diff options
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/list_nulls.h | 145 | ||||
| -rw-r--r-- | include/linux/overflow.h | 346 | ||||
| -rw-r--r-- | include/linux/poison.h | 85 | ||||
| -rw-r--r-- | include/linux/random.h | 1 | ||||
| -rw-r--r-- | include/linux/rcupdate.h | 28 | ||||
| -rw-r--r-- | include/linux/rhashtable-types.h | 135 | ||||
| -rw-r--r-- | include/linux/rhashtable.h | 1205 | ||||
| -rw-r--r-- | include/linux/six.h | 1 | ||||
| -rw-r--r-- | include/linux/slab.h | 1 | ||||
| -rw-r--r-- | include/linux/types.h | 2 |
10 files changed, 1749 insertions, 200 deletions
diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h new file mode 100644 index 00000000..fa6e8471 --- /dev/null +++ b/include/linux/list_nulls.h @@ -0,0 +1,145 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_LIST_NULLS_H +#define _LINUX_LIST_NULLS_H + +#include <linux/poison.h> +#include <linux/const.h> + +/* + * Special version of lists, where end of list is not a NULL pointer, + * but a 'nulls' marker, which can have many different values. + * (up to 2^31 different values guaranteed on all platforms) + * + * In the standard hlist, termination of a list is the NULL pointer. + * In this special 'nulls' variant, we use the fact that objects stored in + * a list are aligned on a word (4 or 8 bytes alignment). + * We therefore use the last significant bit of 'ptr' : + * Set to 1 : This is a 'nulls' end-of-list marker (ptr >> 1) + * Set to 0 : This is a pointer to some object (ptr) + */ + +struct hlist_nulls_head { + struct hlist_nulls_node *first; +}; + +struct hlist_nulls_node { + struct hlist_nulls_node *next, **pprev; +}; +#define NULLS_MARKER(value) (1UL | (((long)value) << 1)) +#define INIT_HLIST_NULLS_HEAD(ptr, nulls) \ + ((ptr)->first = (struct hlist_nulls_node *) NULLS_MARKER(nulls)) + +#define hlist_nulls_entry(ptr, type, member) container_of(ptr,type,member) + +#define hlist_nulls_entry_safe(ptr, type, member) \ + ({ typeof(ptr) ____ptr = (ptr); \ + !is_a_nulls(____ptr) ? hlist_nulls_entry(____ptr, type, member) : NULL; \ + }) +/** + * ptr_is_a_nulls - Test if a ptr is a nulls + * @ptr: ptr to be tested + * + */ +static inline int is_a_nulls(const struct hlist_nulls_node *ptr) +{ + return ((unsigned long)ptr & 1); +} + +/** + * get_nulls_value - Get the 'nulls' value of the end of chain + * @ptr: end of chain + * + * Should be called only if is_a_nulls(ptr); + */ +static inline unsigned long get_nulls_value(const struct hlist_nulls_node *ptr) +{ + return ((unsigned long)ptr) >> 1; +} + +/** + * hlist_nulls_unhashed - Has node been removed and reinitialized? + * @h: Node to be checked + * + * Not that not all removal functions will leave a node in unhashed state. + * For example, hlist_del_init_rcu() leaves the node in unhashed state, + * but hlist_nulls_del() does not. + */ +static inline int hlist_nulls_unhashed(const struct hlist_nulls_node *h) +{ + return !h->pprev; +} + +/** + * hlist_nulls_unhashed_lockless - Has node been removed and reinitialized? + * @h: Node to be checked + * + * Not that not all removal functions will leave a node in unhashed state. + * For example, hlist_del_init_rcu() leaves the node in unhashed state, + * but hlist_nulls_del() does not. Unlike hlist_nulls_unhashed(), this + * function may be used locklessly. + */ +static inline int hlist_nulls_unhashed_lockless(const struct hlist_nulls_node *h) +{ + return !READ_ONCE(h->pprev); +} + +static inline int hlist_nulls_empty(const struct hlist_nulls_head *h) +{ + return is_a_nulls(READ_ONCE(h->first)); +} + +static inline void hlist_nulls_add_head(struct hlist_nulls_node *n, + struct hlist_nulls_head *h) +{ + struct hlist_nulls_node *first = h->first; + + n->next = first; + WRITE_ONCE(n->pprev, &h->first); + h->first = n; + if (!is_a_nulls(first)) + WRITE_ONCE(first->pprev, &n->next); +} + +static inline void __hlist_nulls_del(struct hlist_nulls_node *n) +{ + struct hlist_nulls_node *next = n->next; + struct hlist_nulls_node **pprev = n->pprev; + + WRITE_ONCE(*pprev, next); + if (!is_a_nulls(next)) + WRITE_ONCE(next->pprev, pprev); +} + +static inline void hlist_nulls_del(struct hlist_nulls_node *n) +{ + __hlist_nulls_del(n); + WRITE_ONCE(n->pprev, LIST_POISON2); +} + +/** + * hlist_nulls_for_each_entry - iterate over list of given type + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_node to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the hlist_node within the struct. + * + */ +#define hlist_nulls_for_each_entry(tpos, pos, head, member) \ + for (pos = (head)->first; \ + (!is_a_nulls(pos)) && \ + ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1;}); \ + pos = pos->next) + +/** + * hlist_nulls_for_each_entry_from - iterate over a hlist continuing from current point + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_node to use as a loop cursor. + * @member: the name of the hlist_node within the struct. + * + */ +#define hlist_nulls_for_each_entry_from(tpos, pos, member) \ + for (; (!is_a_nulls(pos)) && \ + ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1;}); \ + pos = pos->next) + +#endif diff --git a/include/linux/overflow.h b/include/linux/overflow.h new file mode 100644 index 00000000..ef74051d --- /dev/null +++ b/include/linux/overflow.h @@ -0,0 +1,346 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +#ifndef __LINUX_OVERFLOW_H +#define __LINUX_OVERFLOW_H + +#include <linux/compiler.h> +#include <linux/limits.h> + +/* + * In the fallback code below, we need to compute the minimum and + * maximum values representable in a given type. These macros may also + * be useful elsewhere, so we provide them outside the + * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block. + * + * It would seem more obvious to do something like + * + * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0) + * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0) + * + * Unfortunately, the middle expressions, strictly speaking, have + * undefined behaviour, and at least some versions of gcc warn about + * the type_max expression (but not if -fsanitize=undefined is in + * effect; in that case, the warning is deferred to runtime...). + * + * The slightly excessive casting in type_min is to make sure the + * macros also produce sensible values for the exotic type _Bool. [The + * overflow checkers only almost work for _Bool, but that's + * a-feature-not-a-bug, since people shouldn't be doing arithmetic on + * _Bools. Besides, the gcc builtins don't allow _Bool* as third + * argument.] + * + * Idea stolen from + * https://mail-index.netbsd.org/tech-misc/2007/02/05/0000.html - + * credit to Christian Biere. + */ +#define is_signed_type(type) (((type)(-1)) < (type)1) +#define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type))) +#define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T))) +#define type_min(T) ((T)((T)-type_max(T)-(T)1)) + +/* + * Avoids triggering -Wtype-limits compilation warning, + * while using unsigned data types to check a < 0. + */ +#define is_non_negative(a) ((a) > 0 || (a) == 0) +#define is_negative(a) (!(is_non_negative(a))) + +/* + * Allows for effectively applying __must_check to a macro so we can have + * both the type-agnostic benefits of the macros while also being able to + * enforce that the return value is, in fact, checked. + */ +static inline bool __must_check __must_check_overflow(bool overflow) +{ + return unlikely(overflow); +} + +#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW +/* + * For simplicity and code hygiene, the fallback code below insists on + * a, b and *d having the same type (similar to the min() and max() + * macros), whereas gcc's type-generic overflow checkers accept + * different types. Hence we don't just make check_add_overflow an + * alias for __builtin_add_overflow, but add type checks similar to + * below. + */ +#define check_add_overflow(a, b, d) __must_check_overflow(({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + __builtin_add_overflow(__a, __b, __d); \ +})) + +#define check_sub_overflow(a, b, d) __must_check_overflow(({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + __builtin_sub_overflow(__a, __b, __d); \ +})) + +#define check_mul_overflow(a, b, d) __must_check_overflow(({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + __builtin_mul_overflow(__a, __b, __d); \ +})) + +#else + + +/* Checking for unsigned overflow is relatively easy without causing UB. */ +#define __unsigned_add_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = __a + __b; \ + *__d < __a; \ +}) +#define __unsigned_sub_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = __a - __b; \ + __a < __b; \ +}) +/* + * If one of a or b is a compile-time constant, this avoids a division. + */ +#define __unsigned_mul_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = __a * __b; \ + __builtin_constant_p(__b) ? \ + __b > 0 && __a > type_max(typeof(__a)) / __b : \ + __a > 0 && __b > type_max(typeof(__b)) / __a; \ +}) + +/* + * For signed types, detecting overflow is much harder, especially if + * we want to avoid UB. But the interface of these macros is such that + * we must provide a result in *d, and in fact we must produce the + * result promised by gcc's builtins, which is simply the possibly + * wrapped-around value. Fortunately, we can just formally do the + * operations in the widest relevant unsigned type (u64) and then + * truncate the result - gcc is smart enough to generate the same code + * with and without the (u64) casts. + */ + +/* + * Adding two signed integers can overflow only if they have the same + * sign, and overflow has happened iff the result has the opposite + * sign. + */ +#define __signed_add_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = (u64)__a + (u64)__b; \ + (((~(__a ^ __b)) & (*__d ^ __a)) \ + & type_min(typeof(__a))) != 0; \ +}) + +/* + * Subtraction is similar, except that overflow can now happen only + * when the signs are opposite. In this case, overflow has happened if + * the result has the opposite sign of a. + */ +#define __signed_sub_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = (u64)__a - (u64)__b; \ + ((((__a ^ __b)) & (*__d ^ __a)) \ + & type_min(typeof(__a))) != 0; \ +}) + +/* + * Signed multiplication is rather hard. gcc always follows C99, so + * division is truncated towards 0. This means that we can write the + * overflow check like this: + * + * (a > 0 && (b > MAX/a || b < MIN/a)) || + * (a < -1 && (b > MIN/a || b < MAX/a) || + * (a == -1 && b == MIN) + * + * The redundant casts of -1 are to silence an annoying -Wtype-limits + * (included in -Wextra) warning: When the type is u8 or u16, the + * __b_c_e in check_mul_overflow obviously selects + * __unsigned_mul_overflow, but unfortunately gcc still parses this + * code and warns about the limited range of __b. + */ + +#define __signed_mul_overflow(a, b, d) ({ \ + typeof(a) __a = (a); \ + typeof(b) __b = (b); \ + typeof(d) __d = (d); \ + typeof(a) __tmax = type_max(typeof(a)); \ + typeof(a) __tmin = type_min(typeof(a)); \ + (void) (&__a == &__b); \ + (void) (&__a == __d); \ + *__d = (u64)__a * (u64)__b; \ + (__b > 0 && (__a > __tmax/__b || __a < __tmin/__b)) || \ + (__b < (typeof(__b))-1 && (__a > __tmin/__b || __a < __tmax/__b)) || \ + (__b == (typeof(__b))-1 && __a == __tmin); \ +}) + + +#define check_add_overflow(a, b, d) __must_check_overflow( \ + __builtin_choose_expr(is_signed_type(typeof(a)), \ + __signed_add_overflow(a, b, d), \ + __unsigned_add_overflow(a, b, d))) + +#define check_sub_overflow(a, b, d) __must_check_overflow( \ + __builtin_choose_expr(is_signed_type(typeof(a)), \ + __signed_sub_overflow(a, b, d), \ + __unsigned_sub_overflow(a, b, d))) + +#define check_mul_overflow(a, b, d) __must_check_overflow( \ + __builtin_choose_expr(is_signed_type(typeof(a)), \ + __signed_mul_overflow(a, b, d), \ + __unsigned_mul_overflow(a, b, d))) + +#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ + +/** check_shl_overflow() - Calculate a left-shifted value and check overflow + * + * @a: Value to be shifted + * @s: How many bits left to shift + * @d: Pointer to where to store the result + * + * Computes *@d = (@a << @s) + * + * Returns true if '*d' cannot hold the result or when 'a << s' doesn't + * make sense. Example conditions: + * - 'a << s' causes bits to be lost when stored in *d. + * - 's' is garbage (e.g. negative) or so large that the result of + * 'a << s' is guaranteed to be 0. + * - 'a' is negative. + * - 'a << s' sets the sign bit, if any, in '*d'. + * + * '*d' will hold the results of the attempted shift, but is not + * considered "safe for use" if false is returned. + */ +#define check_shl_overflow(a, s, d) __must_check_overflow(({ \ + typeof(a) _a = a; \ + typeof(s) _s = s; \ + typeof(d) _d = d; \ + u64 _a_full = _a; \ + unsigned int _to_shift = \ + is_non_negative(_s) && _s < 8 * sizeof(*d) ? _s : 0; \ + *_d = (_a_full << _to_shift); \ + (_to_shift != _s || is_negative(*_d) || is_negative(_a) || \ + (*_d >> _to_shift) != _a); \ +})) + +/** + * array_size() - Calculate size of 2-dimensional array. + * + * @a: dimension one + * @b: dimension two + * + * Calculates size of 2-dimensional array: @a * @b. + * + * Returns: number of bytes needed to represent the array or SIZE_MAX on + * overflow. + */ +static inline __must_check size_t array_size(size_t a, size_t b) +{ + size_t bytes; + + if (check_mul_overflow(a, b, &bytes)) + return SIZE_MAX; + + return bytes; +} + +/** + * array3_size() - Calculate size of 3-dimensional array. + * + * @a: dimension one + * @b: dimension two + * @c: dimension three + * + * Calculates size of 3-dimensional array: @a * @b * @c. + * + * Returns: number of bytes needed to represent the array or SIZE_MAX on + * overflow. + */ +static inline __must_check size_t array3_size(size_t a, size_t b, size_t c) +{ + size_t bytes; + + if (check_mul_overflow(a, b, &bytes)) + return SIZE_MAX; + if (check_mul_overflow(bytes, c, &bytes)) + return SIZE_MAX; + + return bytes; +} + +/* + * Compute a*b+c, returning SIZE_MAX on overflow. Internal helper for + * struct_size() below. + */ +static inline __must_check size_t __ab_c_size(size_t a, size_t b, size_t c) +{ + size_t bytes; + + if (check_mul_overflow(a, b, &bytes)) + return SIZE_MAX; + if (check_add_overflow(bytes, c, &bytes)) + return SIZE_MAX; + + return bytes; +} + +/** + * struct_size() - Calculate size of structure with trailing array. + * @p: Pointer to the structure. + * @member: Name of the array member. + * @count: Number of elements in the array. + * + * Calculates size of memory needed for structure @p followed by an + * array of @count number of @member elements. + * + * Return: number of bytes needed or SIZE_MAX on overflow. + */ +#define struct_size(p, member, count) \ + __ab_c_size(count, \ + sizeof(*(p)->member) + __must_be_array((p)->member),\ + sizeof(*(p))) + +/** + * flex_array_size() - Calculate size of a flexible array member + * within an enclosing structure. + * + * @p: Pointer to the structure. + * @member: Name of the flexible array member. + * @count: Number of elements in the array. + * + * Calculates size of a flexible array of @count number of @member + * elements, at the end of structure @p. + * + * Return: number of bytes needed or SIZE_MAX on overflow. + */ +#define flex_array_size(p, member, count) \ + array_size(count, \ + sizeof(*(p)->member) + __must_be_array((p)->member)) + +#endif /* __LINUX_OVERFLOW_H */ diff --git a/include/linux/poison.h b/include/linux/poison.h new file mode 100644 index 00000000..dc8ae5d8 --- /dev/null +++ b/include/linux/poison.h @@ -0,0 +1,85 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_POISON_H +#define _LINUX_POISON_H + +/********** include/linux/list.h **********/ + +/* + * Architectures might want to move the poison pointer offset + * into some well-recognized area such as 0xdead000000000000, + * that is also not mappable by user-space exploits: + */ +#ifdef CONFIG_ILLEGAL_POINTER_VALUE +# define POISON_POINTER_DELTA _AC(CONFIG_ILLEGAL_POINTER_VALUE, UL) +#else +# define POISON_POINTER_DELTA 0 +#endif + +/* + * These are non-NULL pointers that will result in page faults + * under normal circumstances, used to verify that nobody uses + * non-initialized list entries. + */ +#define LIST_POISON1 ((void *) 0x100 + POISON_POINTER_DELTA) +#define LIST_POISON2 ((void *) 0x122 + POISON_POINTER_DELTA) + +/********** include/linux/timer.h **********/ +#define TIMER_ENTRY_STATIC ((void *) 0x300 + POISON_POINTER_DELTA) + +/********** mm/page_poison.c **********/ +#ifdef CONFIG_PAGE_POISONING_ZERO +#define PAGE_POISON 0x00 +#else +#define PAGE_POISON 0xaa +#endif + +/********** mm/page_alloc.c ************/ + +#define TAIL_MAPPING ((void *) 0x400 + POISON_POINTER_DELTA) + +/********** mm/slab.c **********/ +/* + * Magic nums for obj red zoning. + * Placed in the first word before and the first word after an obj. + */ +#define RED_INACTIVE 0x09F911029D74E35BULL /* when obj is inactive */ +#define RED_ACTIVE 0xD84156C5635688C0ULL /* when obj is active */ + +#define SLUB_RED_INACTIVE 0xbb +#define SLUB_RED_ACTIVE 0xcc + +/* ...and for poisoning */ +#define POISON_INUSE 0x5a /* for use-uninitialised poisoning */ +#define POISON_FREE 0x6b /* for use-after-free poisoning */ +#define POISON_END 0xa5 /* end-byte of poisoning */ + +/********** arch/$ARCH/mm/init.c **********/ +#define POISON_FREE_INITMEM 0xcc + +/********** arch/ia64/hp/common/sba_iommu.c **********/ +/* + * arch/ia64/hp/common/sba_iommu.c uses a 16-byte poison string with a + * value of "SBAIOMMU POISON\0" for spill-over poisoning. + */ + +/********** fs/jbd/journal.c **********/ +#define JBD_POISON_FREE 0x5b +#define JBD2_POISON_FREE 0x5c + +/********** drivers/base/dmapool.c **********/ +#define POOL_POISON_FREED 0xa7 /* !inuse */ +#define POOL_POISON_ALLOCATED 0xa9 /* !initted */ + +/********** drivers/atm/ **********/ +#define ATM_POISON_FREE 0x12 +#define ATM_POISON 0xdeadbeef + +/********** kernel/mutexes **********/ +#define MUTEX_DEBUG_INIT 0x11 +#define MUTEX_DEBUG_FREE 0x22 +#define MUTEX_POISON_WW_CTX ((void *) 0x500 + POISON_POINTER_DELTA) + +/********** security/ **********/ +#define KEY_DESTROY 0xbd + +#endif diff --git a/include/linux/random.h b/include/linux/random.h index c38ae46d..28c595a0 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -45,6 +45,7 @@ static inline type get_random_##type(void) \ get_random_type(int); get_random_type(long); +get_random_type(u32); get_random_type(u64); #endif /* _LINUX_RANDOM_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index c99d78a8..ae292241 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -13,4 +13,32 @@ #define RCU_INIT_POINTER(p, v) WRITE_ONCE(p, v) +/* Has the specified rcu_head structure been handed to call_rcu()? */ + +/** + * rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu() + * @rhp: The rcu_head structure to initialize. + * + * If you intend to invoke rcu_head_after_call_rcu() to test whether a + * given rcu_head structure has already been passed to call_rcu(), then + * you must also invoke this rcu_head_init() function on it just after + * allocating that structure. Calls to this function must not race with + * calls to call_rcu(), rcu_head_after_call_rcu(), or callback invocation. + */ +static inline void rcu_head_init(struct rcu_head *rhp) +{ + rhp->func = (void *)~0L; +} + +static inline bool +rcu_head_after_call_rcu(struct rcu_head *rhp, + void (*f)(struct rcu_head *head)) +{ + void (*func)(struct rcu_head *head) = READ_ONCE(rhp->func); + + if (func == f) + return true; + return false; +} + #endif /* __TOOLS_LINUX_RCUPDATE_H */ diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h new file mode 100644 index 00000000..57467cbf --- /dev/null +++ b/include/linux/rhashtable-types.h @@ -0,0 +1,135 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Resizable, Scalable, Concurrent Hash Table + * + * Simple structures that might be needed in include + * files. + */ + +#ifndef _LINUX_RHASHTABLE_TYPES_H +#define _LINUX_RHASHTABLE_TYPES_H + +#include <linux/atomic.h> +#include <linux/compiler.h> +#include <linux/mutex.h> +#include <linux/workqueue.h> + +struct rhash_head { + struct rhash_head __rcu *next; +}; + +struct rhlist_head { + struct rhash_head rhead; + struct rhlist_head __rcu *next; +}; + +struct bucket_table; + +/** + * struct rhashtable_compare_arg - Key for the function rhashtable_compare + * @ht: Hash table + * @key: Key to compare against + */ +struct rhashtable_compare_arg { + struct rhashtable *ht; + const void *key; +}; + +typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed); +typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 len, u32 seed); +typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg, + const void *obj); + +/** + * struct rhashtable_params - Hash table construction parameters + * @nelem_hint: Hint on number of elements, should be 75% of desired size + * @key_len: Length of key + * @key_offset: Offset of key in struct to be hashed + * @head_offset: Offset of rhash_head in struct to be hashed + * @max_size: Maximum size while expanding + * @min_size: Minimum size while shrinking + * @automatic_shrinking: Enable automatic shrinking of tables + * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) + * @obj_hashfn: Function to hash object + * @obj_cmpfn: Function to compare key with object + */ +struct rhashtable_params { + u16 nelem_hint; + u16 key_len; + u16 key_offset; + u16 head_offset; + unsigned int max_size; + u16 min_size; + bool automatic_shrinking; + rht_hashfn_t hashfn; + rht_obj_hashfn_t obj_hashfn; + rht_obj_cmpfn_t obj_cmpfn; +}; + +/** + * struct rhashtable - Hash table handle + * @tbl: Bucket table + * @key_len: Key length for hashfn + * @max_elems: Maximum number of elements in table + * @p: Configuration parameters + * @rhlist: True if this is an rhltable + * @run_work: Deferred worker to expand/shrink asynchronously + * @mutex: Mutex to protect current/future table swapping + * @lock: Spin lock to protect walker list + * @nelems: Number of elements in table + */ +struct rhashtable { + struct bucket_table __rcu *tbl; + unsigned int key_len; + unsigned int max_elems; + struct rhashtable_params p; + bool rhlist; + struct work_struct run_work; + struct mutex mutex; + spinlock_t lock; + atomic_t nelems; +}; + +/** + * struct rhltable - Hash table with duplicate objects in a list + * @ht: Underlying rhtable + */ +struct rhltable { + struct rhashtable ht; +}; + +/** + * struct rhashtable_walker - Hash table walker + * @list: List entry on list of walkers + * @tbl: The table that we were walking over + */ +struct rhashtable_walker { + struct list_head list; + struct bucket_table *tbl; +}; + +/** + * struct rhashtable_iter - Hash table iterator + * @ht: Table to iterate through + * @p: Current pointer + * @list: Current hash list pointer + * @walker: Associated rhashtable walker + * @slot: Current slot + * @skip: Number of entries to skip in slot + */ +struct rhashtable_iter { + struct rhashtable *ht; + struct rhash_head *p; + struct rhlist_head *list; + struct rhashtable_walker walker; + unsigned int slot; + unsigned int skip; + bool end_of_table; +}; + +int rhashtable_init(struct rhashtable *ht, + const struct rhashtable_params *params); +int rhltable_init(struct rhltable *hlt, + const struct rhashtable_params *params); + +#endif /* _LINUX_RHASHTABLE_TYPES_H */ diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 8dbe1533..6cf8c257 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -1,7 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Resizable, Scalable, Concurrent Hash Table * - * Copyright (c) 2015 Herbert Xu <herbert@gondor.apana.org.au> + * Copyright (c) 2015-2016 Herbert Xu <herbert@gondor.apana.org.au> * Copyright (c) 2014-2015 Thomas Graf <tgraf@suug.ch> * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net> * @@ -17,92 +18,93 @@ #ifndef _LINUX_RHASHTABLE_H #define _LINUX_RHASHTABLE_H -#include <linux/atomic.h> -#include <linux/cache.h> -#include <linux/compiler.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/jhash.h> -#include <linux/workqueue.h> -#include <linux/mutex.h> -#include <linux/spinlock.h> +#include <linux/list_nulls.h> #include <linux/rcupdate.h> +#include <linux/workqueue.h> +#include <linux/rculist.h> +#include <linux/bit_spinlock.h> -#define RHT_BASE_BITS 4 -#define RHT_HASH_BITS 27 -#define RHT_BASE_SHIFT RHT_HASH_BITS -#define RHT_HASH_RESERVED_SPACE (RHT_BASE_BITS + 1) +#define BIT(nr) (1UL << (nr)) -struct rhash_head { - struct rhash_head __rcu *next; -}; +#include <linux/rhashtable-types.h> +/* + * Objects in an rhashtable have an embedded struct rhash_head + * which is linked into as hash chain from the hash table - or one + * of two or more hash tables when the rhashtable is being resized. + * The end of the chain is marked with a special nulls marks which has + * the least significant bit set but otherwise stores the address of + * the hash bucket. This allows us to be sure we've found the end + * of the right list. + * The value stored in the hash bucket has BIT(0) used as a lock bit. + * This bit must be atomically set before any changes are made to + * the chain. To avoid dereferencing this pointer without clearing + * the bit first, we use an opaque 'struct rhash_lock_head *' for the + * pointer stored in the bucket. This struct needs to be defined so + * that rcu_dereference() works on it, but it has no content so a + * cast is needed for it to be useful. This ensures it isn't + * used by mistake with clearing the lock bit first. + */ +struct rhash_lock_head {}; +/* Maximum chain length before rehash + * + * The maximum (not average) chain length grows with the size of the hash + * table, at a rate of (log N)/(log log N). + * + * The value of 16 is selected so that even if the hash table grew to + * 2^32 you would not expect the maximum chain length to exceed it + * unless we are under attack (or extremely unlucky). + * + * As this limit is only to detect attacks, we don't need to set it to a + * lower value as you'd need the chain length to vastly exceed 16 to have + * any real effect on the system. + */ +#define RHT_ELASTICITY 16u + +/** + * struct bucket_table - Table of hash buckets + * @size: Number of hash buckets + * @nest: Number of bits of first-level nested table. + * @rehash: Current bucket being rehashed + * @hash_rnd: Random seed to fold into hash + * @walkers: List of active walkers + * @rcu: RCU structure for freeing the table + * @future_tbl: Table under construction during rehashing + * @ntbl: Nested table used when out of memory. + * @buckets: size * hash buckets + */ struct bucket_table { unsigned int size; - unsigned int rehash; + unsigned int nest; u32 hash_rnd; - unsigned int locks_mask; - spinlock_t *locks; struct list_head walkers; struct rcu_head rcu; struct bucket_table __rcu *future_tbl; - struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp; -}; - -struct rhashtable_compare_arg { - struct rhashtable *ht; - const void *key; + struct rhash_lock_head __rcu *buckets[] ____cacheline_aligned_in_smp; }; -typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed); -typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 len, u32 seed); -typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg, - const void *obj); - -struct rhashtable_params { - size_t nelem_hint; - size_t key_len; - size_t key_offset; - size_t head_offset; - unsigned int insecure_max_entries; - unsigned int max_size; - unsigned int min_size; - u32 nulls_base; - bool insecure_elasticity; - bool automatic_shrinking; - size_t locks_mul; - rht_hashfn_t hashfn; - rht_obj_hashfn_t obj_hashfn; - rht_obj_cmpfn_t obj_cmpfn; -}; - -struct rhashtable { - struct bucket_table __rcu *tbl; - atomic_t nelems; - unsigned int key_len; - unsigned int elasticity; - struct rhashtable_params p; - struct work_struct run_work; - struct mutex mutex; - spinlock_t lock; -}; - -struct rhashtable_walker { - struct list_head list; - struct bucket_table *tbl; -}; - -#define NULLS_MARKER(value) (1UL | (((long)value) << 1)) - -static inline unsigned long rht_marker(const struct rhashtable *ht, u32 hash) -{ - return NULLS_MARKER(ht->p.nulls_base + hash); -} - -#define INIT_RHT_NULLS_HEAD(ptr, ht, hash) \ - ((ptr) = (typeof(ptr)) rht_marker(ht, hash)) +/* + * NULLS_MARKER() expects a hash value with the low + * bits mostly likely to be significant, and it discards + * the msb. + * We give it an address, in which the bottom bit is + * always 0, and the msb might be significant. + * So we shift the address down one bit to align with + * expectations and avoid losing a significant bit. + * + * We never store the NULLS_MARKER in the hash table + * itself as we need the lsb for locking. + * Instead we store a NULL + */ +#define RHT_NULLS_MARKER(ptr) \ + ((void *)NULLS_MARKER(((unsigned long) (ptr)) >> 1)) +#define INIT_RHT_NULLS_HEAD(ptr) \ + ((ptr) = NULL) static inline bool rht_is_a_nulls(const struct rhash_head *ptr) { @@ -118,37 +120,45 @@ static inline void *rht_obj(const struct rhashtable *ht, static inline unsigned int rht_bucket_index(const struct bucket_table *tbl, unsigned int hash) { - return (hash >> RHT_HASH_RESERVED_SPACE) & (tbl->size - 1); + return hash & (tbl->size - 1); } -static inline unsigned int rht_key_hashfn( - struct rhashtable *ht, const struct bucket_table *tbl, - const void *key, const struct rhashtable_params params) +static inline unsigned int rht_key_get_hash(struct rhashtable *ht, + const void *key, const struct rhashtable_params params, + unsigned int hash_rnd) { unsigned int hash; /* params must be equal to ht->p if it isn't constant. */ if (!__builtin_constant_p(params.key_len)) - hash = ht->p.hashfn(key, ht->key_len, tbl->hash_rnd); + hash = ht->p.hashfn(key, ht->key_len, hash_rnd); else if (params.key_len) { unsigned int key_len = params.key_len; if (params.hashfn) - hash = params.hashfn(key, key_len, tbl->hash_rnd); + hash = params.hashfn(key, key_len, hash_rnd); else if (key_len & (sizeof(u32) - 1)) - hash = jhash(key, key_len, tbl->hash_rnd); + hash = jhash(key, key_len, hash_rnd); else - hash = jhash2(key, key_len / sizeof(u32), - tbl->hash_rnd); + hash = jhash2(key, key_len / sizeof(u32), hash_rnd); } else { unsigned int key_len = ht->p.key_len; if (params.hashfn) - hash = params.hashfn(key, key_len, tbl->hash_rnd); + hash = params.hashfn(key, key_len, hash_rnd); else - hash = jhash(key, key_len, tbl->hash_rnd); + hash = jhash(key, key_len, hash_rnd); } + return hash; +} + +static inline unsigned int rht_key_hashfn( + struct rhashtable *ht, const struct bucket_table *tbl, + const void *key, const struct rhashtable_params params) +{ + unsigned int hash = rht_key_get_hash(ht, key, params, tbl->hash_rnd); + return rht_bucket_index(tbl, hash); } @@ -165,6 +175,11 @@ static inline unsigned int rht_head_hashfn( rht_key_hashfn(ht, tbl, ptr + params.key_offset, params); } +/** + * rht_grow_above_75 - returns true if nelems > 0.75 * table-size + * @ht: hash table + * @tbl: current table + */ static inline bool rht_grow_above_75(const struct rhashtable *ht, const struct bucket_table *tbl) { @@ -173,6 +188,11 @@ static inline bool rht_grow_above_75(const struct rhashtable *ht, (!ht->p.max_size || tbl->size < ht->p.max_size); } +/** + * rht_shrink_below_30 - returns true if nelems < 0.3 * table-size + * @ht: hash table + * @tbl: current table + */ static inline bool rht_shrink_below_30(const struct rhashtable *ht, const struct bucket_table *tbl) { @@ -181,6 +201,11 @@ static inline bool rht_shrink_below_30(const struct rhashtable *ht, tbl->size > ht->p.min_size; } +/** + * rht_grow_above_100 - returns true if nelems > table-size + * @ht: hash table + * @tbl: current table + */ static inline bool rht_grow_above_100(const struct rhashtable *ht, const struct bucket_table *tbl) { @@ -188,62 +213,353 @@ static inline bool rht_grow_above_100(const struct rhashtable *ht, (!ht->p.max_size || tbl->size < ht->p.max_size); } +/** + * rht_grow_above_max - returns true if table is above maximum + * @ht: hash table + * @tbl: current table + */ static inline bool rht_grow_above_max(const struct rhashtable *ht, const struct bucket_table *tbl) { - return ht->p.insecure_max_entries && - atomic_read(&ht->nelems) >= ht->p.insecure_max_entries; + return atomic_read(&ht->nelems) >= ht->max_elems; } -static inline spinlock_t *rht_bucket_lock(const struct bucket_table *tbl, - unsigned int hash) +#ifdef CONFIG_PROVE_LOCKING +int lockdep_rht_mutex_is_held(struct rhashtable *ht); +int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, u32 hash); +#else +static inline int lockdep_rht_mutex_is_held(struct rhashtable *ht) { - return &tbl->locks[hash & tbl->locks_mask]; + return 1; } -int rhashtable_insert_rehash(struct rhashtable *, struct bucket_table *); -struct bucket_table *rhashtable_insert_slow(struct rhashtable *, - const void *, - struct rhash_head *, - struct bucket_table *); +static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, + u32 hash) +{ + return 1; +} +#endif /* CONFIG_PROVE_LOCKING */ + +void *rhashtable_insert_slow(struct rhashtable *ht, const void *key, + struct rhash_head *obj); -int rhashtable_init(struct rhashtable *, const struct rhashtable_params *); -void rhashtable_destroy(struct rhashtable *); +void rhashtable_walk_enter(struct rhashtable *ht, + struct rhashtable_iter *iter); +void rhashtable_walk_exit(struct rhashtable_iter *iter); +int rhashtable_walk_start_check(struct rhashtable_iter *iter) __acquires(RCU); -#define rht_dereference(p, ht) rcu_dereference(p) -#define rht_dereference_rcu(p, ht) rcu_dereference(p) -#define rht_dereference_bucket(p, tbl, hash) rcu_dereference(p) -#define rht_dereference_bucket_rcu(p, tbl, hash) rcu_dereference(p) +static inline void rhashtable_walk_start(struct rhashtable_iter *iter) +{ + (void)rhashtable_walk_start_check(iter); +} + +void *rhashtable_walk_next(struct rhashtable_iter *iter); +void *rhashtable_walk_peek(struct rhashtable_iter *iter); +void rhashtable_walk_stop(struct rhashtable_iter *iter) __releases(RCU); + +void rhashtable_free_and_destroy(struct rhashtable *ht, + void (*free_fn)(void *ptr, void *arg), + void *arg); +void rhashtable_destroy(struct rhashtable *ht); + +struct rhash_lock_head __rcu **rht_bucket_nested( + const struct bucket_table *tbl, unsigned int hash); +struct rhash_lock_head __rcu **__rht_bucket_nested( + const struct bucket_table *tbl, unsigned int hash); +struct rhash_lock_head __rcu **rht_bucket_nested_insert( + struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash); + +#define rht_dereference(p, ht) \ + rcu_dereference(p) + +#define rht_dereference_rcu(p, ht) \ + rcu_dereference(p) + +#define rht_dereference_bucket(p, tbl, hash) \ + rcu_dereference(p) + +#define rht_dereference_bucket_rcu(p, tbl, hash) \ + rcu_dereference(p) #define rht_entry(tpos, pos, member) \ ({ tpos = container_of(pos, typeof(*tpos), member); 1; }) -#define rht_for_each_continue(pos, head, tbl, hash) \ - for (pos = rht_dereference_bucket(head, tbl, hash); \ - !rht_is_a_nulls(pos); \ +static inline struct rhash_lock_head __rcu *const *rht_bucket( + const struct bucket_table *tbl, unsigned int hash) +{ + return unlikely(tbl->nest) ? rht_bucket_nested(tbl, hash) : + &tbl->buckets[hash]; +} + +static inline struct rhash_lock_head __rcu **rht_bucket_var( + struct bucket_table *tbl, unsigned int hash) +{ + return unlikely(tbl->nest) ? __rht_bucket_nested(tbl, hash) : + &tbl->buckets[hash]; +} + +static inline struct rhash_lock_head __rcu **rht_bucket_insert( + struct rhashtable *ht, struct bucket_table *tbl, unsigned int hash) +{ + return unlikely(tbl->nest) ? rht_bucket_nested_insert(ht, tbl, hash) : + &tbl->buckets[hash]; +} + +/* + * We lock a bucket by setting BIT(0) in the pointer - this is always + * zero in real pointers. The NULLS mark is never stored in the bucket, + * rather we store NULL if the bucket is empty. + * bit_spin_locks do not handle contention well, but the whole point + * of the hashtable design is to achieve minimum per-bucket contention. + * A nested hash table might not have a bucket pointer. In that case + * we cannot get a lock. For remove and replace the bucket cannot be + * interesting and doesn't need locking. + * For insert we allocate the bucket if this is the last bucket_table, + * and then take the lock. + * Sometimes we unlock a bucket by writing a new pointer there. In that + * case we don't need to unlock, but we do need to reset state such as + * local_bh. For that we have rht_assign_unlock(). As rcu_assign_pointer() + * provides the same release semantics that bit_spin_unlock() provides, + * this is safe. + * When we write to a bucket without unlocking, we use rht_assign_locked(). + */ + +static inline void rht_lock(struct bucket_table *tbl, + struct rhash_lock_head __rcu **bkt) +{ + bit_spin_lock(0, (unsigned long *)bkt); +} + +static inline void rht_lock_nested(struct bucket_table *tbl, + struct rhash_lock_head __rcu **bucket, + unsigned int subclass) +{ + bit_spin_lock(0, (unsigned long *)bucket); +} + +static inline void rht_unlock(struct bucket_table *tbl, + struct rhash_lock_head __rcu **bkt) +{ + bit_spin_unlock(0, (unsigned long *)bkt); +} + +static inline struct rhash_head *__rht_ptr( + struct rhash_lock_head *p, struct rhash_lock_head __rcu *const *bkt) +{ + return (struct rhash_head *) + ((unsigned long)p & ~BIT(0) ?: + (unsigned long)RHT_NULLS_MARKER(bkt)); +} + +/* + * Where 'bkt' is a bucket and might be locked: + * rht_ptr_rcu() dereferences that pointer and clears the lock bit. + * rht_ptr() dereferences in a context where the bucket is locked. + * rht_ptr_exclusive() dereferences in a context where exclusive + * access is guaranteed, such as when destroying the table. + */ +static inline struct rhash_head *rht_ptr_rcu( + struct rhash_lock_head __rcu *const *bkt) +{ + return __rht_ptr(rcu_dereference(*bkt), bkt); +} + +static inline struct rhash_head *rht_ptr( + struct rhash_lock_head __rcu *const *bkt, + struct bucket_table *tbl, + unsigned int hash) +{ + return __rht_ptr(rht_dereference_bucket(*bkt, tbl, hash), bkt); +} + +static inline struct rhash_head *rht_ptr_exclusive( + struct rhash_lock_head __rcu *const *bkt) +{ + return __rht_ptr(rcu_dereference(*bkt), bkt); +} + +static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt, + struct rhash_head *obj) +{ + if (rht_is_a_nulls(obj)) + obj = NULL; + rcu_assign_pointer(*bkt, (void *)((unsigned long)obj | BIT(0))); +} + +static inline void rht_assign_unlock(struct bucket_table *tbl, + struct rhash_lock_head __rcu **bkt, + struct rhash_head *obj) +{ + if (rht_is_a_nulls(obj)) + obj = NULL; + rcu_assign_pointer(*bkt, (void *)obj); + preempt_enable(); + __release(bitlock); +} + +/** + * rht_for_each_from - iterate over hash chain from given head + * @pos: the &struct rhash_head to use as a loop cursor. + * @head: the &struct rhash_head to start from + * @tbl: the &struct bucket_table + * @hash: the hash value / bucket index + */ +#define rht_for_each_from(pos, head, tbl, hash) \ + for (pos = head; \ + !rht_is_a_nulls(pos); \ pos = rht_dereference_bucket((pos)->next, tbl, hash)) +/** + * rht_for_each - iterate over hash chain + * @pos: the &struct rhash_head to use as a loop cursor. + * @tbl: the &struct bucket_table + * @hash: the hash value / bucket index + */ #define rht_for_each(pos, tbl, hash) \ - rht_for_each_continue(pos, (tbl)->buckets[hash], tbl, hash) + rht_for_each_from(pos, rht_ptr(rht_bucket(tbl, hash), tbl, hash), \ + tbl, hash) + +/** + * rht_for_each_entry_from - iterate over hash chain from given head + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct rhash_head to use as a loop cursor. + * @head: the &struct rhash_head to start from + * @tbl: the &struct bucket_table + * @hash: the hash value / bucket index + * @member: name of the &struct rhash_head within the hashable struct. + */ +#define rht_for_each_entry_from(tpos, pos, head, tbl, hash, member) \ + for (pos = head; \ + (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ + pos = rht_dereference_bucket((pos)->next, tbl, hash)) -#define rht_for_each_rcu_continue(pos, head, tbl, hash) \ +/** + * rht_for_each_entry - iterate over hash chain of given type + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct rhash_head to use as a loop cursor. + * @tbl: the &struct bucket_table + * @hash: the hash value / bucket index + * @member: name of the &struct rhash_head within the hashable struct. + */ +#define rht_for_each_entry(tpos, pos, tbl, hash, member) \ + rht_for_each_entry_from(tpos, pos, \ + rht_ptr(rht_bucket(tbl, hash), tbl, hash), \ + tbl, hash, member) + +/** + * rht_for_each_entry_safe - safely iterate over hash chain of given type + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct rhash_head to use as a loop cursor. + * @next: the &struct rhash_head to use as next in loop cursor. + * @tbl: the &struct bucket_table + * @hash: the hash value / bucket index + * @member: name of the &struct rhash_head within the hashable struct. + * + * This hash chain list-traversal primitive allows for the looped code to + * remove the loop cursor from the list. + */ +#define rht_for_each_entry_safe(tpos, pos, next, tbl, hash, member) \ + for (pos = rht_ptr(rht_bucket(tbl, hash), tbl, hash), \ + next = !rht_is_a_nulls(pos) ? \ + rht_dereference_bucket(pos->next, tbl, hash) : NULL; \ + (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ + pos = next, \ + next = !rht_is_a_nulls(pos) ? \ + rht_dereference_bucket(pos->next, tbl, hash) : NULL) + +/** + * rht_for_each_rcu_from - iterate over rcu hash chain from given head + * @pos: the &struct rhash_head to use as a loop cursor. + * @head: the &struct rhash_head to start from + * @tbl: the &struct bucket_table + * @hash: the hash value / bucket index + * + * This hash chain list-traversal primitive may safely run concurrently with + * the _rcu mutation primitives such as rhashtable_insert() as long as the + * traversal is guarded by rcu_read_lock(). + */ +#define rht_for_each_rcu_from(pos, head, tbl, hash) \ for (({barrier(); }), \ - pos = rht_dereference_bucket_rcu(head, tbl, hash); \ + pos = head; \ !rht_is_a_nulls(pos); \ pos = rcu_dereference_raw(pos->next)) -#define rht_for_each_rcu(pos, tbl, hash) \ - rht_for_each_rcu_continue(pos, (tbl)->buckets[hash], tbl, hash) +/** + * rht_for_each_rcu - iterate over rcu hash chain + * @pos: the &struct rhash_head to use as a loop cursor. + * @tbl: the &struct bucket_table + * @hash: the hash value / bucket index + * + * This hash chain list-traversal primitive may safely run concurrently with + * the _rcu mutation primitives such as rhashtable_insert() as long as the + * traversal is guarded by rcu_read_lock(). + */ +#define rht_for_each_rcu(pos, tbl, hash) \ + for (({barrier(); }), \ + pos = rht_ptr_rcu(rht_bucket(tbl, hash)); \ + !rht_is_a_nulls(pos); \ + pos = rcu_dereference_raw(pos->next)) -#define rht_for_each_entry_rcu_continue(tpos, pos, head, tbl, hash, member) \ +/** + * rht_for_each_entry_rcu_from - iterated over rcu hash chain from given head + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct rhash_head to use as a loop cursor. + * @head: the &struct rhash_head to start from + * @tbl: the &struct bucket_table + * @hash: the hash value / bucket index + * @member: name of the &struct rhash_head within the hashable struct. + * + * This hash chain list-traversal primitive may safely run concurrently with + * the _rcu mutation primitives such as rhashtable_insert() as long as the + * traversal is guarded by rcu_read_lock(). + */ +#define rht_for_each_entry_rcu_from(tpos, pos, head, tbl, hash, member) \ for (({barrier(); }), \ - pos = rht_dereference_bucket_rcu(head, tbl, hash); \ + pos = head; \ (!rht_is_a_nulls(pos)) && rht_entry(tpos, pos, member); \ pos = rht_dereference_bucket_rcu(pos->next, tbl, hash)) -#define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member) \ - rht_for_each_entry_rcu_continue(tpos, pos, (tbl)->buckets[hash],\ - tbl, hash, member) +/** + * rht_for_each_entry_rcu - iterate over rcu hash chain of given type + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct rhash_head to use as a loop cursor. + * @tbl: the &struct bucket_table + * @hash: the hash value / bucket index + * @member: name of the &struct rhash_head within the hashable struct. + * + * This hash chain list-traversal primitive may safely run concurrently with + * the _rcu mutation primitives such as rhashtable_insert() as long as the + * traversal is guarded by rcu_read_lock(). + */ +#define rht_for_each_entry_rcu(tpos, pos, tbl, hash, member) \ + rht_for_each_entry_rcu_from(tpos, pos, \ + rht_ptr_rcu(rht_bucket(tbl, hash)), \ + tbl, hash, member) + +/** + * rhl_for_each_rcu - iterate over rcu hash table list + * @pos: the &struct rlist_head to use as a loop cursor. + * @list: the head of the list + * + * This hash chain list-traversal primitive should be used on the + * list returned by rhltable_lookup. + */ +#define rhl_for_each_rcu(pos, list) \ + for (pos = list; pos; pos = rcu_dereference_raw(pos->next)) + +/** + * rhl_for_each_entry_rcu - iterate over rcu hash table list of given type + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct rlist_head to use as a loop cursor. + * @list: the head of the list + * @member: name of the &struct rlist_head within the hashable struct. + * + * This hash chain list-traversal primitive should be used on the + * list returned by rhltable_lookup. + */ +#define rhl_for_each_entry_rcu(tpos, pos, list, member) \ + for (pos = list; pos && rht_entry(tpos, pos, member); \ + pos = rcu_dereference_raw(pos->next)) static inline int rhashtable_compare(struct rhashtable_compare_arg *arg, const void *obj) @@ -254,7 +570,8 @@ static inline int rhashtable_compare(struct rhashtable_compare_arg *arg, return memcmp(ptr + ht->p.key_offset, arg->key, ht->p.key_len); } -static inline void *rhashtable_lookup_fast( +/* Internal function, do not use. */ +static inline struct rhash_head *__rhashtable_lookup( struct rhashtable *ht, const void *key, const struct rhashtable_params params) { @@ -262,23 +579,27 @@ static inline void *rhashtable_lookup_fast( .ht = ht, .key = key, }; - const struct bucket_table *tbl; + struct rhash_lock_head __rcu *const *bkt; + struct bucket_table *tbl; struct rhash_head *he; unsigned int hash; - rcu_read_lock(); - tbl = rht_dereference_rcu(ht->tbl, ht); restart: hash = rht_key_hashfn(ht, tbl, key, params); - rht_for_each_rcu(he, tbl, hash) { - if (params.obj_cmpfn ? - params.obj_cmpfn(&arg, rht_obj(ht, he)) : - rhashtable_compare(&arg, rht_obj(ht, he))) - continue; - rcu_read_unlock(); - return rht_obj(ht, he); - } + bkt = rht_bucket(tbl, hash); + do { + rht_for_each_rcu_from(he, rht_ptr_rcu(bkt), tbl, hash) { + if (params.obj_cmpfn ? + params.obj_cmpfn(&arg, rht_obj(ht, he)) : + rhashtable_compare(&arg, rht_obj(ht, he))) + continue; + return he; + } + /* An object might have been moved to a different hash chain, + * while we walk along it - better check and retry. + */ + } while (he != RHT_NULLS_MARKER(bkt)); /* Ensure we see any new tables. */ smp_rmb(); @@ -286,150 +607,594 @@ restart: tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (unlikely(tbl)) goto restart; - rcu_read_unlock(); return NULL; } -static inline int __rhashtable_insert_fast( - struct rhashtable *ht, const void *key, struct rhash_head *obj, +/** + * rhashtable_lookup - search hash table + * @ht: hash table + * @key: the pointer to the key + * @params: hash table parameters + * + * Computes the hash value for the key and traverses the bucket chain looking + * for a entry with an identical key. The first matching entry is returned. + * + * This must only be called under the RCU read lock. + * + * Returns the first entry on which the compare function returned true. + */ +static inline void *rhashtable_lookup( + struct rhashtable *ht, const void *key, + const struct rhashtable_params params) +{ + struct rhash_head *he = __rhashtable_lookup(ht, key, params); + + return he ? rht_obj(ht, he) : NULL; +} + +/** + * rhashtable_lookup_fast - search hash table, without RCU read lock + * @ht: hash table + * @key: the pointer to the key + * @params: hash table parameters + * + * Computes the hash value for the key and traverses the bucket chain looking + * for a entry with an identical key. The first matching entry is returned. + * + * Only use this function when you have other mechanisms guaranteeing + * that the object won't go away after the RCU read lock is released. + * + * Returns the first entry on which the compare function returned true. + */ +static inline void *rhashtable_lookup_fast( + struct rhashtable *ht, const void *key, + const struct rhashtable_params params) +{ + void *obj; + + rcu_read_lock(); + obj = rhashtable_lookup(ht, key, params); + rcu_read_unlock(); + + return obj; +} + +/** + * rhltable_lookup - search hash list table + * @hlt: hash table + * @key: the pointer to the key + * @params: hash table parameters + * + * Computes the hash value for the key and traverses the bucket chain looking + * for a entry with an identical key. All matching entries are returned + * in a list. + * + * This must only be called under the RCU read lock. + * + * Returns the list of entries that match the given key. + */ +static inline struct rhlist_head *rhltable_lookup( + struct rhltable *hlt, const void *key, const struct rhashtable_params params) { + struct rhash_head *he = __rhashtable_lookup(&hlt->ht, key, params); + + return he ? container_of(he, struct rhlist_head, rhead) : NULL; +} + +/* Internal function, please use rhashtable_insert_fast() instead. This + * function returns the existing element already in hashes in there is a clash, + * otherwise it returns an error via ERR_PTR(). + */ +static inline void *__rhashtable_insert_fast( + struct rhashtable *ht, const void *key, struct rhash_head *obj, + const struct rhashtable_params params, bool rhlist) +{ struct rhashtable_compare_arg arg = { .ht = ht, .key = key, }; - struct bucket_table *tbl, *new_tbl; + struct rhash_lock_head __rcu **bkt; + struct rhash_head __rcu **pprev; + struct bucket_table *tbl; struct rhash_head *head; - spinlock_t *lock; - unsigned int elasticity; unsigned int hash; - int err; + int elasticity; + void *data; -restart: rcu_read_lock(); tbl = rht_dereference_rcu(ht->tbl, ht); + hash = rht_head_hashfn(ht, tbl, obj, params); + elasticity = RHT_ELASTICITY; + bkt = rht_bucket_insert(ht, tbl, hash); + data = ERR_PTR(-ENOMEM); + if (!bkt) + goto out; + pprev = NULL; + rht_lock(tbl, bkt); - /* All insertions must grab the oldest table containing - * the hashed bucket that is yet to be rehashed. - */ - for (;;) { - hash = rht_head_hashfn(ht, tbl, obj, params); - lock = rht_bucket_lock(tbl, hash); - spin_lock_bh(lock); + if (unlikely(rcu_access_pointer(tbl->future_tbl))) { +slow_path: + rht_unlock(tbl, bkt); + rcu_read_unlock(); + return rhashtable_insert_slow(ht, key, obj); + } - if (tbl->rehash <= hash) - break; + rht_for_each_from(head, rht_ptr(bkt, tbl, hash), tbl, hash) { + struct rhlist_head *plist; + struct rhlist_head *list; - spin_unlock_bh(lock); - tbl = rht_dereference_rcu(tbl->future_tbl, ht); - } + elasticity--; + if (!key || + (params.obj_cmpfn ? + params.obj_cmpfn(&arg, rht_obj(ht, head)) : + rhashtable_compare(&arg, rht_obj(ht, head)))) { + pprev = &head->next; + continue; + } - new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); - if (unlikely(new_tbl)) { - tbl = rhashtable_insert_slow(ht, key, obj, new_tbl); - if (!IS_ERR_OR_NULL(tbl)) - goto slow_path; + data = rht_obj(ht, head); - err = PTR_ERR(tbl); - goto out; - } + if (!rhlist) + goto out_unlock; - err = -E2BIG; - if (unlikely(rht_grow_above_max(ht, tbl))) - goto out; - if (unlikely(rht_grow_above_100(ht, tbl))) { -slow_path: - spin_unlock_bh(lock); - err = rhashtable_insert_rehash(ht, tbl); - rcu_read_unlock(); - if (err) - return err; + list = container_of(obj, struct rhlist_head, rhead); + plist = container_of(head, struct rhlist_head, rhead); - goto restart; + RCU_INIT_POINTER(list->next, plist); + head = rht_dereference_bucket(head->next, tbl, hash); + RCU_INIT_POINTER(list->rhead.next, head); + if (pprev) { + rcu_assign_pointer(*pprev, obj); + rht_unlock(tbl, bkt); + } else + rht_assign_unlock(tbl, bkt, obj); + data = NULL; + goto out; } - err = -EEXIST; - elasticity = ht->elasticity; - rht_for_each(head, tbl, hash) { - if (key && - unlikely(!(params.obj_cmpfn ? - params.obj_cmpfn(&arg, rht_obj(ht, head)) : - rhashtable_compare(&arg, rht_obj(ht, head))))) - goto out; - if (!--elasticity) - goto slow_path; - } + if (elasticity <= 0) + goto slow_path; + + data = ERR_PTR(-E2BIG); + if (unlikely(rht_grow_above_max(ht, tbl))) + goto out_unlock; - err = 0; + if (unlikely(rht_grow_above_100(ht, tbl))) + goto slow_path; - head = rht_dereference_bucket(tbl->buckets[hash], tbl, hash); + /* Inserting at head of list makes unlocking free. */ + head = rht_ptr(bkt, tbl, hash); RCU_INIT_POINTER(obj->next, head); + if (rhlist) { + struct rhlist_head *list; - rcu_assign_pointer(tbl->buckets[hash], obj); + list = container_of(obj, struct rhlist_head, rhead); + RCU_INIT_POINTER(list->next, NULL); + } atomic_inc(&ht->nelems); + rht_assign_unlock(tbl, bkt, obj); + if (rht_grow_above_75(ht, tbl)) schedule_work(&ht->run_work); + data = NULL; out: - spin_unlock_bh(lock); rcu_read_unlock(); - return err; + return data; + +out_unlock: + rht_unlock(tbl, bkt); + goto out; } +/** + * rhashtable_insert_fast - insert object into hash table + * @ht: hash table + * @obj: pointer to hash head inside object + * @params: hash table parameters + * + * Will take the per bucket bitlock to protect against mutual mutations + * on the same bucket. Multiple insertions may occur in parallel unless + * they map to the same bucket. + * + * It is safe to call this function from atomic context. + * + * Will trigger an automatic deferred table resizing if residency in the + * table grows beyond 70%. + */ +static inline int rhashtable_insert_fast( + struct rhashtable *ht, struct rhash_head *obj, + const struct rhashtable_params params) +{ + void *ret; + + ret = __rhashtable_insert_fast(ht, NULL, obj, params, false); + if (IS_ERR(ret)) + return PTR_ERR(ret); + + return ret == NULL ? 0 : -EEXIST; +} + +/** + * rhltable_insert_key - insert object into hash list table + * @hlt: hash list table + * @key: the pointer to the key + * @list: pointer to hash list head inside object + * @params: hash table parameters + * + * Will take the per bucket bitlock to protect against mutual mutations + * on the same bucket. Multiple insertions may occur in parallel unless + * they map to the same bucket. + * + * It is safe to call this function from atomic context. + * + * Will trigger an automatic deferred table resizing if residency in the + * table grows beyond 70%. + */ +static inline int rhltable_insert_key( + struct rhltable *hlt, const void *key, struct rhlist_head *list, + const struct rhashtable_params params) +{ + return PTR_ERR(__rhashtable_insert_fast(&hlt->ht, key, &list->rhead, + params, true)); +} + +/** + * rhltable_insert - insert object into hash list table + * @hlt: hash list table + * @list: pointer to hash list head inside object + * @params: hash table parameters + * + * Will take the per bucket bitlock to protect against mutual mutations + * on the same bucket. Multiple insertions may occur in parallel unless + * they map to the same bucket. + * + * It is safe to call this function from atomic context. + * + * Will trigger an automatic deferred table resizing if residency in the + * table grows beyond 70%. + */ +static inline int rhltable_insert( + struct rhltable *hlt, struct rhlist_head *list, + const struct rhashtable_params params) +{ + const char *key = rht_obj(&hlt->ht, &list->rhead); + + key += params.key_offset; + + return rhltable_insert_key(hlt, key, list, params); +} + +/** + * rhashtable_lookup_insert_fast - lookup and insert object into hash table + * @ht: hash table + * @obj: pointer to hash head inside object + * @params: hash table parameters + * + * This lookup function may only be used for fixed key hash table (key_len + * parameter set). It will BUG() if used inappropriately. + * + * It is safe to call this function from atomic context. + * + * Will trigger an automatic deferred table resizing if residency in the + * table grows beyond 70%. + */ static inline int rhashtable_lookup_insert_fast( struct rhashtable *ht, struct rhash_head *obj, const struct rhashtable_params params) { const char *key = rht_obj(ht, obj); + void *ret; BUG_ON(ht->p.obj_hashfn); - return __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, - params); + ret = __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params, + false); + if (IS_ERR(ret)) + return PTR_ERR(ret); + + return ret == NULL ? 0 : -EEXIST; } -static inline int __rhashtable_remove_fast( +/** + * rhashtable_lookup_get_insert_fast - lookup and insert object into hash table + * @ht: hash table + * @obj: pointer to hash head inside object + * @params: hash table parameters + * + * Just like rhashtable_lookup_insert_fast(), but this function returns the + * object if it exists, NULL if it did not and the insertion was successful, + * and an ERR_PTR otherwise. + */ +static inline void *rhashtable_lookup_get_insert_fast( + struct rhashtable *ht, struct rhash_head *obj, + const struct rhashtable_params params) +{ + const char *key = rht_obj(ht, obj); + + BUG_ON(ht->p.obj_hashfn); + + return __rhashtable_insert_fast(ht, key + ht->p.key_offset, obj, params, + false); +} + +/** + * rhashtable_lookup_insert_key - search and insert object to hash table + * with explicit key + * @ht: hash table + * @key: key + * @obj: pointer to hash head inside object + * @params: hash table parameters + * + * Lookups may occur in parallel with hashtable mutations and resizing. + * + * Will trigger an automatic deferred table resizing if residency in the + * table grows beyond 70%. + * + * Returns zero on success. + */ +static inline int rhashtable_lookup_insert_key( + struct rhashtable *ht, const void *key, struct rhash_head *obj, + const struct rhashtable_params params) +{ + void *ret; + + BUG_ON(!ht->p.obj_hashfn || !key); + + ret = __rhashtable_insert_fast(ht, key, obj, params, false); + if (IS_ERR(ret)) + return PTR_ERR(ret); + + return ret == NULL ? 0 : -EEXIST; +} + +/** + * rhashtable_lookup_get_insert_key - lookup and insert object into hash table + * @ht: hash table + * @key: key + * @obj: pointer to hash head inside object + * @params: hash table parameters + * + * Just like rhashtable_lookup_insert_key(), but this function returns the + * object if it exists, NULL if it does not and the insertion was successful, + * and an ERR_PTR otherwise. + */ +static inline void *rhashtable_lookup_get_insert_key( + struct rhashtable *ht, const void *key, struct rhash_head *obj, + const struct rhashtable_params params) +{ + BUG_ON(!ht->p.obj_hashfn || !key); + + return __rhashtable_insert_fast(ht, key, obj, params, false); +} + +/* Internal function, please use rhashtable_remove_fast() instead */ +static inline int __rhashtable_remove_fast_one( struct rhashtable *ht, struct bucket_table *tbl, - struct rhash_head *obj, const struct rhashtable_params params) + struct rhash_head *obj, const struct rhashtable_params params, + bool rhlist) { + struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; - spinlock_t * lock; unsigned int hash; int err = -ENOENT; hash = rht_head_hashfn(ht, tbl, obj, params); - lock = rht_bucket_lock(tbl, hash); + bkt = rht_bucket_var(tbl, hash); + if (!bkt) + return -ENOENT; + pprev = NULL; + rht_lock(tbl, bkt); - spin_lock_bh(lock); + rht_for_each_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) { + struct rhlist_head *list; + + list = container_of(he, struct rhlist_head, rhead); - pprev = &tbl->buckets[hash]; - rht_for_each(he, tbl, hash) { if (he != obj) { + struct rhlist_head __rcu **lpprev; + pprev = &he->next; - continue; + + if (!rhlist) + continue; + + do { + lpprev = &list->next; + list = rht_dereference_bucket(list->next, + tbl, hash); + } while (list && obj != &list->rhead); + + if (!list) + continue; + + list = rht_dereference_bucket(list->next, tbl, hash); + RCU_INIT_POINTER(*lpprev, list); + err = 0; + break; } - rcu_assign_pointer(*pprev, obj->next); + obj = rht_dereference_bucket(obj->next, tbl, hash); + err = 1; + + if (rhlist) { + list = rht_dereference_bucket(list->next, tbl, hash); + if (list) { + RCU_INIT_POINTER(list->rhead.next, obj); + obj = &list->rhead; + err = 0; + } + } + + if (pprev) { + rcu_assign_pointer(*pprev, obj); + rht_unlock(tbl, bkt); + } else { + rht_assign_unlock(tbl, bkt, obj); + } + goto unlocked; + } + + rht_unlock(tbl, bkt); +unlocked: + if (err > 0) { + atomic_dec(&ht->nelems); + if (unlikely(ht->p.automatic_shrinking && + rht_shrink_below_30(ht, tbl))) + schedule_work(&ht->run_work); err = 0; - break; } - spin_unlock_bh(lock); + return err; +} + +/* Internal function, please use rhashtable_remove_fast() instead */ +static inline int __rhashtable_remove_fast( + struct rhashtable *ht, struct rhash_head *obj, + const struct rhashtable_params params, bool rhlist) +{ + struct bucket_table *tbl; + int err; + + rcu_read_lock(); + + tbl = rht_dereference_rcu(ht->tbl, ht); + + /* Because we have already taken (and released) the bucket + * lock in old_tbl, if we find that future_tbl is not yet + * visible then that guarantees the entry to still be in + * the old tbl if it exists. + */ + while ((err = __rhashtable_remove_fast_one(ht, tbl, obj, params, + rhlist)) && + (tbl = rht_dereference_rcu(tbl->future_tbl, ht))) + ; + + rcu_read_unlock(); return err; } +/** + * rhashtable_remove_fast - remove object from hash table + * @ht: hash table + * @obj: pointer to hash head inside object + * @params: hash table parameters + * + * Since the hash chain is single linked, the removal operation needs to + * walk the bucket chain upon removal. The removal operation is thus + * considerable slow if the hash table is not correctly sized. + * + * Will automatically shrink the table if permitted when residency drops + * below 30%. + * + * Returns zero on success, -ENOENT if the entry could not be found. + */ static inline int rhashtable_remove_fast( struct rhashtable *ht, struct rhash_head *obj, const struct rhashtable_params params) { + return __rhashtable_remove_fast(ht, obj, params, false); +} + +/** + * rhltable_remove - remove object from hash list table + * @hlt: hash list table + * @list: pointer to hash list head inside object + * @params: hash table parameters + * + * Since the hash chain is single linked, the removal operation needs to + * walk the bucket chain upon removal. The removal operation is thus + * considerable slow if the hash table is not correctly sized. + * + * Will automatically shrink the table if permitted when residency drops + * below 30% + * + * Returns zero on success, -ENOENT if the entry could not be found. + */ +static inline int rhltable_remove( + struct rhltable *hlt, struct rhlist_head *list, + const struct rhashtable_params params) +{ + return __rhashtable_remove_fast(&hlt->ht, &list->rhead, params, true); +} + +/* Internal function, please use rhashtable_replace_fast() instead */ +static inline int __rhashtable_replace_fast( + struct rhashtable *ht, struct bucket_table *tbl, + struct rhash_head *obj_old, struct rhash_head *obj_new, + const struct rhashtable_params params) +{ + struct rhash_lock_head __rcu **bkt; + struct rhash_head __rcu **pprev; + struct rhash_head *he; + unsigned int hash; + int err = -ENOENT; + + /* Minimally, the old and new objects must have same hash + * (which should mean identifiers are the same). + */ + hash = rht_head_hashfn(ht, tbl, obj_old, params); + if (hash != rht_head_hashfn(ht, tbl, obj_new, params)) + return -EINVAL; + + bkt = rht_bucket_var(tbl, hash); + if (!bkt) + return -ENOENT; + + pprev = NULL; + rht_lock(tbl, bkt); + + rht_for_each_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) { + if (he != obj_old) { + pprev = &he->next; + continue; + } + + rcu_assign_pointer(obj_new->next, obj_old->next); + if (pprev) { + rcu_assign_pointer(*pprev, obj_new); + rht_unlock(tbl, bkt); + } else { + rht_assign_unlock(tbl, bkt, obj_new); + } + err = 0; + goto unlocked; + } + + rht_unlock(tbl, bkt); + +unlocked: + return err; +} + +/** + * rhashtable_replace_fast - replace an object in hash table + * @ht: hash table + * @obj_old: pointer to hash head inside object being replaced + * @obj_new: pointer to hash head inside object which is new + * @params: hash table parameters + * + * Replacing an object doesn't affect the number of elements in the hash table + * or bucket, so we don't need to worry about shrinking or expanding the + * table here. + * + * Returns zero on success, -ENOENT if the entry could not be found, + * -EINVAL if hash is not the same for the old and new objects. + */ +static inline int rhashtable_replace_fast( + struct rhashtable *ht, struct rhash_head *obj_old, + struct rhash_head *obj_new, + const struct rhashtable_params params) +{ struct bucket_table *tbl; int err; @@ -442,22 +1207,62 @@ static inline int rhashtable_remove_fast( * visible then that guarantees the entry to still be in * the old tbl if it exists. */ - while ((err = __rhashtable_remove_fast(ht, tbl, obj, params)) && + while ((err = __rhashtable_replace_fast(ht, tbl, obj_old, + obj_new, params)) && (tbl = rht_dereference_rcu(tbl->future_tbl, ht))) ; - if (err) - goto out; - - atomic_dec(&ht->nelems); - if (unlikely(ht->p.automatic_shrinking && - rht_shrink_below_30(ht, tbl))) - schedule_work(&ht->run_work); - -out: rcu_read_unlock(); return err; } +/** + * rhltable_walk_enter - Initialise an iterator + * @hlt: Table to walk over + * @iter: Hash table Iterator + * + * This function prepares a hash table walk. + * + * Note that if you restart a walk after rhashtable_walk_stop you + * may see the same object twice. Also, you may miss objects if + * there are removals in between rhashtable_walk_stop and the next + * call to rhashtable_walk_start. + * + * For a completely stable walk you should construct your own data + * structure outside the hash table. + * + * This function may be called from any process context, including + * non-preemptable context, but cannot be called from softirq or + * hardirq context. + * + * You must call rhashtable_walk_exit after this function returns. + */ +static inline void rhltable_walk_enter(struct rhltable *hlt, + struct rhashtable_iter *iter) +{ + return rhashtable_walk_enter(&hlt->ht, iter); +} + +/** + * rhltable_free_and_destroy - free elements and destroy hash list table + * @hlt: the hash list table to destroy + * @free_fn: callback to release resources of element + * @arg: pointer passed to free_fn + * + * See documentation for rhashtable_free_and_destroy. + */ +static inline void rhltable_free_and_destroy(struct rhltable *hlt, + void (*free_fn)(void *ptr, + void *arg), + void *arg) +{ + return rhashtable_free_and_destroy(&hlt->ht, free_fn, arg); +} + +static inline void rhltable_destroy(struct rhltable *hlt) +{ + return rhltable_free_and_destroy(hlt, NULL, NULL); +} + #endif /* _LINUX_RHASHTABLE_H */ diff --git a/include/linux/six.h b/include/linux/six.h index 0e6df059..477c33eb 100644 --- a/include/linux/six.h +++ b/include/linux/six.h @@ -196,6 +196,7 @@ void six_lock_increment(struct six_lock *, enum six_lock_type); void six_lock_wakeup_all(struct six_lock *); +void six_lock_pcpu_free_rcu(struct six_lock *); void six_lock_pcpu_free(struct six_lock *); void six_lock_pcpu_alloc(struct six_lock *); diff --git a/include/linux/slab.h b/include/linux/slab.h index b8a1235b..775b7e3a 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -66,6 +66,7 @@ static inline void *krealloc(void *old, size_t size, gfp_t flags) #define kzfree(p) free(p) #define kvmalloc(size, flags) kmalloc(size, flags) +#define kvzalloc(size, flags) kzalloc(size, flags) #define kvfree(p) kfree(p) static inline struct page *alloc_pages(gfp_t flags, unsigned int order) diff --git a/include/linux/types.h b/include/linux/types.h index 1e125550..c9886cba 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -11,6 +11,8 @@ #define __SANE_USERSPACE_TYPES__ /* For PPC64, to get LL64 types */ #include <asm/types.h> +#include <linux/cache.h> + #define BITS_PER_LONG __BITS_PER_LONG struct page; |