diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 071fb18dc57c..07fad3d2fc56 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1321,6 +1321,14 @@ accept_ra_from_local - BOOLEAN disabled if accept_ra_from_local is disabled on a specific interface. +accept_ra_min_hop_limit - INTEGER + Minimum hop limit Information in Router Advertisement. + + Hop limit Information in Router Advertisement less than this + variable shall be ignored. + + Default: 1 + accept_ra_pinfo - BOOLEAN Learn Prefix Information in Router Advertisement. diff --git a/Makefile b/Makefile index 001375cfd815..06107f683bbe 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 1 -SUBLEVEL = 18 +SUBLEVEL = 19 EXTRAVERSION = NAME = Series 4800 diff --git a/arch/arm/common/icst.c b/arch/arm/common/icst.c index 2dc6da70ae59..d7ed252708c5 100644 --- a/arch/arm/common/icst.c +++ b/arch/arm/common/icst.c @@ -16,7 +16,7 @@ */ #include #include - +#include #include /* @@ -29,7 +29,11 @@ EXPORT_SYMBOL(icst525_s2div); unsigned long icst_hz(const struct icst_params *p, struct icst_vco vco) { - return p->ref * 2 * (vco.v + 8) / ((vco.r + 2) * p->s2div[vco.s]); + u64 dividend = p->ref * 2 * (u64)(vco.v + 8); + u32 divisor = (vco.r + 2) * p->s2div[vco.s]; + + do_div(dividend, divisor); + return (unsigned long)dividend; } EXPORT_SYMBOL(icst_hz); @@ -58,6 +62,7 @@ icst_hz_to_vco(const struct icst_params *p, unsigned long freq) if (f > p->vco_min && f <= p->vco_max) break; + i++; } while (i < 8); if (i >= 8) diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h index 6499d93ae68d..47bc45a67e9b 100644 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@ -101,10 +101,8 @@ static inline void syscall_get_arguments(struct task_struct *task, /* O32 ABI syscall() - Either 64-bit with O32 or 32-bit */ if ((config_enabled(CONFIG_32BIT) || test_tsk_thread_flag(task, TIF_32BIT_REGS)) && - (regs->regs[2] == __NR_syscall)) { + (regs->regs[2] == __NR_syscall)) i++; - n++; - } while (n--) ret |= mips_get_syscall_arg(args++, task, regs, i++); diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index a52db28ecc1e..4457cb605356 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -79,6 +79,7 @@ struct pci_dn; #define EEH_PE_KEEP (1 << 8) /* Keep PE on hotplug */ #define EEH_PE_CFG_RESTRICTED (1 << 9) /* Block config on error */ #define EEH_PE_REMOVED (1 << 10) /* Removed permanently */ +#define EEH_PE_PRI_BUS (1 << 11) /* Cached primary bus */ struct eeh_pe { int type; /* PE type: PHB/Bus/Device */ @@ -336,19 +337,13 @@ static inline int eeh_check_failure(const volatile void __iomem *token) #define eeh_dev_check_failure(x) (0) -static inline void eeh_addr_cache_build(void) { } - -static inline void eeh_add_device_early(struct pci_dn *pdn) { } - -static inline void eeh_add_device_tree_early(struct pci_dn *pdn) { } - -static inline void eeh_add_device_late(struct pci_dev *dev) { } - -static inline void eeh_add_device_tree_late(struct pci_bus *bus) { } - -static inline void eeh_add_sysfs_files(struct pci_bus *bus) { } - -static inline void eeh_remove_device(struct pci_dev *dev) { } +#define eeh_addr_cache_build() +#define eeh_add_device_early(pdn) +#define eeh_add_device_tree_early(pdn) +#define eeh_add_device_late(pdev) +#define eeh_add_device_tree_late(pbus) +#define eeh_add_sysfs_files(pbus) +#define eeh_remove_device(pdev) #define EEH_POSSIBLE_ERROR(val, type) (0) #define EEH_IO_ERROR_VALUE(size) (-1UL) diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 24768ff3cb73..90cc67904dc6 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -561,6 +561,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) */ eeh_pe_state_mark(pe, EEH_PE_KEEP); if (bus) { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); pci_lock_rescan_remove(); pcibios_remove_pci_devices(bus); pci_unlock_rescan_remove(); @@ -792,6 +793,7 @@ perm_error: * the their PCI config any more. */ if (frozen_bus) { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); pci_lock_rescan_remove(); @@ -875,6 +877,7 @@ static void eeh_handle_special_event(void) continue; /* Notify all devices to be down */ + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); bus = eeh_pe_bus_get(phb_pe); eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 22f6d954ef89..c3e0420b8a42 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -906,7 +906,7 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) bus = pe->phb->bus; } else if (pe->type & EEH_PE_BUS || pe->type & EEH_PE_DEVICE) { - if (pe->bus) { + if (pe->state & EEH_PE_PRI_BUS) { bus = pe->bus; goto out; } diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index ce738ab3d5a9..abb396876b9a 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -455,9 +455,12 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) * PCI devices of the PE are expected to be removed prior * to PE reset. */ - if (!edev->pe->bus) + if (!(edev->pe->state & EEH_PE_PRI_BUS)) { edev->pe->bus = pci_find_bus(hose->global_number, pdn->busno); + if (edev->pe->bus) + edev->pe->state |= EEH_PE_PRI_BUS; + } /* * Enable EEH explicitly so that we will do EEH check diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 181c53bac3a7..62855ac37ab7 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -285,6 +285,9 @@ static noinline int vmalloc_fault(unsigned long address) if (!pmd_k) return -1; + if (pmd_huge(*pmd_k)) + return 0; + pte_k = pte_offset_kernel(pmd_k, address); if (!pte_present(*pte_k)) return -1; @@ -356,8 +359,6 @@ void vmalloc_sync_all(void) * 64-bit: * * Handle a fault on the vmalloc area - * - * This assumes no large pages in there. */ static noinline int vmalloc_fault(unsigned long address) { @@ -399,17 +400,23 @@ static noinline int vmalloc_fault(unsigned long address) if (pud_none(*pud_ref)) return -1; - if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref)) + if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref)) BUG(); + if (pud_huge(*pud)) + return 0; + pmd = pmd_offset(pud, address); pmd_ref = pmd_offset(pud_ref, address); if (pmd_none(*pmd_ref)) return -1; - if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref)) + if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref)) BUG(); + if (pmd_huge(*pmd)) + return 0; + pte_ref = pte_offset_kernel(pmd_ref, address); if (!pte_present(*pte_ref)) return -1; diff --git a/block/bio.c b/block/bio.c index 4441522ca339..cbce3e2208f4 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1122,9 +1122,12 @@ int bio_uncopy_user(struct bio *bio) if (!bio_flagged(bio, BIO_NULL_MAPPED)) { /* * if we're in a workqueue, the request is orphaned, so - * don't copy into a random user address space, just free. + * don't copy into a random user address space, just free + * and return -EINTR so user space doesn't expect any data. */ - if (current->mm && bio_data_dir(bio) == READ) + if (!current->mm) + ret = -EINTR; + else if (bio_data_dir(bio) == READ) ret = bio_copy_to_iter(bio, bmd->iter); if (bmd->is_our_pages) bio_free_pages(bio); diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index 5bc42f9b23f0..c0f03562a145 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -31,6 +31,11 @@ struct skcipher_sg_list { struct scatterlist sg[0]; }; +struct skcipher_tfm { + struct crypto_ablkcipher *skcipher; + bool has_key; +}; + struct skcipher_ctx { struct list_head tsgl; struct af_alg_sgl rsgl; @@ -750,19 +755,139 @@ static struct proto_ops algif_skcipher_ops = { .poll = skcipher_poll, }; +static int skcipher_check_key(struct socket *sock) +{ + int err = 0; + struct sock *psk; + struct alg_sock *pask; + struct skcipher_tfm *tfm; + struct sock *sk = sock->sk; + struct alg_sock *ask = alg_sk(sk); + + lock_sock(sk); + if (ask->refcnt) + goto unlock_child; + + psk = ask->parent; + pask = alg_sk(ask->parent); + tfm = pask->private; + + err = -ENOKEY; + lock_sock_nested(psk, SINGLE_DEPTH_NESTING); + if (!tfm->has_key) + goto unlock; + + if (!pask->refcnt++) + sock_hold(psk); + + ask->refcnt = 1; + sock_put(psk); + + err = 0; + +unlock: + release_sock(psk); +unlock_child: + release_sock(sk); + + return err; +} + +static int skcipher_sendmsg_nokey(struct socket *sock, struct msghdr *msg, + size_t size) +{ + int err; + + err = skcipher_check_key(sock); + if (err) + return err; + + return skcipher_sendmsg(sock, msg, size); +} + +static ssize_t skcipher_sendpage_nokey(struct socket *sock, struct page *page, + int offset, size_t size, int flags) +{ + int err; + + err = skcipher_check_key(sock); + if (err) + return err; + + return skcipher_sendpage(sock, page, offset, size, flags); +} + +static int skcipher_recvmsg_nokey(struct socket *sock, struct msghdr *msg, + size_t ignored, int flags) +{ + int err; + + err = skcipher_check_key(sock); + if (err) + return err; + + return skcipher_recvmsg(sock, msg, ignored, flags); +} + +static struct proto_ops algif_skcipher_ops_nokey = { + .family = PF_ALG, + + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .getname = sock_no_getname, + .ioctl = sock_no_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .getsockopt = sock_no_getsockopt, + .mmap = sock_no_mmap, + .bind = sock_no_bind, + .accept = sock_no_accept, + .setsockopt = sock_no_setsockopt, + + .release = af_alg_release, + .sendmsg = skcipher_sendmsg_nokey, + .sendpage = skcipher_sendpage_nokey, + .recvmsg = skcipher_recvmsg_nokey, + .poll = skcipher_poll, +}; + static void *skcipher_bind(const char *name, u32 type, u32 mask) { - return crypto_alloc_ablkcipher(name, type, mask); + struct skcipher_tfm *tfm; + struct crypto_ablkcipher *skcipher; + + tfm = kzalloc(sizeof(*tfm), GFP_KERNEL); + if (!tfm) + return ERR_PTR(-ENOMEM); + + skcipher = crypto_alloc_ablkcipher(name, type, mask); + if (IS_ERR(skcipher)) { + kfree(tfm); + return ERR_CAST(skcipher); + } + + tfm->skcipher = skcipher; + + return tfm; } static void skcipher_release(void *private) { - crypto_free_ablkcipher(private); + struct skcipher_tfm *tfm = private; + + crypto_free_ablkcipher(tfm->skcipher); + kfree(tfm); } static int skcipher_setkey(void *private, const u8 *key, unsigned int keylen) { - return crypto_ablkcipher_setkey(private, key, keylen); + struct skcipher_tfm *tfm = private; + int err; + + err = crypto_ablkcipher_setkey(tfm->skcipher, key, keylen); + tfm->has_key = !err; + + return err; } static void skcipher_wait(struct sock *sk) @@ -790,24 +915,26 @@ static void skcipher_sock_destruct(struct sock *sk) af_alg_release_parent(sk); } -static int skcipher_accept_parent(void *private, struct sock *sk) +static int skcipher_accept_parent_nokey(void *private, struct sock *sk) { struct skcipher_ctx *ctx; struct alg_sock *ask = alg_sk(sk); - unsigned int len = sizeof(*ctx) + crypto_ablkcipher_reqsize(private); + struct skcipher_tfm *tfm = private; + struct crypto_ablkcipher *skcipher = tfm->skcipher; + unsigned int len = sizeof(*ctx) + crypto_ablkcipher_reqsize(skcipher); ctx = sock_kmalloc(sk, len, GFP_KERNEL); if (!ctx) return -ENOMEM; - ctx->iv = sock_kmalloc(sk, crypto_ablkcipher_ivsize(private), + ctx->iv = sock_kmalloc(sk, crypto_ablkcipher_ivsize(skcipher), GFP_KERNEL); if (!ctx->iv) { sock_kfree_s(sk, ctx, len); return -ENOMEM; } - memset(ctx->iv, 0, crypto_ablkcipher_ivsize(private)); + memset(ctx->iv, 0, crypto_ablkcipher_ivsize(skcipher)); INIT_LIST_HEAD(&ctx->tsgl); ctx->len = len; @@ -820,7 +947,7 @@ static int skcipher_accept_parent(void *private, struct sock *sk) ask->private = ctx; - ablkcipher_request_set_tfm(&ctx->req, private); + ablkcipher_request_set_tfm(&ctx->req, skcipher); ablkcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG, af_alg_complete, &ctx->completion); @@ -829,12 +956,24 @@ static int skcipher_accept_parent(void *private, struct sock *sk) return 0; } +static int skcipher_accept_parent(void *private, struct sock *sk) +{ + struct skcipher_tfm *tfm = private; + + if (!tfm->has_key) + return -ENOKEY; + + return skcipher_accept_parent_nokey(private, sk); +} + static const struct af_alg_type algif_type_skcipher = { .bind = skcipher_bind, .release = skcipher_release, .setkey = skcipher_setkey, .accept = skcipher_accept_parent, + .accept_nokey = skcipher_accept_parent_nokey, .ops = &algif_skcipher_ops, + .ops_nokey = &algif_skcipher_ops_nokey, .name = "skcipher", .owner = THIS_MODULE }; diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c index edf2e3ea1740..6a050e12fcdf 100644 --- a/crypto/crypto_user.c +++ b/crypto/crypto_user.c @@ -499,6 +499,7 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (link->dump == NULL) return -EINVAL; + down_read(&crypto_alg_sem); list_for_each_entry(alg, &crypto_alg_list, cra_list) dump_alloc += CRYPTO_REPORT_MAXSIZE; @@ -508,8 +509,11 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) .done = link->done, .min_dump_alloc = dump_alloc, }; - return netlink_dump_start(crypto_nlsk, skb, nlh, &c); + err = netlink_dump_start(crypto_nlsk, skb, nlh, &c); } + up_read(&crypto_alg_sem); + + return err; } err = nlmsg_parse(nlh, crypto_msg_min[type], attrs, CRYPTOCFGA_MAX, diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index e6ea912aee31..666fd8a1500a 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -262,6 +262,26 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x3b2b), board_ahci }, /* PCH RAID */ { PCI_VDEVICE(INTEL, 0x3b2c), board_ahci }, /* PCH RAID */ { PCI_VDEVICE(INTEL, 0x3b2f), board_ahci }, /* PCH AHCI */ + { PCI_VDEVICE(INTEL, 0x19b0), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b1), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b2), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b3), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b4), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b5), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b6), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b7), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19bE), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19bF), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c0), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c1), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c2), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c3), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c4), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c5), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c6), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c7), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19cE), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19cF), board_ahci }, /* DNV AHCI */ { PCI_VDEVICE(INTEL, 0x1c02), board_ahci }, /* CPT AHCI */ { PCI_VDEVICE(INTEL, 0x1c03), board_ahci }, /* CPT AHCI */ { PCI_VDEVICE(INTEL, 0x1c04), board_ahci }, /* CPT RAID */ diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 287c4ba0219f..49840264dd57 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -495,8 +495,8 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv) } } - /* fabricate port_map from cap.nr_ports */ - if (!port_map) { + /* fabricate port_map from cap.nr_ports for < AHCI 1.3 */ + if (!port_map && vers < 0x10300) { port_map = (1 << ahci_nr_ports(cap)) - 1; dev_warn(dev, "forcing PORTS_IMPL to 0x%x\n", port_map); diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index cdf6215a9a22..7dbba387d12a 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -997,12 +997,9 @@ static inline int ata_hsm_ok_in_wq(struct ata_port *ap, static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq) { struct ata_port *ap = qc->ap; - unsigned long flags; if (ap->ops->error_handler) { if (in_wq) { - spin_lock_irqsave(ap->lock, flags); - /* EH might have kicked in while host lock is * released. */ @@ -1014,8 +1011,6 @@ static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq) } else ata_port_freeze(ap); } - - spin_unlock_irqrestore(ap->lock, flags); } else { if (likely(!(qc->err_mask & AC_ERR_HSM))) ata_qc_complete(qc); @@ -1024,10 +1019,8 @@ static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq) } } else { if (in_wq) { - spin_lock_irqsave(ap->lock, flags); ata_sff_irq_on(ap); ata_qc_complete(qc); - spin_unlock_irqrestore(ap->lock, flags); } else ata_qc_complete(qc); } @@ -1048,9 +1041,10 @@ int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc, { struct ata_link *link = qc->dev->link; struct ata_eh_info *ehi = &link->eh_info; - unsigned long flags = 0; int poll_next; + lockdep_assert_held(ap->lock); + WARN_ON_ONCE((qc->flags & ATA_QCFLAG_ACTIVE) == 0); /* Make sure ata_sff_qc_issue() does not throw things @@ -1112,14 +1106,6 @@ fsm_start: } } - /* Send the CDB (atapi) or the first data block (ata pio out). - * During the state transition, interrupt handler shouldn't - * be invoked before the data transfer is complete and - * hsm_task_state is changed. Hence, the following locking. - */ - if (in_wq) - spin_lock_irqsave(ap->lock, flags); - if (qc->tf.protocol == ATA_PROT_PIO) { /* PIO data out protocol. * send first data block. @@ -1135,9 +1121,6 @@ fsm_start: /* send CDB */ atapi_send_cdb(ap, qc); - if (in_wq) - spin_unlock_irqrestore(ap->lock, flags); - /* if polling, ata_sff_pio_task() handles the rest. * otherwise, interrupt handler takes over from here. */ @@ -1361,12 +1344,14 @@ static void ata_sff_pio_task(struct work_struct *work) u8 status; int poll_next; + spin_lock_irq(ap->lock); + BUG_ON(ap->sff_pio_task_link == NULL); /* qc can be NULL if timeout occurred */ qc = ata_qc_from_tag(ap, link->active_tag); if (!qc) { ap->sff_pio_task_link = NULL; - return; + goto out_unlock; } fsm_start: @@ -1381,11 +1366,14 @@ fsm_start: */ status = ata_sff_busy_wait(ap, ATA_BUSY, 5); if (status & ATA_BUSY) { + spin_unlock_irq(ap->lock); ata_msleep(ap, 2); + spin_lock_irq(ap->lock); + status = ata_sff_busy_wait(ap, ATA_BUSY, 10); if (status & ATA_BUSY) { ata_sff_queue_pio_task(link, ATA_SHORT_PAUSE); - return; + goto out_unlock; } } @@ -1402,6 +1390,8 @@ fsm_start: */ if (poll_next) goto fsm_start; +out_unlock: + spin_unlock_irq(ap->lock); } /** diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c index 0f9a9dc06a83..fb16d812c8f5 100644 --- a/drivers/crypto/atmel-aes.c +++ b/drivers/crypto/atmel-aes.c @@ -260,7 +260,11 @@ static struct atmel_aes_dev *atmel_aes_find_dev(struct atmel_aes_ctx *ctx) static int atmel_aes_hw_init(struct atmel_aes_dev *dd) { - clk_prepare_enable(dd->iclk); + int err; + + err = clk_prepare_enable(dd->iclk); + if (err) + return err; if (!(dd->flags & AES_FLAGS_INIT)) { atmel_aes_write(dd, AES_CR, AES_CR_SWRST); @@ -1320,7 +1324,6 @@ static int atmel_aes_probe(struct platform_device *pdev) struct crypto_platform_data *pdata; struct device *dev = &pdev->dev; struct resource *aes_res; - unsigned long aes_phys_size; int err; pdata = pdev->dev.platform_data; @@ -1337,7 +1340,7 @@ static int atmel_aes_probe(struct platform_device *pdev) goto aes_dd_err; } - aes_dd = kzalloc(sizeof(struct atmel_aes_dev), GFP_KERNEL); + aes_dd = devm_kzalloc(&pdev->dev, sizeof(*aes_dd), GFP_KERNEL); if (aes_dd == NULL) { dev_err(dev, "unable to alloc data struct.\n"); err = -ENOMEM; @@ -1368,36 +1371,35 @@ static int atmel_aes_probe(struct platform_device *pdev) goto res_err; } aes_dd->phys_base = aes_res->start; - aes_phys_size = resource_size(aes_res); /* Get the IRQ */ aes_dd->irq = platform_get_irq(pdev, 0); if (aes_dd->irq < 0) { dev_err(dev, "no IRQ resource info\n"); err = aes_dd->irq; - goto aes_irq_err; + goto res_err; } - err = request_irq(aes_dd->irq, atmel_aes_irq, IRQF_SHARED, "atmel-aes", - aes_dd); + err = devm_request_irq(&pdev->dev, aes_dd->irq, atmel_aes_irq, + IRQF_SHARED, "atmel-aes", aes_dd); if (err) { dev_err(dev, "unable to request aes irq.\n"); - goto aes_irq_err; + goto res_err; } /* Initializing the clock */ - aes_dd->iclk = clk_get(&pdev->dev, "aes_clk"); + aes_dd->iclk = devm_clk_get(&pdev->dev, "aes_clk"); if (IS_ERR(aes_dd->iclk)) { dev_err(dev, "clock initialization failed.\n"); err = PTR_ERR(aes_dd->iclk); - goto clk_err; + goto res_err; } - aes_dd->io_base = ioremap(aes_dd->phys_base, aes_phys_size); + aes_dd->io_base = devm_ioremap_resource(&pdev->dev, aes_res); if (!aes_dd->io_base) { dev_err(dev, "can't ioremap\n"); err = -ENOMEM; - goto aes_io_err; + goto res_err; } atmel_aes_hw_version_init(aes_dd); @@ -1434,17 +1436,9 @@ err_algs: err_aes_dma: atmel_aes_buff_cleanup(aes_dd); err_aes_buff: - iounmap(aes_dd->io_base); -aes_io_err: - clk_put(aes_dd->iclk); -clk_err: - free_irq(aes_dd->irq, aes_dd); -aes_irq_err: res_err: tasklet_kill(&aes_dd->done_task); tasklet_kill(&aes_dd->queue_task); - kfree(aes_dd); - aes_dd = NULL; aes_dd_err: dev_err(dev, "initialization failed.\n"); @@ -1469,16 +1463,6 @@ static int atmel_aes_remove(struct platform_device *pdev) atmel_aes_dma_cleanup(aes_dd); - iounmap(aes_dd->io_base); - - clk_put(aes_dd->iclk); - - if (aes_dd->irq > 0) - free_irq(aes_dd->irq, aes_dd); - - kfree(aes_dd); - aes_dd = NULL; - return 0; } diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c index 5b35433c5399..a71c97c03c39 100644 --- a/drivers/crypto/atmel-sha.c +++ b/drivers/crypto/atmel-sha.c @@ -783,7 +783,7 @@ static void atmel_sha_finish_req(struct ahash_request *req, int err) dd->flags &= ~(SHA_FLAGS_BUSY | SHA_FLAGS_FINAL | SHA_FLAGS_CPU | SHA_FLAGS_DMA_READY | SHA_FLAGS_OUTPUT_READY); - clk_disable_unprepare(dd->iclk); + clk_disable(dd->iclk); if (req->base.complete) req->base.complete(&req->base, err); @@ -794,7 +794,11 @@ static void atmel_sha_finish_req(struct ahash_request *req, int err) static int atmel_sha_hw_init(struct atmel_sha_dev *dd) { - clk_prepare_enable(dd->iclk); + int err; + + err = clk_enable(dd->iclk); + if (err) + return err; if (!(SHA_FLAGS_INIT & dd->flags)) { atmel_sha_write(dd, SHA_CR, SHA_CR_SWRST); @@ -819,7 +823,7 @@ static void atmel_sha_hw_version_init(struct atmel_sha_dev *dd) dev_info(dd->dev, "version: 0x%x\n", dd->hw_version); - clk_disable_unprepare(dd->iclk); + clk_disable(dd->iclk); } static int atmel_sha_handle_queue(struct atmel_sha_dev *dd, @@ -1345,11 +1349,9 @@ static int atmel_sha_probe(struct platform_device *pdev) struct crypto_platform_data *pdata; struct device *dev = &pdev->dev; struct resource *sha_res; - unsigned long sha_phys_size; int err; - sha_dd = devm_kzalloc(&pdev->dev, sizeof(struct atmel_sha_dev), - GFP_KERNEL); + sha_dd = devm_kzalloc(&pdev->dev, sizeof(*sha_dd), GFP_KERNEL); if (sha_dd == NULL) { dev_err(dev, "unable to alloc data struct.\n"); err = -ENOMEM; @@ -1378,7 +1380,6 @@ static int atmel_sha_probe(struct platform_device *pdev) goto res_err; } sha_dd->phys_base = sha_res->start; - sha_phys_size = resource_size(sha_res); /* Get the IRQ */ sha_dd->irq = platform_get_irq(pdev, 0); @@ -1388,28 +1389,32 @@ static int atmel_sha_probe(struct platform_device *pdev) goto res_err; } - err = request_irq(sha_dd->irq, atmel_sha_irq, IRQF_SHARED, "atmel-sha", - sha_dd); + err = devm_request_irq(&pdev->dev, sha_dd->irq, atmel_sha_irq, + IRQF_SHARED, "atmel-sha", sha_dd); if (err) { dev_err(dev, "unable to request sha irq.\n"); goto res_err; } /* Initializing the clock */ - sha_dd->iclk = clk_get(&pdev->dev, "sha_clk"); + sha_dd->iclk = devm_clk_get(&pdev->dev, "sha_clk"); if (IS_ERR(sha_dd->iclk)) { dev_err(dev, "clock initialization failed.\n"); err = PTR_ERR(sha_dd->iclk); - goto clk_err; + goto res_err; } - sha_dd->io_base = ioremap(sha_dd->phys_base, sha_phys_size); + sha_dd->io_base = devm_ioremap_resource(&pdev->dev, sha_res); if (!sha_dd->io_base) { dev_err(dev, "can't ioremap\n"); err = -ENOMEM; - goto sha_io_err; + goto res_err; } + err = clk_prepare(sha_dd->iclk); + if (err) + goto res_err; + atmel_sha_hw_version_init(sha_dd); atmel_sha_get_cap(sha_dd); @@ -1421,12 +1426,12 @@ static int atmel_sha_probe(struct platform_device *pdev) if (IS_ERR(pdata)) { dev_err(&pdev->dev, "platform data not available\n"); err = PTR_ERR(pdata); - goto err_pdata; + goto iclk_unprepare; } } if (!pdata->dma_slave) { err = -ENXIO; - goto err_pdata; + goto iclk_unprepare; } err = atmel_sha_dma_init(sha_dd, pdata); if (err) @@ -1457,12 +1462,8 @@ err_algs: if (sha_dd->caps.has_dma) atmel_sha_dma_cleanup(sha_dd); err_sha_dma: -err_pdata: - iounmap(sha_dd->io_base); -sha_io_err: - clk_put(sha_dd->iclk); -clk_err: - free_irq(sha_dd->irq, sha_dd); +iclk_unprepare: + clk_unprepare(sha_dd->iclk); res_err: tasklet_kill(&sha_dd->done_task); sha_dd_err: @@ -1489,6 +1490,8 @@ static int atmel_sha_remove(struct platform_device *pdev) if (sha_dd->caps.has_dma) atmel_sha_dma_cleanup(sha_dd); + clk_unprepare(sha_dd->iclk); + iounmap(sha_dd->io_base); clk_put(sha_dd->iclk); diff --git a/drivers/crypto/atmel-tdes.c b/drivers/crypto/atmel-tdes.c index ca2999709eb4..2c7a628d0375 100644 --- a/drivers/crypto/atmel-tdes.c +++ b/drivers/crypto/atmel-tdes.c @@ -218,7 +218,11 @@ static struct atmel_tdes_dev *atmel_tdes_find_dev(struct atmel_tdes_ctx *ctx) static int atmel_tdes_hw_init(struct atmel_tdes_dev *dd) { - clk_prepare_enable(dd->iclk); + int err; + + err = clk_prepare_enable(dd->iclk); + if (err) + return err; if (!(dd->flags & TDES_FLAGS_INIT)) { atmel_tdes_write(dd, TDES_CR, TDES_CR_SWRST); @@ -1355,7 +1359,6 @@ static int atmel_tdes_probe(struct platform_device *pdev) struct crypto_platform_data *pdata; struct device *dev = &pdev->dev; struct resource *tdes_res; - unsigned long tdes_phys_size; int err; tdes_dd = devm_kmalloc(&pdev->dev, sizeof(*tdes_dd), GFP_KERNEL); @@ -1389,7 +1392,6 @@ static int atmel_tdes_probe(struct platform_device *pdev) goto res_err; } tdes_dd->phys_base = tdes_res->start; - tdes_phys_size = resource_size(tdes_res); /* Get the IRQ */ tdes_dd->irq = platform_get_irq(pdev, 0); @@ -1399,26 +1401,26 @@ static int atmel_tdes_probe(struct platform_device *pdev) goto res_err; } - err = request_irq(tdes_dd->irq, atmel_tdes_irq, IRQF_SHARED, - "atmel-tdes", tdes_dd); + err = devm_request_irq(&pdev->dev, tdes_dd->irq, atmel_tdes_irq, + IRQF_SHARED, "atmel-tdes", tdes_dd); if (err) { dev_err(dev, "unable to request tdes irq.\n"); - goto tdes_irq_err; + goto res_err; } /* Initializing the clock */ - tdes_dd->iclk = clk_get(&pdev->dev, "tdes_clk"); + tdes_dd->iclk = devm_clk_get(&pdev->dev, "tdes_clk"); if (IS_ERR(tdes_dd->iclk)) { dev_err(dev, "clock initialization failed.\n"); err = PTR_ERR(tdes_dd->iclk); - goto clk_err; + goto res_err; } - tdes_dd->io_base = ioremap(tdes_dd->phys_base, tdes_phys_size); + tdes_dd->io_base = devm_ioremap_resource(&pdev->dev, tdes_res); if (!tdes_dd->io_base) { dev_err(dev, "can't ioremap\n"); err = -ENOMEM; - goto tdes_io_err; + goto res_err; } atmel_tdes_hw_version_init(tdes_dd); @@ -1474,12 +1476,6 @@ err_tdes_dma: err_pdata: atmel_tdes_buff_cleanup(tdes_dd); err_tdes_buff: - iounmap(tdes_dd->io_base); -tdes_io_err: - clk_put(tdes_dd->iclk); -clk_err: - free_irq(tdes_dd->irq, tdes_dd); -tdes_irq_err: res_err: tasklet_kill(&tdes_dd->done_task); tasklet_kill(&tdes_dd->queue_task); @@ -1510,13 +1506,6 @@ static int atmel_tdes_remove(struct platform_device *pdev) atmel_tdes_buff_cleanup(tdes_dd); - iounmap(tdes_dd->io_base); - - clk_put(tdes_dd->iclk); - - if (tdes_dd->irq >= 0) - free_irq(tdes_dd->irq, tdes_dd); - return 0; } diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index 303d937d63c7..ebffc744cb1b 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -156,7 +156,6 @@ static void dwc_initialize(struct dw_dma_chan *dwc) /* Enable interrupts */ channel_set_bit(dw, MASK.XFER, dwc->mask); - channel_set_bit(dw, MASK.BLOCK, dwc->mask); channel_set_bit(dw, MASK.ERROR, dwc->mask); dwc->initialized = true; @@ -588,6 +587,9 @@ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc, spin_unlock_irqrestore(&dwc->lock, flags); } + + /* Re-enable interrupts */ + channel_set_bit(dw, MASK.BLOCK, dwc->mask); } /* ------------------------------------------------------------------------- */ @@ -618,11 +620,8 @@ static void dw_dma_tasklet(unsigned long data) dwc_scan_descriptors(dw, dwc); } - /* - * Re-enable interrupts. - */ + /* Re-enable interrupts */ channel_set_bit(dw, MASK.XFER, dw->all_chan_mask); - channel_set_bit(dw, MASK.BLOCK, dw->all_chan_mask); channel_set_bit(dw, MASK.ERROR, dw->all_chan_mask); } @@ -1256,6 +1255,7 @@ static void dwc_free_chan_resources(struct dma_chan *chan) int dw_dma_cyclic_start(struct dma_chan *chan) { struct dw_dma_chan *dwc = to_dw_dma_chan(chan); + struct dw_dma *dw = to_dw_dma(chan->device); unsigned long flags; if (!test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) { @@ -1264,7 +1264,12 @@ int dw_dma_cyclic_start(struct dma_chan *chan) } spin_lock_irqsave(&dwc->lock, flags); + + /* Enable interrupts to perform cyclic transfer */ + channel_set_bit(dw, MASK.BLOCK, dwc->mask); + dwc_dostart(dwc, dwc->cdesc->desc[0]); + spin_unlock_irqrestore(&dwc->lock, flags); return 0; diff --git a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c index d2cd8d5b27a1..82f8e20cca74 100644 --- a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c +++ b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c @@ -207,7 +207,12 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) gpio = *data++; /* pull up/down */ - action = *data++; + action = *data++ & 1; + + if (gpio >= ARRAY_SIZE(gtable)) { + DRM_DEBUG_KMS("unknown gpio %u\n", gpio); + goto out; + } function = gtable[gpio].function_reg; pad = gtable[gpio].pad_reg; @@ -226,6 +231,7 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) vlv_gpio_nc_write(dev_priv, pad, val); mutex_unlock(&dev_priv->dpio_lock); +out: return data; } diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c index 7354a4cda59d..3aefaa058f0c 100644 --- a/drivers/gpu/drm/qxl/qxl_ioctl.c +++ b/drivers/gpu/drm/qxl/qxl_ioctl.c @@ -168,7 +168,8 @@ static int qxl_process_single_command(struct qxl_device *qdev, cmd->command_size)) return -EFAULT; - reloc_info = kmalloc(sizeof(struct qxl_reloc_info) * cmd->relocs_num, GFP_KERNEL); + reloc_info = kmalloc_array(cmd->relocs_num, + sizeof(struct qxl_reloc_info), GFP_KERNEL); if (!reloc_info) return -ENOMEM; diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c index c507896aca45..197b157b73d0 100644 --- a/drivers/gpu/drm/radeon/radeon_sa.c +++ b/drivers/gpu/drm/radeon/radeon_sa.c @@ -349,8 +349,13 @@ int radeon_sa_bo_new(struct radeon_device *rdev, /* see if we can skip over some allocations */ } while (radeon_sa_bo_next_hole(sa_manager, fences, tries)); + for (i = 0; i < RADEON_NUM_RINGS; ++i) + radeon_fence_ref(fences[i]); + spin_unlock(&sa_manager->wq.lock); r = radeon_fence_wait_any(rdev, fences, false); + for (i = 0; i < RADEON_NUM_RINGS; ++i) + radeon_fence_unref(&fences[i]); spin_lock(&sa_manager->wq.lock); /* if we have nothing to wait for block */ if (r == -ENOENT) { diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index edafd3c2b170..f5c0590bbf73 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -758,7 +758,7 @@ static int radeon_ttm_tt_populate(struct ttm_tt *ttm) 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); if (pci_dma_mapping_error(rdev->pdev, gtt->ttm.dma_address[i])) { - while (--i) { + while (i--) { pci_unmap_page(rdev->pdev, gtt->ttm.dma_address[i], PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); gtt->ttm.dma_address[i] = 0; diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index c32a934f7693..353e2ab090ee 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -1349,7 +1349,7 @@ sequence_cmd: if (!rc && dump_payload == false && unsol_data) iscsit_set_unsoliticed_dataout(cmd); else if (dump_payload && imm_data) - target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd); + target_put_sess_cmd(&cmd->se_cmd); return 0; } @@ -1774,7 +1774,7 @@ isert_put_cmd(struct isert_cmd *isert_cmd, bool comp_err) cmd->se_cmd.t_state == TRANSPORT_WRITE_PENDING) { struct se_cmd *se_cmd = &cmd->se_cmd; - target_put_sess_cmd(se_cmd->se_sess, se_cmd); + target_put_sess_cmd(se_cmd); } } @@ -1947,7 +1947,7 @@ isert_completion_rdma_read(struct iser_tx_desc *tx_desc, spin_unlock_bh(&cmd->istate_lock); if (ret) { - target_put_sess_cmd(se_cmd->se_sess, se_cmd); + target_put_sess_cmd(se_cmd); transport_send_check_condition_and_sense(se_cmd, se_cmd->pi_err, 0); } else { diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 9b84b4c0a000..6fbc7bc824d2 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -1334,7 +1334,7 @@ static int srpt_abort_cmd(struct srpt_send_ioctx *ioctx) BUG_ON(ch->sess == NULL); - target_put_sess_cmd(ch->sess, &ioctx->cmd); + target_put_sess_cmd(&ioctx->cmd); goto out; } @@ -1365,11 +1365,11 @@ static int srpt_abort_cmd(struct srpt_send_ioctx *ioctx) * not been received in time. */ srpt_unmap_sg_to_ib_sge(ioctx->ch, ioctx); - target_put_sess_cmd(ioctx->ch->sess, &ioctx->cmd); + target_put_sess_cmd(&ioctx->cmd); break; case SRPT_STATE_MGMT_RSP_SENT: srpt_set_cmd_state(ioctx, SRPT_STATE_DONE); - target_put_sess_cmd(ioctx->ch->sess, &ioctx->cmd); + target_put_sess_cmd(&ioctx->cmd); break; default: WARN(1, "Unexpected command state (%d)", state); @@ -1679,7 +1679,7 @@ static int srpt_check_stop_free(struct se_cmd *cmd) struct srpt_send_ioctx *ioctx = container_of(cmd, struct srpt_send_ioctx, cmd); - return target_put_sess_cmd(ioctx->ch->sess, &ioctx->cmd); + return target_put_sess_cmd(&ioctx->cmd); } /** @@ -3074,7 +3074,7 @@ static void srpt_queue_response(struct se_cmd *cmd) ioctx->tag); srpt_unmap_sg_to_ib_sge(ch, ioctx); srpt_set_cmd_state(ioctx, SRPT_STATE_DONE); - target_put_sess_cmd(ioctx->ch->sess, &ioctx->cmd); + target_put_sess_cmd(&ioctx->cmd); } } diff --git a/drivers/input/mouse/vmmouse.c b/drivers/input/mouse/vmmouse.c index e272f06258ce..a3f0f5a47490 100644 --- a/drivers/input/mouse/vmmouse.c +++ b/drivers/input/mouse/vmmouse.c @@ -458,8 +458,6 @@ int vmmouse_init(struct psmouse *psmouse) priv->abs_dev = abs_dev; psmouse->private = priv; - input_set_capability(rel_dev, EV_REL, REL_WHEEL); - /* Set up and register absolute device */ snprintf(priv->phys, sizeof(priv->phys), "%s/input1", psmouse->ps2dev.serio->phys); @@ -475,10 +473,6 @@ int vmmouse_init(struct psmouse *psmouse) abs_dev->id.version = psmouse->model; abs_dev->dev.parent = &psmouse->ps2dev.serio->dev; - error = input_register_device(priv->abs_dev); - if (error) - goto init_fail; - /* Set absolute device capabilities */ input_set_capability(abs_dev, EV_KEY, BTN_LEFT); input_set_capability(abs_dev, EV_KEY, BTN_RIGHT); @@ -488,6 +482,13 @@ int vmmouse_init(struct psmouse *psmouse) input_set_abs_params(abs_dev, ABS_X, 0, VMMOUSE_MAX_X, 0, 0); input_set_abs_params(abs_dev, ABS_Y, 0, VMMOUSE_MAX_Y, 0, 0); + error = input_register_device(priv->abs_dev); + if (error) + goto init_fail; + + /* Add wheel capability to the relative device */ + input_set_capability(rel_dev, EV_REL, REL_WHEEL); + psmouse->protocol_handler = vmmouse_process_byte; psmouse->disconnect = vmmouse_disconnect; psmouse->reconnect = vmmouse_reconnect; diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 9847613085e1..5a2ec39e1fd9 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -1342,7 +1342,7 @@ void dmar_disable_qi(struct intel_iommu *iommu) raw_spin_lock_irqsave(&iommu->register_lock, flags); - sts = dmar_readq(iommu->reg + DMAR_GSTS_REG); + sts = readl(iommu->reg + DMAR_GSTS_REG); if (!(sts & DMA_GSTS_QIES)) goto end; diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index 5709ae9c3e77..04b39be8f1f3 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -544,7 +544,7 @@ static void iommu_disable_irq_remapping(struct intel_iommu *iommu) raw_spin_lock_irqsave(&iommu->register_lock, flags); - sts = dmar_readq(iommu->reg + DMAR_GSTS_REG); + sts = readl(iommu->reg + DMAR_GSTS_REG); if (!(sts & DMA_GSTS_IRES)) goto end; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 72ba774df7a7..bd744e31c434 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -214,6 +214,8 @@ static void bond_uninit(struct net_device *bond_dev); static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats); static void bond_slave_arr_handler(struct work_struct *work); +static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act, + int mod); /*---------------------------- General routines -----------------------------*/ @@ -2397,7 +2399,7 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave) { struct arphdr *arp = (struct arphdr *)skb->data; - struct slave *curr_active_slave; + struct slave *curr_active_slave, *curr_arp_slave; unsigned char *arp_ptr; __be32 sip, tip; int alen, is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP); @@ -2444,26 +2446,41 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, &sip, &tip); curr_active_slave = rcu_dereference(bond->curr_active_slave); + curr_arp_slave = rcu_dereference(bond->current_arp_slave); - /* Backup slaves won't see the ARP reply, but do come through - * here for each ARP probe (so we swap the sip/tip to validate - * the probe). In a "redundant switch, common router" type of - * configuration, the ARP probe will (hopefully) travel from - * the active, through one switch, the router, then the other - * switch before reaching the backup. + /* We 'trust' the received ARP enough to validate it if: + * + * (a) the slave receiving the ARP is active (which includes the + * current ARP slave, if any), or + * + * (b) the receiving slave isn't active, but there is a currently + * active slave and it received valid arp reply(s) after it became + * the currently active slave, or + * + * (c) there is an ARP slave that sent an ARP during the prior ARP + * interval, and we receive an ARP reply on any slave. We accept + * these because switch FDB update delays may deliver the ARP + * reply to a slave other than the sender of the ARP request. * - * We 'trust' the arp requests if there is an active slave and - * it received valid arp reply(s) after it became active. This - * is done to avoid endless looping when we can't reach the + * Note: for (b), backup slaves are receiving the broadcast ARP + * request, not a reply. This request passes from the sending + * slave through the L2 switch(es) to the receiving slave. Since + * this is checking the request, sip/tip are swapped for + * validation. + * + * This is done to avoid endless looping when we can't reach the * arp_ip_target and fool ourselves with our own arp requests. */ - if (bond_is_active_slave(slave)) bond_validate_arp(bond, slave, sip, tip); else if (curr_active_slave && time_after(slave_last_rx(bond, curr_active_slave), curr_active_slave->last_link_up)) bond_validate_arp(bond, slave, tip, sip); + else if (curr_arp_slave && (arp->ar_op == htons(ARPOP_REPLY)) && + bond_time_in_interval(bond, + dev_trans_start(curr_arp_slave->dev), 1)) + bond_validate_arp(bond, slave, sip, tip); out_unlock: if (arp != (struct arphdr *)skb->data) diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 0d8af5bb5907..d5415205779f 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -7833,6 +7833,14 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi, return ret; } +static bool tg3_tso_bug_gso_check(struct tg3_napi *tnapi, struct sk_buff *skb) +{ + /* Check if we will never have enough descriptors, + * as gso_segs can be more than current ring size + */ + return skb_shinfo(skb)->gso_segs < tnapi->tx_pending / 3; +} + static netdev_tx_t tg3_start_xmit(struct sk_buff *, struct net_device *); /* Use GSO to workaround all TSO packets that meet HW bug conditions @@ -7936,14 +7944,19 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) * vlan encapsulated. */ if (skb->protocol == htons(ETH_P_8021Q) || - skb->protocol == htons(ETH_P_8021AD)) - return tg3_tso_bug(tp, tnapi, txq, skb); + skb->protocol == htons(ETH_P_8021AD)) { + if (tg3_tso_bug_gso_check(tnapi, skb)) + return tg3_tso_bug(tp, tnapi, txq, skb); + goto drop; + } if (!skb_is_gso_v6(skb)) { if (unlikely((ETH_HLEN + hdr_len) > 80) && - tg3_flag(tp, TSO_BUG)) - return tg3_tso_bug(tp, tnapi, txq, skb); - + tg3_flag(tp, TSO_BUG)) { + if (tg3_tso_bug_gso_check(tnapi, skb)) + return tg3_tso_bug(tp, tnapi, txq, skb); + goto drop; + } ip_csum = iph->check; ip_tot_len = iph->tot_len; iph->check = 0; @@ -8075,7 +8088,7 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) if (would_hit_hwbug) { tg3_tx_skb_unmap(tnapi, tnapi->tx_prod, i); - if (mss) { + if (mss && tg3_tso_bug_gso_check(tnapi, skb)) { /* If it's a TSO packet, do GSO instead of * allocating and copying to a large linear SKB */ diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c index 8a083d73efdb..dae2ebb53af7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c @@ -236,6 +236,24 @@ static const struct ptp_clock_info mlx4_en_ptp_clock_info = { .enable = mlx4_en_phc_enable, }; +#define MLX4_EN_WRAP_AROUND_SEC 10ULL + +/* This function calculates the max shift that enables the user range + * of MLX4_EN_WRAP_AROUND_SEC values in the cycles register. + */ +static u32 freq_to_shift(u16 freq) +{ + u32 freq_khz = freq * 1000; + u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC; + u64 max_val_cycles_rounded = is_power_of_2(max_val_cycles + 1) ? + max_val_cycles : roundup_pow_of_two(max_val_cycles) - 1; + /* calculate max possible multiplier in order to fit in 64bit */ + u64 max_mul = div_u64(0xffffffffffffffffULL, max_val_cycles_rounded); + + /* This comes from the reverse of clocksource_khz2mult */ + return ilog2(div_u64(max_mul * freq_khz, 1000000)); +} + void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev) { struct mlx4_dev *dev = mdev->dev; @@ -247,12 +265,7 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev) memset(&mdev->cycles, 0, sizeof(mdev->cycles)); mdev->cycles.read = mlx4_en_read_clock; mdev->cycles.mask = CLOCKSOURCE_MASK(48); - /* Using shift to make calculation more accurate. Since current HW - * clock frequency is 427 MHz, and cycles are given using a 48 bits - * register, the biggest shift when calculating using u64, is 14 - * (max_cycles * multiplier < 2^64) - */ - mdev->cycles.shift = 14; + mdev->cycles.shift = freq_to_shift(dev->caps.hca_core_clock); mdev->cycles.mult = clocksource_khz2mult(1000 * dev->caps.hca_core_clock, mdev->cycles.shift); mdev->nominal_c_mult = mdev->cycles.mult; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index a5a0b8420d26..e9189597000d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2330,8 +2330,6 @@ out: /* set offloads */ priv->dev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM | NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL; - priv->dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; - priv->dev->features |= NETIF_F_GSO_UDP_TUNNEL; } static void mlx4_en_del_vxlan_offloads(struct work_struct *work) @@ -2342,8 +2340,6 @@ static void mlx4_en_del_vxlan_offloads(struct work_struct *work) /* unset offloads */ priv->dev->hw_enc_features &= ~(NETIF_F_IP_CSUM | NETIF_F_RXCSUM | NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL); - priv->dev->hw_features &= ~NETIF_F_GSO_UDP_TUNNEL; - priv->dev->features &= ~NETIF_F_GSO_UDP_TUNNEL; ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC, 0); @@ -2940,6 +2936,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, priv->rss_hash_fn = ETH_RSS_HASH_TOP; } + if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) { + dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; + dev->features |= NETIF_F_GSO_UDP_TUNNEL; + } + mdev->pndev[port] = dev; mdev->upper[port] = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c index 0a56f010c846..760a8b387912 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_port.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c @@ -223,11 +223,11 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) stats->collisions = 0; stats->rx_dropped = be32_to_cpu(mlx4_en_stats->RDROP); stats->rx_length_errors = be32_to_cpu(mlx4_en_stats->RdropLength); - stats->rx_over_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw); + stats->rx_over_errors = 0; stats->rx_crc_errors = be32_to_cpu(mlx4_en_stats->RCRC); stats->rx_frame_errors = 0; stats->rx_fifo_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw); - stats->rx_missed_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw); + stats->rx_missed_errors = 0; stats->tx_aborted_errors = 0; stats->tx_carrier_errors = 0; stats->tx_fifo_errors = 0; diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 73b6fc21ea00..4fedf7fa72c4 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -3384,12 +3384,14 @@ static void rocker_port_fdb_learn_work(struct work_struct *work) info.addr = lw->addr; info.vid = lw->vid; + rtnl_lock(); if (learned && removing) call_netdev_switch_notifiers(NETDEV_SWITCH_FDB_DEL, lw->dev, &info.info); else if (learned && !removing) call_netdev_switch_notifiers(NETDEV_SWITCH_FDB_ADD, lw->dev, &info.info); + rtnl_unlock(); kfree(work); } diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 00cb41e71312..c56cf0b86f2c 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -833,6 +833,11 @@ static void decode_rxts(struct dp83640_private *dp83640, struct skb_shared_hwtstamps *shhwtstamps = NULL; struct sk_buff *skb; unsigned long flags; + u8 overflow; + + overflow = (phy_rxts->ns_hi >> 14) & 0x3; + if (overflow) + pr_debug("rx timestamp queue overflow, count %d\n", overflow); spin_lock_irqsave(&dp83640->rx_lock, flags); @@ -875,6 +880,7 @@ static void decode_txts(struct dp83640_private *dp83640, struct skb_shared_hwtstamps shhwtstamps; struct sk_buff *skb; u64 ns; + u8 overflow; /* We must already have the skb that triggered this. */ @@ -884,6 +890,17 @@ static void decode_txts(struct dp83640_private *dp83640, pr_debug("have timestamp but tx_queue empty\n"); return; } + + overflow = (phy_txts->ns_hi >> 14) & 0x3; + if (overflow) { + pr_debug("tx timestamp queue overflow, count %d\n", overflow); + while (skb) { + skb_complete_tx_timestamp(skb, NULL); + skb = skb_dequeue(&dp83640->tx_queue); + } + return; + } + ns = phy2txts(phy_txts); memset(&shhwtstamps, 0, sizeof(shhwtstamps)); shhwtstamps.hwtstamp = ns_to_ktime(ns); diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 9c8fabed4444..d1c4bc1c4df0 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -395,6 +395,8 @@ static int pppoe_rcv_core(struct sock *sk, struct sk_buff *skb) if (!__pppoe_xmit(sk_pppox(relay_po), skb)) goto abort_put; + + sock_put(sk_pppox(relay_po)); } else { if (sock_queue_rcv_skb(sk, skb)) goto abort_kfree; diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 0bacabfa486e..b35199cc8f34 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -131,24 +131,27 @@ static int lookup_chan_dst(u16 call_id, __be32 d_addr) return i < MAX_CALLID; } -static int add_chan(struct pppox_sock *sock) +static int add_chan(struct pppox_sock *sock, + struct pptp_addr *sa) { static int call_id; spin_lock(&chan_lock); - if (!sock->proto.pptp.src_addr.call_id) { + if (!sa->call_id) { call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, call_id + 1); if (call_id == MAX_CALLID) { call_id = find_next_zero_bit(callid_bitmap, MAX_CALLID, 1); if (call_id == MAX_CALLID) goto out_err; } - sock->proto.pptp.src_addr.call_id = call_id; - } else if (test_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap)) + sa->call_id = call_id; + } else if (test_bit(sa->call_id, callid_bitmap)) { goto out_err; + } - set_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap); - rcu_assign_pointer(callid_sock[sock->proto.pptp.src_addr.call_id], sock); + sock->proto.pptp.src_addr = *sa; + set_bit(sa->call_id, callid_bitmap); + rcu_assign_pointer(callid_sock[sa->call_id], sock); spin_unlock(&chan_lock); return 0; @@ -417,7 +420,6 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr, struct sock *sk = sock->sk; struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr; struct pppox_sock *po = pppox_sk(sk); - struct pptp_opt *opt = &po->proto.pptp; int error = 0; if (sockaddr_len < sizeof(struct sockaddr_pppox)) @@ -425,10 +427,22 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr, lock_sock(sk); - opt->src_addr = sp->sa_addr.pptp; - if (add_chan(po)) + if (sk->sk_state & PPPOX_DEAD) { + error = -EALREADY; + goto out; + } + + if (sk->sk_state & PPPOX_BOUND) { error = -EBUSY; + goto out; + } + + if (add_chan(po, &sp->sa_addr.pptp)) + error = -EBUSY; + else + sk->sk_state |= PPPOX_BOUND; +out: release_sock(sk); return error; } @@ -499,7 +513,7 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr, } opt->dst_addr = sp->sa_addr.pptp; - sk->sk_state = PPPOX_CONNECTED; + sk->sk_state |= PPPOX_CONNECTED; end: release_sock(sk); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 71190dc1eacf..cffb25280a3b 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -542,6 +542,7 @@ static const struct usb_device_id products[] = { /* 3. Combined interface devices matching on interface number */ {QMI_FIXED_INTF(0x0408, 0xea42, 4)}, /* Yota / Megafon M100-1 */ + {QMI_FIXED_INTF(0x05c6, 0x6001, 3)}, /* 4G LTE usb-modem U901 */ {QMI_FIXED_INTF(0x05c6, 0x7000, 0)}, {QMI_FIXED_INTF(0x05c6, 0x7001, 1)}, {QMI_FIXED_INTF(0x05c6, 0x7002, 1)}, diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c index 0bf82a20a0fb..48d21e0edd56 100644 --- a/drivers/pci/pcie/aer/aerdrv.c +++ b/drivers/pci/pcie/aer/aerdrv.c @@ -262,7 +262,6 @@ static struct aer_rpc *aer_alloc_rpc(struct pcie_device *dev) rpc->rpd = dev; INIT_WORK(&rpc->dpc_handler, aer_isr); mutex_init(&rpc->rpc_mutex); - init_waitqueue_head(&rpc->wait_release); /* Use PCIe bus function to store rpc into PCIe device */ set_service_data(dev, rpc); @@ -285,8 +284,7 @@ static void aer_remove(struct pcie_device *dev) if (rpc->isr) free_irq(dev->irq, dev); - wait_event(rpc->wait_release, rpc->prod_idx == rpc->cons_idx); - + flush_work(&rpc->dpc_handler); aer_disable_rootport(rpc); kfree(rpc); set_service_data(dev, NULL); diff --git a/drivers/pci/pcie/aer/aerdrv.h b/drivers/pci/pcie/aer/aerdrv.h index 84420b7c9456..945c939a86c5 100644 --- a/drivers/pci/pcie/aer/aerdrv.h +++ b/drivers/pci/pcie/aer/aerdrv.h @@ -72,7 +72,6 @@ struct aer_rpc { * recovery on the same * root port hierarchy */ - wait_queue_head_t wait_release; }; struct aer_broadcast_data { diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c index 5653ea94547f..b60a325234c5 100644 --- a/drivers/pci/pcie/aer/aerdrv_core.c +++ b/drivers/pci/pcie/aer/aerdrv_core.c @@ -784,8 +784,6 @@ void aer_isr(struct work_struct *work) while (get_e_source(rpc, &e_src)) aer_isr_one_error(p_device, &e_src); mutex_unlock(&rpc->rpc_mutex); - - wake_up(&rpc->wait_release); } /** diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index 63bc12d7a73e..153e0a27c7ee 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -275,20 +275,21 @@ EXPORT_SYMBOL_GPL(phy_exit); int phy_power_on(struct phy *phy) { - int ret; + int ret = 0; if (!phy) - return 0; + goto out; if (phy->pwr) { ret = regulator_enable(phy->pwr); if (ret) - return ret; + goto out; } ret = phy_pm_runtime_get_sync(phy); if (ret < 0 && ret != -ENOTSUPP) - return ret; + goto err_pm_sync; + ret = 0; /* Override possible ret == -ENOTSUPP */ mutex_lock(&phy->mutex); @@ -296,19 +297,20 @@ int phy_power_on(struct phy *phy) ret = phy->ops->power_on(phy); if (ret < 0) { dev_err(&phy->dev, "phy poweron failed --> %d\n", ret); - goto out; + goto err_pwr_on; } } ++phy->power_count; mutex_unlock(&phy->mutex); return 0; -out: +err_pwr_on: mutex_unlock(&phy->mutex); phy_pm_runtime_put_sync(phy); +err_pm_sync: if (phy->pwr) regulator_disable(phy->pwr); - +out: return ret; } EXPORT_SYMBOL_GPL(phy_power_on); diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c index 6285f46f3ddb..fb9e30ed8018 100644 --- a/drivers/phy/phy-twl4030-usb.c +++ b/drivers/phy/phy-twl4030-usb.c @@ -719,6 +719,7 @@ static int twl4030_usb_probe(struct platform_device *pdev) pm_runtime_use_autosuspend(&pdev->dev); pm_runtime_set_autosuspend_delay(&pdev->dev, 2000); pm_runtime_enable(&pdev->dev); + pm_runtime_get_sync(&pdev->dev); /* Our job is to use irqs and status from the power module * to keep the transceiver disabled when nothing's connected. @@ -754,6 +755,7 @@ static int twl4030_usb_remove(struct platform_device *pdev) struct twl4030_usb *twl = platform_get_drvdata(pdev); int val; + usb_remove_phy(&twl->phy); pm_runtime_get_sync(twl->dev); cancel_delayed_work(&twl->id_workaround_work); device_remove_file(twl->dev, &dev_attr_vbus); @@ -761,6 +763,13 @@ static int twl4030_usb_remove(struct platform_device *pdev) /* set transceiver mode to power on defaults */ twl4030_usb_set_mode(twl, -1); + /* idle ulpi before powering off */ + if (cable_present(twl->linkstat)) + pm_runtime_put_noidle(twl->dev); + pm_runtime_mark_last_busy(twl->dev); + pm_runtime_put_sync_suspend(twl->dev); + pm_runtime_disable(twl->dev); + /* autogate 60MHz ULPI clock, * clear dpll clock request for i2c access, * disable 32KHz @@ -775,11 +784,6 @@ static int twl4030_usb_remove(struct platform_device *pdev) /* disable complete OTG block */ twl4030_usb_clear_bits(twl, POWER_CTRL, POWER_CTRL_OTG_ENAB); - if (cable_present(twl->linkstat)) - pm_runtime_put_noidle(twl->dev); - pm_runtime_mark_last_busy(twl->dev); - pm_runtime_put(twl->dev); - return 0; } diff --git a/drivers/platform/x86/intel_scu_ipcutil.c b/drivers/platform/x86/intel_scu_ipcutil.c index 02bc5a6343c3..aa454241489c 100644 --- a/drivers/platform/x86/intel_scu_ipcutil.c +++ b/drivers/platform/x86/intel_scu_ipcutil.c @@ -49,7 +49,7 @@ struct scu_ipc_data { static int scu_reg_access(u32 cmd, struct scu_ipc_data *data) { - int count = data->count; + unsigned int count = data->count; if (count == 0 || count == 3 || count > 4) return -EINVAL; diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c index a2597e683e79..6a64e86e8ccd 100644 --- a/drivers/s390/block/dasd_alias.c +++ b/drivers/s390/block/dasd_alias.c @@ -264,8 +264,10 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device) spin_unlock_irqrestore(&lcu->lock, flags); cancel_work_sync(&lcu->suc_data.worker); spin_lock_irqsave(&lcu->lock, flags); - if (device == lcu->suc_data.device) + if (device == lcu->suc_data.device) { + dasd_put_device(device); lcu->suc_data.device = NULL; + } } was_pending = 0; if (device == lcu->ruac_data.device) { @@ -273,8 +275,10 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device) was_pending = 1; cancel_delayed_work_sync(&lcu->ruac_data.dwork); spin_lock_irqsave(&lcu->lock, flags); - if (device == lcu->ruac_data.device) + if (device == lcu->ruac_data.device) { + dasd_put_device(device); lcu->ruac_data.device = NULL; + } } private->lcu = NULL; spin_unlock_irqrestore(&lcu->lock, flags); @@ -549,8 +553,10 @@ static void lcu_update_work(struct work_struct *work) if ((rc && (rc != -EOPNOTSUPP)) || (lcu->flags & NEED_UAC_UPDATE)) { DBF_DEV_EVENT(DBF_WARNING, device, "could not update" " alias data in lcu (rc = %d), retry later", rc); - schedule_delayed_work(&lcu->ruac_data.dwork, 30*HZ); + if (!schedule_delayed_work(&lcu->ruac_data.dwork, 30*HZ)) + dasd_put_device(device); } else { + dasd_put_device(device); lcu->ruac_data.device = NULL; lcu->flags &= ~UPDATE_PENDING; } @@ -593,8 +599,10 @@ static int _schedule_lcu_update(struct alias_lcu *lcu, */ if (!usedev) return -EINVAL; + dasd_get_device(usedev); lcu->ruac_data.device = usedev; - schedule_delayed_work(&lcu->ruac_data.dwork, 0); + if (!schedule_delayed_work(&lcu->ruac_data.dwork, 0)) + dasd_put_device(usedev); return 0; } @@ -722,7 +730,7 @@ static int reset_summary_unit_check(struct alias_lcu *lcu, ASCEBC((char *) &cqr->magic, 4); ccw = cqr->cpaddr; ccw->cmd_code = DASD_ECKD_CCW_RSCK; - ccw->flags = 0 ; + ccw->flags = CCW_FLAG_SLI; ccw->count = 16; ccw->cda = (__u32)(addr_t) cqr->data; ((char *)cqr->data)[0] = reason; @@ -926,6 +934,7 @@ static void summary_unit_check_handling_work(struct work_struct *work) /* 3. read new alias configuration */ _schedule_lcu_update(lcu, device); lcu->suc_data.device = NULL; + dasd_put_device(device); spin_unlock_irqrestore(&lcu->lock, flags); } @@ -985,6 +994,8 @@ void dasd_alias_handle_summary_unit_check(struct dasd_device *device, } lcu->suc_data.reason = reason; lcu->suc_data.device = device; + dasd_get_device(device); spin_unlock(&lcu->lock); - schedule_work(&lcu->suc_data.worker); + if (!schedule_work(&lcu->suc_data.worker)) + dasd_put_device(device); }; diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c index b46ace3d4bf0..dd0c133aa312 100644 --- a/drivers/scsi/device_handler/scsi_dh_rdac.c +++ b/drivers/scsi/device_handler/scsi_dh_rdac.c @@ -568,7 +568,7 @@ static int mode_select_handle_sense(struct scsi_device *sdev, /* * Command Lock contention */ - err = SCSI_DH_RETRY; + err = SCSI_DH_IMM_RETRY; break; default: break; @@ -618,6 +618,8 @@ retry: err = mode_select_handle_sense(sdev, h->sense); if (err == SCSI_DH_RETRY && retry_cnt--) goto retry; + if (err == SCSI_DH_IMM_RETRY) + goto retry; } if (err == SCSI_DH_OK) { h->state = RDAC_STATE_ACTIVE; diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c index e9ae6b924c70..8b011aef12bd 100644 --- a/drivers/scsi/qla2xxx/qla_dbg.c +++ b/drivers/scsi/qla2xxx/qla_dbg.c @@ -67,10 +67,10 @@ * | | | 0xd031-0xd0ff | * | | | 0xd101-0xd1fe | * | | | 0xd214-0xd2fe | - * | Target Mode | 0xe079 | | - * | Target Mode Management | 0xf080 | 0xf002 | + * | Target Mode | 0xe080 | | + * | Target Mode Management | 0xf096 | 0xf002 | * | | | 0xf046-0xf049 | - * | Target Mode Task Management | 0x1000b | | + * | Target Mode Task Management | 0x1000d | | * ---------------------------------------------------------------------- */ diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index e86201d3b8c6..90d926ca1200 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -274,6 +274,7 @@ #define RESPONSE_ENTRY_CNT_FX00 256 /* Number of response entries.*/ struct req_que; +struct qla_tgt_sess; /* * (sd.h is not exported, hence local inclusion) @@ -2026,6 +2027,7 @@ typedef struct fc_port { uint16_t port_id; unsigned long retry_delay_timestamp; + struct qla_tgt_sess *tgt_session; } fc_port_t; #include "qla_mr.h" @@ -3579,6 +3581,16 @@ typedef struct scsi_qla_host { uint16_t fcoe_fcf_idx; uint8_t fcoe_vn_port_mac[6]; + /* list of commands waiting on workqueue */ + struct list_head qla_cmd_list; + struct list_head qla_sess_op_cmd_list; + spinlock_t cmd_list_lock; + + /* Counter to detect races between ELS and RSCN events */ + atomic_t generation_tick; + /* Time when global fcport update has been scheduled */ + int total_fcport_update_gen; + uint32_t vp_abort_cnt; struct fc_vport *fc_vport; /* holds fc_vport * for each vport */ diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index 998498e2341b..60f9651f2643 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -115,6 +115,8 @@ qla2x00_async_iocb_timeout(void *data) QLA_LOGIO_LOGIN_RETRIED : 0; qla2x00_post_async_login_done_work(fcport->vha, fcport, lio->u.logio.data); + } else if (sp->type == SRB_LOGOUT_CMD) { + qlt_logo_completion_handler(fcport, QLA_FUNCTION_TIMEOUT); } } @@ -497,7 +499,10 @@ void qla2x00_async_logout_done(struct scsi_qla_host *vha, fc_port_t *fcport, uint16_t *data) { - qla2x00_mark_device_lost(vha, fcport, 1, 0); + /* Don't re-login in target mode */ + if (!fcport->tgt_session) + qla2x00_mark_device_lost(vha, fcport, 1, 0); + qlt_logo_completion_handler(fcport, data[0]); return; } @@ -2189,7 +2194,7 @@ qla2x00_init_rings(scsi_qla_host_t *vha) /* Clear outstanding commands array. */ for (que = 0; que < ha->max_req_queues; que++) { req = ha->req_q_map[que]; - if (!req) + if (!req || !test_bit(que, ha->req_qid_map)) continue; req->out_ptr = (void *)(req->ring + req->length); *req->out_ptr = 0; @@ -2206,7 +2211,7 @@ qla2x00_init_rings(scsi_qla_host_t *vha) for (que = 0; que < ha->max_rsp_queues; que++) { rsp = ha->rsp_q_map[que]; - if (!rsp) + if (!rsp || !test_bit(que, ha->rsp_qid_map)) continue; rsp->in_ptr = (void *)(rsp->ring + rsp->length); *rsp->in_ptr = 0; @@ -2922,24 +2927,14 @@ qla2x00_rport_del(void *data) { fc_port_t *fcport = data; struct fc_rport *rport; - scsi_qla_host_t *vha = fcport->vha; unsigned long flags; - unsigned long vha_flags; spin_lock_irqsave(fcport->vha->host->host_lock, flags); rport = fcport->drport ? fcport->drport: fcport->rport; fcport->drport = NULL; spin_unlock_irqrestore(fcport->vha->host->host_lock, flags); - if (rport) { + if (rport) fc_remote_port_delete(rport); - /* - * Release the target mode FC NEXUS in qla_target.c code - * if target mod is enabled. - */ - spin_lock_irqsave(&vha->hw->hardware_lock, vha_flags); - qlt_fc_port_deleted(vha, fcport); - spin_unlock_irqrestore(&vha->hw->hardware_lock, vha_flags); - } } /** @@ -3379,6 +3374,7 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha) LIST_HEAD(new_fcports); struct qla_hw_data *ha = vha->hw; struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev); + int discovery_gen; /* If FL port exists, then SNS is present */ if (IS_FWI2_CAPABLE(ha)) @@ -3449,6 +3445,14 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha) fcport->scan_state = QLA_FCPORT_SCAN; } + /* Mark the time right before querying FW for connected ports. + * This process is long, asynchronous and by the time it's done, + * collected information might not be accurate anymore. E.g. + * disconnected port might have re-connected and a brand new + * session has been created. In this case session's generation + * will be newer than discovery_gen. */ + qlt_do_generation_tick(vha, &discovery_gen); + rval = qla2x00_find_all_fabric_devs(vha, &new_fcports); if (rval != QLA_SUCCESS) break; @@ -3500,7 +3504,8 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha) atomic_read(&fcport->state), fcport->flags, fcport->fc4_type, fcport->scan_state); - qlt_fc_port_deleted(vha, fcport); + qlt_fc_port_deleted(vha, fcport, + discovery_gen); } } } @@ -4277,6 +4282,14 @@ qla2x00_update_fcports(scsi_qla_host_t *base_vha) atomic_read(&fcport->state) != FCS_UNCONFIGURED) { spin_unlock_irqrestore(&ha->vport_slock, flags); qla2x00_rport_del(fcport); + + /* + * Release the target mode FC NEXUS in + * qla_target.c, if target mod is enabled. + */ + qlt_fc_port_deleted(vha, fcport, + base_vha->total_fcport_update_gen); + spin_lock_irqsave(&ha->vport_slock, flags); } } @@ -4944,7 +4957,7 @@ qla25xx_init_queues(struct qla_hw_data *ha) for (i = 1; i < ha->max_rsp_queues; i++) { rsp = ha->rsp_q_map[i]; - if (rsp) { + if (rsp && test_bit(i, ha->rsp_qid_map)) { rsp->options &= ~BIT_0; ret = qla25xx_init_rsp_que(base_vha, rsp); if (ret != QLA_SUCCESS) @@ -4959,8 +4972,8 @@ qla25xx_init_queues(struct qla_hw_data *ha) } for (i = 1; i < ha->max_req_queues; i++) { req = ha->req_q_map[i]; - if (req) { - /* Clear outstanding commands array. */ + if (req && test_bit(i, ha->req_qid_map)) { + /* Clear outstanding commands array. */ req->options &= ~BIT_0; ret = qla25xx_init_req_que(base_vha, req); if (ret != QLA_SUCCESS) diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index a1ab25fca874..dc96f31a8831 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -1943,6 +1943,9 @@ qla24xx_logout_iocb(srb_t *sp, struct logio_entry_24xx *logio) logio->entry_type = LOGINOUT_PORT_IOCB_TYPE; logio->control_flags = cpu_to_le16(LCF_COMMAND_LOGO|LCF_IMPL_LOGO); + if (!sp->fcport->tgt_session || + !sp->fcport->tgt_session->keep_nport_handle) + logio->control_flags |= cpu_to_le16(LCF_FREE_NPORT); logio->nport_handle = cpu_to_le16(sp->fcport->loop_id); logio->port_id[0] = sp->fcport->d_id.b.al_pa; logio->port_id[1] = sp->fcport->d_id.b.area; diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 6dc14cd782b2..1f3991ba7580 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -2992,9 +2992,9 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp) "MSI-X: Failed to enable support " "-- %d/%d\n Retry with %d vectors.\n", ha->msix_count, ret, ret); + ha->msix_count = ret; + ha->max_rsp_queues = ha->msix_count - 1; } - ha->msix_count = ret; - ha->max_rsp_queues = ha->msix_count - 1; ha->msix_entries = kzalloc(sizeof(struct qla_msix_entry) * ha->msix_count, GFP_KERNEL); if (!ha->msix_entries) { diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c index cc94192511cf..63abed122adf 100644 --- a/drivers/scsi/qla2xxx/qla_mid.c +++ b/drivers/scsi/qla2xxx/qla_mid.c @@ -601,7 +601,7 @@ qla25xx_delete_queues(struct scsi_qla_host *vha) /* Delete request queues */ for (cnt = 1; cnt < ha->max_req_queues; cnt++) { req = ha->req_q_map[cnt]; - if (req) { + if (req && test_bit(cnt, ha->req_qid_map)) { ret = qla25xx_delete_req_que(vha, req); if (ret != QLA_SUCCESS) { ql_log(ql_log_warn, vha, 0x00ea, @@ -615,7 +615,7 @@ qla25xx_delete_queues(struct scsi_qla_host *vha) /* Delete response queues */ for (cnt = 1; cnt < ha->max_rsp_queues; cnt++) { rsp = ha->rsp_q_map[cnt]; - if (rsp) { + if (rsp && test_bit(cnt, ha->rsp_qid_map)) { ret = qla25xx_delete_rsp_que(vha, rsp); if (ret != QLA_SUCCESS) { ql_log(ql_log_warn, vha, 0x00eb, diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 7462dd70b150..d00725574577 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -398,6 +398,9 @@ static void qla2x00_free_queues(struct qla_hw_data *ha) int cnt; for (cnt = 0; cnt < ha->max_req_queues; cnt++) { + if (!test_bit(cnt, ha->req_qid_map)) + continue; + req = ha->req_q_map[cnt]; qla2x00_free_req_que(ha, req); } @@ -405,6 +408,9 @@ static void qla2x00_free_queues(struct qla_hw_data *ha) ha->req_q_map = NULL; for (cnt = 0; cnt < ha->max_rsp_queues; cnt++) { + if (!test_bit(cnt, ha->rsp_qid_map)) + continue; + rsp = ha->rsp_q_map[cnt]; qla2x00_free_rsp_que(ha, rsp); } @@ -3229,11 +3235,14 @@ qla2x00_schedule_rport_del(struct scsi_qla_host *vha, fc_port_t *fcport, spin_lock_irqsave(vha->host->host_lock, flags); fcport->drport = rport; spin_unlock_irqrestore(vha->host->host_lock, flags); + qlt_do_generation_tick(vha, &base_vha->total_fcport_update_gen); set_bit(FCPORT_UPDATE_NEEDED, &base_vha->dpc_flags); qla2xxx_wake_dpc(base_vha); } else { + int now; fc_remote_port_delete(rport); - qlt_fc_port_deleted(vha, fcport); + qlt_do_generation_tick(vha, &now); + qlt_fc_port_deleted(vha, fcport, now); } } @@ -3763,8 +3772,11 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht, INIT_LIST_HEAD(&vha->vp_fcports); INIT_LIST_HEAD(&vha->work_list); INIT_LIST_HEAD(&vha->list); + INIT_LIST_HEAD(&vha->qla_cmd_list); + INIT_LIST_HEAD(&vha->qla_sess_op_cmd_list); spin_lock_init(&vha->work_lock); + spin_lock_init(&vha->cmd_list_lock); sprintf(vha->host_str, "%s_%ld", QLA2XXX_DRIVER_NAME, vha->host_no); ql_dbg(ql_dbg_init, vha, 0x0041, diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 496a733d0ca3..df6193b48177 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -114,6 +114,10 @@ static void qlt_alloc_qfull_cmd(struct scsi_qla_host *vha, struct atio_from_isp *atio, uint16_t status, int qfull); static void qlt_disable_vha(struct scsi_qla_host *vha); static void qlt_clear_tgt_db(struct qla_tgt *tgt); +static void qlt_send_notify_ack(struct scsi_qla_host *vha, + struct imm_ntfy_from_isp *ntfy, + uint32_t add_flags, uint16_t resp_code, int resp_code_valid, + uint16_t srr_flags, uint16_t srr_reject_code, uint8_t srr_explan); /* * Global Variables */ @@ -123,6 +127,16 @@ static struct workqueue_struct *qla_tgt_wq; static DEFINE_MUTEX(qla_tgt_mutex); static LIST_HEAD(qla_tgt_glist); +/* This API intentionally takes dest as a parameter, rather than returning + * int value to avoid caller forgetting to issue wmb() after the store */ +void qlt_do_generation_tick(struct scsi_qla_host *vha, int *dest) +{ + scsi_qla_host_t *base_vha = pci_get_drvdata(vha->hw->pdev); + *dest = atomic_inc_return(&base_vha->generation_tick); + /* memory barrier */ + wmb(); +} + /* ha->hardware_lock supposed to be held on entry (to protect tgt->sess_list) */ static struct qla_tgt_sess *qlt_find_sess_by_port_name( struct qla_tgt *tgt, @@ -382,14 +396,73 @@ static void qlt_free_session_done(struct work_struct *work) struct qla_tgt *tgt = sess->tgt; struct scsi_qla_host *vha = sess->vha; struct qla_hw_data *ha = vha->hw; + unsigned long flags; + bool logout_started = false; + fc_port_t fcport; + + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf084, + "%s: se_sess %p / sess %p from port %8phC loop_id %#04x" + " s_id %02x:%02x:%02x logout %d keep %d plogi %d\n", + __func__, sess->se_sess, sess, sess->port_name, sess->loop_id, + sess->s_id.b.domain, sess->s_id.b.area, sess->s_id.b.al_pa, + sess->logout_on_delete, sess->keep_nport_handle, + sess->plogi_ack_needed); BUG_ON(!tgt); + + if (sess->logout_on_delete) { + int rc; + + memset(&fcport, 0, sizeof(fcport)); + fcport.loop_id = sess->loop_id; + fcport.d_id = sess->s_id; + memcpy(fcport.port_name, sess->port_name, WWN_SIZE); + fcport.vha = vha; + fcport.tgt_session = sess; + + rc = qla2x00_post_async_logout_work(vha, &fcport, NULL); + if (rc != QLA_SUCCESS) + ql_log(ql_log_warn, vha, 0xf085, + "Schedule logo failed sess %p rc %d\n", + sess, rc); + else + logout_started = true; + } + /* * Release the target session for FC Nexus from fabric module code. */ if (sess->se_sess != NULL) ha->tgt.tgt_ops->free_session(sess); + if (logout_started) { + bool traced = false; + + while (!ACCESS_ONCE(sess->logout_completed)) { + if (!traced) { + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf086, + "%s: waiting for sess %p logout\n", + __func__, sess); + traced = true; + } + msleep(100); + } + + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf087, + "%s: sess %p logout completed\n", + __func__, sess); + } + + spin_lock_irqsave(&ha->hardware_lock, flags); + + if (sess->plogi_ack_needed) + qlt_send_notify_ack(vha, &sess->tm_iocb, + 0, 0, 0, 0, 0, 0); + + list_del(&sess->sess_list_entry); + + spin_unlock_irqrestore(&ha->hardware_lock, flags); + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf001, "Unregistration of sess %p finished\n", sess); @@ -410,9 +483,9 @@ void qlt_unreg_sess(struct qla_tgt_sess *sess) vha->hw->tgt.tgt_ops->clear_nacl_from_fcport_map(sess); - list_del(&sess->sess_list_entry); - if (sess->deleted) - list_del(&sess->del_list_entry); + if (!list_empty(&sess->del_list_entry)) + list_del_init(&sess->del_list_entry); + sess->deleted = QLA_SESS_DELETION_IN_PROGRESS; INIT_WORK(&sess->free_work, qlt_free_session_done); schedule_work(&sess->free_work); @@ -490,27 +563,38 @@ static void qlt_schedule_sess_for_deletion(struct qla_tgt_sess *sess, struct qla_tgt *tgt = sess->tgt; uint32_t dev_loss_tmo = tgt->ha->port_down_retry_count + 5; - if (sess->deleted) - return; + if (sess->deleted) { + /* Upgrade to unconditional deletion in case it was temporary */ + if (immediate && sess->deleted == QLA_SESS_DELETION_PENDING) + list_del(&sess->del_list_entry); + else + return; + } ql_dbg(ql_dbg_tgt, sess->vha, 0xe001, "Scheduling sess %p for deletion\n", sess); - list_add_tail(&sess->del_list_entry, &tgt->del_sess_list); - sess->deleted = 1; - if (immediate) + if (immediate) { dev_loss_tmo = 0; + sess->deleted = QLA_SESS_DELETION_IN_PROGRESS; + list_add(&sess->del_list_entry, &tgt->del_sess_list); + } else { + sess->deleted = QLA_SESS_DELETION_PENDING; + list_add_tail(&sess->del_list_entry, &tgt->del_sess_list); + } sess->expires = jiffies + dev_loss_tmo * HZ; ql_dbg(ql_dbg_tgt, sess->vha, 0xe048, - "qla_target(%d): session for port %8phC (loop ID %d) scheduled for " - "deletion in %u secs (expires: %lu) immed: %d\n", - sess->vha->vp_idx, sess->port_name, sess->loop_id, dev_loss_tmo, - sess->expires, immediate); + "qla_target(%d): session for port %8phC (loop ID %d s_id %02x:%02x:%02x)" + " scheduled for deletion in %u secs (expires: %lu) immed: %d, logout: %d, gen: %#x\n", + sess->vha->vp_idx, sess->port_name, sess->loop_id, + sess->s_id.b.domain, sess->s_id.b.area, sess->s_id.b.al_pa, + dev_loss_tmo, sess->expires, immediate, sess->logout_on_delete, + sess->generation); if (immediate) - schedule_delayed_work(&tgt->sess_del_work, 0); + mod_delayed_work(system_wq, &tgt->sess_del_work, 0); else schedule_delayed_work(&tgt->sess_del_work, sess->expires - jiffies); @@ -579,9 +663,9 @@ out_free_id_list: /* ha->hardware_lock supposed to be held on entry */ static void qlt_undelete_sess(struct qla_tgt_sess *sess) { - BUG_ON(!sess->deleted); + BUG_ON(sess->deleted != QLA_SESS_DELETION_PENDING); - list_del(&sess->del_list_entry); + list_del_init(&sess->del_list_entry); sess->deleted = 0; } @@ -600,7 +684,9 @@ static void qlt_del_sess_work_fn(struct delayed_work *work) del_list_entry); elapsed = jiffies; if (time_after_eq(elapsed, sess->expires)) { - qlt_undelete_sess(sess); + /* No turning back */ + list_del_init(&sess->del_list_entry); + sess->deleted = QLA_SESS_DELETION_IN_PROGRESS; ql_dbg(ql_dbg_tgt_mgt, vha, 0xf004, "Timeout: sess %p about to be deleted\n", @@ -644,6 +730,13 @@ static struct qla_tgt_sess *qlt_create_sess( fcport->d_id.b.al_pa, fcport->d_id.b.area, fcport->loop_id); + /* Cannot undelete at this point */ + if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + spin_unlock_irqrestore(&ha->hardware_lock, + flags); + return NULL; + } + if (sess->deleted) qlt_undelete_sess(sess); @@ -653,6 +746,9 @@ static struct qla_tgt_sess *qlt_create_sess( if (sess->local && !local) sess->local = 0; + + qlt_do_generation_tick(vha, &sess->generation); + spin_unlock_irqrestore(&ha->hardware_lock, flags); return sess; @@ -674,6 +770,14 @@ static struct qla_tgt_sess *qlt_create_sess( sess->s_id = fcport->d_id; sess->loop_id = fcport->loop_id; sess->local = local; + INIT_LIST_HEAD(&sess->del_list_entry); + + /* Under normal circumstances we want to logout from firmware when + * session eventually ends and release corresponding nport handle. + * In the exception cases (e.g. when new PLOGI is waiting) corresponding + * code will adjust these flags as necessary. */ + sess->logout_on_delete = 1; + sess->keep_nport_handle = 0; ql_dbg(ql_dbg_tgt_mgt, vha, 0xf006, "Adding sess %p to tgt %p via ->check_initiator_node_acl()\n", @@ -706,6 +810,7 @@ static struct qla_tgt_sess *qlt_create_sess( spin_lock_irqsave(&ha->hardware_lock, flags); list_add_tail(&sess->sess_list_entry, &vha->vha_tgt.qla_tgt->sess_list); vha->vha_tgt.qla_tgt->sess_count++; + qlt_do_generation_tick(vha, &sess->generation); spin_unlock_irqrestore(&ha->hardware_lock, flags); ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04b, @@ -719,7 +824,7 @@ static struct qla_tgt_sess *qlt_create_sess( } /* - * Called from drivers/scsi/qla2xxx/qla_init.c:qla2x00_reg_remote_port() + * Called from qla2x00_reg_remote_port() */ void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport) { @@ -751,6 +856,10 @@ void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport) mutex_unlock(&vha->vha_tgt.tgt_mutex); spin_lock_irqsave(&ha->hardware_lock, flags); + } else if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + /* Point of no return */ + spin_unlock_irqrestore(&ha->hardware_lock, flags); + return; } else { kref_get(&sess->se_sess->sess_kref); @@ -781,7 +890,12 @@ void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport) spin_unlock_irqrestore(&ha->hardware_lock, flags); } -void qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport) +/* + * max_gen - specifies maximum session generation + * at which this deletion requestion is still valid + */ +void +qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport, int max_gen) { struct qla_tgt *tgt = vha->vha_tgt.qla_tgt; struct qla_tgt_sess *sess; @@ -800,6 +914,15 @@ void qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport) return; } + if (max_gen - sess->generation < 0) { + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf092, + "Ignoring stale deletion request for se_sess %p / sess %p" + " for port %8phC, req_gen %d, sess_gen %d\n", + sess->se_sess, sess, sess->port_name, max_gen, + sess->generation); + return; + } + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf008, "qla_tgt_fc_port_deleted %p", sess); sess->local = 1; @@ -1170,6 +1293,70 @@ static void qlt_24xx_retry_term_exchange(struct scsi_qla_host *vha, FCP_TMF_CMPL, true); } +static int abort_cmd_for_tag(struct scsi_qla_host *vha, uint32_t tag) +{ + struct qla_tgt_sess_op *op; + struct qla_tgt_cmd *cmd; + + spin_lock(&vha->cmd_list_lock); + + list_for_each_entry(op, &vha->qla_sess_op_cmd_list, cmd_list) { + if (tag == op->atio.u.isp24.exchange_addr) { + op->aborted = true; + spin_unlock(&vha->cmd_list_lock); + return 1; + } + } + + list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) { + if (tag == cmd->atio.u.isp24.exchange_addr) { + cmd->state = QLA_TGT_STATE_ABORTED; + spin_unlock(&vha->cmd_list_lock); + return 1; + } + } + + spin_unlock(&vha->cmd_list_lock); + return 0; +} + +/* drop cmds for the given lun + * XXX only looks for cmds on the port through which lun reset was recieved + * XXX does not go through the list of other port (which may have cmds + * for the same lun) + */ +static void abort_cmds_for_lun(struct scsi_qla_host *vha, + uint32_t lun, uint8_t *s_id) +{ + struct qla_tgt_sess_op *op; + struct qla_tgt_cmd *cmd; + uint32_t key; + + key = sid_to_key(s_id); + spin_lock(&vha->cmd_list_lock); + list_for_each_entry(op, &vha->qla_sess_op_cmd_list, cmd_list) { + uint32_t op_key; + uint32_t op_lun; + + op_key = sid_to_key(op->atio.u.isp24.fcp_hdr.s_id); + op_lun = scsilun_to_int( + (struct scsi_lun *)&op->atio.u.isp24.fcp_cmnd.lun); + if (op_key == key && op_lun == lun) + op->aborted = true; + } + list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) { + uint32_t cmd_key; + uint32_t cmd_lun; + + cmd_key = sid_to_key(cmd->atio.u.isp24.fcp_hdr.s_id); + cmd_lun = scsilun_to_int( + (struct scsi_lun *)&cmd->atio.u.isp24.fcp_cmnd.lun); + if (cmd_key == key && cmd_lun == lun) + cmd->state = QLA_TGT_STATE_ABORTED; + } + spin_unlock(&vha->cmd_list_lock); +} + /* ha->hardware_lock supposed to be held on entry */ static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha, struct abts_recv_from_24xx *abts, struct qla_tgt_sess *sess) @@ -1194,8 +1381,19 @@ static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha, } spin_unlock(&se_sess->sess_cmd_lock); - if (!found_lun) - return -ENOENT; + /* cmd not in LIO lists, look in qla list */ + if (!found_lun) { + if (abort_cmd_for_tag(vha, abts->exchange_addr_to_abort)) { + /* send TASK_ABORT response immediately */ + qlt_24xx_send_abts_resp(vha, abts, FCP_TMF_CMPL, false); + return 0; + } else { + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf081, + "unable to find cmd in driver or LIO for tag 0x%x\n", + abts->exchange_addr_to_abort); + return -ENOENT; + } + } ql_dbg(ql_dbg_tgt_mgt, vha, 0xf00f, "qla_target(%d): task abort (tag=%d)\n", @@ -1279,6 +1477,11 @@ static void qlt_24xx_handle_abts(struct scsi_qla_host *vha, return; } + if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + qlt_24xx_send_abts_resp(vha, abts, FCP_TMF_REJECTED, false); + return; + } + rc = __qlt_24xx_handle_abts(vha, abts, sess); if (rc != 0) { ql_dbg(ql_dbg_tgt_mgt, vha, 0xf054, @@ -1721,21 +1924,6 @@ static int qlt_pre_xmit_response(struct qla_tgt_cmd *cmd, struct qla_hw_data *ha = vha->hw; struct se_cmd *se_cmd = &cmd->se_cmd; - if (unlikely(cmd->aborted)) { - ql_dbg(ql_dbg_tgt_mgt, vha, 0xf014, - "qla_target(%d): terminating exchange " - "for aborted cmd=%p (se_cmd=%p, tag=%d)", vha->vp_idx, cmd, - se_cmd, cmd->tag); - - cmd->state = QLA_TGT_STATE_ABORTED; - cmd->cmd_flags |= BIT_6; - - qlt_send_term_exchange(vha, cmd, &cmd->atio, 0); - - /* !! At this point cmd could be already freed !! */ - return QLA_TGT_PRE_XMIT_RESP_CMD_ABORTED; - } - prm->cmd = cmd; prm->tgt = tgt; prm->rq_result = scsi_status; @@ -2298,6 +2486,19 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type, unsigned long flags = 0; int res; + spin_lock_irqsave(&ha->hardware_lock, flags); + if (cmd->sess && cmd->sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + cmd->state = QLA_TGT_STATE_PROCESSED; + if (cmd->sess->logout_completed) + /* no need to terminate. FW already freed exchange. */ + qlt_abort_cmd_on_host_reset(cmd->vha, cmd); + else + qlt_send_term_exchange(vha, cmd, &cmd->atio, 1); + spin_unlock_irqrestore(&ha->hardware_lock, flags); + return 0; + } + spin_unlock_irqrestore(&ha->hardware_lock, flags); + memset(&prm, 0, sizeof(prm)); qlt_check_srr_debug(cmd, &xmit_type); @@ -2310,9 +2511,6 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type, res = qlt_pre_xmit_response(cmd, &prm, xmit_type, scsi_status, &full_req_cnt); if (unlikely(res != 0)) { - if (res == QLA_TGT_PRE_XMIT_RESP_CMD_ABORTED) - return 0; - return res; } @@ -2459,7 +2657,8 @@ int qlt_rdy_to_xfer(struct qla_tgt_cmd *cmd) spin_lock_irqsave(&ha->hardware_lock, flags); - if (qla2x00_reset_active(vha) || cmd->reset_count != ha->chip_reset) { + if (qla2x00_reset_active(vha) || (cmd->reset_count != ha->chip_reset) || + (cmd->sess && cmd->sess->deleted == QLA_SESS_DELETION_IN_PROGRESS)) { /* * Either a chip reset is active or this request was from * previous life, just abort the processing. @@ -2652,6 +2851,89 @@ out: /* If hardware_lock held on entry, might drop it, then reaquire */ /* This function sends the appropriate CTIO to ISP 2xxx or 24xx */ +static int __qlt_send_term_imm_notif(struct scsi_qla_host *vha, + struct imm_ntfy_from_isp *ntfy) +{ + struct nack_to_isp *nack; + struct qla_hw_data *ha = vha->hw; + request_t *pkt; + int ret = 0; + + ql_dbg(ql_dbg_tgt_tmr, vha, 0xe01c, + "Sending TERM ELS CTIO (ha=%p)\n", ha); + + pkt = (request_t *)qla2x00_alloc_iocbs_ready(vha, NULL); + if (pkt == NULL) { + ql_dbg(ql_dbg_tgt, vha, 0xe080, + "qla_target(%d): %s failed: unable to allocate " + "request packet\n", vha->vp_idx, __func__); + return -ENOMEM; + } + + pkt->entry_type = NOTIFY_ACK_TYPE; + pkt->entry_count = 1; + pkt->handle = QLA_TGT_SKIP_HANDLE | CTIO_COMPLETION_HANDLE_MARK; + + nack = (struct nack_to_isp *)pkt; + nack->ox_id = ntfy->ox_id; + + nack->u.isp24.nport_handle = ntfy->u.isp24.nport_handle; + if (le16_to_cpu(ntfy->u.isp24.status) == IMM_NTFY_ELS) { + nack->u.isp24.flags = ntfy->u.isp24.flags & + __constant_cpu_to_le32(NOTIFY24XX_FLAGS_PUREX_IOCB); + } + + /* terminate */ + nack->u.isp24.flags |= + __constant_cpu_to_le16(NOTIFY_ACK_FLAGS_TERMINATE); + + nack->u.isp24.srr_rx_id = ntfy->u.isp24.srr_rx_id; + nack->u.isp24.status = ntfy->u.isp24.status; + nack->u.isp24.status_subcode = ntfy->u.isp24.status_subcode; + nack->u.isp24.fw_handle = ntfy->u.isp24.fw_handle; + nack->u.isp24.exchange_address = ntfy->u.isp24.exchange_address; + nack->u.isp24.srr_rel_offs = ntfy->u.isp24.srr_rel_offs; + nack->u.isp24.srr_ui = ntfy->u.isp24.srr_ui; + nack->u.isp24.vp_index = ntfy->u.isp24.vp_index; + + qla2x00_start_iocbs(vha, vha->req); + return ret; +} + +static void qlt_send_term_imm_notif(struct scsi_qla_host *vha, + struct imm_ntfy_from_isp *imm, int ha_locked) +{ + unsigned long flags = 0; + int rc; + + if (qlt_issue_marker(vha, ha_locked) < 0) + return; + + if (ha_locked) { + rc = __qlt_send_term_imm_notif(vha, imm); + +#if 0 /* Todo */ + if (rc == -ENOMEM) + qlt_alloc_qfull_cmd(vha, imm, 0, 0); +#endif + goto done; + } + + spin_lock_irqsave(&vha->hw->hardware_lock, flags); + rc = __qlt_send_term_imm_notif(vha, imm); + +#if 0 /* Todo */ + if (rc == -ENOMEM) + qlt_alloc_qfull_cmd(vha, imm, 0, 0); +#endif + +done: + if (!ha_locked) + spin_unlock_irqrestore(&vha->hw->hardware_lock, flags); +} + +/* If hardware_lock held on entry, might drop it, then reaquire */ +/* This function sends the appropriate CTIO to ISP 2xxx or 24xx */ static int __qlt_send_term_exchange(struct scsi_qla_host *vha, struct qla_tgt_cmd *cmd, struct atio_from_isp *atio) @@ -2794,6 +3076,24 @@ static void qlt_chk_exch_leak_thresh_hold(struct scsi_qla_host *vha) } +void qlt_abort_cmd(struct qla_tgt_cmd *cmd) +{ + struct qla_tgt *tgt = cmd->tgt; + struct scsi_qla_host *vha = tgt->vha; + struct se_cmd *se_cmd = &cmd->se_cmd; + + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf014, + "qla_target(%d): terminating exchange for aborted cmd=%p " + "(se_cmd=%p, tag=%llu)", vha->vp_idx, cmd, &cmd->se_cmd, + cmd->tag); + + cmd->state = QLA_TGT_STATE_ABORTED; + cmd->cmd_flags |= BIT_6; + + qlt_send_term_exchange(vha, cmd, &cmd->atio, 0); +} +EXPORT_SYMBOL(qlt_abort_cmd); + void qlt_free_cmd(struct qla_tgt_cmd *cmd) { struct qla_tgt_sess *sess = cmd->sess; @@ -3265,6 +3565,13 @@ static void __qlt_do_work(struct qla_tgt_cmd *cmd) if (tgt->tgt_stop) goto out_term; + if (cmd->state == QLA_TGT_STATE_ABORTED) { + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf082, + "cmd with tag %u is aborted\n", + cmd->atio.u.isp24.exchange_addr); + goto out_term; + } + cdb = &atio->u.isp24.fcp_cmnd.cdb[0]; cmd->tag = atio->u.isp24.exchange_addr; cmd->unpacked_lun = scsilun_to_int( @@ -3318,6 +3625,12 @@ out_term: static void qlt_do_work(struct work_struct *work) { struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work); + scsi_qla_host_t *vha = cmd->vha; + unsigned long flags; + + spin_lock_irqsave(&vha->cmd_list_lock, flags); + list_del(&cmd->cmd_list); + spin_unlock_irqrestore(&vha->cmd_list_lock, flags); __qlt_do_work(cmd); } @@ -3369,14 +3682,25 @@ static void qlt_create_sess_from_atio(struct work_struct *work) unsigned long flags; uint8_t *s_id = op->atio.u.isp24.fcp_hdr.s_id; + spin_lock_irqsave(&vha->cmd_list_lock, flags); + list_del(&op->cmd_list); + spin_unlock_irqrestore(&vha->cmd_list_lock, flags); + + if (op->aborted) { + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf083, + "sess_op with tag %u is aborted\n", + op->atio.u.isp24.exchange_addr); + goto out_term; + } + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf022, - "qla_target(%d): Unable to find wwn login" - " (s_id %x:%x:%x), trying to create it manually\n", - vha->vp_idx, s_id[0], s_id[1], s_id[2]); + "qla_target(%d): Unable to find wwn login" + " (s_id %x:%x:%x), trying to create it manually\n", + vha->vp_idx, s_id[0], s_id[1], s_id[2]); if (op->atio.u.raw.entry_count > 1) { ql_dbg(ql_dbg_tgt_mgt, vha, 0xf023, - "Dropping multy entry atio %p\n", &op->atio); + "Dropping multy entry atio %p\n", &op->atio); goto out_term; } @@ -3441,10 +3765,25 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha, memcpy(&op->atio, atio, sizeof(*atio)); op->vha = vha; + + spin_lock(&vha->cmd_list_lock); + list_add_tail(&op->cmd_list, &vha->qla_sess_op_cmd_list); + spin_unlock(&vha->cmd_list_lock); + INIT_WORK(&op->work, qlt_create_sess_from_atio); queue_work(qla_tgt_wq, &op->work); return 0; } + + /* Another WWN used to have our s_id. Our PLOGI scheduled its + * session deletion, but it's still in sess_del_work wq */ + if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + ql_dbg(ql_dbg_io, vha, 0x3061, + "New command while old session %p is being deleted\n", + sess); + return -EFAULT; + } + /* * Do kref_get() before returning + dropping qla_hw_data->hardware_lock. */ @@ -3460,6 +3799,11 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha, cmd->cmd_in_wq = 1; cmd->cmd_flags |= BIT_0; + + spin_lock(&vha->cmd_list_lock); + list_add_tail(&cmd->cmd_list, &vha->qla_cmd_list); + spin_unlock(&vha->cmd_list_lock); + INIT_WORK(&cmd->work, qlt_do_work); queue_work(qla_tgt_wq, &cmd->work); return 0; @@ -3473,6 +3817,7 @@ static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun, struct scsi_qla_host *vha = sess->vha; struct qla_hw_data *ha = vha->hw; struct qla_tgt_mgmt_cmd *mcmd; + struct atio_from_isp *a = (struct atio_from_isp *)iocb; int res; uint8_t tmr_func; @@ -3513,6 +3858,7 @@ static int qlt_issue_task_mgmt(struct qla_tgt_sess *sess, uint32_t lun, ql_dbg(ql_dbg_tgt_tmr, vha, 0x10002, "qla_target(%d): LUN_RESET received\n", sess->vha->vp_idx); tmr_func = TMR_LUN_RESET; + abort_cmds_for_lun(vha, lun, a->u.isp24.fcp_hdr.s_id); break; case QLA_TGT_CLEAR_TS: @@ -3601,6 +3947,9 @@ static int qlt_handle_task_mgmt(struct scsi_qla_host *vha, void *iocb) sizeof(struct atio_from_isp)); } + if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) + return -EFAULT; + return qlt_issue_task_mgmt(sess, unpacked_lun, fn, iocb, 0); } @@ -3666,22 +4015,280 @@ static int qlt_abort_task(struct scsi_qla_host *vha, return __qlt_abort_task(vha, iocb, sess); } +void qlt_logo_completion_handler(fc_port_t *fcport, int rc) +{ + if (fcport->tgt_session) { + if (rc != MBS_COMMAND_COMPLETE) { + ql_dbg(ql_dbg_tgt_mgt, fcport->vha, 0xf093, + "%s: se_sess %p / sess %p from" + " port %8phC loop_id %#04x s_id %02x:%02x:%02x" + " LOGO failed: %#x\n", + __func__, + fcport->tgt_session->se_sess, + fcport->tgt_session, + fcport->port_name, fcport->loop_id, + fcport->d_id.b.domain, fcport->d_id.b.area, + fcport->d_id.b.al_pa, rc); + } + + fcport->tgt_session->logout_completed = 1; + } +} + +static void qlt_swap_imm_ntfy_iocb(struct imm_ntfy_from_isp *a, + struct imm_ntfy_from_isp *b) +{ + struct imm_ntfy_from_isp tmp; + memcpy(&tmp, a, sizeof(struct imm_ntfy_from_isp)); + memcpy(a, b, sizeof(struct imm_ntfy_from_isp)); + memcpy(b, &tmp, sizeof(struct imm_ntfy_from_isp)); +} + +/* +* ha->hardware_lock supposed to be held on entry (to protect tgt->sess_list) +* +* Schedules sessions with matching port_id/loop_id but different wwn for +* deletion. Returns existing session with matching wwn if present. +* Null otherwise. +*/ +static struct qla_tgt_sess * +qlt_find_sess_invalidate_other(struct qla_tgt *tgt, uint64_t wwn, + port_id_t port_id, uint16_t loop_id) +{ + struct qla_tgt_sess *sess = NULL, *other_sess; + uint64_t other_wwn; + + list_for_each_entry(other_sess, &tgt->sess_list, sess_list_entry) { + + other_wwn = wwn_to_u64(other_sess->port_name); + + if (wwn == other_wwn) { + WARN_ON(sess); + sess = other_sess; + continue; + } + + /* find other sess with nport_id collision */ + if (port_id.b24 == other_sess->s_id.b24) { + if (loop_id != other_sess->loop_id) { + ql_dbg(ql_dbg_tgt_tmr, tgt->vha, 0x1000c, + "Invalidating sess %p loop_id %d wwn %llx.\n", + other_sess, other_sess->loop_id, other_wwn); + + /* + * logout_on_delete is set by default, but another + * session that has the same s_id/loop_id combo + * might have cleared it when requested this session + * deletion, so don't touch it + */ + qlt_schedule_sess_for_deletion(other_sess, true); + } else { + /* + * Another wwn used to have our s_id/loop_id + * combo - kill the session, but don't log out + */ + sess->logout_on_delete = 0; + qlt_schedule_sess_for_deletion(other_sess, + true); + } + continue; + } + + /* find other sess with nport handle collision */ + if (loop_id == other_sess->loop_id) { + ql_dbg(ql_dbg_tgt_tmr, tgt->vha, 0x1000d, + "Invalidating sess %p loop_id %d wwn %llx.\n", + other_sess, other_sess->loop_id, other_wwn); + + /* Same loop_id but different s_id + * Ok to kill and logout */ + qlt_schedule_sess_for_deletion(other_sess, true); + } + } + + return sess; +} + +/* Abort any commands for this s_id waiting on qla_tgt_wq workqueue */ +static int abort_cmds_for_s_id(struct scsi_qla_host *vha, port_id_t *s_id) +{ + struct qla_tgt_sess_op *op; + struct qla_tgt_cmd *cmd; + uint32_t key; + int count = 0; + + key = (((u32)s_id->b.domain << 16) | + ((u32)s_id->b.area << 8) | + ((u32)s_id->b.al_pa)); + + spin_lock(&vha->cmd_list_lock); + list_for_each_entry(op, &vha->qla_sess_op_cmd_list, cmd_list) { + uint32_t op_key = sid_to_key(op->atio.u.isp24.fcp_hdr.s_id); + if (op_key == key) { + op->aborted = true; + count++; + } + } + list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) { + uint32_t cmd_key = sid_to_key(cmd->atio.u.isp24.fcp_hdr.s_id); + if (cmd_key == key) { + cmd->state = QLA_TGT_STATE_ABORTED; + count++; + } + } + spin_unlock(&vha->cmd_list_lock); + + return count; +} + /* * ha->hardware_lock supposed to be held on entry. Might drop it, then reaquire */ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, struct imm_ntfy_from_isp *iocb) { + struct qla_tgt *tgt = vha->vha_tgt.qla_tgt; + struct qla_hw_data *ha = vha->hw; + struct qla_tgt_sess *sess = NULL; + uint64_t wwn; + port_id_t port_id; + uint16_t loop_id; + uint16_t wd3_lo; int res = 0; + wwn = wwn_to_u64(iocb->u.isp24.port_name); + + port_id.b.domain = iocb->u.isp24.port_id[2]; + port_id.b.area = iocb->u.isp24.port_id[1]; + port_id.b.al_pa = iocb->u.isp24.port_id[0]; + port_id.b.rsvd_1 = 0; + + loop_id = le16_to_cpu(iocb->u.isp24.nport_handle); + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf026, "qla_target(%d): Port ID: 0x%3phC ELS opcode: 0x%02x\n", vha->vp_idx, iocb->u.isp24.port_id, iocb->u.isp24.status_subcode); + /* res = 1 means ack at the end of thread + * res = 0 means ack async/later. + */ switch (iocb->u.isp24.status_subcode) { case ELS_PLOGI: - case ELS_FLOGI: + + /* Mark all stale commands in qla_tgt_wq for deletion */ + abort_cmds_for_s_id(vha, &port_id); + + if (wwn) + sess = qlt_find_sess_invalidate_other(tgt, wwn, + port_id, loop_id); + + if (!sess || IS_SW_RESV_ADDR(sess->s_id)) { + res = 1; + break; + } + + if (sess->plogi_ack_needed) { + /* + * Initiator sent another PLOGI before last PLOGI could + * finish. Swap plogi iocbs and terminate old one + * without acking, new one will get acked when session + * deletion completes. + */ + ql_log(ql_log_warn, sess->vha, 0xf094, + "sess %p received double plogi.\n", sess); + + qlt_swap_imm_ntfy_iocb(iocb, &sess->tm_iocb); + + qlt_send_term_imm_notif(vha, iocb, 1); + + res = 0; + break; + } + + res = 0; + + /* + * Save immediate Notif IOCB for Ack when sess is done + * and being deleted. + */ + memcpy(&sess->tm_iocb, iocb, sizeof(sess->tm_iocb)); + sess->plogi_ack_needed = 1; + + /* + * Under normal circumstances we want to release nport handle + * during LOGO process to avoid nport handle leaks inside FW. + * The exception is when LOGO is done while another PLOGI with + * the same nport handle is waiting as might be the case here. + * Note: there is always a possibily of a race where session + * deletion has already started for other reasons (e.g. ACL + * removal) and now PLOGI arrives: + * 1. if PLOGI arrived in FW after nport handle has been freed, + * FW must have assigned this PLOGI a new/same handle and we + * can proceed ACK'ing it as usual when session deletion + * completes. + * 2. if PLOGI arrived in FW before LOGO with LCF_FREE_NPORT + * bit reached it, the handle has now been released. We'll + * get an error when we ACK this PLOGI. Nothing will be sent + * back to initiator. Initiator should eventually retry + * PLOGI and situation will correct itself. + */ + sess->keep_nport_handle = ((sess->loop_id == loop_id) && + (sess->s_id.b24 == port_id.b24)); + qlt_schedule_sess_for_deletion(sess, true); + break; + case ELS_PRLI: + wd3_lo = le16_to_cpu(iocb->u.isp24.u.prli.wd3_lo); + + if (wwn) + sess = qlt_find_sess_invalidate_other(tgt, wwn, port_id, + loop_id); + + if (sess != NULL) { + if (sess->deleted) { + /* + * Impatient initiator sent PRLI before last + * PLOGI could finish. Will force him to re-try, + * while last one finishes. + */ + ql_log(ql_log_warn, sess->vha, 0xf095, + "sess %p PRLI received, before plogi ack.\n", + sess); + qlt_send_term_imm_notif(vha, iocb, 1); + res = 0; + break; + } + + /* + * This shouldn't happen under normal circumstances, + * since we have deleted the old session during PLOGI + */ + ql_dbg(ql_dbg_tgt_mgt, vha, 0xf096, + "PRLI (loop_id %#04x) for existing sess %p (loop_id %#04x)\n", + sess->loop_id, sess, iocb->u.isp24.nport_handle); + + sess->local = 0; + sess->loop_id = loop_id; + sess->s_id = port_id; + + if (wd3_lo & BIT_7) + sess->conf_compl_supported = 1; + + } + res = 1; /* send notify ack */ + + /* Make session global (not used in fabric mode) */ + if (ha->current_topology != ISP_CFG_F) { + set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags); + set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags); + qla2xxx_wake_dpc(vha); + } else { + /* todo: else - create sess here. */ + res = 1; /* send notify ack */ + } + + break; + case ELS_LOGO: case ELS_PRLO: res = qlt_reset(vha, iocb, QLA_TGT_NEXUS_LOSS_SESS); @@ -3699,6 +4306,7 @@ static int qlt_24xx_handle_els(struct scsi_qla_host *vha, break; } + case ELS_FLOGI: /* should never happen */ default: ql_dbg(ql_dbg_tgt_mgt, vha, 0xf061, "qla_target(%d): Unsupported ELS command %x " @@ -5016,6 +5624,11 @@ static void qlt_abort_work(struct qla_tgt *tgt, if (!sess) goto out_term; } else { + if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + sess = NULL; + goto out_term; + } + kref_get(&sess->se_sess->sess_kref); } @@ -5070,6 +5683,11 @@ static void qlt_tmr_work(struct qla_tgt *tgt, if (!sess) goto out_term; } else { + if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) { + sess = NULL; + goto out_term; + } + kref_get(&sess->se_sess->sess_kref); } diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h index 332086776dfe..d30c60a1d522 100644 --- a/drivers/scsi/qla2xxx/qla_target.h +++ b/drivers/scsi/qla2xxx/qla_target.h @@ -167,7 +167,24 @@ struct imm_ntfy_from_isp { uint32_t srr_rel_offs; uint16_t srr_ui; uint16_t srr_ox_id; - uint8_t reserved_4[19]; + union { + struct { + uint8_t node_name[8]; + } plogi; /* PLOGI/ADISC/PDISC */ + struct { + /* PRLI word 3 bit 0-15 */ + uint16_t wd3_lo; + uint8_t resv0[6]; + } prli; + struct { + uint8_t port_id[3]; + uint8_t resv1; + uint16_t nport_handle; + uint16_t resv2; + } req_els; + } u; + uint8_t port_name[8]; + uint8_t resv3[3]; uint8_t vp_index; uint32_t reserved_5; uint8_t port_id[3]; @@ -234,6 +251,7 @@ struct nack_to_isp { uint8_t reserved[2]; uint16_t ox_id; } __packed; +#define NOTIFY_ACK_FLAGS_TERMINATE BIT_3 #define NOTIFY_ACK_SRR_FLAGS_ACCEPT 0 #define NOTIFY_ACK_SRR_FLAGS_REJECT 1 @@ -790,13 +808,6 @@ int qla2x00_wait_for_hba_online(struct scsi_qla_host *); #define FC_TM_REJECT 4 #define FC_TM_FAILED 5 -/* - * Error code of qlt_pre_xmit_response() meaning that cmd's exchange was - * terminated, so no more actions is needed and success should be returned - * to target. - */ -#define QLA_TGT_PRE_XMIT_RESP_CMD_ABORTED 0x1717 - #if (BITS_PER_LONG > 32) || defined(CONFIG_HIGHMEM64G) #define pci_dma_lo32(a) (a & 0xffffffff) #define pci_dma_hi32(a) ((((a) >> 16)>>16) & 0xffffffff) @@ -874,6 +885,15 @@ struct qla_tgt_sess_op { struct scsi_qla_host *vha; struct atio_from_isp atio; struct work_struct work; + struct list_head cmd_list; + bool aborted; +}; + +enum qla_sess_deletion { + QLA_SESS_DELETION_NONE = 0, + QLA_SESS_DELETION_PENDING = 1, /* hopefully we can get rid of + * this one */ + QLA_SESS_DELETION_IN_PROGRESS = 2, }; /* @@ -884,8 +904,15 @@ struct qla_tgt_sess { port_id_t s_id; unsigned int conf_compl_supported:1; - unsigned int deleted:1; + unsigned int deleted:2; unsigned int local:1; + unsigned int logout_on_delete:1; + unsigned int plogi_ack_needed:1; + unsigned int keep_nport_handle:1; + + unsigned char logout_completed; + + int generation; struct se_session *se_sess; struct scsi_qla_host *vha; @@ -897,6 +924,10 @@ struct qla_tgt_sess { uint8_t port_name[WWN_SIZE]; struct work_struct free_work; + + union { + struct imm_ntfy_from_isp tm_iocb; + }; }; struct qla_tgt_cmd { @@ -912,7 +943,6 @@ struct qla_tgt_cmd { unsigned int conf_compl_supported:1; unsigned int sg_mapped:1; unsigned int free_sg:1; - unsigned int aborted:1; /* Needed in case of SRR */ unsigned int write_data_transferred:1; unsigned int ctx_dsd_alloced:1; unsigned int q_full:1; @@ -1027,6 +1057,10 @@ struct qla_tgt_srr_ctio { struct qla_tgt_cmd *cmd; }; +/* Check for Switch reserved address */ +#define IS_SW_RESV_ADDR(_s_id) \ + ((_s_id.b.domain == 0xff) && (_s_id.b.area == 0xfc)) + #define QLA_TGT_XMIT_DATA 1 #define QLA_TGT_XMIT_STATUS 2 #define QLA_TGT_XMIT_ALL (QLA_TGT_XMIT_STATUS|QLA_TGT_XMIT_DATA) @@ -1044,7 +1078,7 @@ extern int qlt_lport_register(void *, u64, u64, u64, extern void qlt_lport_deregister(struct scsi_qla_host *); extern void qlt_unreg_sess(struct qla_tgt_sess *); extern void qlt_fc_port_added(struct scsi_qla_host *, fc_port_t *); -extern void qlt_fc_port_deleted(struct scsi_qla_host *, fc_port_t *); +extern void qlt_fc_port_deleted(struct scsi_qla_host *, fc_port_t *, int); extern int __init qlt_init(void); extern void qlt_exit(void); extern void qlt_update_vp_map(struct scsi_qla_host *, int); @@ -1074,12 +1108,23 @@ static inline void qla_reverse_ini_mode(struct scsi_qla_host *ha) ha->host->active_mode |= MODE_INITIATOR; } +static inline uint32_t sid_to_key(const uint8_t *s_id) +{ + uint32_t key; + + key = (((unsigned long)s_id[0] << 16) | + ((unsigned long)s_id[1] << 8) | + (unsigned long)s_id[2]); + return key; +} + /* * Exported symbols from qla_target.c LLD logic used by qla2xxx code.. */ extern void qlt_response_pkt_all_vps(struct scsi_qla_host *, response_t *); extern int qlt_rdy_to_xfer(struct qla_tgt_cmd *); extern int qlt_xmit_response(struct qla_tgt_cmd *, int, uint8_t); +extern void qlt_abort_cmd(struct qla_tgt_cmd *); extern void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *); extern void qlt_free_mcmd(struct qla_tgt_mgmt_cmd *); extern void qlt_free_cmd(struct qla_tgt_cmd *cmd); @@ -1110,5 +1155,7 @@ extern void qlt_stop_phase2(struct qla_tgt *); extern irqreturn_t qla83xx_msix_atio_q(int, void *); extern void qlt_83xx_iospace_config(struct qla_hw_data *); extern int qlt_free_qfull_cmds(struct scsi_qla_host *); +extern void qlt_logo_completion_handler(fc_port_t *, int); +extern void qlt_do_generation_tick(struct scsi_qla_host *, int *); #endif /* __QLA_TARGET_H */ diff --git a/drivers/scsi/qla2xxx/qla_tmpl.c b/drivers/scsi/qla2xxx/qla_tmpl.c index 962cb89fe0ae..af806fdb0dbc 100644 --- a/drivers/scsi/qla2xxx/qla_tmpl.c +++ b/drivers/scsi/qla2xxx/qla_tmpl.c @@ -395,6 +395,10 @@ qla27xx_fwdt_entry_t263(struct scsi_qla_host *vha, if (ent->t263.queue_type == T263_QUEUE_TYPE_REQ) { for (i = 0; i < vha->hw->max_req_queues; i++) { struct req_que *req = vha->hw->req_q_map[i]; + + if (!test_bit(i, vha->hw->req_qid_map)) + continue; + if (req || !buf) { length = req ? req->length : REQUEST_ENTRY_CNT_24XX; @@ -408,6 +412,10 @@ qla27xx_fwdt_entry_t263(struct scsi_qla_host *vha, } else if (ent->t263.queue_type == T263_QUEUE_TYPE_RSP) { for (i = 0; i < vha->hw->max_rsp_queues; i++) { struct rsp_que *rsp = vha->hw->rsp_q_map[i]; + + if (!test_bit(i, vha->hw->rsp_qid_map)) + continue; + if (rsp || !buf) { length = rsp ? rsp->length : RESPONSE_ENTRY_CNT_MQ; @@ -634,6 +642,10 @@ qla27xx_fwdt_entry_t274(struct scsi_qla_host *vha, if (ent->t274.queue_type == T274_QUEUE_TYPE_REQ_SHAD) { for (i = 0; i < vha->hw->max_req_queues; i++) { struct req_que *req = vha->hw->req_q_map[i]; + + if (!test_bit(i, vha->hw->req_qid_map)) + continue; + if (req || !buf) { qla27xx_insert16(i, buf, len); qla27xx_insert16(1, buf, len); @@ -645,6 +657,10 @@ qla27xx_fwdt_entry_t274(struct scsi_qla_host *vha, } else if (ent->t274.queue_type == T274_QUEUE_TYPE_RSP_SHAD) { for (i = 0; i < vha->hw->max_rsp_queues; i++) { struct rsp_que *rsp = vha->hw->rsp_q_map[i]; + + if (!test_bit(i, vha->hw->rsp_qid_map)) + continue; + if (rsp || !buf) { qla27xx_insert16(i, buf, len); qla27xx_insert16(1, buf, len); diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 5c9e680aa375..fdad875ca777 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -429,7 +429,7 @@ static int tcm_qla2xxx_check_stop_free(struct se_cmd *se_cmd) cmd->cmd_flags |= BIT_14; } - return target_put_sess_cmd(se_cmd->se_sess, se_cmd); + return target_put_sess_cmd(se_cmd); } /* tcm_qla2xxx_release_cmd - Callback from TCM Core to release underlying @@ -669,7 +669,6 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd) cmd->cmd_flags |= BIT_4; cmd->bufflen = se_cmd->data_length; cmd->dma_data_direction = target_reverse_dma_direction(se_cmd); - cmd->aborted = (se_cmd->transport_state & CMD_T_ABORTED); cmd->sg_cnt = se_cmd->t_data_nents; cmd->sg = se_cmd->t_data_sg; @@ -699,7 +698,6 @@ static int tcm_qla2xxx_queue_status(struct se_cmd *se_cmd) cmd->sg_cnt = 0; cmd->offset = 0; cmd->dma_data_direction = target_reverse_dma_direction(se_cmd); - cmd->aborted = (se_cmd->transport_state & CMD_T_ABORTED); if (cmd->cmd_flags & BIT_5) { pr_crit("Bit_5 already set for cmd = %p.\n", cmd); dump_stack(); @@ -764,14 +762,7 @@ static void tcm_qla2xxx_aborted_task(struct se_cmd *se_cmd) { struct qla_tgt_cmd *cmd = container_of(se_cmd, struct qla_tgt_cmd, se_cmd); - struct scsi_qla_host *vha = cmd->vha; - struct qla_hw_data *ha = vha->hw; - - if (!cmd->sg_mapped) - return; - - pci_unmap_sg(ha->pdev, cmd->sg, cmd->sg_cnt, cmd->dma_data_direction); - cmd->sg_mapped = 0; + qlt_abort_cmd(cmd); } static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *, @@ -1323,9 +1314,7 @@ static struct qla_tgt_sess *tcm_qla2xxx_find_sess_by_s_id( return NULL; } - key = (((unsigned long)s_id[0] << 16) | - ((unsigned long)s_id[1] << 8) | - (unsigned long)s_id[2]); + key = sid_to_key(s_id); pr_debug("find_sess_by_s_id: 0x%06x\n", key); se_nacl = btree_lookup32(&lport->lport_fcport_map, key); @@ -1360,9 +1349,7 @@ static void tcm_qla2xxx_set_sess_by_s_id( void *slot; int rc; - key = (((unsigned long)s_id[0] << 16) | - ((unsigned long)s_id[1] << 8) | - (unsigned long)s_id[2]); + key = sid_to_key(s_id); pr_debug("set_sess_by_s_id: %06x\n", key); slot = btree_lookup32(&lport->lport_fcport_map, key); @@ -1718,6 +1705,10 @@ static void tcm_qla2xxx_update_sess(struct qla_tgt_sess *sess, port_id_t s_id, } sess->conf_compl_supported = conf_compl_supported; + + /* Reset logout parameters to default */ + sess->logout_on_delete = 1; + sess->keep_nport_handle = 0; } /* diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index 64ed88a67e6e..ac418e73536d 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -205,6 +205,7 @@ static struct { {"Intel", "Multi-Flex", NULL, BLIST_NO_RSOC}, {"iRiver", "iFP Mass Driver", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36}, {"LASOUND", "CDX7405", "3.10", BLIST_MAX5LUN | BLIST_SINGLELUN}, + {"Marvell", "Console", NULL, BLIST_SKIP_VPD_PAGES}, {"MATSHITA", "PD-1", NULL, BLIST_FORCELUN | BLIST_SINGLELUN}, {"MATSHITA", "DMC-LC5", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36}, {"MATSHITA", "DMC-LC40", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36}, diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 330bbe831066..2e58279fab60 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -712,7 +712,7 @@ static int iscsit_add_reject_from_cmd( */ if (cmd->se_cmd.se_tfo != NULL) { pr_debug("iscsi reject: calling target_put_sess_cmd >>>>>>\n"); - target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd); + target_put_sess_cmd(&cmd->se_cmd); } return -1; } @@ -998,7 +998,7 @@ int iscsit_setup_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, hdr->cmdsn, be32_to_cpu(hdr->data_length), payload_length, conn->cid); - target_get_sess_cmd(conn->sess->se_sess, &cmd->se_cmd, true); + target_get_sess_cmd(&cmd->se_cmd, true); cmd->sense_reason = transport_lookup_cmd_lun(&cmd->se_cmd, scsilun_to_int(&hdr->lun)); @@ -1064,7 +1064,7 @@ int iscsit_process_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, if (cmdsn_ret == CMDSN_ERROR_CANNOT_RECOVER) return -1; else if (cmdsn_ret == CMDSN_LOWER_THAN_EXP) { - target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd); + target_put_sess_cmd(&cmd->se_cmd); return 0; } } @@ -1080,7 +1080,7 @@ int iscsit_process_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, if (!cmd->sense_reason) return 0; - target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd); + target_put_sess_cmd(&cmd->se_cmd); return 0; } @@ -1111,7 +1111,6 @@ static int iscsit_get_immediate_data(struct iscsi_cmd *cmd, struct iscsi_scsi_req *hdr, bool dump_payload) { - struct iscsi_conn *conn = cmd->conn; int cmdsn_ret = 0, immed_ret = IMMEDIATE_DATA_NORMAL_OPERATION; /* * Special case for Unsupported SAM WRITE Opcodes and ImmediateData=Yes. @@ -1138,7 +1137,7 @@ after_immediate_data: rc = iscsit_dump_data_payload(cmd->conn, cmd->first_burst_len, 1); - target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd); + target_put_sess_cmd(&cmd->se_cmd); return rc; } else if (cmd->unsolicited_data) iscsit_set_unsoliticed_dataout(cmd); @@ -1807,7 +1806,7 @@ iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, conn->sess->se_sess, 0, DMA_NONE, TCM_SIMPLE_TAG, cmd->sense_buffer + 2); - target_get_sess_cmd(conn->sess->se_sess, &cmd->se_cmd, true); + target_get_sess_cmd(&cmd->se_cmd, true); sess_ref = true; switch (function) { @@ -1949,7 +1948,7 @@ attach: */ if (sess_ref) { pr_debug("Handle TMR, using sess_ref=true check\n"); - target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd); + target_put_sess_cmd(&cmd->se_cmd); } iscsit_add_cmd_to_response_queue(cmd, conn, cmd->i_state); diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c index 5a8add721741..83bb55b94434 100644 --- a/drivers/target/iscsi/iscsi_target_configfs.c +++ b/drivers/target/iscsi/iscsi_target_configfs.c @@ -1981,7 +1981,7 @@ static void lio_set_default_node_attributes(struct se_node_acl *se_acl) static int lio_check_stop_free(struct se_cmd *se_cmd) { - return target_put_sess_cmd(se_cmd->se_sess, se_cmd); + return target_put_sess_cmd(se_cmd); } static void lio_release_cmd(struct se_cmd *se_cmd) diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index b18edda3e8af..231e2e0e5894 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -746,7 +746,7 @@ void iscsit_free_cmd(struct iscsi_cmd *cmd, bool shutdown) rc = transport_generic_free_cmd(&cmd->se_cmd, shutdown); if (!rc && shutdown && se_cmd && se_cmd->se_sess) { __iscsit_free_cmd(cmd, true, shutdown); - target_put_sess_cmd(se_cmd->se_sess, se_cmd); + target_put_sess_cmd(se_cmd); } break; case ISCSI_OP_REJECT: @@ -762,7 +762,7 @@ void iscsit_free_cmd(struct iscsi_cmd *cmd, bool shutdown) rc = transport_generic_free_cmd(&cmd->se_cmd, shutdown); if (!rc && shutdown && se_cmd->se_sess) { __iscsit_free_cmd(cmd, true, shutdown); - target_put_sess_cmd(se_cmd->se_sess, se_cmd); + target_put_sess_cmd(se_cmd); } break; } diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index 315ec3458eeb..adb8016955c4 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -71,7 +71,7 @@ void core_tmr_release_req(struct se_tmr_req *tmr) if (dev) { spin_lock_irqsave(&dev->se_tmr_lock, flags); - list_del(&tmr->tmr_list); + list_del_init(&tmr->tmr_list); spin_unlock_irqrestore(&dev->se_tmr_lock, flags); } @@ -153,7 +153,7 @@ void core_tmr_abort_task( cancel_work_sync(&se_cmd->work); transport_wait_for_tasks(se_cmd); - target_put_sess_cmd(se_sess, se_cmd); + target_put_sess_cmd(se_cmd); transport_cmd_finish_abort(se_cmd, true); printk("ABORT_TASK: Sending TMR_FUNCTION_COMPLETE for" @@ -175,9 +175,11 @@ static void core_tmr_drain_tmr_list( struct list_head *preempt_and_abort_list) { LIST_HEAD(drain_tmr_list); + struct se_session *sess; struct se_tmr_req *tmr_p, *tmr_pp; struct se_cmd *cmd; unsigned long flags; + bool rc; /* * Release all pending and outgoing TMRs aside from the received * LUN_RESET tmr.. @@ -203,17 +205,31 @@ static void core_tmr_drain_tmr_list( if (target_check_cdb_and_preempt(preempt_and_abort_list, cmd)) continue; + sess = cmd->se_sess; + if (WARN_ON_ONCE(!sess)) + continue; + + spin_lock(&sess->sess_cmd_lock); spin_lock(&cmd->t_state_lock); if (!(cmd->transport_state & CMD_T_ACTIVE)) { spin_unlock(&cmd->t_state_lock); + spin_unlock(&sess->sess_cmd_lock); continue; } if (cmd->t_state == TRANSPORT_ISTATE_PROCESSING) { spin_unlock(&cmd->t_state_lock); + spin_unlock(&sess->sess_cmd_lock); continue; } + cmd->transport_state |= CMD_T_ABORTED; spin_unlock(&cmd->t_state_lock); + rc = kref_get_unless_zero(&cmd->cmd_kref); + spin_unlock(&sess->sess_cmd_lock); + if (!rc) { + printk("LUN_RESET TMR: non-zero kref_get_unless_zero\n"); + continue; + } list_move_tail(&tmr_p->tmr_list, &drain_tmr_list); } spin_unlock_irqrestore(&dev->se_tmr_lock, flags); @@ -227,7 +243,11 @@ static void core_tmr_drain_tmr_list( (preempt_and_abort_list) ? "Preempt" : "", tmr_p, tmr_p->function, tmr_p->response, cmd->t_state); + cancel_work_sync(&cmd->work); + transport_wait_for_tasks(cmd); + transport_cmd_finish_abort(cmd, 1); + target_put_sess_cmd(cmd); } } diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 675f2d9d1f14..3881504b40d8 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1419,7 +1419,7 @@ int target_submit_cmd_map_sgls(struct se_cmd *se_cmd, struct se_session *se_sess * for fabrics using TARGET_SCF_ACK_KREF that expect a second * kref_put() to happen during fabric packet acknowledgement. */ - ret = target_get_sess_cmd(se_sess, se_cmd, (flags & TARGET_SCF_ACK_KREF)); + ret = target_get_sess_cmd(se_cmd, flags & TARGET_SCF_ACK_KREF); if (ret) return ret; /* @@ -1433,7 +1433,7 @@ int target_submit_cmd_map_sgls(struct se_cmd *se_cmd, struct se_session *se_sess rc = transport_lookup_cmd_lun(se_cmd, unpacked_lun); if (rc) { transport_send_check_condition_and_sense(se_cmd, rc, 0); - target_put_sess_cmd(se_sess, se_cmd); + target_put_sess_cmd(se_cmd); return 0; } @@ -1584,7 +1584,7 @@ int target_submit_tmr(struct se_cmd *se_cmd, struct se_session *se_sess, se_cmd->se_tmr_req->ref_task_tag = tag; /* See target_submit_cmd for commentary */ - ret = target_get_sess_cmd(se_sess, se_cmd, (flags & TARGET_SCF_ACK_KREF)); + ret = target_get_sess_cmd(se_cmd, flags & TARGET_SCF_ACK_KREF); if (ret) { core_tmr_release_req(se_cmd->se_tmr_req); return ret; @@ -2227,7 +2227,7 @@ static int transport_release_cmd(struct se_cmd *cmd) * If this cmd has been setup with target_get_sess_cmd(), drop * the kref and call ->release_cmd() in kref callback. */ - return target_put_sess_cmd(cmd->se_sess, cmd); + return target_put_sess_cmd(cmd); } /** @@ -2471,13 +2471,12 @@ int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks) EXPORT_SYMBOL(transport_generic_free_cmd); /* target_get_sess_cmd - Add command to active ->sess_cmd_list - * @se_sess: session to reference * @se_cmd: command descriptor to add * @ack_kref: Signal that fabric will perform an ack target_put_sess_cmd() */ -int target_get_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd, - bool ack_kref) +int target_get_sess_cmd(struct se_cmd *se_cmd, bool ack_kref) { + struct se_session *se_sess = se_cmd->se_sess; unsigned long flags; int ret = 0; @@ -2499,7 +2498,7 @@ out: spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); if (ret && ack_kref) - target_put_sess_cmd(se_sess, se_cmd); + target_put_sess_cmd(se_cmd); return ret; } @@ -2528,11 +2527,12 @@ static void target_release_cmd_kref(struct kref *kref) } /* target_put_sess_cmd - Check for active I/O shutdown via kref_put - * @se_sess: session to reference * @se_cmd: command descriptor to drop */ -int target_put_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd) +int target_put_sess_cmd(struct se_cmd *se_cmd) { + struct se_session *se_sess = se_cmd->se_sess; + if (!se_sess) { se_cmd->se_tfo->release_cmd(se_cmd); return 1; @@ -3025,8 +3025,17 @@ static void target_tmr_work(struct work_struct *work) struct se_cmd *cmd = container_of(work, struct se_cmd, work); struct se_device *dev = cmd->se_dev; struct se_tmr_req *tmr = cmd->se_tmr_req; + unsigned long flags; int ret; + spin_lock_irqsave(&cmd->t_state_lock, flags); + if (cmd->transport_state & CMD_T_ABORTED) { + tmr->response = TMR_FUNCTION_REJECTED; + spin_unlock_irqrestore(&cmd->t_state_lock, flags); + goto check_stop; + } + spin_unlock_irqrestore(&cmd->t_state_lock, flags); + switch (tmr->function) { case TMR_ABORT_TASK: core_tmr_abort_task(dev, tmr, cmd->se_sess); @@ -3054,9 +3063,17 @@ static void target_tmr_work(struct work_struct *work) break; } + spin_lock_irqsave(&cmd->t_state_lock, flags); + if (cmd->transport_state & CMD_T_ABORTED) { + spin_unlock_irqrestore(&cmd->t_state_lock, flags); + goto check_stop; + } cmd->t_state = TRANSPORT_ISTATE_PROCESSING; + spin_unlock_irqrestore(&cmd->t_state_lock, flags); + cmd->se_tfo->queue_tm_rsp(cmd); +check_stop: transport_cmd_check_stop_to_fabric(cmd); } diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index 4d5e8409769c..254c183a5efe 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -672,7 +672,14 @@ static void pty_unix98_remove(struct tty_driver *driver, struct tty_struct *tty) /* this is called once with whichever end is closed last */ static void pty_unix98_shutdown(struct tty_struct *tty) { - devpts_kill_index(tty->driver_data, tty->index); + struct inode *ptmx_inode; + + if (tty->driver->subtype == PTY_TYPE_MASTER) + ptmx_inode = tty->driver_data; + else + ptmx_inode = tty->link->driver_data; + devpts_kill_index(ptmx_inode, tty->index); + devpts_del_ref(ptmx_inode); } static const struct tty_operations ptm_unix98_ops = { @@ -764,6 +771,18 @@ static int ptmx_open(struct inode *inode, struct file *filp) set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */ tty->driver_data = inode; + /* + * In the case where all references to ptmx inode are dropped and we + * still have /dev/tty opened pointing to the master/slave pair (ptmx + * is closed/released before /dev/tty), we must make sure that the inode + * is still valid when we call the final pty_unix98_shutdown, thus we + * hold an additional reference to the ptmx inode. For the same /dev/tty + * last close case, we also need to make sure the super_block isn't + * destroyed (devpts instance unmounted), before /dev/tty is closed and + * on its release devpts_kill_index is called. + */ + devpts_add_ref(inode); + tty_add_file(tty, filp); slave_inode = devpts_pty_new(inode, diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 2fd163b75665..b82b2a0f82a3 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -2002,6 +2002,7 @@ pci_wch_ch38x_setup(struct serial_private *priv, #define PCIE_VENDOR_ID_WCH 0x1c00 #define PCIE_DEVICE_ID_WCH_CH382_2S1P 0x3250 #define PCIE_DEVICE_ID_WCH_CH384_4S 0x3470 +#define PCIE_DEVICE_ID_WCH_CH382_2S 0x3253 #define PCI_DEVICE_ID_EXAR_XR17V4358 0x4358 #define PCI_DEVICE_ID_EXAR_XR17V8358 0x8358 @@ -2729,6 +2730,14 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = { .subdevice = PCI_ANY_ID, .setup = pci_wch_ch353_setup, }, + /* WCH CH382 2S card (16850 clone) */ + { + .vendor = PCIE_VENDOR_ID_WCH, + .device = PCIE_DEVICE_ID_WCH_CH382_2S, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = pci_wch_ch38x_setup, + }, /* WCH CH382 2S1P card (16850 clone) */ { .vendor = PCIE_VENDOR_ID_WCH, @@ -3049,6 +3058,7 @@ enum pci_board_num_t { pbn_fintek_4, pbn_fintek_8, pbn_fintek_12, + pbn_wch382_2, pbn_wch384_4, pbn_pericom_PI7C9X7951, pbn_pericom_PI7C9X7952, @@ -3879,6 +3889,13 @@ static struct pciserial_board pci_boards[] = { .base_baud = 115200, .first_offset = 0x40, }, + [pbn_wch382_2] = { + .flags = FL_BASE0, + .num_ports = 2, + .base_baud = 115200, + .uart_offset = 8, + .first_offset = 0xC0, + }, [pbn_wch384_4] = { .flags = FL_BASE0, .num_ports = 4, @@ -5691,6 +5708,10 @@ static struct pci_device_id serial_pci_tbl[] = { PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_b0_bt_2_115200 }, + { PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH382_2S, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, pbn_wch382_2 }, + { PCIE_VENDOR_ID_WCH, PCIE_DEVICE_ID_WCH_CH384_4S, PCI_ANY_ID, PCI_ANY_ID, 0, 0, pbn_wch384_4 }, diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index 7f49172ccd86..0a88693cd8ca 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -1368,7 +1368,7 @@ static inline void serial_omap_add_console_port(struct uart_omap_port *up) /* Enable or disable the rs485 support */ static int -serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485conf) +serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485) { struct uart_omap_port *up = to_uart_omap_port(port); unsigned int mode; @@ -1381,8 +1381,12 @@ serial_omap_config_rs485(struct uart_port *port, struct serial_rs485 *rs485conf) up->ier = 0; serial_out(up, UART_IER, 0); + /* Clamp the delays to [0, 100ms] */ + rs485->delay_rts_before_send = min(rs485->delay_rts_before_send, 100U); + rs485->delay_rts_after_send = min(rs485->delay_rts_after_send, 100U); + /* store new config */ - port->rs485 = *rs485conf; + port->rs485 = *rs485; /* * Just as a precaution, only allow rs485 diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index ea32b386797f..636435b41293 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -607,7 +607,7 @@ static void vhost_scsi_free_cmd(struct vhost_scsi_cmd *cmd) static int vhost_scsi_check_stop_free(struct se_cmd *se_cmd) { - return target_put_sess_cmd(se_cmd->se_sess, se_cmd); + return target_put_sess_cmd(se_cmd); } static void diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 723470850b94..30bc9fa763bd 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1369,7 +1369,8 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, read_extent_buffer(eb, dest + bytes_left, name_off, name_len); if (eb != eb_in) { - btrfs_tree_read_unlock_blocking(eb); + if (!path->skip_locking) + btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); } ret = btrfs_find_item(fs_root, path, parent, 0, @@ -1389,9 +1390,10 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, eb = path->nodes[0]; /* make sure we can use eb after releasing the path */ if (eb != eb_in) { - atomic_inc(&eb->refs); - btrfs_tree_read_lock(eb); - btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + if (!path->skip_locking) + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + path->nodes[0] = NULL; + path->locks[0] = 0; } btrfs_release_path(path); iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref); diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index a2ae42720a6a..bc2d048a9eb9 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1690,7 +1690,7 @@ int btrfs_should_delete_dir_index(struct list_head *del_list, * */ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, - struct list_head *ins_list) + struct list_head *ins_list, bool *emitted) { struct btrfs_dir_item *di; struct btrfs_delayed_item *curr, *next; @@ -1734,6 +1734,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, if (over) return 1; + *emitted = true; } return 0; } diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index f70119f25421..0167853c84ae 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -144,7 +144,7 @@ void btrfs_put_delayed_items(struct list_head *ins_list, int btrfs_should_delete_dir_index(struct list_head *del_list, u64 index); int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, - struct list_head *ins_list); + struct list_head *ins_list, bool *emitted); /* for init */ int __init btrfs_delayed_inode_init(void); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index df4e0462976e..b114a0539d3d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5666,6 +5666,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) char *name_ptr; int name_len; int is_curr = 0; /* ctx->pos points to the current index? */ + bool emitted; /* FIXME, use a real flag for deciding about the key type */ if (root->fs_info->tree_root == root) @@ -5694,6 +5695,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) if (ret < 0) goto err; + emitted = false; while (1) { leaf = path->nodes[0]; slot = path->slots[0]; @@ -5773,6 +5775,7 @@ skip: if (over) goto nopos; + emitted = true; di_len = btrfs_dir_name_len(leaf, di) + btrfs_dir_data_len(leaf, di) + sizeof(*di); di_cur += di_len; @@ -5785,11 +5788,20 @@ next: if (key_type == BTRFS_DIR_INDEX_KEY) { if (is_curr) ctx->pos++; - ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list); + ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list, &emitted); if (ret) goto nopos; } + /* + * If we haven't emitted any dir entry, we must not touch ctx->pos as + * it was was set to the termination value in previous call. We assume + * that "." and ".." were emitted if we reach this point and set the + * termination value as well for an empty directory. + */ + if (ctx->pos > 2 && !emitted) + goto nopos; + /* Reached end of directory/root. Bump pos past the last item. */ ctx->pos++; diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index afa09fce8151..e682b36a210f 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -714,7 +714,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) ses->auth_key.response = kmalloc(baselen + tilen, GFP_KERNEL); if (!ses->auth_key.response) { - rc = ENOMEM; + rc = -ENOMEM; ses->auth_key.len = 0; goto setup_ntlmv2_rsp_ret; } diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index add566303c68..91360444adf5 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -569,6 +569,26 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx) mutex_unlock(&allocated_ptys_lock); } +/* + * pty code needs to hold extra references in case of last /dev/tty close + */ + +void devpts_add_ref(struct inode *ptmx_inode) +{ + struct super_block *sb = pts_sb_from_inode(ptmx_inode); + + atomic_inc(&sb->s_active); + ihold(ptmx_inode); +} + +void devpts_del_ref(struct inode *ptmx_inode) +{ + struct super_block *sb = pts_sb_from_inode(ptmx_inode); + + iput(ptmx_inode); + deactivate_super(sb); +} + /** * devpts_pty_new -- create a new inode in /dev/pts/ * @ptmx_inode: inode of the master diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 966c614822cc..2b3a53a51582 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3133,29 +3133,29 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, * case, we allocate an io_end structure to hook to the iocb. */ iocb->private = NULL; - ext4_inode_aio_set(inode, NULL); - if (!is_sync_kiocb(iocb)) { - io_end = ext4_init_io_end(inode, GFP_NOFS); - if (!io_end) { - ret = -ENOMEM; - goto retake_lock; - } - /* - * Grab reference for DIO. Will be dropped in ext4_end_io_dio() - */ - iocb->private = ext4_get_io_end(io_end); - /* - * we save the io structure for current async direct - * IO, so that later ext4_map_blocks() could flag the - * io structure whether there is a unwritten extents - * needs to be converted when IO is completed. - */ - ext4_inode_aio_set(inode, io_end); - } - if (overwrite) { get_block_func = ext4_get_block_write_nolock; } else { + ext4_inode_aio_set(inode, NULL); + if (!is_sync_kiocb(iocb)) { + io_end = ext4_init_io_end(inode, GFP_NOFS); + if (!io_end) { + ret = -ENOMEM; + goto retake_lock; + } + /* + * Grab reference for DIO. Will be dropped in + * ext4_end_io_dio() + */ + iocb->private = ext4_get_io_end(io_end); + /* + * we save the io structure for current async direct + * IO, so that later ext4_map_blocks() could flag the + * io structure whether there is a unwritten extents + * needs to be converted when IO is completed. + */ + ext4_inode_aio_set(inode, io_end); + } get_block_func = ext4_get_block_write; dio_flags = DIO_LOCKING; } diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 370420bfae8d..7da8ac1047f8 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -268,11 +268,12 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode, ext4_lblk_t orig_blk_offset, donor_blk_offset; unsigned long blocksize = orig_inode->i_sb->s_blocksize; unsigned int tmp_data_size, data_size, replaced_size; - int err2, jblocks, retries = 0; + int i, err2, jblocks, retries = 0; int replaced_count = 0; int from = data_offset_in_page << orig_inode->i_blkbits; int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; struct super_block *sb = orig_inode->i_sb; + struct buffer_head *bh = NULL; /* * It needs twice the amount of ordinary journal buffers because @@ -383,8 +384,16 @@ data_copy: } /* Perform all necessary steps similar write_begin()/write_end() * but keeping in mind that i_size will not change */ - *err = __block_write_begin(pagep[0], from, replaced_size, - ext4_get_block); + if (!page_has_buffers(pagep[0])) + create_empty_buffers(pagep[0], 1 << orig_inode->i_blkbits, 0); + bh = page_buffers(pagep[0]); + for (i = 0; i < data_offset_in_page; i++) + bh = bh->b_this_page; + for (i = 0; i < block_len_in_page; i++) { + *err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0); + if (*err < 0) + break; + } if (!*err) *err = block_commit_write(pagep[0], from, from + replaced_size); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index cf0c472047e3..0e783b9f7007 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -198,7 +198,7 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size) if (flex_gd == NULL) goto out3; - if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data)) + if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data)) goto out2; flex_gd->count = flexbg_size; diff --git a/include/asm-generic/cputime_nsecs.h b/include/asm-generic/cputime_nsecs.h index 0419485891f2..0f1c6f315cdc 100644 --- a/include/asm-generic/cputime_nsecs.h +++ b/include/asm-generic/cputime_nsecs.h @@ -75,7 +75,7 @@ typedef u64 __nocast cputime64_t; */ static inline cputime_t timespec_to_cputime(const struct timespec *val) { - u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_nsec; + u64 ret = (u64)val->tv_sec * NSEC_PER_SEC + val->tv_nsec; return (__force cputime_t) ret; } static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val) @@ -91,7 +91,8 @@ static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val) */ static inline cputime_t timeval_to_cputime(const struct timeval *val) { - u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_usec * NSEC_PER_USEC; + u64 ret = (u64)val->tv_sec * NSEC_PER_SEC + + val->tv_usec * NSEC_PER_USEC; return (__force cputime_t) ret; } static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val) diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h new file mode 100644 index 000000000000..8d9c7e7a6432 --- /dev/null +++ b/include/linux/cgroup-defs.h @@ -0,0 +1,470 @@ +/* + * linux/cgroup-defs.h - basic definitions for cgroup + * + * This file provides basic type and interface. Include this file directly + * only if necessary to avoid cyclic dependencies. + */ +#ifndef _LINUX_CGROUP_DEFS_H +#define _LINUX_CGROUP_DEFS_H + +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_CGROUPS + +struct cgroup; +struct cgroup_root; +struct cgroup_subsys; +struct cgroup_taskset; +struct kernfs_node; +struct kernfs_ops; +struct kernfs_open_file; + +#define MAX_CGROUP_TYPE_NAMELEN 32 +#define MAX_CGROUP_ROOT_NAMELEN 64 +#define MAX_CFTYPE_NAME 64 + +/* define the enumeration of all cgroup subsystems */ +#define SUBSYS(_x) _x ## _cgrp_id, +enum cgroup_subsys_id { +#include + CGROUP_SUBSYS_COUNT, +}; +#undef SUBSYS + +/* bits in struct cgroup_subsys_state flags field */ +enum { + CSS_NO_REF = (1 << 0), /* no reference counting for this css */ + CSS_ONLINE = (1 << 1), /* between ->css_online() and ->css_offline() */ + CSS_RELEASED = (1 << 2), /* refcnt reached zero, released */ +}; + +/* bits in struct cgroup flags field */ +enum { + /* Control Group requires release notifications to userspace */ + CGRP_NOTIFY_ON_RELEASE, + /* + * Clone the parent's configuration when creating a new child + * cpuset cgroup. For historical reasons, this option can be + * specified at mount time and thus is implemented here. + */ + CGRP_CPUSET_CLONE_CHILDREN, +}; + +/* cgroup_root->flags */ +enum { + CGRP_ROOT_SANE_BEHAVIOR = (1 << 0), /* __DEVEL__sane_behavior specified */ + CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */ + CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */ +}; + +/* cftype->flags */ +enum { + CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ + CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ + CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ + + /* internal flags, do not use outside cgroup core proper */ + __CFTYPE_ONLY_ON_DFL = (1 << 16), /* only on default hierarchy */ + __CFTYPE_NOT_ON_DFL = (1 << 17), /* not on default hierarchy */ +}; + +/* + * Per-subsystem/per-cgroup state maintained by the system. This is the + * fundamental structural building block that controllers deal with. + * + * Fields marked with "PI:" are public and immutable and may be accessed + * directly without synchronization. + */ +struct cgroup_subsys_state { + /* PI: the cgroup that this css is attached to */ + struct cgroup *cgroup; + + /* PI: the cgroup subsystem that this css is attached to */ + struct cgroup_subsys *ss; + + /* reference count - access via css_[try]get() and css_put() */ + struct percpu_ref refcnt; + + /* PI: the parent css */ + struct cgroup_subsys_state *parent; + + /* siblings list anchored at the parent's ->children */ + struct list_head sibling; + struct list_head children; + + /* + * PI: Subsys-unique ID. 0 is unused and root is always 1. The + * matching css can be looked up using css_from_id(). + */ + int id; + + unsigned int flags; + + /* + * Monotonically increasing unique serial number which defines a + * uniform order among all csses. It's guaranteed that all + * ->children lists are in the ascending order of ->serial_nr and + * used to allow interrupting and resuming iterations. + */ + u64 serial_nr; + + /* + * Incremented by online self and children. Used to guarantee that + * parents are not offlined before their children. + */ + atomic_t online_cnt; + + /* percpu_ref killing and RCU release */ + struct rcu_head rcu_head; + struct work_struct destroy_work; +}; + +/* + * A css_set is a structure holding pointers to a set of + * cgroup_subsys_state objects. This saves space in the task struct + * object and speeds up fork()/exit(), since a single inc/dec and a + * list_add()/del() can bump the reference count on the entire cgroup + * set for a task. + */ +struct css_set { + /* Reference count */ + atomic_t refcount; + + /* + * List running through all cgroup groups in the same hash + * slot. Protected by css_set_lock + */ + struct hlist_node hlist; + + /* + * Lists running through all tasks using this cgroup group. + * mg_tasks lists tasks which belong to this cset but are in the + * process of being migrated out or in. Protected by + * css_set_rwsem, but, during migration, once tasks are moved to + * mg_tasks, it can be read safely while holding cgroup_mutex. + */ + struct list_head tasks; + struct list_head mg_tasks; + + /* + * List of cgrp_cset_links pointing at cgroups referenced from this + * css_set. Protected by css_set_lock. + */ + struct list_head cgrp_links; + + /* the default cgroup associated with this css_set */ + struct cgroup *dfl_cgrp; + + /* + * Set of subsystem states, one for each subsystem. This array is + * immutable after creation apart from the init_css_set during + * subsystem registration (at boot time). + */ + struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + + /* + * List of csets participating in the on-going migration either as + * source or destination. Protected by cgroup_mutex. + */ + struct list_head mg_preload_node; + struct list_head mg_node; + + /* + * If this cset is acting as the source of migration the following + * two fields are set. mg_src_cgrp is the source cgroup of the + * on-going migration and mg_dst_cset is the destination cset the + * target tasks on this cset should be migrated to. Protected by + * cgroup_mutex. + */ + struct cgroup *mg_src_cgrp; + struct css_set *mg_dst_cset; + + /* + * On the default hierarhcy, ->subsys[ssid] may point to a css + * attached to an ancestor instead of the cgroup this css_set is + * associated with. The following node is anchored at + * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to + * iterate through all css's attached to a given cgroup. + */ + struct list_head e_cset_node[CGROUP_SUBSYS_COUNT]; + + /* For RCU-protected deletion */ + struct rcu_head rcu_head; +}; + +struct cgroup { + /* self css with NULL ->ss, points back to this cgroup */ + struct cgroup_subsys_state self; + + unsigned long flags; /* "unsigned long" so bitops work */ + + /* + * idr allocated in-hierarchy ID. + * + * ID 0 is not used, the ID of the root cgroup is always 1, and a + * new cgroup will be assigned with a smallest available ID. + * + * Allocating/Removing ID must be protected by cgroup_mutex. + */ + int id; + + /* + * If this cgroup contains any tasks, it contributes one to + * populated_cnt. All children with non-zero popuplated_cnt of + * their own contribute one. The count is zero iff there's no task + * in this cgroup or its subtree. + */ + int populated_cnt; + + struct kernfs_node *kn; /* cgroup kernfs entry */ + struct kernfs_node *populated_kn; /* kn for "cgroup.subtree_populated" */ + + /* + * The bitmask of subsystems enabled on the child cgroups. + * ->subtree_control is the one configured through + * "cgroup.subtree_control" while ->child_subsys_mask is the + * effective one which may have more subsystems enabled. + * Controller knobs are made available iff it's enabled in + * ->subtree_control. + */ + unsigned int subtree_control; + unsigned int child_subsys_mask; + + /* Private pointers for each registered subsystem */ + struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; + + struct cgroup_root *root; + + /* + * List of cgrp_cset_links pointing at css_sets with tasks in this + * cgroup. Protected by css_set_lock. + */ + struct list_head cset_links; + + /* + * On the default hierarchy, a css_set for a cgroup with some + * susbsys disabled will point to css's which are associated with + * the closest ancestor which has the subsys enabled. The + * following lists all css_sets which point to this cgroup's css + * for the given subsystem. + */ + struct list_head e_csets[CGROUP_SUBSYS_COUNT]; + + /* + * list of pidlists, up to two for each namespace (one for procs, one + * for tasks); created on demand. + */ + struct list_head pidlists; + struct mutex pidlist_mutex; + + /* used to wait for offlining of csses */ + wait_queue_head_t offline_waitq; + + /* used to schedule release agent */ + struct work_struct release_agent_work; +}; + +/* + * A cgroup_root represents the root of a cgroup hierarchy, and may be + * associated with a kernfs_root to form an active hierarchy. This is + * internal to cgroup core. Don't access directly from controllers. + */ +struct cgroup_root { + struct kernfs_root *kf_root; + + /* The bitmask of subsystems attached to this hierarchy */ + unsigned int subsys_mask; + + /* Unique id for this hierarchy. */ + int hierarchy_id; + + /* The root cgroup. Root is destroyed on its release. */ + struct cgroup cgrp; + + /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ + atomic_t nr_cgrps; + + /* A list running through the active hierarchies */ + struct list_head root_list; + + /* Hierarchy-specific flags */ + unsigned int flags; + + /* IDs for cgroups in this hierarchy */ + struct idr cgroup_idr; + + /* The path to use for release notifications. */ + char release_agent_path[PATH_MAX]; + + /* The name for this hierarchy - may be empty */ + char name[MAX_CGROUP_ROOT_NAMELEN]; +}; + +/* + * struct cftype: handler definitions for cgroup control files + * + * When reading/writing to a file: + * - the cgroup to use is file->f_path.dentry->d_parent->d_fsdata + * - the 'cftype' of the file is file->f_path.dentry->d_fsdata + */ +struct cftype { + /* + * By convention, the name should begin with the name of the + * subsystem, followed by a period. Zero length string indicates + * end of cftype array. + */ + char name[MAX_CFTYPE_NAME]; + int private; + /* + * If not 0, file mode is set to this value, otherwise it will + * be figured out automatically + */ + umode_t mode; + + /* + * The maximum length of string, excluding trailing nul, that can + * be passed to write. If < PAGE_SIZE-1, PAGE_SIZE-1 is assumed. + */ + size_t max_write_len; + + /* CFTYPE_* flags */ + unsigned int flags; + + /* + * Fields used for internal bookkeeping. Initialized automatically + * during registration. + */ + struct cgroup_subsys *ss; /* NULL for cgroup core files */ + struct list_head node; /* anchored at ss->cfts */ + struct kernfs_ops *kf_ops; + + /* + * read_u64() is a shortcut for the common case of returning a + * single integer. Use it in place of read() + */ + u64 (*read_u64)(struct cgroup_subsys_state *css, struct cftype *cft); + /* + * read_s64() is a signed version of read_u64() + */ + s64 (*read_s64)(struct cgroup_subsys_state *css, struct cftype *cft); + + /* generic seq_file read interface */ + int (*seq_show)(struct seq_file *sf, void *v); + + /* optional ops, implement all or none */ + void *(*seq_start)(struct seq_file *sf, loff_t *ppos); + void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos); + void (*seq_stop)(struct seq_file *sf, void *v); + + /* + * write_u64() is a shortcut for the common case of accepting + * a single integer (as parsed by simple_strtoull) from + * userspace. Use in place of write(); return 0 or error. + */ + int (*write_u64)(struct cgroup_subsys_state *css, struct cftype *cft, + u64 val); + /* + * write_s64() is a signed version of write_u64() + */ + int (*write_s64)(struct cgroup_subsys_state *css, struct cftype *cft, + s64 val); + + /* + * write() is the generic write callback which maps directly to + * kernfs write operation and overrides all other operations. + * Maximum write size is determined by ->max_write_len. Use + * of_css/cft() to access the associated css and cft. + */ + ssize_t (*write)(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lock_class_key lockdep_key; +#endif +}; + +/* + * Control Group subsystem type. + * See Documentation/cgroups/cgroups.txt for details + */ +struct cgroup_subsys { + struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css); + int (*css_online)(struct cgroup_subsys_state *css); + void (*css_offline)(struct cgroup_subsys_state *css); + void (*css_released)(struct cgroup_subsys_state *css); + void (*css_free)(struct cgroup_subsys_state *css); + void (*css_reset)(struct cgroup_subsys_state *css); + void (*css_e_css_changed)(struct cgroup_subsys_state *css); + + int (*can_attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); + void (*cancel_attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); + void (*attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); + void (*fork)(struct task_struct *task); + void (*exit)(struct cgroup_subsys_state *css, + struct cgroup_subsys_state *old_css, + struct task_struct *task); + void (*bind)(struct cgroup_subsys_state *root_css); + + int disabled; + int early_init; + + /* + * If %false, this subsystem is properly hierarchical - + * configuration, resource accounting and restriction on a parent + * cgroup cover those of its children. If %true, hierarchy support + * is broken in some ways - some subsystems ignore hierarchy + * completely while others are only implemented half-way. + * + * It's now disallowed to create nested cgroups if the subsystem is + * broken and cgroup core will emit a warning message on such + * cases. Eventually, all subsystems will be made properly + * hierarchical and this will go away. + */ + bool broken_hierarchy; + bool warned_broken_hierarchy; + + /* the following two fields are initialized automtically during boot */ + int id; + const char *name; + + /* link to parent, protected by cgroup_lock() */ + struct cgroup_root *root; + + /* idr for css->id */ + struct idr css_idr; + + /* + * List of cftypes. Each entry is the first entry of an array + * terminated by zero length name. + */ + struct list_head cfts; + + /* + * Base cftypes which are automatically registered. The two can + * point to the same array. + */ + struct cftype *dfl_cftypes; /* for the default hierarchy */ + struct cftype *legacy_cftypes; /* for the legacy hierarchies */ + + /* + * A subsystem may depend on other subsystems. When such subsystem + * is enabled on a cgroup, the depended-upon subsystems are enabled + * together if available. Subsystems enabled due to dependency are + * not visible to userland until explicitly enabled. The following + * specifies the mask of subsystems that this one depends on. + */ + unsigned int depends_on; +}; + +#endif /* CONFIG_CGROUPS */ +#endif /* _LINUX_CGROUP_DEFS_H */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b9cb94c3102a..96a2ecd5aa69 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -11,23 +11,16 @@ #include #include #include -#include #include #include #include -#include -#include #include -#include #include #include -#include -#ifdef CONFIG_CGROUPS +#include -struct cgroup_root; -struct cgroup_subsys; -struct cgroup; +#ifdef CONFIG_CGROUPS extern int cgroup_init_early(void); extern int cgroup_init(void); @@ -40,66 +33,6 @@ extern int cgroupstats_build(struct cgroupstats *stats, extern int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk); -/* define the enumeration of all cgroup subsystems */ -#define SUBSYS(_x) _x ## _cgrp_id, -enum cgroup_subsys_id { -#include - CGROUP_SUBSYS_COUNT, -}; -#undef SUBSYS - -/* - * Per-subsystem/per-cgroup state maintained by the system. This is the - * fundamental structural building block that controllers deal with. - * - * Fields marked with "PI:" are public and immutable and may be accessed - * directly without synchronization. - */ -struct cgroup_subsys_state { - /* PI: the cgroup that this css is attached to */ - struct cgroup *cgroup; - - /* PI: the cgroup subsystem that this css is attached to */ - struct cgroup_subsys *ss; - - /* reference count - access via css_[try]get() and css_put() */ - struct percpu_ref refcnt; - - /* PI: the parent css */ - struct cgroup_subsys_state *parent; - - /* siblings list anchored at the parent's ->children */ - struct list_head sibling; - struct list_head children; - - /* - * PI: Subsys-unique ID. 0 is unused and root is always 1. The - * matching css can be looked up using css_from_id(). - */ - int id; - - unsigned int flags; - - /* - * Monotonically increasing unique serial number which defines a - * uniform order among all csses. It's guaranteed that all - * ->children lists are in the ascending order of ->serial_nr and - * used to allow interrupting and resuming iterations. - */ - u64 serial_nr; - - /* percpu_ref killing and RCU release */ - struct rcu_head rcu_head; - struct work_struct destroy_work; -}; - -/* bits in struct cgroup_subsys_state flags field */ -enum { - CSS_NO_REF = (1 << 0), /* no reference counting for this css */ - CSS_ONLINE = (1 << 1), /* between ->css_online() and ->css_offline() */ - CSS_RELEASED = (1 << 2), /* refcnt reached zero, released */ -}; - /** * css_get - obtain a reference on the specified css * @css: target css @@ -185,307 +118,6 @@ static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n) percpu_ref_put_many(&css->refcnt, n); } -/* bits in struct cgroup flags field */ -enum { - /* Control Group requires release notifications to userspace */ - CGRP_NOTIFY_ON_RELEASE, - /* - * Clone the parent's configuration when creating a new child - * cpuset cgroup. For historical reasons, this option can be - * specified at mount time and thus is implemented here. - */ - CGRP_CPUSET_CLONE_CHILDREN, -}; - -struct cgroup { - /* self css with NULL ->ss, points back to this cgroup */ - struct cgroup_subsys_state self; - - unsigned long flags; /* "unsigned long" so bitops work */ - - /* - * idr allocated in-hierarchy ID. - * - * ID 0 is not used, the ID of the root cgroup is always 1, and a - * new cgroup will be assigned with a smallest available ID. - * - * Allocating/Removing ID must be protected by cgroup_mutex. - */ - int id; - - /* - * If this cgroup contains any tasks, it contributes one to - * populated_cnt. All children with non-zero popuplated_cnt of - * their own contribute one. The count is zero iff there's no task - * in this cgroup or its subtree. - */ - int populated_cnt; - - struct kernfs_node *kn; /* cgroup kernfs entry */ - struct kernfs_node *populated_kn; /* kn for "cgroup.subtree_populated" */ - - /* - * The bitmask of subsystems enabled on the child cgroups. - * ->subtree_control is the one configured through - * "cgroup.subtree_control" while ->child_subsys_mask is the - * effective one which may have more subsystems enabled. - * Controller knobs are made available iff it's enabled in - * ->subtree_control. - */ - unsigned int subtree_control; - unsigned int child_subsys_mask; - - /* Private pointers for each registered subsystem */ - struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; - - struct cgroup_root *root; - - /* - * List of cgrp_cset_links pointing at css_sets with tasks in this - * cgroup. Protected by css_set_lock. - */ - struct list_head cset_links; - - /* - * On the default hierarchy, a css_set for a cgroup with some - * susbsys disabled will point to css's which are associated with - * the closest ancestor which has the subsys enabled. The - * following lists all css_sets which point to this cgroup's css - * for the given subsystem. - */ - struct list_head e_csets[CGROUP_SUBSYS_COUNT]; - - /* - * list of pidlists, up to two for each namespace (one for procs, one - * for tasks); created on demand. - */ - struct list_head pidlists; - struct mutex pidlist_mutex; - - /* used to wait for offlining of csses */ - wait_queue_head_t offline_waitq; - - /* used to schedule release agent */ - struct work_struct release_agent_work; -}; - -#define MAX_CGROUP_ROOT_NAMELEN 64 - -/* cgroup_root->flags */ -enum { - CGRP_ROOT_SANE_BEHAVIOR = (1 << 0), /* __DEVEL__sane_behavior specified */ - CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */ - CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */ -}; - -/* - * A cgroup_root represents the root of a cgroup hierarchy, and may be - * associated with a kernfs_root to form an active hierarchy. This is - * internal to cgroup core. Don't access directly from controllers. - */ -struct cgroup_root { - struct kernfs_root *kf_root; - - /* The bitmask of subsystems attached to this hierarchy */ - unsigned int subsys_mask; - - /* Unique id for this hierarchy. */ - int hierarchy_id; - - /* The root cgroup. Root is destroyed on its release. */ - struct cgroup cgrp; - - /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ - atomic_t nr_cgrps; - - /* A list running through the active hierarchies */ - struct list_head root_list; - - /* Hierarchy-specific flags */ - unsigned int flags; - - /* IDs for cgroups in this hierarchy */ - struct idr cgroup_idr; - - /* The path to use for release notifications. */ - char release_agent_path[PATH_MAX]; - - /* The name for this hierarchy - may be empty */ - char name[MAX_CGROUP_ROOT_NAMELEN]; -}; - -/* - * A css_set is a structure holding pointers to a set of - * cgroup_subsys_state objects. This saves space in the task struct - * object and speeds up fork()/exit(), since a single inc/dec and a - * list_add()/del() can bump the reference count on the entire cgroup - * set for a task. - */ - -struct css_set { - - /* Reference count */ - atomic_t refcount; - - /* - * List running through all cgroup groups in the same hash - * slot. Protected by css_set_lock - */ - struct hlist_node hlist; - - /* - * Lists running through all tasks using this cgroup group. - * mg_tasks lists tasks which belong to this cset but are in the - * process of being migrated out or in. Protected by - * css_set_rwsem, but, during migration, once tasks are moved to - * mg_tasks, it can be read safely while holding cgroup_mutex. - */ - struct list_head tasks; - struct list_head mg_tasks; - - /* - * List of cgrp_cset_links pointing at cgroups referenced from this - * css_set. Protected by css_set_lock. - */ - struct list_head cgrp_links; - - /* the default cgroup associated with this css_set */ - struct cgroup *dfl_cgrp; - - /* - * Set of subsystem states, one for each subsystem. This array is - * immutable after creation apart from the init_css_set during - * subsystem registration (at boot time). - */ - struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; - - /* - * List of csets participating in the on-going migration either as - * source or destination. Protected by cgroup_mutex. - */ - struct list_head mg_preload_node; - struct list_head mg_node; - - /* - * If this cset is acting as the source of migration the following - * two fields are set. mg_src_cgrp is the source cgroup of the - * on-going migration and mg_dst_cset is the destination cset the - * target tasks on this cset should be migrated to. Protected by - * cgroup_mutex. - */ - struct cgroup *mg_src_cgrp; - struct css_set *mg_dst_cset; - - /* - * On the default hierarhcy, ->subsys[ssid] may point to a css - * attached to an ancestor instead of the cgroup this css_set is - * associated with. The following node is anchored at - * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to - * iterate through all css's attached to a given cgroup. - */ - struct list_head e_cset_node[CGROUP_SUBSYS_COUNT]; - - /* For RCU-protected deletion */ - struct rcu_head rcu_head; -}; - -/* - * struct cftype: handler definitions for cgroup control files - * - * When reading/writing to a file: - * - the cgroup to use is file->f_path.dentry->d_parent->d_fsdata - * - the 'cftype' of the file is file->f_path.dentry->d_fsdata - */ - -/* cftype->flags */ -enum { - CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ - CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ - CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ - - /* internal flags, do not use outside cgroup core proper */ - __CFTYPE_ONLY_ON_DFL = (1 << 16), /* only on default hierarchy */ - __CFTYPE_NOT_ON_DFL = (1 << 17), /* not on default hierarchy */ -}; - -#define MAX_CFTYPE_NAME 64 - -struct cftype { - /* - * By convention, the name should begin with the name of the - * subsystem, followed by a period. Zero length string indicates - * end of cftype array. - */ - char name[MAX_CFTYPE_NAME]; - int private; - /* - * If not 0, file mode is set to this value, otherwise it will - * be figured out automatically - */ - umode_t mode; - - /* - * The maximum length of string, excluding trailing nul, that can - * be passed to write. If < PAGE_SIZE-1, PAGE_SIZE-1 is assumed. - */ - size_t max_write_len; - - /* CFTYPE_* flags */ - unsigned int flags; - - /* - * Fields used for internal bookkeeping. Initialized automatically - * during registration. - */ - struct cgroup_subsys *ss; /* NULL for cgroup core files */ - struct list_head node; /* anchored at ss->cfts */ - struct kernfs_ops *kf_ops; - - /* - * read_u64() is a shortcut for the common case of returning a - * single integer. Use it in place of read() - */ - u64 (*read_u64)(struct cgroup_subsys_state *css, struct cftype *cft); - /* - * read_s64() is a signed version of read_u64() - */ - s64 (*read_s64)(struct cgroup_subsys_state *css, struct cftype *cft); - - /* generic seq_file read interface */ - int (*seq_show)(struct seq_file *sf, void *v); - - /* optional ops, implement all or none */ - void *(*seq_start)(struct seq_file *sf, loff_t *ppos); - void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos); - void (*seq_stop)(struct seq_file *sf, void *v); - - /* - * write_u64() is a shortcut for the common case of accepting - * a single integer (as parsed by simple_strtoull) from - * userspace. Use in place of write(); return 0 or error. - */ - int (*write_u64)(struct cgroup_subsys_state *css, struct cftype *cft, - u64 val); - /* - * write_s64() is a signed version of write_u64() - */ - int (*write_s64)(struct cgroup_subsys_state *css, struct cftype *cft, - s64 val); - - /* - * write() is the generic write callback which maps directly to - * kernfs write operation and overrides all other operations. - * Maximum write size is determined by ->max_write_len. Use - * of_css/cft() to access the associated css and cft. - */ - ssize_t (*write)(struct kernfs_open_file *of, - char *buf, size_t nbytes, loff_t off); - -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lock_class_key lockdep_key; -#endif -}; - extern struct cgroup_root cgrp_dfl_root; extern struct css_set init_css_set; @@ -612,11 +244,6 @@ int cgroup_rm_cftypes(struct cftype *cfts); bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor); -/* - * Control Group taskset, used to pass around set of tasks to cgroup_subsys - * methods. - */ -struct cgroup_taskset; struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset); struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset); @@ -629,84 +256,6 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset); for ((task) = cgroup_taskset_first((tset)); (task); \ (task) = cgroup_taskset_next((tset))) -/* - * Control Group subsystem type. - * See Documentation/cgroups/cgroups.txt for details - */ - -struct cgroup_subsys { - struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css); - int (*css_online)(struct cgroup_subsys_state *css); - void (*css_offline)(struct cgroup_subsys_state *css); - void (*css_released)(struct cgroup_subsys_state *css); - void (*css_free)(struct cgroup_subsys_state *css); - void (*css_reset)(struct cgroup_subsys_state *css); - void (*css_e_css_changed)(struct cgroup_subsys_state *css); - - int (*can_attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*cancel_attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*fork)(struct task_struct *task); - void (*exit)(struct cgroup_subsys_state *css, - struct cgroup_subsys_state *old_css, - struct task_struct *task); - void (*bind)(struct cgroup_subsys_state *root_css); - - int disabled; - int early_init; - - /* - * If %false, this subsystem is properly hierarchical - - * configuration, resource accounting and restriction on a parent - * cgroup cover those of its children. If %true, hierarchy support - * is broken in some ways - some subsystems ignore hierarchy - * completely while others are only implemented half-way. - * - * It's now disallowed to create nested cgroups if the subsystem is - * broken and cgroup core will emit a warning message on such - * cases. Eventually, all subsystems will be made properly - * hierarchical and this will go away. - */ - bool broken_hierarchy; - bool warned_broken_hierarchy; - - /* the following two fields are initialized automtically during boot */ - int id; -#define MAX_CGROUP_TYPE_NAMELEN 32 - const char *name; - - /* link to parent, protected by cgroup_lock() */ - struct cgroup_root *root; - - /* idr for css->id */ - struct idr css_idr; - - /* - * List of cftypes. Each entry is the first entry of an array - * terminated by zero length name. - */ - struct list_head cfts; - - /* - * Base cftypes which are automatically registered. The two can - * point to the same array. - */ - struct cftype *dfl_cftypes; /* for the default hierarchy */ - struct cftype *legacy_cftypes; /* for the legacy hierarchies */ - - /* - * A subsystem may depend on other subsystems. When such subsystem - * is enabled on a cgroup, the depended-upon subsystems are enabled - * together if available. Subsystems enabled due to dependency are - * not visible to userland until explicitly enabled. The following - * specifies the mask of subsystems that this one depends on. - */ - unsigned int depends_on; -}; - #define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys; #include #undef SUBSYS diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 867722591be2..99728072e536 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -142,7 +142,7 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); */ #define if(cond, ...) __trace_if( (cond , ## __VA_ARGS__) ) #define __trace_if(cond) \ - if (__builtin_constant_p((cond)) ? !!(cond) : \ + if (__builtin_constant_p(!!(cond)) ? !!(cond) : \ ({ \ int ______r; \ static struct ftrace_branch_data \ diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h index 251a2090a554..e0ee0b3000b2 100644 --- a/include/linux/devpts_fs.h +++ b/include/linux/devpts_fs.h @@ -19,6 +19,8 @@ int devpts_new_index(struct inode *ptmx_inode); void devpts_kill_index(struct inode *ptmx_inode, int idx); +void devpts_add_ref(struct inode *ptmx_inode); +void devpts_del_ref(struct inode *ptmx_inode); /* mknod in devpts */ struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index, void *priv); @@ -32,6 +34,8 @@ void devpts_pty_kill(struct inode *inode); /* Dummy stubs in the no-pty case */ static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; } static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { } +static inline void devpts_add_ref(struct inode *ptmx_inode) { } +static inline void devpts_del_ref(struct inode *ptmx_inode) { } static inline struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index, void *priv) { diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index e4b464983322..01c25923675b 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -29,6 +29,7 @@ struct ipv6_devconf { __s32 max_desync_factor; __s32 max_addresses; __s32 accept_ra_defrtr; + __s32 accept_ra_min_hop_limit; __s32 accept_ra_pinfo; #ifdef CONFIG_IPV6_ROUTER_PREF __s32 accept_ra_rtr_pref; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1f17abe23725..6633b0cd3fb9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -203,6 +203,7 @@ struct sk_buff; #else #define MAX_SKB_FRAGS (65536/PAGE_SIZE + 1) #endif +extern int sysctl_max_skb_frags; typedef struct skb_frag_struct skb_frag_t; diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index a5f7f3ecafa3..a6e1bca88cc6 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -14,8 +14,10 @@ * See the file COPYING for more details. */ +#include #include #include +#include #include #include @@ -129,6 +131,9 @@ extern void syscall_unregfunc(void); void *it_func; \ void *__data; \ \ + if (!cpu_online(raw_smp_processor_id())) \ + return; \ + \ if (!(cond)) \ return; \ prercu; \ diff --git a/include/net/af_unix.h b/include/net/af_unix.h index e830c3dff61a..7bb69c9c3c43 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -6,8 +6,8 @@ #include #include -void unix_inflight(struct file *fp); -void unix_notinflight(struct file *fp); +void unix_inflight(struct user_struct *user, struct file *fp); +void unix_notinflight(struct user_struct *user, struct file *fp); void unix_gc(void); void wait_for_unix_gc(void); struct sock *unix_get_socket(struct file *filp); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 5e192068e6cb..388dea4da083 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -64,8 +64,16 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr) void ip6_route_input(struct sk_buff *skb); -struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, - struct flowi6 *fl6); +struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, + struct flowi6 *fl6, int flags); + +static inline struct dst_entry *ip6_route_output(struct net *net, + const struct sock *sk, + struct flowi6 *fl6) +{ + return ip6_route_output_flags(net, sk, fl6, 0); +} + struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, int flags); diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 54271ed0ed45..13f1a97f6b2b 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -59,6 +59,7 @@ struct fib_nh_exception { struct rtable __rcu *fnhe_rth_input; struct rtable __rcu *fnhe_rth_output; unsigned long fnhe_stamp; + struct rcu_head rcu; }; struct fnhe_hash_bucket { diff --git a/include/net/scm.h b/include/net/scm.h index 262532d111f5..59fa93c01d2a 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -21,6 +21,7 @@ struct scm_creds { struct scm_fp_list { short count; short max; + struct user_struct *user; struct file *fp[SCM_MAX_FD]; }; diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h index 0f4dc3768587..24c8d9d0d946 100644 --- a/include/target/target_core_fabric.h +++ b/include/target/target_core_fabric.h @@ -155,8 +155,8 @@ bool transport_wait_for_tasks(struct se_cmd *); int transport_check_aborted_status(struct se_cmd *, int); int transport_send_check_condition_and_sense(struct se_cmd *, sense_reason_t, int); -int target_get_sess_cmd(struct se_session *, struct se_cmd *, bool); -int target_put_sess_cmd(struct se_session *, struct se_cmd *); +int target_get_sess_cmd(struct se_cmd *, bool); +int target_put_sess_cmd(struct se_cmd *); void target_sess_cmd_list_set_waiting(struct se_session *); void target_wait_for_sess_cmds(struct se_session *); diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 5efa54ae567c..80f3b74446a1 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -171,6 +171,8 @@ enum { DEVCONF_USE_OPTIMISTIC, DEVCONF_ACCEPT_RA_MTU, DEVCONF_STABLE_SECRET, + DEVCONF_USE_OIF_ADDRS_ONLY, + DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT, DEVCONF_MAX }; diff --git a/ipc/msgutil.c b/ipc/msgutil.c index 2b491590ebab..71f448e5e927 100644 --- a/ipc/msgutil.c +++ b/ipc/msgutil.c @@ -123,7 +123,7 @@ struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst) size_t len = src->m_ts; size_t alen; - BUG_ON(dst == NULL); + WARN_ON(dst == NULL); if (src->m_ts > dst->m_ts) return ERR_PTR(-EINVAL); diff --git a/ipc/shm.c b/ipc/shm.c index 499a8bd22fad..bbe5f62f2b12 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -155,9 +155,13 @@ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_lock(&shm_ids(ns), id); + /* + * Callers of shm_lock() must validate the status of the returned ipc + * object pointer (as returned by ipc_lock()), and error out as + * appropriate. + */ if (IS_ERR(ipcp)) - return (struct shmid_kernel *)ipcp; - + return (void *)ipcp; return container_of(ipcp, struct shmid_kernel, shm_perm); } @@ -183,19 +187,33 @@ static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s) } -/* This is called by fork, once for every shm attach. */ -static void shm_open(struct vm_area_struct *vma) +static int __shm_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); struct shmid_kernel *shp; shp = shm_lock(sfd->ns, sfd->id); - BUG_ON(IS_ERR(shp)); + + if (IS_ERR(shp)) + return PTR_ERR(shp); + shp->shm_atim = get_seconds(); shp->shm_lprid = task_tgid_vnr(current); shp->shm_nattch++; shm_unlock(shp); + return 0; +} + +/* This is called by fork, once for every shm attach. */ +static void shm_open(struct vm_area_struct *vma) +{ + int err = __shm_open(vma); + /* + * We raced in the idr lookup or with shm_destroy(). + * Either way, the ID is busted. + */ + WARN_ON_ONCE(err); } /* @@ -258,7 +276,14 @@ static void shm_close(struct vm_area_struct *vma) down_write(&shm_ids(ns).rwsem); /* remove from the list of attaches of the shm segment */ shp = shm_lock(ns, sfd->id); - BUG_ON(IS_ERR(shp)); + + /* + * We raced in the idr lookup or with shm_destroy(). + * Either way, the ID is busted. + */ + if (WARN_ON_ONCE(IS_ERR(shp))) + goto done; /* no-op */ + shp->shm_lprid = task_tgid_vnr(current); shp->shm_dtim = get_seconds(); shp->shm_nattch--; @@ -266,6 +291,7 @@ static void shm_close(struct vm_area_struct *vma) shm_destroy(ns, shp); else shm_unlock(shp); +done: up_write(&shm_ids(ns).rwsem); } @@ -387,17 +413,25 @@ static int shm_mmap(struct file *file, struct vm_area_struct *vma) struct shm_file_data *sfd = shm_file_data(file); int ret; + /* + * In case of remap_file_pages() emulation, the file can represent + * removed IPC ID: propogate shm_lock() error to caller. + */ + ret =__shm_open(vma); + if (ret) + return ret; + ret = sfd->file->f_op->mmap(sfd->file, vma); - if (ret != 0) + if (ret) { + shm_close(vma); return ret; + } sfd->vm_ops = vma->vm_ops; #ifdef CONFIG_MMU - BUG_ON(!sfd->vm_ops->fault); + WARN_ON(!sfd->vm_ops->fault); #endif vma->vm_ops = &shm_vm_ops; - shm_open(vma); - - return ret; + return 0; } static int shm_release(struct inode *ino, struct file *file) @@ -1192,7 +1226,6 @@ out_fput: out_nattch: down_write(&shm_ids(ns).rwsem); shp = shm_lock(ns, shmid); - BUG_ON(IS_ERR(shp)); shp->shm_nattch--; if (shm_may_destroy(ns, shp)) shm_destroy(ns, shp); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 141d562064a7..6582410a71c7 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1944,7 +1944,7 @@ static void adjust_branches(struct bpf_prog *prog, int pos, int delta) /* adjust offset of jmps if necessary */ if (i < pos && i + insn->off + 1 > pos) insn->off += delta; - else if (i > pos && i + insn->off + 1 < pos) + else if (i > pos + delta && i + insn->off + 1 <= pos + delta) insn->off -= delta; } } diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 4d65b66ae60d..359da3abb004 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4481,6 +4481,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css, INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); css->serial_nr = css_serial_nr_next++; + atomic_set(&css->online_cnt, 0); if (cgroup_parent(cgrp)) { css->parent = cgroup_css(cgroup_parent(cgrp), ss); @@ -4503,6 +4504,10 @@ static int online_css(struct cgroup_subsys_state *css) if (!ret) { css->flags |= CSS_ONLINE; rcu_assign_pointer(css->cgroup->subsys[ss->id], css); + + atomic_inc(&css->online_cnt); + if (css->parent) + atomic_inc(&css->parent->online_cnt); } return ret; } @@ -4740,10 +4745,15 @@ static void css_killed_work_fn(struct work_struct *work) container_of(work, struct cgroup_subsys_state, destroy_work); mutex_lock(&cgroup_mutex); - offline_css(css); - mutex_unlock(&cgroup_mutex); - css_put(css); + do { + offline_css(css); + css_put(css); + /* @css can't go away while we're holding cgroup_mutex */ + css = css->parent; + } while (css && atomic_dec_and_test(&css->online_cnt)); + + mutex_unlock(&cgroup_mutex); } /* css kill confirmation processing requires process context, bounce */ @@ -4752,8 +4762,10 @@ static void css_killed_ref_fn(struct percpu_ref *ref) struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); - INIT_WORK(&css->destroy_work, css_killed_work_fn); - queue_work(cgroup_destroy_wq, &css->destroy_work); + if (atomic_dec_and_test(&css->online_cnt)) { + INIT_WORK(&css->destroy_work, css_killed_work_fn); + queue_work(cgroup_destroy_wq, &css->destroy_work); + } } /** diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 5c01664c26e2..6d631161705c 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -127,6 +127,11 @@ enum { * * PR: wq_pool_mutex protected for writes. Sched-RCU protected for reads. * + * PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads. + * + * PWR: wq_pool_mutex and wq->mutex protected for writes. Either or + * sched-RCU for reads. + * * WQ: wq->mutex protected. * * WR: wq->mutex protected for writes. Sched-RCU protected for reads. @@ -247,8 +252,8 @@ struct workqueue_struct { int nr_drainers; /* WQ: drain in progress */ int saved_max_active; /* WQ: saved pwq max_active */ - struct workqueue_attrs *unbound_attrs; /* WQ: only for unbound wqs */ - struct pool_workqueue *dfl_pwq; /* WQ: only for unbound wqs */ + struct workqueue_attrs *unbound_attrs; /* PW: only for unbound wqs */ + struct pool_workqueue *dfl_pwq; /* PW: only for unbound wqs */ #ifdef CONFIG_SYSFS struct wq_device *wq_dev; /* I: for sysfs interface */ @@ -268,7 +273,7 @@ struct workqueue_struct { /* hot fields used during command issue, aligned to cacheline */ unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */ struct pool_workqueue __percpu *cpu_pwqs; /* I: per-cpu pwqs */ - struct pool_workqueue __rcu *numa_pwq_tbl[]; /* FR: unbound pwqs indexed by node */ + struct pool_workqueue __rcu *numa_pwq_tbl[]; /* PWR: unbound pwqs indexed by node */ }; static struct kmem_cache *pwq_cache; @@ -347,6 +352,12 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq); lockdep_is_held(&wq->mutex), \ "sched RCU or wq->mutex should be held") +#define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \ + rcu_lockdep_assert(rcu_read_lock_sched_held() || \ + lockdep_is_held(&wq->mutex) || \ + lockdep_is_held(&wq_pool_mutex), \ + "sched RCU, wq->mutex or wq_pool_mutex should be held") + #define for_each_cpu_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ (pool) < &per_cpu(cpu_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ @@ -551,7 +562,8 @@ static int worker_pool_assign_id(struct worker_pool *pool) * @wq: the target workqueue * @node: the node ID * - * This must be called either with pwq_lock held or sched RCU read locked. + * This must be called with any of wq_pool_mutex, wq->mutex or sched RCU + * read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. * @@ -560,7 +572,17 @@ static int worker_pool_assign_id(struct worker_pool *pool) static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq, int node) { - assert_rcu_or_wq_mutex(wq); + assert_rcu_or_wq_mutex_or_pool_mutex(wq); + + /* + * XXX: @node can be NUMA_NO_NODE if CPU goes offline while a + * delayed item is pending. The plan is to keep CPU -> NODE + * mapping valid and stable across CPU on/offlines. Once that + * happens, this workaround can be removed. + */ + if (unlikely(node == NUMA_NO_NODE)) + return wq->dfl_pwq; + return rcu_dereference_raw(wq->numa_pwq_tbl[node]); } @@ -1451,13 +1473,13 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, timer_stats_timer_set_start_info(&dwork->timer); dwork->wq = wq; - /* timer isn't guaranteed to run in this cpu, record earlier */ - if (cpu == WORK_CPU_UNBOUND) - cpu = raw_smp_processor_id(); dwork->cpu = cpu; timer->expires = jiffies + delay; - add_timer_on(timer, cpu); + if (unlikely(cpu != WORK_CPU_UNBOUND)) + add_timer_on(timer, cpu); + else + add_timer(timer); } /** @@ -3425,17 +3447,6 @@ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, return pwq; } -/* undo alloc_unbound_pwq(), used only in the error path */ -static void free_unbound_pwq(struct pool_workqueue *pwq) -{ - lockdep_assert_held(&wq_pool_mutex); - - if (pwq) { - put_unbound_pool(pwq->pool); - kmem_cache_free(pwq_cache, pwq); - } -} - /** * wq_calc_node_mask - calculate a wq_attrs' cpumask for the specified node * @attrs: the wq_attrs of interest @@ -3488,6 +3499,7 @@ static struct pool_workqueue *numa_pwq_tbl_install(struct workqueue_struct *wq, { struct pool_workqueue *old_pwq; + lockdep_assert_held(&wq_pool_mutex); lockdep_assert_held(&wq->mutex); /* link_pwq() can handle duplicate calls */ @@ -3498,42 +3510,48 @@ static struct pool_workqueue *numa_pwq_tbl_install(struct workqueue_struct *wq, return old_pwq; } -/** - * apply_workqueue_attrs - apply new workqueue_attrs to an unbound workqueue - * @wq: the target workqueue - * @attrs: the workqueue_attrs to apply, allocated with alloc_workqueue_attrs() - * - * Apply @attrs to an unbound workqueue @wq. Unless disabled, on NUMA - * machines, this function maps a separate pwq to each NUMA node with - * possibles CPUs in @attrs->cpumask so that work items are affine to the - * NUMA node it was issued on. Older pwqs are released as in-flight work - * items finish. Note that a work item which repeatedly requeues itself - * back-to-back will stay on its current pwq. - * - * Performs GFP_KERNEL allocations. - * - * Return: 0 on success and -errno on failure. - */ -int apply_workqueue_attrs(struct workqueue_struct *wq, - const struct workqueue_attrs *attrs) +/* context to store the prepared attrs & pwqs before applying */ +struct apply_wqattrs_ctx { + struct workqueue_struct *wq; /* target workqueue */ + struct workqueue_attrs *attrs; /* attrs to apply */ + struct pool_workqueue *dfl_pwq; + struct pool_workqueue *pwq_tbl[]; +}; + +/* free the resources after success or abort */ +static void apply_wqattrs_cleanup(struct apply_wqattrs_ctx *ctx) { + if (ctx) { + int node; + + for_each_node(node) + put_pwq_unlocked(ctx->pwq_tbl[node]); + put_pwq_unlocked(ctx->dfl_pwq); + + free_workqueue_attrs(ctx->attrs); + + kfree(ctx); + } +} + +/* allocate the attrs and pwqs for later installation */ +static struct apply_wqattrs_ctx * +apply_wqattrs_prepare(struct workqueue_struct *wq, + const struct workqueue_attrs *attrs) +{ + struct apply_wqattrs_ctx *ctx; struct workqueue_attrs *new_attrs, *tmp_attrs; - struct pool_workqueue **pwq_tbl, *dfl_pwq; - int node, ret; + int node; - /* only unbound workqueues can change attributes */ - if (WARN_ON(!(wq->flags & WQ_UNBOUND))) - return -EINVAL; + lockdep_assert_held(&wq_pool_mutex); - /* creating multiple pwqs breaks ordering guarantee */ - if (WARN_ON((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs))) - return -EINVAL; + ctx = kzalloc(sizeof(*ctx) + nr_node_ids * sizeof(ctx->pwq_tbl[0]), + GFP_KERNEL); - pwq_tbl = kzalloc(nr_node_ids * sizeof(pwq_tbl[0]), GFP_KERNEL); new_attrs = alloc_workqueue_attrs(GFP_KERNEL); tmp_attrs = alloc_workqueue_attrs(GFP_KERNEL); - if (!pwq_tbl || !new_attrs || !tmp_attrs) - goto enomem; + if (!ctx || !new_attrs || !tmp_attrs) + goto out_free; /* make a copy of @attrs and sanitize it */ copy_workqueue_attrs(new_attrs, attrs); @@ -3547,75 +3565,111 @@ int apply_workqueue_attrs(struct workqueue_struct *wq, copy_workqueue_attrs(tmp_attrs, new_attrs); /* - * CPUs should stay stable across pwq creations and installations. - * Pin CPUs, determine the target cpumask for each node and create - * pwqs accordingly. - */ - get_online_cpus(); - - mutex_lock(&wq_pool_mutex); - - /* * If something goes wrong during CPU up/down, we'll fall back to * the default pwq covering whole @attrs->cpumask. Always create * it even if we don't use it immediately. */ - dfl_pwq = alloc_unbound_pwq(wq, new_attrs); - if (!dfl_pwq) - goto enomem_pwq; + ctx->dfl_pwq = alloc_unbound_pwq(wq, new_attrs); + if (!ctx->dfl_pwq) + goto out_free; for_each_node(node) { if (wq_calc_node_cpumask(attrs, node, -1, tmp_attrs->cpumask)) { - pwq_tbl[node] = alloc_unbound_pwq(wq, tmp_attrs); - if (!pwq_tbl[node]) - goto enomem_pwq; + ctx->pwq_tbl[node] = alloc_unbound_pwq(wq, tmp_attrs); + if (!ctx->pwq_tbl[node]) + goto out_free; } else { - dfl_pwq->refcnt++; - pwq_tbl[node] = dfl_pwq; + ctx->dfl_pwq->refcnt++; + ctx->pwq_tbl[node] = ctx->dfl_pwq; } } - mutex_unlock(&wq_pool_mutex); + ctx->attrs = new_attrs; + ctx->wq = wq; + free_workqueue_attrs(tmp_attrs); + return ctx; + +out_free: + free_workqueue_attrs(tmp_attrs); + free_workqueue_attrs(new_attrs); + apply_wqattrs_cleanup(ctx); + return NULL; +} + +/* set attrs and install prepared pwqs, @ctx points to old pwqs on return */ +static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx) +{ + int node; /* all pwqs have been created successfully, let's install'em */ - mutex_lock(&wq->mutex); + mutex_lock(&ctx->wq->mutex); - copy_workqueue_attrs(wq->unbound_attrs, new_attrs); + copy_workqueue_attrs(ctx->wq->unbound_attrs, ctx->attrs); /* save the previous pwq and install the new one */ for_each_node(node) - pwq_tbl[node] = numa_pwq_tbl_install(wq, node, pwq_tbl[node]); + ctx->pwq_tbl[node] = numa_pwq_tbl_install(ctx->wq, node, + ctx->pwq_tbl[node]); /* @dfl_pwq might not have been used, ensure it's linked */ - link_pwq(dfl_pwq); - swap(wq->dfl_pwq, dfl_pwq); + link_pwq(ctx->dfl_pwq); + swap(ctx->wq->dfl_pwq, ctx->dfl_pwq); - mutex_unlock(&wq->mutex); + mutex_unlock(&ctx->wq->mutex); +} - /* put the old pwqs */ - for_each_node(node) - put_pwq_unlocked(pwq_tbl[node]); - put_pwq_unlocked(dfl_pwq); +/** + * apply_workqueue_attrs - apply new workqueue_attrs to an unbound workqueue + * @wq: the target workqueue + * @attrs: the workqueue_attrs to apply, allocated with alloc_workqueue_attrs() + * + * Apply @attrs to an unbound workqueue @wq. Unless disabled, on NUMA + * machines, this function maps a separate pwq to each NUMA node with + * possibles CPUs in @attrs->cpumask so that work items are affine to the + * NUMA node it was issued on. Older pwqs are released as in-flight work + * items finish. Note that a work item which repeatedly requeues itself + * back-to-back will stay on its current pwq. + * + * Performs GFP_KERNEL allocations. + * + * Return: 0 on success and -errno on failure. + */ +int apply_workqueue_attrs(struct workqueue_struct *wq, + const struct workqueue_attrs *attrs) +{ + struct apply_wqattrs_ctx *ctx; + int ret = -ENOMEM; - put_online_cpus(); - ret = 0; - /* fall through */ -out_free: - free_workqueue_attrs(tmp_attrs); - free_workqueue_attrs(new_attrs); - kfree(pwq_tbl); - return ret; + /* only unbound workqueues can change attributes */ + if (WARN_ON(!(wq->flags & WQ_UNBOUND))) + return -EINVAL; + + /* creating multiple pwqs breaks ordering guarantee */ + if (WARN_ON((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs))) + return -EINVAL; + + /* + * CPUs should stay stable across pwq creations and installations. + * Pin CPUs, determine the target cpumask for each node and create + * pwqs accordingly. + */ + get_online_cpus(); + mutex_lock(&wq_pool_mutex); + + ctx = apply_wqattrs_prepare(wq, attrs); + + /* the ctx has been prepared successfully, let's commit it */ + if (ctx) { + apply_wqattrs_commit(ctx); + ret = 0; + } -enomem_pwq: - free_unbound_pwq(dfl_pwq); - for_each_node(node) - if (pwq_tbl && pwq_tbl[node] != dfl_pwq) - free_unbound_pwq(pwq_tbl[node]); mutex_unlock(&wq_pool_mutex); put_online_cpus(); -enomem: - ret = -ENOMEM; - goto out_free; + + apply_wqattrs_cleanup(ctx); + + return ret; } /** diff --git a/lib/klist.c b/lib/klist.c index 89b485a2a58d..2a072bfaeace 100644 --- a/lib/klist.c +++ b/lib/klist.c @@ -282,9 +282,9 @@ void klist_iter_init_node(struct klist *k, struct klist_iter *i, struct klist_node *n) { i->i_klist = k; - i->i_cur = n; - if (n) - kref_get(&n->n_ref); + i->i_cur = NULL; + if (n && kref_get_unless_zero(&n->n_ref)) + i->i_cur = n; } EXPORT_SYMBOL_GPL(klist_iter_init_node); diff --git a/mm/mmap.c b/mm/mmap.c index b639fa2721d8..d30b8f8f02b1 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2654,12 +2654,29 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, if (!vma || !(vma->vm_flags & VM_SHARED)) goto out; - if (start < vma->vm_start || start + size > vma->vm_end) + if (start < vma->vm_start) goto out; - if (pgoff == linear_page_index(vma, start)) { - ret = 0; - goto out; + if (start + size > vma->vm_end) { + struct vm_area_struct *next; + + for (next = vma->vm_next; next; next = next->vm_next) { + /* hole between vmas ? */ + if (next->vm_start != next->vm_prev->vm_end) + goto out; + + if (next->vm_file != vma->vm_file) + goto out; + + if (next->vm_flags != vma->vm_flags) + goto out; + + if (start + size <= next->vm_end) + break; + } + + if (!next) + goto out; } prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; @@ -2669,9 +2686,16 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, flags &= MAP_NONBLOCK; flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; if (vma->vm_flags & VM_LOCKED) { + struct vm_area_struct *tmp; flags |= MAP_LOCKED; + /* drop PG_Mlocked flag for over-mapped range */ - munlock_vma_pages_range(vma, start, start + size); + for (tmp = vma; tmp->vm_start >= start + size; + tmp = tmp->vm_next) { + munlock_vma_pages_range(tmp, + max(tmp->vm_start, start), + min(tmp->vm_end, start + size)); + } } file = get_file(vma->vm_file); diff --git a/net/bridge/br.c b/net/bridge/br.c index 02c24cf63c34..c72e01cf09d0 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -121,6 +121,7 @@ static struct notifier_block br_device_notifier = { .notifier_call = br_device_event }; +/* called with RTNL */ static int br_netdev_switch_event(struct notifier_block *unused, unsigned long event, void *ptr) { @@ -130,7 +131,6 @@ static int br_netdev_switch_event(struct notifier_block *unused, struct netdev_switch_notifier_fdb_info *fdb_info; int err = NOTIFY_DONE; - rtnl_lock(); p = br_port_get_rtnl(dev); if (!p) goto out; @@ -155,7 +155,6 @@ static int br_netdev_switch_event(struct notifier_block *unused, } out: - rtnl_unlock(); return err; } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 2c35c02a931e..3556791fdc6e 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -113,7 +113,6 @@ ip: case htons(ETH_P_IPV6): { const struct ipv6hdr *iph; struct ipv6hdr _iph; - __be32 flow_label; ipv6: iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph); @@ -130,8 +129,9 @@ ipv6: flow->src = (__force __be32)ipv6_addr_hash(&iph->saddr); flow->dst = (__force __be32)ipv6_addr_hash(&iph->daddr); - flow_label = ip6_flowlabel(iph); - if (flow_label) { + if (skb && ip6_flowlabel(iph)) { + __be32 flow_label = ip6_flowlabel(iph); + /* Awesome, IPv6 packet has a flow label so we can * use that to represent the ports without any * further dissection. @@ -233,6 +233,13 @@ ipv6: return false; proto = eth->h_proto; nhoff += sizeof(*eth); + + /* Cap headers that we access via pointers at the + * end of the Ethernet header as our maximum alignment + * at that point is only 2 bytes. + */ + if (NET_IP_ALIGN) + hlen = nhoff; } goto again; } diff --git a/net/core/scm.c b/net/core/scm.c index 8a1741b14302..dce0acb929f1 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -87,6 +87,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) *fplp = fpl; fpl->count = 0; fpl->max = SCM_MAX_FD; + fpl->user = NULL; } fpp = &fpl->fp[fpl->count]; @@ -107,6 +108,10 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) *fpp++ = file; fpl->count++; } + + if (!fpl->user) + fpl->user = get_uid(current_user()); + return num; } @@ -119,6 +124,7 @@ void __scm_destroy(struct scm_cookie *scm) scm->fp = NULL; for (i=fpl->count-1; i>=0; i--) fput(fpl->fp[i]); + free_uid(fpl->user); kfree(fpl); } } @@ -336,6 +342,7 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) for (i = 0; i < fpl->count; i++) get_file(fpl->fp[i]); new_fpl->max = new_fpl->count; + new_fpl->user = get_uid(fpl->user); } return new_fpl; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2e5fcda16570..c9793c6c5005 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -79,6 +79,8 @@ struct kmem_cache *skbuff_head_cache __read_mostly; static struct kmem_cache *skbuff_fclone_cache __read_mostly; +int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS; +EXPORT_SYMBOL(sysctl_max_skb_frags); /** * skb_panic - private function for out-of-line support diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 95b6139d710c..a6beb7b6ae55 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -26,6 +26,7 @@ static int zero = 0; static int one = 1; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; +static int max_skb_frags = MAX_SKB_FRAGS; static int net_msg_warn; /* Unused, but still a sysctl */ @@ -392,6 +393,15 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "max_skb_frags", + .data = &sysctl_max_skb_frags, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &max_skb_frags, + }, { } }; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 419d23c53ec7..280d46f947ea 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1839,7 +1839,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, if (err < 0) goto errout; - err = EINVAL; + err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) goto errout; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 6ddde89996f4..b6c7bdea4853 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -249,6 +249,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc, switch (cmsg->cmsg_type) { case IP_RETOPTS: err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr)); + + /* Our caller is responsible for freeing ipc->opt */ err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg), err < 40 ? err : 40); if (err) diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 05ff44b758df..f6ee0d561aab 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -745,8 +745,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(sock_net(sk), msg, &ipc, false); - if (err) + if (unlikely(err)) { + kfree(ipc.opt); return err; + } if (ipc.opt) free = 1; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 561cd4b8fc6e..c77aac75759d 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -543,8 +543,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(sock_net(sk), msg, &ipc, false); - if (err) + if (unlikely(err)) { + kfree(ipc.opt); goto out; + } if (ipc.opt) free = 1; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f45f2a12f37b..1d3cdb4d4ebc 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -125,6 +125,7 @@ static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; +static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; /* * Interface to generic destination cache. */ @@ -753,7 +754,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow struct fib_nh *nh = &FIB_RES_NH(res); update_or_create_fnhe(nh, fl4->daddr, new_gw, - 0, 0); + 0, jiffies + ip_rt_gc_timeout); } if (kill_route) rt->dst.obsolete = DST_OBSOLETE_KILL; @@ -1538,6 +1539,36 @@ static void ip_handle_martian_source(struct net_device *dev, #endif } +static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) +{ + struct fnhe_hash_bucket *hash; + struct fib_nh_exception *fnhe, __rcu **fnhe_p; + u32 hval = fnhe_hashfun(daddr); + + spin_lock_bh(&fnhe_lock); + + hash = rcu_dereference_protected(nh->nh_exceptions, + lockdep_is_held(&fnhe_lock)); + hash += hval; + + fnhe_p = &hash->chain; + fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); + while (fnhe) { + if (fnhe->fnhe_daddr == daddr) { + rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( + fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); + fnhe_flush_routes(fnhe); + kfree_rcu(fnhe, rcu); + break; + } + fnhe_p = &fnhe->fnhe_next; + fnhe = rcu_dereference_protected(fnhe->fnhe_next, + lockdep_is_held(&fnhe_lock)); + } + + spin_unlock_bh(&fnhe_lock); +} + /* called in rcu_read_lock() section */ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, @@ -1592,11 +1623,20 @@ static int __mkroute_input(struct sk_buff *skb, fnhe = find_exception(&FIB_RES_NH(*res), daddr); if (do_cache) { - if (fnhe) + if (fnhe) { rth = rcu_dereference(fnhe->fnhe_rth_input); - else - rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); + if (rth && rth->dst.expires && + time_after(jiffies, rth->dst.expires)) { + ip_del_fnhe(&FIB_RES_NH(*res), daddr); + fnhe = NULL; + } else { + goto rt_cache; + } + } + + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); +rt_cache: if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; @@ -1945,19 +1985,29 @@ static struct rtable *__mkroute_output(const struct fib_result *res, struct fib_nh *nh = &FIB_RES_NH(*res); fnhe = find_exception(nh, fl4->daddr); - if (fnhe) + if (fnhe) { prth = &fnhe->fnhe_rth_output; - else { - if (unlikely(fl4->flowi4_flags & - FLOWI_FLAG_KNOWN_NH && - !(nh->nh_gw && - nh->nh_scope == RT_SCOPE_LINK))) { - do_cache = false; - goto add; + rth = rcu_dereference(*prth); + if (rth && rth->dst.expires && + time_after(jiffies, rth->dst.expires)) { + ip_del_fnhe(nh, fl4->daddr); + fnhe = NULL; + } else { + goto rt_cache; } - prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); } + + if (unlikely(fl4->flowi4_flags & + FLOWI_FLAG_KNOWN_NH && + !(nh->nh_gw && + nh->nh_scope == RT_SCOPE_LINK))) { + do_cache = false; + goto add; + } + prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); rth = rcu_dereference(*prth); + +rt_cache: if (rt_cache_valid(rth)) { dst_hold(&rth->dst); return rth; @@ -2504,7 +2554,6 @@ void ip_rt_multicast_event(struct in_device *in_dev) } #ifdef CONFIG_SYSCTL -static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bb2ce74f6004..19d385a0f02d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -279,6 +279,7 @@ #include #include +#include #include int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; @@ -921,7 +922,7 @@ new_segment: i = skb_shinfo(skb)->nr_frags; can_coalesce = skb_can_coalesce(skb, i, page, offset); - if (!can_coalesce && i >= MAX_SKB_FRAGS) { + if (!can_coalesce && i >= sysctl_max_skb_frags) { tcp_mark_push(tp, skb); goto new_segment; } @@ -1187,7 +1188,7 @@ new_segment: if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { - if (i == MAX_SKB_FRAGS || !sg) { + if (i == sysctl_max_skb_frags || !sg) { tcp_mark_push(tp, skb); goto new_segment; } @@ -2603,6 +2604,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) const struct inet_connection_sock *icsk = inet_csk(sk); u32 now = tcp_time_stamp; unsigned int start; + u64 rate64; u32 rate; memset(info, 0, sizeof(*info)); @@ -2665,15 +2667,17 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_total_retrans = tp->total_retrans; rate = READ_ONCE(sk->sk_pacing_rate); - info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL; + rate64 = rate != ~0U ? rate : ~0ULL; + put_unaligned(rate64, &info->tcpi_pacing_rate); rate = READ_ONCE(sk->sk_max_pacing_rate); - info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL; + rate64 = rate != ~0U ? rate : ~0ULL; + put_unaligned(rate64, &info->tcpi_max_pacing_rate); do { start = u64_stats_fetch_begin_irq(&tp->syncp); - info->tcpi_bytes_acked = tp->bytes_acked; - info->tcpi_bytes_received = tp->bytes_received; + put_unaligned(tp->bytes_acked, &info->tcpi_bytes_acked); + put_unaligned(tp->bytes_received, &info->tcpi_bytes_received); } while (u64_stats_fetch_retry_irq(&tp->syncp, start)); } EXPORT_SYMBOL_GPL(tcp_get_info); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index cd18c3d3251e..13b92d595138 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -705,7 +705,8 @@ release_sk1: outside socket context is ugly, certainly. What can I do? */ -static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, +static void tcp_v4_send_ack(struct net *net, + struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, int reply_flags, u8 tos) @@ -720,7 +721,6 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, ]; } rep; struct ip_reply_arg arg; - struct net *net = dev_net(skb_dst(skb)->dev); memset(&rep.th, 0, sizeof(struct tcphdr)); memset(&arg, 0, sizeof(arg)); @@ -782,7 +782,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); - tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, + tcp_v4_send_ack(sock_net(sk), skb, + tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp + tcptw->tw_ts_offset, tcptw->tw_ts_recent, @@ -801,8 +802,10 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ - tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ? - tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, + u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : + tcp_sk(sk)->snd_nxt; + + tcp_v4_send_ack(sock_net(sk), skb, seq, tcp_rsk(req)->rcv_nxt, req->rcv_wnd, tcp_time_stamp, req->ts_recent, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1b8c5ba7d5f7..a390174b96de 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -963,8 +963,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(sock_net(sk), msg, &ipc, sk->sk_family == AF_INET6); - if (err) + if (unlikely(err)) { + kfree(ipc.opt); return err; + } if (ipc.opt) free = 1; connected = 0; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f4795b0d6e6e..f555f4fc1d62 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -195,6 +195,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, .accept_ra_from_local = 0, + .accept_ra_min_hop_limit= 1, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -236,6 +237,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, .accept_ra_from_local = 0, + .accept_ra_min_hop_limit= 1, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -567,7 +569,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, if (err < 0) goto errout; - err = EINVAL; + err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) goto errout; @@ -3421,6 +3423,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net_device *dev = idev->dev; + bool notify = false; addrconf_join_solict(dev, &ifp->addr); @@ -3466,7 +3469,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) /* Because optimistic nodes can use this address, * notify listeners. If DAD fails, RTM_DELADDR is sent. */ - ipv6_ifa_notify(RTM_NEWADDR, ifp); + notify = true; } } @@ -3474,6 +3477,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) out: spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); + if (notify) + ipv6_ifa_notify(RTM_NEWADDR, ifp); } static void addrconf_dad_start(struct inet6_ifaddr *ifp) @@ -4565,6 +4570,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor; array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses; array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr; + array[DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT] = cnf->accept_ra_min_hop_limit; array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo; #ifdef CONFIG_IPV6_ROUTER_PREF array[DEVCONF_ACCEPT_RA_RTR_PREF] = cnf->accept_ra_rtr_pref; @@ -5458,6 +5464,13 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { + .procname = "accept_ra_min_hop_limit", + .data = &ipv6_devconf.accept_ra_min_hop_limit, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "accept_ra_pinfo", .data = &ipv6_devconf.accept_ra_pinfo, .maxlen = sizeof(int), diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 13ca4cf5616f..8e6cb3f14326 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -162,6 +162,9 @@ ipv4_connected: fl6.fl6_dport = inet->inet_dport; fl6.fl6_sport = inet->inet_sport; + if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; + if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST)) fl6.flowi6_oif = np->mcast_oif; diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index d491125011c4..db939e4ac68a 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -540,12 +540,13 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) } spin_lock_bh(&ip6_sk_fl_lock); for (sflp = &np->ipv6_fl_list; - (sfl = rcu_dereference(*sflp)) != NULL; + (sfl = rcu_dereference_protected(*sflp, + lockdep_is_held(&ip6_sk_fl_lock))) != NULL; sflp = &sfl->next) { if (sfl->fl->label == freq.flr_label) { if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK)) np->flow_label &= ~IPV6_FLOWLABEL_MASK; - *sflp = rcu_dereference(sfl->next); + *sflp = sfl->next; spin_unlock_bh(&ip6_sk_fl_lock); fl_release(sfl->fl); kfree_rcu(sfl, rcu); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index f50228b0abe5..36b9ac48b8fb 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -885,6 +885,7 @@ static int ip6_dst_lookup_tail(struct sock *sk, struct rt6_info *rt; #endif int err; + int flags = 0; /* The correct way to handle this would be to do * ip6_route_get_saddr, and then ip6_route_output; however, @@ -916,10 +917,13 @@ static int ip6_dst_lookup_tail(struct sock *sk, dst_release(*dst); *dst = NULL; } + + if (fl6->flowi6_oif) + flags |= RT6_LOOKUP_F_IFACE; } if (!*dst) - *dst = ip6_route_output(net, sk, fl6); + *dst = ip6_route_output_flags(net, sk, fl6, flags); err = (*dst)->error; if (err) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 96f153c0846b..abb0bdda759a 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1225,18 +1225,16 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (rt) rt6_set_expires(rt, jiffies + (HZ * lifetime)); - if (ra_msg->icmph.icmp6_hop_limit) { - /* Only set hop_limit on the interface if it is higher than - * the current hop_limit. - */ - if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) { + if (in6_dev->cnf.accept_ra_min_hop_limit < 256 && + ra_msg->icmph.icmp6_hop_limit) { + if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) { in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; + if (rt) + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, + ra_msg->icmph.icmp6_hop_limit); } else { - ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than current\n"); + ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n"); } - if (rt) - dst_metric_set(&rt->dst, RTAX_HOPLIMIT, - ra_msg->icmph.icmp6_hop_limit); } skip_defrtr: diff --git a/net/ipv6/route.c b/net/ipv6/route.c index f371fefa7fdc..fe70bd6a7516 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1030,11 +1030,9 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags); } -struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, - struct flowi6 *fl6) +struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, + struct flowi6 *fl6, int flags) { - int flags = 0; - fl6->flowi6_iif = LOOPBACK_IFINDEX; if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr)) @@ -1047,7 +1045,7 @@ struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output); } -EXPORT_SYMBOL(ip6_route_output); +EXPORT_SYMBOL_GPL(ip6_route_output_flags); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig) { diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 6daa52a18d40..123f6f9f854c 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -709,6 +709,9 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr, if (!addr || addr->sa_family != AF_IUCV) return -EINVAL; + if (addr_len < sizeof(struct sockaddr_iucv)) + return -EINVAL; + lock_sock(sk); if (sk->sk_state != IUCV_OPEN) { err = -EBADFD; diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 9e13c2ff8789..fe92a08b3cd5 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -124,8 +124,13 @@ static int l2tp_tunnel_notify(struct genl_family *family, ret = l2tp_nl_tunnel_send(msg, info->snd_portid, info->snd_seq, NLM_F_ACK, tunnel, cmd); - if (ret >= 0) - return genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + if (ret >= 0) { + ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + /* We don't care if no one is listening */ + if (ret == -ESRCH) + ret = 0; + return ret; + } nlmsg_free(msg); @@ -147,8 +152,13 @@ static int l2tp_session_notify(struct genl_family *family, ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq, NLM_F_ACK, session, cmd); - if (ret >= 0) - return genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + if (ret >= 0) { + ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + /* We don't care if no one is listening */ + if (ret == -ESRCH) + ret = 0; + return ret; + } nlmsg_free(msg); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index e13c3c3ea4ac..9d134ab3351f 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -60,6 +60,8 @@ #include #include +#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024) + /* Global data structures. */ struct sctp_globals sctp_globals __read_mostly; @@ -1332,6 +1334,8 @@ static __init int sctp_init(void) unsigned long limit; int max_share; int order; + int num_entries; + int max_entry_order; sock_skb_cb_check_size(sizeof(struct sctp_ulpevent)); @@ -1384,14 +1388,24 @@ static __init int sctp_init(void) /* Size and allocate the association hash table. * The methodology is similar to that of the tcp hash tables. + * Though not identical. Start by getting a goal size */ if (totalram_pages >= (128 * 1024)) goal = totalram_pages >> (22 - PAGE_SHIFT); else goal = totalram_pages >> (24 - PAGE_SHIFT); - for (order = 0; (1UL << order) < goal; order++) - ; + /* Then compute the page order for said goal */ + order = get_order(goal); + + /* Now compute the required page order for the maximum sized table we + * want to create + */ + max_entry_order = get_order(MAX_SCTP_PORT_HASH_ENTRIES * + sizeof(struct sctp_bind_hashbucket)); + + /* Limit the page order by that maximum hash table size */ + order = min(order, max_entry_order); do { sctp_assoc_hashsize = (1UL << order) * PAGE_SIZE / @@ -1425,27 +1439,42 @@ static __init int sctp_init(void) INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain); } - /* Allocate and initialize the SCTP port hash table. */ + /* Allocate and initialize the SCTP port hash table. + * Note that order is initalized to start at the max sized + * table we want to support. If we can't get that many pages + * reduce the order and try again + */ do { - sctp_port_hashsize = (1UL << order) * PAGE_SIZE / - sizeof(struct sctp_bind_hashbucket); - if ((sctp_port_hashsize > (64 * 1024)) && order > 0) - continue; sctp_port_hashtable = (struct sctp_bind_hashbucket *) __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, order); } while (!sctp_port_hashtable && --order > 0); + if (!sctp_port_hashtable) { pr_err("Failed bind hash alloc\n"); status = -ENOMEM; goto err_bhash_alloc; } + + /* Now compute the number of entries that will fit in the + * port hash space we allocated + */ + num_entries = (1UL << order) * PAGE_SIZE / + sizeof(struct sctp_bind_hashbucket); + + /* And finish by rounding it down to the nearest power of two + * this wastes some memory of course, but its needed because + * the hash function operates based on the assumption that + * that the number of entries is a power of two + */ + sctp_port_hashsize = rounddown_pow_of_two(num_entries); + for (i = 0; i < sctp_port_hashsize; i++) { spin_lock_init(&sctp_port_hashtable[i].lock); INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain); } - pr_info("Hash tables configured (established %d bind %d)\n", - sctp_assoc_hashsize, sctp_port_hashsize); + pr_info("Hash tables configured (established %d bind %d/%d)\n", + sctp_assoc_hashsize, sctp_port_hashsize, num_entries); sctp_sysctl_register(); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 76e6ec62cf92..3c5833058b03 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5555,6 +5555,7 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, struct sctp_hmac_algo_param *hmacs; __u16 data_len = 0; u32 num_idents; + int i; if (!ep->auth_enable) return -EACCES; @@ -5572,8 +5573,12 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, return -EFAULT; if (put_user(num_idents, &p->shmac_num_idents)) return -EFAULT; - if (copy_to_user(p->shmac_idents, hmacs->hmac_ids, data_len)) - return -EFAULT; + for (i = 0; i < num_idents; i++) { + __u16 hmacid = ntohs(hmacs->hmac_ids[i]); + + if (copy_to_user(&p->shmac_idents[i], &hmacid, sizeof(__u16))) + return -EFAULT; + } return 0; } @@ -6653,6 +6658,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) if (cmsgs->srinfo->sinfo_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | + SCTP_SACK_IMMEDIATELY | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; @@ -6676,6 +6682,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) if (cmsgs->sinfo->snd_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | + SCTP_SACK_IMMEDIATELY | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 055453d48668..a8dbe8001e46 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -64,7 +65,6 @@ int netdev_switch_port_stp_update(struct net_device *dev, u8 state) } EXPORT_SYMBOL_GPL(netdev_switch_port_stp_update); -static DEFINE_MUTEX(netdev_switch_mutex); static RAW_NOTIFIER_HEAD(netdev_switch_notif_chain); /** @@ -79,9 +79,9 @@ int register_netdev_switch_notifier(struct notifier_block *nb) { int err; - mutex_lock(&netdev_switch_mutex); + rtnl_lock(); err = raw_notifier_chain_register(&netdev_switch_notif_chain, nb); - mutex_unlock(&netdev_switch_mutex); + rtnl_unlock(); return err; } EXPORT_SYMBOL_GPL(register_netdev_switch_notifier); @@ -97,9 +97,9 @@ int unregister_netdev_switch_notifier(struct notifier_block *nb) { int err; - mutex_lock(&netdev_switch_mutex); + rtnl_lock(); err = raw_notifier_chain_unregister(&netdev_switch_notif_chain, nb); - mutex_unlock(&netdev_switch_mutex); + rtnl_unlock(); return err; } EXPORT_SYMBOL_GPL(unregister_netdev_switch_notifier); @@ -113,16 +113,17 @@ EXPORT_SYMBOL_GPL(unregister_netdev_switch_notifier); * Call all network notifier blocks. This should be called by driver * when it needs to propagate hardware event. * Return values are same as for atomic_notifier_call_chain(). + * rtnl_lock must be held. */ int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev, struct netdev_switch_notifier_info *info) { int err; + ASSERT_RTNL(); + info->dev = dev; - mutex_lock(&netdev_switch_mutex); err = raw_notifier_call_chain(&netdev_switch_notif_chain, val, info); - mutex_unlock(&netdev_switch_mutex); return err; } EXPORT_SYMBOL_GPL(call_netdev_switch_notifiers); diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 1c147c869c2e..948f316019d7 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -302,11 +302,10 @@ static void subscr_conn_msg_event(struct net *net, int conid, struct tipc_net *tn = net_generic(net, tipc_net_id); spin_lock_bh(&subscriber->lock); - subscr_subscribe(net, (struct tipc_subscr *)buf, subscriber, &sub); - if (sub) - tipc_nametbl_subscribe(sub); - else + if (subscr_subscribe(net, (struct tipc_subscr *)buf, subscriber, &sub)) tipc_conn_terminate(tn->topsrv, subscriber->conid); + else + tipc_nametbl_subscribe(sub); spin_unlock_bh(&subscriber->lock); } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index cb3a01a9ed38..535a642a1688 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1464,7 +1464,7 @@ static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) UNIXCB(skb).fp = NULL; for (i = scm->fp->count-1; i >= 0; i--) - unix_notinflight(scm->fp->fp[i]); + unix_notinflight(scm->fp->user, scm->fp->fp[i]); } static void unix_destruct_scm(struct sk_buff *skb) @@ -1529,7 +1529,7 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) return -ENOMEM; for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->fp[i]); + unix_inflight(scm->fp->user, scm->fp->fp[i]); return max_level; } @@ -1714,7 +1714,12 @@ restart_locked: goto out_unlock; } - if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { + /* other == sk && unix_peer(other) != sk if + * - unix_peer(sk) == NULL, destination address bound to sk + * - unix_peer(sk) == sk by time of get but disconnected before lock + */ + if (other != sk && + unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { if (timeo) { timeo = unix_wait_for_peer(other, timeo); @@ -2131,6 +2136,7 @@ again: if (signal_pending(current)) { err = sock_intr_errno(timeo); + scm_destroy(&scm); goto out; } diff --git a/net/unix/diag.c b/net/unix/diag.c index c512f64d5287..4d9679701a6d 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -220,7 +220,7 @@ done: return skb->len; } -static struct sock *unix_lookup_by_ino(int ino) +static struct sock *unix_lookup_by_ino(unsigned int ino) { int i; struct sock *sk; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 8fcdc2283af5..6a0d48525fcf 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -116,7 +116,7 @@ struct sock *unix_get_socket(struct file *filp) * descriptor if it is for an AF_UNIX socket. */ -void unix_inflight(struct file *fp) +void unix_inflight(struct user_struct *user, struct file *fp) { struct sock *s = unix_get_socket(fp); @@ -133,11 +133,11 @@ void unix_inflight(struct file *fp) } unix_tot_inflight++; } - fp->f_cred->user->unix_inflight++; + user->unix_inflight++; spin_unlock(&unix_gc_lock); } -void unix_notinflight(struct file *fp) +void unix_notinflight(struct user_struct *user, struct file *fp) { struct sock *s = unix_get_socket(fp); @@ -152,7 +152,7 @@ void unix_notinflight(struct file *fp) list_del_init(&u->link); unix_tot_inflight--; } - fp->f_cred->user->unix_inflight--; + user->unix_inflight--; spin_unlock(&unix_gc_lock); } diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c index 582091498819..d6bc2b3af9ef 100644 --- a/security/integrity/evm/evm_main.c +++ b/security/integrity/evm/evm_main.c @@ -23,6 +23,7 @@ #include #include #include +#include #include "evm.h" int evm_initialized; @@ -148,7 +149,7 @@ static enum integrity_status evm_verify_hmac(struct dentry *dentry, xattr_value_len, calc.digest); if (rc) break; - rc = memcmp(xattr_data->digest, calc.digest, + rc = crypto_memneq(xattr_data->digest, calc.digest, sizeof(calc.digest)); if (rc) rc = -EINVAL; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 75888dd38a7f..aa999e747c94 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -74,6 +74,18 @@ static int snd_pcm_open(struct file *file, struct snd_pcm *pcm, int stream); static DEFINE_RWLOCK(snd_pcm_link_rwlock); static DECLARE_RWSEM(snd_pcm_link_rwsem); +/* Writer in rwsem may block readers even during its waiting in queue, + * and this may lead to a deadlock when the code path takes read sem + * twice (e.g. one in snd_pcm_action_nonatomic() and another in + * snd_pcm_stream_lock()). As a (suboptimal) workaround, let writer to + * spin until it gets the lock. + */ +static inline void down_write_nonblock(struct rw_semaphore *lock) +{ + while (!down_write_trylock(lock)) + cond_resched(); +} + /** * snd_pcm_stream_lock - Lock the PCM stream * @substream: PCM substream @@ -1816,7 +1828,7 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) res = -ENOMEM; goto _nolock; } - down_write(&snd_pcm_link_rwsem); + down_write_nonblock(&snd_pcm_link_rwsem); write_lock_irq(&snd_pcm_link_rwlock); if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN || substream->runtime->status->state != substream1->runtime->status->state || @@ -1863,7 +1875,7 @@ static int snd_pcm_unlink(struct snd_pcm_substream *substream) struct snd_pcm_substream *s; int res = 0; - down_write(&snd_pcm_link_rwsem); + down_write_nonblock(&snd_pcm_link_rwsem); write_lock_irq(&snd_pcm_link_rwlock); if (!snd_pcm_stream_linked(substream)) { res = -EALREADY; diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c index 801076687bb1..c850345c43b5 100644 --- a/sound/core/seq/seq_memory.c +++ b/sound/core/seq/seq_memory.c @@ -383,15 +383,20 @@ int snd_seq_pool_init(struct snd_seq_pool *pool) if (snd_BUG_ON(!pool)) return -EINVAL; - if (pool->ptr) /* should be atomic? */ - return 0; - pool->ptr = vmalloc(sizeof(struct snd_seq_event_cell) * pool->size); - if (!pool->ptr) + cellptr = vmalloc(sizeof(struct snd_seq_event_cell) * pool->size); + if (!cellptr) return -ENOMEM; /* add new cells to the free cell list */ spin_lock_irqsave(&pool->lock, flags); + if (pool->ptr) { + spin_unlock_irqrestore(&pool->lock, flags); + vfree(cellptr); + return 0; + } + + pool->ptr = cellptr; pool->free = NULL; for (cell = 0; cell < pool->size; cell++) { diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c index 921fb2bd8fad..fe686ee41c6d 100644 --- a/sound/core/seq/seq_ports.c +++ b/sound/core/seq/seq_ports.c @@ -535,19 +535,22 @@ static void delete_and_unsubscribe_port(struct snd_seq_client *client, bool is_src, bool ack) { struct snd_seq_port_subs_info *grp; + struct list_head *list; + bool empty; grp = is_src ? &port->c_src : &port->c_dest; + list = is_src ? &subs->src_list : &subs->dest_list; down_write(&grp->list_mutex); write_lock_irq(&grp->list_lock); - if (is_src) - list_del(&subs->src_list); - else - list_del(&subs->dest_list); + empty = list_empty(list); + if (!empty) + list_del_init(list); grp->exclusive = 0; write_unlock_irq(&grp->list_lock); up_write(&grp->list_mutex); - unsubscribe_port(client, port, grp, &subs->info, ack); + if (!empty) + unsubscribe_port(client, port, grp, &subs->info, ack); } /* connect two ports */ diff --git a/sound/core/timer.c b/sound/core/timer.c index 00e8c5f4de17..bf48e71f73cd 100644 --- a/sound/core/timer.c +++ b/sound/core/timer.c @@ -422,7 +422,7 @@ static void snd_timer_notify1(struct snd_timer_instance *ti, int event) spin_lock_irqsave(&timer->lock, flags); list_for_each_entry(ts, &ti->slave_active_head, active_list) if (ts->ccallback) - ts->ccallback(ti, event + 100, &tstamp, resolution); + ts->ccallback(ts, event + 100, &tstamp, resolution); spin_unlock_irqrestore(&timer->lock, flags); } @@ -518,9 +518,13 @@ static int _snd_timer_stop(struct snd_timer_instance *timeri, int event) spin_unlock_irqrestore(&slave_active_lock, flags); return -EBUSY; } + if (timeri->timer) + spin_lock(&timeri->timer->lock); timeri->flags &= ~SNDRV_TIMER_IFLG_RUNNING; list_del_init(&timeri->ack_list); list_del_init(&timeri->active_list); + if (timeri->timer) + spin_unlock(&timeri->timer->lock); spin_unlock_irqrestore(&slave_active_lock, flags); goto __end; } @@ -1920,6 +1924,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, { struct snd_timer_user *tu; long result = 0, unit; + int qhead; int err = 0; tu = file->private_data; @@ -1931,7 +1936,7 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) { err = -EAGAIN; - break; + goto _error; } set_current_state(TASK_INTERRUPTIBLE); @@ -1946,42 +1951,37 @@ static ssize_t snd_timer_user_read(struct file *file, char __user *buffer, if (tu->disconnected) { err = -ENODEV; - break; + goto _error; } if (signal_pending(current)) { err = -ERESTARTSYS; - break; + goto _error; } } + qhead = tu->qhead++; + tu->qhead %= tu->queue_size; spin_unlock_irq(&tu->qlock); - if (err < 0) - goto _error; if (tu->tread) { - if (copy_to_user(buffer, &tu->tqueue[tu->qhead++], - sizeof(struct snd_timer_tread))) { + if (copy_to_user(buffer, &tu->tqueue[qhead], + sizeof(struct snd_timer_tread))) err = -EFAULT; - goto _error; - } } else { - if (copy_to_user(buffer, &tu->queue[tu->qhead++], - sizeof(struct snd_timer_read))) { + if (copy_to_user(buffer, &tu->queue[qhead], + sizeof(struct snd_timer_read))) err = -EFAULT; - goto _error; - } } - tu->qhead %= tu->queue_size; - - result += unit; - buffer += unit; - spin_lock_irq(&tu->qlock); tu->qused--; + if (err < 0) + goto _error; + result += unit; + buffer += unit; } - spin_unlock_irq(&tu->qlock); _error: + spin_unlock_irq(&tu->qlock); return result > 0 ? result : err; } diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c index 96592d5ba7bf..c5d5217a4180 100644 --- a/sound/drivers/dummy.c +++ b/sound/drivers/dummy.c @@ -87,7 +87,7 @@ MODULE_PARM_DESC(pcm_substreams, "PCM substreams # (1-128) for dummy driver."); module_param(fake_buffer, bool, 0444); MODULE_PARM_DESC(fake_buffer, "Fake buffer allocations."); #ifdef CONFIG_HIGH_RES_TIMERS -module_param(hrtimer, bool, 0444); +module_param(hrtimer, bool, 0644); MODULE_PARM_DESC(hrtimer, "Use hrtimer as the timer source."); #endif @@ -109,6 +109,9 @@ struct dummy_timer_ops { snd_pcm_uframes_t (*pointer)(struct snd_pcm_substream *); }; +#define get_dummy_ops(substream) \ + (*(const struct dummy_timer_ops **)(substream)->runtime->private_data) + struct dummy_model { const char *name; int (*playback_constraints)(struct snd_pcm_runtime *runtime); @@ -137,7 +140,6 @@ struct snd_dummy { int iobox; struct snd_kcontrol *cd_volume_ctl; struct snd_kcontrol *cd_switch_ctl; - const struct dummy_timer_ops *timer_ops; }; /* @@ -231,6 +233,8 @@ struct dummy_model *dummy_models[] = { */ struct dummy_systimer_pcm { + /* ops must be the first item */ + const struct dummy_timer_ops *timer_ops; spinlock_t lock; struct timer_list timer; unsigned long base_time; @@ -366,6 +370,8 @@ static struct dummy_timer_ops dummy_systimer_ops = { */ struct dummy_hrtimer_pcm { + /* ops must be the first item */ + const struct dummy_timer_ops *timer_ops; ktime_t base_time; ktime_t period_time; atomic_t running; @@ -492,31 +498,25 @@ static struct dummy_timer_ops dummy_hrtimer_ops = { static int dummy_pcm_trigger(struct snd_pcm_substream *substream, int cmd) { - struct snd_dummy *dummy = snd_pcm_substream_chip(substream); - switch (cmd) { case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: - return dummy->timer_ops->start(substream); + return get_dummy_ops(substream)->start(substream); case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: - return dummy->timer_ops->stop(substream); + return get_dummy_ops(substream)->stop(substream); } return -EINVAL; } static int dummy_pcm_prepare(struct snd_pcm_substream *substream) { - struct snd_dummy *dummy = snd_pcm_substream_chip(substream); - - return dummy->timer_ops->prepare(substream); + return get_dummy_ops(substream)->prepare(substream); } static snd_pcm_uframes_t dummy_pcm_pointer(struct snd_pcm_substream *substream) { - struct snd_dummy *dummy = snd_pcm_substream_chip(substream); - - return dummy->timer_ops->pointer(substream); + return get_dummy_ops(substream)->pointer(substream); } static struct snd_pcm_hardware dummy_pcm_hardware = { @@ -562,17 +562,19 @@ static int dummy_pcm_open(struct snd_pcm_substream *substream) struct snd_dummy *dummy = snd_pcm_substream_chip(substream); struct dummy_model *model = dummy->model; struct snd_pcm_runtime *runtime = substream->runtime; + const struct dummy_timer_ops *ops; int err; - dummy->timer_ops = &dummy_systimer_ops; + ops = &dummy_systimer_ops; #ifdef CONFIG_HIGH_RES_TIMERS if (hrtimer) - dummy->timer_ops = &dummy_hrtimer_ops; + ops = &dummy_hrtimer_ops; #endif - err = dummy->timer_ops->create(substream); + err = ops->create(substream); if (err < 0) return err; + get_dummy_ops(substream) = ops; runtime->hw = dummy->pcm_hw; if (substream->pcm->device & 1) { @@ -594,7 +596,7 @@ static int dummy_pcm_open(struct snd_pcm_substream *substream) err = model->capture_constraints(substream->runtime); } if (err < 0) { - dummy->timer_ops->free(substream); + get_dummy_ops(substream)->free(substream); return err; } return 0; @@ -602,8 +604,7 @@ static int dummy_pcm_open(struct snd_pcm_substream *substream) static int dummy_pcm_close(struct snd_pcm_substream *substream) { - struct snd_dummy *dummy = snd_pcm_substream_chip(substream); - dummy->timer_ops->free(substream); + get_dummy_ops(substream)->free(substream); return 0; } diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index 5bc7f2e2715c..194627c6c42b 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -3998,9 +3998,9 @@ static void pin_power_callback(struct hda_codec *codec, struct hda_jack_callback *jack, bool on) { - if (jack && jack->tbl->nid) + if (jack && jack->nid) sync_power_state_change(codec, - set_pin_power_jack(codec, jack->tbl->nid, on)); + set_pin_power_jack(codec, jack->nid, on)); } /* callback only doing power up -- called at first */ diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 09920ba55ba1..69093ce34231 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -1976,10 +1976,10 @@ static void azx_remove(struct pci_dev *pci) struct hda_intel *hda; if (card) { - /* flush the pending probing work */ + /* cancel the pending probing work */ chip = card->private_data; hda = container_of(chip, struct hda_intel, chip); - flush_work(&hda->probe_work); + cancel_work_sync(&hda->probe_work); snd_card_free(card); } diff --git a/sound/pci/hda/hda_jack.c b/sound/pci/hda/hda_jack.c index d7cfe7b8c32b..52cc36758dd4 100644 --- a/sound/pci/hda/hda_jack.c +++ b/sound/pci/hda/hda_jack.c @@ -259,7 +259,7 @@ snd_hda_jack_detect_enable_callback(struct hda_codec *codec, hda_nid_t nid, if (!callback) return ERR_PTR(-ENOMEM); callback->func = func; - callback->tbl = jack; + callback->nid = jack->nid; callback->next = jack->callback; jack->callback = callback; } diff --git a/sound/pci/hda/hda_jack.h b/sound/pci/hda/hda_jack.h index b279e327a23b..a13c11c3ddbb 100644 --- a/sound/pci/hda/hda_jack.h +++ b/sound/pci/hda/hda_jack.h @@ -21,7 +21,7 @@ struct hda_jack_callback; typedef void (*hda_jack_callback_fn) (struct hda_codec *, struct hda_jack_callback *); struct hda_jack_callback { - struct hda_jack_tbl *tbl; + hda_nid_t nid; hda_jack_callback_fn func; unsigned int private_data; /* arbitrary data */ struct hda_jack_callback *next; diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 4a4e7b282e4f..0374bd5b61c8 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -4401,13 +4401,16 @@ static void ca0132_process_dsp_response(struct hda_codec *codec, static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb) { struct ca0132_spec *spec = codec->spec; + struct hda_jack_tbl *tbl; /* Delay enabling the HP amp, to let the mic-detection * state machine run. */ cancel_delayed_work_sync(&spec->unsol_hp_work); schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500)); - cb->tbl->block_report = 1; + tbl = snd_hda_jack_tbl_get(codec, cb->nid); + if (tbl) + tbl->block_report = 1; } static void amic_callback(struct hda_codec *codec, struct hda_jack_callback *cb) diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index d02eccd51f6e..51d519554744 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -433,7 +433,8 @@ static int hdmi_eld_ctl_get(struct snd_kcontrol *kcontrol, eld = &per_pin->sink_eld; mutex_lock(&per_pin->lock); - if (eld->eld_size > ARRAY_SIZE(ucontrol->value.bytes.data)) { + if (eld->eld_size > ARRAY_SIZE(ucontrol->value.bytes.data) || + eld->eld_size > ELD_MAX_SIZE) { mutex_unlock(&per_pin->lock); snd_BUG(); return -EINVAL; @@ -1178,7 +1179,7 @@ static void check_presence_and_report(struct hda_codec *codec, hda_nid_t nid) static void jack_callback(struct hda_codec *codec, struct hda_jack_callback *jack) { - check_presence_and_report(codec, jack->tbl->nid); + check_presence_and_report(codec, jack->nid); } static void hdmi_intrinsic_event(struct hda_codec *codec, unsigned int res) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 8189f02f8446..df34c78a6ced 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -277,7 +277,7 @@ static void alc_update_knob_master(struct hda_codec *codec, uctl = kzalloc(sizeof(*uctl), GFP_KERNEL); if (!uctl) return; - val = snd_hda_codec_read(codec, jack->tbl->nid, 0, + val = snd_hda_codec_read(codec, jack->nid, 0, AC_VERB_GET_VOLUME_KNOB_CONTROL, 0); val &= HDA_AMP_VOLMASK; uctl->value.integer.value[0] = val; @@ -1792,7 +1792,6 @@ enum { ALC882_FIXUP_NO_PRIMARY_HP, ALC887_FIXUP_ASUS_BASS, ALC887_FIXUP_BASS_CHMAP, - ALC882_FIXUP_DISABLE_AAMIX, }; static void alc889_fixup_coef(struct hda_codec *codec, @@ -1954,8 +1953,6 @@ static void alc882_fixup_no_primary_hp(struct hda_codec *codec, static void alc_fixup_bass_chmap(struct hda_codec *codec, const struct hda_fixup *fix, int action); -static void alc_fixup_disable_aamix(struct hda_codec *codec, - const struct hda_fixup *fix, int action); static const struct hda_fixup alc882_fixups[] = { [ALC882_FIXUP_ABIT_AW9D_MAX] = { @@ -2193,10 +2190,6 @@ static const struct hda_fixup alc882_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_bass_chmap, }, - [ALC882_FIXUP_DISABLE_AAMIX] = { - .type = HDA_FIXUP_FUNC, - .v.func = alc_fixup_disable_aamix, - }, }; static const struct snd_pci_quirk alc882_fixup_tbl[] = { @@ -2235,6 +2228,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x104d, 0x9047, "Sony Vaio TT", ALC889_FIXUP_VAIO_TT), SND_PCI_QUIRK(0x104d, 0x905a, "Sony Vaio Z", ALC882_FIXUP_NO_PRIMARY_HP), SND_PCI_QUIRK(0x104d, 0x9043, "Sony Vaio VGC-LN51JGB", ALC882_FIXUP_NO_PRIMARY_HP), + SND_PCI_QUIRK(0x104d, 0x9044, "Sony VAIO AiO", ALC882_FIXUP_NO_PRIMARY_HP), /* All Apple entries are in codec SSIDs */ SND_PCI_QUIRK(0x106b, 0x00a0, "MacBookPro 3,1", ALC889_FIXUP_MBP_VREF), @@ -2264,7 +2258,6 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD), SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3), SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE), - SND_PCI_QUIRK(0x1458, 0xa182, "Gigabyte Z170X-UD3", ALC882_FIXUP_DISABLE_AAMIX), SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX), SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD), SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD), diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index 8e7d4c087a7a..840178a26a6b 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -493,9 +493,9 @@ static void jack_update_power(struct hda_codec *codec, if (!spec->num_pwrs) return; - if (jack && jack->tbl->nid) { - stac_toggle_power_map(codec, jack->tbl->nid, - snd_hda_jack_detect(codec, jack->tbl->nid), + if (jack && jack->nid) { + stac_toggle_power_map(codec, jack->nid, + snd_hda_jack_detect(codec, jack->nid), true); return; } diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index 2ee44abd56a6..6cbd03a5e53d 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -487,7 +487,7 @@ static const struct snd_kcontrol_new rt5645_snd_controls[] = { /* IN1/IN2 Control */ SOC_SINGLE_TLV("IN1 Boost", RT5645_IN1_CTRL1, - RT5645_BST_SFT1, 8, 0, bst_tlv), + RT5645_BST_SFT1, 12, 0, bst_tlv), SOC_SINGLE_TLV("IN2 Boost", RT5645_IN2_CTRL, RT5645_BST_SFT2, 8, 0, bst_tlv), diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 35fe58f4fa86..52fe7eb2dea1 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -1661,7 +1661,8 @@ int dpcm_be_dai_hw_free(struct snd_soc_pcm_runtime *fe, int stream) (be->dpcm[stream].state != SND_SOC_DPCM_STATE_PREPARE) && (be->dpcm[stream].state != SND_SOC_DPCM_STATE_HW_FREE) && (be->dpcm[stream].state != SND_SOC_DPCM_STATE_PAUSED) && - (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP)) + (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP) && + (be->dpcm[stream].state != SND_SOC_DPCM_STATE_SUSPEND)) continue; dev_dbg(be->dev, "ASoC: hw_free BE %s\n", diff --git a/sound/usb/midi.c b/sound/usb/midi.c index bec63e0d2605..f059326a4914 100644 --- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -2451,7 +2451,6 @@ int snd_usbmidi_create(struct snd_card *card, else err = snd_usbmidi_create_endpoints(umidi, endpoints); if (err < 0) { - snd_usbmidi_free(umidi); return err; }