT; restorer = (unsigned long __force) svc | PSW32_ADDR_AMODE; diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c index c4f7a3d655b8..d7fa2f0f1425 100644 --- a/arch/s390/kernel/compat_wrapper.c +++ b/arch/s390/kernel/compat_wrapper.c @@ -218,3 +218,5 @@ COMPAT_SYSCALL_WRAP3(seccomp, unsigned int, op, unsigned int, flags, const char COMPAT_SYSCALL_WRAP3(getrandom, char __user *, buf, size_t, count, unsigned int, flags) COMPAT_SYSCALL_WRAP2(memfd_create, const char __user *, uname, unsigned int, flags) COMPAT_SYSCALL_WRAP3(bpf, int, cmd, union bpf_attr *, attr, unsigned int, size); +COMPAT_SYSCALL_WRAP3(s390_pci_mmio_write, const unsigned long, mmio_addr, const void __user *, user_buffer, const size_t, length); +COMPAT_SYSCALL_WRAP3(s390_pci_mmio_read, const unsigned long, mmio_addr, void __user *, user_buffer, const size_t, length); diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index ee8390da6ea7..c1f21aca76e7 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -1019,7 +1019,7 @@ debug_count_numargs(char *string) */ debug_entry_t* -debug_sprintf_event(debug_info_t* id, int level,char *string,...) +__debug_sprintf_event(debug_info_t *id, int level, char *string, ...) { va_list ap; int numargs,idx; @@ -1027,8 +1027,6 @@ debug_sprintf_event(debug_info_t* id, int level,char *string,...) debug_sprintf_entry_t *curr_event; debug_entry_t *active; - if((!id) || (level > id->level)) - return NULL; if (!debug_active || !id->areas) return NULL; numargs=debug_count_numargs(string); @@ -1050,14 +1048,14 @@ debug_sprintf_event(debug_info_t* id, int level,char *string,...) return active; } -EXPORT_SYMBOL(debug_sprintf_event); +EXPORT_SYMBOL(__debug_sprintf_event); /* * debug_sprintf_exception: */ debug_entry_t* -debug_sprintf_exception(debug_info_t* id, int level,char *string,...) +__debug_sprintf_exception(debug_info_t *id, int level, char *string, ...) { va_list ap; int numargs,idx; @@ -1065,8 +1063,6 @@ debug_sprintf_exception(debug_info_t* id, int level,char *string,...) debug_sprintf_entry_t *curr_event; debug_entry_t *active; - if((!id) || (level > id->level)) - return NULL; if (!debug_active || !id->areas) return NULL; @@ -1089,7 +1085,7 @@ debug_sprintf_exception(debug_info_t* id, int level,char *string,...) return active; } -EXPORT_SYMBOL(debug_sprintf_exception); +EXPORT_SYMBOL(__debug_sprintf_exception); /* * debug_register_view: diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index acb412442e5e..a99852e96a77 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -191,7 +191,8 @@ void die(struct pt_regs *regs, const char *str) console_verbose(); spin_lock_irq(&die_lock); bust_spinlocks(1); - printk("%s: %04x [#%d] ", str, regs->int_code & 0xffff, ++die_counter); + printk("%s: %04x ilc:%d [#%d] ", str, regs->int_code & 0xffff, + regs->int_code >> 17, ++die_counter); #ifdef CONFIG_PREEMPT printk("PREEMPT "); #endif diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index cef2879edff3..302ac1f7f8e7 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -12,7 +12,6 @@ #include <linux/errno.h> #include <linux/string.h> #include <linux/ctype.h> -#include <linux/ftrace.h> #include <linux/lockdep.h> #include <linux/module.h> #include <linux/pfn.h> @@ -490,8 +489,5 @@ void __init startup_init(void) detect_machine_facilities(); setup_topology(); sclp_early_detect(); -#ifdef CONFIG_DYNAMIC_FTRACE - S390_lowcore.ftrace_func = (unsigned long)ftrace_caller; -#endif lockdep_on(); } diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 70203265196f..398329b2b518 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -53,7 +53,7 @@ _PIF_WORK = (_PIF_PER_TRAP) .macro TRACE_IRQS_ON #ifdef CONFIG_TRACE_IRQFLAGS basr %r2,%r0 - l %r1,BASED(.Lhardirqs_on) + l %r1,BASED(.Lc_hardirqs_on) basr %r14,%r1 # call trace_hardirqs_on_caller #endif .endm @@ -61,7 +61,7 @@ _PIF_WORK = (_PIF_PER_TRAP) .macro TRACE_IRQS_OFF #ifdef CONFIG_TRACE_IRQFLAGS basr %r2,%r0 - l %r1,BASED(.Lhardirqs_off) + l %r1,BASED(.Lc_hardirqs_off) basr %r14,%r1 # call trace_hardirqs_off_caller #endif .endm @@ -70,7 +70,7 @@ _PIF_WORK = (_PIF_PER_TRAP) #ifdef CONFIG_LOCKDEP tm __PT_PSW+1(%r11),0x01 # returning to user ? jz .+10 - l %r1,BASED(.Llockdep_sys_exit) + l %r1,BASED(.Lc_lockdep_sys_exit) basr %r14,%r1 # call lockdep_sys_exit #endif .endm @@ -87,8 +87,8 @@ _PIF_WORK = (_PIF_PER_TRAP) tmh %r8,0x0001 # interrupting from user ? jnz 1f lr %r14,%r9 - sl %r14,BASED(.Lcritical_start) - cl %r14,BASED(.Lcritical_length) + sl %r14,BASED(.Lc_critical_start) + cl %r14,BASED(.Lc_critical_length) jhe 0f la %r11,\savearea # inside critical section, do cleanup bras %r14,cleanup_critical @@ -162,7 +162,7 @@ ENTRY(__switch_to) lm %r6,%r15,__SF_GPRS(%r15) # load gprs of next task br %r14 -__critical_start: +.L__critical_start: /* * SVC interrupt handler routine. System calls are synchronous events and * are executed with interrupts enabled. @@ -170,145 +170,145 @@ __critical_start: ENTRY(system_call) stpt __LC_SYNC_ENTER_TIMER -sysc_stm: +.Lsysc_stm: stm %r8,%r15,__LC_SAVE_AREA_SYNC l %r12,__LC_THREAD_INFO l %r13,__LC_SVC_NEW_PSW+4 lhi %r14,_PIF_SYSCALL -sysc_per: +.Lsysc_per: l %r15,__LC_KERNEL_STACK la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs -sysc_vtime: +.Lsysc_vtime: UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER stm %r0,%r7,__PT_R0(%r11) mvc __PT_R8(32,%r11),__LC_SAVE_AREA_SYNC mvc __PT_PSW(8,%r11),__LC_SVC_OLD_PSW mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC st %r14,__PT_FLAGS(%r11) -sysc_do_svc: +.Lsysc_do_svc: l %r10,__TI_sysc_table(%r12) # 31 bit system call table lh %r8,__PT_INT_CODE+2(%r11) sla %r8,2 # shift and test for svc0 - jnz sysc_nr_ok + jnz .Lsysc_nr_ok # svc 0: system call number in %r1 cl %r1,BASED(.Lnr_syscalls) - jnl sysc_nr_ok + jnl .Lsysc_nr_ok sth %r1,__PT_INT_CODE+2(%r11) lr %r8,%r1 sla %r8,2 -sysc_nr_ok: +.Lsysc_nr_ok: xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) st %r2,__PT_ORIG_GPR2(%r11) st %r7,STACK_FRAME_OVERHEAD(%r15) l %r9,0(%r8,%r10) # get system call addr. tm __TI_flags+3(%r12),_TIF_TRACE - jnz sysc_tracesys + jnz .Lsysc_tracesys basr %r14,%r9 # call sys_xxxx st %r2,__PT_R2(%r11) # store return value -sysc_return: +.Lsysc_return: LOCKDEP_SYS_EXIT -sysc_tif: +.Lsysc_tif: tm __PT_PSW+1(%r11),0x01 # returning to user ? - jno sysc_restore + jno .Lsysc_restore tm __PT_FLAGS+3(%r11),_PIF_WORK - jnz sysc_work + jnz .Lsysc_work tm __TI_flags+3(%r12),_TIF_WORK - jnz sysc_work # check for thread work + jnz .Lsysc_work # check for thread work tm __LC_CPU_FLAGS+3,_CIF_WORK - jnz sysc_work -sysc_restore: + jnz .Lsysc_work +.Lsysc_restore: mvc __LC_RETURN_PSW(8),__PT_PSW(%r11) stpt __LC_EXIT_TIMER lm %r0,%r15,__PT_R0(%r11) lpsw __LC_RETURN_PSW -sysc_done: +.Lsysc_done: # # One of the work bits is on. Find out which one. # -sysc_work: +.Lsysc_work: tm __LC_CPU_FLAGS+3,_CIF_MCCK_PENDING - jo sysc_mcck_pending + jo .Lsysc_mcck_pending tm __TI_flags+3(%r12),_TIF_NEED_RESCHED - jo sysc_reschedule + jo .Lsysc_reschedule tm __PT_FLAGS+3(%r11),_PIF_PER_TRAP - jo sysc_singlestep + jo .Lsysc_singlestep tm __TI_flags+3(%r12),_TIF_SIGPENDING - jo sysc_sigpending + jo .Lsysc_sigpending tm __TI_flags+3(%r12),_TIF_NOTIFY_RESUME - jo sysc_notify_resume + jo .Lsysc_notify_resume tm __LC_CPU_FLAGS+3,_CIF_ASCE - jo sysc_uaccess - j sysc_return # beware of critical section cleanup + jo .Lsysc_uaccess + j .Lsysc_return # beware of critical section cleanup # # _TIF_NEED_RESCHED is set, call schedule # -sysc_reschedule: - l %r1,BASED(.Lschedule) - la %r14,BASED(sysc_return) +.Lsysc_reschedule: + l %r1,BASED(.Lc_schedule) + la %r14,BASED(.Lsysc_return) br %r1 # call schedule # # _CIF_MCCK_PENDING is set, call handler # -sysc_mcck_pending: - l %r1,BASED(.Lhandle_mcck) - la %r14,BASED(sysc_return) +.Lsysc_mcck_pending: + l %r1,BASED(.Lc_handle_mcck) + la %r14,BASED(.Lsysc_return) br %r1 # TIF bit will be cleared by handler # # _CIF_ASCE is set, load user space asce # -sysc_uaccess: +.Lsysc_uaccess: ni __LC_CPU_FLAGS+3,255-_CIF_ASCE lctl %c1,%c1,__LC_USER_ASCE # load primary asce - j sysc_return + j .Lsysc_return # # _TIF_SIGPENDING is set, call do_signal # -sysc_sigpending: +.Lsysc_sigpending: lr %r2,%r11 # pass pointer to pt_regs - l %r1,BASED(.Ldo_signal) + l %r1,BASED(.Lc_do_signal) basr %r14,%r1 # call do_signal tm __PT_FLAGS+3(%r11),_PIF_SYSCALL - jno sysc_return + jno .Lsysc_return lm %r2,%r7,__PT_R2(%r11) # load svc arguments l %r10,__TI_sysc_table(%r12) # 31 bit system call table xr %r8,%r8 # svc 0 returns -ENOSYS clc __PT_INT_CODE+2(2,%r11),BASED(.Lnr_syscalls+2) - jnl sysc_nr_ok # invalid svc number -> do svc 0 + jnl .Lsysc_nr_ok # invalid svc number -> do svc 0 lh %r8,__PT_INT_CODE+2(%r11) # load new svc number sla %r8,2 - j sysc_nr_ok # restart svc + j .Lsysc_nr_ok # restart svc # # _TIF_NOTIFY_RESUME is set, call do_notify_resume # -sysc_notify_resume: +.Lsysc_notify_resume: lr %r2,%r11 # pass pointer to pt_regs - l %r1,BASED(.Ldo_notify_resume) - la %r14,BASED(sysc_return) + l %r1,BASED(.Lc_do_notify_resume) + la %r14,BASED(.Lsysc_return) br %r1 # call do_notify_resume # # _PIF_PER_TRAP is set, call do_per_trap # -sysc_singlestep: +.Lsysc_singlestep: ni __PT_FLAGS+3(%r11),255-_PIF_PER_TRAP lr %r2,%r11 # pass pointer to pt_regs - l %r1,BASED(.Ldo_per_trap) - la %r14,BASED(sysc_return) + l %r1,BASED(.Lc_do_per_trap) + la %r14,BASED(.Lsysc_return) br %r1 # call do_per_trap # # call tracehook_report_syscall_entry/tracehook_report_syscall_exit before # and after the system call # -sysc_tracesys: - l %r1,BASED(.Ltrace_enter) +.Lsysc_tracesys: + l %r1,BASED(.Lc_trace_enter) lr %r2,%r11 # pass pointer to pt_regs la %r3,0 xr %r0,%r0 @@ -316,22 +316,22 @@ sysc_tracesys: st %r0,__PT_R2(%r11) basr %r14,%r1 # call do_syscall_trace_enter cl %r2,BASED(.Lnr_syscalls) - jnl sysc_tracenogo + jnl .Lsysc_tracenogo lr %r8,%r2 sll %r8,2 l %r9,0(%r8,%r10) -sysc_tracego: +.Lsysc_tracego: lm %r3,%r7,__PT_R3(%r11) st %r7,STACK_FRAME_OVERHEAD(%r15) l %r2,__PT_ORIG_GPR2(%r11) basr %r14,%r9 # call sys_xxx st %r2,__PT_R2(%r11) # store return value -sysc_tracenogo: +.Lsysc_tracenogo: tm __TI_flags+3(%r12),_TIF_TRACE - jz sysc_return - l %r1,BASED(.Ltrace_exit) + jz .Lsysc_return + l %r1,BASED(.Lc_trace_exit) lr %r2,%r11 # pass pointer to pt_regs - la %r14,BASED(sysc_return) + la %r14,BASED(.Lsysc_return) br %r1 # call do_syscall_trace_exit # @@ -341,18 +341,18 @@ ENTRY(ret_from_fork) la %r11,STACK_FRAME_OVERHEAD(%r15) l %r12,__LC_THREAD_INFO l %r13,__LC_SVC_NEW_PSW+4 - l %r1,BASED(.Lschedule_tail) + l %r1,BASED(.Lc_schedule_tail) basr %r14,%r1 # call schedule_tail TRACE_IRQS_ON ssm __LC_SVC_NEW_PSW # reenable interrupts tm __PT_PSW+1(%r11),0x01 # forking a kernel thread ? - jne sysc_tracenogo + jne .Lsysc_tracenogo # it's a kernel thread lm %r9,%r10,__PT_R9(%r11) # load gprs ENTRY(kernel_thread_starter) la %r2,0(%r10) basr %r14,%r9 - j sysc_tracenogo + j .Lsysc_tracenogo /* * Program check handler routine @@ -369,7 +369,7 @@ ENTRY(pgm_check_handler) tmh %r8,0x4000 # PER bit set in old PSW ? jnz 0f # -> enabled, can't be a double fault tm __LC_PGM_ILC+3,0x80 # check for per exception - jnz pgm_svcper # -> single stepped svc + jnz .Lpgm_svcper # -> single stepped svc 0: CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f @@ -386,42 +386,42 @@ ENTRY(pgm_check_handler) jz 0f l %r1,__TI_task(%r12) tmh %r8,0x0001 # kernel per event ? - jz pgm_kprobe + jz .Lpgm_kprobe oi __PT_FLAGS+3(%r11),_PIF_PER_TRAP mvc __THREAD_per_address(4,%r1),__LC_PER_ADDRESS mvc __THREAD_per_cause(2,%r1),__LC_PER_CODE mvc __THREAD_per_paid(1,%r1),__LC_PER_ACCESS_ID 0: REENABLE_IRQS xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) - l %r1,BASED(.Ljump_table) + l %r1,BASED(.Lc_jump_table) la %r10,0x7f n %r10,__PT_INT_CODE(%r11) - je sysc_return + je .Lsysc_return sll %r10,2 l %r1,0(%r10,%r1) # load address of handler routine lr %r2,%r11 # pass pointer to pt_regs basr %r14,%r1 # branch to interrupt-handler - j sysc_return + j .Lsysc_return # # PER event in supervisor state, must be kprobes # -pgm_kprobe: +.Lpgm_kprobe: REENABLE_IRQS xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) - l %r1,BASED(.Ldo_per_trap) + l %r1,BASED(.Lc_do_per_trap) lr %r2,%r11 # pass pointer to pt_regs basr %r14,%r1 # call do_per_trap - j sysc_return + j .Lsysc_return # # single stepped system call # -pgm_svcper: +.Lpgm_svcper: mvc __LC_RETURN_PSW(4),__LC_SVC_NEW_PSW - mvc __LC_RETURN_PSW+4(4),BASED(.Lsysc_per) + mvc __LC_RETURN_PSW+4(4),BASED(.Lc_sysc_per) lhi %r14,_PIF_SYSCALL | _PIF_PER_TRAP - lpsw __LC_RETURN_PSW # branch to sysc_per and enable irqs + lpsw __LC_RETURN_PSW # branch to .Lsysc_per and enable irqs /* * IO interrupt handler routine @@ -435,9 +435,9 @@ ENTRY(io_int_handler) l %r13,__LC_SVC_NEW_PSW+4 lm %r8,%r9,__LC_IO_OLD_PSW tmh %r8,0x0001 # interrupting from user ? - jz io_skip + jz .Lio_skip UPDATE_VTIME %r14,%r15,__LC_ASYNC_ENTER_TIMER -io_skip: +.Lio_skip: SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT stm %r0,%r7,__PT_R0(%r11) mvc __PT_R8(32,%r11),__LC_SAVE_AREA_ASYNC @@ -446,35 +446,35 @@ io_skip: xc __PT_FLAGS(4,%r11),__PT_FLAGS(%r11) TRACE_IRQS_OFF xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) -io_loop: - l %r1,BASED(.Ldo_IRQ) +.Lio_loop: + l %r1,BASED(.Lc_do_IRQ) lr %r2,%r11 # pass pointer to pt_regs lhi %r3,IO_INTERRUPT tm __PT_INT_CODE+8(%r11),0x80 # adapter interrupt ? - jz io_call + jz .Lio_call lhi %r3,THIN_INTERRUPT -io_call: +.Lio_call: basr %r14,%r1 # call do_IRQ tm __LC_MACHINE_FLAGS+2,0x10 # MACHINE_FLAG_LPAR - jz io_return + jz .Lio_return tpi 0 - jz io_return + jz .Lio_return mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID - j io_loop -io_return: + j .Lio_loop +.Lio_return: LOCKDEP_SYS_EXIT TRACE_IRQS_ON -io_tif: +.Lio_tif: tm __TI_flags+3(%r12),_TIF_WORK - jnz io_work # there is work to do (signals etc.) + jnz .Lio_work # there is work to do (signals etc.) tm __LC_CPU_FLAGS+3,_CIF_WORK - jnz io_work -io_restore: + jnz .Lio_work +.Lio_restore: mvc __LC_RETURN_PSW(8),__PT_PSW(%r11) stpt __LC_EXIT_TIMER lm %r0,%r15,__PT_R0(%r11) lpsw __LC_RETURN_PSW -io_done: +.Lio_done: # # There is work todo, find out in which context we have been interrupted: @@ -483,15 +483,15 @@ io_done: # the preemption counter and if it is zero call preempt_schedule_irq # Before any work can be done, a switch to the kernel stack is required. # -io_work: +.Lio_work: tm __PT_PSW+1(%r11),0x01 # returning to user ? - jo io_work_user # yes -> do resched & signal + jo .Lio_work_user # yes -> do resched & signal #ifdef CONFIG_PREEMPT # check for preemptive scheduling icm %r0,15,__TI_precount(%r12) - jnz io_restore # preemption disabled + jnz .Lio_restore # preemption disabled tm __TI_flags+3(%r12),_TIF_NEED_RESCHED - jno io_restore + jno .Lio_restore # switch to kernel stack l %r1,__PT_R15(%r11) ahi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) @@ -499,20 +499,20 @@ io_work: xc __SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1) la %r11,STACK_FRAME_OVERHEAD(%r1) lr %r15,%r1 - # TRACE_IRQS_ON already done at io_return, call + # TRACE_IRQS_ON already done at .Lio_return, call # TRACE_IRQS_OFF to keep things symmetrical TRACE_IRQS_OFF - l %r1,BASED(.Lpreempt_irq) + l %r1,BASED(.Lc_preempt_irq) basr %r14,%r1 # call preempt_schedule_irq - j io_return + j .Lio_return #else - j io_restore + j .Lio_restore #endif # # Need to do work before returning to userspace, switch to kernel stack # -io_work_user: +.Lio_work_user: l %r1,__LC_KERNEL_STACK mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) xc __SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1) @@ -522,74 +522,74 @@ io_work_user: # # One of the work bits is on. Find out which one. # -io_work_tif: +.Lio_work_tif: tm __LC_CPU_FLAGS+3(%r12),_CIF_MCCK_PENDING - jo io_mcck_pending + jo .Lio_mcck_pending tm __TI_flags+3(%r12),_TIF_NEED_RESCHED - jo io_reschedule + jo .Lio_reschedule tm __TI_flags+3(%r12),_TIF_SIGPENDING - jo io_sigpending + jo .Lio_sigpending tm __TI_flags+3(%r12),_TIF_NOTIFY_RESUME - jo io_notify_resume + jo .Lio_notify_resume tm __LC_CPU_FLAGS+3,_CIF_ASCE - jo io_uaccess - j io_return # beware of critical section cleanup + jo .Lio_uaccess + j .Lio_return # beware of critical section cleanup # # _CIF_MCCK_PENDING is set, call handler # -io_mcck_pending: - # TRACE_IRQS_ON already done at io_return - l %r1,BASED(.Lhandle_mcck) +.Lio_mcck_pending: + # TRACE_IRQS_ON already done at .Lio_return + l %r1,BASED(.Lc_handle_mcck) basr %r14,%r1 # TIF bit will be cleared by handler TRACE_IRQS_OFF - j io_return + j .Lio_return # # _CIF_ASCE is set, load user space asce # -io_uaccess: +.Lio_uaccess: ni __LC_CPU_FLAGS+3,255-_CIF_ASCE lctl %c1,%c1,__LC_USER_ASCE # load primary asce - j io_return + j .Lio_return # # _TIF_NEED_RESCHED is set, call schedule # -io_reschedule: - # TRACE_IRQS_ON already done at io_return - l %r1,BASED(.Lschedule) +.Lio_reschedule: + # TRACE_IRQS_ON already done at .Lio_return + l %r1,BASED(.Lc_schedule) ssm __LC_SVC_NEW_PSW # reenable interrupts basr %r14,%r1 # call scheduler ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts TRACE_IRQS_OFF - j io_return + j .Lio_return # # _TIF_SIGPENDING is set, call do_signal # -io_sigpending: - # TRACE_IRQS_ON already done at io_return - l %r1,BASED(.Ldo_signal) +.Lio_sigpending: + # TRACE_IRQS_ON already done at .Lio_return + l %r1,BASED(.Lc_do_signal) ssm __LC_SVC_NEW_PSW # reenable interrupts lr %r2,%r11 # pass pointer to pt_regs basr %r14,%r1 # call do_signal ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts TRACE_IRQS_OFF - j io_return + j .Lio_return # # _TIF_SIGPENDING is set, call do_signal # -io_notify_resume: - # TRACE_IRQS_ON already done at io_return - l %r1,BASED(.Ldo_notify_resume) +.Lio_notify_resume: + # TRACE_IRQS_ON already done at .Lio_return + l %r1,BASED(.Lc_do_notify_resume) ssm __LC_SVC_NEW_PSW # reenable interrupts lr %r2,%r11 # pass pointer to pt_regs basr %r14,%r1 # call do_notify_resume ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts TRACE_IRQS_OFF - j io_return + j .Lio_return /* * External interrupt handler routine @@ -603,9 +603,9 @@ ENTRY(ext_int_handler) l %r13,__LC_SVC_NEW_PSW+4 lm %r8,%r9,__LC_EXT_OLD_PSW tmh %r8,0x0001 # interrupting from user ? - jz ext_skip + jz .Lext_skip UPDATE_VTIME %r14,%r15,__LC_ASYNC_ENTER_TIMER -ext_skip: +.Lext_skip: SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT stm %r0,%r7,__PT_R0(%r11) mvc __PT_R8(32,%r11),__LC_SAVE_AREA_ASYNC @@ -614,29 +614,29 @@ ext_skip: mvc __PT_INT_PARM(4,%r11),__LC_EXT_PARAMS xc __PT_FLAGS(4,%r11),__PT_FLAGS(%r11) TRACE_IRQS_OFF - l %r1,BASED(.Ldo_IRQ) + l %r1,BASED(.Lc_do_IRQ) lr %r2,%r11 # pass pointer to pt_regs lhi %r3,EXT_INTERRUPT basr %r14,%r1 # call do_IRQ - j io_return + j .Lio_return /* - * Load idle PSW. The second "half" of this function is in cleanup_idle. + * Load idle PSW. The second "half" of this function is in .Lcleanup_idle. */ ENTRY(psw_idle) st %r3,__SF_EMPTY(%r15) basr %r1,0 - la %r1,psw_idle_lpsw+4-.(%r1) + la %r1,.Lpsw_idle_lpsw+4-.(%r1) st %r1,__SF_EMPTY+4(%r15) oi __SF_EMPTY+4(%r15),0x80 stck __CLOCK_IDLE_ENTER(%r2) stpt __TIMER_IDLE_ENTER(%r2) -psw_idle_lpsw: +.Lpsw_idle_lpsw: lpsw __SF_EMPTY(%r15) br %r14 -psw_idle_end: +.Lpsw_idle_end: -__critical_end: +.L__critical_end: /* * Machine check handler routines @@ -650,7 +650,7 @@ ENTRY(mcck_int_handler) l %r13,__LC_SVC_NEW_PSW+4 lm %r8,%r9,__LC_MCK_OLD_PSW tm __LC_MCCK_CODE,0x80 # system damage? - jo mcck_panic # yes -> rest of mcck code invalid + jo .Lmcck_panic # yes -> rest of mcck code invalid la %r14,__LC_CPU_TIMER_SAVE_AREA mvc __LC_MCCK_ENTER_TIMER(8),0(%r14) tm __LC_MCCK_CODE+5,0x02 # stored cpu timer value valid? @@ -668,22 +668,22 @@ ENTRY(mcck_int_handler) 2: spt 0(%r14) mvc __LC_MCCK_ENTER_TIMER(8),0(%r14) 3: tm __LC_MCCK_CODE+2,0x09 # mwp + ia of old psw valid? - jno mcck_panic # no -> skip cleanup critical + jno .Lmcck_panic # no -> skip cleanup critical tm %r8,0x0001 # interrupting from user ? - jz mcck_skip + jz .Lmcck_skip UPDATE_VTIME %r14,%r15,__LC_MCCK_ENTER_TIMER -mcck_skip: +.Lmcck_skip: SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+32,__LC_PANIC_STACK,PAGE_SHIFT stm %r0,%r7,__PT_R0(%r11) mvc __PT_R8(32,%r11),__LC_GPREGS_SAVE_AREA+32 stm %r8,%r9,__PT_PSW(%r11) xc __PT_FLAGS(4,%r11),__PT_FLAGS(%r11) xc __SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) - l %r1,BASED(.Ldo_machine_check) + l %r1,BASED(.Lc_do_machine_check) lr %r2,%r11 # pass pointer to pt_regs basr %r14,%r1 # call s390_do_machine_check tm __PT_PSW+1(%r11),0x01 # returning to user ? - jno mcck_return + jno .Lmcck_return l %r1,__LC_KERNEL_STACK # switch to kernel stack mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) xc __SF_BACKCHAIN(4,%r1),__SF_BACKCHAIN(%r1) @@ -691,12 +691,12 @@ mcck_skip: lr %r15,%r1 ssm __LC_PGM_NEW_PSW # turn dat on, keep irqs off tm __LC_CPU_FLAGS+3,_CIF_MCCK_PENDING - jno mcck_return + jno .Lmcck_return TRACE_IRQS_OFF - l %r1,BASED(.Lhandle_mcck) + l %r1,BASED(.Lc_handle_mcck) basr %r14,%r1 # call s390_handle_mcck TRACE_IRQS_ON -mcck_return: +.Lmcck_return: mvc __LC_RETURN_MCCK_PSW(8),__PT_PSW(%r11) # move return PSW tm __LC_RETURN_MCCK_PSW+1,0x01 # returning to user ? jno 0f @@ -706,15 +706,15 @@ mcck_return: 0: lm %r0,%r15,__PT_R0(%r11) lpsw __LC_RETURN_MCCK_PSW -mcck_panic: +.Lmcck_panic: l %r14,__LC_PANIC_STACK slr %r14,%r15 sra %r14,PAGE_SHIFT jz 0f l %r15,__LC_PANIC_STACK - j mcck_skip + j .Lmcck_skip 0: ahi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - j mcck_skip + j .Lmcck_skip # # PSW restart interrupt handler @@ -764,58 +764,58 @@ stack_overflow: 1: .long kernel_stack_overflow #endif -cleanup_table: +.Lcleanup_table: .long system_call + 0x80000000 - .long sysc_do_svc + 0x80000000 - .long sysc_tif + 0x80000000 - .long sysc_restore + 0x80000000 - .long sysc_done + 0x80000000 - .long io_tif + 0x80000000 - .long io_restore + 0x80000000 - .long io_done + 0x80000000 + .long .Lsysc_do_svc + 0x80000000 + .long .Lsysc_tif + 0x80000000 + .long .Lsysc_restore + 0x80000000 + .long .Lsysc_done + 0x80000000 + .long .Lio_tif + 0x80000000 + .long .Lio_restore + 0x80000000 + .long .Lio_done + 0x80000000 .long psw_idle + 0x80000000 - .long psw_idle_end + 0x80000000 + .long .Lpsw_idle_end + 0x80000000 cleanup_critical: - cl %r9,BASED(cleanup_table) # system_call + cl %r9,BASED(.Lcleanup_table) # system_call jl 0f - cl %r9,BASED(cleanup_table+4) # sysc_do_svc - jl cleanup_system_call - cl %r9,BASED(cleanup_table+8) # sysc_tif + cl %r9,BASED(.Lcleanup_table+4) # .Lsysc_do_svc + jl .Lcleanup_system_call + cl %r9,BASED(.Lcleanup_table+8) # .Lsysc_tif jl 0f - cl %r9,BASED(cleanup_table+12) # sysc_restore - jl cleanup_sysc_tif - cl %r9,BASED(cleanup_table+16) # sysc_done - jl cleanup_sysc_restore - cl %r9,BASED(cleanup_table+20) # io_tif + cl %r9,BASED(.Lcleanup_table+12) # .Lsysc_restore + jl .Lcleanup_sysc_tif + cl %r9,BASED(.Lcleanup_table+16) # .Lsysc_done + jl .Lcleanup_sysc_restore + cl %r9,BASED(.Lcleanup_table+20) # .Lio_tif jl 0f - cl %r9,BASED(cleanup_table+24) # io_restore - jl cleanup_io_tif - cl %r9,BASED(cleanup_table+28) # io_done - jl cleanup_io_restore - cl %r9,BASED(cleanup_table+32) # psw_idle + cl %r9,BASED(.Lcleanup_table+24) # .Lio_restore + jl .Lcleanup_io_tif + cl %r9,BASED(.Lcleanup_table+28) # .Lio_done + jl .Lcleanup_io_restore + cl %r9,BASED(.Lcleanup_table+32) # psw_idle jl 0f - cl %r9,BASED(cleanup_table+36) # psw_idle_end - jl cleanup_idle + cl %r9,BASED(.Lcleanup_table+36) # .Lpsw_idle_end + jl .Lcleanup_idle 0: br %r14 -cleanup_system_call: +.Lcleanup_system_call: # check if stpt has been executed - cl %r9,BASED(cleanup_system_call_insn) + cl %r9,BASED(.Lcleanup_system_call_insn) jh 0f mvc __LC_SYNC_ENTER_TIMER(8),__LC_ASYNC_ENTER_TIMER chi %r11,__LC_SAVE_AREA_ASYNC je 0f mvc __LC_SYNC_ENTER_TIMER(8),__LC_MCCK_ENTER_TIMER 0: # check if stm has been executed - cl %r9,BASED(cleanup_system_call_insn+4) + cl %r9,BASED(.Lcleanup_system_call_insn+4) jh 0f mvc __LC_SAVE_AREA_SYNC(32),0(%r11) 0: # set up saved registers r12, and r13 st %r12,16(%r11) # r12 thread-info pointer st %r13,20(%r11) # r13 literal-pool pointer # check if the user time calculation has been done - cl %r9,BASED(cleanup_system_call_insn+8) + cl %r9,BASED(.Lcleanup_system_call_insn+8) jh 0f l %r10,__LC_EXIT_TIMER l %r15,__LC_EXIT_TIMER+4 @@ -824,7 +824,7 @@ cleanup_system_call: st %r10,__LC_USER_TIMER st %r15,__LC_USER_TIMER+4 0: # check if the system time calculation has been done - cl %r9,BASED(cleanup_system_call_insn+12) + cl %r9,BASED(.Lcleanup_system_call_insn+12) jh 0f l %r10,__LC_LAST_UPDATE_TIMER l %r15,__LC_LAST_UPDATE_TIMER+4 @@ -848,20 +848,20 @@ cleanup_system_call: # setup saved register 15 st %r15,28(%r11) # r15 stack pointer # set new psw address and exit - l %r9,BASED(cleanup_table+4) # sysc_do_svc + 0x80000000 + l %r9,BASED(.Lcleanup_table+4) # .Lsysc_do_svc + 0x80000000 br %r14 -cleanup_system_call_insn: +.Lcleanup_system_call_insn: .long system_call + 0x80000000 - .long sysc_stm + 0x80000000 - .long sysc_vtime + 0x80000000 + 36 - .long sysc_vtime + 0x80000000 + 76 + .long .Lsysc_stm + 0x80000000 + .long .Lsysc_vtime + 0x80000000 + 36 + .long .Lsysc_vtime + 0x80000000 + 76 -cleanup_sysc_tif: - l %r9,BASED(cleanup_table+8) # sysc_tif + 0x80000000 +.Lcleanup_sysc_tif: + l %r9,BASED(.Lcleanup_table+8) # .Lsysc_tif + 0x80000000 br %r14 -cleanup_sysc_restore: - cl %r9,BASED(cleanup_sysc_restore_insn) +.Lcleanup_sysc_restore: + cl %r9,BASED(.Lcleanup_sysc_restore_insn) jhe 0f l %r9,12(%r11) # get saved pointer to pt_regs mvc __LC_RETURN_PSW(8),__PT_PSW(%r9) @@ -869,15 +869,15 @@ cleanup_sysc_restore: lm %r0,%r7,__PT_R0(%r9) 0: lm %r8,%r9,__LC_RETURN_PSW br %r14 -cleanup_sysc_restore_insn: - .long sysc_done - 4 + 0x80000000 +.Lcleanup_sysc_restore_insn: + .long .Lsysc_done - 4 + 0x80000000 -cleanup_io_tif: - l %r9,BASED(cleanup_table+20) # io_tif + 0x80000000 +.Lcleanup_io_tif: + l %r9,BASED(.Lcleanup_table+20) # .Lio_tif + 0x80000000 br %r14 -cleanup_io_restore: - cl %r9,BASED(cleanup_io_restore_insn) +.Lcleanup_io_restore: + cl %r9,BASED(.Lcleanup_io_restore_insn) jhe 0f l %r9,12(%r11) # get saved r11 pointer to pt_regs mvc __LC_RETURN_PSW(8),__PT_PSW(%r9) @@ -885,10 +885,10 @@ cleanup_io_restore: lm %r0,%r7,__PT_R0(%r9) 0: lm %r8,%r9,__LC_RETURN_PSW br %r14 -cleanup_io_restore_insn: - .long io_done - 4 + 0x80000000 +.Lcleanup_io_restore_insn: + .long .Lio_done - 4 + 0x80000000 -cleanup_idle: +.Lcleanup_idle: # copy interrupt clock & cpu timer mvc __CLOCK_IDLE_EXIT(8,%r2),__LC_INT_CLOCK mvc __TIMER_IDLE_EXIT(8,%r2),__LC_ASYNC_ENTER_TIMER @@ -897,7 +897,7 @@ cleanup_idle: mvc __CLOCK_IDLE_EXIT(8,%r2),__LC_MCCK_CLOCK mvc __TIMER_IDLE_EXIT(8,%r2),__LC_MCCK_ENTER_TIMER 0: # check if stck has been executed - cl %r9,BASED(cleanup_idle_insn) + cl %r9,BASED(.Lcleanup_idle_insn) jhe 1f mvc __CLOCK_IDLE_ENTER(8,%r2),__CLOCK_IDLE_EXIT(%r2) mvc __TIMER_IDLE_ENTER(8,%r2),__TIMER_IDLE_EXIT(%r3) @@ -913,12 +913,12 @@ cleanup_idle: stm %r9,%r10,__LC_SYSTEM_TIMER mvc __LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2) # prepare return psw - n %r8,BASED(cleanup_idle_wait) # clear irq & wait state bits + n %r8,BASED(.Lcleanup_idle_wait) # clear irq & wait state bits l %r9,24(%r11) # return from psw_idle br %r14 -cleanup_idle_insn: - .long psw_idle_lpsw + 0x80000000 -cleanup_idle_wait: +.Lcleanup_idle_insn: + .long .Lpsw_idle_lpsw + 0x80000000 +.Lcleanup_idle_wait: .long 0xfcfdffff /* @@ -933,30 +933,30 @@ cleanup_idle_wait: /* * Symbol constants */ -.Ldo_machine_check: .long s390_do_machine_check -.Lhandle_mcck: .long s390_handle_mcck -.Ldo_IRQ: .long do_IRQ -.Ldo_signal: .long do_signal -.Ldo_notify_resume: .long do_notify_resume -.Ldo_per_trap: .long do_per_trap -.Ljump_table: .long pgm_check_table -.Lschedule: .long schedule +.Lc_do_machine_check: .long s390_do_machine_check +.Lc_handle_mcck: .long s390_handle_mcck +.Lc_do_IRQ: .long do_IRQ +.Lc_do_signal: .long do_signal +.Lc_do_notify_resume: .long do_notify_resume +.Lc_do_per_trap: .long do_per_trap +.Lc_jump_table: .long pgm_check_table +.Lc_schedule: .long schedule #ifdef CONFIG_PREEMPT -.Lpreempt_irq: .long preempt_schedule_irq +.Lc_preempt_irq: .long preempt_schedule_irq #endif -.Ltrace_enter: .long do_syscall_trace_enter -.Ltrace_exit: .long do_syscall_trace_exit -.Lschedule_tail: .long schedule_tail -.Lsysc_per: .long sysc_per + 0x80000000 +.Lc_trace_enter: .long do_syscall_trace_enter +.Lc_trace_exit: .long do_syscall_trace_exit +.Lc_schedule_tail: .long schedule_tail +.Lc_sysc_per: .long .Lsysc_per + 0x80000000 #ifdef CONFIG_TRACE_IRQFLAGS -.Lhardirqs_on: .long trace_hardirqs_on_caller -.Lhardirqs_off: .long trace_hardirqs_off_caller +.Lc_hardirqs_on: .long trace_hardirqs_on_caller +.Lc_hardirqs_off: .long trace_hardirqs_off_caller #endif #ifdef CONFIG_LOCKDEP -.Llockdep_sys_exit: .long lockdep_sys_exit +.Lc_lockdep_sys_exit: .long lockdep_sys_exit #endif -.Lcritical_start: .long __critical_start + 0x80000000 -.Lcritical_length: .long __critical_end - __critical_start +.Lc_critical_start: .long .L__critical_start + 0x80000000 +.Lc_critical_length: .long .L__critical_end - .L__critical_start .section .rodata, "a" #define SYSCALL(esa,esame,emu) .long esa diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 0554b9771c9f..8e61393c8275 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -74,4 +74,6 @@ struct old_sigaction; long sys_s390_personality(unsigned int personality); long sys_s390_runtime_instr(int command, int signum); +long sys_s390_pci_mmio_write(unsigned long, const void __user *, size_t); +long sys_s390_pci_mmio_read(unsigned long, void __user *, size_t); #endif /* _ENTRY_H */ diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index 7b2e03afd017..c329446a951d 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -91,7 +91,7 @@ _PIF_WORK = (_PIF_PER_TRAP) .if \reason==1 # Some program interrupts are suppressing (e.g. protection). # We must also check the instruction after SIE in that case. - # do_protection_exception will rewind to rewind_pad + # do_protection_exception will rewind to .Lrewind_pad jh .+42 .else jhe .+42 @@ -192,7 +192,7 @@ ENTRY(__switch_to) lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task br %r14 -__critical_start: +.L__critical_start: /* * SVC interrupt handler routine. System calls are synchronous events and * are executed with interrupts enabled. @@ -200,15 +200,15 @@ __critical_start: ENTRY(system_call) stpt __LC_SYNC_ENTER_TIMER -sysc_stmg: +.Lsysc_stmg: stmg %r8,%r15,__LC_SAVE_AREA_SYNC lg %r10,__LC_LAST_BREAK lg %r12,__LC_THREAD_INFO lghi %r14,_PIF_SYSCALL -sysc_per: +.Lsysc_per: lg %r15,__LC_KERNEL_STACK la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs -sysc_vtime: +.Lsysc_vtime: UPDATE_VTIME %r13,__LC_SYNC_ENTER_TIMER LAST_BREAK %r13 stmg %r0,%r7,__PT_R0(%r11) @@ -216,39 +216,39 @@ sysc_vtime: mvc __PT_PSW(16,%r11),__LC_SVC_OLD_PSW mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC stg %r14,__PT_FLAGS(%r11) -sysc_do_svc: +.Lsysc_do_svc: lg %r10,__TI_sysc_table(%r12) # address of system call table llgh %r8,__PT_INT_CODE+2(%r11) slag %r8,%r8,2 # shift and test for svc 0 - jnz sysc_nr_ok + jnz .Lsysc_nr_ok # svc 0: system call number in %r1 llgfr %r1,%r1 # clear high word in r1 cghi %r1,NR_syscalls - jnl sysc_nr_ok + jnl .Lsysc_nr_ok sth %r1,__PT_INT_CODE+2(%r11) slag %r8,%r1,2 -sysc_nr_ok: +.Lsysc_nr_ok: xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) stg %r2,__PT_ORIG_GPR2(%r11) stg %r7,STACK_FRAME_OVERHEAD(%r15) lgf %r9,0(%r8,%r10) # get system call add. tm __TI_flags+7(%r12),_TIF_TRACE - jnz sysc_tracesys + jnz .Lsysc_tracesys basr %r14,%r9 # call sys_xxxx stg %r2,__PT_R2(%r11) # store return value -sysc_return: +.Lsysc_return: LOCKDEP_SYS_EXIT -sysc_tif: +.Lsysc_tif: tm __PT_PSW+1(%r11),0x01 # returning to user ? - jno sysc_restore + jno .Lsysc_restore tm __PT_FLAGS+7(%r11),_PIF_WORK - jnz sysc_work + jnz .Lsysc_work tm __TI_flags+7(%r12),_TIF_WORK - jnz sysc_work # check for work + jnz .Lsysc_work # check for work tm __LC_CPU_FLAGS+7,_CIF_WORK - jnz sysc_work -sysc_restore: + jnz .Lsysc_work +.Lsysc_restore: lg %r14,__LC_VDSO_PER_CPU lmg %r0,%r10,__PT_R0(%r11) mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) @@ -256,101 +256,101 @@ sysc_restore: mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER lmg %r11,%r15,__PT_R11(%r11) lpswe __LC_RETURN_PSW -sysc_done: +.Lsysc_done: # # One of the work bits is on. Find out which one. # -sysc_work: +.Lsysc_work: tm __LC_CPU_FLAGS+7,_CIF_MCCK_PENDING - jo sysc_mcck_pending + jo .Lsysc_mcck_pending tm __TI_flags+7(%r12),_TIF_NEED_RESCHED - jo sysc_reschedule + jo .Lsysc_reschedule #ifdef CONFIG_UPROBES tm __TI_flags+7(%r12),_TIF_UPROBE - jo sysc_uprobe_notify + jo .Lsysc_uprobe_notify #endif tm __PT_FLAGS+7(%r11),_PIF_PER_TRAP - jo sysc_singlestep + jo .Lsysc_singlestep tm __TI_flags+7(%r12),_TIF_SIGPENDING - jo sysc_sigpending + jo .Lsysc_sigpending tm __TI_flags+7(%r12),_TIF_NOTIFY_RESUME - jo sysc_notify_resume + jo .Lsysc_notify_resume tm __LC_CPU_FLAGS+7,_CIF_ASCE - jo sysc_uaccess - j sysc_return # beware of critical section cleanup + jo .Lsysc_uaccess + j .Lsysc_return # beware of critical section cleanup # # _TIF_NEED_RESCHED is set, call schedule # -sysc_reschedule: - larl %r14,sysc_return +.Lsysc_reschedule: + larl %r14,.Lsysc_return jg schedule # # _CIF_MCCK_PENDING is set, call handler # -sysc_mcck_pending: - larl %r14,sysc_return +.Lsysc_mcck_pending: + larl %r14,.Lsysc_return jg s390_handle_mcck # TIF bit will be cleared by handler # # _CIF_ASCE is set, load user space asce # -sysc_uaccess: +.Lsysc_uaccess: ni __LC_CPU_FLAGS+7,255-_CIF_ASCE lctlg %c1,%c1,__LC_USER_ASCE # load primary asce - j sysc_return + j .Lsysc_return # # _TIF_SIGPENDING is set, call do_signal # -sysc_sigpending: +.Lsysc_sigpending: lgr %r2,%r11 # pass pointer to pt_regs brasl %r14,do_signal tm __PT_FLAGS+7(%r11),_PIF_SYSCALL - jno sysc_return + jno .Lsysc_return lmg %r2,%r7,__PT_R2(%r11) # load svc arguments lg %r10,__TI_sysc_table(%r12) # address of system call table lghi %r8,0 # svc 0 returns -ENOSYS llgh %r1,__PT_INT_CODE+2(%r11) # load new svc number cghi %r1,NR_syscalls - jnl sysc_nr_ok # invalid svc number -> do svc 0 + jnl .Lsysc_nr_ok # invalid svc number -> do svc 0 slag %r8,%r1,2 - j sysc_nr_ok # restart svc + j .Lsysc_nr_ok # restart svc # # _TIF_NOTIFY_RESUME is set, call do_notify_resume # -sysc_notify_resume: +.Lsysc_notify_resume: lgr %r2,%r11 # pass pointer to pt_regs - larl %r14,sysc_return + larl %r14,.Lsysc_return jg do_notify_resume # # _TIF_UPROBE is set, call uprobe_notify_resume # #ifdef CONFIG_UPROBES -sysc_uprobe_notify: +.Lsysc_uprobe_notify: lgr %r2,%r11 # pass pointer to pt_regs - larl %r14,sysc_return + larl %r14,.Lsysc_return jg uprobe_notify_resume #endif # # _PIF_PER_TRAP is set, call do_per_trap # -sysc_singlestep: +.Lsysc_singlestep: ni __PT_FLAGS+7(%r11),255-_PIF_PER_TRAP lgr %r2,%r11 # pass pointer to pt_regs - larl %r14,sysc_return + larl %r14,.Lsysc_return jg do_per_trap # # call tracehook_report_syscall_entry/tracehook_report_syscall_exit before # and after the system call # -sysc_tracesys: +.Lsysc_tracesys: lgr %r2,%r11 # pass pointer to pt_regs la %r3,0 llgh %r0,__PT_INT_CODE+2(%r11) @@ -358,20 +358,20 @@ sysc_tracesys: brasl %r14,do_syscall_trace_enter lghi %r0,NR_syscalls clgr %r0,%r2 - jnh sysc_tracenogo + jnh .Lsysc_tracenogo sllg %r8,%r2,2 lgf %r9,0(%r8,%r10) -sysc_tracego: +.Lsysc_tracego: lmg %r3,%r7,__PT_R3(%r11) stg %r7,STACK_FRAME_OVERHEAD(%r15) lg %r2,__PT_ORIG_GPR2(%r11) basr %r14,%r9 # call sys_xxx stg %r2,__PT_R2(%r11) # store return value -sysc_tracenogo: +.Lsysc_tracenogo: tm __TI_flags+7(%r12),_TIF_TRACE - jz sysc_return + jz .Lsysc_return lgr %r2,%r11 # pass pointer to pt_regs - larl %r14,sysc_return + larl %r14,.Lsysc_return jg do_syscall_trace_exit # @@ -384,13 +384,13 @@ ENTRY(ret_from_fork) TRACE_IRQS_ON ssm __LC_SVC_NEW_PSW # reenable interrupts tm __PT_PSW+1(%r11),0x01 # forking a kernel thread ? - jne sysc_tracenogo + jne .Lsysc_tracenogo # it's a kernel thread lmg %r9,%r10,__PT_R9(%r11) # load gprs ENTRY(kernel_thread_starter) la %r2,0(%r10) basr %r14,%r9 - j sysc_tracenogo + j .Lsysc_tracenogo /* * Program check handler routine @@ -409,7 +409,7 @@ ENTRY(pgm_check_handler) tmhh %r8,0x4000 # PER bit set in old PSW ? jnz 0f # -> enabled, can't be a double fault tm __LC_PGM_ILC+3,0x80 # check for per exception - jnz pgm_svcper # -> single stepped svc + jnz .Lpgm_svcper # -> single stepped svc 0: CHECK_STACK STACK_SIZE,__LC_SAVE_AREA_SYNC aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f @@ -432,7 +432,7 @@ ENTRY(pgm_check_handler) tm __LC_PGM_ILC+3,0x80 # check for per exception jz 0f tmhh %r8,0x0001 # kernel per event ? - jz pgm_kprobe + jz .Lpgm_kprobe oi __PT_FLAGS+7(%r11),_PIF_PER_TRAP mvc __THREAD_per_address(8,%r14),__LC_PER_ADDRESS mvc __THREAD_per_cause(2,%r14),__LC_PER_CODE @@ -443,31 +443,31 @@ ENTRY(pgm_check_handler) llgh %r10,__PT_INT_CODE+2(%r11) nill %r10,0x007f sll %r10,2 - je sysc_return + je .Lsysc_return lgf %r1,0(%r10,%r1) # load address of handler routine lgr %r2,%r11 # pass pointer to pt_regs basr %r14,%r1 # branch to interrupt-handler - j sysc_return + j .Lsysc_return # # PER event in supervisor state, must be kprobes # -pgm_kprobe: +.Lpgm_kprobe: REENABLE_IRQS xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) lgr %r2,%r11 # pass pointer to pt_regs brasl %r14,do_per_trap - j sysc_return + j .Lsysc_return # # single stepped system call # -pgm_svcper: +.Lpgm_svcper: mvc __LC_RETURN_PSW(8),__LC_SVC_NEW_PSW - larl %r14,sysc_per + larl %r14,.Lsysc_per stg %r14,__LC_RETURN_PSW+8 lghi %r14,_PIF_SYSCALL | _PIF_PER_TRAP - lpswe __LC_RETURN_PSW # branch to sysc_per and enable irqs + lpswe __LC_RETURN_PSW # branch to .Lsysc_per and enable irqs /* * IO interrupt handler routine @@ -483,10 +483,10 @@ ENTRY(io_int_handler) HANDLE_SIE_INTERCEPT %r14,2 SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT tmhh %r8,0x0001 # interrupting from user? - jz io_skip + jz .Lio_skip UPDATE_VTIME %r14,__LC_ASYNC_ENTER_TIMER LAST_BREAK %r14 -io_skip: +.Lio_skip: stmg %r0,%r7,__PT_R0(%r11) mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC stmg %r8,%r9,__PT_PSW(%r11) @@ -494,29 +494,29 @@ io_skip: xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) TRACE_IRQS_OFF xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) -io_loop: +.Lio_loop: lgr %r2,%r11 # pass pointer to pt_regs lghi %r3,IO_INTERRUPT tm __PT_INT_CODE+8(%r11),0x80 # adapter interrupt ? - jz io_call + jz .Lio_call lghi %r3,THIN_INTERRUPT -io_call: +.Lio_call: brasl %r14,do_IRQ tm __LC_MACHINE_FLAGS+6,0x10 # MACHINE_FLAG_LPAR - jz io_return + jz .Lio_return tpi 0 - jz io_return + jz .Lio_return mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID - j io_loop -io_return: + j .Lio_loop +.Lio_return: LOCKDEP_SYS_EXIT TRACE_IRQS_ON -io_tif: +.Lio_tif: tm __TI_flags+7(%r12),_TIF_WORK - jnz io_work # there is work to do (signals etc.) + jnz .Lio_work # there is work to do (signals etc.) tm __LC_CPU_FLAGS+7,_CIF_WORK - jnz io_work -io_restore: + jnz .Lio_work +.Lio_restore: lg %r14,__LC_VDSO_PER_CPU lmg %r0,%r10,__PT_R0(%r11) mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) @@ -524,7 +524,7 @@ io_restore: mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER lmg %r11,%r15,__PT_R11(%r11) lpswe __LC_RETURN_PSW -io_done: +.Lio_done: # # There is work todo, find out in which context we have been interrupted: @@ -535,15 +535,15 @@ io_done: # the preemption counter and if it is zero call preempt_schedule_irq # Before any work can be done, a switch to the kernel stack is required. # -io_work: +.Lio_work: tm __PT_PSW+1(%r11),0x01 # returning to user ? - jo io_work_user # yes -> do resched & signal + jo .Lio_work_user # yes -> do resched & signal #ifdef CONFIG_PREEMPT # check for preemptive scheduling icm %r0,15,__TI_precount(%r12) - jnz io_restore # preemption is disabled + jnz .Lio_restore # preemption is disabled tm __TI_flags+7(%r12),_TIF_NEED_RESCHED - jno io_restore + jno .Lio_restore # switch to kernel stack lg %r1,__PT_R15(%r11) aghi %r1,-(STACK_FRAME_OVERHEAD + __PT_SIZE) @@ -551,19 +551,19 @@ io_work: xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) la %r11,STACK_FRAME_OVERHEAD(%r1) lgr %r15,%r1 - # TRACE_IRQS_ON already done at io_return, call + # TRACE_IRQS_ON already done at .Lio_return, call # TRACE_IRQS_OFF to keep things symmetrical TRACE_IRQS_OFF brasl %r14,preempt_schedule_irq - j io_return + j .Lio_return #else - j io_restore + j .Lio_restore #endif # # Need to do work before returning to userspace, switch to kernel stack # -io_work_user: +.Lio_work_user: lg %r1,__LC_KERNEL_STACK mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) @@ -573,70 +573,70 @@ io_work_user: # # One of the work bits is on. Find out which one. # -io_work_tif: +.Lio_work_tif: tm __LC_CPU_FLAGS+7,_CIF_MCCK_PENDING - jo io_mcck_pending + jo .Lio_mcck_pending tm __TI_flags+7(%r12),_TIF_NEED_RESCHED - jo io_reschedule + jo .Lio_reschedule tm __TI_flags+7(%r12),_TIF_SIGPENDING - jo io_sigpending + jo .Lio_sigpending tm __TI_flags+7(%r12),_TIF_NOTIFY_RESUME - jo io_notify_resume + jo .Lio_notify_resume tm __LC_CPU_FLAGS+7,_CIF_ASCE - jo io_uaccess - j io_return # beware of critical section cleanup + jo .Lio_uaccess + j .Lio_return # beware of critical section cleanup # # _CIF_MCCK_PENDING is set, call handler # -io_mcck_pending: - # TRACE_IRQS_ON already done at io_return +.Lio_mcck_pending: + # TRACE_IRQS_ON already done at .Lio_return brasl %r14,s390_handle_mcck # TIF bit will be cleared by handler TRACE_IRQS_OFF - j io_return + j .Lio_return # # _CIF_ASCE is set, load user space asce # -io_uaccess: +.Lio_uaccess: ni __LC_CPU_FLAGS+7,255-_CIF_ASCE lctlg %c1,%c1,__LC_USER_ASCE # load primary asce - j io_return + j .Lio_return # # _TIF_NEED_RESCHED is set, call schedule # -io_reschedule: - # TRACE_IRQS_ON already done at io_return +.Lio_reschedule: + # TRACE_IRQS_ON already done at .Lio_return ssm __LC_SVC_NEW_PSW # reenable interrupts brasl %r14,schedule # call scheduler ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts TRACE_IRQS_OFF - j io_return + j .Lio_return # # _TIF_SIGPENDING or is set, call do_signal # -io_sigpending: - # TRACE_IRQS_ON already done at io_return +.Lio_sigpending: + # TRACE_IRQS_ON already done at .Lio_return ssm __LC_SVC_NEW_PSW # reenable interrupts lgr %r2,%r11 # pass pointer to pt_regs brasl %r14,do_signal ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts TRACE_IRQS_OFF - j io_return + j .Lio_return # # _TIF_NOTIFY_RESUME or is set, call do_notify_resume # -io_notify_resume: - # TRACE_IRQS_ON already done at io_return +.Lio_notify_resume: + # TRACE_IRQS_ON already done at .Lio_return ssm __LC_SVC_NEW_PSW # reenable interrupts lgr %r2,%r11 # pass pointer to pt_regs brasl %r14,do_notify_resume ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts TRACE_IRQS_OFF - j io_return + j .Lio_return /* * External interrupt handler routine @@ -652,10 +652,10 @@ ENTRY(ext_int_handler) HANDLE_SIE_INTERCEPT %r14,3 SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_STACK,STACK_SHIFT tmhh %r8,0x0001 # interrupting from user ? - jz ext_skip + jz .Lext_skip UPDATE_VTIME %r14,__LC_ASYNC_ENTER_TIMER LAST_BREAK %r14 -ext_skip: +.Lext_skip: stmg %r0,%r7,__PT_R0(%r11) mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC stmg %r8,%r9,__PT_PSW(%r11) @@ -669,23 +669,23 @@ ext_skip: lgr %r2,%r11 # pass pointer to pt_regs lghi %r3,EXT_INTERRUPT brasl %r14,do_IRQ - j io_return + j .Lio_return /* - * Load idle PSW. The second "half" of this function is in cleanup_idle. + * Load idle PSW. The second "half" of this function is in .Lcleanup_idle. */ ENTRY(psw_idle) stg %r3,__SF_EMPTY(%r15) - larl %r1,psw_idle_lpsw+4 + larl %r1,.Lpsw_idle_lpsw+4 stg %r1,__SF_EMPTY+8(%r15) STCK __CLOCK_IDLE_ENTER(%r2) stpt __TIMER_IDLE_ENTER(%r2) -psw_idle_lpsw: +.Lpsw_idle_lpsw: lpswe __SF_EMPTY(%r15) br %r14 -psw_idle_end: +.Lpsw_idle_end: -__critical_end: +.L__critical_end: /* * Machine check handler routines @@ -701,7 +701,7 @@ ENTRY(mcck_int_handler) lmg %r8,%r9,__LC_MCK_OLD_PSW HANDLE_SIE_INTERCEPT %r14,4 tm __LC_MCCK_CODE,0x80 # system damage? - jo mcck_panic # yes -> rest of mcck code invalid + jo .Lmcck_panic # yes -> rest of mcck code invalid lghi %r14,__LC_CPU_TIMER_SAVE_AREA mvc __LC_MCCK_ENTER_TIMER(8),0(%r14) tm __LC_MCCK_CODE+5,0x02 # stored cpu timer value valid? @@ -719,13 +719,13 @@ ENTRY(mcck_int_handler) 2: spt 0(%r14) mvc __LC_MCCK_ENTER_TIMER(8),0(%r14) 3: tm __LC_MCCK_CODE+2,0x09 # mwp + ia of old psw valid? - jno mcck_panic # no -> skip cleanup critical + jno .Lmcck_panic # no -> skip cleanup critical SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+64,__LC_PANIC_STACK,PAGE_SHIFT tm %r8,0x0001 # interrupting from user ? - jz mcck_skip + jz .Lmcck_skip UPDATE_VTIME %r14,__LC_MCCK_ENTER_TIMER LAST_BREAK %r14 -mcck_skip: +.Lmcck_skip: lghi %r14,__LC_GPREGS_SAVE_AREA+64 stmg %r0,%r7,__PT_R0(%r11) mvc __PT_R8(64,%r11),0(%r14) @@ -735,7 +735,7 @@ mcck_skip: lgr %r2,%r11 # pass pointer to pt_regs brasl %r14,s390_do_machine_check tm __PT_PSW+1(%r11),0x01 # returning to user ? - jno mcck_return + jno .Lmcck_return lg %r1,__LC_KERNEL_STACK # switch to kernel stack mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) @@ -743,11 +743,11 @@ mcck_skip: lgr %r15,%r1 ssm __LC_PGM_NEW_PSW # turn dat on, keep irqs off tm __LC_CPU_FLAGS+7,_CIF_MCCK_PENDING - jno mcck_return + jno .Lmcck_return TRACE_IRQS_OFF brasl %r14,s390_handle_mcck TRACE_IRQS_ON -mcck_return: +.Lmcck_return: lg %r14,__LC_VDSO_PER_CPU lmg %r0,%r10,__PT_R0(%r11) mvc __LC_RETURN_MCCK_PSW(16),__PT_PSW(%r11) # move return PSW @@ -758,14 +758,14 @@ mcck_return: 0: lmg %r11,%r15,__PT_R11(%r11) lpswe __LC_RETURN_MCCK_PSW -mcck_panic: +.Lmcck_panic: lg %r14,__LC_PANIC_STACK slgr %r14,%r15 srag %r14,%r14,PAGE_SHIFT jz 0f lg %r15,__LC_PANIC_STACK 0: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - j mcck_skip + j .Lmcck_skip # # PSW restart interrupt handler @@ -815,69 +815,69 @@ stack_overflow: #endif .align 8 -cleanup_table: +.Lcleanup_table: .quad system_call - .quad sysc_do_svc - .quad sysc_tif - .quad sysc_restore - .quad sysc_done - .quad io_tif - .quad io_restore - .quad io_done + .quad .Lsysc_do_svc + .quad .Lsysc_tif + .quad .Lsysc_restore + .quad .Lsysc_done + .quad .Lio_tif + .quad .Lio_restore + .quad .Lio_done .quad psw_idle - .quad psw_idle_end + .quad .Lpsw_idle_end cleanup_critical: - clg %r9,BASED(cleanup_table) # system_call + clg %r9,BASED(.Lcleanup_table) # system_call jl 0f - clg %r9,BASED(cleanup_table+8) # sysc_do_svc - jl cleanup_system_call - clg %r9,BASED(cleanup_table+16) # sysc_tif + clg %r9,BASED(.Lcleanup_table+8) # .Lsysc_do_svc + jl .Lcleanup_system_call + clg %r9,BASED(.Lcleanup_table+16) # .Lsysc_tif jl 0f - clg %r9,BASED(cleanup_table+24) # sysc_restore - jl cleanup_sysc_tif - clg %r9,BASED(cleanup_table+32) # sysc_done - jl cleanup_sysc_restore - clg %r9,BASED(cleanup_table+40) # io_tif + clg %r9,BASED(.Lcleanup_table+24) # .Lsysc_restore + jl .Lcleanup_sysc_tif + clg %r9,BASED(.Lcleanup_table+32) # .Lsysc_done + jl .Lcleanup_sysc_restore + clg %r9,BASED(.Lcleanup_table+40) # .Lio_tif jl 0f - clg %r9,BASED(cleanup_table+48) # io_restore - jl cleanup_io_tif - clg %r9,BASED(cleanup_table+56) # io_done - jl cleanup_io_restore - clg %r9,BASED(cleanup_table+64) # psw_idle + clg %r9,BASED(.Lcleanup_table+48) # .Lio_restore + jl .Lcleanup_io_tif + clg %r9,BASED(.Lcleanup_table+56) # .Lio_done + jl .Lcleanup_io_restore + clg %r9,BASED(.Lcleanup_table+64) # psw_idle jl 0f - clg %r9,BASED(cleanup_table+72) # psw_idle_end - jl cleanup_idle + clg %r9,BASED(.Lcleanup_table+72) # .Lpsw_idle_end + jl .Lcleanup_idle 0: br %r14 -cleanup_system_call: +.Lcleanup_system_call: # check if stpt has been executed - clg %r9,BASED(cleanup_system_call_insn) + clg %r9,BASED(.Lcleanup_system_call_insn) jh 0f mvc __LC_SYNC_ENTER_TIMER(8),__LC_ASYNC_ENTER_TIMER cghi %r11,__LC_SAVE_AREA_ASYNC je 0f mvc __LC_SYNC_ENTER_TIMER(8),__LC_MCCK_ENTER_TIMER 0: # check if stmg has been executed - clg %r9,BASED(cleanup_system_call_insn+8) + clg %r9,BASED(.Lcleanup_system_call_insn+8) jh 0f mvc __LC_SAVE_AREA_SYNC(64),0(%r11) 0: # check if base register setup + TIF bit load has been done - clg %r9,BASED(cleanup_system_call_insn+16) + clg %r9,BASED(.Lcleanup_system_call_insn+16) jhe 0f # set up saved registers r10 and r12 stg %r10,16(%r11) # r10 last break stg %r12,32(%r11) # r12 thread-info pointer 0: # check if the user time update has been done - clg %r9,BASED(cleanup_system_call_insn+24) + clg %r9,BASED(.Lcleanup_system_call_insn+24) jh 0f lg %r15,__LC_EXIT_TIMER slg %r15,__LC_SYNC_ENTER_TIMER alg %r15,__LC_USER_TIMER stg %r15,__LC_USER_TIMER 0: # check if the system time update has been done - clg %r9,BASED(cleanup_system_call_insn+32) + clg %r9,BASED(.Lcleanup_system_call_insn+32) jh 0f lg %r15,__LC_LAST_UPDATE_TIMER slg %r15,__LC_EXIT_TIMER @@ -904,21 +904,21 @@ cleanup_system_call: # setup saved register r15 stg %r15,56(%r11) # r15 stack pointer # set new psw address and exit - larl %r9,sysc_do_svc + larl %r9,.Lsysc_do_svc br %r14 -cleanup_system_call_insn: +.Lcleanup_system_call_insn: .quad system_call - .quad sysc_stmg - .quad sysc_per - .quad sysc_vtime+18 - .quad sysc_vtime+42 + .quad .Lsysc_stmg + .quad .Lsysc_per + .quad .Lsysc_vtime+18 + .quad .Lsysc_vtime+42 -cleanup_sysc_tif: - larl %r9,sysc_tif +.Lcleanup_sysc_tif: + larl %r9,.Lsysc_tif br %r14 -cleanup_sysc_restore: - clg %r9,BASED(cleanup_sysc_restore_insn) +.Lcleanup_sysc_restore: + clg %r9,BASED(.Lcleanup_sysc_restore_insn) je 0f lg %r9,24(%r11) # get saved pointer to pt_regs mvc __LC_RETURN_PSW(16),__PT_PSW(%r9) @@ -926,15 +926,15 @@ cleanup_sysc_restore: lmg %r0,%r7,__PT_R0(%r9) 0: lmg %r8,%r9,__LC_RETURN_PSW br %r14 -cleanup_sysc_restore_insn: - .quad sysc_done - 4 +.Lcleanup_sysc_restore_insn: + .quad .Lsysc_done - 4 -cleanup_io_tif: - larl %r9,io_tif +.Lcleanup_io_tif: + larl %r9,.Lio_tif br %r14 -cleanup_io_restore: - clg %r9,BASED(cleanup_io_restore_insn) +.Lcleanup_io_restore: + clg %r9,BASED(.Lcleanup_io_restore_insn) je 0f lg %r9,24(%r11) # get saved r11 pointer to pt_regs mvc __LC_RETURN_PSW(16),__PT_PSW(%r9) @@ -942,10 +942,10 @@ cleanup_io_restore: lmg %r0,%r7,__PT_R0(%r9) 0: lmg %r8,%r9,__LC_RETURN_PSW br %r14 -cleanup_io_restore_insn: - .quad io_done - 4 +.Lcleanup_io_restore_insn: + .quad .Lio_done - 4 -cleanup_idle: +.Lcleanup_idle: # copy interrupt clock & cpu timer mvc __CLOCK_IDLE_EXIT(8,%r2),__LC_INT_CLOCK mvc __TIMER_IDLE_EXIT(8,%r2),__LC_ASYNC_ENTER_TIMER @@ -954,7 +954,7 @@ cleanup_idle: mvc __CLOCK_IDLE_EXIT(8,%r2),__LC_MCCK_CLOCK mvc __TIMER_IDLE_EXIT(8,%r2),__LC_MCCK_ENTER_TIMER 0: # check if stck & stpt have been executed - clg %r9,BASED(cleanup_idle_insn) + clg %r9,BASED(.Lcleanup_idle_insn) jhe 1f mvc __CLOCK_IDLE_ENTER(8,%r2),__CLOCK_IDLE_EXIT(%r2) mvc __TIMER_IDLE_ENTER(8,%r2),__TIMER_IDLE_EXIT(%r2) @@ -973,17 +973,17 @@ cleanup_idle: nihh %r8,0xfcfd # clear irq & wait state bits lg %r9,48(%r11) # return from psw_idle br %r14 -cleanup_idle_insn: - .quad psw_idle_lpsw +.Lcleanup_idle_insn: + .quad .Lpsw_idle_lpsw /* * Integer constants */ .align 8 .Lcritical_start: - .quad __critical_start + .quad .L__critical_start .Lcritical_length: - .quad __critical_end - __critical_start + .quad .L__critical_end - .L__critical_start #if IS_ENABLED(CONFIG_KVM) @@ -1000,25 +1000,25 @@ ENTRY(sie64a) lmg %r0,%r13,0(%r3) # load guest gprs 0-13 lg %r14,__LC_GMAP # get gmap pointer ltgr %r14,%r14 - jz sie_gmap + jz .Lsie_gmap lctlg %c1,%c1,__GMAP_ASCE(%r14) # load primary asce -sie_gmap: +.Lsie_gmap: lg %r14,__SF_EMPTY(%r15) # get control block pointer oi __SIE_PROG0C+3(%r14),1 # we are going into SIE now tm __SIE_PROG20+3(%r14),1 # last exit... - jnz sie_done + jnz .Lsie_done LPP __SF_EMPTY(%r15) # set guest id sie 0(%r14) -sie_done: +.Lsie_done: LPP __SF_EMPTY+16(%r15) # set host id ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE lctlg %c1,%c1,__LC_USER_ASCE # load primary asce # some program checks are suppressing. C code (e.g. do_protection_exception) # will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other -# instructions between sie64a and sie_done should not cause program +# instructions between sie64a and .Lsie_done should not cause program # interrupts. So lets use a nop (47 00 00 00) as a landing pad. # See also HANDLE_SIE_INTERCEPT -rewind_pad: +.Lrewind_pad: nop 0 .globl sie_exit sie_exit: @@ -1027,19 +1027,19 @@ sie_exit: lmg %r6,%r14,__SF_GPRS(%r15) # restore kernel registers lg %r2,__SF_EMPTY+24(%r15) # return exit reason code br %r14 -sie_fault: +.Lsie_fault: lghi %r14,-EFAULT stg %r14,__SF_EMPTY+24(%r15) # set exit reason code j sie_exit .align 8 .Lsie_critical: - .quad sie_gmap + .quad .Lsie_gmap .Lsie_critical_length: - .quad sie_done - sie_gmap + .quad .Lsie_done - .Lsie_gmap - EX_TABLE(rewind_pad,sie_fault) - EX_TABLE(sie_exit,sie_fault) + EX_TABLE(.Lrewind_pad,.Lsie_fault) + EX_TABLE(sie_exit,.Lsie_fault) #endif .section .rodata, "a" diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index ca1cabb3a96c..b86bb8823f15 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -7,6 +7,7 @@ * Martin Schwidefsky <schwidefsky@de.ibm.com> */ +#include <linux/moduleloader.h> #include <linux/hardirq.h> #include <linux/uaccess.h> #include <linux/ftrace.h> @@ -15,60 +16,39 @@ #include <linux/kprobes.h> #include <trace/syscall.h> #include <asm/asm-offsets.h> +#include <asm/cacheflush.h> #include "entry.h" -void mcount_replace_code(void); -void ftrace_disable_code(void); -void ftrace_enable_insn(void); - /* * The mcount code looks like this: * stg %r14,8(%r15) # offset 0 * larl %r1,<&counter> # offset 6 * brasl %r14,_mcount # offset 12 * lg %r14,8(%r15) # offset 18 - * Total length is 24 bytes. The complete mcount block initially gets replaced - * by ftrace_make_nop. Subsequent calls to ftrace_make_call / ftrace_make_nop - * only patch the jg/lg instruction within the block. - * Note: we do not patch the first instruction to an unconditional branch, - * since that would break kprobes/jprobes. It is easier to leave the larl - * instruction in and only modify the second instruction. + * Total length is 24 bytes. Only the first instruction will be patched + * by ftrace_make_call / ftrace_make_nop. * The enabled ftrace code block looks like this: - * larl %r0,.+24 # offset 0 - * > lg %r1,__LC_FTRACE_FUNC # offset 6 - * br %r1 # offset 12 - * brcl 0,0 # offset 14 - * brc 0,0 # offset 20 + * > brasl %r0,ftrace_caller # offset 0 + * larl %r1,<&counter> # offset 6 + * brasl %r14,_mcount # offset 12 + * lg %r14,8(%r15) # offset 18 * The ftrace function gets called with a non-standard C function call ABI * where r0 contains the return address. It is also expected that the called * function only clobbers r0 and r1, but restores r2-r15. + * For module code we can't directly jump to ftrace caller, but need a + * trampoline (ftrace_plt), which clobbers also r1. * The return point of the ftrace function has offset 24, so execution * continues behind the mcount block. - * larl %r0,.+24 # offset 0 - * > jg .+18 # offset 6 - * br %r1 # offset 12 - * brcl 0,0 # offset 14 - * brc 0,0 # offset 20 + * The disabled ftrace code block looks like this: + * > jg .+24 # offset 0 + * larl %r1,<&counter> # offset 6 + * brasl %r14,_mcount # offset 12 + * lg %r14,8(%r15) # offset 18 * The jg instruction branches to offset 24 to skip as many instructions * as possible. */ -asm( - " .align 4\n" - "mcount_replace_code:\n" - " larl %r0,0f\n" - "ftrace_disable_code:\n" - " jg 0f\n" - " br %r1\n" - " brcl 0,0\n" - " brc 0,0\n" - "0:\n" - " .align 4\n" - "ftrace_enable_insn:\n" - " lg %r1,"__stringify(__LC_FTRACE_FUNC)"\n"); - -#define MCOUNT_BLOCK_SIZE 24 -#define MCOUNT_INSN_OFFSET 6 -#define FTRACE_INSN_SIZE 6 + +unsigned long ftrace_plt; int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) @@ -79,24 +59,62 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - /* Initial replacement of the whole mcount block */ - if (addr == MCOUNT_ADDR) { - if (probe_kernel_write((void *) rec->ip - MCOUNT_INSN_OFFSET, - mcount_replace_code, - MCOUNT_BLOCK_SIZE)) - return -EPERM; - return 0; + struct ftrace_insn insn; + unsigned short op; + void *from, *to; + size_t size; + + ftrace_generate_nop_insn(&insn); + size = sizeof(insn); + from = &insn; + to = (void *) rec->ip; + if (probe_kernel_read(&op, (void *) rec->ip, sizeof(op))) + return -EFAULT; + /* + * If we find a breakpoint instruction, a kprobe has been placed + * at the beginning of the function. We write the constant + * KPROBE_ON_FTRACE_NOP into the remaining four bytes of the original + * instruction so that the kprobes handler can execute a nop, if it + * reaches this breakpoint. + */ + if (op == BREAKPOINT_INSTRUCTION) { + size -= 2; + from += 2; + to += 2; + insn.disp = KPROBE_ON_FTRACE_NOP; } - if (probe_kernel_write((void *) rec->ip, ftrace_disable_code, - MCOUNT_INSN_SIZE)) + if (probe_kernel_write(to, from, size)) return -EPERM; return 0; } int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - if (probe_kernel_write((void *) rec->ip, ftrace_enable_insn, - FTRACE_INSN_SIZE)) + struct ftrace_insn insn; + unsigned short op; + void *from, *to; + size_t size; + + ftrace_generate_call_insn(&insn, rec->ip); + size = sizeof(insn); + from = &insn; + to = (void *) rec->ip; + if (probe_kernel_read(&op, (void *) rec->ip, sizeof(op))) + return -EFAULT; + /* + * If we find a breakpoint instruction, a kprobe has been placed + * at the beginning of the function. We write the constant + * KPROBE_ON_FTRACE_CALL into the remaining four bytes of the original + * instruction so that the kprobes handler can execute a brasl if it + * reaches this breakpoint. + */ + if (op == BREAKPOINT_INSTRUCTION) { + size -= 2; + from += 2; + to += 2; + insn.disp = KPROBE_ON_FTRACE_CALL; + } + if (probe_kernel_write(to, from, size)) return -EPERM; return 0; } @@ -111,13 +129,30 @@ int __init ftrace_dyn_arch_init(void) return 0; } +static int __init ftrace_plt_init(void) +{ + unsigned int *ip; + + ftrace_plt = (unsigned long) module_alloc(PAGE_SIZE); + if (!ftrace_plt) + panic("cannot allocate ftrace plt\n"); + ip = (unsigned int *) ftrace_plt; + ip[0] = 0x0d10e310; /* basr 1,0; lg 1,10(1); br 1 */ + ip[1] = 0x100a0004; + ip[2] = 0x07f10000; + ip[3] = FTRACE_ADDR >> 32; + ip[4] = FTRACE_ADDR & 0xffffffff; + set_memory_ro(ftrace_plt, 1); + return 0; +} +device_initcall(ftrace_plt_init); + #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* * Hook the return address and push it in the stack of return addresses * in current thread info. */ -unsigned long __kprobes prepare_ftrace_return(unsigned long parent, - unsigned long ip) +unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip) { struct ftrace_graph_ent trace; @@ -137,6 +172,7 @@ unsigned long __kprobes prepare_ftrace_return(unsigned long parent, out: return parent; } +NOKPROBE_SYMBOL(prepare_ftrace_return); /* * Patch the kernel code at ftrace_graph_caller location. The instruction diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index 7559f1beab29..7a55c29b0b33 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -19,7 +19,7 @@ static DEFINE_PER_CPU(struct s390_idle_data, s390_idle); -void __kprobes enabled_wait(void) +void enabled_wait(void) { struct s390_idle_data *idle = this_cpu_ptr(&s390_idle); unsigned long long idle_time; @@ -35,31 +35,32 @@ void __kprobes enabled_wait(void) /* Call the assembler magic in entry.S */ psw_idle(idle, psw_mask); + trace_hardirqs_off(); + /* Account time spent with enabled wait psw loaded as idle time. */ - idle->sequence++; - smp_wmb(); + write_seqcount_begin(&idle->seqcount); idle_time = idle->clock_idle_exit - idle->clock_idle_enter; idle->clock_idle_enter = idle->clock_idle_exit = 0ULL; idle->idle_time += idle_time; idle->idle_count++; account_idle_time(idle_time); - smp_wmb(); - idle->sequence++; + write_seqcount_end(&idle->seqcount); } +NOKPROBE_SYMBOL(enabled_wait); static ssize_t show_idle_count(struct device *dev, struct device_attribute *attr, char *buf) { struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id); unsigned long long idle_count; - unsigned int sequence; + unsigned int seq; do { - sequence = ACCESS_ONCE(idle->sequence); + seq = read_seqcount_begin(&idle->seqcount); idle_count = ACCESS_ONCE(idle->idle_count); if (ACCESS_ONCE(idle->clock_idle_enter)) idle_count++; - } while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence)); + } while (read_seqcount_retry(&idle->seqcount, seq)); return sprintf(buf, "%llu\n", idle_count); } DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL); @@ -69,15 +70,15 @@ static ssize_t show_idle_time(struct device *dev, { struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id); unsigned long long now, idle_time, idle_enter, idle_exit; - unsigned int sequence; + unsigned int seq; do { now = get_tod_clock(); - sequence = ACCESS_ONCE(idle->sequence); + seq = read_seqcount_begin(&idle->seqcount); idle_time = ACCESS_ONCE(idle->idle_time); idle_enter = ACCESS_ONCE(idle->clock_idle_enter); idle_exit = ACCESS_ONCE(idle->clock_idle_exit); - } while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence)); + } while (read_seqcount_retry(&idle->seqcount, seq)); idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0; return sprintf(buf, "%llu\n", idle_time >> 12); } @@ -87,14 +88,14 @@ cputime64_t arch_cpu_idle_time(int cpu) { struct s390_idle_data *idle = &per_cpu(s390_idle, cpu); unsigned long long now, idle_enter, idle_exit; - unsigned int sequence; + unsigned int seq; do { now = get_tod_clock(); - sequence = ACCESS_ONCE(idle->sequence); + seq = read_seqcount_begin(&idle->seqcount); idle_enter = ACCESS_ONCE(idle->clock_idle_enter); idle_exit = ACCESS_ONCE(idle->clock_idle_exit); - } while ((sequence & 1) || (ACCESS_ONCE(idle->sequence) != sequence)); + } while (read_seqcount_retry(&idle->seqcount, seq)); return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0; } diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index 1b8a38ab7861..f238720690f3 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -127,13 +127,10 @@ int show_interrupts(struct seq_file *p, void *v) for_each_online_cpu(cpu) seq_printf(p, "CPU%d ", cpu); seq_putc(p, '\n'); - goto out; } if (index < NR_IRQS) { if (index >= NR_IRQS_BASE) goto out; - /* Adjust index to process irqclass_main_desc array entries */ - index--; seq_printf(p, "%s: ", irqclass_main_desc[index].name); irq = irqclass_main_desc[index].irq; for_each_online_cpu(cpu) @@ -158,7 +155,7 @@ out: unsigned int arch_dynirq_lower_bound(unsigned int from) { - return from < THIN_INTERRUPT ? THIN_INTERRUPT : from; + return from < NR_IRQS_BASE ? NR_IRQS_BASE : from; } /* diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 014d4729b134..1e4c710dfb92 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -29,6 +29,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/hardirq.h> +#include <linux/ftrace.h> #include <asm/cacheflush.h> #include <asm/sections.h> #include <asm/dis.h> @@ -58,12 +59,23 @@ struct kprobe_insn_cache kprobe_dmainsn_slots = { .insn_size = MAX_INSN_SIZE, }; -static void __kprobes copy_instruction(struct kprobe *p) +static void copy_instruction(struct kprobe *p) { + unsigned long ip = (unsigned long) p->addr; s64 disp, new_disp; u64 addr, new_addr; - memcpy(p->ainsn.insn, p->addr, insn_length(p->opcode >> 8)); + if (ftrace_location(ip) == ip) { + /* + * If kprobes patches the instruction that is morphed by + * ftrace make sure that kprobes always sees the branch + * "jg .+24" that skips the mcount block + */ + ftrace_generate_nop_insn((struct ftrace_insn *)p->ainsn.insn); + p->ainsn.is_ftrace_insn = 1; + } else + memcpy(p->ainsn.insn, p->addr, insn_length(*p->addr >> 8)); + p->opcode = p->ainsn.insn[0]; if (!probe_is_insn_relative_long(p->ainsn.insn)) return; /* @@ -79,25 +91,14 @@ static void __kprobes copy_instruction(struct kprobe *p) new_disp = ((addr + (disp * 2)) - new_addr) / 2; *(s32 *)&p->ainsn.insn[1] = new_disp; } +NOKPROBE_SYMBOL(copy_instruction); static inline int is_kernel_addr(void *addr) { return addr < (void *)_end; } -static inline int is_module_addr(void *addr) -{ -#ifdef CONFIG_64BIT - BUILD_BUG_ON(MODULES_LEN > (1UL << 31)); - if (addr < (void *)MODULES_VADDR) - return 0; - if (addr > (void *)MODULES_END) - return 0; -#endif - return 1; -} - -static int __kprobes s390_get_insn_slot(struct kprobe *p) +static int s390_get_insn_slot(struct kprobe *p) { /* * Get an insn slot that is within the same 2GB area like the original @@ -111,8 +112,9 @@ static int __kprobes s390_get_insn_slot(struct kprobe *p) p->ainsn.insn = get_insn_slot(); return p->ainsn.insn ? 0 : -ENOMEM; } +NOKPROBE_SYMBOL(s390_get_insn_slot); -static void __kprobes s390_free_insn_slot(struct kprobe *p) +static void s390_free_insn_slot(struct kprobe *p) { if (!p->ainsn.insn) return; @@ -122,8 +124,9 @@ static void __kprobes s390_free_insn_slot(struct kprobe *p) free_insn_slot(p->ainsn.insn, 0); p->ainsn.insn = NULL; } +NOKPROBE_SYMBOL(s390_free_insn_slot); -int __kprobes arch_prepare_kprobe(struct kprobe *p) +int arch_prepare_kprobe(struct kprobe *p) { if ((unsigned long) p->addr & 0x01) return -EINVAL; @@ -132,54 +135,79 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) return -EINVAL; if (s390_get_insn_slot(p)) return -ENOMEM; - p->opcode = *p->addr; copy_instruction(p); return 0; } +NOKPROBE_SYMBOL(arch_prepare_kprobe); -struct ins_replace_args { - kprobe_opcode_t *ptr; - kprobe_opcode_t opcode; +int arch_check_ftrace_location(struct kprobe *p) +{ + return 0; +} + +struct swap_insn_args { + struct kprobe *p; + unsigned int arm_kprobe : 1; }; -static int __kprobes swap_instruction(void *aref) +static int swap_instruction(void *data) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); unsigned long status = kcb->kprobe_status; - struct ins_replace_args *args = aref; - + struct swap_insn_args *args = data; + struct ftrace_insn new_insn, *insn; + struct kprobe *p = args->p; + size_t len; + + new_insn.opc = args->arm_kprobe ? BREAKPOINT_INSTRUCTION : p->opcode; + len = sizeof(new_insn.opc); + if (!p->ainsn.is_ftrace_insn) + goto skip_ftrace; + len = sizeof(new_insn); + insn = (struct ftrace_insn *) p->addr; + if (args->arm_kprobe) { + if (is_ftrace_nop(insn)) + new_insn.disp = KPROBE_ON_FTRACE_NOP; + else + new_insn.disp = KPROBE_ON_FTRACE_CALL; + } else { + ftrace_generate_call_insn(&new_insn, (unsigned long)p->addr); + if (insn->disp == KPROBE_ON_FTRACE_NOP) + ftrace_generate_nop_insn(&new_insn); + } +skip_ftrace: kcb->kprobe_status = KPROBE_SWAP_INST; - probe_kernel_write(args->ptr, &args->opcode, sizeof(args->opcode)); + probe_kernel_write(p->addr, &new_insn, len); kcb->kprobe_status = status; return 0; } +NOKPROBE_SYMBOL(swap_instruction); -void __kprobes arch_arm_kprobe(struct kprobe *p) +void arch_arm_kprobe(struct kprobe *p) { - struct ins_replace_args args; + struct swap_insn_args args = {.p = p, .arm_kprobe = 1}; - args.ptr = p->addr; - args.opcode = BREAKPOINT_INSTRUCTION; stop_machine(swap_instruction, &args, NULL); } +NOKPROBE_SYMBOL(arch_arm_kprobe); -void __kprobes arch_disarm_kprobe(struct kprobe *p) +void arch_disarm_kprobe(struct kprobe *p) { - struct ins_replace_args args; + struct swap_insn_args args = {.p = p, .arm_kprobe = 0}; - args.ptr = p->addr; - args.opcode = p->opcode; stop_machine(swap_instruction, &args, NULL); } +NOKPROBE_SYMBOL(arch_disarm_kprobe); -void __kprobes arch_remove_kprobe(struct kprobe *p) +void arch_remove_kprobe(struct kprobe *p) { s390_free_insn_slot(p); } +NOKPROBE_SYMBOL(arch_remove_kprobe); -static void __kprobes enable_singlestep(struct kprobe_ctlblk *kcb, - struct pt_regs *regs, - unsigned long ip) +static void enable_singlestep(struct kprobe_ctlblk *kcb, + struct pt_regs *regs, + unsigned long ip) { struct per_regs per_kprobe; @@ -199,10 +227,11 @@ static void __kprobes enable_singlestep(struct kprobe_ctlblk *kcb, regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT); regs->psw.addr = ip | PSW_ADDR_AMODE; } +NOKPROBE_SYMBOL(enable_singlestep); -static void __kprobes disable_singlestep(struct kprobe_ctlblk *kcb, - struct pt_regs *regs, - unsigned long ip) +static void disable_singlestep(struct kprobe_ctlblk *kcb, + struct pt_regs *regs, + unsigned long ip) { /* Restore control regs and psw mask, set new psw address */ __ctl_load(kcb->kprobe_saved_ctl, 9, 11); @@ -210,41 +239,43 @@ static void __kprobes disable_singlestep(struct kprobe_ctlblk *kcb, regs->psw.mask |= kcb->kprobe_saved_imask; regs->psw.addr = ip | PSW_ADDR_AMODE; } +NOKPROBE_SYMBOL(disable_singlestep); /* * Activate a kprobe by storing its pointer to current_kprobe. The * previous kprobe is stored in kcb->prev_kprobe. A stack of up to * two kprobes can be active, see KPROBE_REENTER. */ -static void __kprobes push_kprobe(struct kprobe_ctlblk *kcb, struct kprobe *p) +static void push_kprobe(struct kprobe_ctlblk *kcb, struct kprobe *p) { kcb->prev_kprobe.kp = __this_cpu_read(current_kprobe); kcb->prev_kprobe.status = kcb->kprobe_status; __this_cpu_write(current_kprobe, p); } +NOKPROBE_SYMBOL(push_kprobe); /* * Deactivate a kprobe by backing up to the previous state. If the * current state is KPROBE_REENTER prev_kprobe.kp will be non-NULL, * for any other state prev_kprobe.kp will be NULL. */ -static void __kprobes pop_kprobe(struct kprobe_ctlblk *kcb) +static void pop_kprobe(struct kprobe_ctlblk *kcb) { __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); kcb->kprobe_status = kcb->prev_kprobe.status; } +NOKPROBE_SYMBOL(pop_kprobe); -void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, - struct pt_regs *regs) +void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) { ri->ret_addr = (kprobe_opcode_t *) regs->gprs[14]; /* Replace the return addr with trampoline addr */ regs->gprs[14] = (unsigned long) &kretprobe_trampoline; } +NOKPROBE_SYMBOL(arch_prepare_kretprobe); -static void __kprobes kprobe_reenter_check(struct kprobe_ctlblk *kcb, - struct kprobe *p) +static void kprobe_reenter_check(struct kprobe_ctlblk *kcb, struct kprobe *p) { switch (kcb->kprobe_status) { case KPROBE_HIT_SSDONE: @@ -264,8 +295,9 @@ static void __kprobes kprobe_reenter_check(struct kprobe_ctlblk *kcb, BUG(); } } +NOKPROBE_SYMBOL(kprobe_reenter_check); -static int __kprobes kprobe_handler(struct pt_regs *regs) +static int kprobe_handler(struct pt_regs *regs) { struct kprobe_ctlblk *kcb; struct kprobe *p; @@ -339,6 +371,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) preempt_enable_no_resched(); return 0; } +NOKPROBE_SYMBOL(kprobe_handler); /* * Function return probe trampoline: @@ -355,8 +388,7 @@ static void __used kretprobe_trampoline_holder(void) /* * Called when the probe at kretprobe trampoline is hit */ -static int __kprobes trampoline_probe_handler(struct kprobe *p, - struct pt_regs *regs) +static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { struct kretprobe_instance *ri; struct hlist_head *head, empty_rp; @@ -444,6 +476,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, */ return 1; } +NOKPROBE_SYMBOL(trampoline_probe_handler); /* * Called after single-stepping. p->addr is the address of the @@ -453,12 +486,30 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, * single-stepped a copy of the instruction. The address of this * copy is p->ainsn.insn. */ -static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs) +static void resume_execution(struct kprobe *p, struct pt_regs *regs) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); unsigned long ip = regs->psw.addr & PSW_ADDR_INSN; int fixup = probe_get_fixup_type(p->ainsn.insn); + /* Check if the kprobes location is an enabled ftrace caller */ + if (p->ainsn.is_ftrace_insn) { + struct ftrace_insn *insn = (struct ftrace_insn *) p->addr; + struct ftrace_insn call_insn; + + ftrace_generate_call_insn(&call_insn, (unsigned long) p->addr); + /* + * A kprobe on an enabled ftrace call site actually single + * stepped an unconditional branch (ftrace nop equivalent). + * Now we need to fixup things and pretend that a brasl r0,... + * was executed instead. + */ + if (insn->disp == KPROBE_ON_FTRACE_CALL) { + ip += call_insn.disp * 2 - MCOUNT_INSN_SIZE; + regs->gprs[0] = (unsigned long)p->addr + sizeof(*insn); + } + } + if (fixup & FIXUP_PSW_NORMAL) ip += (unsigned long) p->addr - (unsigned long) p->ainsn.insn; @@ -476,8 +527,9 @@ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs) disable_singlestep(kcb, regs, ip); } +NOKPROBE_SYMBOL(resume_execution); -static int __kprobes post_kprobe_handler(struct pt_regs *regs) +static int post_kprobe_handler(struct pt_regs *regs) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); struct kprobe *p = kprobe_running(); @@ -504,8 +556,9 @@ static int __kprobes post_kprobe_handler(struct pt_regs *regs) return 1; } +NOKPROBE_SYMBOL(post_kprobe_handler); -static int __kprobes kprobe_trap_handler(struct pt_regs *regs, int trapnr) +static int kprobe_trap_handler(struct pt_regs *regs, int trapnr) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); struct kprobe *p = kprobe_running(); @@ -567,8 +620,9 @@ static int __kprobes kprobe_trap_handler(struct pt_regs *regs, int trapnr) } return 0; } +NOKPROBE_SYMBOL(kprobe_trap_handler); -int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) +int kprobe_fault_handler(struct pt_regs *regs, int trapnr) { int ret; @@ -579,12 +633,13 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) local_irq_restore(regs->psw.mask & ~PSW_MASK_PER); return ret; } +NOKPROBE_SYMBOL(kprobe_fault_handler); /* * Wrapper routine to for handling exceptions. */ -int __kprobes kprobe_exceptions_notify(struct notifier_block *self, - unsigned long val, void *data) +int kprobe_exceptions_notify(struct notifier_block *self, + unsigned long val, void *data) { struct die_args *args = (struct die_args *) data; struct pt_regs *regs = args->regs; @@ -616,8 +671,9 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, return ret; } +NOKPROBE_SYMBOL(kprobe_exceptions_notify); -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) +int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct jprobe *jp = container_of(p, struct jprobe, kp); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); @@ -635,13 +691,15 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) memcpy(kcb->jprobes_stack, (void *) stack, MIN_STACK_SIZE(stack)); return 1; } +NOKPROBE_SYMBOL(setjmp_pre_handler); -void __kprobes jprobe_return(void) +void jprobe_return(void) { asm volatile(".word 0x0002"); } +NOKPROBE_SYMBOL(jprobe_return); -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) +int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); unsigned long stack; @@ -655,6 +713,7 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) preempt_enable_no_resched(); return 1; } +NOKPROBE_SYMBOL(longjmp_break_handler); static struct kprobe trampoline = { .addr = (kprobe_opcode_t *) &kretprobe_trampoline, @@ -666,7 +725,8 @@ int __init arch_init_kprobes(void) return register_kprobe(&trampoline); } -int __kprobes arch_trampoline_kprobe(struct kprobe *p) +int arch_trampoline_kprobe(struct kprobe *p) { return p->addr == (kprobe_opcode_t *) &kretprobe_trampoline; } +NOKPROBE_SYMBOL(arch_trampoline_kprobe); diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 4300ea374826..b6dfc5bfcb89 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -27,6 +27,7 @@ ENTRY(ftrace_caller) .globl ftrace_regs_caller .set ftrace_regs_caller,ftrace_caller lgr %r1,%r15 + aghi %r0,MCOUNT_RETURN_FIXUP aghi %r15,-STACK_FRAME_SIZE stg %r1,__SF_BACKCHAIN(%r15) stg %r1,(STACK_PTREGS_GPRS+15*8)(%r15) diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index dd1c24ceda50..3f51cf4e8f02 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -54,12 +54,8 @@ void s390_handle_mcck(void) */ local_irq_save(flags); local_mcck_disable(); - /* - * Ummm... Does this make sense at all? Copying the percpu struct - * and then zapping it one statement later? - */ - memcpy(&mcck, this_cpu_ptr(&cpu_mcck), sizeof(mcck)); - memset(&mcck, 0, sizeof(struct mcck_struct)); + mcck = *this_cpu_ptr(&cpu_mcck); + memset(this_cpu_ptr(&cpu_mcck), 0, sizeof(mcck)); clear_cpu_flag(CIF_MCCK_PENDING); local_mcck_enable(); local_irq_restore(flags); diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index b878f12a9597..c3f8d157cb0d 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1383,7 +1383,6 @@ static int cpumsf_pmu_add(struct perf_event *event, int flags) cpuhw->lsctl.ed = 1; /* Set in_use flag and store event */ - event->hw.idx = 0; /* only one sampling event per CPU supported */ cpuhw->event = event; cpuhw->flags |= PMU_F_IN_USE; diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index ed84cc224899..aa7a83948c7b 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -61,7 +61,7 @@ unsigned long thread_saved_pc(struct task_struct *tsk) return sf->gprs[8]; } -extern void __kprobes kernel_thread_starter(void); +extern void kernel_thread_starter(void); /* * Free current thread data structures etc.. @@ -153,6 +153,7 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp, save_fp_ctl(&p->thread.fp_regs.fpc); save_fp_regs(p->thread.fp_regs.fprs); p->thread.fp_regs.pad = 0; + p->thread.vxrs = NULL; /* Set a new TLS ? */ if (clone_flags & CLONE_SETTLS) { unsigned long tls = frame->childregs.gprs[6]; diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 99a567b70d16..eabfb4594517 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -248,14 +248,27 @@ static unsigned long __peek_user(struct task_struct *child, addr_t addr) */ tmp = 0; + } else if (addr == (addr_t) &dummy->regs.fp_regs.fpc) { + /* + * floating point control reg. is in the thread structure + */ + tmp = child->thread.fp_regs.fpc; + tmp <<= BITS_PER_LONG - 32; + } else if (addr < (addr_t) (&dummy->regs.fp_regs + 1)) { - /* - * floating point regs. are stored in the thread structure + /* + * floating point regs. are either in child->thread.fp_regs + * or the child->thread.vxrs array */ - offset = addr - (addr_t) &dummy->regs.fp_regs; - tmp = *(addr_t *)((addr_t) &child->thread.fp_regs + offset); - if (addr == (addr_t) &dummy->regs.fp_regs.fpc) - tmp <<= BITS_PER_LONG - 32; + offset = addr - (addr_t) &dummy->regs.fp_regs.fprs; +#ifdef CONFIG_64BIT + if (child->thread.vxrs) + tmp = *(addr_t *) + ((addr_t) child->thread.vxrs + 2*offset); + else +#endif + tmp = *(addr_t *) + ((addr_t) &child->thread.fp_regs.fprs + offset); } else if (addr < (addr_t) (&dummy->regs.per_info + 1)) { /* @@ -383,16 +396,29 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) */ return 0; + } else if (addr == (addr_t) &dummy->regs.fp_regs.fpc) { + /* + * floating point control reg. is in the thread structure + */ + if ((unsigned int) data != 0 || + test_fp_ctl(data >> (BITS_PER_LONG - 32))) + return -EINVAL; + child->thread.fp_regs.fpc = data >> (BITS_PER_LONG - 32); + } else if (addr < (addr_t) (&dummy->regs.fp_regs + 1)) { /* - * floating point regs. are stored in the thread structure + * floating point regs. are either in child->thread.fp_regs + * or the child->thread.vxrs array */ - if (addr == (addr_t) &dummy->regs.fp_regs.fpc) - if ((unsigned int) data != 0 || - test_fp_ctl(data >> (BITS_PER_LONG - 32))) - return -EINVAL; - offset = addr - (addr_t) &dummy->regs.fp_regs; - *(addr_t *)((addr_t) &child->thread.fp_regs + offset) = data; + offset = addr - (addr_t) &dummy->regs.fp_regs.fprs; +#ifdef CONFIG_64BIT + if (child->thread.vxrs) + *(addr_t *)((addr_t) + child->thread.vxrs + 2*offset) = data; + else +#endif + *(addr_t *)((addr_t) + &child->thread.fp_regs.fprs + offset) = data; } else if (addr < (addr_t) (&dummy->regs.per_info + 1)) { /* @@ -611,12 +637,26 @@ static u32 __peek_user_compat(struct task_struct *child, addr_t addr) */ tmp = 0; + } else if (addr == (addr_t) &dummy32->regs.fp_regs.fpc) { + /* + * floating point control reg. is in the thread structure + */ + tmp = child->thread.fp_regs.fpc; + } else if (addr < (addr_t) (&dummy32->regs.fp_regs + 1)) { /* - * floating point regs. are stored in the thread structure + * floating point regs. are either in child->thread.fp_regs + * or the child->thread.vxrs array */ - offset = addr - (addr_t) &dummy32->regs.fp_regs; - tmp = *(__u32 *)((addr_t) &child->thread.fp_regs + offset); + offset = addr - (addr_t) &dummy32->regs.fp_regs.fprs; +#ifdef CONFIG_64BIT + if (child->thread.vxrs) + tmp = *(__u32 *) + ((addr_t) child->thread.vxrs + 2*offset); + else +#endif + tmp = *(__u32 *) + ((addr_t) &child->thread.fp_regs.fprs + offset); } else if (addr < (addr_t) (&dummy32->regs.per_info + 1)) { /* @@ -722,15 +762,28 @@ static int __poke_user_compat(struct task_struct *child, */ return 0; - } else if (addr < (addr_t) (&dummy32->regs.fp_regs + 1)) { + } else if (addr == (addr_t) &dummy32->regs.fp_regs.fpc) { /* - * floating point regs. are stored in the thread structure + * floating point control reg. is in the thread structure */ - if (addr == (addr_t) &dummy32->regs.fp_regs.fpc && - test_fp_ctl(tmp)) + if (test_fp_ctl(tmp)) return -EINVAL; - offset = addr - (addr_t) &dummy32->regs.fp_regs; - *(__u32 *)((addr_t) &child->thread.fp_regs + offset) = tmp; + child->thread.fp_regs.fpc = data; + + } else if (addr < (addr_t) (&dummy32->regs.fp_regs + 1)) { + /* + * floating point regs. are either in child->thread.fp_regs + * or the child->thread.vxrs array + */ + offset = addr - (addr_t) &dummy32->regs.fp_regs.fprs; +#ifdef CONFIG_64BIT + if (child->thread.vxrs) + *(__u32 *)((addr_t) + child->thread.vxrs + 2*offset) = tmp; + else +#endif + *(__u32 *)((addr_t) + &child->thread.fp_regs.fprs + offset) = tmp; } else if (addr < (addr_t) (&dummy32->regs.per_info + 1)) { /* @@ -1038,12 +1091,6 @@ static int s390_tdb_set(struct task_struct *target, return 0; } -static int s390_vxrs_active(struct task_struct *target, - const struct user_regset *regset) -{ - return !!target->thread.vxrs; -} - static int s390_vxrs_low_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, @@ -1052,6 +1099,8 @@ static int s390_vxrs_low_get(struct task_struct *target, __u64 vxrs[__NUM_VXRS_LOW]; int i; + if (!MACHINE_HAS_VX) + return -ENODEV; if (target->thread.vxrs) { if (target == current) save_vx_regs(target->thread.vxrs); @@ -1070,6 +1119,8 @@ static int s390_vxrs_low_set(struct task_struct *target, __u64 vxrs[__NUM_VXRS_LOW]; int i, rc; + if (!MACHINE_HAS_VX) + return -ENODEV; if (!target->thread.vxrs) { rc = alloc_vector_registers(target); if (rc) @@ -1095,6 +1146,8 @@ static int s390_vxrs_high_get(struct task_struct *target, { __vector128 vxrs[__NUM_VXRS_HIGH]; + if (!MACHINE_HAS_VX) + return -ENODEV; if (target->thread.vxrs) { if (target == current) save_vx_regs(target->thread.vxrs); @@ -1112,6 +1165,8 @@ static int s390_vxrs_high_set(struct task_struct *target, { int rc; + if (!MACHINE_HAS_VX) + return -ENODEV; if (!target->thread.vxrs) { rc = alloc_vector_registers(target); if (rc) @@ -1196,7 +1251,6 @@ static const struct user_regset s390_regsets[] = { .n = __NUM_VXRS_LOW, .size = sizeof(__u64), .align = sizeof(__u64), - .active = s390_vxrs_active, .get = s390_vxrs_low_get, .set = s390_vxrs_low_set, }, @@ -1205,7 +1259,6 @@ static const struct user_regset s390_regsets[] = { .n = __NUM_VXRS_HIGH, .size = sizeof(__vector128), .align = sizeof(__vector128), - .active = s390_vxrs_active, .get = s390_vxrs_high_get, .set = s390_vxrs_high_set, }, @@ -1419,7 +1472,6 @@ static const struct user_regset s390_compat_regsets[] = { .n = __NUM_VXRS_LOW, .size = sizeof(__u64), .align = sizeof(__u64), - .active = s390_vxrs_active, .get = s390_vxrs_low_get, .set = s390_vxrs_low_set, }, @@ -1428,7 +1480,6 @@ static const struct user_regset s390_compat_regsets[] = { .n = __NUM_VXRS_HIGH, .size = sizeof(__vector128), .align = sizeof(__vector128), - .active = s390_vxrs_active, .get = s390_vxrs_high_get, .set = s390_vxrs_high_set, }, diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index e80d9ff9a56d..4e532c67832f 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -41,7 +41,6 @@ #include <linux/ctype.h> #include <linux/reboot.h> #include <linux/topology.h> -#include <linux/ftrace.h> #include <linux/kexec.h> #include <linux/crash_dump.h> #include <linux/memory.h> @@ -356,7 +355,6 @@ static void __init setup_lowcore(void) lc->steal_timer = S390_lowcore.steal_timer; lc->last_update_timer = S390_lowcore.last_update_timer; lc->last_update_clock = S390_lowcore.last_update_clock; - lc->ftrace_func = S390_lowcore.ftrace_func; restart_stack = __alloc_bootmem(ASYNC_SIZE, ASYNC_SIZE, 0); restart_stack += ASYNC_SIZE; diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index 0c1a0ff0a558..6a2ac257d98f 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -371,7 +371,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, restorer = (unsigned long) ka->sa.sa_restorer | PSW_ADDR_AMODE; } else { /* Signal frame without vector registers are short ! */ - __u16 __user *svc = (void *) frame + frame_size - 2; + __u16 __user *svc = (void __user *) frame + frame_size - 2; if (__put_user(S390_SYSCALL_OPCODE | __NR_sigreturn, svc)) return -EFAULT; restorer = (unsigned long) svc | PSW_ADDR_AMODE; diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 6fd9e60101f1..0b499f5cbe19 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -236,7 +236,6 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu) lc->percpu_offset = __per_cpu_offset[cpu]; lc->kernel_asce = S390_lowcore.kernel_asce; lc->machine_flags = S390_lowcore.machine_flags; - lc->ftrace_func = S390_lowcore.ftrace_func; lc->user_timer = lc->system_timer = lc->steal_timer = 0; __ctl_store(lc->cregs_save_area, 0, 15); save_access_regs((unsigned int *) lc->access_regs_save_area); diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S index 9f7087fd58de..a2987243bc76 100644 --- a/arch/s390/kernel/syscalls.S +++ b/arch/s390/kernel/syscalls.S @@ -360,3 +360,5 @@ SYSCALL(sys_seccomp,sys_seccomp,compat_sys_seccomp) SYSCALL(sys_getrandom,sys_getrandom,compat_sys_getrandom) SYSCALL(sys_memfd_create,sys_memfd_create,compat_sys_memfd_create) /* 350 */ SYSCALL(sys_bpf,sys_bpf,compat_sys_bpf) +SYSCALL(sys_ni_syscall,sys_s390_pci_mmio_write,compat_sys_s390_pci_mmio_write) +SYSCALL(sys_ni_syscall,sys_s390_pci_mmio_read,compat_sys_s390_pci_mmio_read) diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 005d665fe4a5..20660dddb2d6 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -61,10 +61,11 @@ static DEFINE_PER_CPU(struct clock_event_device, comparators); /* * Scheduler clock - returns current time in nanosec units. */ -unsigned long long notrace __kprobes sched_clock(void) +unsigned long long notrace sched_clock(void) { return tod_to_ns(get_tod_clock_monotonic()); } +NOKPROBE_SYMBOL(sched_clock); /* * Monotonic_clock - returns # of nanoseconds passed since time_init() diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index 9ff5ecba26ab..f081cf1157c3 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -49,7 +49,8 @@ static inline void report_user_fault(struct pt_regs *regs, int signr) return; if (!printk_ratelimit()) return; - printk("User process fault: interruption code 0x%X ", regs->int_code); + printk("User process fault: interruption code %04x ilc:%d ", + regs->int_code & 0xffff, regs->int_code >> 17); print_vma_addr("in ", regs->psw.addr & PSW_ADDR_INSN); printk("\n"); show_regs(regs); @@ -87,16 +88,16 @@ void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str) } } -static void __kprobes do_trap(struct pt_regs *regs, int si_signo, int si_code, - char *str) +static void do_trap(struct pt_regs *regs, int si_signo, int si_code, char *str) { if (notify_die(DIE_TRAP, str, regs, 0, regs->int_code, si_signo) == NOTIFY_STOP) return; do_report_trap(regs, si_signo, si_code, str); } +NOKPROBE_SYMBOL(do_trap); -void __kprobes do_per_trap(struct pt_regs *regs) +void do_per_trap(struct pt_regs *regs) { siginfo_t info; @@ -111,6 +112,7 @@ void __kprobes do_per_trap(struct pt_regs *regs) (void __force __user *) current->thread.per_event.address; force_sig_info(SIGTRAP, &info, current); } +NOKPROBE_SYMBOL(do_per_trap); void default_trap_handler(struct pt_regs *regs) { @@ -151,8 +153,6 @@ DO_ERROR_INFO(privileged_op, SIGILL, ILL_PRVOPC, "privileged operation") DO_ERROR_INFO(special_op_exception, SIGILL, ILL_ILLOPN, "special operation exception") -DO_ERROR_INFO(translation_exception, SIGILL, ILL_ILLOPN, - "translation exception") #ifdef CONFIG_64BIT DO_ERROR_INFO(transaction_exception, SIGILL, ILL_ILLOPN, @@ -179,7 +179,13 @@ static inline void do_fp_trap(struct pt_regs *regs, int fpc) do_trap(regs, SIGFPE, si_code, "floating point exception"); } -void __kprobes illegal_op(struct pt_regs *regs) +void translation_exception(struct pt_regs *regs) +{ + /* May never happen. */ + die(regs, "Translation exception"); +} + +void illegal_op(struct pt_regs *regs) { siginfo_t info; __u8 opcode[6]; @@ -252,7 +258,7 @@ void __kprobes illegal_op(struct pt_regs *regs) if (signal) do_trap(regs, signal, ILL_ILLOPC, "illegal operation"); } - +NOKPROBE_SYMBOL(illegal_op); #ifdef CONFIG_MATHEMU void specification_exception(struct pt_regs *regs) @@ -469,7 +475,7 @@ void space_switch_exception(struct pt_regs *regs) do_trap(regs, SIGILL, ILL_PRVOPC, "space switch event"); } -void __kprobes kernel_stack_overflow(struct pt_regs * regs) +void kernel_stack_overflow(struct pt_regs *regs) { bust_spinlocks(1); printk("Kernel stack overflow.\n"); @@ -477,6 +483,7 @@ void __kprobes kernel_stack_overflow(struct pt_regs * regs) bust_spinlocks(0); panic("Corrupt kernel stack, can't continue."); } +NOKPROBE_SYMBOL(kernel_stack_overflow); void __init trap_init(void) { diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 0f961a1c64b3..8a1be9017730 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -207,8 +207,6 @@ union raddress { unsigned long pfra : 52; /* Page-Frame Real Address */ }; -static int ipte_lock_count; -static DEFINE_MUTEX(ipte_mutex); int ipte_lock_held(struct kvm_vcpu *vcpu) { @@ -216,47 +214,48 @@ int ipte_lock_held(struct kvm_vcpu *vcpu) if (vcpu->arch.sie_block->eca & 1) return ic->kh != 0; - return ipte_lock_count != 0; + return vcpu->kvm->arch.ipte_lock_count != 0; } static void ipte_lock_simple(struct kvm_vcpu *vcpu) { union ipte_control old, new, *ic; - mutex_lock(&ipte_mutex); - ipte_lock_count++; - if (ipte_lock_count > 1) + mutex_lock(&vcpu->kvm->arch.ipte_mutex); + vcpu->kvm->arch.ipte_lock_count++; + if (vcpu->kvm->arch.ipte_lock_count > 1) goto out; ic = &vcpu->kvm->arch.sca->ipte_control; do { - old = ACCESS_ONCE(*ic); + old = READ_ONCE(*ic); while (old.k) { cond_resched(); - old = ACCESS_ONCE(*ic); + old = READ_ONCE(*ic); } new = old; new.k = 1; } while (cmpxchg(&ic->val, old.val, new.val) != old.val); out: - mutex_unlock(&ipte_mutex); + mutex_unlock(&vcpu->kvm->arch.ipte_mutex); } static void ipte_unlock_simple(struct kvm_vcpu *vcpu) { union ipte_control old, new, *ic; - mutex_lock(&ipte_mutex); - ipte_lock_count--; - if (ipte_lock_count) + mutex_lock(&vcpu->kvm->arch.ipte_mutex); + vcpu->kvm->arch.ipte_lock_count--; + if (vcpu->kvm->arch.ipte_lock_count) goto out; ic = &vcpu->kvm->arch.sca->ipte_control; do { - new = old = ACCESS_ONCE(*ic); + old = READ_ONCE(*ic); + new = old; new.k = 0; } while (cmpxchg(&ic->val, old.val, new.val) != old.val); wake_up(&vcpu->kvm->arch.ipte_wq); out: - mutex_unlock(&ipte_mutex); + mutex_unlock(&vcpu->kvm->arch.ipte_mutex); } static void ipte_lock_siif(struct kvm_vcpu *vcpu) @@ -265,10 +264,10 @@ static void ipte_lock_siif(struct kvm_vcpu *vcpu) ic = &vcpu->kvm->arch.sca->ipte_control; do { - old = ACCESS_ONCE(*ic); + old = READ_ONCE(*ic); while (old.kg) { cond_resched(); - old = ACCESS_ONCE(*ic); + old = READ_ONCE(*ic); } new = old; new.k = 1; @@ -282,7 +281,8 @@ static void ipte_unlock_siif(struct kvm_vcpu *vcpu) ic = &vcpu->kvm->arch.sca->ipte_control; do { - new = old = ACCESS_ONCE(*ic); + old = READ_ONCE(*ic); + new = old; new.kh--; if (!new.kh) new.k = 0; diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index eaf46291d361..81c77ab8102e 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -38,6 +38,19 @@ static const intercept_handler_t instruction_handlers[256] = { [0xeb] = kvm_s390_handle_eb, }; +void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc) +{ + struct kvm_s390_sie_block *sie_block = vcpu->arch.sie_block; + + /* Use the length of the EXECUTE instruction if necessary */ + if (sie_block->icptstatus & 1) { + ilc = (sie_block->icptstatus >> 4) & 0x6; + if (!ilc) + ilc = 4; + } + sie_block->gpsw.addr = __rewind_psw(sie_block->gpsw, ilc); +} + static int handle_noop(struct kvm_vcpu *vcpu) { switch (vcpu->arch.sie_block->icptcode) { @@ -244,7 +257,7 @@ static int handle_instruction_and_prog(struct kvm_vcpu *vcpu) static int handle_external_interrupt(struct kvm_vcpu *vcpu) { u16 eic = vcpu->arch.sie_block->eic; - struct kvm_s390_interrupt irq; + struct kvm_s390_irq irq; psw_t newpsw; int rc; @@ -269,7 +282,7 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu) if (kvm_s390_si_ext_call_pending(vcpu)) return 0; irq.type = KVM_S390_INT_EXTERNAL_CALL; - irq.parm = vcpu->arch.sie_block->extcpuaddr; + irq.u.extcall.code = vcpu->arch.sie_block->extcpuaddr; break; default: return -EOPNOTSUPP; @@ -288,7 +301,6 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu) */ static int handle_mvpg_pei(struct kvm_vcpu *vcpu) { - psw_t *psw = &vcpu->arch.sie_block->gpsw; unsigned long srcaddr, dstaddr; int reg1, reg2, rc; @@ -310,7 +322,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu) if (rc != 0) return rc; - psw->addr = __rewind_psw(*psw, 4); + kvm_s390_rewind_psw(vcpu, 4); return 0; } diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index a39838457f01..f00f31e66cd8 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -16,6 +16,7 @@ #include <linux/mmu_context.h> #include <linux/signal.h> #include <linux/slab.h> +#include <linux/bitmap.h> #include <asm/asm-offsets.h> #include <asm/uaccess.h> #include "kvm-s390.h" @@ -27,8 +28,8 @@ #define IOINT_CSSID_MASK 0x03fc0000 #define IOINT_AI_MASK 0x04000000 #define PFAULT_INIT 0x0600 - -static int __must_check deliver_ckc_interrupt(struct kvm_vcpu *vcpu); +#define PFAULT_DONE 0x0680 +#define VIRTIO_PARAM 0x0d00 static int is_ioint(u64 type) { @@ -136,6 +137,31 @@ static int __must_check __interrupt_is_deliverable(struct kvm_vcpu *vcpu, return 0; } +static inline unsigned long pending_local_irqs(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.local_int.pending_irqs; +} + +static unsigned long deliverable_local_irqs(struct kvm_vcpu *vcpu) +{ + unsigned long active_mask = pending_local_irqs(vcpu); + + if (psw_extint_disabled(vcpu)) + active_mask &= ~IRQ_PEND_EXT_MASK; + if (!(vcpu->arch.sie_block->gcr[0] & 0x2000ul)) + __clear_bit(IRQ_PEND_EXT_EXTERNAL, &active_mask); + if (!(vcpu->arch.sie_block->gcr[0] & 0x4000ul)) + __clear_bit(IRQ_PEND_EXT_EMERGENCY, &active_mask); + if (!(vcpu->arch.sie_block->gcr[0] & 0x800ul)) + __clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &active_mask); + if (!(vcpu->arch.sie_block->gcr[0] & 0x400ul)) + __clear_bit(IRQ_PEND_EXT_CPU_TIMER, &active_mask); + if (psw_mchk_disabled(vcpu)) + active_mask &= ~IRQ_PEND_MCHK_MASK; + + return active_mask; +} + static void __set_cpu_idle(struct kvm_vcpu *vcpu) { atomic_set_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags); @@ -170,26 +196,45 @@ static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag) atomic_set_mask(flag, &vcpu->arch.sie_block->cpuflags); } +static void set_intercept_indicators_ext(struct kvm_vcpu *vcpu) +{ + if (!(pending_local_irqs(vcpu) & IRQ_PEND_EXT_MASK)) + return; + if (psw_extint_disabled(vcpu)) + __set_cpuflag(vcpu, CPUSTAT_EXT_INT); + else + vcpu->arch.sie_block->lctl |= LCTL_CR0; +} + +static void set_intercept_indicators_mchk(struct kvm_vcpu *vcpu) +{ + if (!(pending_local_irqs(vcpu) & IRQ_PEND_MCHK_MASK)) + return; + if (psw_mchk_disabled(vcpu)) + vcpu->arch.sie_block->ictl |= ICTL_LPSW; + else + vcpu->arch.sie_block->lctl |= LCTL_CR14; +} + +/* Set interception request for non-deliverable local interrupts */ +static void set_intercept_indicators_local(struct kvm_vcpu *vcpu) +{ + set_intercept_indicators_ext(vcpu); + set_intercept_indicators_mchk(vcpu); +} + static void __set_intercept_indicator(struct kvm_vcpu *vcpu, struct kvm_s390_interrupt_info *inti) { switch (inti->type) { - case KVM_S390_INT_EXTERNAL_CALL: - case KVM_S390_INT_EMERGENCY: case KVM_S390_INT_SERVICE: - case KVM_S390_INT_PFAULT_INIT: case KVM_S390_INT_PFAULT_DONE: case KVM_S390_INT_VIRTIO: - case KVM_S390_INT_CLOCK_COMP: - case KVM_S390_INT_CPU_TIMER: if (psw_extint_disabled(vcpu)) __set_cpuflag(vcpu, CPUSTAT_EXT_INT); else vcpu->arch.sie_block->lctl |= LCTL_CR0; break; - case KVM_S390_SIGP_STOP: - __set_cpuflag(vcpu, CPUSTAT_STOP_INT); - break; case KVM_S390_MCHK: if (psw_mchk_disabled(vcpu)) vcpu->arch.sie_block->ictl |= ICTL_LPSW; @@ -226,13 +271,236 @@ static u16 get_ilc(struct kvm_vcpu *vcpu) } } -static int __must_check __deliver_prog_irq(struct kvm_vcpu *vcpu, - struct kvm_s390_pgm_info *pgm_info) +static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + int rc; + + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER, + 0, 0); + + rc = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER, + (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs); + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_ckc(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + int rc; + + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP, + 0, 0); + + rc = put_guest_lc(vcpu, EXT_IRQ_CLK_COMP, + (u16 __user *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs); + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_pfault_init(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_ext_info ext; + int rc; + + spin_lock(&li->lock); + ext = li->irq.ext; + clear_bit(IRQ_PEND_PFAULT_INIT, &li->pending_irqs); + li->irq.ext.ext_params2 = 0; + spin_unlock(&li->lock); + + VCPU_EVENT(vcpu, 4, "interrupt: pfault init parm:%x,parm64:%llx", + 0, ext.ext_params2); + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + KVM_S390_INT_PFAULT_INIT, + 0, ext.ext_params2); + + rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, (u16 *) __LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, PFAULT_INIT, (u16 *) __LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= put_guest_lc(vcpu, ext.ext_params2, (u64 *) __LC_EXT_PARAMS2); + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_mchk_info mchk; + int rc; + + spin_lock(&li->lock); + mchk = li->irq.mchk; + /* + * If there was an exigent machine check pending, then any repressible + * machine checks that might have been pending are indicated along + * with it, so always clear both bits + */ + clear_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs); + clear_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs); + memset(&li->irq.mchk, 0, sizeof(mchk)); + spin_unlock(&li->lock); + + VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx", + mchk.mcic); + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_MCHK, + mchk.cr14, mchk.mcic); + + rc = kvm_s390_vcpu_store_status(vcpu, KVM_S390_STORE_STATUS_PREFIXED); + rc |= put_guest_lc(vcpu, mchk.mcic, + (u64 __user *) __LC_MCCK_CODE); + rc |= put_guest_lc(vcpu, mchk.failing_storage_address, + (u64 __user *) __LC_MCCK_FAIL_STOR_ADDR); + rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA, + &mchk.fixed_logout, sizeof(mchk.fixed_logout)); + rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_MCK_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_restart(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + int rc; + + VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu restart"); + vcpu->stat.deliver_restart_signal++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0); + + rc = write_guest_lc(vcpu, + offsetof(struct _lowcore, restart_old_psw), + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, offsetof(struct _lowcore, restart_psw), + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + clear_bit(IRQ_PEND_RESTART, &li->pending_irqs); + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_stop(struct kvm_vcpu *vcpu) +{ + VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu stop"); + vcpu->stat.deliver_stop_signal++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_SIGP_STOP, + 0, 0); + + __set_cpuflag(vcpu, CPUSTAT_STOP_INT); + clear_bit(IRQ_PEND_SIGP_STOP, &vcpu->arch.local_int.pending_irqs); + return 0; +} + +static int __must_check __deliver_set_prefix(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_prefix_info prefix; + + spin_lock(&li->lock); + prefix = li->irq.prefix; + li->irq.prefix.address = 0; + clear_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs); + spin_unlock(&li->lock); + + VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x", prefix.address); + vcpu->stat.deliver_prefix_signal++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + KVM_S390_SIGP_SET_PREFIX, + prefix.address, 0); + + kvm_s390_set_prefix(vcpu, prefix.address); + return 0; +} + +static int __must_check __deliver_emergency_signal(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + int rc; + int cpu_addr; + + spin_lock(&li->lock); + cpu_addr = find_first_bit(li->sigp_emerg_pending, KVM_MAX_VCPUS); + clear_bit(cpu_addr, li->sigp_emerg_pending); + if (bitmap_empty(li->sigp_emerg_pending, KVM_MAX_VCPUS)) + clear_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs); + spin_unlock(&li->lock); + + VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg"); + vcpu->stat.deliver_emergency_signal++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY, + cpu_addr, 0); + + rc = put_guest_lc(vcpu, EXT_IRQ_EMERGENCY_SIG, + (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, cpu_addr, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_extcall_info extcall; + int rc; + + spin_lock(&li->lock); + extcall = li->irq.extcall; + li->irq.extcall.code = 0; + clear_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs); + spin_unlock(&li->lock); + + VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp ext call"); + vcpu->stat.deliver_external_call++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + KVM_S390_INT_EXTERNAL_CALL, + extcall.code, 0); + + rc = put_guest_lc(vcpu, EXT_IRQ_EXTERNAL_CALL, + (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, extcall.code, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, &vcpu->arch.sie_block->gpsw, + sizeof(psw_t)); + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_prog(struct kvm_vcpu *vcpu) { + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_pgm_info pgm_info; int rc = 0; u16 ilc = get_ilc(vcpu); - switch (pgm_info->code & ~PGM_PER) { + spin_lock(&li->lock); + pgm_info = li->irq.pgm; + clear_bit(IRQ_PEND_PROG, &li->pending_irqs); + memset(&li->irq.pgm, 0, sizeof(pgm_info)); + spin_unlock(&li->lock); + + VCPU_EVENT(vcpu, 4, "interrupt: pgm check code:%x, ilc:%x", + pgm_info.code, ilc); + vcpu->stat.deliver_program_int++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT, + pgm_info.code, 0); + + switch (pgm_info.code & ~PGM_PER) { case PGM_AFX_TRANSLATION: case PGM_ASX_TRANSLATION: case PGM_EX_TRANSLATION: @@ -243,7 +511,7 @@ static int __must_check __deliver_prog_irq(struct kvm_vcpu *vcpu, case PGM_PRIMARY_AUTHORITY: case PGM_SECONDARY_AUTHORITY: case PGM_SPACE_SWITCH: - rc = put_guest_lc(vcpu, pgm_info->trans_exc_code, + rc = put_guest_lc(vcpu, pgm_info.trans_exc_code, (u64 *)__LC_TRANS_EXC_CODE); break; case PGM_ALEN_TRANSLATION: @@ -252,7 +520,7 @@ static int __must_check __deliver_prog_irq(struct kvm_vcpu *vcpu, case PGM_ASTE_SEQUENCE: case PGM_ASTE_VALIDITY: case PGM_EXTENDED_AUTHORITY: - rc = put_guest_lc(vcpu, pgm_info->exc_access_id, + rc = put_guest_lc(vcpu, pgm_info.exc_access_id, (u8 *)__LC_EXC_ACCESS_ID); break; case PGM_ASCE_TYPE: @@ -261,247 +529,208 @@ static int __must_check __deliver_prog_irq(struct kvm_vcpu *vcpu, case PGM_REGION_SECOND_TRANS: case PGM_REGION_THIRD_TRANS: case PGM_SEGMENT_TRANSLATION: - rc = put_guest_lc(vcpu, pgm_info->trans_exc_code, + rc = put_guest_lc(vcpu, pgm_info.trans_exc_code, (u64 *)__LC_TRANS_EXC_CODE); - rc |= put_guest_lc(vcpu, pgm_info->exc_access_id, + rc |= put_guest_lc(vcpu, pgm_info.exc_access_id, (u8 *)__LC_EXC_ACCESS_ID); - rc |= put_guest_lc(vcpu, pgm_info->op_access_id, + rc |= put_guest_lc(vcpu, pgm_info.op_access_id, (u8 *)__LC_OP_ACCESS_ID); break; case PGM_MONITOR: - rc = put_guest_lc(vcpu, pgm_info->mon_class_nr, - (u64 *)__LC_MON_CLASS_NR); - rc |= put_guest_lc(vcpu, pgm_info->mon_code, + rc = put_guest_lc(vcpu, pgm_info.mon_class_nr, + (u16 *)__LC_MON_CLASS_NR); + rc |= put_guest_lc(vcpu, pgm_info.mon_code, (u64 *)__LC_MON_CODE); break; case PGM_DATA: - rc = put_guest_lc(vcpu, pgm_info->data_exc_code, + rc = put_guest_lc(vcpu, pgm_info.data_exc_code, (u32 *)__LC_DATA_EXC_CODE); break; case PGM_PROTECTION: - rc = put_guest_lc(vcpu, pgm_info->trans_exc_code, + rc = put_guest_lc(vcpu, pgm_info.trans_exc_code, (u64 *)__LC_TRANS_EXC_CODE); - rc |= put_guest_lc(vcpu, pgm_info->exc_access_id, + rc |= put_guest_lc(vcpu, pgm_info.exc_access_id, (u8 *)__LC_EXC_ACCESS_ID); break; } - if (pgm_info->code & PGM_PER) { - rc |= put_guest_lc(vcpu, pgm_info->per_code, + if (pgm_info.code & PGM_PER) { + rc |= put_guest_lc(vcpu, pgm_info.per_code, (u8 *) __LC_PER_CODE); - rc |= put_guest_lc(vcpu, pgm_info->per_atmid, + rc |= put_guest_lc(vcpu, pgm_info.per_atmid, (u8 *)__LC_PER_ATMID); - rc |= put_guest_lc(vcpu, pgm_info->per_address, + rc |= put_guest_lc(vcpu, pgm_info.per_address, (u64 *) __LC_PER_ADDRESS); - rc |= put_guest_lc(vcpu, pgm_info->per_access_id, + rc |= put_guest_lc(vcpu, pgm_info.per_access_id, (u8 *) __LC_PER_ACCESS_ID); } rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC); - rc |= put_guest_lc(vcpu, pgm_info->code, + rc |= put_guest_lc(vcpu, pgm_info.code, (u16 *)__LC_PGM_INT_CODE); rc |= write_guest_lc(vcpu, __LC_PGM_OLD_PSW, &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); rc |= read_guest_lc(vcpu, __LC_PGM_NEW_PSW, &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + return rc ? -EFAULT : 0; +} - return rc; +static int __must_check __deliver_service(struct kvm_vcpu *vcpu, + struct kvm_s390_interrupt_info *inti) +{ + int rc; + + VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x", + inti->ext.ext_params); + vcpu->stat.deliver_service_signal++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, + inti->ext.ext_params, 0); + + rc = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= put_guest_lc(vcpu, inti->ext.ext_params, + (u32 *)__LC_EXT_PARAMS); + return rc ? -EFAULT : 0; } -static int __must_check __do_deliver_interrupt(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt_info *inti) +static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu, + struct kvm_s390_interrupt_info *inti) { - const unsigned short table[] = { 2, 4, 4, 6 }; - int rc = 0; + int rc; + + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, + KVM_S390_INT_PFAULT_DONE, 0, + inti->ext.ext_params2); + + rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, PFAULT_DONE, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= put_guest_lc(vcpu, inti->ext.ext_params2, + (u64 *)__LC_EXT_PARAMS2); + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu, + struct kvm_s390_interrupt_info *inti) +{ + int rc; + + VCPU_EVENT(vcpu, 4, "interrupt: virtio parm:%x,parm64:%llx", + inti->ext.ext_params, inti->ext.ext_params2); + vcpu->stat.deliver_virtio_interrupt++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, + inti->ext.ext_params, + inti->ext.ext_params2); + + rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, (u16 *)__LC_EXT_INT_CODE); + rc |= put_guest_lc(vcpu, VIRTIO_PARAM, (u16 *)__LC_EXT_CPU_ADDR); + rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= put_guest_lc(vcpu, inti->ext.ext_params, + (u32 *)__LC_EXT_PARAMS); + rc |= put_guest_lc(vcpu, inti->ext.ext_params2, + (u64 *)__LC_EXT_PARAMS2); + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_io(struct kvm_vcpu *vcpu, + struct kvm_s390_interrupt_info *inti) +{ + int rc; + + VCPU_EVENT(vcpu, 4, "interrupt: I/O %llx", inti->type); + vcpu->stat.deliver_io_int++; + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, + ((__u32)inti->io.subchannel_id << 16) | + inti->io.subchannel_nr, + ((__u64)inti->io.io_int_parm << 32) | + inti->io.io_int_word); + + rc = put_guest_lc(vcpu, inti->io.subchannel_id, + (u16 *)__LC_SUBCHANNEL_ID); + rc |= put_guest_lc(vcpu, inti->io.subchannel_nr, + (u16 *)__LC_SUBCHANNEL_NR); + rc |= put_guest_lc(vcpu, inti->io.io_int_parm, + (u32 *)__LC_IO_INT_PARM); + rc |= put_guest_lc(vcpu, inti->io.io_int_word, + (u32 *)__LC_IO_INT_WORD); + rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + return rc ? -EFAULT : 0; +} + +static int __must_check __deliver_mchk_floating(struct kvm_vcpu *vcpu, + struct kvm_s390_interrupt_info *inti) +{ + struct kvm_s390_mchk_info *mchk = &inti->mchk; + int rc; + + VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx", + mchk->mcic); + trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_MCHK, + mchk->cr14, mchk->mcic); + + rc = kvm_s390_vcpu_store_status(vcpu, KVM_S390_STORE_STATUS_PREFIXED); + rc |= put_guest_lc(vcpu, mchk->mcic, + (u64 __user *) __LC_MCCK_CODE); + rc |= put_guest_lc(vcpu, mchk->failing_storage_address, + (u64 __user *) __LC_MCCK_FAIL_STOR_ADDR); + rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA, + &mchk->fixed_logout, sizeof(mchk->fixed_logout)); + rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc |= read_guest_lc(vcpu, __LC_MCK_NEW_PSW, + &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + return rc ? -EFAULT : 0; +} + +typedef int (*deliver_irq_t)(struct kvm_vcpu *vcpu); + +static const deliver_irq_t deliver_irq_funcs[] = { + [IRQ_PEND_MCHK_EX] = __deliver_machine_check, + [IRQ_PEND_PROG] = __deliver_prog, + [IRQ_PEND_EXT_EMERGENCY] = __deliver_emergency_signal, + [IRQ_PEND_EXT_EXTERNAL] = __deliver_external_call, + [IRQ_PEND_EXT_CLOCK_COMP] = __deliver_ckc, + [IRQ_PEND_EXT_CPU_TIMER] = __deliver_cpu_timer, + [IRQ_PEND_RESTART] = __deliver_restart, + [IRQ_PEND_SIGP_STOP] = __deliver_stop, + [IRQ_PEND_SET_PREFIX] = __deliver_set_prefix, + [IRQ_PEND_PFAULT_INIT] = __deliver_pfault_init, +}; + +static int __must_check __deliver_floating_interrupt(struct kvm_vcpu *vcpu, + struct kvm_s390_interrupt_info *inti) +{ + int rc; switch (inti->type) { - case KVM_S390_INT_EMERGENCY: - VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg"); - vcpu->stat.deliver_emergency_signal++; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - inti->emerg.code, 0); - rc = put_guest_lc(vcpu, 0x1201, (u16 *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, inti->emerg.code, - (u16 *)__LC_EXT_CPU_ADDR); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - break; - case KVM_S390_INT_EXTERNAL_CALL: - VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp ext call"); - vcpu->stat.deliver_external_call++; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - inti->extcall.code, 0); - rc = put_guest_lc(vcpu, 0x1202, (u16 *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, inti->extcall.code, - (u16 *)__LC_EXT_CPU_ADDR); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, - sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, - sizeof(psw_t)); - break; - case KVM_S390_INT_CLOCK_COMP: - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - inti->ext.ext_params, 0); - rc = deliver_ckc_interrupt(vcpu); - break; - case KVM_S390_INT_CPU_TIMER: - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - inti->ext.ext_params, 0); - rc = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER, - (u16 *)__LC_EXT_INT_CODE); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, - sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= put_guest_lc(vcpu, inti->ext.ext_params, - (u32 *)__LC_EXT_PARAMS); - break; case KVM_S390_INT_SERVICE: - VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x", - inti->ext.ext_params); - vcpu->stat.deliver_service_signal++; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - inti->ext.ext_params, 0); - rc = put_guest_lc(vcpu, 0x2401, (u16 *)__LC_EXT_INT_CODE); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, - sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= put_guest_lc(vcpu, inti->ext.ext_params, - (u32 *)__LC_EXT_PARAMS); - break; - case KVM_S390_INT_PFAULT_INIT: - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, 0, - inti->ext.ext_params2); - rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, - (u16 *) __LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, PFAULT_INIT, (u16 *) __LC_EXT_CPU_ADDR); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= put_guest_lc(vcpu, inti->ext.ext_params2, - (u64 *) __LC_EXT_PARAMS2); + rc = __deliver_service(vcpu, inti); break; case KVM_S390_INT_PFAULT_DONE: - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, 0, - inti->ext.ext_params2); - rc = put_guest_lc(vcpu, 0x2603, (u16 *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, 0x0680, (u16 *)__LC_EXT_CPU_ADDR); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, - sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= put_guest_lc(vcpu, inti->ext.ext_params2, - (u64 *)__LC_EXT_PARAMS2); + rc = __deliver_pfault_done(vcpu, inti); break; case KVM_S390_INT_VIRTIO: - VCPU_EVENT(vcpu, 4, "interrupt: virtio parm:%x,parm64:%llx", - inti->ext.ext_params, inti->ext.ext_params2); - vcpu->stat.deliver_virtio_interrupt++; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - inti->ext.ext_params, - inti->ext.ext_params2); - rc = put_guest_lc(vcpu, 0x2603, (u16 *)__LC_EXT_INT_CODE); - rc |= put_guest_lc(vcpu, 0x0d00, (u16 *)__LC_EXT_CPU_ADDR); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, - sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= put_guest_lc(vcpu, inti->ext.ext_params, - (u32 *)__LC_EXT_PARAMS); - rc |= put_guest_lc(vcpu, inti->ext.ext_params2, - (u64 *)__LC_EXT_PARAMS2); - break; - case KVM_S390_SIGP_STOP: - VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu stop"); - vcpu->stat.deliver_stop_signal++; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - 0, 0); - __set_intercept_indicator(vcpu, inti); - break; - - case KVM_S390_SIGP_SET_PREFIX: - VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x", - inti->prefix.address); - vcpu->stat.deliver_prefix_signal++; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - inti->prefix.address, 0); - kvm_s390_set_prefix(vcpu, inti->prefix.address); - break; - - case KVM_S390_RESTART: - VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu restart"); - vcpu->stat.deliver_restart_signal++; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - 0, 0); - rc = write_guest_lc(vcpu, - offsetof(struct _lowcore, restart_old_psw), - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, offsetof(struct _lowcore, restart_psw), - &vcpu->arch.sie_block->gpsw, - sizeof(psw_t)); + rc = __deliver_virtio(vcpu, inti); break; - case KVM_S390_PROGRAM_INT: - VCPU_EVENT(vcpu, 4, "interrupt: pgm check code:%x, ilc:%x", - inti->pgm.code, - table[vcpu->arch.sie_block->ipa >> 14]); - vcpu->stat.deliver_program_int++; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - inti->pgm.code, 0); - rc = __deliver_prog_irq(vcpu, &inti->pgm); - break; - case KVM_S390_MCHK: - VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx", - inti->mchk.mcic); - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - inti->mchk.cr14, - inti->mchk.mcic); - rc = kvm_s390_vcpu_store_status(vcpu, - KVM_S390_STORE_STATUS_PREFIXED); - rc |= put_guest_lc(vcpu, inti->mchk.mcic, (u64 *)__LC_MCCK_CODE); - rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW, - &vcpu->arch.sie_block->gpsw, - sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_MCK_NEW_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); + rc = __deliver_mchk_floating(vcpu, inti); break; - case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: - { - __u32 param0 = ((__u32)inti->io.subchannel_id << 16) | - inti->io.subchannel_nr; - __u64 param1 = ((__u64)inti->io.io_int_parm << 32) | - inti->io.io_int_word; - VCPU_EVENT(vcpu, 4, "interrupt: I/O %llx", inti->type); - vcpu->stat.deliver_io_int++; - trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type, - param0, param1); - rc = put_guest_lc(vcpu, inti->io.subchannel_id, - (u16 *)__LC_SUBCHANNEL_ID); - rc |= put_guest_lc(vcpu, inti->io.subchannel_nr, - (u16 *)__LC_SUBCHANNEL_NR); - rc |= put_guest_lc(vcpu, inti->io.io_int_parm, - (u32 *)__LC_IO_INT_PARM); - rc |= put_guest_lc(vcpu, inti->io.io_int_word, - (u32 *)__LC_IO_INT_WORD); - rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW, - &vcpu->arch.sie_block->gpsw, - sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW, - &vcpu->arch.sie_block->gpsw, - sizeof(psw_t)); + rc = __deliver_io(vcpu, inti); break; - } default: BUG(); } @@ -509,19 +738,6 @@ static int __must_check __do_deliver_interrupt(struct kvm_vcpu *vcpu, return rc; } -static int __must_check deliver_ckc_interrupt(struct kvm_vcpu *vcpu) -{ - int rc; - - rc = put_guest_lc(vcpu, 0x1004, (u16 __user *)__LC_EXT_INT_CODE); - rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW, - &vcpu->arch.sie_block->gpsw, sizeof(psw_t)); - rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, - &vcpu->arch.sie_block->gpsw, - sizeof(psw_t)); - return rc; -} - /* Check whether SIGP interpretation facility has an external call pending */ int kvm_s390_si_ext_call_pending(struct kvm_vcpu *vcpu) { @@ -538,20 +754,11 @@ int kvm_s390_si_ext_call_pending(struct kvm_vcpu *vcpu) int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu) { - struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int; struct kvm_s390_interrupt_info *inti; - int rc = 0; + int rc; - if (atomic_read(&li->active)) { - spin_lock(&li->lock); - list_for_each_entry(inti, &li->list, list) - if (__interrupt_is_deliverable(vcpu, inti)) { - rc = 1; - break; - } - spin_unlock(&li->lock); - } + rc = !!deliverable_local_irqs(vcpu); if ((!rc) && atomic_read(&fi->active)) { spin_lock(&fi->lock); @@ -643,18 +850,15 @@ enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer) void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - struct kvm_s390_interrupt_info *n, *inti = NULL; spin_lock(&li->lock); - list_for_each_entry_safe(inti, n, &li->list, list) { - list_del(&inti->list); - kfree(inti); - } - atomic_set(&li->active, 0); + li->pending_irqs = 0; + bitmap_zero(li->sigp_emerg_pending, KVM_MAX_VCPUS); + memset(&li->irq, 0, sizeof(li->irq)); spin_unlock(&li->lock); /* clear pending external calls set by sigp interpretation facility */ - atomic_clear_mask(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags); + atomic_clear_mask(CPUSTAT_ECALL_PEND, li->cpuflags); atomic_clear_mask(SIGP_CTRL_C, &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].ctrl); } @@ -664,34 +868,35 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int; struct kvm_s390_interrupt_info *n, *inti = NULL; + deliver_irq_t func; int deliver; int rc = 0; + unsigned long irq_type; + unsigned long deliverable_irqs; __reset_intercept_indicators(vcpu); - if (atomic_read(&li->active)) { - do { - deliver = 0; - spin_lock(&li->lock); - list_for_each_entry_safe(inti, n, &li->list, list) { - if (__interrupt_is_deliverable(vcpu, inti)) { - list_del(&inti->list); - deliver = 1; - break; - } - __set_intercept_indicator(vcpu, inti); - } - if (list_empty(&li->list)) - atomic_set(&li->active, 0); - spin_unlock(&li->lock); - if (deliver) { - rc = __do_deliver_interrupt(vcpu, inti); - kfree(inti); - } - } while (!rc && deliver); - } - if (!rc && kvm_cpu_has_pending_timer(vcpu)) - rc = deliver_ckc_interrupt(vcpu); + /* pending ckc conditions might have been invalidated */ + clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs); + if (kvm_cpu_has_pending_timer(vcpu)) + set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs); + + do { + deliverable_irqs = deliverable_local_irqs(vcpu); + /* bits are in the order of interrupt priority */ + irq_type = find_first_bit(&deliverable_irqs, IRQ_PEND_COUNT); + if (irq_type == IRQ_PEND_COUNT) + break; + func = deliver_irq_funcs[irq_type]; + if (!func) { + WARN_ON_ONCE(func == NULL); + clear_bit(irq_type, &li->pending_irqs); + continue; + } + rc = func(vcpu); + } while (!rc && irq_type != IRQ_PEND_COUNT); + + set_intercept_indicators_local(vcpu); if (!rc && atomic_read(&fi->active)) { do { @@ -710,7 +915,7 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) atomic_set(&fi->active, 0); spin_unlock(&fi->lock); if (deliver) { - rc = __do_deliver_interrupt(vcpu, inti); + rc = __deliver_floating_interrupt(vcpu, inti); kfree(inti); } } while (!rc && deliver); @@ -719,23 +924,26 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) return rc; } -int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code) +static int __inject_prog(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - struct kvm_s390_interrupt_info *inti; - inti = kzalloc(sizeof(*inti), GFP_KERNEL); - if (!inti) - return -ENOMEM; + li->irq.pgm = irq->u.pgm; + set_bit(IRQ_PEND_PROG, &li->pending_irqs); + return 0; +} - inti->type = KVM_S390_PROGRAM_INT; - inti->pgm.code = code; +int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_irq irq; VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code); - trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, inti->type, code, 0, 1); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT, code, + 0, 1); spin_lock(&li->lock); - list_add(&inti->list, &li->list); - atomic_set(&li->active, 1); + irq.u.pgm.code = code; + __inject_prog(vcpu, &irq); BUG_ON(waitqueue_active(li->wq)); spin_unlock(&li->lock); return 0; @@ -745,27 +953,166 @@ int kvm_s390_inject_prog_irq(struct kvm_vcpu *vcpu, struct kvm_s390_pgm_info *pgm_info) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - struct kvm_s390_interrupt_info *inti; - - inti = kzalloc(sizeof(*inti), GFP_KERNEL); - if (!inti) - return -ENOMEM; + struct kvm_s390_irq irq; + int rc; VCPU_EVENT(vcpu, 3, "inject: prog irq %d (from kernel)", pgm_info->code); trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_PROGRAM_INT, pgm_info->code, 0, 1); - - inti->type = KVM_S390_PROGRAM_INT; - memcpy(&inti->pgm, pgm_info, sizeof(inti->pgm)); spin_lock(&li->lock); - list_add(&inti->list, &li->list); - atomic_set(&li->active, 1); + irq.u.pgm = *pgm_info; + rc = __inject_prog(vcpu, &irq); BUG_ON(waitqueue_active(li->wq)); spin_unlock(&li->lock); + return rc; +} + +static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + + VCPU_EVENT(vcpu, 3, "inject: external irq params:%x, params2:%llx", + irq->u.ext.ext_params, irq->u.ext.ext_params2); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_PFAULT_INIT, + irq->u.ext.ext_params, + irq->u.ext.ext_params2, 2); + + li->irq.ext = irq->u.ext; + set_bit(IRQ_PEND_PFAULT_INIT, &li->pending_irqs); + atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); return 0; } +int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_extcall_info *extcall = &li->irq.extcall; + + VCPU_EVENT(vcpu, 3, "inject: external call source-cpu:%u", + irq->u.extcall.code); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EXTERNAL_CALL, + irq->u.extcall.code, 0, 2); + + *extcall = irq->u.extcall; + set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs); + atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); + return 0; +} + +static int __inject_set_prefix(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_prefix_info *prefix = &li->irq.prefix; + + VCPU_EVENT(vcpu, 3, "inject: set prefix to %x (from user)", + prefix->address); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_SET_PREFIX, + prefix->address, 0, 2); + + *prefix = irq->u.prefix; + set_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs); + return 0; +} + +static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_SIGP_STOP, 0, 0, 2); + + li->action_bits |= ACTION_STOP_ON_STOP; + set_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs); + return 0; +} + +static int __inject_sigp_restart(struct kvm_vcpu *vcpu, + struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + + VCPU_EVENT(vcpu, 3, "inject: restart type %llx", irq->type); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0, 2); + + set_bit(IRQ_PEND_RESTART, &li->pending_irqs); + return 0; +} + +static int __inject_sigp_emergency(struct kvm_vcpu *vcpu, + struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_emerg_info *emerg = &li->irq.emerg; + + VCPU_EVENT(vcpu, 3, "inject: emergency %u\n", + irq->u.emerg.code); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY, + emerg->code, 0, 2); + + set_bit(emerg->code, li->sigp_emerg_pending); + set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs); + atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); + return 0; +} + +static int __inject_mchk(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + struct kvm_s390_mchk_info *mchk = &li->irq.mchk; + + VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx", + mchk->mcic); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_MCHK, 0, + mchk->mcic, 2); + + /* + * Because repressible machine checks can be indicated along with + * exigent machine checks (PoP, Chapter 11, Interruption action) + * we need to combine cr14, mcic and external damage code. + * Failing storage address and the logout area should not be or'ed + * together, we just indicate the last occurrence of the corresponding + * machine check + */ + mchk->cr14 |= irq->u.mchk.cr14; + mchk->mcic |= irq->u.mchk.mcic; + mchk->ext_damage_code |= irq->u.mchk.ext_damage_code; + mchk->failing_storage_address = irq->u.mchk.failing_storage_address; + memcpy(&mchk->fixed_logout, &irq->u.mchk.fixed_logout, + sizeof(mchk->fixed_logout)); + if (mchk->mcic & MCHK_EX_MASK) + set_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs); + else if (mchk->mcic & MCHK_REP_MASK) + set_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs); + return 0; +} + +static int __inject_ckc(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + + VCPU_EVENT(vcpu, 3, "inject: type %x", KVM_S390_INT_CLOCK_COMP); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP, + 0, 0, 2); + + set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs); + atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); + return 0; +} + +static int __inject_cpu_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + + VCPU_EVENT(vcpu, 3, "inject: type %x", KVM_S390_INT_CPU_TIMER); + trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER, + 0, 0, 2); + + set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs); + atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); + return 0; +} + + struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, u64 cr6, u64 schid) { @@ -851,7 +1198,17 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti) dst_vcpu = kvm_get_vcpu(kvm, sigcpu); li = &dst_vcpu->arch.local_int; spin_lock(&li->lock); - atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); + switch (inti->type) { + case KVM_S390_MCHK: + atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags); + break; + case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: + atomic_set_mask(CPUSTAT_IO_INT, li->cpuflags); + break; + default: + atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); + break; + } spin_unlock(&li->lock); kvm_s390_vcpu_wakeup(kvm_get_vcpu(kvm, sigcpu)); unlock_fi: @@ -920,92 +1277,85 @@ void kvm_s390_reinject_io_int(struct kvm *kvm, __inject_vm(kvm, inti); } -int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt *s390int) +int s390int_to_s390irq(struct kvm_s390_interrupt *s390int, + struct kvm_s390_irq *irq) { - struct kvm_s390_local_interrupt *li; - struct kvm_s390_interrupt_info *inti; + irq->type = s390int->type; + switch (irq->type) { + case KVM_S390_PROGRAM_INT: + if (s390int->parm & 0xffff0000) + return -EINVAL; + irq->u.pgm.code = s390int->parm; + break; + case KVM_S390_SIGP_SET_PREFIX: + irq->u.prefix.address = s390int->parm; + break; + case KVM_S390_INT_EXTERNAL_CALL: + if (irq->u.extcall.code & 0xffff0000) + return -EINVAL; + irq->u.extcall.code = s390int->parm; + break; + case KVM_S390_INT_EMERGENCY: + if (irq->u.emerg.code & 0xffff0000) + return -EINVAL; + irq->u.emerg.code = s390int->parm; + break; + case KVM_S390_MCHK: + irq->u.mchk.mcic = s390int->parm64; + break; + } + return 0; +} - inti = kzalloc(sizeof(*inti), GFP_KERNEL); - if (!inti) - return -ENOMEM; +int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + int rc; - switch (s390int->type) { + spin_lock(&li->lock); + switch (irq->type) { case KVM_S390_PROGRAM_INT: - if (s390int->parm & 0xffff0000) { - kfree(inti); - return -EINVAL; - } - inti->type = s390int->type; - inti->pgm.code = s390int->parm; VCPU_EVENT(vcpu, 3, "inject: program check %d (from user)", - s390int->parm); + irq->u.pgm.code); + rc = __inject_prog(vcpu, irq); break; case KVM_S390_SIGP_SET_PREFIX: - inti->prefix.address = s390int->parm; - inti->type = s390int->type; - VCPU_EVENT(vcpu, 3, "inject: set prefix to %x (from user)", - s390int->parm); + rc = __inject_set_prefix(vcpu, irq); break; case KVM_S390_SIGP_STOP: + rc = __inject_sigp_stop(vcpu, irq); + break; case KVM_S390_RESTART: + rc = __inject_sigp_restart(vcpu, irq); + break; case KVM_S390_INT_CLOCK_COMP: + rc = __inject_ckc(vcpu); + break; case KVM_S390_INT_CPU_TIMER: - VCPU_EVENT(vcpu, 3, "inject: type %x", s390int->type); - inti->type = s390int->type; + rc = __inject_cpu_timer(vcpu); break; case KVM_S390_INT_EXTERNAL_CALL: - if (s390int->parm & 0xffff0000) { - kfree(inti); - return -EINVAL; - } - VCPU_EVENT(vcpu, 3, "inject: external call source-cpu:%u", - s390int->parm); - inti->type = s390int->type; - inti->extcall.code = s390int->parm; + rc = __inject_extcall(vcpu, irq); break; case KVM_S390_INT_EMERGENCY: - if (s390int->parm & 0xffff0000) { - kfree(inti); - return -EINVAL; - } - VCPU_EVENT(vcpu, 3, "inject: emergency %u\n", s390int->parm); - inti->type = s390int->type; - inti->emerg.code = s390int->parm; + rc = __inject_sigp_emergency(vcpu, irq); break; case KVM_S390_MCHK: - VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx", - s390int->parm64); - inti->type = s390int->type; - inti->mchk.mcic = s390int->parm64; + rc = __inject_mchk(vcpu, irq); break; case KVM_S390_INT_PFAULT_INIT: - inti->type = s390int->type; - inti->ext.ext_params2 = s390int->parm64; + rc = __inject_pfault_init(vcpu, irq); break; case KVM_S390_INT_VIRTIO: case KVM_S390_INT_SERVICE: case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX: default: - kfree(inti); - return -EINVAL; + rc = -EINVAL; } - trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, s390int->type, s390int->parm, - s390int->parm64, 2); - - li = &vcpu->arch.local_int; - spin_lock(&li->lock); - if (inti->type == KVM_S390_PROGRAM_INT) - list_add(&inti->list, &li->list); - else - list_add_tail(&inti->list, &li->list); - atomic_set(&li->active, 1); - if (inti->type == KVM_S390_SIGP_STOP) - li->action_bits |= ACTION_STOP_ON_STOP; - atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags); spin_unlock(&li->lock); - kvm_s390_vcpu_wakeup(vcpu); - return 0; + if (!rc) + kvm_s390_vcpu_wakeup(vcpu); + return rc; } void kvm_s390_clear_float_irqs(struct kvm *kvm) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 55aade49b6d1..3e09801e3104 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -81,10 +81,17 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) }, { "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) }, { "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) }, + { "instruction_sigp_cond_emergency", VCPU_STAT(instruction_sigp_cond_emergency) }, + { "instruction_sigp_start", VCPU_STAT(instruction_sigp_start) }, { "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) }, + { "instruction_sigp_stop_store_status", VCPU_STAT(instruction_sigp_stop_store_status) }, + { "instruction_sigp_store_status", VCPU_STAT(instruction_sigp_store_status) }, { "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) }, { "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) }, { "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) }, + { "instruction_sigp_cpu_reset", VCPU_STAT(instruction_sigp_cpu_reset) }, + { "instruction_sigp_init_cpu_reset", VCPU_STAT(instruction_sigp_init_cpu_reset) }, + { "instruction_sigp_unknown", VCPU_STAT(instruction_sigp_unknown) }, { "diagnose_10", VCPU_STAT(diagnose_10) }, { "diagnose_44", VCPU_STAT(diagnose_44) }, { "diagnose_9c", VCPU_STAT(diagnose_9c) }, @@ -271,7 +278,7 @@ static int kvm_s390_mem_control(struct kvm *kvm, struct kvm_device_attr *attr) case KVM_S390_VM_MEM_CLR_CMMA: mutex_lock(&kvm->lock); idx = srcu_read_lock(&kvm->srcu); - page_table_reset_pgste(kvm->arch.gmap->mm, 0, TASK_SIZE, false); + s390_reset_cmma(kvm->arch.gmap->mm); srcu_read_unlock(&kvm->srcu, idx); mutex_unlock(&kvm->lock); ret = 0; @@ -453,6 +460,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) spin_lock_init(&kvm->arch.float_int.lock); INIT_LIST_HEAD(&kvm->arch.float_int.list); init_waitqueue_head(&kvm->arch.ipte_wq); + mutex_init(&kvm->arch.ipte_mutex); debug_register_view(kvm->arch.dbf, &debug_sprintf_view); VM_EVENT(kvm, 3, "%s", "vm created"); @@ -711,7 +719,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, } spin_lock_init(&vcpu->arch.local_int.lock); - INIT_LIST_HEAD(&vcpu->arch.local_int.list); vcpu->arch.local_int.float_int = &kvm->arch.float_int; vcpu->arch.local_int.wq = &vcpu->wq; vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags; @@ -1114,13 +1121,15 @@ static void __kvm_inject_pfault_token(struct kvm_vcpu *vcpu, bool start_token, unsigned long token) { struct kvm_s390_interrupt inti; - inti.parm64 = token; + struct kvm_s390_irq irq; if (start_token) { - inti.type = KVM_S390_INT_PFAULT_INIT; - WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &inti)); + irq.u.ext.ext_params2 = token; + irq.type = KVM_S390_INT_PFAULT_INIT; + WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &irq)); } else { inti.type = KVM_S390_INT_PFAULT_DONE; + inti.parm64 = token; WARN_ON_ONCE(kvm_s390_inject_vm(vcpu->kvm, &inti)); } } @@ -1614,11 +1623,14 @@ long kvm_arch_vcpu_ioctl(struct file *filp, switch (ioctl) { case KVM_S390_INTERRUPT: { struct kvm_s390_interrupt s390int; + struct kvm_s390_irq s390irq; r = -EFAULT; if (copy_from_user(&s390int, argp, sizeof(s390int))) break; - r = kvm_s390_inject_vcpu(vcpu, &s390int); + if (s390int_to_s390irq(&s390int, &s390irq)) + return -EINVAL; + r = kvm_s390_inject_vcpu(vcpu, &s390irq); break; } case KVM_S390_STORE_STATUS: diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 244d02303182..a8f3d9b71c11 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -24,8 +24,6 @@ typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu); /* declare vfacilities extern */ extern unsigned long *vfacilities; -int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu); - /* Transactional Memory Execution related macros */ #define IS_TE_ENABLED(vcpu) ((vcpu->arch.sie_block->ecb & 0x10)) #define TDB_FORMAT1 1 @@ -144,7 +142,7 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm); int __must_check kvm_s390_inject_vm(struct kvm *kvm, struct kvm_s390_interrupt *s390int); int __must_check kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu, - struct kvm_s390_interrupt *s390int); + struct kvm_s390_irq *irq); int __must_check kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code); struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm, u64 cr6, u64 schid); @@ -152,6 +150,10 @@ void kvm_s390_reinject_io_int(struct kvm *kvm, struct kvm_s390_interrupt_info *inti); int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked); +/* implemented in intercept.c */ +void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc); +int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu); + /* implemented in priv.c */ int is_valid_psw(psw_t *psw); int kvm_s390_handle_b2(struct kvm_vcpu *vcpu); @@ -222,6 +224,9 @@ static inline int kvm_s390_inject_prog_cond(struct kvm_vcpu *vcpu, int rc) return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); } +int s390int_to_s390irq(struct kvm_s390_interrupt *s390int, + struct kvm_s390_irq *s390irq); + /* implemented in interrupt.c */ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int psw_extint_disabled(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 72bb2dd8b9cd..1be578d64dfc 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -156,41 +156,42 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu) return 0; } -static void __skey_check_enable(struct kvm_vcpu *vcpu) +static int __skey_check_enable(struct kvm_vcpu *vcpu) { + int rc = 0; if (!(vcpu->arch.sie_block->ictl & (ICTL_ISKE | ICTL_SSKE | ICTL_RRBE))) - return; + return rc; - s390_enable_skey(); + rc = s390_enable_skey(); trace_kvm_s390_skey_related_inst(vcpu); vcpu->arch.sie_block->ictl &= ~(ICTL_ISKE | ICTL_SSKE | ICTL_RRBE); + return rc; } static int handle_skey(struct kvm_vcpu *vcpu) { - __skey_check_enable(vcpu); + int rc = __skey_check_enable(vcpu); + if (rc) + return rc; vcpu->stat.instruction_storage_key++; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - vcpu->arch.sie_block->gpsw.addr = - __rewind_psw(vcpu->arch.sie_block->gpsw, 4); + kvm_s390_rewind_psw(vcpu, 4); VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation"); return 0; } static int handle_ipte_interlock(struct kvm_vcpu *vcpu) { - psw_t *psw = &vcpu->arch.sie_block->gpsw; - vcpu->stat.instruction_ipte_interlock++; - if (psw_bits(*psw).p) + if (psw_bits(vcpu->arch.sie_block->gpsw).p) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); wait_event(vcpu->kvm->arch.ipte_wq, !ipte_lock_held(vcpu)); - psw->addr = __rewind_psw(*psw, 4); + kvm_s390_rewind_psw(vcpu, 4); VCPU_EVENT(vcpu, 4, "%s", "retrying ipte interlock operation"); return 0; } @@ -646,10 +647,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); start = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK; - if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) { - if (kvm_s390_check_low_addr_protection(vcpu, start)) - return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); - } + start = kvm_s390_logical_to_effective(vcpu, start); switch (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) { case 0x00000000: @@ -665,6 +663,12 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) default: return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); } + + if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) { + if (kvm_s390_check_low_addr_protection(vcpu, start)) + return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); + } + while (start < end) { unsigned long useraddr, abs_addr; @@ -683,7 +687,10 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) } if (vcpu->run->s.regs.gprs[reg1] & PFMF_SK) { - __skey_check_enable(vcpu); + int rc = __skey_check_enable(vcpu); + + if (rc) + return rc; if (set_guest_storage_key(current->mm, useraddr, vcpu->run->s.regs.gprs[reg1] & PFMF_KEY, vcpu->run->s.regs.gprs[reg1] & PFMF_NQ)) @@ -718,8 +725,7 @@ static int handle_essa(struct kvm_vcpu *vcpu) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); /* Rewind PSW to repeat the ESSA instruction */ - vcpu->arch.sie_block->gpsw.addr = - __rewind_psw(vcpu->arch.sie_block->gpsw, 4); + kvm_s390_rewind_psw(vcpu, 4); vcpu->arch.sie_block->cbrlo &= PAGE_MASK; /* reset nceo */ cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo); down_read(&gmap->mm->mmap_sem); @@ -762,8 +768,8 @@ int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu) { int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; int reg3 = vcpu->arch.sie_block->ipa & 0x000f; - u32 val = 0; - int reg, rc; + int reg, rc, nr_regs; + u32 ctl_array[16]; u64 ga; vcpu->stat.instruction_lctl++; @@ -779,19 +785,20 @@ int kvm_s390_handle_lctl(struct kvm_vcpu *vcpu) VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x, addr:%llx", reg1, reg3, ga); trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, ga); + nr_regs = ((reg3 - reg1) & 0xf) + 1; + rc = read_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u32)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); reg = reg1; + nr_regs = 0; do { - rc = read_guest(vcpu, ga, &val, sizeof(val)); - if (rc) - return kvm_s390_inject_prog_cond(vcpu, rc); vcpu->arch.sie_block->gcr[reg] &= 0xffffffff00000000ul; - vcpu->arch.sie_block->gcr[reg] |= val; - ga += 4; + vcpu->arch.sie_block->gcr[reg] |= ctl_array[nr_regs++]; if (reg == reg3) break; reg = (reg + 1) % 16; } while (1); - + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); return 0; } @@ -799,9 +806,9 @@ int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu) { int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; int reg3 = vcpu->arch.sie_block->ipa & 0x000f; + int reg, rc, nr_regs; + u32 ctl_array[16]; u64 ga; - u32 val; - int reg, rc; vcpu->stat.instruction_stctl++; @@ -817,26 +824,24 @@ int kvm_s390_handle_stctl(struct kvm_vcpu *vcpu) trace_kvm_s390_handle_stctl(vcpu, 0, reg1, reg3, ga); reg = reg1; + nr_regs = 0; do { - val = vcpu->arch.sie_block->gcr[reg] & 0x00000000fffffffful; - rc = write_guest(vcpu, ga, &val, sizeof(val)); - if (rc) - return kvm_s390_inject_prog_cond(vcpu, rc); - ga += 4; + ctl_array[nr_regs++] = vcpu->arch.sie_block->gcr[reg]; if (reg == reg3) break; reg = (reg + 1) % 16; } while (1); - - return 0; + rc = write_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u32)); + return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0; } static int handle_lctlg(struct kvm_vcpu *vcpu) { int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; int reg3 = vcpu->arch.sie_block->ipa & 0x000f; - u64 ga, val; - int reg, rc; + int reg, rc, nr_regs; + u64 ctl_array[16]; + u64 ga; vcpu->stat.instruction_lctlg++; @@ -848,22 +853,22 @@ static int handle_lctlg(struct kvm_vcpu *vcpu) if (ga & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - reg = reg1; - VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x, addr:%llx", reg1, reg3, ga); trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, ga); + nr_regs = ((reg3 - reg1) & 0xf) + 1; + rc = read_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u64)); + if (rc) + return kvm_s390_inject_prog_cond(vcpu, rc); + reg = reg1; + nr_regs = 0; do { - rc = read_guest(vcpu, ga, &val, sizeof(val)); - if (rc) - return kvm_s390_inject_prog_cond(vcpu, rc); - vcpu->arch.sie_block->gcr[reg] = val; - ga += 8; + vcpu->arch.sie_block->gcr[reg] = ctl_array[nr_regs++]; if (reg == reg3) break; reg = (reg + 1) % 16; } while (1); - + kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); return 0; } @@ -871,8 +876,9 @@ static int handle_stctg(struct kvm_vcpu *vcpu) { int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; int reg3 = vcpu->arch.sie_block->ipa & 0x000f; - u64 ga, val; - int reg, rc; + int reg, rc, nr_regs; + u64 ctl_array[16]; + u64 ga; vcpu->stat.instruction_stctg++; @@ -884,23 +890,19 @@ static int handle_stctg(struct kvm_vcpu *vcpu) if (ga & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - reg = reg1; - VCPU_EVENT(vcpu, 5, "stctg r1:%x, r3:%x, addr:%llx", reg1, reg3, ga); trace_kvm_s390_handle_stctl(vcpu, 1, reg1, reg3, ga); + reg = reg1; + nr_regs = 0; do { - val = vcpu->arch.sie_block->gcr[reg]; - rc = write_guest(vcpu, ga, &val, sizeof(val)); - if (rc) - return kvm_s390_inject_prog_cond(vcpu, rc); - ga += 8; + ctl_array[nr_regs++] = vcpu->arch.sie_block->gcr[reg]; if (reg == reg3) break; reg = (reg + 1) % 16; } while (1); - - return 0; + rc = write_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u64)); + return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0; } static const intercept_handler_t eb_handlers[256] = { diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index cf243ba3d50f..6651f9f73973 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -20,20 +20,13 @@ #include "kvm-s390.h" #include "trace.h" -static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr, +static int __sigp_sense(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu, u64 *reg) { struct kvm_s390_local_interrupt *li; - struct kvm_vcpu *dst_vcpu = NULL; int cpuflags; int rc; - if (cpu_addr >= KVM_MAX_VCPUS) - return SIGP_CC_NOT_OPERATIONAL; - - dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr); - if (!dst_vcpu) - return SIGP_CC_NOT_OPERATIONAL; li = &dst_vcpu->arch.local_int; cpuflags = atomic_read(li->cpuflags); @@ -48,55 +41,53 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr, rc = SIGP_CC_STATUS_STORED; } - VCPU_EVENT(vcpu, 4, "sensed status of cpu %x rc %x", cpu_addr, rc); + VCPU_EVENT(vcpu, 4, "sensed status of cpu %x rc %x", dst_vcpu->vcpu_id, + rc); return rc; } -static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr) +static int __inject_sigp_emergency(struct kvm_vcpu *vcpu, + struct kvm_vcpu *dst_vcpu) { - struct kvm_s390_interrupt s390int = { + struct kvm_s390_irq irq = { .type = KVM_S390_INT_EMERGENCY, - .parm = vcpu->vcpu_id, + .u.emerg.code = vcpu->vcpu_id, }; - struct kvm_vcpu *dst_vcpu = NULL; int rc = 0; - if (cpu_addr < KVM_MAX_VCPUS) - dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr); - if (!dst_vcpu) - return SIGP_CC_NOT_OPERATIONAL; - - rc = kvm_s390_inject_vcpu(dst_vcpu, &s390int); + rc = kvm_s390_inject_vcpu(dst_vcpu, &irq); if (!rc) - VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr); + VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", + dst_vcpu->vcpu_id); return rc ? rc : SIGP_CC_ORDER_CODE_ACCEPTED; } -static int __sigp_conditional_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr, +static int __sigp_emergency(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu) +{ + return __inject_sigp_emergency(vcpu, dst_vcpu); +} + +static int __sigp_conditional_emergency(struct kvm_vcpu *vcpu, + struct kvm_vcpu *dst_vcpu, u16 asn, u64 *reg) { - struct kvm_vcpu *dst_vcpu = NULL; const u64 psw_int_mask = PSW_MASK_IO | PSW_MASK_EXT; u16 p_asn, s_asn; psw_t *psw; u32 flags; - if (cpu_addr < KVM_MAX_VCPUS) - dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr); - if (!dst_vcpu) - return SIGP_CC_NOT_OPERATIONAL; flags = atomic_read(&dst_vcpu->arch.sie_block->cpuflags); psw = &dst_vcpu->arch.sie_block->gpsw; p_asn = dst_vcpu->arch.sie_block->gcr[4] & 0xffff; /* Primary ASN */ s_asn = dst_vcpu->arch.sie_block->gcr[3] & 0xffff; /* Secondary ASN */ - /* Deliver the emergency signal? */ + /* Inject the emergency signal? */ if (!(flags & CPUSTAT_STOPPED) || (psw->mask & psw_int_mask) != psw_int_mask || ((flags & CPUSTAT_WAIT) && psw->addr != 0) || (!(flags & CPUSTAT_WAIT) && (asn == p_asn || asn == s_asn))) { - return __sigp_emergency(vcpu, cpu_addr); + return __inject_sigp_emergency(vcpu, dst_vcpu); } else { *reg &= 0xffffffff00000000UL; *reg |= SIGP_STATUS_INCORRECT_STATE; @@ -104,23 +95,19 @@ static int __sigp_conditional_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr, } } -static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr) +static int __sigp_external_call(struct kvm_vcpu *vcpu, + struct kvm_vcpu *dst_vcpu) { - struct kvm_s390_interrupt s390int = { + struct kvm_s390_irq irq = { .type = KVM_S390_INT_EXTERNAL_CALL, - .parm = vcpu->vcpu_id, + .u.extcall.code = vcpu->vcpu_id, }; - struct kvm_vcpu *dst_vcpu = NULL; int rc; - if (cpu_addr < KVM_MAX_VCPUS) - dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr); - if (!dst_vcpu) - return SIGP_CC_NOT_OPERATIONAL; - - rc = kvm_s390_inject_vcpu(dst_vcpu, &s390int); + rc = kvm_s390_inject_vcpu(dst_vcpu, &irq); if (!rc) - VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x", cpu_addr); + VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x", + dst_vcpu->vcpu_id); return rc ? rc : SIGP_CC_ORDER_CODE_ACCEPTED; } @@ -128,29 +115,20 @@ static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr) static int __inject_sigp_stop(struct kvm_vcpu *dst_vcpu, int action) { struct kvm_s390_local_interrupt *li = &dst_vcpu->arch.local_int; - struct kvm_s390_interrupt_info *inti; int rc = SIGP_CC_ORDER_CODE_ACCEPTED; - inti = kzalloc(sizeof(*inti), GFP_ATOMIC); - if (!inti) - return -ENOMEM; - inti->type = KVM_S390_SIGP_STOP; - spin_lock(&li->lock); if (li->action_bits & ACTION_STOP_ON_STOP) { /* another SIGP STOP is pending */ - kfree(inti); rc = SIGP_CC_BUSY; goto out; } if ((atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) { - kfree(inti); if ((action & ACTION_STORE_ON_STOP) != 0) rc = -ESHUTDOWN; goto out; } - list_add_tail(&inti->list, &li->list); - atomic_set(&li->active, 1); + set_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs); li->action_bits |= action; atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags); kvm_s390_vcpu_wakeup(dst_vcpu); @@ -160,23 +138,27 @@ out: return rc; } -static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int action) +static int __sigp_stop(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu) { - struct kvm_vcpu *dst_vcpu = NULL; int rc; - if (cpu_addr >= KVM_MAX_VCPUS) - return SIGP_CC_NOT_OPERATIONAL; + rc = __inject_sigp_stop(dst_vcpu, ACTION_STOP_ON_STOP); + VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", dst_vcpu->vcpu_id); - dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr); - if (!dst_vcpu) - return SIGP_CC_NOT_OPERATIONAL; + return rc; +} - rc = __inject_sigp_stop(dst_vcpu, action); +static int __sigp_stop_and_store_status(struct kvm_vcpu *vcpu, + struct kvm_vcpu *dst_vcpu, u64 *reg) +{ + int rc; - VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", cpu_addr); + rc = __inject_sigp_stop(dst_vcpu, ACTION_STOP_ON_STOP | + ACTION_STORE_ON_STOP); + VCPU_EVENT(vcpu, 4, "sent sigp stop and store status to cpu %x", + dst_vcpu->vcpu_id); - if ((action & ACTION_STORE_ON_STOP) != 0 && rc == -ESHUTDOWN) { + if (rc == -ESHUTDOWN) { /* If the CPU has already been stopped, we still have * to save the status when doing stop-and-store. This * has to be done after unlocking all spinlocks. */ @@ -212,18 +194,12 @@ static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter) return rc; } -static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, - u64 *reg) +static int __sigp_set_prefix(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu, + u32 address, u64 *reg) { struct kvm_s390_local_interrupt *li; - struct kvm_vcpu *dst_vcpu = NULL; - struct kvm_s390_interrupt_info *inti; int rc; - if (cpu_addr < KVM_MAX_VCPUS) - dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr); - if (!dst_vcpu) - return SIGP_CC_NOT_OPERATIONAL; li = &dst_vcpu->arch.local_int; /* @@ -238,46 +214,34 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, return SIGP_CC_STATUS_STORED; } - inti = kzalloc(sizeof(*inti), GFP_KERNEL); - if (!inti) - return SIGP_CC_BUSY; - spin_lock(&li->lock); /* cpu must be in stopped state */ if (!(atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) { *reg &= 0xffffffff00000000UL; *reg |= SIGP_STATUS_INCORRECT_STATE; rc = SIGP_CC_STATUS_STORED; - kfree(inti); goto out_li; } - inti->type = KVM_S390_SIGP_SET_PREFIX; - inti->prefix.address = address; - - list_add_tail(&inti->list, &li->list); - atomic_set(&li->active, 1); + li->irq.prefix.address = address; + set_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs); kvm_s390_vcpu_wakeup(dst_vcpu); rc = SIGP_CC_ORDER_CODE_ACCEPTED; - VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x", cpu_addr, address); + VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x", dst_vcpu->vcpu_id, + address); out_li: spin_unlock(&li->lock); return rc; } -static int __sigp_store_status_at_addr(struct kvm_vcpu *vcpu, u16 cpu_id, - u32 addr, u64 *reg) +static int __sigp_store_status_at_addr(struct kvm_vcpu *vcpu, + struct kvm_vcpu *dst_vcpu, + u32 addr, u64 *reg) { - struct kvm_vcpu *dst_vcpu = NULL; int flags; int rc; - if (cpu_id < KVM_MAX_VCPUS) - dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_id); - if (!dst_vcpu) - return SIGP_CC_NOT_OPERATIONAL; - spin_lock(&dst_vcpu->arch.local_int.lock); flags = atomic_read(dst_vcpu->arch.local_int.cpuflags); spin_unlock(&dst_vcpu->arch.local_int.lock); @@ -297,19 +261,12 @@ static int __sigp_store_status_at_addr(struct kvm_vcpu *vcpu, u16 cpu_id, return rc; } -static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr, - u64 *reg) +static int __sigp_sense_running(struct kvm_vcpu *vcpu, + struct kvm_vcpu *dst_vcpu, u64 *reg) { struct kvm_s390_local_interrupt *li; - struct kvm_vcpu *dst_vcpu = NULL; int rc; - if (cpu_addr >= KVM_MAX_VCPUS) - return SIGP_CC_NOT_OPERATIONAL; - - dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr); - if (!dst_vcpu) - return SIGP_CC_NOT_OPERATIONAL; li = &dst_vcpu->arch.local_int; if (atomic_read(li->cpuflags) & CPUSTAT_RUNNING) { /* running */ @@ -321,26 +278,19 @@ static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr, rc = SIGP_CC_STATUS_STORED; } - VCPU_EVENT(vcpu, 4, "sensed running status of cpu %x rc %x", cpu_addr, - rc); + VCPU_EVENT(vcpu, 4, "sensed running status of cpu %x rc %x", + dst_vcpu->vcpu_id, rc); return rc; } -/* Test whether the destination CPU is available and not busy */ -static int sigp_check_callable(struct kvm_vcpu *vcpu, u16 cpu_addr) +static int __prepare_sigp_re_start(struct kvm_vcpu *vcpu, + struct kvm_vcpu *dst_vcpu, u8 order_code) { - struct kvm_s390_local_interrupt *li; - int rc = SIGP_CC_ORDER_CODE_ACCEPTED; - struct kvm_vcpu *dst_vcpu = NULL; - - if (cpu_addr >= KVM_MAX_VCPUS) - return SIGP_CC_NOT_OPERATIONAL; + struct kvm_s390_local_interrupt *li = &dst_vcpu->arch.local_int; + /* handle (RE)START in user space */ + int rc = -EOPNOTSUPP; - dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr); - if (!dst_vcpu) - return SIGP_CC_NOT_OPERATIONAL; - li = &dst_vcpu->arch.local_int; spin_lock(&li->lock); if (li->action_bits & ACTION_STOP_ON_STOP) rc = SIGP_CC_BUSY; @@ -349,90 +299,131 @@ static int sigp_check_callable(struct kvm_vcpu *vcpu, u16 cpu_addr) return rc; } -int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) +static int __prepare_sigp_cpu_reset(struct kvm_vcpu *vcpu, + struct kvm_vcpu *dst_vcpu, u8 order_code) { - int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; - int r3 = vcpu->arch.sie_block->ipa & 0x000f; - u32 parameter; - u16 cpu_addr = vcpu->run->s.regs.gprs[r3]; - u8 order_code; - int rc; + /* handle (INITIAL) CPU RESET in user space */ + return -EOPNOTSUPP; +} - /* sigp in userspace can exit */ - if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) - return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); +static int __prepare_sigp_unknown(struct kvm_vcpu *vcpu, + struct kvm_vcpu *dst_vcpu) +{ + /* handle unknown orders in user space */ + return -EOPNOTSUPP; +} - order_code = kvm_s390_get_base_disp_rs(vcpu); +static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code, + u16 cpu_addr, u32 parameter, u64 *status_reg) +{ + int rc; + struct kvm_vcpu *dst_vcpu; - if (r1 % 2) - parameter = vcpu->run->s.regs.gprs[r1]; - else - parameter = vcpu->run->s.regs.gprs[r1 + 1]; + if (cpu_addr >= KVM_MAX_VCPUS) + return SIGP_CC_NOT_OPERATIONAL; + + dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr); + if (!dst_vcpu) + return SIGP_CC_NOT_OPERATIONAL; - trace_kvm_s390_handle_sigp(vcpu, order_code, cpu_addr, parameter); switch (order_code) { case SIGP_SENSE: vcpu->stat.instruction_sigp_sense++; - rc = __sigp_sense(vcpu, cpu_addr, - &vcpu->run->s.regs.gprs[r1]); + rc = __sigp_sense(vcpu, dst_vcpu, status_reg); break; case SIGP_EXTERNAL_CALL: vcpu->stat.instruction_sigp_external_call++; - rc = __sigp_external_call(vcpu, cpu_addr); + rc = __sigp_external_call(vcpu, dst_vcpu); break; case SIGP_EMERGENCY_SIGNAL: vcpu->stat.instruction_sigp_emergency++; - rc = __sigp_emergency(vcpu, cpu_addr); + rc = __sigp_emergency(vcpu, dst_vcpu); break; case SIGP_STOP: vcpu->stat.instruction_sigp_stop++; - rc = __sigp_stop(vcpu, cpu_addr, ACTION_STOP_ON_STOP); + rc = __sigp_stop(vcpu, dst_vcpu); break; case SIGP_STOP_AND_STORE_STATUS: - vcpu->stat.instruction_sigp_stop++; - rc = __sigp_stop(vcpu, cpu_addr, ACTION_STORE_ON_STOP | - ACTION_STOP_ON_STOP); + vcpu->stat.instruction_sigp_stop_store_status++; + rc = __sigp_stop_and_store_status(vcpu, dst_vcpu, status_reg); break; case SIGP_STORE_STATUS_AT_ADDRESS: - rc = __sigp_store_status_at_addr(vcpu, cpu_addr, parameter, - &vcpu->run->s.regs.gprs[r1]); - break; - case SIGP_SET_ARCHITECTURE: - vcpu->stat.instruction_sigp_arch++; - rc = __sigp_set_arch(vcpu, parameter); + vcpu->stat.instruction_sigp_store_status++; + rc = __sigp_store_status_at_addr(vcpu, dst_vcpu, parameter, + status_reg); break; case SIGP_SET_PREFIX: vcpu->stat.instruction_sigp_prefix++; - rc = __sigp_set_prefix(vcpu, cpu_addr, parameter, - &vcpu->run->s.regs.gprs[r1]); + rc = __sigp_set_prefix(vcpu, dst_vcpu, parameter, status_reg); break; case SIGP_COND_EMERGENCY_SIGNAL: - rc = __sigp_conditional_emergency(vcpu, cpu_addr, parameter, - &vcpu->run->s.regs.gprs[r1]); + vcpu->stat.instruction_sigp_cond_emergency++; + rc = __sigp_conditional_emergency(vcpu, dst_vcpu, parameter, + status_reg); break; case SIGP_SENSE_RUNNING: vcpu->stat.instruction_sigp_sense_running++; - rc = __sigp_sense_running(vcpu, cpu_addr, - &vcpu->run->s.regs.gprs[r1]); + rc = __sigp_sense_running(vcpu, dst_vcpu, status_reg); break; case SIGP_START: - rc = sigp_check_callable(vcpu, cpu_addr); - if (rc == SIGP_CC_ORDER_CODE_ACCEPTED) - rc = -EOPNOTSUPP; /* Handle START in user space */ + vcpu->stat.instruction_sigp_start++; + rc = __prepare_sigp_re_start(vcpu, dst_vcpu, order_code); break; case SIGP_RESTART: vcpu->stat.instruction_sigp_restart++; - rc = sigp_check_callable(vcpu, cpu_addr); - if (rc == SIGP_CC_ORDER_CODE_ACCEPTED) { - VCPU_EVENT(vcpu, 4, - "sigp restart %x to handle userspace", - cpu_addr); - /* user space must know about restart */ - rc = -EOPNOTSUPP; - } + rc = __prepare_sigp_re_start(vcpu, dst_vcpu, order_code); + break; + case SIGP_INITIAL_CPU_RESET: + vcpu->stat.instruction_sigp_init_cpu_reset++; + rc = __prepare_sigp_cpu_reset(vcpu, dst_vcpu, order_code); + break; + case SIGP_CPU_RESET: + vcpu->stat.instruction_sigp_cpu_reset++; + rc = __prepare_sigp_cpu_reset(vcpu, dst_vcpu, order_code); + break; + default: + vcpu->stat.instruction_sigp_unknown++; + rc = __prepare_sigp_unknown(vcpu, dst_vcpu); + } + + if (rc == -EOPNOTSUPP) + VCPU_EVENT(vcpu, 4, + "sigp order %u -> cpu %x: handled in user space", + order_code, dst_vcpu->vcpu_id); + + return rc; +} + +int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu) +{ + int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4; + int r3 = vcpu->arch.sie_block->ipa & 0x000f; + u32 parameter; + u16 cpu_addr = vcpu->run->s.regs.gprs[r3]; + u8 order_code; + int rc; + + /* sigp in userspace can exit */ + if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) + return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); + + order_code = kvm_s390_get_base_disp_rs(vcpu); + + if (r1 % 2) + parameter = vcpu->run->s.regs.gprs[r1]; + else + parameter = vcpu->run->s.regs.gprs[r1 + 1]; + + trace_kvm_s390_handle_sigp(vcpu, order_code, cpu_addr, parameter); + switch (order_code) { + case SIGP_SET_ARCHITECTURE: + vcpu->stat.instruction_sigp_arch++; + rc = __sigp_set_arch(vcpu, parameter); break; default: - return -EOPNOTSUPP; + rc = handle_sigp_dst(vcpu, order_code, cpu_addr, + parameter, + &vcpu->run->s.regs.gprs[r1]); } if (rc < 0) diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index a2b81d6ce8a5..811937bb90be 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/maccess.c b/arch/s390/mm/maccess.c index 2a2e35416d2f..2eb34bdfc613 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -176,7 +176,7 @@ static int is_swapped(unsigned long addr) * For swapped prefix pages a new buffer is returned that contains a copy of * the absolute memory. The buffer size is maximum one page large. */ -void *xlate_dev_mem_ptr(unsigned long addr) +void *xlate_dev_mem_ptr(phys_addr_t addr) { void *bounce = (void *) addr; unsigned long size; @@ -197,7 +197,7 @@ void *xlate_dev_mem_ptr(unsigned long addr) /* * Free converted buffer for /dev/mem access (if necessary) */ -void unxlate_dev_mem_ptr(unsigned long addr, void *buf) +void unxlate_dev_mem_ptr(phys_addr_t addr, void *buf) { if ((void *) addr != buf) free_page((unsigned long) buf); diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 3fef3b299665..426c9d462d1c 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -120,7 +120,7 @@ static void ipte_range(pte_t *pte, unsigned long address, int nr) } } -void kernel_map_pages(struct page *page, int numpages, int enable) +void __kernel_map_pages(struct page *page, int numpages, int enable) { unsigned long address; int nr, i, j; diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 1b79ca67392f..be99357d238c 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) { @@ -936,7 +844,7 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, down_read(&mm->mmap_sem); retry: - ptep = get_locked_pte(current->mm, addr, &ptl); + ptep = get_locked_pte(mm, addr, &ptl); if (unlikely(!ptep)) { up_read(&mm->mmap_sem); return -EFAULT; @@ -980,6 +888,45 @@ retry: } EXPORT_SYMBOL(set_guest_storage_key); +unsigned long get_guest_storage_key(struct mm_struct *mm, unsigned long addr) +{ + spinlock_t *ptl; + pgste_t pgste; + pte_t *ptep; + uint64_t physaddr; + unsigned long key = 0; + + down_read(&mm->mmap_sem); + ptep = get_locked_pte(mm, addr, &ptl); + if (unlikely(!ptep)) { + up_read(&mm->mmap_sem); + return -EFAULT; + } + pgste = pgste_get_lock(ptep); + + if (pte_val(*ptep) & _PAGE_INVALID) { + key |= (pgste_val(pgste) & PGSTE_ACC_BITS) >> 56; + key |= (pgste_val(pgste) & PGSTE_FP_BIT) >> 56; + key |= (pgste_val(pgste) & PGSTE_GR_BIT) >> 48; + key |= (pgste_val(pgste) & PGSTE_GC_BIT) >> 48; + } else { + physaddr = pte_val(*ptep) & PAGE_MASK; + key = page_get_storage_key(physaddr); + + /* Reflect guest's logical view, not physical */ + if (pgste_val(pgste) & PGSTE_GR_BIT) + key |= _PAGE_REFERENCED; + if (pgste_val(pgste) & PGSTE_GC_BIT) + key |= _PAGE_CHANGED; + } + + pgste_set_unlock(ptep, pgste); + pte_unmap_unlock(ptep, ptl); + up_read(&mm->mmap_sem); + return key; +} +EXPORT_SYMBOL(get_guest_storage_key); + #else /* CONFIG_PGSTE */ static inline int page_table_with_pgste(struct page *page) @@ -992,11 +939,6 @@ 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 +1289,89 @@ 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) diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile index a9e1dc4ae442..805d8b29193a 100644 --- a/arch/s390/pci/Makefile +++ b/arch/s390/pci/Makefile @@ -3,4 +3,4 @@ # obj-$(CONFIG_PCI) += pci.o pci_dma.o pci_clp.o pci_sysfs.o \ - pci_event.o pci_debug.o pci_insn.o + pci_event.o pci_debug.o pci_insn.o pci_mmio.o diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 2fa7b14b9c08..3290f11ae1d9 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -50,8 +50,8 @@ static DEFINE_SPINLOCK(zpci_list_lock); static struct irq_chip zpci_irq_chip = { .name = "zPCI", - .irq_unmask = unmask_msi_irq, - .irq_mask = mask_msi_irq, + .irq_unmask = pci_msi_unmask_irq, + .irq_mask = pci_msi_mask_irq, }; static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES); @@ -369,8 +369,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) if (type == PCI_CAP_ID_MSI && nvec > 1) return 1; - msi_vecs = min(nvec, ZPCI_MSI_VEC_MAX); - msi_vecs = min_t(unsigned int, msi_vecs, CONFIG_PCI_NR_MSI); + msi_vecs = min_t(unsigned int, nvec, zdev->max_msi); /* Allocate adapter summary indicator bit */ rc = -EIO; @@ -403,7 +402,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) msg.data = hwirq; msg.address_lo = zdev->msi_addr & 0xffffffff; msg.address_hi = zdev->msi_addr >> 32; - write_msi_msg(irq, &msg); + pci_write_msi_msg(irq, &msg); airq_iv_set_data(zdev->aibv, hwirq, irq); hwirq++; } @@ -448,9 +447,9 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev) /* Release MSI interrupts */ list_for_each_entry(msi, &pdev->msi_list, list) { if (msi->msi_attrib.is_msix) - default_msix_mask_irq(msi, 1); + __pci_msix_desc_mask_irq(msi, 1); else - default_msi_mask_irq(msi, 1, 1); + __pci_msi_desc_mask_irq(msi, 1, 1); irq_set_msi_desc(msi->irq, NULL); irq_free_desc(msi->irq); msi->msg.address_lo = 0; @@ -474,7 +473,8 @@ static void zpci_map_resources(struct zpci_dev *zdev) len = pci_resource_len(pdev, i); if (!len) continue; - pdev->resource[i].start = (resource_size_t) pci_iomap(pdev, i, 0); + pdev->resource[i].start = + (resource_size_t __force) pci_iomap(pdev, i, 0); pdev->resource[i].end = pdev->resource[i].start + len - 1; } } @@ -489,7 +489,8 @@ static void zpci_unmap_resources(struct zpci_dev *zdev) len = pci_resource_len(pdev, i); if (!len) continue; - pci_iounmap(pdev, (void *) pdev->resource[i].start); + pci_iounmap(pdev, (void __iomem __force *) + pdev->resource[i].start); } } diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 6e22a247de9b..d6e411ed8b1f 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -62,6 +62,7 @@ static void clp_store_query_pci_fngrp(struct zpci_dev *zdev, zdev->tlb_refresh = response->refresh; zdev->dma_mask = response->dasm; zdev->msi_addr = response->msia; + zdev->max_msi = response->noi; zdev->fmb_update = response->mui; switch (response->version) { diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c index eec598c5939f..3229a2e570df 100644 --- a/arch/s390/pci/pci_debug.c +++ b/arch/s390/pci/pci_debug.c @@ -158,10 +158,7 @@ int __init zpci_debug_init(void) void zpci_debug_exit(void) { - if (pci_debug_msg_id) - debug_unregister(pci_debug_msg_id); - if (pci_debug_err_id) - debug_unregister(pci_debug_err_id); - + debug_unregister(pci_debug_msg_id); + debug_unregister(pci_debug_err_id); debugfs_remove(debugfs_root); } diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c new file mode 100644 index 000000000000..62c5ea6d8682 --- /dev/null +++ b/arch/s390/pci/pci_mmio.c @@ -0,0 +1,115 @@ +/* + * Access to PCI I/O memory from user space programs. + * + * Copyright IBM Corp. 2014 + * Author(s): Alexey Ishchuk <aishchuk@linux.vnet.ibm.com> + */ +#include <linux/kernel.h> +#include <linux/syscalls.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/errno.h> +#include <linux/pci.h> + +static long get_pfn(unsigned long user_addr, unsigned long access, + unsigned long *pfn) +{ + struct vm_area_struct *vma; + long ret; + + down_read(¤t->mm->mmap_sem); + ret = -EINVAL; + vma = find_vma(current->mm, user_addr); + if (!vma) + goto out; + ret = -EACCES; + if (!(vma->vm_flags & access)) + goto out; + ret = follow_pfn(vma, user_addr, pfn); +out: + up_read(¤t->mm->mmap_sem); + return ret; +} + +SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr, + const void __user *, user_buffer, size_t, length) +{ + u8 local_buf[64]; + void __iomem *io_addr; + void *buf; + unsigned long pfn; + long ret; + + if (!zpci_is_enabled()) + return -ENODEV; + + if (length <= 0 || PAGE_SIZE - (mmio_addr & ~PAGE_MASK) < length) + return -EINVAL; + if (length > 64) { + buf = kmalloc(length, GFP_KERNEL); + if (!buf) + return -ENOMEM; + } else + buf = local_buf; + + ret = get_pfn(mmio_addr, VM_WRITE, &pfn); + if (ret) + goto out; + io_addr = (void *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK)); + + ret = -EFAULT; + if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE) + goto out; + + if (copy_from_user(buf, user_buffer, length)) + goto out; + + memcpy_toio(io_addr, buf, length); + ret = 0; +out: + if (buf != local_buf) + kfree(buf); + return ret; +} + +SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr, + void __user *, user_buffer, size_t, length) +{ + u8 local_buf[64]; + void __iomem *io_addr; + void *buf; + unsigned long pfn; + long ret; + + if (!zpci_is_enabled()) + return -ENODEV; + + if (length <= 0 || PAGE_SIZE - (mmio_addr & ~PAGE_MASK) < length) + return -EINVAL; + if (length > 64) { + buf = kmalloc(length, GFP_KERNEL); + if (!buf) + return -ENOMEM; + } else + buf = local_buf; + + ret = get_pfn(mmio_addr, VM_READ, &pfn); + if (ret) + goto out; + io_addr = (void *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK)); + + ret = -EFAULT; + if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE) + goto out; + + memcpy_fromio(buf, io_addr, length); + + if (copy_to_user(user_buffer, buf, length)) + goto out; + + ret = 0; +out: + if (buf != local_buf) + kfree(buf); + return ret; +} |