diff --git a/arch/riscv/include/asm/sections.h b/arch/riscv/include/asm/sections.h index 1595c5b60cfd0ba04d9fb87700528512106fc2cd..9bbfea7e4b0c4243ba1bef07c61e1565ff311719 100644 --- a/arch/riscv/include/asm/sections.h +++ b/arch/riscv/include/asm/sections.h @@ -11,5 +11,6 @@ extern char _start[]; extern char _start_kernel[]; extern char __init_data_begin[], __init_data_end[]; extern char __init_text_begin[], __init_text_end[]; +extern char __exittext_begin[], __exittext_end[]; #endif /* __ASM_SECTIONS_H */ diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index c3fced410e74298198248810fb034e5b5a698223..86760d01a776b077adaee7c216a5449675adb8e1 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -13,6 +13,7 @@ #include #include #include +#include struct patch_insn { void *addr; @@ -23,12 +24,19 @@ struct patch_insn { int riscv_patch_in_stop_machine = false; #ifdef CONFIG_MMU +static inline bool is_kernel_exittext(uintptr_t addr) +{ + return system_state < SYSTEM_RUNNING && + addr >= (uintptr_t)__exittext_begin && + addr < (uintptr_t)__exittext_end; +} + static void *patch_map(void *addr, int fixmap) { uintptr_t uintaddr = (uintptr_t) addr; struct page *page; - if (core_kernel_text(uintaddr)) + if (core_kernel_text(uintaddr) || is_kernel_exittext(uintaddr)) page = phys_to_page(__pa_symbol(addr)); else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) page = vmalloc_to_page(addr); diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 89fc7ef96bde73d6a271edda9ab1ddfca939f61b..ce9f22cc0719700312063305d51770a79284f568 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -66,10 +66,12 @@ SECTIONS __soc_builtin_dtb_table_end = .; } /* we have to discard exit text and such at runtime, not link time */ + __exittext_begin = .; .exit.text : { EXIT_TEXT } + __exittext_end = .; __init_text_end = .; . = ALIGN(SECTION_ALIGN); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index d81baf750aebbac9f9e53593f3ada2881418589d..dbd2829fffdc5d9b5bd5d3e82f1ffbe01aec0b80 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -346,6 +346,10 @@ struct mmc_blk_ioc_data { struct mmc_ioc_cmd ic; unsigned char *buf; u64 buf_bytes; + unsigned int flags; +#define MMC_BLK_IOC_DROP BIT(0) /* drop this mrq */ +#define MMC_BLK_IOC_SBC BIT(1) /* use mrq.sbc */ + struct mmc_rpmb_data *rpmb; }; @@ -447,7 +451,7 @@ static int card_busy_detect(struct mmc_card *card, unsigned int timeout_ms, } static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, - struct mmc_blk_ioc_data *idata) + struct mmc_blk_ioc_data **idatas, int i) { struct mmc_command cmd = {}, sbc = {}; struct mmc_data data = {}; @@ -455,10 +459,18 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, struct scatterlist sg; int err; unsigned int target_part; + struct mmc_blk_ioc_data *idata = idatas[i]; + struct mmc_blk_ioc_data *prev_idata = NULL; if (!card || !md || !idata) return -EINVAL; + if (idata->flags & MMC_BLK_IOC_DROP) + return 0; + + if (idata->flags & MMC_BLK_IOC_SBC && i > 0) + prev_idata = idatas[i - 1]; + /* * The RPMB accesses comes in from the character device, so we * need to target these explicitly. Else we just target the @@ -525,7 +537,7 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, return err; } - if (idata->rpmb) { + if (idata->rpmb || prev_idata) { sbc.opcode = MMC_SET_BLOCK_COUNT; /* * We don't do any blockcount validation because the max size @@ -533,6 +545,8 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, * 'Reliable Write' bit here. */ sbc.arg = data.blocks | (idata->ic.write_flag & BIT(31)); + if (prev_idata) + sbc.arg = prev_idata->ic.arg; sbc.flags = MMC_RSP_R1 | MMC_CMD_AC; mrq.sbc = &sbc; } @@ -544,6 +558,15 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, mmc_wait_for_req(card->host, &mrq); memcpy(&idata->ic.response, cmd.resp, sizeof(cmd.resp)); + if (prev_idata) { + memcpy(&prev_idata->ic.response, sbc.resp, sizeof(sbc.resp)); + if (sbc.error) { + dev_err(mmc_dev(card->host), "%s: sbc error %d\n", + __func__, sbc.error); + return sbc.error; + } + } + if (cmd.error) { dev_err(mmc_dev(card->host), "%s: cmd error %d\n", __func__, cmd.error); @@ -983,6 +1006,20 @@ static inline void mmc_blk_reset_success(struct mmc_blk_data *md, int type) md->reset_done &= ~type; } +static void mmc_blk_check_sbc(struct mmc_queue_req *mq_rq) +{ + struct mmc_blk_ioc_data **idata = mq_rq->drv_op_data; + int i; + + for (i = 1; i < mq_rq->ioc_count; i++) { + if (idata[i - 1]->ic.opcode == MMC_SET_BLOCK_COUNT && + mmc_op_multi(idata[i]->ic.opcode)) { + idata[i - 1]->flags |= MMC_BLK_IOC_DROP; + idata[i]->flags |= MMC_BLK_IOC_SBC; + } + } +} + /* * The non-block commands come back from the block layer after it queued it and * processed it with all other requests and then they get issued in this @@ -1010,11 +1047,14 @@ static void mmc_blk_issue_drv_op(struct mmc_queue *mq, struct request *req) if (ret) break; } + + mmc_blk_check_sbc(mq_rq); + fallthrough; case MMC_DRV_OP_IOCTL_RPMB: idata = mq_rq->drv_op_data; for (i = 0, ret = 0; i < mq_rq->ioc_count; i++) { - ret = __mmc_blk_ioctl_cmd(card, md, idata[i]); + ret = __mmc_blk_ioctl_cmd(card, md, idata, i); if (ret) break; } diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index c22cc20db1a7499a1680e5d66286cbdf7461006b..ae675c5a47151b0c86424a64f592f9688acf0dca 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -444,16 +444,21 @@ static int pci_device_remove(struct device *dev) struct pci_dev *pci_dev = to_pci_dev(dev); struct pci_driver *drv = pci_dev->driver; - if (drv) { - if (drv->remove) { - pm_runtime_get_sync(dev); - drv->remove(pci_dev); - pm_runtime_put_noidle(dev); - } - pcibios_free_irq(pci_dev); - pci_dev->driver = NULL; - pci_iov_remove(pci_dev); + if (drv->remove) { + pm_runtime_get_sync(dev); + /* + * If the driver provides a .runtime_idle() callback and it has + * started to run already, it may continue to run in parallel + * with the code below, so wait until all of the runtime PM + * activity has completed. + */ + pm_runtime_barrier(dev); + drv->remove(pci_dev); + pm_runtime_put_noidle(dev); } + pcibios_free_irq(pci_dev); + pci_dev->driver = NULL; + pci_iov_remove(pci_dev); /* Undo the runtime PM settings in local_pci_probe() */ pm_runtime_put_sync(dev); diff --git a/drivers/pinctrl/devicetree.c b/drivers/pinctrl/devicetree.c index eac55fee5281c4e247ff5f975a3de1d29662c5cf..0220228c5040473c08fc8db3d5ed58de21a999d5 100644 --- a/drivers/pinctrl/devicetree.c +++ b/drivers/pinctrl/devicetree.c @@ -220,14 +220,16 @@ int pinctrl_dt_to_map(struct pinctrl *p, struct pinctrl_dev *pctldev) for (state = 0; ; state++) { /* Retrieve the pinctrl-* property */ propname = kasprintf(GFP_KERNEL, "pinctrl-%d", state); - if (!propname) - return -ENOMEM; + if (!propname) { + ret = -ENOMEM; + goto err; + } prop = of_find_property(np, propname, &size); kfree(propname); if (!prop) { if (state == 0) { - of_node_put(np); - return -ENODEV; + ret = -ENODEV; + goto err; } break; } diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 857a1399850c30be4efd6c2030a258faf7c81efa..d5bc995de16be410b948090c1108695158a32ac4 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -472,12 +472,6 @@ static LIST_HEAD(spi_controller_list); */ static DEFINE_MUTEX(board_lock); -/* - * Prevents addition of devices with same chip select and - * addition of devices below an unregistering controller. - */ -static DEFINE_MUTEX(spi_add_lock); - /** * spi_alloc_device - Allocate a new SPI device * @ctlr: Controller to which device is connected @@ -581,7 +575,7 @@ int spi_add_device(struct spi_device *spi) * chipselect **BEFORE** we call setup(), else we'll trash * its configuration. Lock against concurrent add() calls. */ - mutex_lock(&spi_add_lock); + mutex_lock(&ctlr->add_lock); status = bus_for_each_dev(&spi_bus_type, NULL, spi, spi_dev_check); if (status) { @@ -625,7 +619,7 @@ int spi_add_device(struct spi_device *spi) } done: - mutex_unlock(&spi_add_lock); + mutex_unlock(&ctlr->add_lock); return status; } EXPORT_SYMBOL_GPL(spi_add_device); @@ -2730,6 +2724,7 @@ int spi_register_controller(struct spi_controller *ctlr) spin_lock_init(&ctlr->bus_lock_spinlock); mutex_init(&ctlr->bus_lock_mutex); mutex_init(&ctlr->io_mutex); + mutex_init(&ctlr->add_lock); ctlr->bus_lock_flag = 0; init_completion(&ctlr->xfer_completion); if (!ctlr->max_dma_len) @@ -2875,7 +2870,7 @@ void spi_unregister_controller(struct spi_controller *ctlr) /* Prevent addition of new devices, unregister existing ones */ if (IS_ENABLED(CONFIG_SPI_DYNAMIC)) - mutex_lock(&spi_add_lock); + mutex_lock(&ctlr->add_lock); device_for_each_child(&ctlr->dev, NULL, __unregister); @@ -2906,7 +2901,7 @@ void spi_unregister_controller(struct spi_controller *ctlr) mutex_unlock(&board_lock); if (IS_ENABLED(CONFIG_SPI_DYNAMIC)) - mutex_unlock(&spi_add_lock); + mutex_unlock(&ctlr->add_lock); } EXPORT_SYMBOL_GPL(spi_unregister_controller); diff --git a/fs/pipe.c b/fs/pipe.c index dbb090e1b026ce7a7b52b1e9167e75ca1a84a719..588fe37d8d955fd5c93b620ca9699b84660b9ace 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -435,12 +435,10 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) goto out; } -#ifdef CONFIG_WATCH_QUEUE - if (pipe->watch_queue) { + if (pipe_has_watch_queue(pipe)) { ret = -EXDEV; goto out; } -#endif /* * If it wasn't empty we try to merge new data into @@ -1302,6 +1300,11 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) pipe->tail = tail; pipe->head = head; + if (!pipe_has_watch_queue(pipe)) { + pipe->max_usage = nr_slots; + pipe->nr_accounted = nr_slots; + } + spin_unlock_irq(&pipe->rd_wait.lock); /* This might have made more room for writers */ @@ -1319,10 +1322,8 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) unsigned int nr_slots, size; long ret = 0; -#ifdef CONFIG_WATCH_QUEUE - if (pipe->watch_queue) + if (pipe_has_watch_queue(pipe)) return -EBUSY; -#endif size = round_pipe_size(arg); nr_slots = size >> PAGE_SHIFT; @@ -1355,8 +1356,6 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) if (ret < 0) goto out_revert_acct; - pipe->max_usage = nr_slots; - pipe->nr_accounted = nr_slots; return pipe->max_usage * PAGE_SIZE; out_revert_acct: @@ -1375,10 +1374,8 @@ struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice) if (file->f_op != &pipefifo_fops || !pipe) return NULL; -#ifdef CONFIG_WATCH_QUEUE - if (for_splice && pipe->watch_queue) + if (for_splice && pipe_has_watch_queue(pipe)) return NULL; -#endif return pipe; } diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index d89f6a2f184a1905d6207d22769e89012189f867..5c4f3926136f4a39444dca8171e0de3d0acec0bb 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -262,9 +262,6 @@ static int write_begin_slow(struct address_space *mapping, return err; } } - - SetPageUptodate(page); - ClearPageError(page); } if (PagePrivate(page)) @@ -463,9 +460,6 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, return err; } } - - SetPageUptodate(page); - ClearPageError(page); } err = allocate_budget(c, page, ui, appending); @@ -475,10 +469,8 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, * If we skipped reading the page because we were going to * write all of it, then it is not up to date. */ - if (skipped_read) { + if (skipped_read) ClearPageChecked(page); - ClearPageUptodate(page); - } /* * Budgeting failed which means it would have to force * write-back but didn't, because we set the @fast flag in the @@ -569,6 +561,9 @@ static int ubifs_write_end(struct file *file, struct address_space *mapping, goto out; } + if (len == PAGE_SIZE) + SetPageUptodate(page); + if (!PagePrivate(page)) { attach_page_private(page, (void *)1); atomic_long_inc(&c->dirty_pg_cnt); diff --git a/include/linux/key-type.h b/include/linux/key-type.h index 2ab2d6d6aeab857a5e6175bd413a473d2e21515f..7de851a9af8f36374e68f0e6e3f8710a3f9d6c26 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -72,6 +72,7 @@ struct key_type { unsigned int flags; #define KEY_TYPE_NET_DOMAIN 0x00000001 /* Keys of this type have a net namespace domain */ +#define KEY_TYPE_INSTANT_REAP 0x00000002 /* Keys of this type don't have a delay after expiring */ /* vet a description */ int (*vet_description)(const char *description); diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index ef236dbaa2945cdbd8ecf56ec834f6ddac17d754..7b72d93c265302760dd708f33a5e537f11ff271a 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -124,6 +124,22 @@ struct pipe_buf_operations { bool (*get)(struct pipe_inode_info *, struct pipe_buffer *); }; +/** + * pipe_has_watch_queue - Check whether the pipe is a watch_queue, + * i.e. it was created with O_NOTIFICATION_PIPE + * @pipe: The pipe to check + * + * Return: true if pipe is a watch queue, false otherwise. + */ +static inline bool pipe_has_watch_queue(const struct pipe_inode_info *pipe) +{ +#ifdef CONFIG_WATCH_QUEUE + return pipe->watch_queue != NULL; +#else + return false; +#endif +} + /** * pipe_empty - Return true if the pipe is empty * @head: The pipe ring head pointer diff --git a/include/linux/pwm.h b/include/linux/pwm.h index a13ff383fa1d55c5d5f68a99beae3061bb2ff758..c0cf6613373f9ed564f92554b589fe4b3f54674e 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -44,8 +44,8 @@ struct pwm_args { }; enum { - PWMF_REQUESTED = 1 << 0, - PWMF_EXPORTED = 1 << 1, + PWMF_REQUESTED = 0, + PWMF_EXPORTED = 1, }; /* diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 1138dd3071dbd6cecf20c7c75c92d80ec026e34c..a197c9a49e97a7ca00bb0165a6577776cbe5bb53 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -406,10 +406,12 @@ static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock) { + read_lock_bh(&sk->sk_callback_lock); if (psock->parser.enabled) psock->parser.saved_data_ready(sk); else sk->sk_data_ready(sk); + read_unlock_bh(&sk->sk_callback_lock); } static inline void psock_set_prog(struct bpf_prog **pprog, diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index e1d88630ff24390938ad205bbb34a941e8fafb4c..8f5ed0beeea4a9d5afd366ca1d7e6887c8448fb6 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -527,6 +527,9 @@ struct spi_controller { /* I/O mutex */ struct mutex io_mutex; + /* Used to avoid adding the same CS twice */ + struct mutex add_lock; + /* lock and mutex for SPI bus locking */ spinlock_t bus_lock_spinlock; struct mutex bus_lock_mutex; diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 355835639ae583872fc5c6c0f67e2cba7547c693..7d2bd562da4bebf63d73a4d37c19aa18d0096d20 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -487,6 +487,15 @@ static inline struct sk_buff *bt_skb_sendmmsg(struct sock *sk, return skb; } +static inline int bt_copy_from_sockptr(void *dst, size_t dst_size, + sockptr_t src, size_t src_size) +{ + if (dst_size > src_size) + return -EINVAL; + + return copy_from_sockptr(dst, src, dst_size); +} + int bt_to_errno(u16 code); void hci_sock_set_flag(struct sock *sk, int nr); diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 632086b2f644a90f38f2382111c5f0430aff0e8b..3ae2fda29507382ff83867ed5898f433bb38783a 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -24,7 +24,7 @@ struct dst_ops { void (*destroy)(struct dst_entry *); void (*ifdown)(struct dst_entry *, struct net_device *dev, int how); - struct dst_entry * (*negative_advice)(struct dst_entry *); + void (*negative_advice)(struct sock *sk, struct dst_entry *); void (*link_failure)(struct sk_buff *); void (*update_pmtu)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, diff --git a/include/net/sock.h b/include/net/sock.h index 127ac9a265151e4f8fc3dcec7e71ba555950a8ee..e54eb85bcb0bd275b568a469e492b14ccc2363b0 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1868,21 +1868,33 @@ static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) /* sk_tx_queue_mapping accept only upto a 16-bit value */ if (WARN_ON_ONCE((unsigned short)tx_queue >= USHRT_MAX)) return; - sk->sk_tx_queue_mapping = tx_queue; + /* Paired with READ_ONCE() in sk_tx_queue_get() and + * other WRITE_ONCE() because socket lock might be not held. + */ + WRITE_ONCE(sk->sk_tx_queue_mapping, tx_queue); } #define NO_QUEUE_MAPPING USHRT_MAX static inline void sk_tx_queue_clear(struct sock *sk) { - sk->sk_tx_queue_mapping = NO_QUEUE_MAPPING; + /* Paired with READ_ONCE() in sk_tx_queue_get() and + * other WRITE_ONCE() because socket lock might be not held. + */ + WRITE_ONCE(sk->sk_tx_queue_mapping, NO_QUEUE_MAPPING); } static inline int sk_tx_queue_get(const struct sock *sk) { - if (sk && sk->sk_tx_queue_mapping != NO_QUEUE_MAPPING) - return sk->sk_tx_queue_mapping; + if (sk) { + /* Paired with WRITE_ONCE() in sk_tx_queue_clear() + * and sk_tx_queue_set(). + */ + int val = READ_ONCE(sk->sk_tx_queue_mapping); + if (val != NO_QUEUE_MAPPING) + return val; + } return -1; } @@ -2008,17 +2020,10 @@ sk_dst_get(struct sock *sk) static inline void __dst_negative_advice(struct sock *sk) { - struct dst_entry *ndst, *dst = __sk_dst_get(sk); + struct dst_entry *dst = __sk_dst_get(sk); - if (dst && dst->ops->negative_advice) { - ndst = dst->ops->negative_advice(dst); - - if (ndst != dst) { - rcu_assign_pointer(sk->sk_dst_cache, ndst); - sk_tx_queue_clear(sk); - sk->sk_dst_pending_confirm = 0; - } - } + if (dst && dst->ops->negative_advice) + dst->ops->negative_advice(sk, dst); } static inline void dst_negative_advice(struct sock *sk) @@ -2033,7 +2038,7 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst) struct dst_entry *old_dst; sk_tx_queue_clear(sk); - sk->sk_dst_pending_confirm = 0; + WRITE_ONCE(sk->sk_dst_pending_confirm, 0); old_dst = rcu_dereference_protected(sk->sk_dst_cache, lockdep_sock_is_held(sk)); rcu_assign_pointer(sk->sk_dst_cache, dst); @@ -2046,7 +2051,7 @@ sk_dst_set(struct sock *sk, struct dst_entry *dst) struct dst_entry *old_dst; sk_tx_queue_clear(sk); - sk->sk_dst_pending_confirm = 0; + WRITE_ONCE(sk->sk_dst_pending_confirm, 0); old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst); dst_release(old_dst); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 96d19df0dfa061cb3f083b5baeb223186d04b5ef..e26d2c255109b14c22a54df52f3cb4742ea6968b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3921,10 +3921,7 @@ static int check_stack_access_within_bounds( if (tnum_is_const(reg->var_off)) { min_off = (s64)reg->var_off.value + off; - if (access_size > 0) - max_off = min_off + access_size - 1; - else - max_off = min_off; + max_off = min_off + access_size; } else { if (reg->smax_value >= BPF_MAX_VAR_OFF || reg->smin_value <= -BPF_MAX_VAR_OFF) { @@ -3932,16 +3929,18 @@ static int check_stack_access_within_bounds( err_extra, regno); return -EACCES; } - min_off = reg->smin_value + off; - if (access_size > 0) - max_off = reg->smax_value + off + access_size - 1; - else - max_off = min_off; + min_off = (s64)reg->smin_value + off; + max_off = (s64)reg->smax_value + off + access_size; } err = check_stack_slot_within_bounds(min_off, state, type); - if (!err) - err = check_stack_slot_within_bounds(max_off, state, type); + if (!err && max_off > 0) + err = -EINVAL; /* out of stack access into non-negative offsets */ + if (!err && access_size < 0) + /* access_size should not be negative (or overflow an int); others checks + * along the way should have prevented such an access. + */ + err = -EFAULT; /* invalid negative access size; integer overflow? */ if (err) { if (tnum_is_const(reg->var_off)) { diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 69dd036b53d1f9ac3d4ed25e9fb64e36ecbc7c25..ca27946fdaaf2faf5d7fc31a1da53b14cf89df0f 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -694,6 +694,12 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event, max_order--; } + /* + * kcalloc_node() is unable to allocate buffer if the size is larger + * than: PAGE_SIZE << MAX_ORDER; directly bail out in this case. + */ + if (get_order((unsigned long)nr_pages * sizeof(void *)) > MAX_ORDER) + return -ENOMEM; rb->aux_pages = kcalloc_node(nr_pages, sizeof(void *), GFP_KERNEL, node); if (!rb->aux_pages) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index ad5294de975948b7bd14ccc599beddbcf90466b1..c731ead3719cdbc54ddfd49e5873c4b2b356f7f6 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -4618,9 +4618,12 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); - if (!conn || !hci_conn_ssp_enabled(conn)) + if (!conn || !hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) goto unlock; + /* Assume remote supports SSP since it has triggered this event */ + set_bit(HCI_CONN_SSP_ENABLED, &conn->flags); + hci_conn_hold(conn); if (!hci_dev_test_flag(hdev, HCI_MGMT)) diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 4cf1fa9900cae9f0a2e18c3f0b1b7a85cf531c3b..82f404d3eba2d59349142fdcc1e1a4c24e9410f4 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -631,7 +631,7 @@ static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, switch (optname) { case RFCOMM_LM: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { + if (bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen)) { err = -EFAULT; break; } @@ -666,7 +666,6 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, struct sock *sk = sock->sk; struct bt_security sec; int err = 0; - size_t len; u32 opt; BT_DBG("sk %p", sk); @@ -688,11 +687,9 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, sec.level = BT_SECURITY_LOW; - len = min_t(unsigned int, sizeof(sec), optlen); - if (copy_from_sockptr(&sec, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&sec, sizeof(sec), optval, optlen); + if (err) break; - } if (sec.level > BT_SECURITY_HIGH) { err = -EINVAL; @@ -708,10 +705,9 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 3ee342665c975a8b61606c704957b7864716ac88..f9a2993fd4522b99a5712ee32867128200cb4ec7 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -829,7 +829,7 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; - int len, err = 0; + int err = 0; struct bt_voice voice; u32 opt; @@ -845,10 +845,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); @@ -865,11 +864,10 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, voice.setting = sco_pi(sk)->setting; - len = min_t(unsigned int, sizeof(voice), optlen); - if (copy_from_sockptr(&voice, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&voice, sizeof(voice), optval, + optlen); + if (err) break; - } /* Explicitly check for these values */ if (voice.setting != BT_VOICE_TRANSPARENT && @@ -882,10 +880,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_PKT_STATUS: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) sco_pi(sk)->cmsg_mask |= SCO_CMSG_PKT_STATUS; diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index e05dd4f3279a8c119d53a96bf72f5a6ca3660e3f..72cfe5248b764267d970c2d536bf56c6fc494bc6 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -86,12 +86,15 @@ u64 __net_gen_cookie(struct net *net) static struct net_generic *net_alloc_generic(void) { + unsigned int gen_ptrs = READ_ONCE(max_gen_ptrs); + unsigned int generic_size; struct net_generic *ng; - unsigned int generic_size = offsetof(struct net_generic, ptr[max_gen_ptrs]); + + generic_size = offsetof(struct net_generic, ptr[gen_ptrs]); ng = kzalloc(generic_size, GFP_KERNEL); if (ng) - ng->s.len = max_gen_ptrs; + ng->s.len = gen_ptrs; return ng; } @@ -1241,7 +1244,11 @@ static int register_pernet_operations(struct list_head *list, if (error < 0) return error; *ops->id = error; - max_gen_ptrs = max(max_gen_ptrs, *ops->id + 1); + /* This does not require READ_ONCE as writers already hold + * pernet_ops_rwsem. But WRITE_ONCE is needed to protect + * net_alloc_generic. + */ + WRITE_ONCE(max_gen_ptrs, max(max_gen_ptrs, *ops->id + 1)); } error = __register_pernet_operations(list, ops); if (error) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 50261f3aec82bf2eee0f428c5b7fca871df70a50..fd53b66f2ca1d2f8f51345526b5c0616b913aa6d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1516,11 +1516,17 @@ static inline int skb_alloc_rx_flag(const struct sk_buff *skb) struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { - int headerlen = skb_headroom(skb); - unsigned int size = skb_end_offset(skb) + skb->data_len; - struct sk_buff *n = __alloc_skb(size, gfp_mask, - skb_alloc_rx_flag(skb), NUMA_NO_NODE); + struct sk_buff *n; + unsigned int size; + int headerlen; + + if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) + return NULL; + headerlen = skb_headroom(skb); + size = skb_end_offset(skb) + skb->data_len; + n = __alloc_skb(size, gfp_mask, + skb_alloc_rx_flag(skb), NUMA_NO_NODE); if (!n) return NULL; @@ -1750,12 +1756,17 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, /* * Allocate the copy buffer */ - struct sk_buff *n = __alloc_skb(newheadroom + skb->len + newtailroom, - gfp_mask, skb_alloc_rx_flag(skb), - NUMA_NO_NODE); - int oldheadroom = skb_headroom(skb); int head_copy_len, head_copy_off; + struct sk_buff *n; + int oldheadroom; + + if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) + return NULL; + oldheadroom = skb_headroom(skb); + n = __alloc_skb(newheadroom + skb->len + newtailroom, + gfp_mask, skb_alloc_rx_flag(skb), + NUMA_NO_NODE); if (!n) return NULL; diff --git a/net/core/sock.c b/net/core/sock.c index c5b9d1fc3b0f484755a7b984569be1be127c9834..ee26f09faac84c49b1af5ed7e0213c879ea7900a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -532,7 +532,7 @@ struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { sk_tx_queue_clear(sk); - sk->sk_dst_pending_confirm = 0; + WRITE_ONCE(sk->sk_dst_pending_confirm, 0); RCU_INIT_POINTER(sk->sk_dst_cache, NULL); dst_release(dst); return NULL; diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 3aced951d5ab8b589f370edab51e3aba54f2174b..03f8f33dc134c76c80199136be67b857639a8bae 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -91,6 +91,7 @@ const struct cred *dns_resolver_cache; static int dns_resolver_preparse(struct key_preparsed_payload *prep) { + const struct dns_server_list_v1_header *v1; const struct dns_payload_header *bin; struct user_key_payload *upayload; unsigned long derrno; @@ -122,6 +123,13 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) return -EINVAL; } + v1 = (const struct dns_server_list_v1_header *)bin; + if ((v1->status != DNS_LOOKUP_GOOD && + v1->status != DNS_LOOKUP_GOOD_WITH_BAD)) { + if (prep->expiry == TIME64_MAX) + prep->expiry = ktime_get_real_seconds() + 1; + } + result_len = datalen; goto store_result; } @@ -314,7 +322,7 @@ static long dns_resolver_read(const struct key *key, struct key_type key_type_dns_resolver = { .name = "dns_resolver", - .flags = KEY_TYPE_NET_DOMAIN, + .flags = KEY_TYPE_NET_DOMAIN | KEY_TYPE_INSTANT_REAP, .preparse = dns_resolver_preparse, .free_preparse = dns_resolver_free_preparse, .instantiate = generic_key_instantiate, diff --git a/net/ipv4/route.c b/net/ipv4/route.c index bfb70a7a96964013fb286c5edde55818fac01f2d..77ec9a284fc74cb76267b817fd3ba0ca66369532 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -137,7 +137,8 @@ static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); static unsigned int ipv4_mtu(const struct dst_entry *dst); -static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); +static void ipv4_negative_advice(struct sock *sk, + struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, @@ -866,22 +867,15 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf __ip_do_redirect(rt, skb, &fl4, true); } -static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) +static void ipv4_negative_advice(struct sock *sk, + struct dst_entry *dst) { struct rtable *rt = (struct rtable *)dst; - struct dst_entry *ret = dst; - if (rt) { - if (dst->obsolete > 0) { - ip_rt_put(rt); - ret = NULL; - } else if ((rt->rt_flags & RTCF_REDIRECTED) || - rt->dst.expires) { - ip_rt_put(rt); - ret = NULL; - } - } - return ret; + if ((dst->obsolete > 0) || + (rt->rt_flags & RTCF_REDIRECTED) || + rt->dst.expires) + sk_dst_reset(sk); } /* diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 08d100ad4248676fa4eedf2d63d1a8e921689799..942c6befc5e06ad73df62bd9ded67629e36d9a4c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2504,7 +2504,7 @@ void tcp_shutdown(struct sock *sk, int how) /* If we've already sent a FIN, or it's a closed state, skip this. */ if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_SENT | - TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) { + TCPF_CLOSE_WAIT)) { /* Clear out any half completed packets. FIN if needed. */ if (tcp_close_state(sk)) tcp_send_fin(sk); @@ -2615,7 +2615,7 @@ void __tcp_close(struct sock *sk, long timeout) * machine. State transitions: * * TCP_ESTABLISHED -> TCP_FIN_WAIT1 - * TCP_SYN_RECV -> TCP_FIN_WAIT1 (forget it, it's impossible) + * TCP_SYN_RECV -> TCP_FIN_WAIT1 (it is difficult) * TCP_CLOSE_WAIT -> TCP_LAST_ACK * * are legal only when FIN has been sent (i.e. in window), diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index fe8eb427f491fb25b4abca76273e79988a2d5675..7bf169378b321bfd1a6fd0e0beba80afbd3ce9a6 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3775,8 +3775,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) * then we can probably ignore it. */ if (before(ack, prior_snd_una)) { + u32 max_window; + + /* do not accept ACK for bytes we never sent. */ + max_window = min_t(u64, tp->max_window, tp->bytes_acked); /* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */ - if (before(ack, prior_snd_una - tp->max_window)) { + if (before(ack, prior_snd_una - max_window)) { if (!(flag & FLAG_NO_CHALLENGE_ACK)) tcp_send_challenge_ack(sk, skb); return -1; @@ -6517,6 +6521,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_initialize_rcv_mss(sk); tcp_fast_path_on(tp); + if (sk->sk_shutdown & SEND_SHUTDOWN) + tcp_shutdown(sk, SEND_SHUTDOWN); break; case TCP_FIN_WAIT1: { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 808fbeb3b6870bf804438b51d75d760d4722feb0..74f0f9eb07afd53f74597e3306f7aeaf655a267c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1322,7 +1322,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, skb_set_hash_from_sk(skb, sk); refcount_add(skb->truesize, &sk->sk_wmem_alloc); - skb_set_dst_pending_confirm(skb, sk->sk_dst_pending_confirm); + skb_set_dst_pending_confirm(skb, READ_ONCE(sk->sk_dst_pending_confirm)); /* Build TCP header and checksum it. */ th = (struct tcphdr *)skb->data; @@ -3436,7 +3436,9 @@ void tcp_send_fin(struct sock *sk) return; } } else { - skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation); + skb = alloc_skb_fclone(MAX_TCP_HEADER, + sk_gfp_mask(sk, GFP_ATOMIC | + __GFP_NOWARN)); if (unlikely(!skb)) return; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 03d3145691c6c4cb6d33d5a0e1650a6135b80bf6..b3029aedeef84fac75428a182bc6e44c638db985 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5422,9 +5422,10 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, } addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); - if (!addr) - return -EINVAL; - + if (!addr) { + err = -EINVAL; + goto errout; + } ifm = nlmsg_data(nlh); if (ifm->ifa_index) dev = dev_get_by_index(tgt_net, ifm->ifa_index); diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 3e4c87b29b11522f090608a2c30446f6c8657260..a4276e40a429ac3508e843340d4c95fff81e7883 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -232,8 +232,12 @@ static int __fib6_rule_action(struct fib_rule *rule, struct flowi *flp, rt = pol_lookup_func(lookup, net, table, flp6, arg->lookup_data, flags); if (rt != net->ipv6.ip6_null_entry) { + struct inet6_dev *idev = ip6_dst_idev(&rt->dst); + + if (!idev) + goto again; err = fib6_rule_saddr(net, rule, flags, flp6, - ip6_dst_idev(&rt->dst)->dev); + idev->dev); if (err == -EAGAIN) goto again; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2d53c362f309ea7acd9848b5b421bf88cab601b6..f41f9232857c102404f76e7dd03a9d8c93475533 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -85,7 +85,8 @@ enum rt6_nud_state { static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); static unsigned int ip6_mtu(const struct dst_entry *dst); -static struct dst_entry *ip6_negative_advice(struct dst_entry *); +static void ip6_negative_advice(struct sock *sk, + struct dst_entry *dst); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, struct net_device *dev, int how); @@ -2635,24 +2636,24 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) return dst_ret; } -static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) +static void ip6_negative_advice(struct sock *sk, + struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *) dst; - if (rt) { - if (rt->rt6i_flags & RTF_CACHE) { - rcu_read_lock(); - if (rt6_check_expired(rt)) { - rt6_remove_exception_rt(rt); - dst = NULL; - } - rcu_read_unlock(); - } else { - dst_release(dst); - dst = NULL; + if (rt->rt6i_flags & RTF_CACHE) { + rcu_read_lock(); + if (rt6_check_expired(rt)) { + /* counteract the dst_release() in sk_dst_reset() */ + dst_hold(dst); + sk_dst_reset(sk); + + rt6_remove_exception_rt(rt); } + rcu_read_unlock(); + return; } - return dst; + sk_dst_reset(sk); } static void ip6_link_failure(struct sk_buff *skb) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5d520b88492c9d608c3a2ef186399d03df9cac96..8b4f36b4bec19d35b701fa20acf8923900835244 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -12641,6 +12641,8 @@ static int nl80211_set_coalesce(struct sk_buff *skb, struct genl_info *info) error: for (i = 0; i < new_coalesce.n_rules; i++) { tmp_rule = &new_coalesce.rules[i]; + if (!tmp_rule) + continue; for (j = 0; j < tmp_rule->n_patterns; j++) kfree(tmp_rule->patterns[j].mask); kfree(tmp_rule->patterns); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 664d55957feb52d6a54141e58dab15cde885ff57..fadb309b25b40dd568b2c807328a26295a18f36d 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3807,15 +3807,10 @@ static void xfrm_link_failure(struct sk_buff *skb) /* Impossible. Such dst must be popped before reaches point of failure. */ } -static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst) +static void xfrm_negative_advice(struct sock *sk, struct dst_entry *dst) { - if (dst) { - if (dst->obsolete) { - dst_release(dst); - dst = NULL; - } - } - return dst; + if (dst->obsolete) + sk_dst_reset(sk); } static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr) diff --git a/security/keys/gc.c b/security/keys/gc.c index 3c90807476eb0e293a85940daff55c30bf636169..eaddaceda14eab077512f75081f102cf00157566 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -66,6 +66,19 @@ void key_schedule_gc(time64_t gc_at) } } +/* + * Set the expiration time on a key. + */ +void key_set_expiry(struct key *key, time64_t expiry) +{ + key->expiry = expiry; + if (expiry != TIME64_MAX) { + if (!(key->type->flags & KEY_TYPE_INSTANT_REAP)) + expiry += key_gc_delay; + key_schedule_gc(expiry); + } +} + /* * Schedule a dead links collection run. */ @@ -176,7 +189,6 @@ static void key_garbage_collector(struct work_struct *work) static u8 gc_state; /* Internal persistent state */ #define KEY_GC_REAP_AGAIN 0x01 /* - Need another cycle */ #define KEY_GC_REAPING_LINKS 0x02 /* - We need to reap links */ -#define KEY_GC_SET_TIMER 0x04 /* - We need to restart the timer */ #define KEY_GC_REAPING_DEAD_1 0x10 /* - We need to mark dead keys */ #define KEY_GC_REAPING_DEAD_2 0x20 /* - We need to reap dead key links */ #define KEY_GC_REAPING_DEAD_3 0x40 /* - We need to reap dead keys */ @@ -184,21 +196,17 @@ static void key_garbage_collector(struct work_struct *work) struct rb_node *cursor; struct key *key; - time64_t new_timer, limit; + time64_t new_timer, limit, expiry; kenter("[%lx,%x]", key_gc_flags, gc_state); limit = ktime_get_real_seconds(); - if (limit > key_gc_delay) - limit -= key_gc_delay; - else - limit = key_gc_delay; /* Work out what we're going to be doing in this pass */ gc_state &= KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2; gc_state <<= 1; if (test_and_clear_bit(KEY_GC_KEY_EXPIRED, &key_gc_flags)) - gc_state |= KEY_GC_REAPING_LINKS | KEY_GC_SET_TIMER; + gc_state |= KEY_GC_REAPING_LINKS; if (test_and_clear_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags)) gc_state |= KEY_GC_REAPING_DEAD_1; @@ -233,8 +241,11 @@ static void key_garbage_collector(struct work_struct *work) } } - if (gc_state & KEY_GC_SET_TIMER) { - if (key->expiry > limit && key->expiry < new_timer) { + expiry = key->expiry; + if (expiry != TIME64_MAX) { + if (!(key->type->flags & KEY_TYPE_INSTANT_REAP)) + expiry += key_gc_delay; + if (expiry > limit && expiry < new_timer) { kdebug("will expire %x in %lld", key_serial(key), key->expiry - limit); new_timer = key->expiry; @@ -276,7 +287,7 @@ static void key_garbage_collector(struct work_struct *work) */ kdebug("pass complete"); - if (gc_state & KEY_GC_SET_TIMER && new_timer != (time64_t)TIME64_MAX) { + if (new_timer != TIME64_MAX) { new_timer += key_gc_delay; key_schedule_gc(new_timer); } diff --git a/security/keys/internal.h b/security/keys/internal.h index 9b9cf3b6fcbb4d5e57e57100055cee2772d1db40..bede6c71ffd971533eb7ed3d1615bd00c78e4714 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -176,6 +176,7 @@ extern unsigned key_gc_delay; extern void keyring_gc(struct key *keyring, time64_t limit); extern void keyring_restriction_gc(struct key *keyring, struct key_type *dead_type); +void key_set_expiry(struct key *key, time64_t expiry); extern void key_schedule_gc(time64_t gc_at); extern void key_schedule_gc_links(void); extern void key_gc_keytype(struct key_type *ktype); @@ -224,10 +225,18 @@ extern struct key *key_get_instantiation_authkey(key_serial_t target_id); */ static inline bool key_is_dead(const struct key *key, time64_t limit) { + time64_t expiry = key->expiry; + + if (expiry != TIME64_MAX) { + if (!(key->type->flags & KEY_TYPE_INSTANT_REAP)) + expiry += key_gc_delay; + if (expiry <= limit) + return true; + } + return key->flags & ((1 << KEY_FLAG_DEAD) | (1 << KEY_FLAG_INVALIDATED)) || - (key->expiry > 0 && key->expiry <= limit) || key->domain_tag->removed; } diff --git a/security/keys/key.c b/security/keys/key.c index 151ff39b68030c4fe0bf9993843e41b1c80b264c..e5111ce17e2545bc58a7cf5a291c46b3fe97b12d 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -294,6 +294,7 @@ struct key *key_alloc(struct key_type *type, const char *desc, key->uid = uid; key->gid = gid; key->perm = perm; + key->expiry = TIME64_MAX; key->restrict_link = restrict_link; key->last_used_at = ktime_get_real_seconds(); @@ -463,10 +464,8 @@ static int __key_instantiate_and_link(struct key *key, if (authkey) key_invalidate(authkey); - if (prep->expiry != TIME64_MAX) { - key->expiry = prep->expiry; - key_schedule_gc(prep->expiry + key_gc_delay); - } + if (prep->expiry != TIME64_MAX) + key_set_expiry(key, prep->expiry); } } @@ -605,8 +604,7 @@ int key_reject_and_link(struct key *key, atomic_inc(&key->user->nikeys); mark_key_instantiated(key, -error); notify_key(key, NOTIFY_KEY_INSTANTIATED, -error); - key->expiry = ktime_get_real_seconds() + timeout; - key_schedule_gc(key->expiry + key_gc_delay); + key_set_expiry(key, ktime_get_real_seconds() + timeout); if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags)) awaken = 1; @@ -721,16 +719,14 @@ struct key_type *key_type_lookup(const char *type) void key_set_timeout(struct key *key, unsigned timeout) { - time64_t expiry = 0; + time64_t expiry = TIME64_MAX; /* make the changes with the locks held to prevent races */ down_write(&key->sem); if (timeout > 0) expiry = ktime_get_real_seconds() + timeout; - - key->expiry = expiry; - key_schedule_gc(key->expiry + key_gc_delay); + key_set_expiry(key, expiry); up_write(&key->sem); } diff --git a/security/keys/proc.c b/security/keys/proc.c index d0cde6685627f2ab6d3cc0d6919b7e8a50c10dd0..4f4e2c1824f18bd480554661f6f2f2d67c9bce51 100644 --- a/security/keys/proc.c +++ b/security/keys/proc.c @@ -198,7 +198,7 @@ static int proc_keys_show(struct seq_file *m, void *v) /* come up with a suitable timeout value */ expiry = READ_ONCE(key->expiry); - if (expiry == 0) { + if (expiry == TIME64_MAX) { memcpy(xbuf, "perm", 5); } else if (now >= expiry) { memcpy(xbuf, "expd", 5);