diff options
Diffstat (limited to 'src/include/qemu')
48 files changed, 7394 insertions, 0 deletions
diff --git a/src/include/qemu/acl.h b/src/include/qemu/acl.h new file mode 100644 index 0000000..116487e --- /dev/null +++ b/src/include/qemu/acl.h @@ -0,0 +1,74 @@ +/* + * QEMU access control list management + * + * Copyright (C) 2009 Red Hat, Inc + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef __QEMU_ACL_H__ +#define __QEMU_ACL_H__ + +#include "qemu/queue.h" + +typedef struct qemu_acl_entry qemu_acl_entry; +typedef struct qemu_acl qemu_acl; + +struct qemu_acl_entry { + char *match; + int deny; + + QTAILQ_ENTRY(qemu_acl_entry) next; +}; + +struct qemu_acl { + char *aclname; + unsigned int nentries; + QTAILQ_HEAD(,qemu_acl_entry) entries; + int defaultDeny; +}; + +qemu_acl *qemu_acl_init(const char *aclname); + +qemu_acl *qemu_acl_find(const char *aclname); + +int qemu_acl_party_is_allowed(qemu_acl *acl, + const char *party); + +void qemu_acl_reset(qemu_acl *acl); + +int qemu_acl_append(qemu_acl *acl, + int deny, + const char *match); +int qemu_acl_insert(qemu_acl *acl, + int deny, + const char *match, + int index); +int qemu_acl_remove(qemu_acl *acl, + const char *match); + +#endif /* __QEMU_ACL_H__ */ + +/* + * Local variables: + * c-indent-level: 4 + * c-basic-offset: 4 + * tab-width: 8 + * End: + */ diff --git a/src/include/qemu/atomic.h b/src/include/qemu/atomic.h new file mode 100644 index 0000000..e2125bd --- /dev/null +++ b/src/include/qemu/atomic.h @@ -0,0 +1,269 @@ +/* + * Simple interface for atomic operations. + * + * Copyright (C) 2013 Red Hat, Inc. + * + * Author: Paolo Bonzini <pbonzini@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef __QEMU_ATOMIC_H +#define __QEMU_ATOMIC_H 1 + +#include "qemu/compiler.h" + +/* For C11 atomic ops */ + +/* Compiler barrier */ +#define barrier() ({ asm volatile("" ::: "memory"); (void)0; }) + +#ifndef __ATOMIC_RELAXED + +/* + * We use GCC builtin if it's available, as that can use mfence on + * 32-bit as well, e.g. if built with -march=pentium-m. However, on + * i386 the spec is buggy, and the implementation followed it until + * 4.3 (http://gcc.gnu.org/bugzilla/show_bug.cgi?id=36793). + */ +#if defined(__i386__) || defined(__x86_64__) +#if !QEMU_GNUC_PREREQ(4, 4) +#if defined __x86_64__ +#define smp_mb() ({ asm volatile("mfence" ::: "memory"); (void)0; }) +#else +#define smp_mb() ({ asm volatile("lock; addl $0,0(%%esp) " ::: "memory"); (void)0; }) +#endif +#endif +#endif + + +#ifdef __alpha__ +#define smp_read_barrier_depends() asm volatile("mb":::"memory") +#endif + +#if defined(__i386__) || defined(__x86_64__) || defined(__s390x__) + +/* + * Because of the strongly ordered storage model, wmb() and rmb() are nops + * here (a compiler barrier only). QEMU doesn't do accesses to write-combining + * qemu memory or non-temporal load/stores from C code. + */ +#define smp_wmb() barrier() +#define smp_rmb() barrier() + +/* + * __sync_lock_test_and_set() is documented to be an acquire barrier only, + * but it is a full barrier at the hardware level. Add a compiler barrier + * to make it a full barrier also at the compiler level. + */ +#define atomic_xchg(ptr, i) (barrier(), __sync_lock_test_and_set(ptr, i)) + +/* + * Load/store with Java volatile semantics. + */ +#define atomic_mb_set(ptr, i) ((void)atomic_xchg(ptr, i)) + +#elif defined(_ARCH_PPC) + +/* + * We use an eieio() for wmb() on powerpc. This assumes we don't + * need to order cacheable and non-cacheable stores with respect to + * each other. + * + * smp_mb has the same problem as on x86 for not-very-new GCC + * (http://patchwork.ozlabs.org/patch/126184/, Nov 2011). + */ +#define smp_wmb() ({ asm volatile("eieio" ::: "memory"); (void)0; }) +#if defined(__powerpc64__) +#define smp_rmb() ({ asm volatile("lwsync" ::: "memory"); (void)0; }) +#else +#define smp_rmb() ({ asm volatile("sync" ::: "memory"); (void)0; }) +#endif +#define smp_mb() ({ asm volatile("sync" ::: "memory"); (void)0; }) + +#endif /* _ARCH_PPC */ + +#endif /* C11 atomics */ + +/* + * For (host) platforms we don't have explicit barrier definitions + * for, we use the gcc __sync_synchronize() primitive to generate a + * full barrier. This should be safe on all platforms, though it may + * be overkill for smp_wmb() and smp_rmb(). + */ +#ifndef smp_mb +#define smp_mb() __sync_synchronize() +#endif + +#ifndef smp_wmb +#ifdef __ATOMIC_RELEASE +/* __atomic_thread_fence does not include a compiler barrier; instead, + * the barrier is part of __atomic_load/__atomic_store's "volatile-like" + * semantics. If smp_wmb() is a no-op, absence of the barrier means that + * the compiler is free to reorder stores on each side of the barrier. + * Add one here, and similarly in smp_rmb() and smp_read_barrier_depends(). + */ +#define smp_wmb() ({ barrier(); __atomic_thread_fence(__ATOMIC_RELEASE); barrier(); }) +#else +#define smp_wmb() __sync_synchronize() +#endif +#endif + +#ifndef smp_rmb +#ifdef __ATOMIC_ACQUIRE +#define smp_rmb() ({ barrier(); __atomic_thread_fence(__ATOMIC_ACQUIRE); barrier(); }) +#else +#define smp_rmb() __sync_synchronize() +#endif +#endif + +#ifndef smp_read_barrier_depends +#ifdef __ATOMIC_CONSUME +#define smp_read_barrier_depends() ({ barrier(); __atomic_thread_fence(__ATOMIC_CONSUME); barrier(); }) +#else +#define smp_read_barrier_depends() barrier() +#endif +#endif + +#ifndef atomic_read +#define atomic_read(ptr) (*(__typeof__(*ptr) volatile*) (ptr)) +#endif + +#ifndef atomic_set +#define atomic_set(ptr, i) ((*(__typeof__(*ptr) volatile*) (ptr)) = (i)) +#endif + +/** + * atomic_rcu_read - reads a RCU-protected pointer to a local variable + * into a RCU read-side critical section. The pointer can later be safely + * dereferenced within the critical section. + * + * This ensures that the pointer copy is invariant thorough the whole critical + * section. + * + * Inserts memory barriers on architectures that require them (currently only + * Alpha) and documents which pointers are protected by RCU. + * + * Unless the __ATOMIC_CONSUME memory order is available, atomic_rcu_read also + * includes a compiler barrier to ensure that value-speculative optimizations + * (e.g. VSS: Value Speculation Scheduling) does not perform the data read + * before the pointer read by speculating the value of the pointer. On new + * enough compilers, atomic_load takes care of such concern about + * dependency-breaking optimizations. + * + * Should match atomic_rcu_set(), atomic_xchg(), atomic_cmpxchg(). + */ +#ifndef atomic_rcu_read +#ifdef __ATOMIC_CONSUME +#define atomic_rcu_read(ptr) ({ \ + __typeof__(*ptr) _val; \ + __atomic_load(ptr, &_val, __ATOMIC_CONSUME); \ + _val; \ +}) +#else +#define atomic_rcu_read(ptr) ({ \ + __typeof__(*ptr) _val = atomic_read(ptr); \ + smp_read_barrier_depends(); \ + _val; \ +}) +#endif +#endif + +/** + * atomic_rcu_set - assigns (publicizes) a pointer to a new data structure + * meant to be read by RCU read-side critical sections. + * + * Documents which pointers will be dereferenced by RCU read-side critical + * sections and adds the required memory barriers on architectures requiring + * them. It also makes sure the compiler does not reorder code initializing the + * data structure before its publication. + * + * Should match atomic_rcu_read(). + */ +#ifndef atomic_rcu_set +#ifdef __ATOMIC_RELEASE +#define atomic_rcu_set(ptr, i) do { \ + __typeof__(*ptr) _val = (i); \ + __atomic_store(ptr, &_val, __ATOMIC_RELEASE); \ +} while(0) +#else +#define atomic_rcu_set(ptr, i) do { \ + smp_wmb(); \ + atomic_set(ptr, i); \ +} while (0) +#endif +#endif + +/* These have the same semantics as Java volatile variables. + * See http://gee.cs.oswego.edu/dl/jmm/cookbook.html: + * "1. Issue a StoreStore barrier (wmb) before each volatile store." + * 2. Issue a StoreLoad barrier after each volatile store. + * Note that you could instead issue one before each volatile load, but + * this would be slower for typical programs using volatiles in which + * reads greatly outnumber writes. Alternatively, if available, you + * can implement volatile store as an atomic instruction (for example + * XCHG on x86) and omit the barrier. This may be more efficient if + * atomic instructions are cheaper than StoreLoad barriers. + * 3. Issue LoadLoad and LoadStore barriers after each volatile load." + * + * If you prefer to think in terms of "pairing" of memory barriers, + * an atomic_mb_read pairs with an atomic_mb_set. + * + * And for the few ia64 lovers that exist, an atomic_mb_read is a ld.acq, + * while an atomic_mb_set is a st.rel followed by a memory barrier. + * + * These are a bit weaker than __atomic_load/store with __ATOMIC_SEQ_CST + * (see docs/atomics.txt), and I'm not sure that __ATOMIC_ACQ_REL is enough. + * Just always use the barriers manually by the rules above. + */ +#ifndef atomic_mb_read +#define atomic_mb_read(ptr) ({ \ + __typeof__(*ptr) _val = atomic_read(ptr); \ + smp_rmb(); \ + _val; \ +}) +#endif + +#ifndef atomic_mb_set +#define atomic_mb_set(ptr, i) do { \ + smp_wmb(); \ + atomic_set(ptr, i); \ + smp_mb(); \ +} while (0) +#endif + +#ifndef atomic_xchg +#if defined(__clang__) +#define atomic_xchg(ptr, i) __sync_swap(ptr, i) +#elif defined(__ATOMIC_SEQ_CST) +#define atomic_xchg(ptr, i) ({ \ + __typeof__(*ptr) _new = (i), _old; \ + __atomic_exchange(ptr, &_new, &_old, __ATOMIC_SEQ_CST); \ + _old; \ +}) +#else +/* __sync_lock_test_and_set() is documented to be an acquire barrier only. */ +#define atomic_xchg(ptr, i) (smp_mb(), __sync_lock_test_and_set(ptr, i)) +#endif +#endif + +/* Provide shorter names for GCC atomic builtins. */ +#define atomic_fetch_inc(ptr) __sync_fetch_and_add(ptr, 1) +#define atomic_fetch_dec(ptr) __sync_fetch_and_add(ptr, -1) +#define atomic_fetch_add __sync_fetch_and_add +#define atomic_fetch_sub __sync_fetch_and_sub +#define atomic_fetch_and __sync_fetch_and_and +#define atomic_fetch_or __sync_fetch_and_or +#define atomic_cmpxchg __sync_val_compare_and_swap + +/* And even shorter names that return void. */ +#define atomic_inc(ptr) ((void) __sync_fetch_and_add(ptr, 1)) +#define atomic_dec(ptr) ((void) __sync_fetch_and_add(ptr, -1)) +#define atomic_add(ptr, n) ((void) __sync_fetch_and_add(ptr, n)) +#define atomic_sub(ptr, n) ((void) __sync_fetch_and_sub(ptr, n)) +#define atomic_and(ptr, n) ((void) __sync_fetch_and_and(ptr, n)) +#define atomic_or(ptr, n) ((void) __sync_fetch_and_or(ptr, n)) + +#endif diff --git a/src/include/qemu/bitmap.h b/src/include/qemu/bitmap.h new file mode 100644 index 0000000..b53f462 --- /dev/null +++ b/src/include/qemu/bitmap.h @@ -0,0 +1,249 @@ +/* + * Bitmap Module + * + * Copyright (C) 2010 Corentin Chary <corentin.chary@gmail.com> + * + * Mostly inspired by (stolen from) linux/bitmap.h and linux/bitops.h + * + * This work is licensed under the terms of the GNU LGPL, version 2.1 or later. + * See the COPYING.LIB file in the top-level directory. + */ + +#ifndef BITMAP_H +#define BITMAP_H + +#include <glib.h> +#include <string.h> +#include <stdlib.h> + +#include "qemu/osdep.h" +#include "qemu/bitops.h" + +/* + * The available bitmap operations and their rough meaning in the + * case that the bitmap is a single unsigned long are thus: + * + * Note that nbits should be always a compile time evaluable constant. + * Otherwise many inlines will generate horrible code. + * + * bitmap_zero(dst, nbits) *dst = 0UL + * bitmap_fill(dst, nbits) *dst = ~0UL + * bitmap_copy(dst, src, nbits) *dst = *src + * bitmap_and(dst, src1, src2, nbits) *dst = *src1 & *src2 + * bitmap_or(dst, src1, src2, nbits) *dst = *src1 | *src2 + * bitmap_xor(dst, src1, src2, nbits) *dst = *src1 ^ *src2 + * bitmap_andnot(dst, src1, src2, nbits) *dst = *src1 & ~(*src2) + * bitmap_complement(dst, src, nbits) *dst = ~(*src) + * bitmap_equal(src1, src2, nbits) Are *src1 and *src2 equal? + * bitmap_intersects(src1, src2, nbits) Do *src1 and *src2 overlap? + * bitmap_empty(src, nbits) Are all bits zero in *src? + * bitmap_full(src, nbits) Are all bits set in *src? + * bitmap_set(dst, pos, nbits) Set specified bit area + * bitmap_set_atomic(dst, pos, nbits) Set specified bit area with atomic ops + * bitmap_clear(dst, pos, nbits) Clear specified bit area + * bitmap_test_and_clear_atomic(dst, pos, nbits) Test and clear area + * bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area + */ + +/* + * Also the following operations apply to bitmaps. + * + * set_bit(bit, addr) *addr |= bit + * clear_bit(bit, addr) *addr &= ~bit + * change_bit(bit, addr) *addr ^= bit + * test_bit(bit, addr) Is bit set in *addr? + * test_and_set_bit(bit, addr) Set bit and return old value + * test_and_clear_bit(bit, addr) Clear bit and return old value + * test_and_change_bit(bit, addr) Change bit and return old value + * find_first_zero_bit(addr, nbits) Position first zero bit in *addr + * find_first_bit(addr, nbits) Position first set bit in *addr + * find_next_zero_bit(addr, nbits, bit) Position next zero bit in *addr >= bit + * find_next_bit(addr, nbits, bit) Position next set bit in *addr >= bit + */ + +#define BITMAP_LAST_WORD_MASK(nbits) \ + ( \ + ((nbits) % BITS_PER_LONG) ? \ + (1UL<<((nbits) % BITS_PER_LONG))-1 : ~0UL \ + ) + +#define DECLARE_BITMAP(name,bits) \ + unsigned long name[BITS_TO_LONGS(bits)] + +#define small_nbits(nbits) \ + ((nbits) <= (long)BITS_PER_LONG) + +int slow_bitmap_empty(const unsigned long *bitmap, long bits); +int slow_bitmap_full(const unsigned long *bitmap, long bits); +int slow_bitmap_equal(const unsigned long *bitmap1, + const unsigned long *bitmap2, long bits); +void slow_bitmap_complement(unsigned long *dst, const unsigned long *src, + long bits); +void slow_bitmap_shift_right(unsigned long *dst, + const unsigned long *src, int shift, long bits); +void slow_bitmap_shift_left(unsigned long *dst, + const unsigned long *src, int shift, long bits); +int slow_bitmap_and(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, long bits); +void slow_bitmap_or(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, long bits); +void slow_bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, long bits); +int slow_bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, long bits); +int slow_bitmap_intersects(const unsigned long *bitmap1, + const unsigned long *bitmap2, long bits); + +static inline unsigned long *bitmap_try_new(long nbits) +{ + long len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + return (unsigned long *)g_try_malloc0(len); +} + +static inline unsigned long *bitmap_new(long nbits) +{ + unsigned long *ptr = bitmap_try_new(nbits); + if (ptr == NULL) { + abort(); + } + return ptr; +} + +static inline void bitmap_zero(unsigned long *dst, long nbits) +{ + if (small_nbits(nbits)) { + *dst = 0UL; + } else { + long len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + memset(dst, 0, len); + } +} + +static inline void bitmap_fill(unsigned long *dst, long nbits) +{ + size_t nlongs = BITS_TO_LONGS(nbits); + if (!small_nbits(nbits)) { + long len = (nlongs - 1) * sizeof(unsigned long); + memset(dst, 0xff, len); + } + dst[nlongs - 1] = BITMAP_LAST_WORD_MASK(nbits); +} + +static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, + long nbits) +{ + if (small_nbits(nbits)) { + *dst = *src; + } else { + long len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + memcpy(dst, src, len); + } +} + +static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, long nbits) +{ + if (small_nbits(nbits)) { + return (*dst = *src1 & *src2) != 0; + } + return slow_bitmap_and(dst, src1, src2, nbits); +} + +static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, long nbits) +{ + if (small_nbits(nbits)) { + *dst = *src1 | *src2; + } else { + slow_bitmap_or(dst, src1, src2, nbits); + } +} + +static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, long nbits) +{ + if (small_nbits(nbits)) { + *dst = *src1 ^ *src2; + } else { + slow_bitmap_xor(dst, src1, src2, nbits); + } +} + +static inline int bitmap_andnot(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, long nbits) +{ + if (small_nbits(nbits)) { + return (*dst = *src1 & ~(*src2)) != 0; + } + return slow_bitmap_andnot(dst, src1, src2, nbits); +} + +static inline void bitmap_complement(unsigned long *dst, + const unsigned long *src, + long nbits) +{ + if (small_nbits(nbits)) { + *dst = ~(*src) & BITMAP_LAST_WORD_MASK(nbits); + } else { + slow_bitmap_complement(dst, src, nbits); + } +} + +static inline int bitmap_equal(const unsigned long *src1, + const unsigned long *src2, long nbits) +{ + if (small_nbits(nbits)) { + return ! ((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); + } else { + return slow_bitmap_equal(src1, src2, nbits); + } +} + +static inline int bitmap_empty(const unsigned long *src, long nbits) +{ + if (small_nbits(nbits)) { + return ! (*src & BITMAP_LAST_WORD_MASK(nbits)); + } else { + return slow_bitmap_empty(src, nbits); + } +} + +static inline int bitmap_full(const unsigned long *src, long nbits) +{ + if (small_nbits(nbits)) { + return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits)); + } else { + return slow_bitmap_full(src, nbits); + } +} + +static inline int bitmap_intersects(const unsigned long *src1, + const unsigned long *src2, long nbits) +{ + if (small_nbits(nbits)) { + return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; + } else { + return slow_bitmap_intersects(src1, src2, nbits); + } +} + +void bitmap_set(unsigned long *map, long i, long len); +void bitmap_set_atomic(unsigned long *map, long i, long len); +void bitmap_clear(unsigned long *map, long start, long nr); +bool bitmap_test_and_clear_atomic(unsigned long *map, long start, long nr); +unsigned long bitmap_find_next_zero_area(unsigned long *map, + unsigned long size, + unsigned long start, + unsigned long nr, + unsigned long align_mask); + +static inline unsigned long *bitmap_zero_extend(unsigned long *old, + long old_nbits, long new_nbits) +{ + long new_len = BITS_TO_LONGS(new_nbits) * sizeof(unsigned long); + unsigned long *new_bitmap = (unsigned long *)g_realloc(old, new_len); + bitmap_clear(new_bitmap, old_nbits, new_nbits - old_nbits); + return new_bitmap; +} + +#endif /* BITMAP_H */ diff --git a/src/include/qemu/bitops.h b/src/include/qemu/bitops.h new file mode 100644 index 0000000..8164225 --- /dev/null +++ b/src/include/qemu/bitops.h @@ -0,0 +1,433 @@ +/* + * Bitops Module + * + * Copyright (C) 2010 Corentin Chary <corentin.chary@gmail.com> + * + * Mostly inspired by (stolen from) linux/bitmap.h and linux/bitops.h + * + * This work is licensed under the terms of the GNU LGPL, version 2.1 or later. + * See the COPYING.LIB file in the top-level directory. + */ + +#ifndef BITOPS_H +#define BITOPS_H + +#include <stdint.h> +#include <assert.h> + +#include "host-utils.h" +#include "atomic.h" + +#define BITS_PER_BYTE CHAR_BIT +#define BITS_PER_LONG (sizeof (unsigned long) * BITS_PER_BYTE) + +#define BIT(nr) (1UL << (nr)) +#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) +#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) +#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) + +/** + * set_bit - Set a bit in memory + * @nr: the bit to set + * @addr: the address to start counting from + */ +static inline void set_bit(long nr, unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = addr + BIT_WORD(nr); + + *p |= mask; +} + +/** + * set_bit_atomic - Set a bit in memory atomically + * @nr: the bit to set + * @addr: the address to start counting from + */ +static inline void set_bit_atomic(long nr, unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = addr + BIT_WORD(nr); + + atomic_or(p, mask); +} + +/** + * clear_bit - Clears a bit in memory + * @nr: Bit to clear + * @addr: Address to start counting from + */ +static inline void clear_bit(long nr, unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = addr + BIT_WORD(nr); + + *p &= ~mask; +} + +/** + * change_bit - Toggle a bit in memory + * @nr: Bit to change + * @addr: Address to start counting from + */ +static inline void change_bit(long nr, unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = addr + BIT_WORD(nr); + + *p ^= mask; +} + +/** + * test_and_set_bit - Set a bit and return its old value + * @nr: Bit to set + * @addr: Address to count from + */ +static inline int test_and_set_bit(long nr, unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = addr + BIT_WORD(nr); + unsigned long old = *p; + + *p = old | mask; + return (old & mask) != 0; +} + +/** + * test_and_clear_bit - Clear a bit and return its old value + * @nr: Bit to clear + * @addr: Address to count from + */ +static inline int test_and_clear_bit(long nr, unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = addr + BIT_WORD(nr); + unsigned long old = *p; + + *p = old & ~mask; + return (old & mask) != 0; +} + +/** + * test_and_change_bit - Change a bit and return its old value + * @nr: Bit to change + * @addr: Address to count from + */ +static inline int test_and_change_bit(long nr, unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = addr + BIT_WORD(nr); + unsigned long old = *p; + + *p = old ^ mask; + return (old & mask) != 0; +} + +/** + * test_bit - Determine whether a bit is set + * @nr: bit number to test + * @addr: Address to start counting from + */ +static inline int test_bit(long nr, const unsigned long *addr) +{ + return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); +} + +/** + * find_last_bit - find the last set bit in a memory region + * @addr: The address to start the search at + * @size: The maximum size to search + * + * Returns the bit number of the first set bit, or size. + */ +unsigned long find_last_bit(const unsigned long *addr, + unsigned long size); + +/** + * find_next_bit - find the next set bit in a memory region + * @addr: The address to base the search on + * @offset: The bitnumber to start searching at + * @size: The bitmap size in bits + */ +unsigned long find_next_bit(const unsigned long *addr, + unsigned long size, + unsigned long offset); + +/** + * find_next_zero_bit - find the next cleared bit in a memory region + * @addr: The address to base the search on + * @offset: The bitnumber to start searching at + * @size: The bitmap size in bits + */ + +unsigned long find_next_zero_bit(const unsigned long *addr, + unsigned long size, + unsigned long offset); + +/** + * find_first_bit - find the first set bit in a memory region + * @addr: The address to start the search at + * @size: The maximum size to search + * + * Returns the bit number of the first set bit. + */ +static inline unsigned long find_first_bit(const unsigned long *addr, + unsigned long size) +{ + unsigned long result, tmp; + + for (result = 0; result < size; result += BITS_PER_LONG) { + tmp = *addr++; + if (tmp) { + result += ctzl(tmp); + return result < size ? result : size; + } + } + /* Not found */ + return size; +} + +/** + * find_first_zero_bit - find the first cleared bit in a memory region + * @addr: The address to start the search at + * @size: The maximum size to search + * + * Returns the bit number of the first cleared bit. + */ +static inline unsigned long find_first_zero_bit(const unsigned long *addr, + unsigned long size) +{ + return find_next_zero_bit(addr, size, 0); +} + +static inline unsigned long hweight_long(unsigned long w) +{ + unsigned long count; + + for (count = 0; w; w >>= 1) { + count += w & 1; + } + return count; +} + +/** + * rol8 - rotate an 8-bit value left + * @word: value to rotate + * @shift: bits to roll + */ +static inline uint8_t rol8(uint8_t word, unsigned int shift) +{ + return (word << shift) | (word >> (8 - shift)); +} + +/** + * ror8 - rotate an 8-bit value right + * @word: value to rotate + * @shift: bits to roll + */ +static inline uint8_t ror8(uint8_t word, unsigned int shift) +{ + return (word >> shift) | (word << (8 - shift)); +} + +/** + * rol16 - rotate a 16-bit value left + * @word: value to rotate + * @shift: bits to roll + */ +static inline uint16_t rol16(uint16_t word, unsigned int shift) +{ + return (word << shift) | (word >> (16 - shift)); +} + +/** + * ror16 - rotate a 16-bit value right + * @word: value to rotate + * @shift: bits to roll + */ +static inline uint16_t ror16(uint16_t word, unsigned int shift) +{ + return (word >> shift) | (word << (16 - shift)); +} + +/** + * rol32 - rotate a 32-bit value left + * @word: value to rotate + * @shift: bits to roll + */ +static inline uint32_t rol32(uint32_t word, unsigned int shift) +{ + return (word << shift) | (word >> (32 - shift)); +} + +/** + * ror32 - rotate a 32-bit value right + * @word: value to rotate + * @shift: bits to roll + */ +static inline uint32_t ror32(uint32_t word, unsigned int shift) +{ + return (word >> shift) | (word << (32 - shift)); +} + +/** + * rol64 - rotate a 64-bit value left + * @word: value to rotate + * @shift: bits to roll + */ +static inline uint64_t rol64(uint64_t word, unsigned int shift) +{ + return (word << shift) | (word >> (64 - shift)); +} + +/** + * ror64 - rotate a 64-bit value right + * @word: value to rotate + * @shift: bits to roll + */ +static inline uint64_t ror64(uint64_t word, unsigned int shift) +{ + return (word >> shift) | (word << (64 - shift)); +} + +/** + * extract32: + * @value: the value to extract the bit field from + * @start: the lowest bit in the bit field (numbered from 0) + * @length: the length of the bit field + * + * Extract from the 32 bit input @value the bit field specified by the + * @start and @length parameters, and return it. The bit field must + * lie entirely within the 32 bit word. It is valid to request that + * all 32 bits are returned (ie @length 32 and @start 0). + * + * Returns: the value of the bit field extracted from the input value. + */ +static inline uint32_t extract32(uint32_t value, int start, int length) +{ + assert(start >= 0 && length > 0 && length <= 32 - start); + return (value >> start) & (~0U >> (32 - length)); +} + +/** + * extract64: + * @value: the value to extract the bit field from + * @start: the lowest bit in the bit field (numbered from 0) + * @length: the length of the bit field + * + * Extract from the 64 bit input @value the bit field specified by the + * @start and @length parameters, and return it. The bit field must + * lie entirely within the 64 bit word. It is valid to request that + * all 64 bits are returned (ie @length 64 and @start 0). + * + * Returns: the value of the bit field extracted from the input value. + */ +static inline uint64_t extract64(uint64_t value, int start, int length) +{ + assert(start >= 0 && length > 0 && length <= 64 - start); + return (value >> start) & (~0ULL >> (64 - length)); +} + +/** + * sextract32: + * @value: the value to extract the bit field from + * @start: the lowest bit in the bit field (numbered from 0) + * @length: the length of the bit field + * + * Extract from the 32 bit input @value the bit field specified by the + * @start and @length parameters, and return it, sign extended to + * an int32_t (ie with the most significant bit of the field propagated + * to all the upper bits of the return value). The bit field must lie + * entirely within the 32 bit word. It is valid to request that + * all 32 bits are returned (ie @length 32 and @start 0). + * + * Returns: the sign extended value of the bit field extracted from the + * input value. + */ +static inline int32_t sextract32(uint32_t value, int start, int length) +{ + assert(start >= 0 && length > 0 && length <= 32 - start); + /* Note that this implementation relies on right shift of signed + * integers being an arithmetic shift. + */ + return ((int32_t)(value << (32 - length - start))) >> (32 - length); +} + +/** + * sextract64: + * @value: the value to extract the bit field from + * @start: the lowest bit in the bit field (numbered from 0) + * @length: the length of the bit field + * + * Extract from the 64 bit input @value the bit field specified by the + * @start and @length parameters, and return it, sign extended to + * an int64_t (ie with the most significant bit of the field propagated + * to all the upper bits of the return value). The bit field must lie + * entirely within the 64 bit word. It is valid to request that + * all 64 bits are returned (ie @length 64 and @start 0). + * + * Returns: the sign extended value of the bit field extracted from the + * input value. + */ +static inline int64_t sextract64(uint64_t value, int start, int length) +{ + assert(start >= 0 && length > 0 && length <= 64 - start); + /* Note that this implementation relies on right shift of signed + * integers being an arithmetic shift. + */ + return ((int64_t)(value << (64 - length - start))) >> (64 - length); +} + +/** + * deposit32: + * @value: initial value to insert bit field into + * @start: the lowest bit in the bit field (numbered from 0) + * @length: the length of the bit field + * @fieldval: the value to insert into the bit field + * + * Deposit @fieldval into the 32 bit @value at the bit field specified + * by the @start and @length parameters, and return the modified + * @value. Bits of @value outside the bit field are not modified. + * Bits of @fieldval above the least significant @length bits are + * ignored. The bit field must lie entirely within the 32 bit word. + * It is valid to request that all 32 bits are modified (ie @length + * 32 and @start 0). + * + * Returns: the modified @value. + */ +static inline uint32_t deposit32(uint32_t value, int start, int length, + uint32_t fieldval) +{ + uint32_t mask; + assert(start >= 0 && length > 0 && length <= 32 - start); + mask = (~0U >> (32 - length)) << start; + return (value & ~mask) | ((fieldval << start) & mask); +} + +/** + * deposit64: + * @value: initial value to insert bit field into + * @start: the lowest bit in the bit field (numbered from 0) + * @length: the length of the bit field + * @fieldval: the value to insert into the bit field + * + * Deposit @fieldval into the 64 bit @value at the bit field specified + * by the @start and @length parameters, and return the modified + * @value. Bits of @value outside the bit field are not modified. + * Bits of @fieldval above the least significant @length bits are + * ignored. The bit field must lie entirely within the 64 bit word. + * It is valid to request that all 64 bits are modified (ie @length + * 64 and @start 0). + * + * Returns: the modified @value. + */ +static inline uint64_t deposit64(uint64_t value, int start, int length, + uint64_t fieldval) +{ + uint64_t mask; + assert(start >= 0 && length > 0 && length <= 64 - start); + mask = (~0ULL >> (64 - length)) << start; + return (value & ~mask) | ((fieldval << start) & mask); +} + +#endif diff --git a/src/include/qemu/bswap.h b/src/include/qemu/bswap.h new file mode 100644 index 0000000..07d88de --- /dev/null +++ b/src/include/qemu/bswap.h @@ -0,0 +1,443 @@ +#ifndef BSWAP_H +#define BSWAP_H + +#include "config-host.h" +#include <inttypes.h> +#include <limits.h> +#include <string.h> +#include "fpu/softfloat.h" + +#ifdef CONFIG_MACHINE_BSWAP_H +# include <sys/endian.h> +# include <sys/types.h> +# include <machine/bswap.h> +#elif defined(__FreeBSD__) +# include <sys/endian.h> +#elif defined(CONFIG_BYTESWAP_H) +# include <byteswap.h> + +static inline uint16_t bswap16(uint16_t x) +{ + return bswap_16(x); +} + +static inline uint32_t bswap32(uint32_t x) +{ + return bswap_32(x); +} + +static inline uint64_t bswap64(uint64_t x) +{ + return bswap_64(x); +} +# else +static inline uint16_t bswap16(uint16_t x) +{ + return (((x & 0x00ff) << 8) | + ((x & 0xff00) >> 8)); +} + +static inline uint32_t bswap32(uint32_t x) +{ + return (((x & 0x000000ffU) << 24) | + ((x & 0x0000ff00U) << 8) | + ((x & 0x00ff0000U) >> 8) | + ((x & 0xff000000U) >> 24)); +} + +static inline uint64_t bswap64(uint64_t x) +{ + return (((x & 0x00000000000000ffULL) << 56) | + ((x & 0x000000000000ff00ULL) << 40) | + ((x & 0x0000000000ff0000ULL) << 24) | + ((x & 0x00000000ff000000ULL) << 8) | + ((x & 0x000000ff00000000ULL) >> 8) | + ((x & 0x0000ff0000000000ULL) >> 24) | + ((x & 0x00ff000000000000ULL) >> 40) | + ((x & 0xff00000000000000ULL) >> 56)); +} +#endif /* ! CONFIG_MACHINE_BSWAP_H */ + +static inline void bswap16s(uint16_t *s) +{ + *s = bswap16(*s); +} + +static inline void bswap32s(uint32_t *s) +{ + *s = bswap32(*s); +} + +static inline void bswap64s(uint64_t *s) +{ + *s = bswap64(*s); +} + +#if defined(HOST_WORDS_BIGENDIAN) +#define be_bswap(v, size) (v) +#define le_bswap(v, size) glue(bswap, size)(v) +#define be_bswaps(v, size) +#define le_bswaps(p, size) do { *p = glue(bswap, size)(*p); } while(0) +#else +#define le_bswap(v, size) (v) +#define be_bswap(v, size) glue(bswap, size)(v) +#define le_bswaps(v, size) +#define be_bswaps(p, size) do { *p = glue(bswap, size)(*p); } while(0) +#endif + +#define CPU_CONVERT(endian, size, type)\ +static inline type endian ## size ## _to_cpu(type v)\ +{\ + return glue(endian, _bswap)(v, size);\ +}\ +\ +static inline type cpu_to_ ## endian ## size(type v)\ +{\ + return glue(endian, _bswap)(v, size);\ +}\ +\ +static inline void endian ## size ## _to_cpus(type *p)\ +{\ + glue(endian, _bswaps)(p, size);\ +}\ +\ +static inline void cpu_to_ ## endian ## size ## s(type *p)\ +{\ + glue(endian, _bswaps)(p, size);\ +}\ +\ +static inline type endian ## size ## _to_cpup(const type *p)\ +{\ + return glue(glue(endian, size), _to_cpu)(*p);\ +}\ +\ +static inline void cpu_to_ ## endian ## size ## w(type *p, type v)\ +{\ + *p = glue(glue(cpu_to_, endian), size)(v);\ +} + +CPU_CONVERT(be, 16, uint16_t) +CPU_CONVERT(be, 32, uint32_t) +CPU_CONVERT(be, 64, uint64_t) + +CPU_CONVERT(le, 16, uint16_t) +CPU_CONVERT(le, 32, uint32_t) +CPU_CONVERT(le, 64, uint64_t) + +/* len must be one of 1, 2, 4 */ +static inline uint32_t qemu_bswap_len(uint32_t value, int len) +{ + return bswap32(value) >> (32 - 8 * len); +} + +/* Unions for reinterpreting between floats and integers. */ + +typedef union { + float32 f; + uint32_t l; +} CPU_FloatU; + +typedef union { + float64 d; +#if defined(HOST_WORDS_BIGENDIAN) + struct { + uint32_t upper; + uint32_t lower; + } l; +#else + struct { + uint32_t lower; + uint32_t upper; + } l; +#endif + uint64_t ll; +} CPU_DoubleU; + +typedef union { + floatx80 d; + struct { + uint64_t lower; + uint16_t upper; + } l; +} CPU_LDoubleU; + +typedef union { + float128 q; +#if defined(HOST_WORDS_BIGENDIAN) + struct { + uint32_t upmost; + uint32_t upper; + uint32_t lower; + uint32_t lowest; + } l; + struct { + uint64_t upper; + uint64_t lower; + } ll; +#else + struct { + uint32_t lowest; + uint32_t lower; + uint32_t upper; + uint32_t upmost; + } l; + struct { + uint64_t lower; + uint64_t upper; + } ll; +#endif +} CPU_QuadU; + +/* unaligned/endian-independent pointer access */ + +/* + * the generic syntax is: + * + * load: ld{type}{sign}{size}{endian}_p(ptr) + * + * store: st{type}{size}{endian}_p(ptr, val) + * + * Note there are small differences with the softmmu access API! + * + * type is: + * (empty): integer access + * f : float access + * + * sign is: + * (empty): for 32 or 64 bit sizes (including floats and doubles) + * u : unsigned + * s : signed + * + * size is: + * b: 8 bits + * w: 16 bits + * l: 32 bits + * q: 64 bits + * + * endian is: + * he : host endian + * be : big endian + * le : little endian + * te : target endian + * (except for byte accesses, which have no endian infix). + * + * The target endian accessors are obviously only available to source + * files which are built per-target; they are defined in cpu-all.h. + * + * In all cases these functions take a host pointer. + * For accessors that take a guest address rather than a + * host address, see the cpu_{ld,st}_* accessors defined in + * cpu_ldst.h. + */ + +static inline int ldub_p(const void *ptr) +{ + return *(uint8_t *)ptr; +} + +static inline int ldsb_p(const void *ptr) +{ + return *(int8_t *)ptr; +} + +static inline void stb_p(void *ptr, uint8_t v) +{ + *(uint8_t *)ptr = v; +} + +/* Any compiler worth its salt will turn these memcpy into native unaligned + operations. Thus we don't need to play games with packed attributes, or + inline byte-by-byte stores. */ + +static inline int lduw_he_p(const void *ptr) +{ + uint16_t r; + memcpy(&r, ptr, sizeof(r)); + return r; +} + +static inline int ldsw_he_p(const void *ptr) +{ + int16_t r; + memcpy(&r, ptr, sizeof(r)); + return r; +} + +static inline void stw_he_p(void *ptr, uint16_t v) +{ + memcpy(ptr, &v, sizeof(v)); +} + +static inline int ldl_he_p(const void *ptr) +{ + int32_t r; + memcpy(&r, ptr, sizeof(r)); + return r; +} + +static inline void stl_he_p(void *ptr, uint32_t v) +{ + memcpy(ptr, &v, sizeof(v)); +} + +static inline uint64_t ldq_he_p(const void *ptr) +{ + uint64_t r; + memcpy(&r, ptr, sizeof(r)); + return r; +} + +static inline void stq_he_p(void *ptr, uint64_t v) +{ + memcpy(ptr, &v, sizeof(v)); +} + +static inline int lduw_le_p(const void *ptr) +{ + return (uint16_t)le_bswap(lduw_he_p(ptr), 16); +} + +static inline int ldsw_le_p(const void *ptr) +{ + return (int16_t)le_bswap(lduw_he_p(ptr), 16); +} + +static inline int ldl_le_p(const void *ptr) +{ + return le_bswap(ldl_he_p(ptr), 32); +} + +static inline uint64_t ldq_le_p(const void *ptr) +{ + return le_bswap(ldq_he_p(ptr), 64); +} + +static inline void stw_le_p(void *ptr, uint16_t v) +{ + stw_he_p(ptr, le_bswap(v, 16)); +} + +static inline void stl_le_p(void *ptr, uint32_t v) +{ + stl_he_p(ptr, le_bswap(v, 32)); +} + +static inline void stq_le_p(void *ptr, uint64_t v) +{ + stq_he_p(ptr, le_bswap(v, 64)); +} + +/* float access */ + +static inline float32 ldfl_le_p(const void *ptr) +{ + CPU_FloatU u; + u.l = ldl_le_p(ptr); + return u.f; +} + +static inline void stfl_le_p(void *ptr, float32 v) +{ + CPU_FloatU u; + u.f = v; + stl_le_p(ptr, u.l); +} + +static inline float64 ldfq_le_p(const void *ptr) +{ + CPU_DoubleU u; + u.ll = ldq_le_p(ptr); + return u.d; +} + +static inline void stfq_le_p(void *ptr, float64 v) +{ + CPU_DoubleU u; + u.d = v; + stq_le_p(ptr, u.ll); +} + +static inline int lduw_be_p(const void *ptr) +{ + return (uint16_t)be_bswap(lduw_he_p(ptr), 16); +} + +static inline int ldsw_be_p(const void *ptr) +{ + return (int16_t)be_bswap(lduw_he_p(ptr), 16); +} + +static inline int ldl_be_p(const void *ptr) +{ + return be_bswap(ldl_he_p(ptr), 32); +} + +static inline uint64_t ldq_be_p(const void *ptr) +{ + return be_bswap(ldq_he_p(ptr), 64); +} + +static inline void stw_be_p(void *ptr, uint16_t v) +{ + stw_he_p(ptr, be_bswap(v, 16)); +} + +static inline void stl_be_p(void *ptr, uint32_t v) +{ + stl_he_p(ptr, be_bswap(v, 32)); +} + +static inline void stq_be_p(void *ptr, uint64_t v) +{ + stq_he_p(ptr, be_bswap(v, 64)); +} + +/* float access */ + +static inline float32 ldfl_be_p(const void *ptr) +{ + CPU_FloatU u; + u.l = ldl_be_p(ptr); + return u.f; +} + +static inline void stfl_be_p(void *ptr, float32 v) +{ + CPU_FloatU u; + u.f = v; + stl_be_p(ptr, u.l); +} + +static inline float64 ldfq_be_p(const void *ptr) +{ + CPU_DoubleU u; + u.ll = ldq_be_p(ptr); + return u.d; +} + +static inline void stfq_be_p(void *ptr, float64 v) +{ + CPU_DoubleU u; + u.d = v; + stq_be_p(ptr, u.ll); +} + +static inline unsigned long leul_to_cpu(unsigned long v) +{ + /* In order to break an include loop between here and + qemu-common.h, don't rely on HOST_LONG_BITS. */ +#if ULONG_MAX == UINT32_MAX + return le_bswap(v, 32); +#elif ULONG_MAX == UINT64_MAX + return le_bswap(v, 64); +#else +# error Unknown sizeof long +#endif +} + +#undef le_bswap +#undef be_bswap +#undef le_bswaps +#undef be_bswaps + +#endif /* BSWAP_H */ diff --git a/src/include/qemu/buffer.h b/src/include/qemu/buffer.h new file mode 100644 index 0000000..dead9b7 --- /dev/null +++ b/src/include/qemu/buffer.h @@ -0,0 +1,161 @@ +/* + * QEMU generic buffers + * + * Copyright (c) 2015 Red Hat, Inc. + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + * + */ + +#ifndef QEMU_BUFFER_H__ +#define QEMU_BUFFER_H__ + +#include "qemu-common.h" + +typedef struct Buffer Buffer; + +/** + * Buffer: + * + * The Buffer object provides a simple dynamically resizing + * array, with separate tracking of capacity and usage. This + * is typically useful when buffering I/O or processing data. + */ + +struct Buffer { + char *name; + size_t capacity; + size_t offset; + uint64_t avg_size; + uint8_t *buffer; +}; + +/** + * buffer_init: + * @buffer: the buffer object + * @name: buffer name + * + * Optionally attach a name to the buffer, to make it easier + * to identify in debug traces. + */ +void buffer_init(Buffer *buffer, const char *name, ...) + GCC_FMT_ATTR(2, 3); + +/** + * buffer_shrink: + * @buffer: the buffer object + * + * Try to shrink the buffer. Checks current buffer capacity and size + * and reduces capacity in case only a fraction of the buffer is + * actually used. + */ +void buffer_shrink(Buffer *buffer); + +/** + * buffer_reserve: + * @buffer: the buffer object + * @len: the minimum required free space + * + * Ensure that the buffer has space allocated for at least + * @len bytes. If the current buffer is too small, it will + * be reallocated, possibly to a larger size than requested. + */ +void buffer_reserve(Buffer *buffer, size_t len); + +/** + * buffer_reset: + * @buffer: the buffer object + * + * Reset the length of the stored data to zero, but do + * not free / reallocate the memory buffer + */ +void buffer_reset(Buffer *buffer); + +/** + * buffer_free: + * @buffer: the buffer object + * + * Reset the length of the stored data to zero and also + * free the internal memory buffer + */ +void buffer_free(Buffer *buffer); + +/** + * buffer_append: + * @buffer: the buffer object + * @data: the data block to append + * @len: the length of @data in bytes + * + * Append the contents of @data to the end of the buffer. + * The caller must ensure that the buffer has sufficient + * free space for @len bytes, typically by calling the + * buffer_reserve() method prior to appending. + */ +void buffer_append(Buffer *buffer, const void *data, size_t len); + +/** + * buffer_advance: + * @buffer: the buffer object + * @len: the number of bytes to skip + * + * Remove @len bytes of data from the head of the buffer. + * The internal buffer will not be reallocated, so will + * have at least @len bytes of free space after this + * call completes + */ +void buffer_advance(Buffer *buffer, size_t len); + +/** + * buffer_end: + * @buffer: the buffer object + * + * Get a pointer to the tail end of the internal buffer + * The returned pointer is only valid until the next + * call to buffer_reserve(). + * + * Returns: the tail of the buffer + */ +uint8_t *buffer_end(Buffer *buffer); + +/** + * buffer_empty: + * @buffer: the buffer object + * + * Determine if the buffer contains any current data + * + * Returns: true if the buffer holds data, false otherwise + */ +gboolean buffer_empty(Buffer *buffer); + +/** + * buffer_move_empty: + * @to: destination buffer object + * @from: source buffer object + * + * Moves buffer, without copying data. 'to' buffer must be empty. + * 'from' buffer is empty and zero-sized on return. + */ +void buffer_move_empty(Buffer *to, Buffer *from); + +/** + * buffer_move: + * @to: destination buffer object + * @from: source buffer object + * + * Moves buffer, copying data (unless 'to' buffer happens to be empty). + * 'from' buffer is empty and zero-sized on return. + */ +void buffer_move(Buffer *to, Buffer *from); + +#endif /* QEMU_BUFFER_H__ */ diff --git a/src/include/qemu/compatfd.h b/src/include/qemu/compatfd.h new file mode 100644 index 0000000..fc37915 --- /dev/null +++ b/src/include/qemu/compatfd.h @@ -0,0 +1,43 @@ +/* + * signalfd/eventfd compatibility + * + * Copyright IBM, Corp. 2008 + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#ifndef QEMU_COMPATFD_H +#define QEMU_COMPATFD_H + +#include <signal.h> + +struct qemu_signalfd_siginfo { + uint32_t ssi_signo; /* Signal number */ + int32_t ssi_errno; /* Error number (unused) */ + int32_t ssi_code; /* Signal code */ + uint32_t ssi_pid; /* PID of sender */ + uint32_t ssi_uid; /* Real UID of sender */ + int32_t ssi_fd; /* File descriptor (SIGIO) */ + uint32_t ssi_tid; /* Kernel timer ID (POSIX timers) */ + uint32_t ssi_band; /* Band event (SIGIO) */ + uint32_t ssi_overrun; /* POSIX timer overrun count */ + uint32_t ssi_trapno; /* Trap number that caused signal */ + int32_t ssi_status; /* Exit status or signal (SIGCHLD) */ + int32_t ssi_int; /* Integer sent by sigqueue(2) */ + uint64_t ssi_ptr; /* Pointer sent by sigqueue(2) */ + uint64_t ssi_utime; /* User CPU time consumed (SIGCHLD) */ + uint64_t ssi_stime; /* System CPU time consumed (SIGCHLD) */ + uint64_t ssi_addr; /* Address that generated signal + (for hardware-generated signals) */ + uint8_t pad[48]; /* Pad size to 128 bytes (allow for + additional fields in the future) */ +}; + +int qemu_signalfd(const sigset_t *mask); + +#endif diff --git a/src/include/qemu/compiler.h b/src/include/qemu/compiler.h new file mode 100644 index 0000000..0abf0f8 --- /dev/null +++ b/src/include/qemu/compiler.h @@ -0,0 +1,112 @@ +/* public domain */ + +#ifndef COMPILER_H +#define COMPILER_H + +#include "config-host.h" + +/*---------------------------------------------------------------------------- +| The macro QEMU_GNUC_PREREQ tests for minimum version of the GNU C compiler. +| The code is a copy of SOFTFLOAT_GNUC_PREREQ, see softfloat-macros.h. +*----------------------------------------------------------------------------*/ +#if defined(__GNUC__) && defined(__GNUC_MINOR__) +# define QEMU_GNUC_PREREQ(maj, min) \ + ((__GNUC__ << 16) + __GNUC_MINOR__ >= ((maj) << 16) + (min)) +#else +# define QEMU_GNUC_PREREQ(maj, min) 0 +#endif + +#define QEMU_NORETURN __attribute__ ((__noreturn__)) + +#if QEMU_GNUC_PREREQ(3, 4) +#define QEMU_WARN_UNUSED_RESULT __attribute__((warn_unused_result)) +#else +#define QEMU_WARN_UNUSED_RESULT +#endif + +#if QEMU_GNUC_PREREQ(4, 0) +#define QEMU_SENTINEL __attribute__((sentinel)) +#else +#define QEMU_SENTINEL +#endif + +#if QEMU_GNUC_PREREQ(4, 3) +#define QEMU_ARTIFICIAL __attribute__((always_inline, artificial)) +#else +#define QEMU_ARTIFICIAL +#endif + +#if defined(_WIN32) +# define QEMU_PACKED __attribute__((gcc_struct, packed)) +#else +# define QEMU_PACKED __attribute__((packed)) +#endif + +#ifndef glue +#define xglue(x, y) x ## y +#define glue(x, y) xglue(x, y) +#define stringify(s) tostring(s) +#define tostring(s) #s +#endif + +#ifndef likely +#if __GNUC__ < 3 +#define __builtin_expect(x, n) (x) +#endif + +#define likely(x) __builtin_expect(!!(x), 1) +#define unlikely(x) __builtin_expect(!!(x), 0) +#endif + +#ifndef container_of +#define container_of(ptr, type, member) ({ \ + const __typeof__(((type *) 0)->member) *__mptr = (ptr); \ + (type *) ((char *) __mptr - offsetof(type, member));}) +#endif + +/* Convert from a base type to a parent type, with compile time checking. */ +#ifdef __GNUC__ +#define DO_UPCAST(type, field, dev) ( __extension__ ( { \ + char __attribute__((unused)) offset_must_be_zero[ \ + -offsetof(type, field)]; \ + container_of(dev, type, field);})) +#else +#define DO_UPCAST(type, field, dev) container_of(dev, type, field) +#endif + +#define typeof_field(type, field) __typeof__(((type *)0)->field) +#define type_check(t1,t2) ((t1*)0 - (t2*)0) + +#ifndef always_inline +#if !((__GNUC__ < 3) || defined(__APPLE__)) +#ifdef __OPTIMIZE__ +#undef inline +#define inline __attribute__ (( always_inline )) __inline__ +#endif +#endif +#else +#undef inline +#define inline always_inline +#endif + +#define QEMU_BUILD_BUG_ON(x) \ + typedef char glue(qemu_build_bug_on__,__LINE__)[(x)?-1:1] __attribute__((unused)); + +#if defined __GNUC__ +# if !QEMU_GNUC_PREREQ(4, 4) + /* gcc versions before 4.4.x don't support gnu_printf, so use printf. */ +# define GCC_FMT_ATTR(n, m) __attribute__((format(printf, n, m))) +# else + /* Use gnu_printf when supported (qemu uses standard format strings). */ +# define GCC_FMT_ATTR(n, m) __attribute__((format(gnu_printf, n, m))) +# if defined(_WIN32) + /* Map __printf__ to __gnu_printf__ because we want standard format strings + * even when MinGW or GLib include files use __printf__. */ +# define __printf__ __gnu_printf__ +# endif +# endif +#else +#define GCC_FMT_ATTR(n, m) +#endif + +#endif /* COMPILER_H */ diff --git a/src/include/qemu/config-file.h b/src/include/qemu/config-file.h new file mode 100644 index 0000000..d4ba20e --- /dev/null +++ b/src/include/qemu/config-file.h @@ -0,0 +1,33 @@ +#ifndef QEMU_CONFIG_H +#define QEMU_CONFIG_H + +#include <stdio.h> +#include "qemu/option.h" +#include "qapi/error.h" +#include "qapi/qmp/qdict.h" + +QemuOptsList *qemu_find_opts(const char *group); +QemuOptsList *qemu_find_opts_err(const char *group, Error **errp); +QemuOpts *qemu_find_opts_singleton(const char *group); + +void qemu_add_opts(QemuOptsList *list); +void qemu_add_drive_opts(QemuOptsList *list); +int qemu_set_option(const char *str); +int qemu_global_option(const char *str); +void qemu_add_globals(void); + +void qemu_config_write(FILE *fp); +int qemu_config_parse(FILE *fp, QemuOptsList **lists, const char *fname); + +int qemu_read_config_file(const char *filename); + +/* Parse QDict options as a replacement for a config file (allowing multiple + enumerated (0..(n-1)) configuration "sections") */ +void qemu_config_parse_qdict(QDict *options, QemuOptsList **lists, + Error **errp); + +/* Read default QEMU config files + */ +int qemu_read_default_config_files(bool userconfig); + +#endif /* QEMU_CONFIG_H */ diff --git a/src/include/qemu/coroutine.h b/src/include/qemu/coroutine.h new file mode 100644 index 0000000..20c027a --- /dev/null +++ b/src/include/qemu/coroutine.h @@ -0,0 +1,219 @@ +/* + * QEMU coroutine implementation + * + * Copyright IBM, Corp. 2011 + * + * Authors: + * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com> + * Kevin Wolf <kwolf@redhat.com> + * + * This work is licensed under the terms of the GNU LGPL, version 2 or later. + * See the COPYING.LIB file in the top-level directory. + * + */ + +#ifndef QEMU_COROUTINE_H +#define QEMU_COROUTINE_H + +#include <stdbool.h> +#include "qemu/typedefs.h" +#include "qemu/queue.h" +#include "qemu/timer.h" + +/** + * Coroutines are a mechanism for stack switching and can be used for + * cooperative userspace threading. These functions provide a simple but + * useful flavor of coroutines that is suitable for writing sequential code, + * rather than callbacks, for operations that need to give up control while + * waiting for events to complete. + * + * These functions are re-entrant and may be used outside the global mutex. + */ + +/** + * Mark a function that executes in coroutine context + * + * Functions that execute in coroutine context cannot be called directly from + * normal functions. In the future it would be nice to enable compiler or + * static checker support for catching such errors. This annotation might make + * it possible and in the meantime it serves as documentation. + * + * For example: + * + * static void coroutine_fn foo(void) { + * .... + * } + */ +#define coroutine_fn + +typedef struct Coroutine Coroutine; + +/** + * Coroutine entry point + * + * When the coroutine is entered for the first time, opaque is passed in as an + * argument. + * + * When this function returns, the coroutine is destroyed automatically and + * execution continues in the caller who last entered the coroutine. + */ +typedef void coroutine_fn CoroutineEntry(void *opaque); + +/** + * Create a new coroutine + * + * Use qemu_coroutine_enter() to actually transfer control to the coroutine. + */ +Coroutine *qemu_coroutine_create(CoroutineEntry *entry); + +/** + * Transfer control to a coroutine + * + * The opaque argument is passed as the argument to the entry point when + * entering the coroutine for the first time. It is subsequently ignored. + */ +void qemu_coroutine_enter(Coroutine *coroutine, void *opaque); + +/** + * Transfer control back to a coroutine's caller + * + * This function does not return until the coroutine is re-entered using + * qemu_coroutine_enter(). + */ +void coroutine_fn qemu_coroutine_yield(void); + +/** + * Get the currently executing coroutine + */ +Coroutine *coroutine_fn qemu_coroutine_self(void); + +/** + * Return whether or not currently inside a coroutine + * + * This can be used to write functions that work both when in coroutine context + * and when not in coroutine context. Note that such functions cannot use the + * coroutine_fn annotation since they work outside coroutine context. + */ +bool qemu_in_coroutine(void); + + + +/** + * CoQueues are a mechanism to queue coroutines in order to continue executing + * them later. They provide the fundamental primitives on which coroutine locks + * are built. + */ +typedef struct CoQueue { + QTAILQ_HEAD(, Coroutine) entries; +} CoQueue; + +/** + * Initialise a CoQueue. This must be called before any other operation is used + * on the CoQueue. + */ +void qemu_co_queue_init(CoQueue *queue); + +/** + * Adds the current coroutine to the CoQueue and transfers control to the + * caller of the coroutine. + */ +void coroutine_fn qemu_co_queue_wait(CoQueue *queue); + +/** + * Restarts the next coroutine in the CoQueue and removes it from the queue. + * + * Returns true if a coroutine was restarted, false if the queue is empty. + */ +bool coroutine_fn qemu_co_queue_next(CoQueue *queue); + +/** + * Restarts all coroutines in the CoQueue and leaves the queue empty. + */ +void coroutine_fn qemu_co_queue_restart_all(CoQueue *queue); + +/** + * Enter the next coroutine in the queue + */ +bool qemu_co_enter_next(CoQueue *queue); + +/** + * Checks if the CoQueue is empty. + */ +bool qemu_co_queue_empty(CoQueue *queue); + + +/** + * Provides a mutex that can be used to synchronise coroutines + */ +typedef struct CoMutex { + bool locked; + CoQueue queue; +} CoMutex; + +/** + * Initialises a CoMutex. This must be called before any other operation is used + * on the CoMutex. + */ +void qemu_co_mutex_init(CoMutex *mutex); + +/** + * Locks the mutex. If the lock cannot be taken immediately, control is + * transferred to the caller of the current coroutine. + */ +void coroutine_fn qemu_co_mutex_lock(CoMutex *mutex); + +/** + * Unlocks the mutex and schedules the next coroutine that was waiting for this + * lock to be run. + */ +void coroutine_fn qemu_co_mutex_unlock(CoMutex *mutex); + +typedef struct CoRwlock { + bool writer; + int reader; + CoQueue queue; +} CoRwlock; + +/** + * Initialises a CoRwlock. This must be called before any other operation + * is used on the CoRwlock + */ +void qemu_co_rwlock_init(CoRwlock *lock); + +/** + * Read locks the CoRwlock. If the lock cannot be taken immediately because + * of a parallel writer, control is transferred to the caller of the current + * coroutine. + */ +void qemu_co_rwlock_rdlock(CoRwlock *lock); + +/** + * Write Locks the mutex. If the lock cannot be taken immediately because + * of a parallel reader, control is transferred to the caller of the current + * coroutine. + */ +void qemu_co_rwlock_wrlock(CoRwlock *lock); + +/** + * Unlocks the read/write lock and schedules the next coroutine that was + * waiting for this lock to be run. + */ +void qemu_co_rwlock_unlock(CoRwlock *lock); + +/** + * Yield the coroutine for a given duration + * + * Behaves similarly to co_sleep_ns(), but the sleeping coroutine will be + * resumed when using aio_poll(). + */ +void coroutine_fn co_aio_sleep_ns(AioContext *ctx, QEMUClockType type, + int64_t ns); + +/** + * Yield until a file descriptor becomes readable + * + * Note that this function clobbers the handlers for the file descriptor. + */ +void coroutine_fn yield_until_fd_readable(int fd); + +#endif /* QEMU_COROUTINE_H */ diff --git a/src/include/qemu/coroutine_int.h b/src/include/qemu/coroutine_int.h new file mode 100644 index 0000000..42d6838 --- /dev/null +++ b/src/include/qemu/coroutine_int.h @@ -0,0 +1,54 @@ +/* + * Coroutine internals + * + * Copyright (c) 2011 Kevin Wolf <kwolf@redhat.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef QEMU_COROUTINE_INT_H +#define QEMU_COROUTINE_INT_H + +#include "qemu/queue.h" +#include "qemu/coroutine.h" + +typedef enum { + COROUTINE_YIELD = 1, + COROUTINE_TERMINATE = 2, + COROUTINE_ENTER = 3, +} CoroutineAction; + +struct Coroutine { + CoroutineEntry *entry; + void *entry_arg; + Coroutine *caller; + QSLIST_ENTRY(Coroutine) pool_next; + + /* Coroutines that should be woken up when we yield or terminate */ + QTAILQ_HEAD(, Coroutine) co_queue_wakeup; + QTAILQ_ENTRY(Coroutine) co_queue_next; +}; + +Coroutine *qemu_coroutine_new(void); +void qemu_coroutine_delete(Coroutine *co); +CoroutineAction qemu_coroutine_switch(Coroutine *from, Coroutine *to, + CoroutineAction action); +void coroutine_fn qemu_co_queue_run_restart(Coroutine *co); + +#endif diff --git a/src/include/qemu/crc32c.h b/src/include/qemu/crc32c.h new file mode 100644 index 0000000..dafb6a1 --- /dev/null +++ b/src/include/qemu/crc32c.h @@ -0,0 +1,35 @@ +/* + * Castagnoli CRC32C Checksum Algorithm + * + * Polynomial: 0x11EDC6F41 + * + * Castagnoli93: Guy Castagnoli and Stefan Braeuer and Martin Herrman + * "Optimization of Cyclic Redundancy-Check Codes with 24 + * and 32 Parity Bits",IEEE Transactions on Communication, + * Volume 41, Number 6, June 1993 + * + * Copyright (c) 2013 Red Hat, Inc., + * + * Authors: + * Jeff Cody <jcody@redhat.com> + * + * Based on the Linux kernel cryptographic crc32c module, + * + * Copyright (c) 2004 Cisco Systems, Inc. + * Copyright (c) 2008 Herbert Xu <herbert@gondor.apana.org.au> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ + +#ifndef QEMU_CRC32C_H +#define QEMU_CRC32C_H + +#include "qemu-common.h" + +uint32_t crc32c(uint32_t crc, const uint8_t *data, unsigned int length); + +#endif diff --git a/src/include/qemu/envlist.h b/src/include/qemu/envlist.h new file mode 100644 index 0000000..b9addcc --- /dev/null +++ b/src/include/qemu/envlist.h @@ -0,0 +1,22 @@ +#ifndef ENVLIST_H +#define ENVLIST_H + +#ifdef __cplusplus +extern "C" { +#endif + +typedef struct envlist envlist_t; + +envlist_t *envlist_create(void); +void envlist_free(envlist_t *); +int envlist_setenv(envlist_t *, const char *); +int envlist_unsetenv(envlist_t *, const char *); +int envlist_parse_set(envlist_t *, const char *); +int envlist_parse_unset(envlist_t *, const char *); +char **envlist_to_environ(const envlist_t *, size_t *); + +#ifdef __cplusplus +} +#endif + +#endif /* ENVLIST_H */ diff --git a/src/include/qemu/error-report.h b/src/include/qemu/error-report.h new file mode 100644 index 0000000..7ab2355 --- /dev/null +++ b/src/include/qemu/error-report.h @@ -0,0 +1,46 @@ +/* + * Error reporting + * + * Copyright (C) 2010 Red Hat Inc. + * + * Authors: + * Markus Armbruster <armbru@redhat.com>, + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef QEMU_ERROR_H +#define QEMU_ERROR_H + +#include <stdarg.h> +#include <stdbool.h> +#include "qemu/compiler.h" + +typedef struct Location { + /* all members are private to qemu-error.c */ + enum { LOC_NONE, LOC_CMDLINE, LOC_FILE } kind; + int num; + const void *ptr; + struct Location *prev; +} Location; + +Location *loc_push_restore(Location *loc); +Location *loc_push_none(Location *loc); +Location *loc_pop(Location *loc); +Location *loc_save(Location *loc); +void loc_restore(Location *loc); +void loc_set_none(void); +void loc_set_cmdline(char **argv, int idx, int cnt); +void loc_set_file(const char *fname, int lno); + +void error_vprintf(const char *fmt, va_list ap) GCC_FMT_ATTR(1, 0); +void error_printf(const char *fmt, ...) GCC_FMT_ATTR(1, 2); +void error_printf_unless_qmp(const char *fmt, ...) GCC_FMT_ATTR(1, 2); +void error_set_progname(const char *argv0); +void error_vreport(const char *fmt, va_list ap) GCC_FMT_ATTR(1, 0); +void error_report(const char *fmt, ...) GCC_FMT_ATTR(1, 2); +const char *error_get_progname(void); +extern bool enable_timestamp_msg; + +#endif diff --git a/src/include/qemu/event_notifier.h b/src/include/qemu/event_notifier.h new file mode 100644 index 0000000..a8f2854 --- /dev/null +++ b/src/include/qemu/event_notifier.h @@ -0,0 +1,46 @@ +/* + * event notifier support + * + * Copyright Red Hat, Inc. 2010 + * + * Authors: + * Michael S. Tsirkin <mst@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef QEMU_EVENT_NOTIFIER_H +#define QEMU_EVENT_NOTIFIER_H + +#include "qemu-common.h" + +#ifdef _WIN32 +#include <windows.h> +#endif + +struct EventNotifier { +#ifdef _WIN32 + HANDLE event; +#else + int rfd; + int wfd; +#endif +}; + +typedef void EventNotifierHandler(EventNotifier *); + +int event_notifier_init(EventNotifier *, int active); +void event_notifier_cleanup(EventNotifier *); +int event_notifier_set(EventNotifier *); +int event_notifier_test_and_clear(EventNotifier *); +int event_notifier_set_handler(EventNotifier *, EventNotifierHandler *); + +#ifdef CONFIG_POSIX +void event_notifier_init_fd(EventNotifier *, int fd); +int event_notifier_get_fd(const EventNotifier *); +#else +HANDLE event_notifier_get_handle(EventNotifier *); +#endif + +#endif diff --git a/src/include/qemu/fifo8.h b/src/include/qemu/fifo8.h new file mode 100644 index 0000000..8820780 --- /dev/null +++ b/src/include/qemu/fifo8.h @@ -0,0 +1,160 @@ +#ifndef FIFO_H +#define FIFO_H + +#include "migration/vmstate.h" + +typedef struct { + /* All fields are private */ + uint8_t *data; + uint32_t capacity; + uint32_t head; + uint32_t num; +} Fifo8; + +/** + * fifo8_create: + * @fifo: struct Fifo8 to initialise with new FIFO + * @capacity: capacity of the newly created FIFO + * + * Create a FIFO of the specified size. Clients should call fifo8_destroy() + * when finished using the fifo. The FIFO is initially empty. + */ + +void fifo8_create(Fifo8 *fifo, uint32_t capacity); + +/** + * fifo8_destroy: + * @fifo: FIFO to cleanup + * + * Cleanup a FIFO created with fifo8_create(). Frees memory created for FIFO + *storage. The FIFO is no longer usable after this has been called. + */ + +void fifo8_destroy(Fifo8 *fifo); + +/** + * fifo8_push: + * @fifo: FIFO to push to + * @data: data byte to push + * + * Push a data byte to the FIFO. Behaviour is undefined if the FIFO is full. + * Clients are responsible for checking for fullness using fifo8_is_full(). + */ + +void fifo8_push(Fifo8 *fifo, uint8_t data); + +/** + * fifo8_push_all: + * @fifo: FIFO to push to + * @data: data to push + * @size: number of bytes to push + * + * Push a byte array to the FIFO. Behaviour is undefined if the FIFO is full. + * Clients are responsible for checking the space left in the FIFO using + * fifo8_num_free(). + */ + +void fifo8_push_all(Fifo8 *fifo, const uint8_t *data, uint32_t num); + +/** + * fifo8_pop: + * @fifo: fifo to pop from + * + * Pop a data byte from the FIFO. Behaviour is undefined if the FIFO is empty. + * Clients are responsible for checking for emptyness using fifo8_is_empty(). + * + * Returns: The popped data byte. + */ + +uint8_t fifo8_pop(Fifo8 *fifo); + +/** + * fifo8_pop_buf: + * @fifo: FIFO to pop from + * @max: maximum number of bytes to pop + * @num: actual number of returned bytes + * + * Pop a number of elements from the FIFO up to a maximum of max. The buffer + * containing the popped data is returned. This buffer points directly into + * the FIFO backing store and data is invalidated once any of the fifo8_* APIs + * are called on the FIFO. + * + * The function may return fewer bytes than requested when the data wraps + * around in the ring buffer; in this case only a contiguous part of the data + * is returned. + * + * The number of valid bytes returned is populated in *num; will always return + * at least 1 byte. max must not be 0 or greater than the number of bytes in + * the FIFO. + * + * Clients are responsible for checking the availability of requested data + * using fifo8_num_used(). + * + * Returns: A pointer to popped data. + */ +const uint8_t *fifo8_pop_buf(Fifo8 *fifo, uint32_t max, uint32_t *num); + +/** + * fifo8_reset: + * @fifo: FIFO to reset + * + * Reset a FIFO. All data is discarded and the FIFO is emptied. + */ + +void fifo8_reset(Fifo8 *fifo); + +/** + * fifo8_is_empty: + * @fifo: FIFO to check + * + * Check if a FIFO is empty. + * + * Returns: True if the fifo is empty, false otherwise. + */ + +bool fifo8_is_empty(Fifo8 *fifo); + +/** + * fifo8_is_full: + * @fifo: FIFO to check + * + * Check if a FIFO is full. + * + * Returns: True if the fifo is full, false otherwise. + */ + +bool fifo8_is_full(Fifo8 *fifo); + +/** + * fifo8_num_free: + * @fifo: FIFO to check + * + * Return the number of free bytes in the FIFO. + * + * Returns: Number of free bytes. + */ + +uint32_t fifo8_num_free(Fifo8 *fifo); + +/** + * fifo8_num_used: + * @fifo: FIFO to check + * + * Return the number of used bytes in the FIFO. + * + * Returns: Number of used bytes. + */ + +uint32_t fifo8_num_used(Fifo8 *fifo); + +extern const VMStateDescription vmstate_fifo8; + +#define VMSTATE_FIFO8(_field, _state) { \ + .name = (stringify(_field)), \ + .size = sizeof(Fifo8), \ + .vmsd = &vmstate_fifo8, \ + .flags = VMS_STRUCT, \ + .offset = vmstate_offset_value(_state, _field, Fifo8), \ +} + +#endif /* FIFO_H */ diff --git a/src/include/qemu/fprintf-fn.h b/src/include/qemu/fprintf-fn.h new file mode 100644 index 0000000..9ddc90f --- /dev/null +++ b/src/include/qemu/fprintf-fn.h @@ -0,0 +1,17 @@ +/* + * Typedef for fprintf-alike function pointers. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef QEMU_FPRINTF_FN_H +#define QEMU_FPRINTF_FN_H 1 + +#include "qemu/compiler.h" +#include <stdio.h> + +typedef int (*fprintf_function)(FILE *f, const char *fmt, ...) + GCC_FMT_ATTR(2, 3); + +#endif diff --git a/src/include/qemu/hbitmap.h b/src/include/qemu/hbitmap.h new file mode 100644 index 0000000..bb94a00 --- /dev/null +++ b/src/include/qemu/hbitmap.h @@ -0,0 +1,240 @@ +/* + * Hierarchical Bitmap Data Type + * + * Copyright Red Hat, Inc., 2012 + * + * Author: Paolo Bonzini <pbonzini@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * later. See the COPYING file in the top-level directory. + */ + +#ifndef HBITMAP_H +#define HBITMAP_H 1 + +#include <limits.h> +#include <stdint.h> +#include <stdbool.h> +#include "bitops.h" +#include "host-utils.h" + +typedef struct HBitmap HBitmap; +typedef struct HBitmapIter HBitmapIter; + +#define BITS_PER_LEVEL (BITS_PER_LONG == 32 ? 5 : 6) + +/* For 32-bit, the largest that fits in a 4 GiB address space. + * For 64-bit, the number of sectors in 1 PiB. Good luck, in + * either case... :) + */ +#define HBITMAP_LOG_MAX_SIZE (BITS_PER_LONG == 32 ? 34 : 41) + +/* We need to place a sentinel in level 0 to speed up iteration. Thus, + * we do this instead of HBITMAP_LOG_MAX_SIZE / BITS_PER_LEVEL. The + * difference is that it allocates an extra level when HBITMAP_LOG_MAX_SIZE + * is an exact multiple of BITS_PER_LEVEL. + */ +#define HBITMAP_LEVELS ((HBITMAP_LOG_MAX_SIZE / BITS_PER_LEVEL) + 1) + +struct HBitmapIter { + const HBitmap *hb; + + /* Copied from hb for access in the inline functions (hb is opaque). */ + int granularity; + + /* Entry offset into the last-level array of longs. */ + size_t pos; + + /* The currently-active path in the tree. Each item of cur[i] stores + * the bits (i.e. the subtrees) yet to be processed under that node. + */ + unsigned long cur[HBITMAP_LEVELS]; +}; + +/** + * hbitmap_alloc: + * @size: Number of bits in the bitmap. + * @granularity: Granularity of the bitmap. Aligned groups of 2^@granularity + * bits will be represented by a single bit. Each operation on a + * range of bits first rounds the bits to determine which group they land + * in, and then affect the entire set; iteration will only visit the first + * bit of each group. + * + * Allocate a new HBitmap. + */ +HBitmap *hbitmap_alloc(uint64_t size, int granularity); + +/** + * hbitmap_truncate: + * @hb: The bitmap to change the size of. + * @size: The number of elements to change the bitmap to accommodate. + * + * truncate or grow an existing bitmap to accommodate a new number of elements. + * This may invalidate existing HBitmapIterators. + */ +void hbitmap_truncate(HBitmap *hb, uint64_t size); + +/** + * hbitmap_merge: + * @a: The bitmap to store the result in. + * @b: The bitmap to merge into @a. + * @return true if the merge was successful, + * false if it was not attempted. + * + * Merge two bitmaps together. + * A := A (BITOR) B. + * B is left unmodified. + */ +bool hbitmap_merge(HBitmap *a, const HBitmap *b); + +/** + * hbitmap_empty: + * @hb: HBitmap to operate on. + * + * Return whether the bitmap is empty. + */ +bool hbitmap_empty(const HBitmap *hb); + +/** + * hbitmap_granularity: + * @hb: HBitmap to operate on. + * + * Return the granularity of the HBitmap. + */ +int hbitmap_granularity(const HBitmap *hb); + +/** + * hbitmap_count: + * @hb: HBitmap to operate on. + * + * Return the number of bits set in the HBitmap. + */ +uint64_t hbitmap_count(const HBitmap *hb); + +/** + * hbitmap_set: + * @hb: HBitmap to operate on. + * @start: First bit to set (0-based). + * @count: Number of bits to set. + * + * Set a consecutive range of bits in an HBitmap. + */ +void hbitmap_set(HBitmap *hb, uint64_t start, uint64_t count); + +/** + * hbitmap_reset: + * @hb: HBitmap to operate on. + * @start: First bit to reset (0-based). + * @count: Number of bits to reset. + * + * Reset a consecutive range of bits in an HBitmap. + */ +void hbitmap_reset(HBitmap *hb, uint64_t start, uint64_t count); + +/** + * hbitmap_reset_all: + * @hb: HBitmap to operate on. + * + * Reset all bits in an HBitmap. + */ +void hbitmap_reset_all(HBitmap *hb); + +/** + * hbitmap_get: + * @hb: HBitmap to operate on. + * @item: Bit to query (0-based). + * + * Return whether the @item-th bit in an HBitmap is set. + */ +bool hbitmap_get(const HBitmap *hb, uint64_t item); + +/** + * hbitmap_free: + * @hb: HBitmap to operate on. + * + * Free an HBitmap and all of its associated memory. + */ +void hbitmap_free(HBitmap *hb); + +/** + * hbitmap_iter_init: + * @hbi: HBitmapIter to initialize. + * @hb: HBitmap to iterate on. + * @first: First bit to visit (0-based, must be strictly less than the + * size of the bitmap). + * + * Set up @hbi to iterate on the HBitmap @hb. hbitmap_iter_next will return + * the lowest-numbered bit that is set in @hb, starting at @first. + * + * Concurrent setting of bits is acceptable, and will at worst cause the + * iteration to miss some of those bits. Resetting bits before the current + * position of the iterator is also okay. However, concurrent resetting of + * bits can lead to unexpected behavior if the iterator has not yet reached + * those bits. + */ +void hbitmap_iter_init(HBitmapIter *hbi, const HBitmap *hb, uint64_t first); + +/* hbitmap_iter_skip_words: + * @hbi: HBitmapIter to operate on. + * + * Internal function used by hbitmap_iter_next and hbitmap_iter_next_word. + */ +unsigned long hbitmap_iter_skip_words(HBitmapIter *hbi); + +/** + * hbitmap_iter_next: + * @hbi: HBitmapIter to operate on. + * + * Return the next bit that is set in @hbi's associated HBitmap, + * or -1 if all remaining bits are zero. + */ +static inline int64_t hbitmap_iter_next(HBitmapIter *hbi) +{ + unsigned long cur = hbi->cur[HBITMAP_LEVELS - 1]; + int64_t item; + + if (cur == 0) { + cur = hbitmap_iter_skip_words(hbi); + if (cur == 0) { + return -1; + } + } + + /* The next call will resume work from the next bit. */ + hbi->cur[HBITMAP_LEVELS - 1] = cur & (cur - 1); + item = ((uint64_t)hbi->pos << BITS_PER_LEVEL) + ctzl(cur); + + return item << hbi->granularity; +} + +/** + * hbitmap_iter_next_word: + * @hbi: HBitmapIter to operate on. + * @p_cur: Location where to store the next non-zero word. + * + * Return the index of the next nonzero word that is set in @hbi's + * associated HBitmap, and set *p_cur to the content of that word + * (bits before the index that was passed to hbitmap_iter_init are + * trimmed on the first call). Return -1, and set *p_cur to zero, + * if all remaining words are zero. + */ +static inline size_t hbitmap_iter_next_word(HBitmapIter *hbi, unsigned long *p_cur) +{ + unsigned long cur = hbi->cur[HBITMAP_LEVELS - 1]; + + if (cur == 0) { + cur = hbitmap_iter_skip_words(hbi); + if (cur == 0) { + *p_cur = 0; + return -1; + } + } + + /* The next call will resume work from the next word. */ + hbi->cur[HBITMAP_LEVELS - 1] = 0; + *p_cur = cur; + return hbi->pos; +} + + +#endif diff --git a/src/include/qemu/host-utils.h b/src/include/qemu/host-utils.h new file mode 100644 index 0000000..3ef97d5 --- /dev/null +++ b/src/include/qemu/host-utils.h @@ -0,0 +1,521 @@ +/* + * Utility compute operations used by translated code. + * + * Copyright (c) 2007 Thiemo Seufer + * Copyright (c) 2007 Jocelyn Mayer + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ +#ifndef HOST_UTILS_H +#define HOST_UTILS_H 1 + +#include "qemu/compiler.h" /* QEMU_GNUC_PREREQ */ +#include "qemu/bswap.h" +#include <limits.h> +#include <stdbool.h> + +#ifdef CONFIG_INT128 +static inline void mulu64(uint64_t *plow, uint64_t *phigh, + uint64_t a, uint64_t b) +{ + __uint128_t r = (__uint128_t)a * b; + *plow = r; + *phigh = r >> 64; +} + +static inline void muls64(uint64_t *plow, uint64_t *phigh, + int64_t a, int64_t b) +{ + __int128_t r = (__int128_t)a * b; + *plow = r; + *phigh = r >> 64; +} + +/* compute with 96 bit intermediate result: (a*b)/c */ +static inline uint64_t muldiv64(uint64_t a, uint32_t b, uint32_t c) +{ + return (__int128_t)a * b / c; +} + +static inline int divu128(uint64_t *plow, uint64_t *phigh, uint64_t divisor) +{ + if (divisor == 0) { + return 1; + } else { + __uint128_t dividend = ((__uint128_t)*phigh << 64) | *plow; + __uint128_t result = dividend / divisor; + *plow = result; + *phigh = dividend % divisor; + return result > UINT64_MAX; + } +} + +static inline int divs128(int64_t *plow, int64_t *phigh, int64_t divisor) +{ + if (divisor == 0) { + return 1; + } else { + __int128_t dividend = ((__int128_t)*phigh << 64) | *plow; + __int128_t result = dividend / divisor; + *plow = result; + *phigh = dividend % divisor; + return result != *plow; + } +} +#else +void muls64(uint64_t *phigh, uint64_t *plow, int64_t a, int64_t b); +void mulu64(uint64_t *phigh, uint64_t *plow, uint64_t a, uint64_t b); +int divu128(uint64_t *plow, uint64_t *phigh, uint64_t divisor); +int divs128(int64_t *plow, int64_t *phigh, int64_t divisor); + +static inline uint64_t muldiv64(uint64_t a, uint32_t b, uint32_t c) +{ + union { + uint64_t ll; + struct { +#ifdef HOST_WORDS_BIGENDIAN + uint32_t high, low; +#else + uint32_t low, high; +#endif + } l; + } u, res; + uint64_t rl, rh; + + u.ll = a; + rl = (uint64_t)u.l.low * (uint64_t)b; + rh = (uint64_t)u.l.high * (uint64_t)b; + rh += (rl >> 32); + res.l.high = rh / c; + res.l.low = (((rh % c) << 32) + (rl & 0xffffffff)) / c; + return res.ll; +} +#endif + +/** + * clz32 - count leading zeros in a 32-bit value. + * @val: The value to search + * + * Returns 32 if the value is zero. Note that the GCC builtin is + * undefined if the value is zero. + */ +static inline int clz32(uint32_t val) +{ +#if QEMU_GNUC_PREREQ(3, 4) + return val ? __builtin_clz(val) : 32; +#else + /* Binary search for the leading one bit. */ + int cnt = 0; + + if (!(val & 0xFFFF0000U)) { + cnt += 16; + val <<= 16; + } + if (!(val & 0xFF000000U)) { + cnt += 8; + val <<= 8; + } + if (!(val & 0xF0000000U)) { + cnt += 4; + val <<= 4; + } + if (!(val & 0xC0000000U)) { + cnt += 2; + val <<= 2; + } + if (!(val & 0x80000000U)) { + cnt++; + val <<= 1; + } + if (!(val & 0x80000000U)) { + cnt++; + } + return cnt; +#endif +} + +/** + * clo32 - count leading ones in a 32-bit value. + * @val: The value to search + * + * Returns 32 if the value is -1. + */ +static inline int clo32(uint32_t val) +{ + return clz32(~val); +} + +/** + * clz64 - count leading zeros in a 64-bit value. + * @val: The value to search + * + * Returns 64 if the value is zero. Note that the GCC builtin is + * undefined if the value is zero. + */ +static inline int clz64(uint64_t val) +{ +#if QEMU_GNUC_PREREQ(3, 4) + return val ? __builtin_clzll(val) : 64; +#else + int cnt = 0; + + if (!(val >> 32)) { + cnt += 32; + } else { + val >>= 32; + } + + return cnt + clz32(val); +#endif +} + +/** + * clo64 - count leading ones in a 64-bit value. + * @val: The value to search + * + * Returns 64 if the value is -1. + */ +static inline int clo64(uint64_t val) +{ + return clz64(~val); +} + +/** + * ctz32 - count trailing zeros in a 32-bit value. + * @val: The value to search + * + * Returns 32 if the value is zero. Note that the GCC builtin is + * undefined if the value is zero. + */ +static inline int ctz32(uint32_t val) +{ +#if QEMU_GNUC_PREREQ(3, 4) + return val ? __builtin_ctz(val) : 32; +#else + /* Binary search for the trailing one bit. */ + int cnt; + + cnt = 0; + if (!(val & 0x0000FFFFUL)) { + cnt += 16; + val >>= 16; + } + if (!(val & 0x000000FFUL)) { + cnt += 8; + val >>= 8; + } + if (!(val & 0x0000000FUL)) { + cnt += 4; + val >>= 4; + } + if (!(val & 0x00000003UL)) { + cnt += 2; + val >>= 2; + } + if (!(val & 0x00000001UL)) { + cnt++; + val >>= 1; + } + if (!(val & 0x00000001UL)) { + cnt++; + } + + return cnt; +#endif +} + +/** + * cto32 - count trailing ones in a 32-bit value. + * @val: The value to search + * + * Returns 32 if the value is -1. + */ +static inline int cto32(uint32_t val) +{ + return ctz32(~val); +} + +/** + * ctz64 - count trailing zeros in a 64-bit value. + * @val: The value to search + * + * Returns 64 if the value is zero. Note that the GCC builtin is + * undefined if the value is zero. + */ +static inline int ctz64(uint64_t val) +{ +#if QEMU_GNUC_PREREQ(3, 4) + return val ? __builtin_ctzll(val) : 64; +#else + int cnt; + + cnt = 0; + if (!((uint32_t)val)) { + cnt += 32; + val >>= 32; + } + + return cnt + ctz32(val); +#endif +} + +/** + * cto64 - count trailing ones in a 64-bit value. + * @val: The value to search + * + * Returns 64 if the value is -1. + */ +static inline int cto64(uint64_t val) +{ + return ctz64(~val); +} + +/** + * clrsb32 - count leading redundant sign bits in a 32-bit value. + * @val: The value to search + * + * Returns the number of bits following the sign bit that are equal to it. + * No special cases; output range is [0-31]. + */ +static inline int clrsb32(uint32_t val) +{ +#if QEMU_GNUC_PREREQ(4, 7) + return __builtin_clrsb(val); +#else + return clz32(val ^ ((int32_t)val >> 1)) - 1; +#endif +} + +/** + * clrsb64 - count leading redundant sign bits in a 64-bit value. + * @val: The value to search + * + * Returns the number of bits following the sign bit that are equal to it. + * No special cases; output range is [0-63]. + */ +static inline int clrsb64(uint64_t val) +{ +#if QEMU_GNUC_PREREQ(4, 7) + return __builtin_clrsbll(val); +#else + return clz64(val ^ ((int64_t)val >> 1)) - 1; +#endif +} + +/** + * ctpop8 - count the population of one bits in an 8-bit value. + * @val: The value to search + */ +static inline int ctpop8(uint8_t val) +{ +#if QEMU_GNUC_PREREQ(3, 4) + return __builtin_popcount(val); +#else + val = (val & 0x55) + ((val >> 1) & 0x55); + val = (val & 0x33) + ((val >> 2) & 0x33); + val = (val & 0x0f) + ((val >> 4) & 0x0f); + + return val; +#endif +} + +/** + * ctpop16 - count the population of one bits in a 16-bit value. + * @val: The value to search + */ +static inline int ctpop16(uint16_t val) +{ +#if QEMU_GNUC_PREREQ(3, 4) + return __builtin_popcount(val); +#else + val = (val & 0x5555) + ((val >> 1) & 0x5555); + val = (val & 0x3333) + ((val >> 2) & 0x3333); + val = (val & 0x0f0f) + ((val >> 4) & 0x0f0f); + val = (val & 0x00ff) + ((val >> 8) & 0x00ff); + + return val; +#endif +} + +/** + * ctpop32 - count the population of one bits in a 32-bit value. + * @val: The value to search + */ +static inline int ctpop32(uint32_t val) +{ +#if QEMU_GNUC_PREREQ(3, 4) + return __builtin_popcount(val); +#else + val = (val & 0x55555555) + ((val >> 1) & 0x55555555); + val = (val & 0x33333333) + ((val >> 2) & 0x33333333); + val = (val & 0x0f0f0f0f) + ((val >> 4) & 0x0f0f0f0f); + val = (val & 0x00ff00ff) + ((val >> 8) & 0x00ff00ff); + val = (val & 0x0000ffff) + ((val >> 16) & 0x0000ffff); + + return val; +#endif +} + +/** + * ctpop64 - count the population of one bits in a 64-bit value. + * @val: The value to search + */ +static inline int ctpop64(uint64_t val) +{ +#if QEMU_GNUC_PREREQ(3, 4) + return __builtin_popcountll(val); +#else + val = (val & 0x5555555555555555ULL) + ((val >> 1) & 0x5555555555555555ULL); + val = (val & 0x3333333333333333ULL) + ((val >> 2) & 0x3333333333333333ULL); + val = (val & 0x0f0f0f0f0f0f0f0fULL) + ((val >> 4) & 0x0f0f0f0f0f0f0f0fULL); + val = (val & 0x00ff00ff00ff00ffULL) + ((val >> 8) & 0x00ff00ff00ff00ffULL); + val = (val & 0x0000ffff0000ffffULL) + ((val >> 16) & 0x0000ffff0000ffffULL); + val = (val & 0x00000000ffffffffULL) + ((val >> 32) & 0x00000000ffffffffULL); + + return val; +#endif +} + +/** + * revbit8 - reverse the bits in an 8-bit value. + * @x: The value to modify. + */ +static inline uint8_t revbit8(uint8_t x) +{ + /* Assign the correct nibble position. */ + x = ((x & 0xf0) >> 4) + | ((x & 0x0f) << 4); + /* Assign the correct bit position. */ + x = ((x & 0x88) >> 3) + | ((x & 0x44) >> 1) + | ((x & 0x22) << 1) + | ((x & 0x11) << 3); + return x; +} + +/** + * revbit16 - reverse the bits in a 16-bit value. + * @x: The value to modify. + */ +static inline uint16_t revbit16(uint16_t x) +{ + /* Assign the correct byte position. */ + x = bswap16(x); + /* Assign the correct nibble position. */ + x = ((x & 0xf0f0) >> 4) + | ((x & 0x0f0f) << 4); + /* Assign the correct bit position. */ + x = ((x & 0x8888) >> 3) + | ((x & 0x4444) >> 1) + | ((x & 0x2222) << 1) + | ((x & 0x1111) << 3); + return x; +} + +/** + * revbit32 - reverse the bits in a 32-bit value. + * @x: The value to modify. + */ +static inline uint32_t revbit32(uint32_t x) +{ + /* Assign the correct byte position. */ + x = bswap32(x); + /* Assign the correct nibble position. */ + x = ((x & 0xf0f0f0f0u) >> 4) + | ((x & 0x0f0f0f0fu) << 4); + /* Assign the correct bit position. */ + x = ((x & 0x88888888u) >> 3) + | ((x & 0x44444444u) >> 1) + | ((x & 0x22222222u) << 1) + | ((x & 0x11111111u) << 3); + return x; +} + +/** + * revbit64 - reverse the bits in a 64-bit value. + * @x: The value to modify. + */ +static inline uint64_t revbit64(uint64_t x) +{ + /* Assign the correct byte position. */ + x = bswap64(x); + /* Assign the correct nibble position. */ + x = ((x & 0xf0f0f0f0f0f0f0f0ull) >> 4) + | ((x & 0x0f0f0f0f0f0f0f0full) << 4); + /* Assign the correct bit position. */ + x = ((x & 0x8888888888888888ull) >> 3) + | ((x & 0x4444444444444444ull) >> 1) + | ((x & 0x2222222222222222ull) << 1) + | ((x & 0x1111111111111111ull) << 3); + return x; +} + +/* Host type specific sizes of these routines. */ + +#if ULONG_MAX == UINT32_MAX +# define clzl clz32 +# define ctzl ctz32 +# define clol clo32 +# define ctol cto32 +# define ctpopl ctpop32 +# define revbitl revbit32 +#elif ULONG_MAX == UINT64_MAX +# define clzl clz64 +# define ctzl ctz64 +# define clol clo64 +# define ctol cto64 +# define ctpopl ctpop64 +# define revbitl revbit64 +#else +# error Unknown sizeof long +#endif + +static inline bool is_power_of_2(uint64_t value) +{ + if (!value) { + return 0; + } + + return !(value & (value - 1)); +} + +/* round down to the nearest power of 2*/ +static inline int64_t pow2floor(int64_t value) +{ + if (!is_power_of_2(value)) { + value = 0x8000000000000000ULL >> clz64(value); + } + return value; +} + +/* round up to the nearest power of 2 (0 if overflow) */ +static inline uint64_t pow2ceil(uint64_t value) +{ + uint8_t nlz = clz64(value); + + if (is_power_of_2(value)) { + return value; + } + if (!nlz) { + return 0; + } + return 1ULL << (64 - nlz); +} + +#endif diff --git a/src/include/qemu/int128.h b/src/include/qemu/int128.h new file mode 100644 index 0000000..fb782aa --- /dev/null +++ b/src/include/qemu/int128.h @@ -0,0 +1,149 @@ +#ifndef INT128_H +#define INT128_H + +#include <assert.h> +#include <stdint.h> +#include <stdbool.h> + +typedef struct Int128 Int128; + +struct Int128 { + uint64_t lo; + int64_t hi; +}; + +static inline Int128 int128_make64(uint64_t a) +{ + return (Int128) { a, 0 }; +} + +static inline uint64_t int128_get64(Int128 a) +{ + assert(!a.hi); + return a.lo; +} + +static inline Int128 int128_zero(void) +{ + return int128_make64(0); +} + +static inline Int128 int128_one(void) +{ + return int128_make64(1); +} + +static inline Int128 int128_2_64(void) +{ + return (Int128) { 0, 1 }; +} + +static inline Int128 int128_exts64(int64_t a) +{ + return (Int128) { .lo = a, .hi = (a < 0) ? -1 : 0 }; +} + +static inline Int128 int128_and(Int128 a, Int128 b) +{ + return (Int128) { a.lo & b.lo, a.hi & b.hi }; +} + +static inline Int128 int128_rshift(Int128 a, int n) +{ + int64_t h; + if (!n) { + return a; + } + h = a.hi >> (n & 63); + if (n >= 64) { + return (Int128) { h, h >> 63 }; + } else { + return (Int128) { (a.lo >> n) | ((uint64_t)a.hi << (64 - n)), h }; + } +} + +static inline Int128 int128_add(Int128 a, Int128 b) +{ + uint64_t lo = a.lo + b.lo; + + /* a.lo <= a.lo + b.lo < a.lo + k (k is the base, 2^64). Hence, + * a.lo + b.lo >= k implies 0 <= lo = a.lo + b.lo - k < a.lo. + * Similarly, a.lo + b.lo < k implies a.lo <= lo = a.lo + b.lo < k. + * + * So the carry is lo < a.lo. + */ + return (Int128) { lo, (uint64_t)a.hi + b.hi + (lo < a.lo) }; +} + +static inline Int128 int128_neg(Int128 a) +{ + uint64_t lo = -a.lo; + return (Int128) { lo, ~(uint64_t)a.hi + !lo }; +} + +static inline Int128 int128_sub(Int128 a, Int128 b) +{ + return (Int128){ a.lo - b.lo, (uint64_t)a.hi - b.hi - (a.lo < b.lo) }; +} + +static inline bool int128_nonneg(Int128 a) +{ + return a.hi >= 0; +} + +static inline bool int128_eq(Int128 a, Int128 b) +{ + return a.lo == b.lo && a.hi == b.hi; +} + +static inline bool int128_ne(Int128 a, Int128 b) +{ + return !int128_eq(a, b); +} + +static inline bool int128_ge(Int128 a, Int128 b) +{ + return a.hi > b.hi || (a.hi == b.hi && a.lo >= b.lo); +} + +static inline bool int128_lt(Int128 a, Int128 b) +{ + return !int128_ge(a, b); +} + +static inline bool int128_le(Int128 a, Int128 b) +{ + return int128_ge(b, a); +} + +static inline bool int128_gt(Int128 a, Int128 b) +{ + return !int128_le(a, b); +} + +static inline bool int128_nz(Int128 a) +{ + return a.lo || a.hi; +} + +static inline Int128 int128_min(Int128 a, Int128 b) +{ + return int128_le(a, b) ? a : b; +} + +static inline Int128 int128_max(Int128 a, Int128 b) +{ + return int128_ge(a, b) ? a : b; +} + +static inline void int128_addto(Int128 *a, Int128 b) +{ + *a = int128_add(*a, b); +} + +static inline void int128_subfrom(Int128 *a, Int128 b) +{ + *a = int128_sub(*a, b); +} + +#endif diff --git a/src/include/qemu/iov.h b/src/include/qemu/iov.h new file mode 100644 index 0000000..569b2c2 --- /dev/null +++ b/src/include/qemu/iov.h @@ -0,0 +1,115 @@ +/* + * Helpers for using (partial) iovecs. + * + * Copyright (C) 2010 Red Hat, Inc. + * + * Author(s): + * Amit Shah <amit.shah@redhat.com> + * Michael Tokarev <mjt@tls.msk.ru> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#ifndef IOV_H +#define IOV_H + +#include "qemu-common.h" + +/** + * count and return data size, in bytes, of an iovec + * starting at `iov' of `iov_cnt' number of elements. + */ +size_t iov_size(const struct iovec *iov, const unsigned int iov_cnt); + +/** + * Copy from single continuous buffer to scatter-gather vector of buffers + * (iovec) and back like memcpy() between two continuous memory regions. + * Data in single continuous buffer starting at address `buf' and + * `bytes' bytes long will be copied to/from an iovec `iov' with + * `iov_cnt' number of elements, starting at byte position `offset' + * within the iovec. If the iovec does not contain enough space, + * only part of data will be copied, up to the end of the iovec. + * Number of bytes actually copied will be returned, which is + * min(bytes, iov_size(iov)-offset) + * `Offset' must point to the inside of iovec. + * It is okay to use very large value for `bytes' since we're + * limited by the size of the iovec anyway, provided that the + * buffer pointed to by buf has enough space. One possible + * such "large" value is -1 (sinice size_t is unsigned), + * so specifying `-1' as `bytes' means 'up to the end of iovec'. + */ +size_t iov_from_buf(const struct iovec *iov, unsigned int iov_cnt, + size_t offset, const void *buf, size_t bytes); +size_t iov_to_buf(const struct iovec *iov, const unsigned int iov_cnt, + size_t offset, void *buf, size_t bytes); + +/** + * Set data bytes pointed out by iovec `iov' of size `iov_cnt' elements, + * starting at byte offset `start', to value `fillc', repeating it + * `bytes' number of times. `Offset' must point to the inside of iovec. + * If `bytes' is large enough, only last bytes portion of iovec, + * up to the end of it, will be filled with the specified value. + * Function return actual number of bytes processed, which is + * min(size, iov_size(iov) - offset). + * Again, it is okay to use large value for `bytes' to mean "up to the end". + */ +size_t iov_memset(const struct iovec *iov, const unsigned int iov_cnt, + size_t offset, int fillc, size_t bytes); + +/* + * Send/recv data from/to iovec buffers directly + * + * `offset' bytes in the beginning of iovec buffer are skipped and + * next `bytes' bytes are used, which must be within data of iovec. + * + * r = iov_send_recv(sockfd, iov, iovcnt, offset, bytes, true); + * + * is logically equivalent to + * + * char *buf = malloc(bytes); + * iov_to_buf(iov, iovcnt, offset, buf, bytes); + * r = send(sockfd, buf, bytes, 0); + * free(buf); + * + * For iov_send_recv() _whole_ area being sent or received + * should be within the iovec, not only beginning of it. + */ +ssize_t iov_send_recv(int sockfd, const struct iovec *iov, unsigned iov_cnt, + size_t offset, size_t bytes, bool do_send); +#define iov_recv(sockfd, iov, iov_cnt, offset, bytes) \ + iov_send_recv(sockfd, iov, iov_cnt, offset, bytes, false) +#define iov_send(sockfd, iov, iov_cnt, offset, bytes) \ + iov_send_recv(sockfd, iov, iov_cnt, offset, bytes, true) + +/** + * Produce a text hexdump of iovec `iov' with `iov_cnt' number of elements + * in file `fp', prefixing each line with `prefix' and processing not more + * than `limit' data bytes. + */ +void iov_hexdump(const struct iovec *iov, const unsigned int iov_cnt, + FILE *fp, const char *prefix, size_t limit); + +/* + * Partial copy of vector from iov to dst_iov (data is not copied). + * dst_iov overlaps iov at a specified offset. + * size of dst_iov is at most bytes. dst vector count is returned. + */ +unsigned iov_copy(struct iovec *dst_iov, unsigned int dst_iov_cnt, + const struct iovec *iov, unsigned int iov_cnt, + size_t offset, size_t bytes); + +/* + * Remove a given number of bytes from the front or back of a vector. + * This may update iov and/or iov_cnt to exclude iovec elements that are + * no longer required. + * + * The number of bytes actually discarded is returned. This number may be + * smaller than requested if the vector is too small. + */ +size_t iov_discard_front(struct iovec **iov, unsigned int *iov_cnt, + size_t bytes); +size_t iov_discard_back(struct iovec *iov, unsigned int *iov_cnt, + size_t bytes); + +#endif diff --git a/src/include/qemu/log.h b/src/include/qemu/log.h new file mode 100644 index 0000000..362cbc4 --- /dev/null +++ b/src/include/qemu/log.h @@ -0,0 +1,185 @@ +#ifndef QEMU_LOG_H +#define QEMU_LOG_H + +#include <stdarg.h> +#include <stdbool.h> +#include <stdio.h> +#include "qemu/compiler.h" +#include "qom/cpu.h" +#ifdef NEED_CPU_H +#include "disas/disas.h" +#endif + +/* Private global variables, don't use */ +extern FILE *qemu_logfile; +extern int qemu_loglevel; + +/* + * The new API: + * + */ + +/* Log settings checking macros: */ + +/* Returns true if qemu_log() will really write somewhere + */ +static inline bool qemu_log_enabled(void) +{ + return qemu_logfile != NULL; +} + +#define CPU_LOG_TB_OUT_ASM (1 << 0) +#define CPU_LOG_TB_IN_ASM (1 << 1) +#define CPU_LOG_TB_OP (1 << 2) +#define CPU_LOG_TB_OP_OPT (1 << 3) +#define CPU_LOG_INT (1 << 4) +#define CPU_LOG_EXEC (1 << 5) +#define CPU_LOG_PCALL (1 << 6) +#define CPU_LOG_TB_CPU (1 << 8) +#define CPU_LOG_RESET (1 << 9) +#define LOG_UNIMP (1 << 10) +#define LOG_GUEST_ERROR (1 << 11) +#define CPU_LOG_MMU (1 << 12) +#define CPU_LOG_TB_NOCHAIN (1 << 13) + +/* Returns true if a bit is set in the current loglevel mask + */ +static inline bool qemu_loglevel_mask(int mask) +{ + return (qemu_loglevel & mask) != 0; +} + +/* Logging functions: */ + +/* main logging function + */ +void GCC_FMT_ATTR(1, 2) qemu_log(const char *fmt, ...); + +/* vfprintf-like logging function + */ +static inline void GCC_FMT_ATTR(1, 0) +qemu_log_vprintf(const char *fmt, va_list va) +{ + if (qemu_logfile) { + vfprintf(qemu_logfile, fmt, va); + } +} + +/* log only if a bit is set on the current loglevel mask + */ +void GCC_FMT_ATTR(2, 3) qemu_log_mask(int mask, const char *fmt, ...); + + +/* Special cases: */ + +/* cpu_dump_state() logging functions: */ +/** + * log_cpu_state: + * @cpu: The CPU whose state is to be logged. + * @flags: Flags what to log. + * + * Logs the output of cpu_dump_state(). + */ +static inline void log_cpu_state(CPUState *cpu, int flags) +{ + if (qemu_log_enabled()) { + cpu_dump_state(cpu, qemu_logfile, fprintf, flags); + } +} + +/** + * log_cpu_state_mask: + * @mask: Mask when to log. + * @cpu: The CPU whose state is to be logged. + * @flags: Flags what to log. + * + * Logs the output of cpu_dump_state() if loglevel includes @mask. + */ +static inline void log_cpu_state_mask(int mask, CPUState *cpu, int flags) +{ + if (qemu_loglevel & mask) { + log_cpu_state(cpu, flags); + } +} + +#ifdef NEED_CPU_H +/* disas() and target_disas() to qemu_logfile: */ +static inline void log_target_disas(CPUState *cpu, target_ulong start, + target_ulong len, int flags) +{ + target_disas(qemu_logfile, cpu, start, len, flags); +} + +static inline void log_disas(void *code, unsigned long size) +{ + disas(qemu_logfile, code, size); +} + +#if defined(CONFIG_USER_ONLY) +/* page_dump() output to the log file: */ +static inline void log_page_dump(void) +{ + page_dump(qemu_logfile); +} +#endif +#endif + + +/* Maintenance: */ + +/* fflush() the log file */ +static inline void qemu_log_flush(void) +{ + fflush(qemu_logfile); +} + +/* Close the log file */ +static inline void qemu_log_close(void) +{ + if (qemu_logfile) { + if (qemu_logfile != stderr) { + fclose(qemu_logfile); + } + qemu_logfile = NULL; + } +} + +/* Set up a new log file */ +static inline void qemu_log_set_file(FILE *f) +{ + qemu_logfile = f; +} + +/* define log items */ +typedef struct QEMULogItem { + int mask; + const char *name; + const char *help; +} QEMULogItem; + +extern const QEMULogItem qemu_log_items[]; + +/* This is the function that actually does the work of + * changing the log level; it should only be accessed via + * the qemu_set_log() wrapper. + */ +void do_qemu_set_log(int log_flags, bool use_own_buffers); + +static inline void qemu_set_log(int log_flags) +{ +#ifdef CONFIG_USER_ONLY + do_qemu_set_log(log_flags, true); +#else + do_qemu_set_log(log_flags, false); +#endif +} + +void qemu_set_log_filename(const char *filename); +int qemu_str_to_log_mask(const char *str); + +/* Print a usage message listing all the valid logging categories + * to the specified FILE*. + */ +void qemu_print_log_usage(FILE *f); + +#endif diff --git a/src/include/qemu/main-loop.h b/src/include/qemu/main-loop.h new file mode 100644 index 0000000..9976909 --- /dev/null +++ b/src/include/qemu/main-loop.h @@ -0,0 +1,273 @@ +/* + * QEMU System Emulator + * + * Copyright (c) 2003-2008 Fabrice Bellard + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef QEMU_MAIN_LOOP_H +#define QEMU_MAIN_LOOP_H 1 + +#include "block/aio.h" + +#define SIG_IPI SIGUSR1 + +/** + * qemu_init_main_loop: Set up the process so that it can run the main loop. + * + * This includes setting up signal handlers. It should be called before + * any other threads are created. In addition, threads other than the + * main one should block signals that are trapped by the main loop. + * For simplicity, you can consider these signals to be safe: SIGUSR1, + * SIGUSR2, thread signals (SIGFPE, SIGILL, SIGSEGV, SIGBUS) and real-time + * signals if available. Remember that Windows in practice does not have + * signals, though. + * + * In the case of QEMU tools, this will also start/initialize timers. + */ +int qemu_init_main_loop(Error **errp); + +/** + * main_loop_wait: Run one iteration of the main loop. + * + * If @nonblocking is true, poll for events, otherwise suspend until + * one actually occurs. The main loop usually consists of a loop that + * repeatedly calls main_loop_wait(false). + * + * Main loop services include file descriptor callbacks, bottom halves + * and timers (defined in qemu-timer.h). Bottom halves are similar to timers + * that execute immediately, but have a lower overhead and scheduling them + * is wait-free, thread-safe and signal-safe. + * + * It is sometimes useful to put a whole program in a coroutine. In this + * case, the coroutine actually should be started from within the main loop, + * so that the main loop can run whenever the coroutine yields. To do this, + * you can use a bottom half to enter the coroutine as soon as the main loop + * starts: + * + * void enter_co_bh(void *opaque) { + * QEMUCoroutine *co = opaque; + * qemu_coroutine_enter(co, NULL); + * } + * + * ... + * QEMUCoroutine *co = qemu_coroutine_create(coroutine_entry); + * QEMUBH *start_bh = qemu_bh_new(enter_co_bh, co); + * qemu_bh_schedule(start_bh); + * while (...) { + * main_loop_wait(false); + * } + * + * (In the future we may provide a wrapper for this). + * + * @nonblocking: Whether the caller should block until an event occurs. + */ +int main_loop_wait(int nonblocking); + +/** + * qemu_get_aio_context: Return the main loop's AioContext + */ +AioContext *qemu_get_aio_context(void); + +/** + * qemu_notify_event: Force processing of pending events. + * + * Similar to signaling a condition variable, qemu_notify_event forces + * main_loop_wait to look at pending events and exit. The caller of + * main_loop_wait will usually call it again very soon, so qemu_notify_event + * also has the side effect of recalculating the sets of file descriptors + * that the main loop waits for. + * + * Calling qemu_notify_event is rarely necessary, because main loop + * services (bottom halves and timers) call it themselves. + */ +void qemu_notify_event(void); + +#ifdef _WIN32 +/* return TRUE if no sleep should be done afterwards */ +typedef int PollingFunc(void *opaque); + +/** + * qemu_add_polling_cb: Register a Windows-specific polling callback + * + * Currently, under Windows some events are polled rather than waited for. + * Polling callbacks do not ensure that @func is called timely, because + * the main loop might wait for an arbitrarily long time. If possible, + * you should instead create a separate thread that does a blocking poll + * and set a Win32 event object. The event can then be passed to + * qemu_add_wait_object. + * + * Polling callbacks really have nothing Windows specific in them, but + * as they are a hack and are currently not necessary under POSIX systems, + * they are only available when QEMU is running under Windows. + * + * @func: The function that does the polling, and returns 1 to force + * immediate completion of main_loop_wait. + * @opaque: A pointer-size value that is passed to @func. + */ +int qemu_add_polling_cb(PollingFunc *func, void *opaque); + +/** + * qemu_del_polling_cb: Unregister a Windows-specific polling callback + * + * This function removes a callback that was registered with + * qemu_add_polling_cb. + * + * @func: The function that was passed to qemu_add_polling_cb. + * @opaque: A pointer-size value that was passed to qemu_add_polling_cb. + */ +void qemu_del_polling_cb(PollingFunc *func, void *opaque); + +/* Wait objects handling */ +typedef void WaitObjectFunc(void *opaque); + +/** + * qemu_add_wait_object: Register a callback for a Windows handle + * + * Under Windows, the iohandler mechanism can only be used with sockets. + * QEMU must use the WaitForMultipleObjects API to wait on other handles. + * This function registers a #HANDLE with QEMU, so that it will be included + * in the main loop's calls to WaitForMultipleObjects. When the handle + * is in a signaled state, QEMU will call @func. + * + * @handle: The Windows handle to be observed. + * @func: A function to be called when @handle is in a signaled state. + * @opaque: A pointer-size value that is passed to @func. + */ +int qemu_add_wait_object(HANDLE handle, WaitObjectFunc *func, void *opaque); + +/** + * qemu_del_wait_object: Unregister a callback for a Windows handle + * + * This function removes a callback that was registered with + * qemu_add_wait_object. + * + * @func: The function that was passed to qemu_add_wait_object. + * @opaque: A pointer-size value that was passed to qemu_add_wait_object. + */ +void qemu_del_wait_object(HANDLE handle, WaitObjectFunc *func, void *opaque); +#endif + +/* async I/O support */ + +typedef void IOReadHandler(void *opaque, const uint8_t *buf, int size); +typedef int IOCanReadHandler(void *opaque); + +/** + * qemu_set_fd_handler: Register a file descriptor with the main loop + * + * This function tells the main loop to wake up whenever one of the + * following conditions is true: + * + * 1) if @fd_write is not %NULL, when the file descriptor is writable; + * + * 2) if @fd_read is not %NULL, when the file descriptor is readable. + * + * The callbacks that are set up by qemu_set_fd_handler are level-triggered. + * If @fd_read does not read from @fd, or @fd_write does not write to @fd + * until its buffers are full, they will be called again on the next + * iteration. + * + * @fd: The file descriptor to be observed. Under Windows it must be + * a #SOCKET. + * + * @fd_read: A level-triggered callback that is fired if @fd is readable + * at the beginning of a main loop iteration, or if it becomes readable + * during one. + * + * @fd_write: A level-triggered callback that is fired when @fd is writable + * at the beginning of a main loop iteration, or if it becomes writable + * during one. + * + * @opaque: A pointer-sized value that is passed to @fd_read and @fd_write. + */ +void qemu_set_fd_handler(int fd, + IOHandler *fd_read, + IOHandler *fd_write, + void *opaque); + +GSource *iohandler_get_g_source(void); +#ifdef CONFIG_POSIX +/** + * qemu_add_child_watch: Register a child process for reaping. + * + * Under POSIX systems, a parent process must read the exit status of + * its child processes using waitpid, or the operating system will not + * free some of the resources attached to that process. + * + * This function directs the QEMU main loop to observe a child process + * and call waitpid as soon as it exits; the watch is then removed + * automatically. It is useful whenever QEMU forks a child process + * but will find out about its termination by other means such as a + * "broken pipe". + * + * @pid: The pid that QEMU should observe. + */ +int qemu_add_child_watch(pid_t pid); +#endif + +/** + * qemu_mutex_iothread_locked: Return lock status of the main loop mutex. + * + * The main loop mutex is the coarsest lock in QEMU, and as such it + * must always be taken outside other locks. This function helps + * functions take different paths depending on whether the current + * thread is running within the main loop mutex. + */ +bool qemu_mutex_iothread_locked(void); + +/** + * qemu_mutex_lock_iothread: Lock the main loop mutex. + * + * This function locks the main loop mutex. The mutex is taken by + * qemu_init_main_loop and always taken except while waiting on + * external events (such as with select). The mutex should be taken + * by threads other than the main loop thread when calling + * qemu_bh_new(), qemu_set_fd_handler() and basically all other + * functions documented in this file. + * + * NOTE: tools currently are single-threaded and qemu_mutex_lock_iothread + * is a no-op there. + */ +void qemu_mutex_lock_iothread(void); + +/** + * qemu_mutex_unlock_iothread: Unlock the main loop mutex. + * + * This function unlocks the main loop mutex. The mutex is taken by + * qemu_init_main_loop and always taken except while waiting on + * external events (such as with select). The mutex should be unlocked + * as soon as possible by threads other than the main loop thread, + * because it prevents the main loop from processing callbacks, + * including timers and bottom halves. + * + * NOTE: tools currently are single-threaded and qemu_mutex_unlock_iothread + * is a no-op there. + */ +void qemu_mutex_unlock_iothread(void); + +/* internal interfaces */ + +void qemu_fd_register(int fd); + +QEMUBH *qemu_bh_new(QEMUBHFunc *cb, void *opaque); +void qemu_bh_schedule_idle(QEMUBH *bh); + +#endif diff --git a/src/include/qemu/memfd.h b/src/include/qemu/memfd.h new file mode 100644 index 0000000..53858ed --- /dev/null +++ b/src/include/qemu/memfd.h @@ -0,0 +1,26 @@ +#ifndef QEMU_MEMFD_H +#define QEMU_MEMFD_H + +#include "config-host.h" +#include <stdbool.h> + +#ifndef F_LINUX_SPECIFIC_BASE +#define F_LINUX_SPECIFIC_BASE 1024 +#endif + +#ifndef F_ADD_SEALS +#define F_ADD_SEALS (F_LINUX_SPECIFIC_BASE + 9) +#define F_GET_SEALS (F_LINUX_SPECIFIC_BASE + 10) + +#define F_SEAL_SEAL 0x0001 /* prevent further seals from being set */ +#define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */ +#define F_SEAL_GROW 0x0004 /* prevent file from growing */ +#define F_SEAL_WRITE 0x0008 /* prevent writes */ +#endif + +void *qemu_memfd_alloc(const char *name, size_t size, unsigned int seals, + int *fd); +void qemu_memfd_free(void *ptr, size_t size, int fd); +bool qemu_memfd_check(void); + +#endif /* QEMU_MEMFD_H */ diff --git a/src/include/qemu/mmap-alloc.h b/src/include/qemu/mmap-alloc.h new file mode 100644 index 0000000..0899b2f --- /dev/null +++ b/src/include/qemu/mmap-alloc.h @@ -0,0 +1,12 @@ +#ifndef QEMU_MMAP_ALLOC +#define QEMU_MMAP_ALLOC + +#include "qemu-common.h" + +size_t qemu_fd_getpagesize(int fd); + +void *qemu_ram_mmap(int fd, size_t size, size_t align, bool shared); + +void qemu_ram_munmap(void *ptr, size_t size); + +#endif diff --git a/src/include/qemu/module.h b/src/include/qemu/module.h new file mode 100644 index 0000000..72d9498 --- /dev/null +++ b/src/include/qemu/module.h @@ -0,0 +1,61 @@ +/* + * QEMU Module Infrastructure + * + * Copyright IBM, Corp. 2009 + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#ifndef QEMU_MODULE_H +#define QEMU_MODULE_H + +#include "qemu/osdep.h" + +#define DSO_STAMP_FUN glue(qemu_stamp, CONFIG_STAMP) +#define DSO_STAMP_FUN_STR stringify(DSO_STAMP_FUN) + +#ifdef BUILD_DSO +void DSO_STAMP_FUN(void); +/* This is a dummy symbol to identify a loaded DSO as a QEMU module, so we can + * distinguish "version mismatch" from "not a QEMU module", when the stamp + * check fails during module loading */ +void qemu_module_dummy(void); + +#define module_init(function, type) \ +static void __attribute__((constructor)) do_qemu_init_ ## function(void) \ +{ \ + register_dso_module_init(function, type); \ +} +#else +/* This should not be used directly. Use block_init etc. instead. */ +#define module_init(function, type) \ +static void __attribute__((constructor)) do_qemu_init_ ## function(void) \ +{ \ + register_module_init(function, type); \ +} +#endif + +typedef enum { + MODULE_INIT_BLOCK, + MODULE_INIT_MACHINE, + MODULE_INIT_QAPI, + MODULE_INIT_QOM, + MODULE_INIT_MAX +} module_init_type; + +#define block_init(function) module_init(function, MODULE_INIT_BLOCK) +#define machine_init(function) module_init(function, MODULE_INIT_MACHINE) +#define qapi_init(function) module_init(function, MODULE_INIT_QAPI) +#define type_init(function) module_init(function, MODULE_INIT_QOM) + +void register_module_init(void (*fn)(void), module_init_type type); +void register_dso_module_init(void (*fn)(void), module_init_type type); + +void module_call_init(module_init_type type); + +#endif diff --git a/src/include/qemu/notify.h b/src/include/qemu/notify.h new file mode 100644 index 0000000..a3d73e4 --- /dev/null +++ b/src/include/qemu/notify.h @@ -0,0 +1,72 @@ +/* + * Notifier lists + * + * Copyright IBM, Corp. 2010 + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#ifndef QEMU_NOTIFY_H +#define QEMU_NOTIFY_H + +#include "qemu/queue.h" + +typedef struct Notifier Notifier; + +struct Notifier +{ + void (*notify)(Notifier *notifier, void *data); + QLIST_ENTRY(Notifier) node; +}; + +typedef struct NotifierList +{ + QLIST_HEAD(, Notifier) notifiers; +} NotifierList; + +#define NOTIFIER_LIST_INITIALIZER(head) \ + { QLIST_HEAD_INITIALIZER((head).notifiers) } + +void notifier_list_init(NotifierList *list); + +void notifier_list_add(NotifierList *list, Notifier *notifier); + +void notifier_remove(Notifier *notifier); + +void notifier_list_notify(NotifierList *list, void *data); + +/* Same as Notifier but allows .notify() to return errors */ +typedef struct NotifierWithReturn NotifierWithReturn; + +struct NotifierWithReturn { + /** + * Return 0 on success (next notifier will be invoked), otherwise + * notifier_with_return_list_notify() will stop and return the value. + */ + int (*notify)(NotifierWithReturn *notifier, void *data); + QLIST_ENTRY(NotifierWithReturn) node; +}; + +typedef struct NotifierWithReturnList { + QLIST_HEAD(, NotifierWithReturn) notifiers; +} NotifierWithReturnList; + +#define NOTIFIER_WITH_RETURN_LIST_INITIALIZER(head) \ + { QLIST_HEAD_INITIALIZER((head).notifiers) } + +void notifier_with_return_list_init(NotifierWithReturnList *list); + +void notifier_with_return_list_add(NotifierWithReturnList *list, + NotifierWithReturn *notifier); + +void notifier_with_return_remove(NotifierWithReturn *notifier); + +int notifier_with_return_list_notify(NotifierWithReturnList *list, + void *data); + +#endif diff --git a/src/include/qemu/option.h b/src/include/qemu/option.h new file mode 100644 index 0000000..71f5f27 --- /dev/null +++ b/src/include/qemu/option.h @@ -0,0 +1,138 @@ +/* + * Commandline option parsing functions + * + * Copyright (c) 2003-2008 Fabrice Bellard + * Copyright (c) 2009 Kevin Wolf <kwolf@redhat.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef QEMU_OPTIONS_H +#define QEMU_OPTIONS_H + +#include <stdint.h> +#include "qemu/queue.h" +#include "qapi/error.h" +#include "qapi/qmp/qdict.h" +#include "qemu/typedefs.h" + +const char *get_opt_name(char *buf, int buf_size, const char *p, char delim); +const char *get_opt_value(char *buf, int buf_size, const char *p); +int get_next_param_value(char *buf, int buf_size, + const char *tag, const char **pstr); +int get_param_value(char *buf, int buf_size, + const char *tag, const char *str); + + +void parse_option_size(const char *name, const char *value, + uint64_t *ret, Error **errp); +bool has_help_option(const char *param); +bool is_valid_option_list(const char *param); + +enum QemuOptType { + QEMU_OPT_STRING = 0, /* no parsing (use string as-is) */ + QEMU_OPT_BOOL, /* on/off */ + QEMU_OPT_NUMBER, /* simple number */ + QEMU_OPT_SIZE, /* size, accepts (K)ilo, (M)ega, (G)iga, (T)era postfix */ +}; + +typedef struct QemuOptDesc { + const char *name; + enum QemuOptType type; + const char *help; + const char *def_value_str; +} QemuOptDesc; + +struct QemuOptsList { + const char *name; + const char *implied_opt_name; + bool merge_lists; /* Merge multiple uses of option into a single list? */ + QTAILQ_HEAD(, QemuOpts) head; + QemuOptDesc desc[]; +}; + +const char *qemu_opt_get(QemuOpts *opts, const char *name); +char *qemu_opt_get_del(QemuOpts *opts, const char *name); +/** + * qemu_opt_has_help_opt: + * @opts: options to search for a help request + * + * Check whether the options specified by @opts include one of the + * standard strings which indicate that the user is asking for a + * list of the valid values for a command line option (as defined + * by is_help_option()). + * + * Returns: true if @opts includes 'help' or equivalent. + */ +bool qemu_opt_has_help_opt(QemuOpts *opts); +QemuOpt *qemu_opt_find(QemuOpts *opts, const char *name); +bool qemu_opt_get_bool(QemuOpts *opts, const char *name, bool defval); +uint64_t qemu_opt_get_number(QemuOpts *opts, const char *name, uint64_t defval); +uint64_t qemu_opt_get_size(QemuOpts *opts, const char *name, uint64_t defval); +bool qemu_opt_get_bool_del(QemuOpts *opts, const char *name, bool defval); +uint64_t qemu_opt_get_number_del(QemuOpts *opts, const char *name, + uint64_t defval); +uint64_t qemu_opt_get_size_del(QemuOpts *opts, const char *name, + uint64_t defval); +int qemu_opt_unset(QemuOpts *opts, const char *name); +void qemu_opt_set(QemuOpts *opts, const char *name, const char *value, + Error **errp); +void qemu_opt_set_bool(QemuOpts *opts, const char *name, bool val, + Error **errp); +void qemu_opt_set_number(QemuOpts *opts, const char *name, int64_t val, + Error **errp); +typedef int (*qemu_opt_loopfunc)(void *opaque, + const char *name, const char *value, + Error **errp); +int qemu_opt_foreach(QemuOpts *opts, qemu_opt_loopfunc func, void *opaque, + Error **errp); + +QemuOpts *qemu_opts_find(QemuOptsList *list, const char *id); +QemuOpts *qemu_opts_create(QemuOptsList *list, const char *id, + int fail_if_exists, Error **errp); +void qemu_opts_reset(QemuOptsList *list); +void qemu_opts_loc_restore(QemuOpts *opts); +void qemu_opts_set(QemuOptsList *list, const char *id, + const char *name, const char *value, Error **errp); +const char *qemu_opts_id(QemuOpts *opts); +void qemu_opts_set_id(QemuOpts *opts, char *id); +void qemu_opts_del(QemuOpts *opts); +void qemu_opts_validate(QemuOpts *opts, const QemuOptDesc *desc, Error **errp); +void qemu_opts_do_parse(QemuOpts *opts, const char *params, + const char *firstname, Error **errp); +QemuOpts *qemu_opts_parse_noisily(QemuOptsList *list, const char *params, + bool permit_abbrev); +QemuOpts *qemu_opts_parse(QemuOptsList *list, const char *params, + bool permit_abbrev, Error **errp); +void qemu_opts_set_defaults(QemuOptsList *list, const char *params, + int permit_abbrev); +QemuOpts *qemu_opts_from_qdict(QemuOptsList *list, const QDict *qdict, + Error **errp); +QDict *qemu_opts_to_qdict(QemuOpts *opts, QDict *qdict); +void qemu_opts_absorb_qdict(QemuOpts *opts, QDict *qdict, Error **errp); + +typedef int (*qemu_opts_loopfunc)(void *opaque, QemuOpts *opts, Error **errp); +int qemu_opts_foreach(QemuOptsList *list, qemu_opts_loopfunc func, + void *opaque, Error **errp); +void qemu_opts_print(QemuOpts *opts, const char *sep); +void qemu_opts_print_help(QemuOptsList *list); +void qemu_opts_free(QemuOptsList *list); +QemuOptsList *qemu_opts_append(QemuOptsList *dst, QemuOptsList *list); + +#endif diff --git a/src/include/qemu/option_int.h b/src/include/qemu/option_int.h new file mode 100644 index 0000000..6432c1a --- /dev/null +++ b/src/include/qemu/option_int.h @@ -0,0 +1,54 @@ +/* + * Commandline option parsing functions + * + * Copyright (c) 2003-2008 Fabrice Bellard + * Copyright (c) 2009 Kevin Wolf <kwolf@redhat.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef QEMU_OPTIONS_INTERNAL_H +#define QEMU_OPTIONS_INTERNAL_H + +#include "qemu/option.h" +#include "qemu/error-report.h" + +struct QemuOpt { + char *name; + char *str; + + const QemuOptDesc *desc; + union { + bool boolean; + uint64_t uint; + } value; + + QemuOpts *opts; + QTAILQ_ENTRY(QemuOpt) next; +}; + +struct QemuOpts { + char *id; + QemuOptsList *list; + Location loc; + QTAILQ_HEAD(QemuOptHead, QemuOpt) head; + QTAILQ_ENTRY(QemuOpts) next; +}; + +#endif diff --git a/src/include/qemu/osdep.h b/src/include/qemu/osdep.h new file mode 100644 index 0000000..84e84ac --- /dev/null +++ b/src/include/qemu/osdep.h @@ -0,0 +1,318 @@ +/* + * OS includes and handling of OS dependencies + * + * This header exists to pull in some common system headers that + * most code in QEMU will want, and to fix up some possible issues with + * it (missing defines, Windows weirdness, and so on). + * + * To avoid getting into possible circular include dependencies, this + * file should not include any other QEMU headers, with the exceptions + * of config-host.h, compiler.h, os-posix.h and os-win32.h, all of which + * are doing a similar job to this file and are under similar constraints. + * + * This header also contains prototypes for functions defined in + * os-*.c and util/oslib-*.c; those would probably be better split + * out into separate header files. + * + * In an ideal world this header would contain only: + * (1) things which everybody needs + * (2) things without which code would work on most platforms but + * fail to compile or misbehave on a minority of host OSes + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ +#ifndef QEMU_OSDEP_H +#define QEMU_OSDEP_H + +#include "config-host.h" +#include "qemu/compiler.h" +#include <stdarg.h> +#include <stddef.h> +#include <stdbool.h> +#include <stdint.h> +#include <sys/types.h> +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <strings.h> +#include <inttypes.h> +#include <limits.h> +/* Put unistd.h before time.h as that triggers localtime_r/gmtime_r + * function availability on recentish Mingw-w64 platforms. */ +#include <unistd.h> +#include <time.h> +#include <ctype.h> +#include <errno.h> +#include <fcntl.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <assert.h> +#include <signal.h> + +#ifdef __OpenBSD__ +#include <sys/signal.h> +#endif + +#ifndef _WIN32 +#include <sys/wait.h> +#else +#define WIFEXITED(x) 1 +#define WEXITSTATUS(x) (x) +#endif + +#ifdef _WIN32 +#include "sysemu/os-win32.h" +#endif + +#ifdef CONFIG_POSIX +#include "sysemu/os-posix.h" +#endif + +#include "qapi/error.h" + +#if defined(CONFIG_SOLARIS) && CONFIG_SOLARIS_VERSION < 10 +/* [u]int_fast*_t not in <sys/int_types.h> */ +typedef unsigned char uint_fast8_t; +typedef unsigned int uint_fast16_t; +typedef signed int int_fast16_t; +#endif + +#ifndef O_LARGEFILE +#define O_LARGEFILE 0 +#endif +#ifndef O_BINARY +#define O_BINARY 0 +#endif +#ifndef MAP_ANONYMOUS +#define MAP_ANONYMOUS MAP_ANON +#endif +#ifndef ENOMEDIUM +#define ENOMEDIUM ENODEV +#endif +#if !defined(ENOTSUP) +#define ENOTSUP 4096 +#endif +#if !defined(ECANCELED) +#define ECANCELED 4097 +#endif +#if !defined(EMEDIUMTYPE) +#define EMEDIUMTYPE 4098 +#endif +#ifndef TIME_MAX +#define TIME_MAX LONG_MAX +#endif + +#ifndef MIN +#define MIN(a, b) (((a) < (b)) ? (a) : (b)) +#endif +#ifndef MAX +#define MAX(a, b) (((a) > (b)) ? (a) : (b)) +#endif + +/* Minimum function that returns zero only iff both values are zero. + * Intended for use with unsigned values only. */ +#ifndef MIN_NON_ZERO +#define MIN_NON_ZERO(a, b) (((a) != 0 && (a) < (b)) ? (a) : (b)) +#endif + +#ifndef ROUND_UP +#define ROUND_UP(n,d) (((n) + (d) - 1) & -(d)) +#endif + +#ifndef DIV_ROUND_UP +#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) +#endif + +#ifndef ARRAY_SIZE +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +int qemu_daemon(int nochdir, int noclose); +void *qemu_try_memalign(size_t alignment, size_t size); +void *qemu_memalign(size_t alignment, size_t size); +void *qemu_anon_ram_alloc(size_t size, uint64_t *align); +void qemu_vfree(void *ptr); +void qemu_anon_ram_free(void *ptr, size_t size); + +#define QEMU_MADV_INVALID -1 + +#if defined(CONFIG_MADVISE) + +#include <sys/mman.h> + +#define QEMU_MADV_WILLNEED MADV_WILLNEED +#define QEMU_MADV_DONTNEED MADV_DONTNEED +#ifdef MADV_DONTFORK +#define QEMU_MADV_DONTFORK MADV_DONTFORK +#else +#define QEMU_MADV_DONTFORK QEMU_MADV_INVALID +#endif +#ifdef MADV_MERGEABLE +#define QEMU_MADV_MERGEABLE MADV_MERGEABLE +#else +#define QEMU_MADV_MERGEABLE QEMU_MADV_INVALID +#endif +#ifdef MADV_UNMERGEABLE +#define QEMU_MADV_UNMERGEABLE MADV_UNMERGEABLE +#else +#define QEMU_MADV_UNMERGEABLE QEMU_MADV_INVALID +#endif +#ifdef MADV_DODUMP +#define QEMU_MADV_DODUMP MADV_DODUMP +#else +#define QEMU_MADV_DODUMP QEMU_MADV_INVALID +#endif +#ifdef MADV_DONTDUMP +#define QEMU_MADV_DONTDUMP MADV_DONTDUMP +#else +#define QEMU_MADV_DONTDUMP QEMU_MADV_INVALID +#endif +#ifdef MADV_HUGEPAGE +#define QEMU_MADV_HUGEPAGE MADV_HUGEPAGE +#else +#define QEMU_MADV_HUGEPAGE QEMU_MADV_INVALID +#endif +#ifdef MADV_NOHUGEPAGE +#define QEMU_MADV_NOHUGEPAGE MADV_NOHUGEPAGE +#else +#define QEMU_MADV_NOHUGEPAGE QEMU_MADV_INVALID +#endif + +#elif defined(CONFIG_POSIX_MADVISE) + +#define QEMU_MADV_WILLNEED POSIX_MADV_WILLNEED +#define QEMU_MADV_DONTNEED POSIX_MADV_DONTNEED +#define QEMU_MADV_DONTFORK QEMU_MADV_INVALID +#define QEMU_MADV_MERGEABLE QEMU_MADV_INVALID +#define QEMU_MADV_UNMERGEABLE QEMU_MADV_INVALID +#define QEMU_MADV_DODUMP QEMU_MADV_INVALID +#define QEMU_MADV_DONTDUMP QEMU_MADV_INVALID +#define QEMU_MADV_HUGEPAGE QEMU_MADV_INVALID +#define QEMU_MADV_NOHUGEPAGE QEMU_MADV_INVALID + +#else /* no-op */ + +#define QEMU_MADV_WILLNEED QEMU_MADV_INVALID +#define QEMU_MADV_DONTNEED QEMU_MADV_INVALID +#define QEMU_MADV_DONTFORK QEMU_MADV_INVALID +#define QEMU_MADV_MERGEABLE QEMU_MADV_INVALID +#define QEMU_MADV_UNMERGEABLE QEMU_MADV_INVALID +#define QEMU_MADV_DODUMP QEMU_MADV_INVALID +#define QEMU_MADV_DONTDUMP QEMU_MADV_INVALID +#define QEMU_MADV_HUGEPAGE QEMU_MADV_INVALID +#define QEMU_MADV_NOHUGEPAGE QEMU_MADV_INVALID + +#endif + +int qemu_madvise(void *addr, size_t len, int advice); + +int qemu_open(const char *name, int flags, ...); +int qemu_close(int fd); + +#if defined(__HAIKU__) && defined(__i386__) +#define FMT_pid "%ld" +#elif defined(WIN64) +#define FMT_pid "%" PRId64 +#else +#define FMT_pid "%d" +#endif + +int qemu_create_pidfile(const char *filename); +int qemu_get_thread_id(void); + +#ifndef CONFIG_IOVEC +struct iovec { + void *iov_base; + size_t iov_len; +}; +/* + * Use the same value as Linux for now. + */ +#define IOV_MAX 1024 + +ssize_t readv(int fd, const struct iovec *iov, int iov_cnt); +ssize_t writev(int fd, const struct iovec *iov, int iov_cnt); +#else +#include <sys/uio.h> +#endif + +#ifdef _WIN32 +static inline void qemu_timersub(const struct timeval *val1, + const struct timeval *val2, + struct timeval *res) +{ + res->tv_sec = val1->tv_sec - val2->tv_sec; + if (val1->tv_usec < val2->tv_usec) { + res->tv_sec--; + res->tv_usec = val1->tv_usec - val2->tv_usec + 1000 * 1000; + } else { + res->tv_usec = val1->tv_usec - val2->tv_usec; + } +} +#else +#define qemu_timersub timersub +#endif + +void qemu_set_cloexec(int fd); + +/* QEMU "hardware version" setting. Used to replace code that exposed + * QEMU_VERSION to guests in the past and need to keep compatibilty. + * Do not use qemu_hw_version() in new code. + */ +void qemu_set_hw_version(const char *); +const char *qemu_hw_version(void); + +void fips_set_state(bool requested); +bool fips_get_state(void); + +/* Return a dynamically allocated pathname denoting a file or directory that is + * appropriate for storing local state. + * + * @relative_pathname need not start with a directory separator; one will be + * added automatically. + * + * The caller is responsible for releasing the value returned with g_free() + * after use. + */ +char *qemu_get_local_state_pathname(const char *relative_pathname); + +/* Find program directory, and save it for later usage with + * qemu_get_exec_dir(). + * Try OS specific API first, if not working, parse from argv0. */ +void qemu_init_exec_dir(const char *argv0); + +/* Get the saved exec dir. + * Caller needs to release the returned string by g_free() */ +char *qemu_get_exec_dir(void); + +/** + * qemu_getauxval: + * @type: the auxiliary vector key to lookup + * + * Search the auxiliary vector for @type, returning the value + * or 0 if @type is not present. + */ +unsigned long qemu_getauxval(unsigned long type); + +void qemu_set_tty_echo(int fd, bool echo); + +void os_mem_prealloc(int fd, char *area, size_t sz); + +int qemu_read_password(char *buf, int buf_size); + +/** + * qemu_fork: + * + * A version of fork that avoids signal handler race + * conditions that can lead to child process getting + * signals that are otherwise only expected by the + * parent. It also resets all signal handlers to the + * default settings. + * + * Returns 0 to child process, pid number to parent + * or -1 on failure. + */ +pid_t qemu_fork(Error **errp); + +#endif diff --git a/src/include/qemu/queue.h b/src/include/qemu/queue.h new file mode 100644 index 0000000..b56bce5 --- /dev/null +++ b/src/include/qemu/queue.h @@ -0,0 +1,439 @@ +/* $NetBSD: queue.h,v 1.52 2009/04/20 09:56:08 mschuett Exp $ */ + +/* + * QEMU version: Copy from netbsd, removed debug code, removed some of + * the implementations. Left in singly-linked lists, lists, simple + * queues, and tail queues. + */ + +/* + * Copyright (c) 1991, 1993 + * The Regents of the University of California. All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * @(#)queue.h 8.5 (Berkeley) 8/20/94 + */ + +#ifndef QEMU_SYS_QUEUE_H_ +#define QEMU_SYS_QUEUE_H_ + +/* + * This file defines four types of data structures: singly-linked lists, + * lists, simple queues, and tail queues. + * + * A singly-linked list is headed by a single forward pointer. The + * elements are singly linked for minimum space and pointer manipulation + * overhead at the expense of O(n) removal for arbitrary elements. New + * elements can be added to the list after an existing element or at the + * head of the list. Elements being removed from the head of the list + * should use the explicit macro for this purpose for optimum + * efficiency. A singly-linked list may only be traversed in the forward + * direction. Singly-linked lists are ideal for applications with large + * datasets and few or no removals or for implementing a LIFO queue. + * + * A list is headed by a single forward pointer (or an array of forward + * pointers for a hash table header). The elements are doubly linked + * so that an arbitrary element can be removed without a need to + * traverse the list. New elements can be added to the list before + * or after an existing element or at the head of the list. A list + * may only be traversed in the forward direction. + * + * A simple queue is headed by a pair of pointers, one the head of the + * list and the other to the tail of the list. The elements are singly + * linked to save space, so elements can only be removed from the + * head of the list. New elements can be added to the list after + * an existing element, at the head of the list, or at the end of the + * list. A simple queue may only be traversed in the forward direction. + * + * A tail queue is headed by a pair of pointers, one to the head of the + * list and the other to the tail of the list. The elements are doubly + * linked so that an arbitrary element can be removed without a need to + * traverse the list. New elements can be added to the list before or + * after an existing element, at the head of the list, or at the end of + * the list. A tail queue may be traversed in either direction. + * + * For details on the use of these macros, see the queue(3) manual page. + */ + +#include "qemu/atomic.h" /* for smp_wmb() */ + +/* + * List definitions. + */ +#define QLIST_HEAD(name, type) \ +struct name { \ + struct type *lh_first; /* first element */ \ +} + +#define QLIST_HEAD_INITIALIZER(head) \ + { NULL } + +#define QLIST_ENTRY(type) \ +struct { \ + struct type *le_next; /* next element */ \ + struct type **le_prev; /* address of previous next element */ \ +} + +/* + * List functions. + */ +#define QLIST_INIT(head) do { \ + (head)->lh_first = NULL; \ +} while (/*CONSTCOND*/0) + +#define QLIST_SWAP(dstlist, srclist, field) do { \ + void *tmplist; \ + tmplist = (srclist)->lh_first; \ + (srclist)->lh_first = (dstlist)->lh_first; \ + if ((srclist)->lh_first != NULL) { \ + (srclist)->lh_first->field.le_prev = &(srclist)->lh_first; \ + } \ + (dstlist)->lh_first = tmplist; \ + if ((dstlist)->lh_first != NULL) { \ + (dstlist)->lh_first->field.le_prev = &(dstlist)->lh_first; \ + } \ +} while (/*CONSTCOND*/0) + +#define QLIST_INSERT_AFTER(listelm, elm, field) do { \ + if (((elm)->field.le_next = (listelm)->field.le_next) != NULL) \ + (listelm)->field.le_next->field.le_prev = \ + &(elm)->field.le_next; \ + (listelm)->field.le_next = (elm); \ + (elm)->field.le_prev = &(listelm)->field.le_next; \ +} while (/*CONSTCOND*/0) + +#define QLIST_INSERT_BEFORE(listelm, elm, field) do { \ + (elm)->field.le_prev = (listelm)->field.le_prev; \ + (elm)->field.le_next = (listelm); \ + *(listelm)->field.le_prev = (elm); \ + (listelm)->field.le_prev = &(elm)->field.le_next; \ +} while (/*CONSTCOND*/0) + +#define QLIST_INSERT_HEAD(head, elm, field) do { \ + if (((elm)->field.le_next = (head)->lh_first) != NULL) \ + (head)->lh_first->field.le_prev = &(elm)->field.le_next;\ + (head)->lh_first = (elm); \ + (elm)->field.le_prev = &(head)->lh_first; \ +} while (/*CONSTCOND*/0) + +#define QLIST_REMOVE(elm, field) do { \ + if ((elm)->field.le_next != NULL) \ + (elm)->field.le_next->field.le_prev = \ + (elm)->field.le_prev; \ + *(elm)->field.le_prev = (elm)->field.le_next; \ +} while (/*CONSTCOND*/0) + +#define QLIST_FOREACH(var, head, field) \ + for ((var) = ((head)->lh_first); \ + (var); \ + (var) = ((var)->field.le_next)) + +#define QLIST_FOREACH_SAFE(var, head, field, next_var) \ + for ((var) = ((head)->lh_first); \ + (var) && ((next_var) = ((var)->field.le_next), 1); \ + (var) = (next_var)) + +/* + * List access methods. + */ +#define QLIST_EMPTY(head) ((head)->lh_first == NULL) +#define QLIST_FIRST(head) ((head)->lh_first) +#define QLIST_NEXT(elm, field) ((elm)->field.le_next) + + +/* + * Singly-linked List definitions. + */ +#define QSLIST_HEAD(name, type) \ +struct name { \ + struct type *slh_first; /* first element */ \ +} + +#define QSLIST_HEAD_INITIALIZER(head) \ + { NULL } + +#define QSLIST_ENTRY(type) \ +struct { \ + struct type *sle_next; /* next element */ \ +} + +/* + * Singly-linked List functions. + */ +#define QSLIST_INIT(head) do { \ + (head)->slh_first = NULL; \ +} while (/*CONSTCOND*/0) + +#define QSLIST_INSERT_AFTER(slistelm, elm, field) do { \ + (elm)->field.sle_next = (slistelm)->field.sle_next; \ + (slistelm)->field.sle_next = (elm); \ +} while (/*CONSTCOND*/0) + +#define QSLIST_INSERT_HEAD(head, elm, field) do { \ + (elm)->field.sle_next = (head)->slh_first; \ + (head)->slh_first = (elm); \ +} while (/*CONSTCOND*/0) + +#define QSLIST_INSERT_HEAD_ATOMIC(head, elm, field) do { \ + __typeof__(elm) save_sle_next; \ + do { \ + save_sle_next = (elm)->field.sle_next = (head)->slh_first; \ + } while (atomic_cmpxchg(&(head)->slh_first, save_sle_next, (elm)) != \ + save_sle_next); \ +} while (/*CONSTCOND*/0) + +#define QSLIST_MOVE_ATOMIC(dest, src) do { \ + (dest)->slh_first = atomic_xchg(&(src)->slh_first, NULL); \ +} while (/*CONSTCOND*/0) + +#define QSLIST_REMOVE_HEAD(head, field) do { \ + (head)->slh_first = (head)->slh_first->field.sle_next; \ +} while (/*CONSTCOND*/0) + +#define QSLIST_REMOVE_AFTER(slistelm, field) do { \ + (slistelm)->field.sle_next = \ + QSLIST_NEXT(QSLIST_NEXT((slistelm), field), field); \ +} while (/*CONSTCOND*/0) + +#define QSLIST_FOREACH(var, head, field) \ + for((var) = (head)->slh_first; (var); (var) = (var)->field.sle_next) + +#define QSLIST_FOREACH_SAFE(var, head, field, tvar) \ + for ((var) = QSLIST_FIRST((head)); \ + (var) && ((tvar) = QSLIST_NEXT((var), field), 1); \ + (var) = (tvar)) + +/* + * Singly-linked List access methods. + */ +#define QSLIST_EMPTY(head) ((head)->slh_first == NULL) +#define QSLIST_FIRST(head) ((head)->slh_first) +#define QSLIST_NEXT(elm, field) ((elm)->field.sle_next) + + +/* + * Simple queue definitions. + */ +#define QSIMPLEQ_HEAD(name, type) \ +struct name { \ + struct type *sqh_first; /* first element */ \ + struct type **sqh_last; /* addr of last next element */ \ +} + +#define QSIMPLEQ_HEAD_INITIALIZER(head) \ + { NULL, &(head).sqh_first } + +#define QSIMPLEQ_ENTRY(type) \ +struct { \ + struct type *sqe_next; /* next element */ \ +} + +/* + * Simple queue functions. + */ +#define QSIMPLEQ_INIT(head) do { \ + (head)->sqh_first = NULL; \ + (head)->sqh_last = &(head)->sqh_first; \ +} while (/*CONSTCOND*/0) + +#define QSIMPLEQ_INSERT_HEAD(head, elm, field) do { \ + if (((elm)->field.sqe_next = (head)->sqh_first) == NULL) \ + (head)->sqh_last = &(elm)->field.sqe_next; \ + (head)->sqh_first = (elm); \ +} while (/*CONSTCOND*/0) + +#define QSIMPLEQ_INSERT_TAIL(head, elm, field) do { \ + (elm)->field.sqe_next = NULL; \ + *(head)->sqh_last = (elm); \ + (head)->sqh_last = &(elm)->field.sqe_next; \ +} while (/*CONSTCOND*/0) + +#define QSIMPLEQ_INSERT_AFTER(head, listelm, elm, field) do { \ + if (((elm)->field.sqe_next = (listelm)->field.sqe_next) == NULL) \ + (head)->sqh_last = &(elm)->field.sqe_next; \ + (listelm)->field.sqe_next = (elm); \ +} while (/*CONSTCOND*/0) + +#define QSIMPLEQ_REMOVE_HEAD(head, field) do { \ + if (((head)->sqh_first = (head)->sqh_first->field.sqe_next) == NULL)\ + (head)->sqh_last = &(head)->sqh_first; \ +} while (/*CONSTCOND*/0) + +#define QSIMPLEQ_SPLIT_AFTER(head, elm, field, removed) do { \ + QSIMPLEQ_INIT(removed); \ + if (((removed)->sqh_first = (head)->sqh_first) != NULL) { \ + if (((head)->sqh_first = (elm)->field.sqe_next) == NULL) { \ + (head)->sqh_last = &(head)->sqh_first; \ + } \ + (removed)->sqh_last = &(elm)->field.sqe_next; \ + (elm)->field.sqe_next = NULL; \ + } \ +} while (/*CONSTCOND*/0) + +#define QSIMPLEQ_REMOVE(head, elm, type, field) do { \ + if ((head)->sqh_first == (elm)) { \ + QSIMPLEQ_REMOVE_HEAD((head), field); \ + } else { \ + struct type *curelm = (head)->sqh_first; \ + while (curelm->field.sqe_next != (elm)) \ + curelm = curelm->field.sqe_next; \ + if ((curelm->field.sqe_next = \ + curelm->field.sqe_next->field.sqe_next) == NULL) \ + (head)->sqh_last = &(curelm)->field.sqe_next; \ + } \ +} while (/*CONSTCOND*/0) + +#define QSIMPLEQ_FOREACH(var, head, field) \ + for ((var) = ((head)->sqh_first); \ + (var); \ + (var) = ((var)->field.sqe_next)) + +#define QSIMPLEQ_FOREACH_SAFE(var, head, field, next) \ + for ((var) = ((head)->sqh_first); \ + (var) && ((next = ((var)->field.sqe_next)), 1); \ + (var) = (next)) + +#define QSIMPLEQ_CONCAT(head1, head2) do { \ + if (!QSIMPLEQ_EMPTY((head2))) { \ + *(head1)->sqh_last = (head2)->sqh_first; \ + (head1)->sqh_last = (head2)->sqh_last; \ + QSIMPLEQ_INIT((head2)); \ + } \ +} while (/*CONSTCOND*/0) + +#define QSIMPLEQ_LAST(head, type, field) \ + (QSIMPLEQ_EMPTY((head)) ? \ + NULL : \ + ((struct type *)(void *) \ + ((char *)((head)->sqh_last) - offsetof(struct type, field)))) + +/* + * Simple queue access methods. + */ +#define QSIMPLEQ_EMPTY(head) ((head)->sqh_first == NULL) +#define QSIMPLEQ_FIRST(head) ((head)->sqh_first) +#define QSIMPLEQ_NEXT(elm, field) ((elm)->field.sqe_next) + + +/* + * Tail queue definitions. + */ +#define Q_TAILQ_HEAD(name, type, qual) \ +struct name { \ + qual type *tqh_first; /* first element */ \ + qual type *qual *tqh_last; /* addr of last next element */ \ +} +#define QTAILQ_HEAD(name, type) Q_TAILQ_HEAD(name, struct type,) + +#define QTAILQ_HEAD_INITIALIZER(head) \ + { NULL, &(head).tqh_first } + +#define Q_TAILQ_ENTRY(type, qual) \ +struct { \ + qual type *tqe_next; /* next element */ \ + qual type *qual *tqe_prev; /* address of previous next element */\ +} +#define QTAILQ_ENTRY(type) Q_TAILQ_ENTRY(struct type,) + +/* + * Tail queue functions. + */ +#define QTAILQ_INIT(head) do { \ + (head)->tqh_first = NULL; \ + (head)->tqh_last = &(head)->tqh_first; \ +} while (/*CONSTCOND*/0) + +#define QTAILQ_INSERT_HEAD(head, elm, field) do { \ + if (((elm)->field.tqe_next = (head)->tqh_first) != NULL) \ + (head)->tqh_first->field.tqe_prev = \ + &(elm)->field.tqe_next; \ + else \ + (head)->tqh_last = &(elm)->field.tqe_next; \ + (head)->tqh_first = (elm); \ + (elm)->field.tqe_prev = &(head)->tqh_first; \ +} while (/*CONSTCOND*/0) + +#define QTAILQ_INSERT_TAIL(head, elm, field) do { \ + (elm)->field.tqe_next = NULL; \ + (elm)->field.tqe_prev = (head)->tqh_last; \ + *(head)->tqh_last = (elm); \ + (head)->tqh_last = &(elm)->field.tqe_next; \ +} while (/*CONSTCOND*/0) + +#define QTAILQ_INSERT_AFTER(head, listelm, elm, field) do { \ + if (((elm)->field.tqe_next = (listelm)->field.tqe_next) != NULL)\ + (elm)->field.tqe_next->field.tqe_prev = \ + &(elm)->field.tqe_next; \ + else \ + (head)->tqh_last = &(elm)->field.tqe_next; \ + (listelm)->field.tqe_next = (elm); \ + (elm)->field.tqe_prev = &(listelm)->field.tqe_next; \ +} while (/*CONSTCOND*/0) + +#define QTAILQ_INSERT_BEFORE(listelm, elm, field) do { \ + (elm)->field.tqe_prev = (listelm)->field.tqe_prev; \ + (elm)->field.tqe_next = (listelm); \ + *(listelm)->field.tqe_prev = (elm); \ + (listelm)->field.tqe_prev = &(elm)->field.tqe_next; \ +} while (/*CONSTCOND*/0) + +#define QTAILQ_REMOVE(head, elm, field) do { \ + if (((elm)->field.tqe_next) != NULL) \ + (elm)->field.tqe_next->field.tqe_prev = \ + (elm)->field.tqe_prev; \ + else \ + (head)->tqh_last = (elm)->field.tqe_prev; \ + *(elm)->field.tqe_prev = (elm)->field.tqe_next; \ +} while (/*CONSTCOND*/0) + +#define QTAILQ_FOREACH(var, head, field) \ + for ((var) = ((head)->tqh_first); \ + (var); \ + (var) = ((var)->field.tqe_next)) + +#define QTAILQ_FOREACH_SAFE(var, head, field, next_var) \ + for ((var) = ((head)->tqh_first); \ + (var) && ((next_var) = ((var)->field.tqe_next), 1); \ + (var) = (next_var)) + +#define QTAILQ_FOREACH_REVERSE(var, head, headname, field) \ + for ((var) = (*(((struct headname *)((head)->tqh_last))->tqh_last)); \ + (var); \ + (var) = (*(((struct headname *)((var)->field.tqe_prev))->tqh_last))) + +/* + * Tail queue access methods. + */ +#define QTAILQ_EMPTY(head) ((head)->tqh_first == NULL) +#define QTAILQ_FIRST(head) ((head)->tqh_first) +#define QTAILQ_NEXT(elm, field) ((elm)->field.tqe_next) + +#define QTAILQ_LAST(head, headname) \ + (*(((struct headname *)((head)->tqh_last))->tqh_last)) +#define QTAILQ_PREV(elm, headname, field) \ + (*(((struct headname *)((elm)->field.tqe_prev))->tqh_last)) + +#endif /* !QEMU_SYS_QUEUE_H_ */ diff --git a/src/include/qemu/range.h b/src/include/qemu/range.h new file mode 100644 index 0000000..cfa021f --- /dev/null +++ b/src/include/qemu/range.h @@ -0,0 +1,135 @@ +#ifndef QEMU_RANGE_H +#define QEMU_RANGE_H + +#include <inttypes.h> +#include <qemu/typedefs.h> +#include "qemu/queue.h" + +/* + * Operations on 64 bit address ranges. + * Notes: + * - ranges must not wrap around 0, but can include the last byte ~0x0LL. + * - this can not represent a full 0 to ~0x0LL range. + */ + +/* A structure representing a range of addresses. */ +struct Range { + uint64_t begin; /* First byte of the range, or 0 if empty. */ + uint64_t end; /* 1 + the last byte. 0 if range empty or ends at ~0x0LL. */ +}; + +static inline void range_extend(Range *range, Range *extend_by) +{ + if (!extend_by->begin && !extend_by->end) { + return; + } + if (!range->begin && !range->end) { + *range = *extend_by; + return; + } + if (range->begin > extend_by->begin) { + range->begin = extend_by->begin; + } + /* Compare last byte in case region ends at ~0x0LL */ + if (range->end - 1 < extend_by->end - 1) { + range->end = extend_by->end; + } +} + +/* Get last byte of a range from offset + length. + * Undefined for ranges that wrap around 0. */ +static inline uint64_t range_get_last(uint64_t offset, uint64_t len) +{ + return offset + len - 1; +} + +/* Check whether a given range covers a given byte. */ +static inline int range_covers_byte(uint64_t offset, uint64_t len, + uint64_t byte) +{ + return offset <= byte && byte <= range_get_last(offset, len); +} + +/* Check whether 2 given ranges overlap. + * Undefined if ranges that wrap around 0. */ +static inline int ranges_overlap(uint64_t first1, uint64_t len1, + uint64_t first2, uint64_t len2) +{ + uint64_t last1 = range_get_last(first1, len1); + uint64_t last2 = range_get_last(first2, len2); + + return !(last2 < first1 || last1 < first2); +} + +/* 0,1 can merge with 1,2 but don't overlap */ +static inline bool ranges_can_merge(Range *range1, Range *range2) +{ + return !(range1->end < range2->begin || range2->end < range1->begin); +} + +static inline int range_merge(Range *range1, Range *range2) +{ + if (ranges_can_merge(range1, range2)) { + if (range1->end < range2->end) { + range1->end = range2->end; + } + if (range1->begin > range2->begin) { + range1->begin = range2->begin; + } + return 0; + } + + return -1; +} + +static inline GList *g_list_insert_sorted_merged(GList *list, + gpointer data, + GCompareFunc func) +{ + GList *l, *next = NULL; + Range *r, *nextr; + + if (!list) { + list = g_list_insert_sorted(list, data, func); + return list; + } + + nextr = data; + l = list; + while (l && l != next && nextr) { + r = l->data; + if (ranges_can_merge(r, nextr)) { + range_merge(r, nextr); + l = g_list_remove_link(l, next); + next = g_list_next(l); + if (next) { + nextr = next->data; + } else { + nextr = NULL; + } + } else { + l = g_list_next(l); + } + } + + if (!l) { + list = g_list_insert_sorted(list, data, func); + } + + return list; +} + +static inline gint range_compare(gconstpointer a, gconstpointer b) +{ + Range *ra = (Range *)a, *rb = (Range *)b; + if (ra->begin == rb->begin && ra->end == rb->end) { + return 0; + } else if (range_get_last(ra->begin, ra->end) < + range_get_last(rb->begin, rb->end)) { + return -1; + } else { + return 1; + } +} + +#endif diff --git a/src/include/qemu/ratelimit.h b/src/include/qemu/ratelimit.h new file mode 100644 index 0000000..d413a4a --- /dev/null +++ b/src/include/qemu/ratelimit.h @@ -0,0 +1,48 @@ +/* + * Ratelimiting calculations + * + * Copyright IBM, Corp. 2011 + * + * Authors: + * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com> + * + * This work is licensed under the terms of the GNU LGPL, version 2 or later. + * See the COPYING.LIB file in the top-level directory. + * + */ + +#ifndef QEMU_RATELIMIT_H +#define QEMU_RATELIMIT_H 1 + +typedef struct { + int64_t next_slice_time; + uint64_t slice_quota; + uint64_t slice_ns; + uint64_t dispatched; +} RateLimit; + +static inline int64_t ratelimit_calculate_delay(RateLimit *limit, uint64_t n) +{ + int64_t now = qemu_clock_get_ns(QEMU_CLOCK_REALTIME); + + if (limit->next_slice_time < now) { + limit->next_slice_time = now + limit->slice_ns; + limit->dispatched = 0; + } + if (limit->dispatched == 0 || limit->dispatched + n <= limit->slice_quota) { + limit->dispatched += n; + return 0; + } else { + limit->dispatched = n; + return limit->next_slice_time - now; + } +} + +static inline void ratelimit_set_speed(RateLimit *limit, uint64_t speed, + uint64_t slice_ns) +{ + limit->slice_ns = slice_ns; + limit->slice_quota = ((double)speed * slice_ns)/1000000000ULL; +} + +#endif diff --git a/src/include/qemu/rcu.h b/src/include/qemu/rcu.h new file mode 100644 index 0000000..0d9f677 --- /dev/null +++ b/src/include/qemu/rcu.h @@ -0,0 +1,156 @@ +#ifndef QEMU_RCU_H +#define QEMU_RCU_H + +/* + * urcu-mb.h + * + * Userspace RCU header with explicit memory barrier. + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + * + * IBM's contributions to this file may be relicensed under LGPLv2 or later. + */ + +#include <stdlib.h> +#include <assert.h> +#include <limits.h> +#include <unistd.h> +#include <stdint.h> +#include <stdbool.h> +#include <glib.h> + +#include "qemu/compiler.h" +#include "qemu/thread.h" +#include "qemu/queue.h" +#include "qemu/atomic.h" + +#ifdef __cplusplus +extern "C" { +#endif + +/* + * Important ! + * + * Each thread containing read-side critical sections must be registered + * with rcu_register_thread() before calling rcu_read_lock(). + * rcu_unregister_thread() should be called before the thread exits. + */ + +#ifdef DEBUG_RCU +#define rcu_assert(args...) assert(args) +#else +#define rcu_assert(args...) +#endif + +/* + * Global quiescent period counter with low-order bits unused. + * Using a int rather than a char to eliminate false register dependencies + * causing stalls on some architectures. + */ +extern unsigned long rcu_gp_ctr; + +extern QemuEvent rcu_gp_event; + +struct rcu_reader_data { + /* Data used by both reader and synchronize_rcu() */ + unsigned long ctr; + bool waiting; + + /* Data used by reader only */ + unsigned depth; + + /* Data used for registry, protected by rcu_registry_lock */ + QLIST_ENTRY(rcu_reader_data) node; +}; + +extern __thread struct rcu_reader_data rcu_reader; + +static inline void rcu_read_lock(void) +{ + struct rcu_reader_data *p_rcu_reader = &rcu_reader; + unsigned ctr; + + if (p_rcu_reader->depth++ > 0) { + return; + } + + ctr = atomic_read(&rcu_gp_ctr); + atomic_xchg(&p_rcu_reader->ctr, ctr); + if (atomic_read(&p_rcu_reader->waiting)) { + atomic_set(&p_rcu_reader->waiting, false); + qemu_event_set(&rcu_gp_event); + } +} + +static inline void rcu_read_unlock(void) +{ + struct rcu_reader_data *p_rcu_reader = &rcu_reader; + + assert(p_rcu_reader->depth != 0); + if (--p_rcu_reader->depth > 0) { + return; + } + + atomic_xchg(&p_rcu_reader->ctr, 0); + if (atomic_read(&p_rcu_reader->waiting)) { + atomic_set(&p_rcu_reader->waiting, false); + qemu_event_set(&rcu_gp_event); + } +} + +extern void synchronize_rcu(void); + +/* + * Reader thread registration. + */ +extern void rcu_register_thread(void); +extern void rcu_unregister_thread(void); +extern void rcu_after_fork(void); + +struct rcu_head; +typedef void RCUCBFunc(struct rcu_head *head); + +struct rcu_head { + struct rcu_head *next; + RCUCBFunc *func; +}; + +extern void call_rcu1(struct rcu_head *head, RCUCBFunc *func); + +/* The operands of the minus operator must have the same type, + * which must be the one that we specify in the cast. + */ +#define call_rcu(head, func, field) \ + call_rcu1(({ \ + char __attribute__((unused)) \ + offset_must_be_zero[-offsetof(__typeof__(*(head)), field)], \ + func_type_invalid = (func) - (void (*)(__typeof__(head)))(func); \ + &(head)->field; \ + }), \ + (RCUCBFunc *)(func)) + +#define g_free_rcu(obj, field) \ + call_rcu1(({ \ + char __attribute__((unused)) \ + offset_must_be_zero[-offsetof(__typeof__(*(obj)), field)]; \ + &(obj)->field; \ + }), \ + (RCUCBFunc *)g_free); + +#ifdef __cplusplus +} +#endif + +#endif /* QEMU_RCU_H */ diff --git a/src/include/qemu/rcu_queue.h b/src/include/qemu/rcu_queue.h new file mode 100644 index 0000000..3aca7a5 --- /dev/null +++ b/src/include/qemu/rcu_queue.h @@ -0,0 +1,134 @@ +#ifndef QEMU_RCU_QUEUE_H +#define QEMU_RCU_QUEUE_H + +/* + * rcu_queue.h + * + * RCU-friendly versions of the queue.h primitives. + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + * + * Copyright (c) 2013 Mike D. Day, IBM Corporation. + * + * IBM's contributions to this file may be relicensed under LGPLv2 or later. + */ + +#include "qemu/queue.h" +#include "qemu/atomic.h" + +#ifdef __cplusplus +extern "C" { +#endif + + +/* + * List access methods. + */ +#define QLIST_EMPTY_RCU(head) (atomic_rcu_read(&(head)->lh_first) == NULL) +#define QLIST_FIRST_RCU(head) (atomic_rcu_read(&(head)->lh_first)) +#define QLIST_NEXT_RCU(elm, field) (atomic_rcu_read(&(elm)->field.le_next)) + +/* + * List functions. + */ + + +/* + * The difference between atomic_read/set and atomic_rcu_read/set + * is in the including of a read/write memory barrier to the volatile + * access. atomic_rcu_* macros include the memory barrier, the + * plain atomic macros do not. Therefore, it should be correct to + * issue a series of reads or writes to the same element using only + * the atomic_* macro, until the last read or write, which should be + * atomic_rcu_* to introduce a read or write memory barrier as + * appropriate. + */ + +/* Upon publication of the listelm->next value, list readers + * will see the new node when following next pointers from + * antecedent nodes, but may not see the new node when following + * prev pointers from subsequent nodes until after the RCU grace + * period expires. + * see linux/include/rculist.h __list_add_rcu(new, prev, next) + */ +#define QLIST_INSERT_AFTER_RCU(listelm, elm, field) do { \ + (elm)->field.le_next = (listelm)->field.le_next; \ + (elm)->field.le_prev = &(listelm)->field.le_next; \ + atomic_rcu_set(&(listelm)->field.le_next, (elm)); \ + if ((elm)->field.le_next != NULL) { \ + (elm)->field.le_next->field.le_prev = \ + &(elm)->field.le_next; \ + } \ +} while (/*CONSTCOND*/0) + +/* Upon publication of the listelm->prev->next value, list + * readers will see the new element when following prev pointers + * from subsequent elements, but may not see the new element + * when following next pointers from antecedent elements + * until after the RCU grace period expires. + */ +#define QLIST_INSERT_BEFORE_RCU(listelm, elm, field) do { \ + (elm)->field.le_prev = (listelm)->field.le_prev; \ + (elm)->field.le_next = (listelm); \ + atomic_rcu_set((listelm)->field.le_prev, (elm)); \ + (listelm)->field.le_prev = &(elm)->field.le_next; \ +} while (/*CONSTCOND*/0) + +/* Upon publication of the head->first value, list readers + * will see the new element when following the head, but may + * not see the new element when following prev pointers from + * subsequent elements until after the RCU grace period has + * expired. + */ +#define QLIST_INSERT_HEAD_RCU(head, elm, field) do { \ + (elm)->field.le_prev = &(head)->lh_first; \ + (elm)->field.le_next = (head)->lh_first; \ + atomic_rcu_set((&(head)->lh_first), (elm)); \ + if ((elm)->field.le_next != NULL) { \ + (elm)->field.le_next->field.le_prev = \ + &(elm)->field.le_next; \ + } \ +} while (/*CONSTCOND*/0) + + +/* prior to publication of the elm->prev->next value, some list + * readers may still see the removed element when following + * the antecedent's next pointer. + */ +#define QLIST_REMOVE_RCU(elm, field) do { \ + if ((elm)->field.le_next != NULL) { \ + (elm)->field.le_next->field.le_prev = \ + (elm)->field.le_prev; \ + } \ + *(elm)->field.le_prev = (elm)->field.le_next; \ +} while (/*CONSTCOND*/0) + +/* List traversal must occur within an RCU critical section. */ +#define QLIST_FOREACH_RCU(var, head, field) \ + for ((var) = atomic_rcu_read(&(head)->lh_first); \ + (var); \ + (var) = atomic_rcu_read(&(var)->field.le_next)) + +/* List traversal must occur within an RCU critical section. */ +#define QLIST_FOREACH_SAFE_RCU(var, head, field, next_var) \ + for ((var) = (atomic_rcu_read(&(head)->lh_first)); \ + (var) && \ + ((next_var) = atomic_rcu_read(&(var)->field.le_next), 1); \ + (var) = (next_var)) + +#ifdef __cplusplus +} +#endif +#endif /* QEMU_RCU_QUEUE.H */ diff --git a/src/include/qemu/readline.h b/src/include/qemu/readline.h new file mode 100644 index 0000000..49efe4e --- /dev/null +++ b/src/include/qemu/readline.h @@ -0,0 +1,63 @@ +#ifndef READLINE_H +#define READLINE_H + +#define READLINE_CMD_BUF_SIZE 4095 +#define READLINE_MAX_CMDS 64 +#define READLINE_MAX_COMPLETIONS 256 + +typedef void GCC_FMT_ATTR(2, 3) ReadLinePrintfFunc(void *opaque, + const char *fmt, ...); +typedef void ReadLineFlushFunc(void *opaque); +typedef void ReadLineFunc(void *opaque, const char *str, + void *readline_opaque); +typedef void ReadLineCompletionFunc(void *opaque, + const char *cmdline); + +typedef struct ReadLineState { + char cmd_buf[READLINE_CMD_BUF_SIZE + 1]; + int cmd_buf_index; + int cmd_buf_size; + + char last_cmd_buf[READLINE_CMD_BUF_SIZE + 1]; + int last_cmd_buf_index; + int last_cmd_buf_size; + + int esc_state; + int esc_param; + + char *history[READLINE_MAX_CMDS]; + int hist_entry; + + ReadLineCompletionFunc *completion_finder; + char *completions[READLINE_MAX_COMPLETIONS]; + int nb_completions; + int completion_index; + + ReadLineFunc *readline_func; + void *readline_opaque; + int read_password; + char prompt[256]; + + ReadLinePrintfFunc *printf_func; + ReadLineFlushFunc *flush_func; + void *opaque; +} ReadLineState; + +void readline_add_completion(ReadLineState *rs, const char *str); +void readline_set_completion_index(ReadLineState *rs, int completion_index); + +const char *readline_get_history(ReadLineState *rs, unsigned int index); + +void readline_handle_byte(ReadLineState *rs, int ch); + +void readline_start(ReadLineState *rs, const char *prompt, int read_password, + ReadLineFunc *readline_func, void *readline_opaque); +void readline_restart(ReadLineState *rs); +void readline_show_prompt(ReadLineState *rs); + +ReadLineState *readline_init(ReadLinePrintfFunc *printf_func, + ReadLineFlushFunc *flush_func, + void *opaque, + ReadLineCompletionFunc *completion_finder); + +#endif /* !READLINE_H */ diff --git a/src/include/qemu/rfifolock.h b/src/include/qemu/rfifolock.h new file mode 100644 index 0000000..b23ab53 --- /dev/null +++ b/src/include/qemu/rfifolock.h @@ -0,0 +1,54 @@ +/* + * Recursive FIFO lock + * + * Copyright Red Hat, Inc. 2013 + * + * Authors: + * Stefan Hajnoczi <stefanha@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef QEMU_RFIFOLOCK_H +#define QEMU_RFIFOLOCK_H + +#include "qemu/thread.h" + +/* Recursive FIFO lock + * + * This lock provides more features than a plain mutex: + * + * 1. Fairness - enforces FIFO order. + * 2. Nesting - can be taken recursively. + * 3. Contention callback - optional, called when thread must wait. + * + * The recursive FIFO lock is heavyweight so prefer other synchronization + * primitives if you do not need its features. + */ +typedef struct { + QemuMutex lock; /* protects all fields */ + + /* FIFO order */ + unsigned int head; /* active ticket number */ + unsigned int tail; /* waiting ticket number */ + QemuCond cond; /* used to wait for our ticket number */ + + /* Nesting */ + QemuThread owner_thread; /* thread that currently has ownership */ + unsigned int nesting; /* amount of nesting levels */ + + /* Contention callback */ + void (*cb)(void *); /* called when thread must wait, with ->lock + * held so it may not recursively lock/unlock + */ + void *cb_opaque; +} RFifoLock; + +void rfifolock_init(RFifoLock *r, void (*cb)(void *), void *opaque); +void rfifolock_destroy(RFifoLock *r); +void rfifolock_lock(RFifoLock *r); +void rfifolock_unlock(RFifoLock *r); + +#endif /* QEMU_RFIFOLOCK_H */ diff --git a/src/include/qemu/seqlock.h b/src/include/qemu/seqlock.h new file mode 100644 index 0000000..70b01fd --- /dev/null +++ b/src/include/qemu/seqlock.h @@ -0,0 +1,72 @@ +/* + * Seqlock implementation for QEMU + * + * Copyright Red Hat, Inc. 2013 + * + * Author: + * Paolo Bonzini <pbonzini@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ +#ifndef QEMU_SEQLOCK_H +#define QEMU_SEQLOCK_H 1 + +#include <qemu/atomic.h> +#include <qemu/thread.h> + +typedef struct QemuSeqLock QemuSeqLock; + +struct QemuSeqLock { + QemuMutex *mutex; + unsigned sequence; +}; + +static inline void seqlock_init(QemuSeqLock *sl, QemuMutex *mutex) +{ + sl->mutex = mutex; + sl->sequence = 0; +} + +/* Lock out other writers and update the count. */ +static inline void seqlock_write_lock(QemuSeqLock *sl) +{ + if (sl->mutex) { + qemu_mutex_lock(sl->mutex); + } + ++sl->sequence; + + /* Write sequence before updating other fields. */ + smp_wmb(); +} + +static inline void seqlock_write_unlock(QemuSeqLock *sl) +{ + /* Write other fields before finalizing sequence. */ + smp_wmb(); + + ++sl->sequence; + if (sl->mutex) { + qemu_mutex_unlock(sl->mutex); + } +} + +static inline unsigned seqlock_read_begin(QemuSeqLock *sl) +{ + /* Always fail if a write is in progress. */ + unsigned ret = atomic_read(&sl->sequence); + + /* Read sequence before reading other fields. */ + smp_rmb(); + return ret & ~1; +} + +static inline int seqlock_read_retry(const QemuSeqLock *sl, unsigned start) +{ + /* Read other fields before reading final sequence. */ + smp_rmb(); + return unlikely(atomic_read(&sl->sequence) != start); +} + +#endif diff --git a/src/include/qemu/sockets.h b/src/include/qemu/sockets.h new file mode 100644 index 0000000..5a183c5 --- /dev/null +++ b/src/include/qemu/sockets.h @@ -0,0 +1,125 @@ +/* headers to use the BSD sockets */ +#ifndef QEMU_SOCKET_H +#define QEMU_SOCKET_H + +#ifdef _WIN32 +#include <windows.h> +#include <winsock2.h> +#include <ws2tcpip.h> + +#define socket_error() WSAGetLastError() + +int inet_aton(const char *cp, struct in_addr *ia); + +#else + +#include <sys/types.h> +#include <sys/socket.h> +#include <netinet/in.h> +#include <netinet/tcp.h> +#include <arpa/inet.h> +#include <netdb.h> +#include <sys/un.h> + +#define socket_error() errno +#define closesocket(s) close(s) + +#endif /* !_WIN32 */ + +#include "qemu/option.h" +#include "qapi/error.h" +#include "qapi-types.h" + +extern QemuOptsList socket_optslist; + +/* misc helpers */ +int qemu_socket(int domain, int type, int protocol); +int qemu_accept(int s, struct sockaddr *addr, socklen_t *addrlen); +int socket_set_cork(int fd, int v); +int socket_set_nodelay(int fd); +void qemu_set_block(int fd); +void qemu_set_nonblock(int fd); +int socket_set_fast_reuse(int fd); +int send_all(int fd, const void *buf, int len1); +int recv_all(int fd, void *buf, int len1, bool single_read); + +#ifdef WIN32 +/* Windows has different names for the same constants with the same values */ +#define SHUT_RD 0 +#define SHUT_WR 1 +#define SHUT_RDWR 2 +#endif + +/* callback function for nonblocking connect + * valid fd on success, negative error code on failure + */ +typedef void NonBlockingConnectHandler(int fd, Error *errp, void *opaque); + +InetSocketAddress *inet_parse(const char *str, Error **errp); +int inet_listen_opts(QemuOpts *opts, int port_offset, Error **errp); +int inet_listen(const char *str, char *ostr, int olen, + int socktype, int port_offset, Error **errp); +int inet_connect_opts(QemuOpts *opts, Error **errp, + NonBlockingConnectHandler *callback, void *opaque); +int inet_connect(const char *str, Error **errp); +int inet_nonblocking_connect(const char *str, + NonBlockingConnectHandler *callback, + void *opaque, Error **errp); + +int inet_dgram_opts(QemuOpts *opts, Error **errp); +NetworkAddressFamily inet_netfamily(int family); + +int unix_listen_opts(QemuOpts *opts, Error **errp); +int unix_listen(const char *path, char *ostr, int olen, Error **errp); +int unix_connect_opts(QemuOpts *opts, Error **errp, + NonBlockingConnectHandler *callback, void *opaque); +int unix_connect(const char *path, Error **errp); +int unix_nonblocking_connect(const char *str, + NonBlockingConnectHandler *callback, + void *opaque, Error **errp); + +SocketAddress *socket_parse(const char *str, Error **errp); +int socket_connect(SocketAddress *addr, Error **errp, + NonBlockingConnectHandler *callback, void *opaque); +int socket_listen(SocketAddress *addr, Error **errp); +int socket_dgram(SocketAddress *remote, SocketAddress *local, Error **errp); + +/* Old, ipv4 only bits. Don't use for new code. */ +int parse_host_port(struct sockaddr_in *saddr, const char *str); +int socket_init(void); + +/** + * socket_local_address: + * @fd: the socket file handle + * @errp: pointer to uninitialized error object + * + * Get the string representation of the local socket + * address. A pointer to the allocated address information + * struct will be returned, which the caller is required to + * release with a call qapi_free_SocketAddress when no + * longer required. + * + * Returns: the socket address struct, or NULL on error + */ +SocketAddress *socket_local_address(int fd, Error **errp); + +/** + * socket_remote_address: + * @fd: the socket file handle + * @errp: pointer to uninitialized error object + * + * Get the string representation of the remote socket + * address. A pointer to the allocated address information + * struct will be returned, which the caller is required to + * release with a call qapi_free_SocketAddress when no + * longer required. + * + * Returns: the socket address struct, or NULL on error + */ +SocketAddress *socket_remote_address(int fd, Error **errp); + + +void qapi_copy_SocketAddress(SocketAddress **p_dest, + SocketAddress *src); + +#endif /* QEMU_SOCKET_H */ diff --git a/src/include/qemu/thread-posix.h b/src/include/qemu/thread-posix.h new file mode 100644 index 0000000..eb5c7a1 --- /dev/null +++ b/src/include/qemu/thread-posix.h @@ -0,0 +1,36 @@ +#ifndef __QEMU_THREAD_POSIX_H +#define __QEMU_THREAD_POSIX_H 1 +#include "pthread.h" +#include <semaphore.h> + +struct QemuMutex { + pthread_mutex_t lock; +}; + +struct QemuCond { + pthread_cond_t cond; +}; + +struct QemuSemaphore { +#if defined(__APPLE__) || defined(__NetBSD__) + pthread_mutex_t lock; + pthread_cond_t cond; + unsigned int count; +#else + sem_t sem; +#endif +}; + +struct QemuEvent { +#ifndef __linux__ + pthread_mutex_t lock; + pthread_cond_t cond; +#endif + unsigned value; +}; + +struct QemuThread { + pthread_t thread; +}; + +#endif diff --git a/src/include/qemu/thread-win32.h b/src/include/qemu/thread-win32.h new file mode 100644 index 0000000..385ff5f --- /dev/null +++ b/src/include/qemu/thread-win32.h @@ -0,0 +1,34 @@ +#ifndef __QEMU_THREAD_WIN32_H +#define __QEMU_THREAD_WIN32_H 1 +#include "windows.h" + +struct QemuMutex { + CRITICAL_SECTION lock; + LONG owner; +}; + +struct QemuCond { + LONG waiters, target; + HANDLE sema; + HANDLE continue_event; +}; + +struct QemuSemaphore { + HANDLE sema; +}; + +struct QemuEvent { + int value; + HANDLE event; +}; + +typedef struct QemuThreadData QemuThreadData; +struct QemuThread { + QemuThreadData *data; + unsigned tid; +}; + +/* Only valid for joinable threads. */ +HANDLE qemu_thread_get_handle(QemuThread *thread); + +#endif diff --git a/src/include/qemu/thread.h b/src/include/qemu/thread.h new file mode 100644 index 0000000..5114ec8 --- /dev/null +++ b/src/include/qemu/thread.h @@ -0,0 +1,65 @@ +#ifndef __QEMU_THREAD_H +#define __QEMU_THREAD_H 1 + +#include <inttypes.h> +#include <stdbool.h> + +typedef struct QemuMutex QemuMutex; +typedef struct QemuCond QemuCond; +typedef struct QemuSemaphore QemuSemaphore; +typedef struct QemuEvent QemuEvent; +typedef struct QemuThread QemuThread; + +#ifdef _WIN32 +#include "qemu/thread-win32.h" +#else +#include "qemu/thread-posix.h" +#endif + +#define QEMU_THREAD_JOINABLE 0 +#define QEMU_THREAD_DETACHED 1 + +void qemu_mutex_init(QemuMutex *mutex); +void qemu_mutex_destroy(QemuMutex *mutex); +void qemu_mutex_lock(QemuMutex *mutex); +int qemu_mutex_trylock(QemuMutex *mutex); +void qemu_mutex_unlock(QemuMutex *mutex); + +void qemu_cond_init(QemuCond *cond); +void qemu_cond_destroy(QemuCond *cond); + +/* + * IMPORTANT: The implementation does not guarantee that pthread_cond_signal + * and pthread_cond_broadcast can be called except while the same mutex is + * held as in the corresponding pthread_cond_wait calls! + */ +void qemu_cond_signal(QemuCond *cond); +void qemu_cond_broadcast(QemuCond *cond); +void qemu_cond_wait(QemuCond *cond, QemuMutex *mutex); + +void qemu_sem_init(QemuSemaphore *sem, int init); +void qemu_sem_post(QemuSemaphore *sem); +void qemu_sem_wait(QemuSemaphore *sem); +int qemu_sem_timedwait(QemuSemaphore *sem, int ms); +void qemu_sem_destroy(QemuSemaphore *sem); + +void qemu_event_init(QemuEvent *ev, bool init); +void qemu_event_set(QemuEvent *ev); +void qemu_event_reset(QemuEvent *ev); +void qemu_event_wait(QemuEvent *ev); +void qemu_event_destroy(QemuEvent *ev); + +void qemu_thread_create(QemuThread *thread, const char *name, + void *(*start_routine)(void *), + void *arg, int mode); +void *qemu_thread_join(QemuThread *thread); +void qemu_thread_get_self(QemuThread *thread); +bool qemu_thread_is_self(QemuThread *thread); +void qemu_thread_exit(void *retval); +void qemu_thread_naming(bool enable); + +struct Notifier; +void qemu_thread_atexit_add(struct Notifier *notifier); +void qemu_thread_atexit_remove(struct Notifier *notifier); + +#endif diff --git a/src/include/qemu/throttle.h b/src/include/qemu/throttle.h new file mode 100644 index 0000000..12faaad --- /dev/null +++ b/src/include/qemu/throttle.h @@ -0,0 +1,132 @@ +/* + * QEMU throttling infrastructure + * + * Copyright (C) Nodalink, EURL. 2013-2014 + * Copyright (C) Igalia, S.L. 2015 + * + * Authors: + * Benoît Canet <benoit.canet@nodalink.com> + * Alberto Garcia <berto@igalia.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 or + * (at your option) version 3 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef THROTTLE_H +#define THROTTLE_H + +#include <stdint.h> +#include "qemu-common.h" +#include "qemu/timer.h" + +typedef enum { + THROTTLE_BPS_TOTAL, + THROTTLE_BPS_READ, + THROTTLE_BPS_WRITE, + THROTTLE_OPS_TOTAL, + THROTTLE_OPS_READ, + THROTTLE_OPS_WRITE, + BUCKETS_COUNT, +} BucketType; + +/* + * The max parameter of the leaky bucket throttling algorithm can be used to + * allow the guest to do bursts. + * The max value is a pool of I/O that the guest can use without being throttled + * at all. Throttling is triggered once this pool is empty. + */ + +typedef struct LeakyBucket { + double avg; /* average goal in units per second */ + double max; /* leaky bucket max burst in units */ + double level; /* bucket level in units */ +} LeakyBucket; + +/* The following structure is used to configure a ThrottleState + * It contains a bit of state: the bucket field of the LeakyBucket structure. + * However it allows to keep the code clean and the bucket field is reset to + * zero at the right time. + */ +typedef struct ThrottleConfig { + LeakyBucket buckets[BUCKETS_COUNT]; /* leaky buckets */ + uint64_t op_size; /* size of an operation in bytes */ +} ThrottleConfig; + +typedef struct ThrottleState { + ThrottleConfig cfg; /* configuration */ + int64_t previous_leak; /* timestamp of the last leak done */ +} ThrottleState; + +typedef struct ThrottleTimers { + QEMUTimer *timers[2]; /* timers used to do the throttling */ + QEMUClockType clock_type; /* the clock used */ + + /* Callbacks */ + QEMUTimerCB *read_timer_cb; + QEMUTimerCB *write_timer_cb; + void *timer_opaque; +} ThrottleTimers; + +/* operations on single leaky buckets */ +void throttle_leak_bucket(LeakyBucket *bkt, int64_t delta); + +int64_t throttle_compute_wait(LeakyBucket *bkt); + +/* expose timer computation function for unit tests */ +bool throttle_compute_timer(ThrottleState *ts, + bool is_write, + int64_t now, + int64_t *next_timestamp); + +/* init/destroy cycle */ +void throttle_init(ThrottleState *ts); + +void throttle_timers_init(ThrottleTimers *tt, + AioContext *aio_context, + QEMUClockType clock_type, + QEMUTimerCB *read_timer_cb, + QEMUTimerCB *write_timer_cb, + void *timer_opaque); + +void throttle_timers_destroy(ThrottleTimers *tt); + +void throttle_timers_detach_aio_context(ThrottleTimers *tt); + +void throttle_timers_attach_aio_context(ThrottleTimers *tt, + AioContext *new_context); + +bool throttle_timers_are_initialized(ThrottleTimers *tt); + +/* configuration */ +bool throttle_enabled(ThrottleConfig *cfg); + +bool throttle_conflicting(ThrottleConfig *cfg); + +bool throttle_is_valid(ThrottleConfig *cfg); + +bool throttle_max_is_missing_limit(ThrottleConfig *cfg); + +void throttle_config(ThrottleState *ts, + ThrottleTimers *tt, + ThrottleConfig *cfg); + +void throttle_get_config(ThrottleState *ts, ThrottleConfig *cfg); + +/* usage */ +bool throttle_schedule_timer(ThrottleState *ts, + ThrottleTimers *tt, + bool is_write); + +void throttle_account(ThrottleState *ts, bool is_write, uint64_t size); + +#endif diff --git a/src/include/qemu/timed-average.h b/src/include/qemu/timed-average.h new file mode 100644 index 0000000..364bf88 --- /dev/null +++ b/src/include/qemu/timed-average.h @@ -0,0 +1,64 @@ +/* + * QEMU timed average computation + * + * Copyright (C) Nodalink, EURL. 2014 + * Copyright (C) Igalia, S.L. 2015 + * + * Authors: + * Benoît Canet <benoit.canet@nodalink.com> + * Alberto Garcia <berto@igalia.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) version 3 or any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef TIMED_AVERAGE_H +#define TIMED_AVERAGE_H + +#include <stdint.h> + +#include "qemu/timer.h" + +typedef struct TimedAverageWindow TimedAverageWindow; +typedef struct TimedAverage TimedAverage; + +/* All fields of both structures are private */ + +struct TimedAverageWindow { + uint64_t min; /* minimum value accounted in the window */ + uint64_t max; /* maximum value accounted in the window */ + uint64_t sum; /* sum of all values */ + uint64_t count; /* number of values */ + int64_t expiration; /* the end of the current window in ns */ +}; + +struct TimedAverage { + uint64_t period; /* period in nanoseconds */ + TimedAverageWindow windows[2]; /* two overlapping windows of with + * an offset of period / 2 between them */ + unsigned current; /* the current window index: it's also the + * oldest window index */ + QEMUClockType clock_type; /* the clock used */ +}; + +void timed_average_init(TimedAverage *ta, QEMUClockType clock_type, + uint64_t period); + +void timed_average_account(TimedAverage *ta, uint64_t value); + +uint64_t timed_average_min(TimedAverage *ta); +uint64_t timed_average_avg(TimedAverage *ta); +uint64_t timed_average_max(TimedAverage *ta); +uint64_t timed_average_sum(TimedAverage *ta, uint64_t *elapsed); + +#endif diff --git a/src/include/qemu/timer.h b/src/include/qemu/timer.h new file mode 100644 index 0000000..a16effa --- /dev/null +++ b/src/include/qemu/timer.h @@ -0,0 +1,1021 @@ +#ifndef QEMU_TIMER_H +#define QEMU_TIMER_H + +#include "qemu/typedefs.h" +#include "qemu-common.h" +#include "qemu/notify.h" +#include "qemu/host-utils.h" + +#define NANOSECONDS_PER_SECOND 1000000000LL + +/* timers */ + +#define SCALE_MS 1000000 +#define SCALE_US 1000 +#define SCALE_NS 1 + +/** + * QEMUClockType: + * + * The following clock types are available: + * + * @QEMU_CLOCK_REALTIME: Real time clock + * + * The real time clock should be used only for stuff which does not + * change the virtual machine state, as it is run even if the virtual + * machine is stopped. The real time clock has a frequency of 1000 + * Hz. + * + * @QEMU_CLOCK_VIRTUAL: virtual clock + * + * The virtual clock is only run during the emulation. It is stopped + * when the virtual machine is stopped. Virtual timers use a high + * precision clock, usually cpu cycles (use ticks_per_sec). + * + * @QEMU_CLOCK_HOST: host clock + * + * The host clock should be use for device models that emulate accurate + * real time sources. It will continue to run when the virtual machine + * is suspended, and it will reflect system time changes the host may + * undergo (e.g. due to NTP). The host clock has the same precision as + * the virtual clock. + * + * @QEMU_CLOCK_VIRTUAL_RT: realtime clock used for icount warp + * + * Outside icount mode, this clock is the same as @QEMU_CLOCK_VIRTUAL. + * In icount mode, this clock counts nanoseconds while the virtual + * machine is running. It is used to increase @QEMU_CLOCK_VIRTUAL + * while the CPUs are sleeping and thus not executing instructions. + */ + +typedef enum { + QEMU_CLOCK_REALTIME = 0, + QEMU_CLOCK_VIRTUAL = 1, + QEMU_CLOCK_HOST = 2, + QEMU_CLOCK_VIRTUAL_RT = 3, + QEMU_CLOCK_MAX +} QEMUClockType; + +typedef struct QEMUTimerList QEMUTimerList; + +struct QEMUTimerListGroup { + QEMUTimerList *tl[QEMU_CLOCK_MAX]; +}; + +typedef void QEMUTimerCB(void *opaque); +typedef void QEMUTimerListNotifyCB(void *opaque); + +struct QEMUTimer { + int64_t expire_time; /* in nanoseconds */ + QEMUTimerList *timer_list; + QEMUTimerCB *cb; + void *opaque; + QEMUTimer *next; + int scale; +}; + +extern QEMUTimerListGroup main_loop_tlg; + +/* + * QEMUClockType + */ + +/* + * qemu_clock_get_ns; + * @type: the clock type + * + * Get the nanosecond value of a clock with + * type @type + * + * Returns: the clock value in nanoseconds + */ +int64_t qemu_clock_get_ns(QEMUClockType type); + +/** + * qemu_clock_get_ms; + * @type: the clock type + * + * Get the millisecond value of a clock with + * type @type + * + * Returns: the clock value in milliseconds + */ +static inline int64_t qemu_clock_get_ms(QEMUClockType type) +{ + return qemu_clock_get_ns(type) / SCALE_MS; +} + +/** + * qemu_clock_get_us; + * @type: the clock type + * + * Get the microsecond value of a clock with + * type @type + * + * Returns: the clock value in microseconds + */ +static inline int64_t qemu_clock_get_us(QEMUClockType type) +{ + return qemu_clock_get_ns(type) / SCALE_US; +} + +/** + * qemu_clock_has_timers: + * @type: the clock type + * + * Determines whether a clock's default timer list + * has timers attached + * + * Note that this function should not be used when other threads also access + * the timer list. The return value may be outdated by the time it is acted + * upon. + * + * Returns: true if the clock's default timer list + * has timers attached + */ +bool qemu_clock_has_timers(QEMUClockType type); + +/** + * qemu_clock_expired: + * @type: the clock type + * + * Determines whether a clock's default timer list + * has an expired clock. + * + * Returns: true if the clock's default timer list has + * an expired timer + */ +bool qemu_clock_expired(QEMUClockType type); + +/** + * qemu_clock_use_for_deadline: + * @type: the clock type + * + * Determine whether a clock should be used for deadline + * calculations. Some clocks, for instance vm_clock with + * use_icount set, do not count in nanoseconds. Such clocks + * are not used for deadline calculations, and are presumed + * to interrupt any poll using qemu_notify/aio_notify + * etc. + * + * Returns: true if the clock runs in nanoseconds and + * should be used for a deadline. + */ +bool qemu_clock_use_for_deadline(QEMUClockType type); + +/** + * qemu_clock_deadline_ns_all: + * @type: the clock type + * + * Calculate the deadline across all timer lists associated + * with a clock (as opposed to just the default one) + * in nanoseconds, or -1 if no timer is set to expire. + * + * Returns: time until expiry in nanoseconds or -1 + */ +int64_t qemu_clock_deadline_ns_all(QEMUClockType type); + +/** + * qemu_clock_get_main_loop_timerlist: + * @type: the clock type + * + * Return the default timer list assocatiated with a clock. + * + * Returns: the default timer list + */ +QEMUTimerList *qemu_clock_get_main_loop_timerlist(QEMUClockType type); + +/** + * qemu_clock_nofify: + * @type: the clock type + * + * Call the notifier callback connected with the default timer + * list linked to the clock, or qemu_notify() if none. + */ +void qemu_clock_notify(QEMUClockType type); + +/** + * qemu_clock_enable: + * @type: the clock type + * @enabled: true to enable, false to disable + * + * Enable or disable a clock + * Disabling the clock will wait for related timerlists to stop + * executing qemu_run_timers. Thus, this functions should not + * be used from the callback of a timer that is based on @clock. + * Doing so would cause a deadlock. + * + * Caller should hold BQL. + */ +void qemu_clock_enable(QEMUClockType type, bool enabled); + +/** + * qemu_clock_warp: + * @type: the clock type + * + * Warp a clock to a new value + */ +void qemu_clock_warp(QEMUClockType type); + +/** + * qemu_clock_register_reset_notifier: + * @type: the clock type + * @notifier: the notifier function + * + * Register a notifier function to call when the clock + * concerned is reset. + */ +void qemu_clock_register_reset_notifier(QEMUClockType type, + Notifier *notifier); + +/** + * qemu_clock_unregister_reset_notifier: + * @type: the clock type + * @notifier: the notifier function + * + * Unregister a notifier function to call when the clock + * concerned is reset. + */ +void qemu_clock_unregister_reset_notifier(QEMUClockType type, + Notifier *notifier); + +/** + * qemu_clock_run_timers: + * @type: clock on which to operate + * + * Run all the timers associated with the default timer list + * of a clock. + * + * Returns: true if any timer ran. + */ +bool qemu_clock_run_timers(QEMUClockType type); + +/** + * qemu_clock_run_all_timers: + * + * Run all the timers associated with the default timer list + * of every clock. + * + * Returns: true if any timer ran. + */ +bool qemu_clock_run_all_timers(void); + +/* + * QEMUTimerList + */ + +/** + * timerlist_new: + * @type: the clock type to associate with the timerlist + * @cb: the callback to call on notification + * @opaque: the opaque pointer to pass to the callback + * + * Create a new timerlist associated with the clock of + * type @type. + * + * Returns: a pointer to the QEMUTimerList created + */ +QEMUTimerList *timerlist_new(QEMUClockType type, + QEMUTimerListNotifyCB *cb, void *opaque); + +/** + * timerlist_free: + * @timer_list: the timer list to free + * + * Frees a timer_list. It must have no active timers. + */ +void timerlist_free(QEMUTimerList *timer_list); + +/** + * timerlist_has_timers: + * @timer_list: the timer list to operate on + * + * Determine whether a timer list has active timers + * + * Note that this function should not be used when other threads also access + * the timer list. The return value may be outdated by the time it is acted + * upon. + * + * Returns: true if the timer list has timers. + */ +bool timerlist_has_timers(QEMUTimerList *timer_list); + +/** + * timerlist_expired: + * @timer_list: the timer list to operate on + * + * Determine whether a timer list has any timers which + * are expired. + * + * Returns: true if the timer list has timers which + * have expired. + */ +bool timerlist_expired(QEMUTimerList *timer_list); + +/** + * timerlist_deadline_ns: + * @timer_list: the timer list to operate on + * + * Determine the deadline for a timer_list, i.e. + * the number of nanoseconds until the first timer + * expires. Return -1 if there are no timers. + * + * Returns: the number of nanoseconds until the earliest + * timer expires -1 if none + */ +int64_t timerlist_deadline_ns(QEMUTimerList *timer_list); + +/** + * timerlist_get_clock: + * @timer_list: the timer list to operate on + * + * Determine the clock type associated with a timer list. + * + * Returns: the clock type associated with the + * timer list. + */ +QEMUClockType timerlist_get_clock(QEMUTimerList *timer_list); + +/** + * timerlist_run_timers: + * @timer_list: the timer list to use + * + * Call all expired timers associated with the timer list. + * + * Returns: true if any timer expired + */ +bool timerlist_run_timers(QEMUTimerList *timer_list); + +/** + * timerlist_notify: + * @timer_list: the timer list to use + * + * call the notifier callback associated with the timer list. + */ +void timerlist_notify(QEMUTimerList *timer_list); + +/* + * QEMUTimerListGroup + */ + +/** + * timerlistgroup_init: + * @tlg: the timer list group + * @cb: the callback to call when a notify is required + * @opaque: the opaque pointer to be passed to the callback. + * + * Initialise a timer list group. This must already be + * allocated in memory and zeroed. The notifier callback is + * called whenever a clock in the timer list group is + * reenabled or whenever a timer associated with any timer + * list is modified. If @cb is specified as null, qemu_notify() + * is used instead. + */ +void timerlistgroup_init(QEMUTimerListGroup *tlg, + QEMUTimerListNotifyCB *cb, void *opaque); + +/** + * timerlistgroup_deinit: + * @tlg: the timer list group + * + * Deinitialise a timer list group. This must already be + * initialised. Note the memory is not freed. + */ +void timerlistgroup_deinit(QEMUTimerListGroup *tlg); + +/** + * timerlistgroup_run_timers: + * @tlg: the timer list group + * + * Run the timers associated with a timer list group. + * This will run timers on multiple clocks. + * + * Returns: true if any timer callback ran + */ +bool timerlistgroup_run_timers(QEMUTimerListGroup *tlg); + +/** + * timerlistgroup_deadline_ns: + * @tlg: the timer list group + * + * Determine the deadline of the soonest timer to + * expire associated with any timer list linked to + * the timer list group. Only clocks suitable for + * deadline calculation are included. + * + * Returns: the deadline in nanoseconds or -1 if no + * timers are to expire. + */ +int64_t timerlistgroup_deadline_ns(QEMUTimerListGroup *tlg); + +/* + * QEMUTimer + */ + +/** + * timer_init_tl: + * @ts: the timer to be initialised + * @timer_list: the timer list to attach the timer to + * @scale: the scale value for the timer + * @cb: the callback to be called when the timer expires + * @opaque: the opaque pointer to be passed to the callback + * + * Initialise a new timer and associate it with @timer_list. + * The caller is responsible for allocating the memory. + * + * You need not call an explicit deinit call. Simply make + * sure it is not on a list with timer_del. + */ +void timer_init_tl(QEMUTimer *ts, + QEMUTimerList *timer_list, int scale, + QEMUTimerCB *cb, void *opaque); + +/** + * timer_init: + * @type: the clock to associate with the timer + * @scale: the scale value for the timer + * @cb: the callback to call when the timer expires + * @opaque: the opaque pointer to pass to the callback + * + * Initialize a timer with the given scale on the default timer list + * associated with the clock. + * + * You need not call an explicit deinit call. Simply make + * sure it is not on a list with timer_del. + */ +static inline void timer_init(QEMUTimer *ts, QEMUClockType type, int scale, + QEMUTimerCB *cb, void *opaque) +{ + timer_init_tl(ts, main_loop_tlg.tl[type], scale, cb, opaque); +} + +/** + * timer_init_ns: + * @type: the clock to associate with the timer + * @cb: the callback to call when the timer expires + * @opaque: the opaque pointer to pass to the callback + * + * Initialize a timer with nanosecond scale on the default timer list + * associated with the clock. + * + * You need not call an explicit deinit call. Simply make + * sure it is not on a list with timer_del. + */ +static inline void timer_init_ns(QEMUTimer *ts, QEMUClockType type, + QEMUTimerCB *cb, void *opaque) +{ + timer_init(ts, type, SCALE_NS, cb, opaque); +} + +/** + * timer_init_us: + * @type: the clock to associate with the timer + * @cb: the callback to call when the timer expires + * @opaque: the opaque pointer to pass to the callback + * + * Initialize a timer with microsecond scale on the default timer list + * associated with the clock. + * + * You need not call an explicit deinit call. Simply make + * sure it is not on a list with timer_del. + */ +static inline void timer_init_us(QEMUTimer *ts, QEMUClockType type, + QEMUTimerCB *cb, void *opaque) +{ + timer_init(ts, type, SCALE_US, cb, opaque); +} + +/** + * timer_init_ms: + * @type: the clock to associate with the timer + * @cb: the callback to call when the timer expires + * @opaque: the opaque pointer to pass to the callback + * + * Initialize a timer with millisecond scale on the default timer list + * associated with the clock. + * + * You need not call an explicit deinit call. Simply make + * sure it is not on a list with timer_del. + */ +static inline void timer_init_ms(QEMUTimer *ts, QEMUClockType type, + QEMUTimerCB *cb, void *opaque) +{ + timer_init(ts, type, SCALE_MS, cb, opaque); +} + +/** + * timer_new_tl: + * @timer_list: the timer list to attach the timer to + * @scale: the scale value for the timer + * @cb: the callback to be called when the timer expires + * @opaque: the opaque pointer to be passed to the callback + * + * Creeate a new timer and associate it with @timer_list. + * The memory is allocated by the function. + * + * This is not the preferred interface unless you know you + * are going to call timer_free. Use timer_init instead. + * + * Returns: a pointer to the timer + */ +static inline QEMUTimer *timer_new_tl(QEMUTimerList *timer_list, + int scale, + QEMUTimerCB *cb, + void *opaque) +{ + QEMUTimer *ts = (QEMUTimer *)g_malloc0(sizeof(QEMUTimer)); + timer_init_tl(ts, timer_list, scale, cb, opaque); + return ts; +} + +/** + * timer_new: + * @type: the clock type to use + * @scale: the scale value for the timer + * @cb: the callback to be called when the timer expires + * @opaque: the opaque pointer to be passed to the callback + * + * Creeate a new timer and associate it with the default + * timer list for the clock type @type. + * + * Returns: a pointer to the timer + */ +static inline QEMUTimer *timer_new(QEMUClockType type, int scale, + QEMUTimerCB *cb, void *opaque) +{ + return timer_new_tl(main_loop_tlg.tl[type], scale, cb, opaque); +} + +/** + * timer_new_ns: + * @clock: the clock to associate with the timer + * @callback: the callback to call when the timer expires + * @opaque: the opaque pointer to pass to the callback + * + * Create a new timer with nanosecond scale on the default timer list + * associated with the clock. + * + * Returns: a pointer to the newly created timer + */ +static inline QEMUTimer *timer_new_ns(QEMUClockType type, QEMUTimerCB *cb, + void *opaque) +{ + return timer_new(type, SCALE_NS, cb, opaque); +} + +/** + * timer_new_us: + * @clock: the clock to associate with the timer + * @callback: the callback to call when the timer expires + * @opaque: the opaque pointer to pass to the callback + * + * Create a new timer with microsecond scale on the default timer list + * associated with the clock. + * + * Returns: a pointer to the newly created timer + */ +static inline QEMUTimer *timer_new_us(QEMUClockType type, QEMUTimerCB *cb, + void *opaque) +{ + return timer_new(type, SCALE_US, cb, opaque); +} + +/** + * timer_new_ms: + * @clock: the clock to associate with the timer + * @callback: the callback to call when the timer expires + * @opaque: the opaque pointer to pass to the callback + * + * Create a new timer with millisecond scale on the default timer list + * associated with the clock. + * + * Returns: a pointer to the newly created timer + */ +static inline QEMUTimer *timer_new_ms(QEMUClockType type, QEMUTimerCB *cb, + void *opaque) +{ + return timer_new(type, SCALE_MS, cb, opaque); +} + +/** + * timer_deinit: + * @ts: the timer to be de-initialised + * + * Deassociate the timer from any timerlist. You should + * call timer_del before. After this call, any further + * timer_del call cannot cause dangling pointer accesses + * even if the previously used timerlist is freed. + */ +void timer_deinit(QEMUTimer *ts); + +/** + * timer_free: + * @ts: the timer + * + * Free a timer (it must not be on the active list) + */ +void timer_free(QEMUTimer *ts); + +/** + * timer_del: + * @ts: the timer + * + * Delete a timer from the active list. + * + * This function is thread-safe but the timer and its timer list must not be + * freed while this function is running. + */ +void timer_del(QEMUTimer *ts); + +/** + * timer_mod_ns: + * @ts: the timer + * @expire_time: the expiry time in nanoseconds + * + * Modify a timer to expire at @expire_time + * + * This function is thread-safe but the timer and its timer list must not be + * freed while this function is running. + */ +void timer_mod_ns(QEMUTimer *ts, int64_t expire_time); + +/** + * timer_mod_anticipate_ns: + * @ts: the timer + * @expire_time: the expiry time in nanoseconds + * + * Modify a timer to expire at @expire_time or the current time, + * whichever comes earlier. + * + * This function is thread-safe but the timer and its timer list must not be + * freed while this function is running. + */ +void timer_mod_anticipate_ns(QEMUTimer *ts, int64_t expire_time); + +/** + * timer_mod: + * @ts: the timer + * @expire_time: the expire time in the units associated with the timer + * + * Modify a timer to expiry at @expire_time, taking into + * account the scale associated with the timer. + * + * This function is thread-safe but the timer and its timer list must not be + * freed while this function is running. + */ +void timer_mod(QEMUTimer *ts, int64_t expire_timer); + +/** + * timer_mod_anticipate: + * @ts: the timer + * @expire_time: the expiry time in nanoseconds + * + * Modify a timer to expire at @expire_time or the current time, whichever + * comes earlier, taking into account the scale associated with the timer. + * + * This function is thread-safe but the timer and its timer list must not be + * freed while this function is running. + */ +void timer_mod_anticipate(QEMUTimer *ts, int64_t expire_time); + +/** + * timer_pending: + * @ts: the timer + * + * Determines whether a timer is pending (i.e. is on the + * active list of timers, whether or not it has not yet expired). + * + * Returns: true if the timer is pending + */ +bool timer_pending(QEMUTimer *ts); + +/** + * timer_expired: + * @ts: the timer + * + * Determines whether a timer has expired. + * + * Returns: true if the timer has expired + */ +bool timer_expired(QEMUTimer *timer_head, int64_t current_time); + +/** + * timer_expire_time_ns: + * @ts: the timer + * + * Determine the expiry time of a timer + * + * Returns: the expiry time in nanoseconds + */ +uint64_t timer_expire_time_ns(QEMUTimer *ts); + +/** + * timer_get: + * @f: the file + * @ts: the timer + * + * Read a timer @ts from a file @f + */ +void timer_get(QEMUFile *f, QEMUTimer *ts); + +/** + * timer_put: + * @f: the file + * @ts: the timer + */ +void timer_put(QEMUFile *f, QEMUTimer *ts); + +/* + * General utility functions + */ + +/** + * qemu_timeout_ns_to_ms: + * @ns: nanosecond timeout value + * + * Convert a nanosecond timeout value (or -1) to + * a millisecond value (or -1), always rounding up. + * + * Returns: millisecond timeout value + */ +int qemu_timeout_ns_to_ms(int64_t ns); + +/** + * qemu_poll_ns: + * @fds: Array of file descriptors + * @nfds: number of file descriptors + * @timeout: timeout in nanoseconds + * + * Perform a poll like g_poll but with a timeout in nanoseconds. + * See g_poll documentation for further details. + * + * Returns: number of fds ready + */ +int qemu_poll_ns(GPollFD *fds, guint nfds, int64_t timeout); + +/** + * qemu_soonest_timeout: + * @timeout1: first timeout in nanoseconds (or -1 for infinite) + * @timeout2: second timeout in nanoseconds (or -1 for infinite) + * + * Calculates the soonest of two timeout values. -1 means infinite, which + * is later than any other value. + * + * Returns: soonest timeout value in nanoseconds (or -1 for infinite) + */ +static inline int64_t qemu_soonest_timeout(int64_t timeout1, int64_t timeout2) +{ + /* we can abuse the fact that -1 (which means infinite) is a maximal + * value when cast to unsigned. As this is disgusting, it's kept in + * one inline function. + */ + return ((uint64_t) timeout1 < (uint64_t) timeout2) ? timeout1 : timeout2; +} + +/** + * initclocks: + * + * Initialise the clock & timer infrastructure + */ +void init_clocks(void); + +int64_t cpu_get_ticks(void); +/* Caller must hold BQL */ +void cpu_enable_ticks(void); +/* Caller must hold BQL */ +void cpu_disable_ticks(void); + +static inline int64_t get_ticks_per_sec(void) +{ + return 1000000000LL; +} + +static inline int64_t get_max_clock_jump(void) +{ + /* This should be small enough to prevent excessive interrupts from being + * generated by the RTC on clock jumps, but large enough to avoid frequent + * unnecessary resets in idle VMs. + */ + return 60 * get_ticks_per_sec(); +} + +/* + * Low level clock functions + */ + +/* real time host monotonic timer */ +static inline int64_t get_clock_realtime(void) +{ + struct timeval tv; + + gettimeofday(&tv, NULL); + return tv.tv_sec * 1000000000LL + (tv.tv_usec * 1000); +} + +/* Warning: don't insert tracepoints into these functions, they are + also used by simpletrace backend and tracepoints would cause + an infinite recursion! */ +#ifdef _WIN32 +extern int64_t clock_freq; + +static inline int64_t get_clock(void) +{ + LARGE_INTEGER ti; + QueryPerformanceCounter(&ti); + return muldiv64(ti.QuadPart, get_ticks_per_sec(), clock_freq); +} + +#else + +extern int use_rt_clock; + +static inline int64_t get_clock(void) +{ +#ifdef CLOCK_MONOTONIC + if (use_rt_clock) { + struct timespec ts; + clock_gettime(CLOCK_MONOTONIC, &ts); + return ts.tv_sec * 1000000000LL + ts.tv_nsec; + } else +#endif + { + /* XXX: using gettimeofday leads to problems if the date + changes, so it should be avoided. */ + return get_clock_realtime(); + } +} +#endif + +/* icount */ +int64_t cpu_get_icount_raw(void); +int64_t cpu_get_icount(void); +int64_t cpu_get_clock(void); +int64_t cpu_icount_to_ns(int64_t icount); + +/*******************************************/ +/* host CPU ticks (if available) */ + +#if defined(_ARCH_PPC) + +static inline int64_t cpu_get_host_ticks(void) +{ + int64_t retval; +#ifdef _ARCH_PPC64 + /* This reads timebase in one 64bit go and includes Cell workaround from: + http://ozlabs.org/pipermail/linuxppc-dev/2006-October/027052.html + */ + __asm__ __volatile__ ("mftb %0\n\t" + "cmpwi %0,0\n\t" + "beq- $-8" + : "=r" (retval)); +#else + /* http://ozlabs.org/pipermail/linuxppc-dev/1999-October/003889.html */ + unsigned long junk; + __asm__ __volatile__ ("mfspr %1,269\n\t" /* mftbu */ + "mfspr %L0,268\n\t" /* mftb */ + "mfspr %0,269\n\t" /* mftbu */ + "cmpw %0,%1\n\t" + "bne $-16" + : "=r" (retval), "=r" (junk)); +#endif + return retval; +} + +#elif defined(__i386__) + +static inline int64_t cpu_get_host_ticks(void) +{ + int64_t val; + asm volatile ("rdtsc" : "=A" (val)); + return val; +} + +#elif defined(__x86_64__) + +static inline int64_t cpu_get_host_ticks(void) +{ + uint32_t low,high; + int64_t val; + asm volatile("rdtsc" : "=a" (low), "=d" (high)); + val = high; + val <<= 32; + val |= low; + return val; +} + +#elif defined(__hppa__) + +static inline int64_t cpu_get_host_ticks(void) +{ + int val; + asm volatile ("mfctl %%cr16, %0" : "=r"(val)); + return val; +} + +#elif defined(__ia64) + +static inline int64_t cpu_get_host_ticks(void) +{ + int64_t val; + asm volatile ("mov %0 = ar.itc" : "=r"(val) :: "memory"); + return val; +} + +#elif defined(__s390__) + +static inline int64_t cpu_get_host_ticks(void) +{ + int64_t val; + asm volatile("stck 0(%1)" : "=m" (val) : "a" (&val) : "cc"); + return val; +} + +#elif defined(__sparc__) + +static inline int64_t cpu_get_host_ticks (void) +{ +#if defined(_LP64) + uint64_t rval; + asm volatile("rd %%tick,%0" : "=r"(rval)); + return rval; +#else + /* We need an %o or %g register for this. For recent enough gcc + there is an "h" constraint for that. Don't bother with that. */ + union { + uint64_t i64; + struct { + uint32_t high; + uint32_t low; + } i32; + } rval; + asm volatile("rd %%tick,%%g1; srlx %%g1,32,%0; mov %%g1,%1" + : "=r"(rval.i32.high), "=r"(rval.i32.low) : : "g1"); + return rval.i64; +#endif +} + +#elif defined(__mips__) && \ + ((defined(__mips_isa_rev) && __mips_isa_rev >= 2) || defined(__linux__)) +/* + * binutils wants to use rdhwr only on mips32r2 + * but as linux kernel emulate it, it's fine + * to use it. + * + */ +#define MIPS_RDHWR(rd, value) { \ + __asm__ __volatile__ (".set push\n\t" \ + ".set mips32r2\n\t" \ + "rdhwr %0, " rd "\n\t" \ + ".set pop" \ + : "=r" (value)); \ + } + +static inline int64_t cpu_get_host_ticks(void) +{ + /* On kernels >= 2.6.25 rdhwr <reg>, $2 and $3 are emulated */ + uint32_t count; + static uint32_t cyc_per_count = 0; + + if (!cyc_per_count) { + MIPS_RDHWR("$3", cyc_per_count); + } + + MIPS_RDHWR("$2", count); + return (int64_t)(count * cyc_per_count); +} + +#elif defined(__alpha__) + +static inline int64_t cpu_get_host_ticks(void) +{ + uint64_t cc; + uint32_t cur, ofs; + + asm volatile("rpcc %0" : "=r"(cc)); + cur = cc; + ofs = cc >> 32; + return cur - ofs; +} + +#else +/* The host CPU doesn't have an easily accessible cycle counter. + Just return a monotonically increasing value. This will be + totally wrong, but hopefully better than nothing. */ +static inline int64_t cpu_get_host_ticks (void) +{ + static int64_t ticks = 0; + return ticks++; +} +#endif + +#ifdef CONFIG_PROFILER +static inline int64_t profile_getclock(void) +{ + return get_clock(); +} + +extern int64_t tcg_time; +extern int64_t dev_time; +#endif + +#endif diff --git a/src/include/qemu/typedefs.h b/src/include/qemu/typedefs.h new file mode 100644 index 0000000..3eedcf4 --- /dev/null +++ b/src/include/qemu/typedefs.h @@ -0,0 +1,93 @@ +#ifndef QEMU_TYPEDEFS_H +#define QEMU_TYPEDEFS_H + +/* A load of opaque types so that device init declarations don't have to + pull in all the real definitions. */ + +/* Please keep this list in alphabetical order */ +typedef struct AdapterInfo AdapterInfo; +typedef struct AddressSpace AddressSpace; +typedef struct AioContext AioContext; +typedef struct AllwinnerAHCIState AllwinnerAHCIState; +typedef struct AudioState AudioState; +typedef struct BlockBackend BlockBackend; +typedef struct BlockBackendRootState BlockBackendRootState; +typedef struct BlockDriverState BlockDriverState; +typedef struct BusClass BusClass; +typedef struct BusState BusState; +typedef struct CharDriverState CharDriverState; +typedef struct CompatProperty CompatProperty; +typedef struct CPUAddressSpace CPUAddressSpace; +typedef struct DeviceListener DeviceListener; +typedef struct DeviceState DeviceState; +typedef struct DisplayChangeListener DisplayChangeListener; +typedef struct DisplayState DisplayState; +typedef struct DisplaySurface DisplaySurface; +typedef struct DriveInfo DriveInfo; +typedef struct EventNotifier EventNotifier; +typedef struct FWCfgIoState FWCfgIoState; +typedef struct FWCfgMemState FWCfgMemState; +typedef struct FWCfgState FWCfgState; +typedef struct HCIInfo HCIInfo; +typedef struct I2CBus I2CBus; +typedef struct I2SCodec I2SCodec; +typedef struct ISABus ISABus; +typedef struct ISADevice ISADevice; +typedef struct LoadStateEntry LoadStateEntry; +typedef struct MACAddr MACAddr; +typedef struct MachineClass MachineClass; +typedef struct MachineState MachineState; +typedef struct MemoryListener MemoryListener; +typedef struct MemoryMappingList MemoryMappingList; +typedef struct MemoryRegion MemoryRegion; +typedef struct MemoryRegionSection MemoryRegionSection; +typedef struct MigrationIncomingState MigrationIncomingState; +typedef struct MigrationParams MigrationParams; +typedef struct MigrationState MigrationState; +typedef struct Monitor Monitor; +typedef struct MonitorDef MonitorDef; +typedef struct MouseTransformInfo MouseTransformInfo; +typedef struct MSIMessage MSIMessage; +typedef struct NetClientState NetClientState; +typedef struct NetFilterState NetFilterState; +typedef struct NICInfo NICInfo; +typedef struct PcGuestInfo PcGuestInfo; +typedef struct PCIBridge PCIBridge; +typedef struct PCIBus PCIBus; +typedef struct PCIDevice PCIDevice; +typedef struct PCIEAERErr PCIEAERErr; +typedef struct PCIEAERLog PCIEAERLog; +typedef struct PCIEAERMsg PCIEAERMsg; +typedef struct PCIEPort PCIEPort; +typedef struct PCIESlot PCIESlot; +typedef struct PCIExpressDevice PCIExpressDevice; +typedef struct PCIExpressHost PCIExpressHost; +typedef struct PCIHostState PCIHostState; +typedef struct PCMachineClass PCMachineClass; +typedef struct PCMachineState PCMachineState; +typedef struct PCMCIACardState PCMCIACardState; +typedef struct PixelFormat PixelFormat; +typedef struct PostcopyDiscardState PostcopyDiscardState; +typedef struct Property Property; +typedef struct PropertyInfo PropertyInfo; +typedef struct QEMUBH QEMUBH; +typedef struct QemuConsole QemuConsole; +typedef struct QEMUFile QEMUFile; +typedef struct QemuOpt QemuOpt; +typedef struct QemuOpts QemuOpts; +typedef struct QemuOptsList QemuOptsList; +typedef struct QEMUSGList QEMUSGList; +typedef struct QEMUSizedBuffer QEMUSizedBuffer; +typedef struct QEMUTimer QEMUTimer; +typedef struct QEMUTimerListGroup QEMUTimerListGroup; +typedef struct RAMBlock RAMBlock; +typedef struct Range Range; +typedef struct SerialState SerialState; +typedef struct SHPCDevice SHPCDevice; +typedef struct SMBusDevice SMBusDevice; +typedef struct SSIBus SSIBus; +typedef struct uWireSlave uWireSlave; +typedef struct VirtIODevice VirtIODevice; +typedef struct Visitor Visitor; + +#endif /* QEMU_TYPEDEFS_H */ diff --git a/src/include/qemu/uri.h b/src/include/qemu/uri.h new file mode 100644 index 0000000..de99b3b --- /dev/null +++ b/src/include/qemu/uri.h @@ -0,0 +1,113 @@ +/** + * Summary: library of generic URI related routines + * Description: library of generic URI related routines + * Implements RFC 2396 + * + * Copyright (C) 1998-2003 Daniel Veillard. All Rights Reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * DANIEL VEILLARD BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER + * IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + * + * Except as contained in this notice, the name of Daniel Veillard shall not + * be used in advertising or otherwise to promote the sale, use or other + * dealings in this Software without prior written authorization from him. + * + * Author: Daniel Veillard + ** + * Copyright (C) 2007 Red Hat, Inc. + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * Authors: + * Richard W.M. Jones <rjones@redhat.com> + * + * Utility functions to help parse and assemble query strings. + */ + +#ifndef QEMU_URI_H +#define QEMU_URI_H + +#ifdef __cplusplus +extern "C" { +#endif + +/** + * URI: + * + * A parsed URI reference. This is a struct containing the various fields + * as described in RFC 2396 but separated for further processing. + */ +typedef struct URI { + char *scheme; /* the URI scheme */ + char *opaque; /* opaque part */ + char *authority; /* the authority part */ + char *server; /* the server part */ + char *user; /* the user part */ + int port; /* the port number */ + char *path; /* the path string */ + char *fragment; /* the fragment identifier */ + int cleanup; /* parsing potentially unclean URI */ + char *query; /* the query string (as it appears in the URI) */ +} URI; + +URI *uri_new(void); +char *uri_resolve(const char *URI, const char *base); +char *uri_resolve_relative(const char *URI, const char *base); +URI *uri_parse(const char *str); +URI *uri_parse_raw(const char *str, int raw); +int uri_parse_into(URI *uri, const char *str); +char *uri_to_string(URI *uri); +char *uri_string_escape(const char *str, const char *list); +char *uri_string_unescape(const char *str, int len, char *target); +void uri_free(URI *uri); + +/* Single web service query parameter 'name=value'. */ +typedef struct QueryParam { + char *name; /* Name (unescaped). */ + char *value; /* Value (unescaped). */ + int ignore; /* Ignore this field in qparam_get_query */ +} QueryParam; + +/* Set of parameters. */ +typedef struct QueryParams { + int n; /* number of parameters used */ + int alloc; /* allocated space */ + QueryParam *p; /* array of parameters */ +} QueryParams; + +struct QueryParams *query_params_new (int init_alloc); +int query_param_append (QueryParams *ps, const char *name, const char *value); +extern char *query_param_to_string (const QueryParams *ps); +extern QueryParams *query_params_parse (const char *query); +extern void query_params_free (QueryParams *ps); + +#ifdef __cplusplus +} +#endif +#endif /* QEMU_URI_H */ diff --git a/src/include/qemu/xattr.h b/src/include/qemu/xattr.h new file mode 100644 index 0000000..f910d96 --- /dev/null +++ b/src/include/qemu/xattr.h @@ -0,0 +1,30 @@ +/* + * Host xattr.h abstraction + * + * Copyright 2011 Red Hat Inc. and/or its affiliates + * + * Authors: + * Avi Kivity <avi@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2, or any + * later version. See the COPYING file in the top-level directory. + * + */ +#ifndef QEMU_XATTR_H +#define QEMU_XATTR_H + +/* + * Modern distributions (e.g. Fedora 15, have no libattr.so, place attr.h + * in /usr/include/sys, and don't have ENOATTR. + */ + +#include "config-host.h" + +#ifdef CONFIG_LIBATTR +# include <attr/xattr.h> +#else +# define ENOATTR ENODATA +# include <sys/xattr.h> +#endif + +#endif |
