Changes in 4.9.238 af_key: pfkey_dump needs parameter validation KVM: fix memory leak in kvm_io_bus_unregister_dev() kprobes: fix kill kprobe which has been marked as gone RDMA/ucma: ucma_context reference leak in error path mtd: Fix comparison in map_word_andequal() hdlc_ppp: add range checks in ppp_cp_parse_cr() ip: fix tos reflection in ack and reset packets tipc: use skb_unshare() instead in tipc_buf_append() bnxt_en: Protect bnxt_set_eee() and bnxt_set_pauseparam() with mutex. net: phy: Avoid NPD upon phy_detach() when driver is unbound net/hsr: Check skb_put_padto() return value net: add __must_check to skb_put_padto() serial: 8250: Avoid error message on reprobe scsi: aacraid: fix illegal IO beyond last LBA m68k: q40: Fix info-leak in rtc_ioctl gma/gma500: fix a memory disclosure bug due to uninitialized bytes ASoC: kirkwood: fix IRQ error handling ALSA: usb-audio: Add delay quirk for H570e USB headsets PM / devfreq: tegra30: Fix integer overflow on CPU's freq max out clk/ti/adpll: allocate room for terminating null mtd: cfi_cmdset_0002: don't free cfi->cfiq in error path of cfi_amdstd_setup() mfd: mfd-core: Protect against NULL call-back function pointer tracing: Adding NULL checks for trace_array descriptor pointer bcache: fix a lost wake-up problem caused by mca_cannibalize_lock RDMA/i40iw: Fix potential use after free xfs: fix attr leaf header freemap.size underflow RDMA/iw_cgxb4: Fix an error handling path in 'c4iw_connect()' debugfs: Fix !DEBUG_FS debugfs_create_automount CIFS: Properly process SMB3 lease breaks kernel/sys.c: avoid copying possible padding bytes in copy_to_user neigh_stat_seq_next() should increase position index rt_cpu_seq_next should increase position index seqlock: Require WRITE_ONCE surrounding raw_seqcount_barrier media: ti-vpe: cal: Restrict DMA to avoid memory corruption ACPI: EC: Reference count query handlers under lock dmaengine: zynqmp_dma: fix burst length configuration tracing: Set kernel_stack's caller size properly ar5523: Add USB ID of SMCWUSBT-G2 wireless adapter Bluetooth: Fix refcount use-after-free issue mm: pagewalk: fix termination condition in walk_pte_range() Bluetooth: prefetch channel before killing sock KVM: fix overflow of zero page refcount with ksm running ALSA: hda: Clear RIRB status before reading WP skbuff: fix a data race in skb_queue_len() audit: CONFIG_CHANGE don't log internal bookkeeping as an event selinux: sel_avc_get_stat_idx should increase position index scsi: lpfc: Fix RQ buffer leakage when no IOCBs available scsi: lpfc: Fix coverity errors in fmdi attribute handling drm/omap: fix possible object reference leak RDMA/rxe: Fix configuration of atomic queue pair attributes KVM: x86: fix incorrect comparison in trace event x86/pkeys: Add check for pkey "overflow" bpf: Remove recursion prevention from rcu free callback dmaengine: tegra-apb: Prevent race conditions on channel's freeing media: go7007: Fix URB type for interrupt handling Bluetooth: guard against controllers sending zero'd events timekeeping: Prevent 32bit truncation in scale64_check_overflow() drm/amdgpu: increase atombios cmd timeout Bluetooth: L2CAP: handle l2cap config request during open state media: tda10071: fix unsigned sign extension overflow xfs: don't ever return a stale pointer from __xfs_dir3_free_read tpm: ibmvtpm: Wait for buffer to be set before proceeding tracing: Use address-of operator on section symbols serial: 8250_port: Don't service RX FIFO if throttled serial: 8250_omap: Fix sleeping function called from invalid context during probe serial: 8250: 8250_omap: Terminate DMA before pushing data on RX timeout cpufreq: powernv: Fix frame-size-overflow in powernv_cpufreq_work_fn tools: gpio-hammer: Avoid potential overflow in main SUNRPC: Fix a potential buffer overflow in 'svc_print_xprts()' svcrdma: Fix leak of transport addresses ubifs: Fix out-of-bounds memory access caused by abnormal value of node_len ALSA: usb-audio: Fix case when USB MIDI interface has more than one extra endpoint descriptor mm/filemap.c: clear page error before actual read mm/mmap.c: initialize align_offset explicitly for vm_unmapped_area KVM: Remove CREATE_IRQCHIP/SET_PIT2 race bdev: Reduce time holding bd_mutex in sync in blkdev_close() drivers: char: tlclk.c: Avoid data race between init and interrupt handler dt-bindings: sound: wm8994: Correct required supplies based on actual implementaion atm: fix a memory leak of vcc->user_back phy: samsung: s5pv210-usb2: Add delay after reset Bluetooth: Handle Inquiry Cancel error after Inquiry Complete USB: EHCI: ehci-mv: fix error handling in mv_ehci_probe() tty: serial: samsung: Correct clock selection logic ALSA: hda: Fix potential race in unsol event handler fuse: don't check refcount after stealing page USB: EHCI: ehci-mv: fix less than zero comparison of an unsigned int e1000: Do not perform reset in reset_task if we are already down printk: handle blank console arguments passed in. btrfs: don't force read-only after error in drop snapshot vfio/pci: fix memory leaks of eventfd ctx perf util: Fix memory leak of prefix_if_not_in perf kcore_copy: Fix module map when there are no modules loaded mtd: rawnand: omap_elm: Fix runtime PM imbalance on error ceph: fix potential race in ceph_check_caps mtd: parser: cmdline: Support MTD names containing one or more colons x86/speculation/mds: Mark mds_user_clear_cpu_buffers() __always_inline vfio/pci: Clear error and request eventfd ctx after releasing cifs: Fix double add page to memcg when cifs_readpages selftests/x86/syscall_nt: Clear weird flags after each test vfio/pci: fix racy on error and request eventfd ctx s390/init: add missing __init annotations i2c: core: Call i2c_acpi_install_space_handler() before i2c_acpi_register_devices() objtool: Fix noreturn detection for ignored functions ieee802154/adf7242: check status of adf7242_read_reg clocksource/drivers/h8300_timer8: Fix wrong return value in h8300_8timer_init() mwifiex: Increase AES key storage size to 256 bits batman-adv: bla: fix type misuse for backbone_gw hash indexing atm: eni: fix the missed pci_disable_device() for eni_init_one() batman-adv: mcast/TT: fix wrongly dropped or rerouted packets mac802154: tx: fix use-after-free batman-adv: Add missing include for in_interrupt() batman-adv: mcast: fix duplicate mcast packets in BLA backbone from mesh ALSA: asihpi: fix iounmap in error handler MIPS: Add the missing 'CPU_1074K' into __get_cpu_type() kprobes: Fix to check probe enabled before disarm_kprobe_ftrace() lib/string.c: implement stpcpy ata: define AC_ERR_OK ata: make qc_prep return ata_completion_errors ata: sata_mv, avoid trigerrable BUG_ON Linux 4.9.238 Signed-off-by: Greg Kroah-Hartman <gregkh@google.com> Change-Id: I799877db3bc49e473bbc023ab948cd241755beff
841 lines
20 KiB
C
841 lines
20 KiB
C
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
|
|
* Copyright (c) 2016 Facebook
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of version 2 of the GNU General Public
|
|
* License as published by the Free Software Foundation.
|
|
*
|
|
* 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.
|
|
*/
|
|
#include <linux/bpf.h>
|
|
#include <linux/jhash.h>
|
|
#include <linux/filter.h>
|
|
#include <linux/rculist_nulls.h>
|
|
#include "percpu_freelist.h"
|
|
#define HTAB_CREATE_FLAG_MASK \
|
|
(BPF_F_NO_PREALLOC | BPF_F_RDONLY | BPF_F_WRONLY)
|
|
|
|
struct bucket {
|
|
struct hlist_nulls_head head;
|
|
raw_spinlock_t lock;
|
|
};
|
|
|
|
struct bpf_htab {
|
|
struct bpf_map map;
|
|
struct bucket *buckets;
|
|
void *elems;
|
|
struct pcpu_freelist freelist;
|
|
void __percpu *extra_elems;
|
|
atomic_t count; /* number of elements in this hashtable */
|
|
u32 n_buckets; /* number of hash buckets */
|
|
u32 elem_size; /* size of each element in bytes */
|
|
};
|
|
|
|
enum extra_elem_state {
|
|
HTAB_NOT_AN_EXTRA_ELEM = 0,
|
|
HTAB_EXTRA_ELEM_FREE,
|
|
HTAB_EXTRA_ELEM_USED
|
|
};
|
|
|
|
/* each htab element is struct htab_elem + key + value */
|
|
struct htab_elem {
|
|
union {
|
|
struct hlist_nulls_node hash_node;
|
|
struct {
|
|
void *padding;
|
|
union {
|
|
struct bpf_htab *htab;
|
|
struct pcpu_freelist_node fnode;
|
|
};
|
|
};
|
|
};
|
|
union {
|
|
struct rcu_head rcu;
|
|
enum extra_elem_state state;
|
|
};
|
|
u32 hash;
|
|
char key[0] __aligned(8);
|
|
};
|
|
|
|
static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size,
|
|
void __percpu *pptr)
|
|
{
|
|
*(void __percpu **)(l->key + key_size) = pptr;
|
|
}
|
|
|
|
static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size)
|
|
{
|
|
return *(void __percpu **)(l->key + key_size);
|
|
}
|
|
|
|
static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i)
|
|
{
|
|
return (struct htab_elem *) (htab->elems + i * htab->elem_size);
|
|
}
|
|
|
|
static void htab_free_elems(struct bpf_htab *htab)
|
|
{
|
|
int i;
|
|
|
|
if (htab->map.map_type != BPF_MAP_TYPE_PERCPU_HASH)
|
|
goto free_elems;
|
|
|
|
for (i = 0; i < htab->map.max_entries; i++) {
|
|
void __percpu *pptr;
|
|
|
|
pptr = htab_elem_get_ptr(get_htab_elem(htab, i),
|
|
htab->map.key_size);
|
|
free_percpu(pptr);
|
|
}
|
|
free_elems:
|
|
bpf_map_area_free(htab->elems);
|
|
}
|
|
|
|
static int prealloc_elems_and_freelist(struct bpf_htab *htab)
|
|
{
|
|
int err = -ENOMEM, i;
|
|
|
|
htab->elems = bpf_map_area_alloc(htab->elem_size *
|
|
htab->map.max_entries);
|
|
if (!htab->elems)
|
|
return -ENOMEM;
|
|
|
|
if (htab->map.map_type != BPF_MAP_TYPE_PERCPU_HASH)
|
|
goto skip_percpu_elems;
|
|
|
|
for (i = 0; i < htab->map.max_entries; i++) {
|
|
u32 size = round_up(htab->map.value_size, 8);
|
|
void __percpu *pptr;
|
|
|
|
pptr = __alloc_percpu_gfp(size, 8, GFP_USER | __GFP_NOWARN);
|
|
if (!pptr)
|
|
goto free_elems;
|
|
htab_elem_set_ptr(get_htab_elem(htab, i), htab->map.key_size,
|
|
pptr);
|
|
}
|
|
|
|
skip_percpu_elems:
|
|
err = pcpu_freelist_init(&htab->freelist);
|
|
if (err)
|
|
goto free_elems;
|
|
|
|
pcpu_freelist_populate(&htab->freelist,
|
|
htab->elems + offsetof(struct htab_elem, fnode),
|
|
htab->elem_size, htab->map.max_entries);
|
|
|
|
return 0;
|
|
|
|
free_elems:
|
|
htab_free_elems(htab);
|
|
return err;
|
|
}
|
|
|
|
static int alloc_extra_elems(struct bpf_htab *htab)
|
|
{
|
|
void __percpu *pptr;
|
|
int cpu;
|
|
|
|
pptr = __alloc_percpu_gfp(htab->elem_size, 8, GFP_USER | __GFP_NOWARN);
|
|
if (!pptr)
|
|
return -ENOMEM;
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
((struct htab_elem *)per_cpu_ptr(pptr, cpu))->state =
|
|
HTAB_EXTRA_ELEM_FREE;
|
|
}
|
|
htab->extra_elems = pptr;
|
|
return 0;
|
|
}
|
|
|
|
/* Called from syscall */
|
|
static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
|
|
{
|
|
bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_HASH;
|
|
struct bpf_htab *htab;
|
|
int err, i;
|
|
u64 cost;
|
|
|
|
BUILD_BUG_ON(offsetof(struct htab_elem, htab) !=
|
|
offsetof(struct htab_elem, hash_node.pprev));
|
|
BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) !=
|
|
offsetof(struct htab_elem, hash_node.pprev));
|
|
|
|
if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK)
|
|
/* reserved bits should not be used */
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
htab = kzalloc(sizeof(*htab), GFP_USER);
|
|
if (!htab)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
/* mandatory map attributes */
|
|
htab->map.map_type = attr->map_type;
|
|
htab->map.key_size = attr->key_size;
|
|
htab->map.value_size = attr->value_size;
|
|
htab->map.max_entries = attr->max_entries;
|
|
htab->map.map_flags = attr->map_flags;
|
|
|
|
/* check sanity of attributes.
|
|
* value_size == 0 may be allowed in the future to use map as a set
|
|
*/
|
|
err = -EINVAL;
|
|
if (htab->map.max_entries == 0 || htab->map.key_size == 0 ||
|
|
htab->map.value_size == 0)
|
|
goto free_htab;
|
|
|
|
/* hash table size must be power of 2 */
|
|
htab->n_buckets = roundup_pow_of_two(htab->map.max_entries);
|
|
|
|
err = -E2BIG;
|
|
if (htab->map.key_size > MAX_BPF_STACK)
|
|
/* eBPF programs initialize keys on stack, so they cannot be
|
|
* larger than max stack size
|
|
*/
|
|
goto free_htab;
|
|
|
|
if (htab->map.value_size >= (1 << (KMALLOC_SHIFT_MAX - 1)) -
|
|
MAX_BPF_STACK - sizeof(struct htab_elem))
|
|
/* if value_size is bigger, the user space won't be able to
|
|
* access the elements via bpf syscall. This check also makes
|
|
* sure that the elem_size doesn't overflow and it's
|
|
* kmalloc-able later in htab_map_update_elem()
|
|
*/
|
|
goto free_htab;
|
|
|
|
if (percpu && round_up(htab->map.value_size, 8) > PCPU_MIN_UNIT_SIZE)
|
|
/* make sure the size for pcpu_alloc() is reasonable */
|
|
goto free_htab;
|
|
|
|
htab->elem_size = sizeof(struct htab_elem) +
|
|
round_up(htab->map.key_size, 8);
|
|
if (percpu)
|
|
htab->elem_size += sizeof(void *);
|
|
else
|
|
htab->elem_size += round_up(htab->map.value_size, 8);
|
|
|
|
/* prevent zero size kmalloc and check for u32 overflow */
|
|
if (htab->n_buckets == 0 ||
|
|
htab->n_buckets > U32_MAX / sizeof(struct bucket))
|
|
goto free_htab;
|
|
|
|
cost = (u64) htab->n_buckets * sizeof(struct bucket) +
|
|
(u64) htab->elem_size * htab->map.max_entries;
|
|
|
|
if (percpu)
|
|
cost += (u64) round_up(htab->map.value_size, 8) *
|
|
num_possible_cpus() * htab->map.max_entries;
|
|
else
|
|
cost += (u64) htab->elem_size * num_possible_cpus();
|
|
|
|
if (cost >= U32_MAX - PAGE_SIZE)
|
|
/* make sure page count doesn't overflow */
|
|
goto free_htab;
|
|
|
|
htab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
|
|
|
|
/* if map size is larger than memlock limit, reject it early */
|
|
err = bpf_map_precharge_memlock(htab->map.pages);
|
|
if (err)
|
|
goto free_htab;
|
|
|
|
err = -ENOMEM;
|
|
htab->buckets = bpf_map_area_alloc(htab->n_buckets *
|
|
sizeof(struct bucket));
|
|
if (!htab->buckets)
|
|
goto free_htab;
|
|
|
|
for (i = 0; i < htab->n_buckets; i++) {
|
|
INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
|
|
raw_spin_lock_init(&htab->buckets[i].lock);
|
|
}
|
|
|
|
if (!percpu) {
|
|
err = alloc_extra_elems(htab);
|
|
if (err)
|
|
goto free_buckets;
|
|
}
|
|
|
|
if (!(attr->map_flags & BPF_F_NO_PREALLOC)) {
|
|
err = prealloc_elems_and_freelist(htab);
|
|
if (err)
|
|
goto free_extra_elems;
|
|
}
|
|
|
|
return &htab->map;
|
|
|
|
free_extra_elems:
|
|
free_percpu(htab->extra_elems);
|
|
free_buckets:
|
|
bpf_map_area_free(htab->buckets);
|
|
free_htab:
|
|
kfree(htab);
|
|
return ERR_PTR(err);
|
|
}
|
|
|
|
static inline u32 htab_map_hash(const void *key, u32 key_len)
|
|
{
|
|
return jhash(key, key_len, 0);
|
|
}
|
|
|
|
static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
|
|
{
|
|
return &htab->buckets[hash & (htab->n_buckets - 1)];
|
|
}
|
|
|
|
static inline struct hlist_nulls_head *select_bucket(struct bpf_htab *htab, u32 hash)
|
|
{
|
|
return &__select_bucket(htab, hash)->head;
|
|
}
|
|
|
|
/* this lookup function can only be called with bucket lock taken */
|
|
static struct htab_elem *lookup_elem_raw(struct hlist_nulls_head *head, u32 hash,
|
|
void *key, u32 key_size)
|
|
{
|
|
struct hlist_nulls_node *n;
|
|
struct htab_elem *l;
|
|
|
|
hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
|
|
if (l->hash == hash && !memcmp(&l->key, key, key_size))
|
|
return l;
|
|
|
|
return NULL;
|
|
}
|
|
|
|
/* can be called without bucket lock. it will repeat the loop in
|
|
* the unlikely event when elements moved from one bucket into another
|
|
* while link list is being walked
|
|
*/
|
|
static struct htab_elem *lookup_nulls_elem_raw(struct hlist_nulls_head *head,
|
|
u32 hash, void *key,
|
|
u32 key_size, u32 n_buckets)
|
|
{
|
|
struct hlist_nulls_node *n;
|
|
struct htab_elem *l;
|
|
|
|
again:
|
|
hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
|
|
if (l->hash == hash && !memcmp(&l->key, key, key_size))
|
|
return l;
|
|
|
|
if (unlikely(get_nulls_value(n) != (hash & (n_buckets - 1))))
|
|
goto again;
|
|
|
|
return NULL;
|
|
}
|
|
|
|
/* Called from syscall or from eBPF program */
|
|
static void *__htab_map_lookup_elem(struct bpf_map *map, void *key)
|
|
{
|
|
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
|
|
struct hlist_nulls_head *head;
|
|
struct htab_elem *l;
|
|
u32 hash, key_size;
|
|
|
|
/* Must be called with rcu_read_lock. */
|
|
WARN_ON_ONCE(!rcu_read_lock_held());
|
|
|
|
key_size = map->key_size;
|
|
|
|
hash = htab_map_hash(key, key_size);
|
|
|
|
head = select_bucket(htab, hash);
|
|
|
|
l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets);
|
|
|
|
return l;
|
|
}
|
|
|
|
static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
|
|
{
|
|
struct htab_elem *l = __htab_map_lookup_elem(map, key);
|
|
|
|
if (l)
|
|
return l->key + round_up(map->key_size, 8);
|
|
|
|
return NULL;
|
|
}
|
|
|
|
/* Called from syscall */
|
|
static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
|
|
{
|
|
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
|
|
struct hlist_nulls_head *head;
|
|
struct htab_elem *l, *next_l;
|
|
u32 hash, key_size;
|
|
int i = 0;
|
|
|
|
WARN_ON_ONCE(!rcu_read_lock_held());
|
|
|
|
key_size = map->key_size;
|
|
|
|
if (!key)
|
|
goto find_first_elem;
|
|
|
|
hash = htab_map_hash(key, key_size);
|
|
|
|
head = select_bucket(htab, hash);
|
|
|
|
/* lookup the key */
|
|
l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets);
|
|
|
|
if (!l)
|
|
goto find_first_elem;
|
|
|
|
/* key was found, get next key in the same bucket */
|
|
next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_next_rcu(&l->hash_node)),
|
|
struct htab_elem, hash_node);
|
|
|
|
if (next_l) {
|
|
/* if next elem in this hash list is non-zero, just return it */
|
|
memcpy(next_key, next_l->key, key_size);
|
|
return 0;
|
|
}
|
|
|
|
/* no more elements in this hash list, go to the next bucket */
|
|
i = hash & (htab->n_buckets - 1);
|
|
i++;
|
|
|
|
find_first_elem:
|
|
/* iterate over buckets */
|
|
for (; i < htab->n_buckets; i++) {
|
|
head = select_bucket(htab, i);
|
|
|
|
/* pick first element in the bucket */
|
|
next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_first_rcu(head)),
|
|
struct htab_elem, hash_node);
|
|
if (next_l) {
|
|
/* if it's not empty, just return it */
|
|
memcpy(next_key, next_l->key, key_size);
|
|
return 0;
|
|
}
|
|
}
|
|
|
|
/* iterated over all buckets and all elements */
|
|
return -ENOENT;
|
|
}
|
|
|
|
static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l)
|
|
{
|
|
if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH)
|
|
free_percpu(htab_elem_get_ptr(l, htab->map.key_size));
|
|
kfree(l);
|
|
}
|
|
|
|
static void htab_elem_free_rcu(struct rcu_head *head)
|
|
{
|
|
struct htab_elem *l = container_of(head, struct htab_elem, rcu);
|
|
struct bpf_htab *htab = l->htab;
|
|
|
|
htab_elem_free(htab, l);
|
|
}
|
|
|
|
static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
|
|
{
|
|
if (l->state == HTAB_EXTRA_ELEM_USED) {
|
|
l->state = HTAB_EXTRA_ELEM_FREE;
|
|
return;
|
|
}
|
|
|
|
if (!(htab->map.map_flags & BPF_F_NO_PREALLOC)) {
|
|
pcpu_freelist_push(&htab->freelist, &l->fnode);
|
|
} else {
|
|
atomic_dec(&htab->count);
|
|
l->htab = htab;
|
|
call_rcu(&l->rcu, htab_elem_free_rcu);
|
|
}
|
|
}
|
|
|
|
static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
|
|
void *value, u32 key_size, u32 hash,
|
|
bool percpu, bool onallcpus,
|
|
bool old_elem_exists)
|
|
{
|
|
u32 size = htab->map.value_size;
|
|
bool prealloc = !(htab->map.map_flags & BPF_F_NO_PREALLOC);
|
|
struct htab_elem *l_new;
|
|
void __percpu *pptr;
|
|
int err = 0;
|
|
|
|
if (prealloc) {
|
|
struct pcpu_freelist_node *l;
|
|
|
|
l = pcpu_freelist_pop(&htab->freelist);
|
|
if (!l)
|
|
err = -E2BIG;
|
|
else
|
|
l_new = container_of(l, struct htab_elem, fnode);
|
|
} else {
|
|
if (atomic_inc_return(&htab->count) > htab->map.max_entries) {
|
|
atomic_dec(&htab->count);
|
|
err = -E2BIG;
|
|
} else {
|
|
l_new = kmalloc(htab->elem_size,
|
|
GFP_ATOMIC | __GFP_NOWARN);
|
|
if (!l_new)
|
|
return ERR_PTR(-ENOMEM);
|
|
}
|
|
}
|
|
|
|
if (err) {
|
|
if (!old_elem_exists)
|
|
return ERR_PTR(err);
|
|
|
|
/* if we're updating the existing element and the hash table
|
|
* is full, use per-cpu extra elems
|
|
*/
|
|
l_new = this_cpu_ptr(htab->extra_elems);
|
|
if (l_new->state != HTAB_EXTRA_ELEM_FREE)
|
|
return ERR_PTR(-E2BIG);
|
|
l_new->state = HTAB_EXTRA_ELEM_USED;
|
|
} else {
|
|
l_new->state = HTAB_NOT_AN_EXTRA_ELEM;
|
|
}
|
|
|
|
memcpy(l_new->key, key, key_size);
|
|
if (percpu) {
|
|
/* round up value_size to 8 bytes */
|
|
size = round_up(size, 8);
|
|
|
|
if (prealloc) {
|
|
pptr = htab_elem_get_ptr(l_new, key_size);
|
|
} else {
|
|
/* alloc_percpu zero-fills */
|
|
pptr = __alloc_percpu_gfp(size, 8,
|
|
GFP_ATOMIC | __GFP_NOWARN);
|
|
if (!pptr) {
|
|
kfree(l_new);
|
|
return ERR_PTR(-ENOMEM);
|
|
}
|
|
}
|
|
|
|
if (!onallcpus) {
|
|
/* copy true value_size bytes */
|
|
memcpy(this_cpu_ptr(pptr), value, htab->map.value_size);
|
|
} else {
|
|
int off = 0, cpu;
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
bpf_long_memcpy(per_cpu_ptr(pptr, cpu),
|
|
value + off, size);
|
|
off += size;
|
|
}
|
|
}
|
|
if (!prealloc)
|
|
htab_elem_set_ptr(l_new, key_size, pptr);
|
|
} else {
|
|
memcpy(l_new->key + round_up(key_size, 8), value, size);
|
|
}
|
|
|
|
l_new->hash = hash;
|
|
return l_new;
|
|
}
|
|
|
|
static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old,
|
|
u64 map_flags)
|
|
{
|
|
if (l_old && map_flags == BPF_NOEXIST)
|
|
/* elem already exists */
|
|
return -EEXIST;
|
|
|
|
if (!l_old && map_flags == BPF_EXIST)
|
|
/* elem doesn't exist, cannot update it */
|
|
return -ENOENT;
|
|
|
|
return 0;
|
|
}
|
|
|
|
/* Called from syscall or from eBPF program */
|
|
static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
|
|
u64 map_flags)
|
|
{
|
|
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
|
|
struct htab_elem *l_new = NULL, *l_old;
|
|
struct hlist_nulls_head *head;
|
|
unsigned long flags;
|
|
struct bucket *b;
|
|
u32 key_size, hash;
|
|
int ret;
|
|
|
|
if (unlikely(map_flags > BPF_EXIST))
|
|
/* unknown flags */
|
|
return -EINVAL;
|
|
|
|
WARN_ON_ONCE(!rcu_read_lock_held());
|
|
|
|
key_size = map->key_size;
|
|
|
|
hash = htab_map_hash(key, key_size);
|
|
|
|
b = __select_bucket(htab, hash);
|
|
head = &b->head;
|
|
|
|
/* bpf_map_update_elem() can be called in_irq() */
|
|
raw_spin_lock_irqsave(&b->lock, flags);
|
|
|
|
l_old = lookup_elem_raw(head, hash, key, key_size);
|
|
|
|
ret = check_flags(htab, l_old, map_flags);
|
|
if (ret)
|
|
goto err;
|
|
|
|
l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false,
|
|
!!l_old);
|
|
if (IS_ERR(l_new)) {
|
|
/* all pre-allocated elements are in use or memory exhausted */
|
|
ret = PTR_ERR(l_new);
|
|
goto err;
|
|
}
|
|
|
|
/* add new element to the head of the list, so that
|
|
* concurrent search will find it before old elem
|
|
*/
|
|
hlist_nulls_add_head_rcu(&l_new->hash_node, head);
|
|
if (l_old) {
|
|
hlist_nulls_del_rcu(&l_old->hash_node);
|
|
free_htab_elem(htab, l_old);
|
|
}
|
|
ret = 0;
|
|
err:
|
|
raw_spin_unlock_irqrestore(&b->lock, flags);
|
|
return ret;
|
|
}
|
|
|
|
static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
|
|
void *value, u64 map_flags,
|
|
bool onallcpus)
|
|
{
|
|
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
|
|
struct htab_elem *l_new = NULL, *l_old;
|
|
struct hlist_nulls_head *head;
|
|
unsigned long flags;
|
|
struct bucket *b;
|
|
u32 key_size, hash;
|
|
int ret;
|
|
|
|
if (unlikely(map_flags > BPF_EXIST))
|
|
/* unknown flags */
|
|
return -EINVAL;
|
|
|
|
WARN_ON_ONCE(!rcu_read_lock_held());
|
|
|
|
key_size = map->key_size;
|
|
|
|
hash = htab_map_hash(key, key_size);
|
|
|
|
b = __select_bucket(htab, hash);
|
|
head = &b->head;
|
|
|
|
/* bpf_map_update_elem() can be called in_irq() */
|
|
raw_spin_lock_irqsave(&b->lock, flags);
|
|
|
|
l_old = lookup_elem_raw(head, hash, key, key_size);
|
|
|
|
ret = check_flags(htab, l_old, map_flags);
|
|
if (ret)
|
|
goto err;
|
|
|
|
if (l_old) {
|
|
void __percpu *pptr = htab_elem_get_ptr(l_old, key_size);
|
|
u32 size = htab->map.value_size;
|
|
|
|
/* per-cpu hash map can update value in-place */
|
|
if (!onallcpus) {
|
|
memcpy(this_cpu_ptr(pptr), value, size);
|
|
} else {
|
|
int off = 0, cpu;
|
|
|
|
size = round_up(size, 8);
|
|
for_each_possible_cpu(cpu) {
|
|
bpf_long_memcpy(per_cpu_ptr(pptr, cpu),
|
|
value + off, size);
|
|
off += size;
|
|
}
|
|
}
|
|
} else {
|
|
l_new = alloc_htab_elem(htab, key, value, key_size,
|
|
hash, true, onallcpus, false);
|
|
if (IS_ERR(l_new)) {
|
|
ret = PTR_ERR(l_new);
|
|
goto err;
|
|
}
|
|
hlist_nulls_add_head_rcu(&l_new->hash_node, head);
|
|
}
|
|
ret = 0;
|
|
err:
|
|
raw_spin_unlock_irqrestore(&b->lock, flags);
|
|
return ret;
|
|
}
|
|
|
|
static int htab_percpu_map_update_elem(struct bpf_map *map, void *key,
|
|
void *value, u64 map_flags)
|
|
{
|
|
return __htab_percpu_map_update_elem(map, key, value, map_flags, false);
|
|
}
|
|
|
|
/* Called from syscall or from eBPF program */
|
|
static int htab_map_delete_elem(struct bpf_map *map, void *key)
|
|
{
|
|
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
|
|
struct hlist_nulls_head *head;
|
|
struct bucket *b;
|
|
struct htab_elem *l;
|
|
unsigned long flags;
|
|
u32 hash, key_size;
|
|
int ret = -ENOENT;
|
|
|
|
WARN_ON_ONCE(!rcu_read_lock_held());
|
|
|
|
key_size = map->key_size;
|
|
|
|
hash = htab_map_hash(key, key_size);
|
|
b = __select_bucket(htab, hash);
|
|
head = &b->head;
|
|
|
|
raw_spin_lock_irqsave(&b->lock, flags);
|
|
|
|
l = lookup_elem_raw(head, hash, key, key_size);
|
|
|
|
if (l) {
|
|
hlist_nulls_del_rcu(&l->hash_node);
|
|
free_htab_elem(htab, l);
|
|
ret = 0;
|
|
}
|
|
|
|
raw_spin_unlock_irqrestore(&b->lock, flags);
|
|
return ret;
|
|
}
|
|
|
|
static void delete_all_elements(struct bpf_htab *htab)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < htab->n_buckets; i++) {
|
|
struct hlist_nulls_head *head = select_bucket(htab, i);
|
|
struct hlist_nulls_node *n;
|
|
struct htab_elem *l;
|
|
|
|
hlist_nulls_for_each_entry_safe(l, n, head, hash_node) {
|
|
hlist_nulls_del_rcu(&l->hash_node);
|
|
if (l->state != HTAB_EXTRA_ELEM_USED)
|
|
htab_elem_free(htab, l);
|
|
}
|
|
}
|
|
}
|
|
/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
|
|
static void htab_map_free(struct bpf_map *map)
|
|
{
|
|
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
|
|
|
|
/* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
|
|
* so the programs (can be more than one that used this map) were
|
|
* disconnected from events. Wait for outstanding critical sections in
|
|
* these programs to complete
|
|
*/
|
|
synchronize_rcu();
|
|
|
|
/* some of free_htab_elem() callbacks for elements of this map may
|
|
* not have executed. Wait for them.
|
|
*/
|
|
rcu_barrier();
|
|
if (htab->map.map_flags & BPF_F_NO_PREALLOC) {
|
|
delete_all_elements(htab);
|
|
} else {
|
|
htab_free_elems(htab);
|
|
pcpu_freelist_destroy(&htab->freelist);
|
|
}
|
|
free_percpu(htab->extra_elems);
|
|
bpf_map_area_free(htab->buckets);
|
|
kfree(htab);
|
|
}
|
|
|
|
static const struct bpf_map_ops htab_ops = {
|
|
.map_alloc = htab_map_alloc,
|
|
.map_free = htab_map_free,
|
|
.map_get_next_key = htab_map_get_next_key,
|
|
.map_lookup_elem = htab_map_lookup_elem,
|
|
.map_update_elem = htab_map_update_elem,
|
|
.map_delete_elem = htab_map_delete_elem,
|
|
};
|
|
|
|
static struct bpf_map_type_list htab_type __read_mostly = {
|
|
.ops = &htab_ops,
|
|
.type = BPF_MAP_TYPE_HASH,
|
|
};
|
|
|
|
/* Called from eBPF program */
|
|
static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key)
|
|
{
|
|
struct htab_elem *l = __htab_map_lookup_elem(map, key);
|
|
|
|
if (l)
|
|
return this_cpu_ptr(htab_elem_get_ptr(l, map->key_size));
|
|
else
|
|
return NULL;
|
|
}
|
|
|
|
int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
|
|
{
|
|
struct htab_elem *l;
|
|
void __percpu *pptr;
|
|
int ret = -ENOENT;
|
|
int cpu, off = 0;
|
|
u32 size;
|
|
|
|
/* per_cpu areas are zero-filled and bpf programs can only
|
|
* access 'value_size' of them, so copying rounded areas
|
|
* will not leak any kernel data
|
|
*/
|
|
size = round_up(map->value_size, 8);
|
|
rcu_read_lock();
|
|
l = __htab_map_lookup_elem(map, key);
|
|
if (!l)
|
|
goto out;
|
|
pptr = htab_elem_get_ptr(l, map->key_size);
|
|
for_each_possible_cpu(cpu) {
|
|
bpf_long_memcpy(value + off,
|
|
per_cpu_ptr(pptr, cpu), size);
|
|
off += size;
|
|
}
|
|
ret = 0;
|
|
out:
|
|
rcu_read_unlock();
|
|
return ret;
|
|
}
|
|
|
|
int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
|
|
u64 map_flags)
|
|
{
|
|
int ret;
|
|
|
|
rcu_read_lock();
|
|
ret = __htab_percpu_map_update_elem(map, key, value, map_flags, true);
|
|
rcu_read_unlock();
|
|
|
|
return ret;
|
|
}
|
|
|
|
static const struct bpf_map_ops htab_percpu_ops = {
|
|
.map_alloc = htab_map_alloc,
|
|
.map_free = htab_map_free,
|
|
.map_get_next_key = htab_map_get_next_key,
|
|
.map_lookup_elem = htab_percpu_map_lookup_elem,
|
|
.map_update_elem = htab_percpu_map_update_elem,
|
|
.map_delete_elem = htab_map_delete_elem,
|
|
};
|
|
|
|
static struct bpf_map_type_list htab_percpu_type __read_mostly = {
|
|
.ops = &htab_percpu_ops,
|
|
.type = BPF_MAP_TYPE_PERCPU_HASH,
|
|
};
|
|
|
|
static int __init register_htab_map(void)
|
|
{
|
|
bpf_register_map_type(&htab_type);
|
|
bpf_register_map_type(&htab_percpu_type);
|
|
return 0;
|
|
}
|
|
late_initcall(register_htab_map);
|