diff --git a/Documentation/sysctl/fs.txt b/Documentation/sysctl/fs.txt index 302b5ed616a6..35e17f748ca7 100644 --- a/Documentation/sysctl/fs.txt +++ b/Documentation/sysctl/fs.txt @@ -265,6 +265,13 @@ aio-nr can grow to. ============================================================== +mount-max: + +This denotes the maximum number of mounts that may exist +in a mount namespace. + +============================================================== + 2. /proc/sys/fs/binfmt_misc ---------------------------------------------------------- diff --git a/Makefile b/Makefile index 1de081602f3e..933d159a74d7 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 63 +SUBLEVEL = 65 EXTRAVERSION = NAME = Blurry Fish Butt diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index dd7f20a490c8..33ee522bb76f 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -301,6 +301,14 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp, next = kvm_pgd_addr_end(addr, end); if (!pgd_none(*pgd)) unmap_puds(kvm, pgd, addr, next); + /* + * If we are dealing with a large range in + * stage2 table, release the kvm->mmu_lock + * to prevent starvation and lockup detector + * warnings. + */ + if (kvm && (next != end)) + cond_resched_lock(&kvm->mmu_lock); } while (pgd++, addr = next, addr != end); } @@ -745,6 +753,7 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm) */ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size) { + assert_spin_locked(&kvm->mmu_lock); unmap_range(kvm, kvm->arch.pgd, start, size); } @@ -831,7 +840,10 @@ void kvm_free_stage2_pgd(struct kvm *kvm) if (kvm->arch.pgd == NULL) return; + spin_lock(&kvm->mmu_lock); unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE); + spin_unlock(&kvm->mmu_lock); + kvm_free_hwpgd(kvm_get_hwpgd(kvm)); if (KVM_PREALLOC_LEVEL > 0) kfree(kvm->arch.pgd); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index edba294620db..f6fd0332c3a2 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -716,7 +716,7 @@ resume_kernel: addi r8,r1,INT_FRAME_SIZE /* Get the kprobed function entry */ - lwz r3,GPR1(r1) + ld r3,GPR1(r1) subi r3,r3,INT_FRAME_SIZE /* dst: Allocate a trampoline exception frame */ mr r4,r1 /* src: current exception frame */ mr r1,r3 /* Reroute the trampoline frame to r1 */ @@ -730,8 +730,8 @@ resume_kernel: addi r6,r6,8 bdnz 2b - /* Do real store operation to complete stwu */ - lwz r5,GPR1(r1) + /* Do real store operation to complete stdu */ + ld r5,GPR1(r1) std r8,0(r5) /* Clear _TIF_EMULATE_STACK_STORE flag */ diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 024f85f947ae..e2c0e4eab037 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -829,6 +829,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, { pgste_t pgste; + if (pte_present(entry)) + pte_val(entry) &= ~_PAGE_UNUSED; if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); pgste_val(pgste) &= ~_PGSTE_GPS_ZERO; diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h index d8ce3ec816ab..bd8ce6bcdfc9 100644 --- a/arch/x86/include/asm/pmem.h +++ b/arch/x86/include/asm/pmem.h @@ -72,8 +72,8 @@ static inline void arch_wmb_pmem(void) * @size: number of bytes to write back * * Write back a cache range using the CLWB (cache line write back) - * instruction. This function requires explicit ordering with an - * arch_wmb_pmem() call. This API is internal to the x86 PMEM implementation. + * instruction. Note that @size is internally rounded up to be cache + * line size aligned. */ static inline void __arch_wb_cache_pmem(void *vaddr, size_t size) { @@ -87,15 +87,6 @@ static inline void __arch_wb_cache_pmem(void *vaddr, size_t size) clwb(p); } -/* - * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec - * iterators, so for other types (bvec & kvec) we must do a cache write-back. - */ -static inline bool __iter_needs_pmem_wb(struct iov_iter *i) -{ - return iter_is_iovec(i) == false; -} - /** * arch_copy_from_iter_pmem - copy data from an iterator to PMEM * @addr: PMEM destination address @@ -114,8 +105,36 @@ static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes, /* TODO: skip the write-back by always using non-temporal stores */ len = copy_from_iter_nocache(vaddr, bytes, i); - if (__iter_needs_pmem_wb(i)) - __arch_wb_cache_pmem(vaddr, bytes); + /* + * In the iovec case on x86_64 copy_from_iter_nocache() uses + * non-temporal stores for the bulk of the transfer, but we need + * to manually flush if the transfer is unaligned. A cached + * memory copy is used when destination or size is not naturally + * aligned. That is: + * - Require 8-byte alignment when size is 8 bytes or larger. + * - Require 4-byte alignment when size is 4 bytes. + * + * In the non-iovec case the entire destination needs to be + * flushed. + */ + if (iter_is_iovec(i)) { + unsigned long flushed, dest = (unsigned long) addr; + + if (bytes < 8) { + if (!IS_ALIGNED(dest, 4) || (bytes != 4)) + __arch_wb_cache_pmem(addr, 1); + } else { + if (!IS_ALIGNED(dest, 8)) { + dest = ALIGN(dest, boot_cpu_data.x86_clflush_size); + __arch_wb_cache_pmem(addr, 1); + } + + flushed = dest - (unsigned long) addr; + if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8)) + __arch_wb_cache_pmem(addr + bytes - 1, 1); + } + } else + __arch_wb_cache_pmem(addr, bytes); return len; } diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index e99b15077e94..62aca448726a 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -53,7 +53,7 @@ static const char * const th_names[] = { "load_store", "insn_fetch", "combined_unit", - "", + "decode_unit", "northbridge", "execution_unit", }; diff --git a/block/genhd.c b/block/genhd.c index 7f1e8f81ceb4..de2a6162e3f3 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -673,7 +673,6 @@ void del_gendisk(struct gendisk *disk) kobject_put(disk->part0.holder_dir); kobject_put(disk->slave_dir); - disk->driverfs_dev = NULL; if (!sysfs_deprecated) sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk))); pm_runtime_set_memalloc_noio(disk_to_dev(disk), false); diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index fcd4ce6f78d5..1c2b846c5776 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -200,6 +200,7 @@ static int acpi_power_get_list_state(struct list_head *list, int *state) return -EINVAL; /* The state of the list is 'on' IFF all resources are 'on'. */ + cur_state = 0; list_for_each_entry(entry, list, node) { struct acpi_power_resource *resource = entry->resource; acpi_handle handle = resource->device.handle; diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 1ef37c727572..d037454fe7b8 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -73,7 +73,6 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size, void *in, *out; unsigned long flags; int ret, err = 0; - unsigned long t; struct page *page; spin_lock_irqsave(&newchannel->lock, flags); @@ -183,11 +182,7 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size, goto error1; } - t = wait_for_completion_timeout(&open_info->waitevent, 5*HZ); - if (t == 0) { - err = -ETIMEDOUT; - goto error1; - } + wait_for_completion(&open_info->waitevent); spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags); list_del(&open_info->msglistentry); @@ -375,7 +370,7 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer, struct vmbus_channel_gpadl_header *gpadlmsg; struct vmbus_channel_gpadl_body *gpadl_body; struct vmbus_channel_msginfo *msginfo = NULL; - struct vmbus_channel_msginfo *submsginfo; + struct vmbus_channel_msginfo *submsginfo, *tmp; u32 msgcount; struct list_head *curr; u32 next_gpadl_handle; @@ -437,6 +432,13 @@ cleanup: list_del(&msginfo->msglistentry); spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags); + if (msgcount > 1) { + list_for_each_entry_safe(submsginfo, tmp, &msginfo->submsglist, + msglistentry) { + kfree(submsginfo); + } + } + kfree(msginfo); return ret; } diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index 4fc2e8836e60..2bbc53025549 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -429,7 +429,7 @@ int vmbus_post_msg(void *buffer, size_t buflen) union hv_connection_id conn_id; int ret = 0; int retries = 0; - u32 msec = 1; + u32 usec = 1; conn_id.asu32 = 0; conn_id.u.id = VMBUS_MESSAGE_CONNECTION_ID; @@ -462,9 +462,9 @@ int vmbus_post_msg(void *buffer, size_t buflen) } retries++; - msleep(msec); - if (msec < 2048) - msec *= 2; + udelay(usec); + if (usec < 2048) + usec *= 2; } return ret; } diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index ddbf7e7e0d98..8ce1f2e22912 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -305,9 +305,10 @@ void hv_cleanup(bool crash) hypercall_msr.as_uint64 = 0; wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64); - if (!crash) + if (!crash) { vfree(hv_context.tsc_page); - hv_context.tsc_page = NULL; + hv_context.tsc_page = NULL; + } } #endif } diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 43af91362be5..354da7f207b7 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -430,16 +430,27 @@ struct dm_info_msg { * currently hot added. We hot add in multiples of 128M * chunks; it is possible that we may not be able to bring * online all the pages in the region. The range - * covered_end_pfn defines the pages that can + * covered_start_pfn:covered_end_pfn defines the pages that can * be brough online. */ struct hv_hotadd_state { struct list_head list; unsigned long start_pfn; + unsigned long covered_start_pfn; unsigned long covered_end_pfn; unsigned long ha_end_pfn; unsigned long end_pfn; + /* + * A list of gaps. + */ + struct list_head gap_list; +}; + +struct hv_hotadd_gap { + struct list_head list; + unsigned long start_pfn; + unsigned long end_pfn; }; struct balloon_state { @@ -595,18 +606,46 @@ static struct notifier_block hv_memory_nb = { .priority = 0 }; +/* Check if the particular page is backed and can be onlined and online it. */ +static void hv_page_online_one(struct hv_hotadd_state *has, struct page *pg) +{ + unsigned long cur_start_pgp; + unsigned long cur_end_pgp; + struct hv_hotadd_gap *gap; -static void hv_bring_pgs_online(unsigned long start_pfn, unsigned long size) + cur_start_pgp = (unsigned long)pfn_to_page(has->covered_start_pfn); + cur_end_pgp = (unsigned long)pfn_to_page(has->covered_end_pfn); + + /* The page is not backed. */ + if (((unsigned long)pg < cur_start_pgp) || + ((unsigned long)pg >= cur_end_pgp)) + return; + + /* Check for gaps. */ + list_for_each_entry(gap, &has->gap_list, list) { + cur_start_pgp = (unsigned long) + pfn_to_page(gap->start_pfn); + cur_end_pgp = (unsigned long) + pfn_to_page(gap->end_pfn); + if (((unsigned long)pg >= cur_start_pgp) && + ((unsigned long)pg < cur_end_pgp)) { + return; + } + } + + /* This frame is currently backed; online the page. */ + __online_page_set_limits(pg); + __online_page_increment_counters(pg); + __online_page_free(pg); +} + +static void hv_bring_pgs_online(struct hv_hotadd_state *has, + unsigned long start_pfn, unsigned long size) { int i; - for (i = 0; i < size; i++) { - struct page *pg; - pg = pfn_to_page(start_pfn + i); - __online_page_set_limits(pg); - __online_page_increment_counters(pg); - __online_page_free(pg); - } + for (i = 0; i < size; i++) + hv_page_online_one(has, pfn_to_page(start_pfn + i)); } static void hv_mem_hot_add(unsigned long start, unsigned long size, @@ -682,26 +721,25 @@ static void hv_online_page(struct page *pg) list_for_each(cur, &dm_device.ha_region_list) { has = list_entry(cur, struct hv_hotadd_state, list); - cur_start_pgp = (unsigned long)pfn_to_page(has->start_pfn); - cur_end_pgp = (unsigned long)pfn_to_page(has->covered_end_pfn); + cur_start_pgp = (unsigned long) + pfn_to_page(has->start_pfn); + cur_end_pgp = (unsigned long)pfn_to_page(has->end_pfn); - if (((unsigned long)pg >= cur_start_pgp) && - ((unsigned long)pg < cur_end_pgp)) { - /* - * This frame is currently backed; online the - * page. - */ - __online_page_set_limits(pg); - __online_page_increment_counters(pg); - __online_page_free(pg); - } + /* The page belongs to a different HAS. */ + if (((unsigned long)pg < cur_start_pgp) || + ((unsigned long)pg >= cur_end_pgp)) + continue; + + hv_page_online_one(has, pg); + break; } } -static bool pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt) +static int pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt) { struct list_head *cur; struct hv_hotadd_state *has; + struct hv_hotadd_gap *gap; unsigned long residual, new_inc; if (list_empty(&dm_device.ha_region_list)) @@ -716,6 +754,24 @@ static bool pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt) */ if (start_pfn < has->start_pfn || start_pfn >= has->end_pfn) continue; + + /* + * If the current start pfn is not where the covered_end + * is, create a gap and update covered_end_pfn. + */ + if (has->covered_end_pfn != start_pfn) { + gap = kzalloc(sizeof(struct hv_hotadd_gap), GFP_ATOMIC); + if (!gap) + return -ENOMEM; + + INIT_LIST_HEAD(&gap->list); + gap->start_pfn = has->covered_end_pfn; + gap->end_pfn = start_pfn; + list_add_tail(&gap->list, &has->gap_list); + + has->covered_end_pfn = start_pfn; + } + /* * If the current hot add-request extends beyond * our current limit; extend it. @@ -732,19 +788,10 @@ static bool pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt) has->end_pfn += new_inc; } - /* - * If the current start pfn is not where the covered_end - * is, update it. - */ - - if (has->covered_end_pfn != start_pfn) - has->covered_end_pfn = start_pfn; - - return true; - + return 1; } - return false; + return 0; } static unsigned long handle_pg_range(unsigned long pg_start, @@ -783,6 +830,8 @@ static unsigned long handle_pg_range(unsigned long pg_start, if (pgs_ol > pfn_cnt) pgs_ol = pfn_cnt; + has->covered_end_pfn += pgs_ol; + pfn_cnt -= pgs_ol; /* * Check if the corresponding memory block is already * online by checking its last previously backed page. @@ -791,10 +840,8 @@ static unsigned long handle_pg_range(unsigned long pg_start, */ if (start_pfn > has->start_pfn && !PageReserved(pfn_to_page(start_pfn - 1))) - hv_bring_pgs_online(start_pfn, pgs_ol); + hv_bring_pgs_online(has, start_pfn, pgs_ol); - has->covered_end_pfn += pgs_ol; - pfn_cnt -= pgs_ol; } if ((has->ha_end_pfn < has->end_pfn) && (pfn_cnt > 0)) { @@ -832,13 +879,19 @@ static unsigned long process_hot_add(unsigned long pg_start, unsigned long rg_size) { struct hv_hotadd_state *ha_region = NULL; + int covered; if (pfn_cnt == 0) return 0; - if (!dm_device.host_specified_ha_region) - if (pfn_covered(pg_start, pfn_cnt)) + if (!dm_device.host_specified_ha_region) { + covered = pfn_covered(pg_start, pfn_cnt); + if (covered < 0) + return 0; + + if (covered) goto do_pg_range; + } /* * If the host has specified a hot-add range; deal with it first. @@ -850,10 +903,12 @@ static unsigned long process_hot_add(unsigned long pg_start, return 0; INIT_LIST_HEAD(&ha_region->list); + INIT_LIST_HEAD(&ha_region->gap_list); list_add_tail(&ha_region->list, &dm_device.ha_region_list); ha_region->start_pfn = rg_start; ha_region->ha_end_pfn = rg_start; + ha_region->covered_start_pfn = pg_start; ha_region->covered_end_pfn = pg_start; ha_region->end_pfn = rg_start + rg_size; } @@ -1581,6 +1636,7 @@ static int balloon_remove(struct hv_device *dev) struct hv_dynmem_device *dm = hv_get_drvdata(dev); struct list_head *cur, *tmp; struct hv_hotadd_state *has; + struct hv_hotadd_gap *gap, *tmp_gap; if (dm->num_pages_ballooned != 0) pr_warn("Ballooned pages: %d\n", dm->num_pages_ballooned); @@ -1597,6 +1653,10 @@ static int balloon_remove(struct hv_device *dev) #endif list_for_each_safe(cur, tmp, &dm->ha_region_list) { has = list_entry(cur, struct hv_hotadd_state, list); + list_for_each_entry_safe(gap, tmp_gap, &has->gap_list, list) { + list_del(&gap->list); + kfree(gap); + } list_del(&has->list); kfree(has); } diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 43482ae1e049..1a2b2620421e 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -1122,6 +1122,7 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse, * Asus UX32VD 0x361f02 00, 15, 0e clickpad * Avatar AVIU-145A2 0x361f00 ? clickpad * Fujitsu LIFEBOOK E544 0x470f00 d0, 12, 09 2 hw buttons + * Fujitsu LIFEBOOK E547 0x470f00 50, 12, 09 2 hw buttons * Fujitsu LIFEBOOK E554 0x570f01 40, 14, 0c 2 hw buttons * Fujitsu T725 0x470f01 05, 12, 09 2 hw buttons * Fujitsu H730 0x570f00 c0, 14, 0c 3 hw buttons (**) @@ -1527,6 +1528,13 @@ static const struct dmi_system_id elantech_dmi_force_crc_enabled[] = { DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E544"), }, }, + { + /* Fujitsu LIFEBOOK E547 does not work with crc_enabled == 0 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E547"), + }, + }, { /* Fujitsu LIFEBOOK E554 does not work with crc_enabled == 0 */ .matches = { diff --git a/drivers/md/Makefile b/drivers/md/Makefile index eef9097c60b3..41ba86576d04 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -71,10 +71,6 @@ ifeq ($(CONFIG_DM_VERITY_FEC),y) dm-verity-objs += dm-verity-fec.o endif -ifeq ($(CONFIG_DM_ANDROID_VERITY),y) -dm-verity-objs += dm-android-verity.o -endif - ifeq ($(CONFIG_DM_VERITY_AVB),y) dm-verity-objs += dm-verity-avb.o endif diff --git a/drivers/misc/uid_sys_stats.c b/drivers/misc/uid_sys_stats.c index 618617f3e867..ad21276c8d9e 100644 --- a/drivers/misc/uid_sys_stats.c +++ b/drivers/misc/uid_sys_stats.c @@ -95,9 +95,11 @@ static int uid_cputime_show(struct seq_file *m, void *v) { struct uid_entry *uid_entry; struct task_struct *task, *temp; + struct user_namespace *user_ns = current_user_ns(); cputime_t utime; cputime_t stime; unsigned long bkt; + uid_t uid; rt_mutex_lock(&uid_lock); @@ -108,14 +110,13 @@ static int uid_cputime_show(struct seq_file *m, void *v) read_lock(&tasklist_lock); do_each_thread(temp, task) { - uid_entry = find_or_register_uid(from_kuid_munged( - current_user_ns(), task_uid(task))); + uid = from_kuid_munged(user_ns, task_uid(task)); + uid_entry = find_or_register_uid(uid); if (!uid_entry) { read_unlock(&tasklist_lock); rt_mutex_unlock(&uid_lock); pr_err("%s: failed to find the uid_entry for uid %d\n", - __func__, from_kuid_munged(current_user_ns(), - task_uid(task))); + __func__, uid); return -ENOMEM; } task_cputime_adjusted(task, &utime, &stime); diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index 1f1582f6cccb..8d838779fd1b 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -804,6 +804,7 @@ static int esdhc_change_pinstate(struct sdhci_host *host, switch (uhs) { case MMC_TIMING_UHS_SDR50: + case MMC_TIMING_UHS_DDR50: pinctrl = imx_data->pins_100mhz; break; case MMC_TIMING_UHS_SDR104: diff --git a/drivers/mtd/ubi/upd.c b/drivers/mtd/ubi/upd.c index 0134ba32a057..39712560b4c1 100644 --- a/drivers/mtd/ubi/upd.c +++ b/drivers/mtd/ubi/upd.c @@ -148,11 +148,11 @@ int ubi_start_update(struct ubi_device *ubi, struct ubi_volume *vol, return err; } - if (bytes == 0) { - err = ubi_wl_flush(ubi, UBI_ALL, UBI_ALL); - if (err) - return err; + err = ubi_wl_flush(ubi, UBI_ALL, UBI_ALL); + if (err) + return err; + if (bytes == 0) { err = clear_update_marker(ubi, vol, 0); if (err) return err; diff --git a/drivers/net/wireless/hostap/hostap_hw.c b/drivers/net/wireless/hostap/hostap_hw.c index 6df3ee561d52..515aa3f993f3 100644 --- a/drivers/net/wireless/hostap/hostap_hw.c +++ b/drivers/net/wireless/hostap/hostap_hw.c @@ -836,25 +836,30 @@ static int hfa384x_get_rid(struct net_device *dev, u16 rid, void *buf, int len, spin_lock_bh(&local->baplock); res = hfa384x_setup_bap(dev, BAP0, rid, 0); - if (!res) - res = hfa384x_from_bap(dev, BAP0, &rec, sizeof(rec)); + if (res) + goto unlock; + + res = hfa384x_from_bap(dev, BAP0, &rec, sizeof(rec)); + if (res) + goto unlock; if (le16_to_cpu(rec.len) == 0) { /* RID not available */ res = -ENODATA; + goto unlock; } rlen = (le16_to_cpu(rec.len) - 1) * 2; - if (!res && exact_len && rlen != len) { + if (exact_len && rlen != len) { printk(KERN_DEBUG "%s: hfa384x_get_rid - RID len mismatch: " "rid=0x%04x, len=%d (expected %d)\n", dev->name, rid, rlen, len); res = -ENODATA; } - if (!res) - res = hfa384x_from_bap(dev, BAP0, buf, len); + res = hfa384x_from_bap(dev, BAP0, buf, len); +unlock: spin_unlock_bh(&local->baplock); mutex_unlock(&local->rid_bap_mtx); diff --git a/drivers/tty/nozomi.c b/drivers/tty/nozomi.c index 80f9de907563..5cc80b80c82b 100644 --- a/drivers/tty/nozomi.c +++ b/drivers/tty/nozomi.c @@ -823,7 +823,7 @@ static int receive_data(enum port_type index, struct nozomi *dc) struct tty_struct *tty = tty_port_tty_get(&port->port); int i, ret; - read_mem32((u32 *) &size, addr, 4); + size = __le32_to_cpu(readl(addr)); /* DBG1( "%d bytes port: %d", size, index); */ if (tty && test_bit(TTY_THROTTLED, &tty->flags)) { diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 9982cb176ce8..830e2fd47642 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -562,8 +562,9 @@ static long vfio_pci_ioctl(void *device_data, } else if (cmd == VFIO_DEVICE_SET_IRQS) { struct vfio_irq_set hdr; + size_t size; u8 *data = NULL; - int ret = 0; + int max, ret = 0; minsz = offsetofend(struct vfio_irq_set, count); @@ -571,23 +572,31 @@ static long vfio_pci_ioctl(void *device_data, return -EFAULT; if (hdr.argsz < minsz || hdr.index >= VFIO_PCI_NUM_IRQS || + hdr.count >= (U32_MAX - hdr.start) || hdr.flags & ~(VFIO_IRQ_SET_DATA_TYPE_MASK | VFIO_IRQ_SET_ACTION_TYPE_MASK)) return -EINVAL; - if (!(hdr.flags & VFIO_IRQ_SET_DATA_NONE)) { - size_t size; - int max = vfio_pci_get_irq_count(vdev, hdr.index); + max = vfio_pci_get_irq_count(vdev, hdr.index); + if (hdr.start >= max || hdr.start + hdr.count > max) + return -EINVAL; - if (hdr.flags & VFIO_IRQ_SET_DATA_BOOL) - size = sizeof(uint8_t); - else if (hdr.flags & VFIO_IRQ_SET_DATA_EVENTFD) - size = sizeof(int32_t); - else - return -EINVAL; + switch (hdr.flags & VFIO_IRQ_SET_DATA_TYPE_MASK) { + case VFIO_IRQ_SET_DATA_NONE: + size = 0; + break; + case VFIO_IRQ_SET_DATA_BOOL: + size = sizeof(uint8_t); + break; + case VFIO_IRQ_SET_DATA_EVENTFD: + size = sizeof(int32_t); + break; + default: + return -EINVAL; + } - if (hdr.argsz - minsz < hdr.count * size || - hdr.start >= max || hdr.start + hdr.count > max) + if (size) { + if (hdr.argsz - minsz < hdr.count * size) return -EINVAL; data = memdup_user((void __user *)(arg + minsz), diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 20e9a86d2dcf..5c8f767b6368 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -255,7 +255,7 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix) if (!is_irq_none(vdev)) return -EINVAL; - vdev->ctx = kzalloc(nvec * sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL); + vdev->ctx = kcalloc(nvec, sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL); if (!vdev->ctx) return -ENOMEM; diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index b76883606e4b..94906aaa9b7c 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -906,7 +906,6 @@ struct cifs_tcon { bool use_persistent:1; /* use persistent instead of durable handles */ #ifdef CONFIG_CIFS_SMB2 bool print:1; /* set if connection to printer share */ - bool bad_network_name:1; /* set if ret status STATUS_BAD_NETWORK_NAME */ __le32 capabilities; __u32 share_flags; __u32 maximal_access; diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index fc537c29044e..87b87e091e8e 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -1015,6 +1015,15 @@ cifs_dir_needs_close(struct cifsFileInfo *cfile) return !cfile->srch_inf.endOfSearch && !cfile->invalidHandle; } +static bool +cifs_can_echo(struct TCP_Server_Info *server) +{ + if (server->tcpStatus == CifsGood) + return true; + + return false; +} + struct smb_version_operations smb1_operations = { .send_cancel = send_nt_cancel, .compare_fids = cifs_compare_fids, @@ -1049,6 +1058,7 @@ struct smb_version_operations smb1_operations = { .get_dfs_refer = CIFSGetDFSRefer, .qfs_tcon = cifs_qfs_tcon, .is_path_accessible = cifs_is_path_accessible, + .can_echo = cifs_can_echo, .query_path_info = cifs_query_path_info, .query_file_info = cifs_query_file_info, .get_srv_inum = cifs_get_srv_inum, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 6cb5c4b30e78..6cb2603f8a5c 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -932,9 +932,6 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, else return -EIO; - if (tcon && tcon->bad_network_name) - return -ENOENT; - if ((tcon && tcon->seal) && ((ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) == 0)) { cifs_dbg(VFS, "encryption requested but no server support"); @@ -1036,8 +1033,6 @@ tcon_exit: tcon_error_exit: if (rsp->hdr.Status == STATUS_BAD_NETWORK_NAME) { cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree); - if (tcon) - tcon->bad_network_name = true; } goto tcon_exit; } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 106dda1e743d..92ac61c3ccf7 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -947,6 +947,14 @@ static int sanity_check_raw_super(struct super_block *sb, return 1; } + /* check log blocks per segment */ + if (le32_to_cpu(raw_super->log_blocks_per_seg) != 9) { + f2fs_msg(sb, KERN_INFO, + "Invalid log blocks per segment (%u)\n", + le32_to_cpu(raw_super->log_blocks_per_seg)); + return 1; + } + /* Currently, support 512/1024/2048/4096 bytes sector size */ if (le32_to_cpu(raw_super->log_sectorsize) > F2FS_MAX_LOG_SECTOR_SIZE || diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index ad8a5b757cc7..a443c6e54412 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -760,7 +760,7 @@ static int get_first_leaf(struct gfs2_inode *dip, u32 index, int error; error = get_leaf_nr(dip, index, &leaf_no); - if (!error) + if (!IS_ERR_VALUE(error)) error = get_leaf(dip, leaf_no, bh_out); return error; @@ -976,7 +976,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name) index = name->hash >> (32 - dip->i_depth); error = get_leaf_nr(dip, index, &leaf_no); - if (error) + if (IS_ERR_VALUE(error)) return error; /* Get the old leaf block */ diff --git a/fs/mount.h b/fs/mount.h index 3dc7dea5a357..13a4ebbbaa74 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -13,6 +13,8 @@ struct mnt_namespace { u64 seq; /* Sequence number to prevent loops */ wait_queue_head_t poll; u64 event; + unsigned int mounts; /* # of mounts in the namespace */ + unsigned int pending_mounts; }; struct mnt_pcp { diff --git a/fs/namespace.c b/fs/namespace.c index c1477882a853..a22959c97384 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -27,6 +27,9 @@ #include "pnode.h" #include "internal.h" +/* Maximum number of mounts in a mount namespace */ +unsigned int sysctl_mount_max __read_mostly = 100000; + static unsigned int m_hash_mask __read_mostly; static unsigned int m_hash_shift __read_mostly; static unsigned int mp_hash_mask __read_mostly; @@ -926,6 +929,9 @@ static void commit_tree(struct mount *mnt) list_splice(&head, n->list.prev); + n->mounts += n->pending_mounts; + n->pending_mounts = 0; + __attach_mnt(mnt, parent); touch_mnt_namespace(n); } @@ -1465,11 +1471,16 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) propagate_umount(&tmp_list); while (!list_empty(&tmp_list)) { + struct mnt_namespace *ns; bool disconnect; p = list_first_entry(&tmp_list, struct mount, mnt_list); list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); - __touch_mnt_namespace(p->mnt_ns); + ns = p->mnt_ns; + if (ns) { + ns->mounts--; + __touch_mnt_namespace(ns); + } p->mnt_ns = NULL; if (how & UMOUNT_SYNC) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; @@ -1870,6 +1881,28 @@ static int invent_group_ids(struct mount *mnt, bool recurse) return 0; } +int count_mounts(struct mnt_namespace *ns, struct mount *mnt) +{ + unsigned int max = READ_ONCE(sysctl_mount_max); + unsigned int mounts = 0, old, pending, sum; + struct mount *p; + + for (p = mnt; p; p = next_mnt(p, mnt)) + mounts++; + + old = ns->mounts; + pending = ns->pending_mounts; + sum = old + pending; + if ((old > sum) || + (pending > sum) || + (max < sum) || + (mounts > (max - sum))) + return -ENOSPC; + + ns->pending_mounts = pending + mounts; + return 0; +} + /* * @source_mnt : mount tree to be attached * @nd : place the mount tree @source_mnt is attached @@ -1939,6 +1972,7 @@ static int attach_recursive_mnt(struct mount *source_mnt, struct path *parent_path) { HLIST_HEAD(tree_list); + struct mnt_namespace *ns = dest_mnt->mnt_ns; struct mountpoint *smp; struct mount *child, *p; struct hlist_node *n; @@ -1951,6 +1985,13 @@ static int attach_recursive_mnt(struct mount *source_mnt, if (IS_ERR(smp)) return PTR_ERR(smp); + /* Is there space to add these mounts to the mount namespace? */ + if (!parent_path) { + err = count_mounts(ns, source_mnt); + if (err) + goto out; + } + if (IS_MNT_SHARED(dest_mnt)) { err = invent_group_ids(source_mnt, true); if (err) @@ -1990,11 +2031,14 @@ static int attach_recursive_mnt(struct mount *source_mnt, out_cleanup_ids: while (!hlist_empty(&tree_list)) { child = hlist_entry(tree_list.first, struct mount, mnt_hash); + child->mnt_parent->mnt_ns->pending_mounts = 0; umount_tree(child, UMOUNT_SYNC); } unlock_mount_hash(); cleanup_group_ids(source_mnt, NULL); out: + ns->pending_mounts = 0; + read_seqlock_excl(&mount_lock); put_mountpoint(smp); read_sequnlock_excl(&mount_lock); @@ -2830,6 +2874,8 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns) init_waitqueue_head(&new_ns->poll); new_ns->event = 0; new_ns->user_ns = get_user_ns(user_ns); + new_ns->mounts = 0; + new_ns->pending_mounts = 0; return new_ns; } @@ -2879,6 +2925,7 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, q = new; while (p) { q->mnt_ns = new_ns; + new_ns->mounts++; if (new_fs) { if (&p->mnt == new_fs->root.mnt) { new_fs->root.mnt = mntget(&q->mnt); @@ -2917,6 +2964,7 @@ static struct mnt_namespace *create_mnt_ns(struct vfsmount *m) struct mount *mnt = real_mount(m); mnt->mnt_ns = new_ns; new_ns->root = mnt; + new_ns->mounts++; list_add(&mnt->mnt_list, &new_ns->list); } else { mntput(m); diff --git a/fs/pnode.c b/fs/pnode.c index 1d16bb3bdf5e..b5f97c605d98 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -259,7 +259,7 @@ static int propagate_one(struct mount *m) read_sequnlock_excl(&mount_lock); } hlist_add_head(&child->mnt_hash, list); - return 0; + return count_mounts(m->mnt_ns, child); } /* diff --git a/fs/pnode.h b/fs/pnode.h index f41fc9a6c48e..a9a6576540ad 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -55,4 +55,5 @@ void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *copy_tree(struct mount *, struct dentry *, int); bool is_path_reachable(struct mount *, struct dentry *, const struct path *root); +int count_mounts(struct mnt_namespace *ns, struct mount *mnt); #endif /* _LINUX_PNODE_H */ diff --git a/fs/sdcardfs/dentry.c b/fs/sdcardfs/dentry.c index 8e31d1a80f0c..7a19e77fce99 100644 --- a/fs/sdcardfs/dentry.c +++ b/fs/sdcardfs/dentry.c @@ -60,6 +60,14 @@ static int sdcardfs_d_revalidate(struct dentry *dentry, unsigned int flags) lower_dentry = lower_path.dentry; lower_cur_parent_dentry = dget_parent(lower_dentry); + if ((lower_dentry->d_flags & DCACHE_OP_REVALIDATE)) { + err = lower_dentry->d_op->d_revalidate(lower_dentry, flags); + if (err == 0) { + d_drop(dentry); + goto out; + } + } + spin_lock(&lower_dentry->d_lock); if (d_unhashed(lower_dentry)) { spin_unlock(&lower_dentry->d_lock); diff --git a/fs/sdcardfs/derived_perm.c b/fs/sdcardfs/derived_perm.c index cddfc79ea365..b4595aab5713 100644 --- a/fs/sdcardfs/derived_perm.c +++ b/fs/sdcardfs/derived_perm.c @@ -215,16 +215,16 @@ void fixup_lower_ownership(struct dentry *dentry, const char *name) gid = AID_MEDIA_OBB; break; case PERM_ANDROID_PACKAGE: - if (info->d_uid != 0) + if (uid_is_app(info->d_uid)) gid = multiuser_get_ext_gid(info->d_uid); else - gid = multiuser_get_uid(info->userid, uid); + gid = multiuser_get_uid(info->userid, AID_MEDIA_RW); break; case PERM_ANDROID_PACKAGE_CACHE: - if (info->d_uid != 0) + if (uid_is_app(info->d_uid)) gid = multiuser_get_ext_cache_gid(info->d_uid); else - gid = multiuser_get_uid(info->userid, uid); + gid = multiuser_get_uid(info->userid, AID_MEDIA_RW); break; case PERM_PRE_ROOT: default: diff --git a/fs/sdcardfs/file.c b/fs/sdcardfs/file.c index 1f6921e2ffbf..6076c342dae6 100644 --- a/fs/sdcardfs/file.c +++ b/fs/sdcardfs/file.c @@ -358,9 +358,12 @@ ssize_t sdcardfs_read_iter(struct kiocb *iocb, struct iov_iter *iter) get_file(lower_file); /* prevent lower_file from being released */ iocb->ki_filp = lower_file; err = lower_file->f_op->read_iter(iocb, iter); - /* ? wait IO finish to update atime as ecryptfs ? */ iocb->ki_filp = file; fput(lower_file); + /* update upper inode atime as needed */ + if (err >= 0 || err == -EIOCBQUEUED) + fsstack_copy_attr_atime(file->f_path.dentry->d_inode, + file_inode(lower_file)); out: return err; } @@ -384,6 +387,13 @@ ssize_t sdcardfs_write_iter(struct kiocb *iocb, struct iov_iter *iter) err = lower_file->f_op->write_iter(iocb, iter); iocb->ki_filp = file; fput(lower_file); + /* update upper inode times/sizes as needed */ + if (err >= 0 || err == -EIOCBQUEUED) { + fsstack_copy_inode_size(file->f_path.dentry->d_inode, + file_inode(lower_file)); + fsstack_copy_attr_times(file->f_path.dentry->d_inode, + file_inode(lower_file)); + } out: return err; } diff --git a/fs/sdcardfs/lookup.c b/fs/sdcardfs/lookup.c index a0f221501b4c..509d5fbcb472 100644 --- a/fs/sdcardfs/lookup.c +++ b/fs/sdcardfs/lookup.c @@ -366,19 +366,22 @@ put_name: /* instatiate a new negative dentry */ dname.name = name->name; dname.len = name->len; - dname.hash = full_name_hash(dname.name, dname.len); - lower_dentry = d_lookup(lower_dir_dentry, &dname); - if (lower_dentry) - goto setup_lower; - lower_dentry = d_alloc(lower_dir_dentry, &dname); + /* See if the low-level filesystem might want + * to use its own hash + */ + lower_dentry = d_hash_and_lookup(lower_dir_dentry, &dname); + if (IS_ERR(lower_dentry)) + return lower_dentry; if (!lower_dentry) { - err = -ENOMEM; + /* We called vfs_path_lookup earlier, and did not get a negative + * dentry then. Don't confuse the lower filesystem by forcing + * one on it now... + */ + err = -ENOENT; goto out; } - d_add(lower_dentry, NULL); /* instantiate and hash */ -setup_lower: lower_path.dentry = lower_dentry; lower_path.mnt = mntget(lower_dir_mnt); sdcardfs_set_lower_path(dentry, &lower_path); diff --git a/fs/sdcardfs/multiuser.h b/fs/sdcardfs/multiuser.h index d0c925cda299..85341e753f8c 100644 --- a/fs/sdcardfs/multiuser.h +++ b/fs/sdcardfs/multiuser.h @@ -35,6 +35,13 @@ static inline uid_t multiuser_get_uid(userid_t user_id, appid_t app_id) return (user_id * AID_USER_OFFSET) + (app_id % AID_USER_OFFSET); } +static inline bool uid_is_app(uid_t uid) +{ + appid_t appid = uid % AID_USER_OFFSET; + + return appid >= AID_APP_START && appid <= AID_APP_END; +} + static inline gid_t multiuser_get_ext_cache_gid(uid_t uid) { return uid - AID_APP_START + AID_EXT_CACHE_GID_START; diff --git a/include/linux/mount.h b/include/linux/mount.h index 0e9b0977237a..b606d8f57adf 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -96,4 +96,6 @@ extern void mark_mounts_for_expiry(struct list_head *mounts); extern dev_t name_to_dev_t(const char *name); +extern unsigned int sysctl_mount_max; + #endif /* _LINUX_MOUNT_H */ diff --git a/kernel/cgroup.c b/kernel/cgroup.c index b52f88e44182..25cf44889559 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2693,7 +2693,7 @@ static int cgroup_procs_write_permission(struct task_struct *task, if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && !uid_eq(cred->euid, tcred->uid) && !uid_eq(cred->euid, tcred->suid) && - !ns_capable(tcred->user_ns, CAP_SYS_RESOURCE)) + !ns_capable(tcred->user_ns, CAP_SYS_NICE)) ret = -EACCES; if (!ret && cgroup_on_dfl(dst_cgrp)) { diff --git a/kernel/events/core.c b/kernel/events/core.c index 06db8b64129d..95c447e658f7 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8454,6 +8454,37 @@ static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id) return 0; } +/* + * Variation on perf_event_ctx_lock_nested(), except we take two context + * mutexes. + */ +static struct perf_event_context * +__perf_event_ctx_lock_double(struct perf_event *group_leader, + struct perf_event_context *ctx) +{ + struct perf_event_context *gctx; + +again: + rcu_read_lock(); + gctx = READ_ONCE(group_leader->ctx); + if (!atomic_inc_not_zero(&gctx->refcount)) { + rcu_read_unlock(); + goto again; + } + rcu_read_unlock(); + + mutex_lock_double(&gctx->mutex, &ctx->mutex); + + if (group_leader->ctx != gctx) { + mutex_unlock(&ctx->mutex); + mutex_unlock(&gctx->mutex); + put_ctx(gctx); + goto again; + } + + return gctx; +} + /** * sys_perf_event_open - open a performance event, associate it to a task/cpu * @@ -8707,8 +8738,26 @@ SYSCALL_DEFINE5(perf_event_open, } if (move_group) { - gctx = group_leader->ctx; - mutex_lock_double(&gctx->mutex, &ctx->mutex); + gctx = __perf_event_ctx_lock_double(group_leader, ctx); + + /* + * Check if we raced against another sys_perf_event_open() call + * moving the software group underneath us. + */ + if (!(group_leader->group_flags & PERF_GROUP_SOFTWARE)) { + /* + * If someone moved the group out from under us, check + * if this new event wound up on the same ctx, if so + * its the regular !move_group case, otherwise fail. + */ + if (gctx != ctx) { + err = -EINVAL; + goto err_locked; + } else { + perf_event_ctx_unlock(group_leader, gctx); + move_group = 0; + } + } } else { mutex_lock(&ctx->mutex); } @@ -8803,7 +8852,7 @@ SYSCALL_DEFINE5(perf_event_open, perf_unpin_context(ctx); if (move_group) - mutex_unlock(&gctx->mutex); + perf_event_ctx_unlock(group_leader, gctx); mutex_unlock(&ctx->mutex); if (group_leader) mutex_unlock(&group_leader->group_leader_mutex); @@ -8833,7 +8882,7 @@ SYSCALL_DEFINE5(perf_event_open, err_locked: if (move_group) - mutex_unlock(&gctx->mutex); + perf_event_ctx_unlock(group_leader, gctx); mutex_unlock(&ctx->mutex); /* err_file: */ fput(event_file); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 8cc5167e4b04..816999804a16 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -65,6 +65,7 @@ #include #include #include +#include #include #include @@ -2077,6 +2078,14 @@ static struct ctl_table fs_table[] = { .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, + { + .procname = "mount-max", + .data = &sysctl_mount_max, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + }, { } }; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 7d7f99b0db47..1275175b0946 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3440,11 +3440,23 @@ EXPORT_SYMBOL_GPL(ring_buffer_iter_reset); int ring_buffer_iter_empty(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer; + struct buffer_page *reader; + struct buffer_page *head_page; + struct buffer_page *commit_page; + unsigned commit; cpu_buffer = iter->cpu_buffer; - return iter->head_page == cpu_buffer->commit_page && - iter->head == rb_commit_index(cpu_buffer); + /* Remember, trace recording is off when iterator is in use */ + reader = cpu_buffer->reader_page; + head_page = cpu_buffer->head_page; + commit_page = cpu_buffer->commit_page; + commit = rb_page_commit(commit_page); + + return ((iter->head_page == commit_page && iter->head == commit) || + (iter->head_page == reader && commit_page == head_page && + head_page->read == commit && + iter->head == rb_page_commit(cpu_buffer->reader_page))); } EXPORT_SYMBOL_GPL(ring_buffer_iter_empty); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c0c10a335b3b..60d246c4eefa 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6170,11 +6170,13 @@ ftrace_trace_snapshot_callback(struct ftrace_hash *hash, return ret; out_reg: + ret = alloc_snapshot(&global_trace); + if (ret < 0) + goto out; + ret = register_ftrace_function_probe(glob, ops, count); - if (ret >= 0) - alloc_snapshot(&global_trace); - + out: return ret < 0 ? ret : 0; } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 3a2b21e22629..72e1e831589a 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -154,17 +154,18 @@ void ping_hash(struct sock *sk) void ping_unhash(struct sock *sk) { struct inet_sock *isk = inet_sk(sk); + pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num); + write_lock_bh(&ping_table.lock); if (sk_hashed(sk)) { - write_lock_bh(&ping_table.lock); hlist_nulls_del(&sk->sk_nulls_node); sk_nulls_node_init(&sk->sk_nulls_node); sock_put(sk); isk->inet_num = 0; isk->inet_sport = 0; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); - write_unlock_bh(&ping_table.lock); } + write_unlock_bh(&ping_table.lock); } EXPORT_SYMBOL_GPL(ping_unhash); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 4f4c45ba7b70..25b5bacaa434 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3397,6 +3397,27 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) !ether_addr_equal(bssid, hdr->addr1)) return false; } + + /* + * 802.11-2016 Table 9-26 says that for data frames, A1 must be + * the BSSID - we've checked that already but may have accepted + * the wildcard (ff:ff:ff:ff:ff:ff). + * + * It also says: + * The BSSID of the Data frame is determined as follows: + * a) If the STA is contained within an AP or is associated + * with an AP, the BSSID is the address currently in use + * by the STA contained in the AP. + * + * So we should not accept data frames with an address that's + * multicast. + * + * Accepting it also opens a security problem because stations + * could encrypt it with the GTK and inject traffic that way. + */ + if (ieee80211_is_data(hdr->frame_control) && multicast) + return false; + return true; case NL80211_IFTYPE_WDS: if (bssid || !ieee80211_is_data(hdr->frame_control)) diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 648f2a67f314..cb1381513c82 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -381,6 +381,10 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, dev = dev_get_by_name(net, driver_name); if (!dev) return -ENODEV; + if (tipc_mtu_bad(dev, 0)) { + dev_put(dev); + return -EINVAL; + } /* Associate TIPC bearer with L2 bearer */ rcu_assign_pointer(b->media_ptr, dev); @@ -570,14 +574,19 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, if (!b_ptr) return NOTIFY_DONE; - b_ptr->mtu = dev->mtu; - switch (evt) { case NETDEV_CHANGE: if (netif_carrier_ok(dev)) break; case NETDEV_GOING_DOWN: + tipc_reset_bearer(net, b_ptr); + break; case NETDEV_CHANGEMTU: + if (tipc_mtu_bad(dev, 0)) { + bearer_disable(net, b_ptr); + break; + } + b_ptr->mtu = dev->mtu; tipc_reset_bearer(net, b_ptr); break; case NETDEV_CHANGEADDR: diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 552185bc4773..5f11e18b1fa1 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -39,6 +39,7 @@ #include "netlink.h" #include "core.h" +#include "msg.h" #include #define MAX_MEDIA 3 @@ -61,6 +62,9 @@ #define TIPC_MEDIA_TYPE_IB 2 #define TIPC_MEDIA_TYPE_UDP 3 +/* minimum bearer MTU */ +#define TIPC_MIN_BEARER_MTU (MAX_H_SIZE + INT_H_SIZE) + /** * struct tipc_node_map - set of node identifiers * @count: # of nodes in set @@ -226,4 +230,13 @@ void tipc_bearer_xmit(struct net *net, u32 bearer_id, void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq); +/* check if device MTU is too low for tipc headers */ +static inline bool tipc_mtu_bad(struct net_device *dev, unsigned int reserve) +{ + if (dev->mtu >= TIPC_MIN_BEARER_MTU + reserve) + return false; + netdev_warn(dev, "MTU too low for tipc bearer\n"); + return true; +} + #endif /* _TIPC_BEARER_H */ diff --git a/net/tipc/core.c b/net/tipc/core.c index 03a842870c52..e2bdb07a49a2 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -69,6 +69,7 @@ static int __net_init tipc_init_net(struct net *net) if (err) goto out_nametbl; + INIT_LIST_HEAD(&tn->dist_queue); err = tipc_topsrv_start(net); if (err) goto out_subscr; diff --git a/net/tipc/core.h b/net/tipc/core.h index 18e95a8020cd..fe3b89e9cde4 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -103,6 +103,9 @@ struct tipc_net { spinlock_t nametbl_lock; struct name_table *nametbl; + /* Name dist queue */ + struct list_head dist_queue; + /* Topology subscription server */ struct tipc_server *topsrv; atomic_t subscription_count; diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index f51c8bdbea1c..c4c151bc000c 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -40,11 +40,6 @@ int sysctl_tipc_named_timeout __read_mostly = 2000; -/** - * struct tipc_dist_queue - queue holding deferred name table updates - */ -static struct list_head tipc_dist_queue = LIST_HEAD_INIT(tipc_dist_queue); - struct distr_queue_item { struct distr_item i; u32 dtype; @@ -67,6 +62,8 @@ static void publ_to_item(struct distr_item *i, struct publication *p) /** * named_prepare_buf - allocate & initialize a publication message + * + * The buffer returned is of size INT_H_SIZE + payload size */ static struct sk_buff *named_prepare_buf(struct net *net, u32 type, u32 size, u32 dest) @@ -171,9 +168,9 @@ static void named_distribute(struct net *net, struct sk_buff_head *list, struct publication *publ; struct sk_buff *skb = NULL; struct distr_item *item = NULL; - uint msg_dsz = (tipc_node_get_mtu(net, dnode, 0) / ITEM_SIZE) * - ITEM_SIZE; - uint msg_rem = msg_dsz; + u32 msg_dsz = ((tipc_node_get_mtu(net, dnode, 0) - INT_H_SIZE) / + ITEM_SIZE) * ITEM_SIZE; + u32 msg_rem = msg_dsz; list_for_each_entry(publ, pls, local_list) { /* Prepare next buffer: */ @@ -340,9 +337,11 @@ static bool tipc_update_nametbl(struct net *net, struct distr_item *i, * tipc_named_add_backlog - add a failed name table update to the backlog * */ -static void tipc_named_add_backlog(struct distr_item *i, u32 type, u32 node) +static void tipc_named_add_backlog(struct net *net, struct distr_item *i, + u32 type, u32 node) { struct distr_queue_item *e; + struct tipc_net *tn = net_generic(net, tipc_net_id); unsigned long now = get_jiffies_64(); e = kzalloc(sizeof(*e), GFP_ATOMIC); @@ -352,7 +351,7 @@ static void tipc_named_add_backlog(struct distr_item *i, u32 type, u32 node) e->node = node; e->expires = now + msecs_to_jiffies(sysctl_tipc_named_timeout); memcpy(e, i, sizeof(*i)); - list_add_tail(&e->next, &tipc_dist_queue); + list_add_tail(&e->next, &tn->dist_queue); } /** @@ -362,10 +361,11 @@ static void tipc_named_add_backlog(struct distr_item *i, u32 type, u32 node) void tipc_named_process_backlog(struct net *net) { struct distr_queue_item *e, *tmp; + struct tipc_net *tn = net_generic(net, tipc_net_id); char addr[16]; unsigned long now = get_jiffies_64(); - list_for_each_entry_safe(e, tmp, &tipc_dist_queue, next) { + list_for_each_entry_safe(e, tmp, &tn->dist_queue, next) { if (time_after(e->expires, now)) { if (!tipc_update_nametbl(net, &e->i, e->node, e->dtype)) continue; @@ -405,7 +405,7 @@ void tipc_named_rcv(struct net *net, struct sk_buff_head *inputq) node = msg_orignode(msg); while (count--) { if (!tipc_update_nametbl(net, item, node, mtype)) - tipc_named_add_backlog(item, mtype, node); + tipc_named_add_backlog(net, item, mtype, node); item++; } kfree_skb(skb); diff --git a/net/tipc/node.c b/net/tipc/node.c index 3926b561f873..2df0b98d4a32 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -102,9 +102,10 @@ static unsigned int tipc_hashfn(u32 addr) static void tipc_node_kref_release(struct kref *kref) { - struct tipc_node *node = container_of(kref, struct tipc_node, kref); + struct tipc_node *n = container_of(kref, struct tipc_node, kref); - tipc_node_delete(node); + kfree(n->bc_entry.link); + kfree_rcu(n, rcu); } void tipc_node_put(struct tipc_node *node) @@ -216,21 +217,20 @@ static void tipc_node_delete(struct tipc_node *node) { list_del_rcu(&node->list); hlist_del_rcu(&node->hash); - kfree(node->bc_entry.link); - kfree_rcu(node, rcu); + tipc_node_put(node); + + del_timer_sync(&node->timer); + tipc_node_put(node); } void tipc_node_stop(struct net *net) { - struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_net *tn = tipc_net(net); struct tipc_node *node, *t_node; spin_lock_bh(&tn->node_list_lock); - list_for_each_entry_safe(node, t_node, &tn->node_list, list) { - if (del_timer(&node->timer)) - tipc_node_put(node); - tipc_node_put(node); - } + list_for_each_entry_safe(node, t_node, &tn->node_list, list) + tipc_node_delete(node); spin_unlock_bh(&tn->node_list_lock); } @@ -313,9 +313,7 @@ static void tipc_node_timeout(unsigned long data) if (rc & TIPC_LINK_DOWN_EVT) tipc_node_link_down(n, bearer_id, false); } - if (!mod_timer(&n->timer, jiffies + n->keepalive_intv)) - tipc_node_get(n); - tipc_node_put(n); + mod_timer(&n->timer, jiffies + n->keepalive_intv); } /** @@ -730,7 +728,7 @@ static void tipc_node_fsm_evt(struct tipc_node *n, int evt) state = SELF_UP_PEER_UP; break; case SELF_LOST_CONTACT_EVT: - state = SELF_DOWN_PEER_LEAVING; + state = SELF_DOWN_PEER_DOWN; break; case SELF_ESTABL_CONTACT_EVT: case PEER_LOST_CONTACT_EVT: @@ -749,7 +747,7 @@ static void tipc_node_fsm_evt(struct tipc_node *n, int evt) state = SELF_UP_PEER_UP; break; case PEER_LOST_CONTACT_EVT: - state = SELF_LEAVING_PEER_DOWN; + state = SELF_DOWN_PEER_DOWN; break; case SELF_LOST_CONTACT_EVT: case PEER_ESTABL_CONTACT_EVT: diff --git a/net/tipc/socket.c b/net/tipc/socket.c index b26b7a127773..65171f8e8c45 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -777,9 +777,11 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, * @tsk: receiving socket * @skb: pointer to message buffer. */ -static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb) +static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb, + struct sk_buff_head *xmitq) { struct sock *sk = &tsk->sk; + u32 onode = tsk_own_node(tsk); struct tipc_msg *hdr = buf_msg(skb); int mtyp = msg_type(hdr); int conn_cong; @@ -792,7 +794,8 @@ static void tipc_sk_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb) if (mtyp == CONN_PROBE) { msg_set_type(hdr, CONN_PROBE_REPLY); - tipc_sk_respond(sk, skb, TIPC_OK); + if (tipc_msg_reverse(onode, &skb, TIPC_OK)) + __skb_queue_tail(xmitq, skb); return; } else if (mtyp == CONN_ACK) { conn_cong = tsk_conn_cong(tsk); @@ -1647,7 +1650,8 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf) * * Returns true if message was added to socket receive queue, otherwise false */ -static bool filter_rcv(struct sock *sk, struct sk_buff *skb) +static bool filter_rcv(struct sock *sk, struct sk_buff *skb, + struct sk_buff_head *xmitq) { struct socket *sock = sk->sk_socket; struct tipc_sock *tsk = tipc_sk(sk); @@ -1657,7 +1661,7 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb) int usr = msg_user(hdr); if (unlikely(msg_user(hdr) == CONN_MANAGER)) { - tipc_sk_proto_rcv(tsk, skb); + tipc_sk_proto_rcv(tsk, skb, xmitq); return false; } @@ -1700,7 +1704,8 @@ static bool filter_rcv(struct sock *sk, struct sk_buff *skb) return true; reject: - tipc_sk_respond(sk, skb, err); + if (tipc_msg_reverse(tsk_own_node(tsk), &skb, err)) + __skb_queue_tail(xmitq, skb); return false; } @@ -1716,9 +1721,24 @@ reject: static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb) { unsigned int truesize = skb->truesize; + struct sk_buff_head xmitq; + u32 dnode, selector; - if (likely(filter_rcv(sk, skb))) + __skb_queue_head_init(&xmitq); + + if (likely(filter_rcv(sk, skb, &xmitq))) { atomic_add(truesize, &tipc_sk(sk)->dupl_rcvcnt); + return 0; + } + + if (skb_queue_empty(&xmitq)) + return 0; + + /* Send response/rejected message */ + skb = __skb_dequeue(&xmitq); + dnode = msg_destnode(buf_msg(skb)); + selector = msg_origport(buf_msg(skb)); + tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector); return 0; } @@ -1732,12 +1752,13 @@ static int tipc_backlog_rcv(struct sock *sk, struct sk_buff *skb) * Caller must hold socket lock */ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, - u32 dport) + u32 dport, struct sk_buff_head *xmitq) { + unsigned long time_limit = jiffies + 2; + struct sk_buff *skb; unsigned int lim; atomic_t *dcnt; - struct sk_buff *skb; - unsigned long time_limit = jiffies + 2; + u32 onode; while (skb_queue_len(inputq)) { if (unlikely(time_after_eq(jiffies, time_limit))) @@ -1749,20 +1770,22 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, /* Add message directly to receive queue if possible */ if (!sock_owned_by_user(sk)) { - filter_rcv(sk, skb); + filter_rcv(sk, skb, xmitq); continue; } /* Try backlog, compensating for double-counted bytes */ dcnt = &tipc_sk(sk)->dupl_rcvcnt; - if (sk->sk_backlog.len) + if (!sk->sk_backlog.len) atomic_set(dcnt, 0); lim = rcvbuf_limit(sk, skb) + atomic_read(dcnt); if (likely(!sk_add_backlog(sk, skb, lim))) continue; /* Overload => reject message back to sender */ - tipc_sk_respond(sk, skb, TIPC_ERR_OVERLOAD); + onode = tipc_own_addr(sock_net(sk)); + if (tipc_msg_reverse(onode, &skb, TIPC_ERR_OVERLOAD)) + __skb_queue_tail(xmitq, skb); break; } } @@ -1775,12 +1798,14 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, */ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) { + struct sk_buff_head xmitq; u32 dnode, dport = 0; int err; struct tipc_sock *tsk; struct sock *sk; struct sk_buff *skb; + __skb_queue_head_init(&xmitq); while (skb_queue_len(inputq)) { dport = tipc_skb_peek_port(inputq, dport); tsk = tipc_sk_lookup(net, dport); @@ -1788,9 +1813,14 @@ void tipc_sk_rcv(struct net *net, struct sk_buff_head *inputq) if (likely(tsk)) { sk = &tsk->sk; if (likely(spin_trylock_bh(&sk->sk_lock.slock))) { - tipc_sk_enqueue(inputq, sk, dport); + tipc_sk_enqueue(inputq, sk, dport, &xmitq); spin_unlock_bh(&sk->sk_lock.slock); } + /* Send pending response/rejected messages, if any */ + while ((skb = __skb_dequeue(&xmitq))) { + dnode = msg_destnode(buf_msg(skb)); + tipc_node_xmit_skb(net, skb, dnode, dport); + } sock_put(sk); continue; } diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 6af78c6276b4..78d6b78de29d 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -52,7 +52,7 @@ /* IANA assigned UDP port */ #define UDP_PORT_DEFAULT 6118 -#define UDP_MIN_HEADROOM 28 +#define UDP_MIN_HEADROOM 48 static const struct nla_policy tipc_nl_udp_policy[TIPC_NLA_UDP_MAX + 1] = { [TIPC_NLA_UDP_UNSPEC] = {.type = NLA_UNSPEC}, @@ -376,6 +376,11 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, udp_conf.local_ip.s_addr = htonl(INADDR_ANY); udp_conf.use_udp_checksums = false; ub->ifindex = dev->ifindex; + if (tipc_mtu_bad(dev, sizeof(struct iphdr) + + sizeof(struct udphdr))) { + err = -EINVAL; + goto err; + } b->mtu = dev->mtu - sizeof(struct iphdr) - sizeof(struct udphdr); #if IS_ENABLED(CONFIG_IPV6) diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 0a369bb440e7..662bdd20a748 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -842,7 +842,7 @@ static void vmci_transport_peer_detach_cb(u32 sub_id, * qp_handle. */ if (vmci_handle_is_invalid(e_payload->handle) || - vmci_handle_is_equal(trans->qp_handle, e_payload->handle)) + !vmci_handle_is_equal(trans->qp_handle, e_payload->handle)) return; /* We don't ask for delayed CBs when we subscribe to this event (we @@ -2154,7 +2154,7 @@ module_exit(vmci_transport_exit); MODULE_AUTHOR("VMware, Inc."); MODULE_DESCRIPTION("VMCI transport for Virtual Sockets"); -MODULE_VERSION("1.0.2.0-k"); +MODULE_VERSION("1.0.3.0-k"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("vmware_vsock"); MODULE_ALIAS_NETPROTO(PF_VSOCK); diff --git a/security/keys/gc.c b/security/keys/gc.c index addf060399e0..9cb4fe4478a1 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -46,7 +46,7 @@ static unsigned long key_gc_flags; * immediately unlinked. */ struct key_type key_type_dead = { - .name = "dead", + .name = ".dead", }; /* diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index 1c3872aeed14..442e350c209d 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -271,7 +271,8 @@ error: * Create and join an anonymous session keyring or join a named session * keyring, creating it if necessary. A named session keyring must have Search * permission for it to be joined. Session keyrings without this permit will - * be skipped over. + * be skipped over. It is not permitted for userspace to create or join + * keyrings whose name begin with a dot. * * If successful, the ID of the joined session keyring will be returned. */ @@ -288,12 +289,16 @@ long keyctl_join_session_keyring(const char __user *_name) ret = PTR_ERR(name); goto error; } + + ret = -EPERM; + if (name[0] == '.') + goto error_name; } /* join the session */ ret = join_session_keyring(name); +error_name: kfree(name); - error: return ret; } @@ -1223,8 +1228,8 @@ error: * Read or set the default keyring in which request_key() will cache keys and * return the old setting. * - * If a process keyring is specified then this will be created if it doesn't - * yet exist. The old setting will be returned if successful. + * If a thread or process keyring is specified then it will be created if it + * doesn't yet exist. The old setting will be returned if successful. */ long keyctl_set_reqkey_keyring(int reqkey_defl) { @@ -1249,11 +1254,8 @@ long keyctl_set_reqkey_keyring(int reqkey_defl) case KEY_REQKEY_DEFL_PROCESS_KEYRING: ret = install_process_keyring_to_cred(new); - if (ret < 0) { - if (ret != -EEXIST) - goto error; - ret = 0; - } + if (ret < 0) + goto error; goto set; case KEY_REQKEY_DEFL_DEFAULT: diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index e6d50172872f..4ed909142956 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -125,13 +125,18 @@ error: } /* - * Install a fresh thread keyring directly to new credentials. This keyring is - * allowed to overrun the quota. + * Install a thread keyring to the given credentials struct if it didn't have + * one already. This is allowed to overrun the quota. + * + * Return: 0 if a thread keyring is now present; -errno on failure. */ int install_thread_keyring_to_cred(struct cred *new) { struct key *keyring; + if (new->thread_keyring) + return 0; + keyring = keyring_alloc("_tid", new->uid, new->gid, new, KEY_POS_ALL | KEY_USR_VIEW, KEY_ALLOC_QUOTA_OVERRUN, NULL); @@ -143,7 +148,9 @@ int install_thread_keyring_to_cred(struct cred *new) } /* - * Install a fresh thread keyring, discarding the old one. + * Install a thread keyring to the current task if it didn't have one already. + * + * Return: 0 if a thread keyring is now present; -errno on failure. */ static int install_thread_keyring(void) { @@ -154,8 +161,6 @@ static int install_thread_keyring(void) if (!new) return -ENOMEM; - BUG_ON(new->thread_keyring); - ret = install_thread_keyring_to_cred(new); if (ret < 0) { abort_creds(new); @@ -166,17 +171,17 @@ static int install_thread_keyring(void) } /* - * Install a process keyring directly to a credentials struct. + * Install a process keyring to the given credentials struct if it didn't have + * one already. This is allowed to overrun the quota. * - * Returns -EEXIST if there was already a process keyring, 0 if one installed, - * and other value on any other error + * Return: 0 if a process keyring is now present; -errno on failure. */ int install_process_keyring_to_cred(struct cred *new) { struct key *keyring; if (new->process_keyring) - return -EEXIST; + return 0; keyring = keyring_alloc("_pid", new->uid, new->gid, new, KEY_POS_ALL | KEY_USR_VIEW, @@ -189,11 +194,9 @@ int install_process_keyring_to_cred(struct cred *new) } /* - * Make sure a process keyring is installed for the current process. The - * existing process keyring is not replaced. + * Install a process keyring to the current task if it didn't have one already. * - * Returns 0 if there is a process keyring by the end of this function, some - * error otherwise. + * Return: 0 if a process keyring is now present; -errno on failure. */ static int install_process_keyring(void) { @@ -207,14 +210,18 @@ static int install_process_keyring(void) ret = install_process_keyring_to_cred(new); if (ret < 0) { abort_creds(new); - return ret != -EEXIST ? ret : 0; + return ret; } return commit_creds(new); } /* - * Install a session keyring directly to a credentials struct. + * Install the given keyring as the session keyring of the given credentials + * struct, replacing the existing one if any. If the given keyring is NULL, + * then install a new anonymous session keyring. + * + * Return: 0 on success; -errno on failure. */ int install_session_keyring_to_cred(struct cred *cred, struct key *keyring) { @@ -249,8 +256,11 @@ int install_session_keyring_to_cred(struct cred *cred, struct key *keyring) } /* - * Install a session keyring, discarding the old one. If a keyring is not - * supplied, an empty one is invented. + * Install the given keyring as the session keyring of the current task, + * replacing the existing one if any. If the given keyring is NULL, then + * install a new anonymous session keyring. + * + * Return: 0 on success; -errno on failure. */ static int install_session_keyring(struct key *keyring) { diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index 0d9f48ec42bb..bc7adb84e679 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -1433,7 +1433,7 @@ int main(int argc, char *argv[]) openlog("KVP", 0, LOG_USER); syslog(LOG_INFO, "KVP starting; pid is:%d", getpid()); - kvp_fd = open("/dev/vmbus/hv_kvp", O_RDWR); + kvp_fd = open("/dev/vmbus/hv_kvp", O_RDWR | O_CLOEXEC); if (kvp_fd < 0) { syslog(LOG_ERR, "open /dev/vmbus/hv_kvp failed; error: %d %s",