diff options
| author | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2026-07-04 13:45:09 +0200 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2026-07-04 13:45:09 +0200 |
| commit | 8ca1f4c6fb1462ee120730ea75c19da10d2f2d6f (patch) | |
| tree | fa6bebc72c42a94b66d4b3676371753d31e66702 | |
| parent | 9372da540bfdcfa345309043e57b335c900a8ad9 (diff) | |
| parent | 199c9959d3a9b53f346c221757fc7ac507fbac50 (diff) | |
| download | linux-stable-linux-rolling-stable.tar.gz linux-stable-linux-rolling-stable.zip | |
Merge v7.1.3linux-rolling-stable
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
134 files changed, 1323 insertions, 448 deletions
@@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 7 PATCHLEVEL = 1 -SUBLEVEL = 2 +SUBLEVEL = 3 EXTRAVERSION = NAME = Baby Opossum Posse @@ -827,12 +827,6 @@ endif # KBUILD_EXTMOD # Defaults to vmlinux, but the arch makefile usually adds further targets all: vmlinux -CFLAGS_GCOV := -fprofile-arcs -ftest-coverage -ifdef CONFIG_CC_IS_GCC -CFLAGS_GCOV += -fno-tree-loop-im -endif -export CFLAGS_GCOV - # The arch Makefiles can override CC_FLAGS_FTRACE. We may also append it later. ifdef CONFIG_FUNCTION_TRACER CC_FLAGS_FTRACE := -pg @@ -1150,6 +1144,27 @@ endif # Ensure compilers do not transform certain loops into calls to wcslen() KBUILD_CFLAGS += -fno-builtin-wcslen +CFLAGS_GCOV := -fprofile-arcs -ftest-coverage +ifdef CONFIG_CC_IS_GCC +CFLAGS_GCOV += -fno-tree-loop-im +# Use atomic counter updates to avoid concurrent-access crashes in GCOV. +# Only enable if -fprofile-update=prefer-atomic does not introduce new +# undefined symbols (e.g. libatomic calls that the kernel cannot link). +CFLAGS_GCOV += $(call try-run,\ + echo 'long long x; void f(void){x++;}' | \ + $(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) -w -fprofile-arcs \ + -ftest-coverage -x c - -c -o "$$TMP.base" && \ + echo 'long long x; void f(void){x++;}' | \ + $(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) -w -fprofile-arcs \ + -ftest-coverage -fprofile-update=prefer-atomic \ + -x c - -c -o "$$TMP" && \ + $(NM) "$$TMP.base" | grep ' U ' > "$$TMP.ubase" || true ; \ + $(NM) "$$TMP" | grep ' U ' > "$$TMP.utest" || true ; \ + cmp -s "$$TMP.ubase" "$$TMP.utest",\ + -fprofile-update=prefer-atomic) +endif +export CFLAGS_GCOV + # change __FILE__ to the relative path to the source directory ifdef building_out_of_srctree KBUILD_CPPFLAGS += -fmacro-prefix-map=$(srcroot)/= diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 4da9281312eb..6e95514d5a76 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1479,6 +1479,11 @@ static void sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn, if (!kvm_has_mte(kvm)) return; + if (is_zero_pfn(pfn)) { + WARN_ON_ONCE(nr_pages != 1); + return; + } + if (folio_test_hugetlb(folio)) { /* Hugetlb has MTE flags set on head page only */ if (folio_try_hugetlb_mte_tagging(folio)) { diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 64a048f1b880..b077b2aa1ab3 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -705,6 +705,7 @@ static void stop_this_cpu(void *dummy) set_cpu_online(smp_processor_id(), false); calculate_cpu_foreign_map(); local_irq_disable(); + rcutree_report_cpu_dead(); while (true); } diff --git a/arch/mips/dec/prom/console.c b/arch/mips/dec/prom/console.c index 31a8441d8431..b4f0dba3fa20 100644 --- a/arch/mips/dec/prom/console.c +++ b/arch/mips/dec/prom/console.c @@ -2,8 +2,9 @@ /* * DECstation PROM-based early console support. * - * Copyright (C) 2004, 2007 Maciej W. Rozycki + * Copyright (C) 2004, 2007, 2026 Maciej W. Rozycki */ +#include <linux/bug.h> #include <linux/console.h> #include <linux/init.h> #include <linux/kernel.h> @@ -14,9 +15,11 @@ static void __init prom_console_write(struct console *con, const char *s, unsigned int c) { - char buf[81]; + static char buf[81] __initdata = { 0 }; unsigned int chunk = sizeof(buf) - 1; + BUG_ON((long)buf != (int)(long)buf); + while (c > 0) { if (chunk > c) chunk = c; diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 4868e79f3b30..0f28b4a62e72 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -20,6 +20,7 @@ #include <linux/sched/mm.h> #include <linux/cpumask.h> #include <linux/cpu.h> +#include <linux/rcupdate.h> #include <linux/err.h> #include <linux/ftrace.h> #include <linux/irqdomain.h> @@ -422,6 +423,7 @@ static void stop_this_cpu(void *dummy) set_cpu_online(smp_processor_id(), false); calculate_cpu_foreign_map(); local_irq_disable(); + rcutree_report_cpu_dead(); while (1); } diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h index 0092513c3376..b1a2ac665792 100644 --- a/arch/riscv/include/asm/cacheflush.h +++ b/arch/riscv/include/asm/cacheflush.h @@ -43,20 +43,23 @@ do { \ #ifdef CONFIG_64BIT extern u64 new_vmalloc[NR_CPUS / sizeof(u64) + 1]; extern char _end[]; +static inline void mark_new_valid_map(void) +{ + int i; + + /* + * We don't care if concurrently a cpu resets this value since + * the only place this can happen is in handle_exception() where + * an sfence.vma is emitted. + */ + for (i = 0; i < ARRAY_SIZE(new_vmalloc); ++i) + new_vmalloc[i] = -1ULL; +} #define flush_cache_vmap flush_cache_vmap static inline void flush_cache_vmap(unsigned long start, unsigned long end) { - if (is_vmalloc_or_module_addr((void *)start)) { - int i; - - /* - * We don't care if concurrently a cpu resets this value since - * the only place this can happen is in handle_exception() where - * an sfence.vma is emitted. - */ - for (i = 0; i < ARRAY_SIZE(new_vmalloc); ++i) - new_vmalloc[i] = -1ULL; - } + if (is_vmalloc_or_module_addr((void *)start)) + mark_new_valid_map(); } #define flush_cache_vmap_early(start, end) local_flush_tlb_kernel_range(start, end) #endif diff --git a/arch/riscv/include/asm/kfence.h b/arch/riscv/include/asm/kfence.h index d08bf7fb3aee..29cb3a6ee113 100644 --- a/arch/riscv/include/asm/kfence.h +++ b/arch/riscv/include/asm/kfence.h @@ -6,6 +6,7 @@ #include <linux/kfence.h> #include <linux/pfn.h> #include <asm-generic/pgalloc.h> +#include <asm/cacheflush.h> #include <asm/pgtable.h> static inline bool arch_kfence_init_pool(void) @@ -17,10 +18,12 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) { pte_t *pte = virt_to_kpte(addr); - if (protect) + if (protect) { set_pte(pte, __pte(pte_val(ptep_get(pte)) & ~_PAGE_PRESENT)); - else + } else { set_pte(pte, __pte(pte_val(ptep_get(pte)) | _PAGE_PRESENT)); + mark_new_valid_map(); + } preempt_disable(); local_flush_tlb_kernel_range(addr, addr + PAGE_SIZE); diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index d011fb51c59a..6c14ed7a5613 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -136,8 +136,10 @@ SYM_CODE_START(handle_exception) #ifdef CONFIG_64BIT /* - * The RISC-V kernel does not eagerly emit a sfence.vma after each - * new vmalloc mapping, which may result in exceptions: + * The RISC-V kernel does not flush TLBs on all CPUS after each new + * vmalloc mapping or kfence_unprotect(), which may result in + * exceptions: + * * - if the uarch caches invalid entries, the new mapping would not be * observed by the page table walker and an invalidation is needed. * - if the uarch does not cache invalid entries, a reordered access diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 4438ecac9a89..ad59c22979bd 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1839,6 +1839,11 @@ static bool hv_is_vp_in_sparse_set(u32 vp_id, u64 valid_bank_mask, u64 sparse_ba int valid_bit_nr = vp_id / HV_VCPUS_PER_SPARSE_BANK; unsigned long sbank; + BUILD_BUG_ON(BITS_PER_TYPE(valid_bank_mask) != HV_MAX_SPARSE_VCPU_BANKS); + + if (valid_bit_nr >= HV_MAX_SPARSE_VCPU_BANKS) + return false; + if (!test_bit(valid_bit_nr, (unsigned long *)&valid_bank_mask)) return false; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index f0144ae8d891..0c2e35e3ffbd 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2453,13 +2453,15 @@ static struct kvm_mmu_page *kvm_mmu_get_child_sp(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, bool direct, unsigned int access) { - union kvm_mmu_page_role role; + union kvm_mmu_page_role role = kvm_mmu_child_role(sptep, direct, access); - if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep) && - spte_to_child_sp(*sptep) && spte_to_child_sp(*sptep)->gfn == gfn) + if (is_shadow_present_pte(*sptep) && + !is_large_pte(*sptep) && + spte_to_child_sp(*sptep) && + spte_to_child_sp(*sptep)->gfn == gfn && + spte_to_child_sp(*sptep)->role.word == role.word) return ERR_PTR(-EEXIST); - role = kvm_mmu_child_role(sptep, direct, access); return kvm_mmu_get_shadow_page(vcpu, gfn, role); } @@ -7286,13 +7288,19 @@ restart: sp = sptep_to_sp(sptep); /* - * We cannot do huge page mapping for indirect shadow pages, - * which are found on the last rmap (level = 1) when not using - * tdp; such shadow pages are synced with the page table in - * the guest, and the guest page table is using 4K page size - * mapping if the indirect sp has level = 1. + * Direct shadow page can be replaced by a hugepage if the host + * mapping level allows it and the memslot maps all of the host + * hugepage. Note! If the memslot maps only part of the + * hugepage, sp->gfn may be below slot->base_gfn, and querying + * the max mapping level would cause an out-of-bounds lpage_info + * access. So the gfn bounds check *must* be done first. + * + * Indirect shadow pages are created when the guest page tables + * are using 4K pages. Since the host mapping is always + * constrained by the page size in the guest, indirect shadow + * pages are never collapsible. */ - if (sp->role.direct && + if (sp->role.direct && is_gfn_in_memslot(slot, sp->gfn) && sp->role.level < kvm_mmu_max_mapping_level(kvm, NULL, slot, sp->gfn)) { kvm_zap_one_rmap_spte(kvm, rmap_head, sptep); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 6c6a6d663e29..29c3d557b78b 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1396,6 +1396,7 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) s_off = vaddr & ~PAGE_MASK; d_off = dst_vaddr & ~PAGE_MASK; len = min_t(size_t, (PAGE_SIZE - s_off), size); + len = min_t(size_t, len, PAGE_SIZE - d_off); if (dec) ret = __sev_dbg_decrypt_user(kvm, diff --git a/block/bdev.c b/block/bdev.c index bb0ffa3bb4df..107ac9eaac7f 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -446,15 +446,10 @@ EXPORT_SYMBOL_GPL(blockdev_superblock); void __init bdev_cache_init(void) { - int err; - bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode), 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| SLAB_ACCOUNT|SLAB_PANIC), init_once); - err = register_filesystem(&bd_type); - if (err) - panic("Cannot register bdev pseudo-fs"); blockdev_mnt = kern_mount(&bd_type); if (IS_ERR(blockdev_mnt)) panic("Cannot create bdev pseudo-fs"); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index bc63bd220865..51a9c3531325 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -164,20 +164,10 @@ static void blkg_free(struct blkcg_gq *blkg) static void __blkg_release(struct rcu_head *rcu) { struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head); - struct blkcg *blkcg = blkg->blkcg; - int cpu; #ifdef CONFIG_BLK_CGROUP_PUNT_BIO WARN_ON(!bio_list_empty(&blkg->async_bios)); #endif - /* - * Flush all the non-empty percpu lockless lists before releasing - * us, given these stat belongs to us. - * - * blkg_stat_lock is for serializing blkg stat update - */ - for_each_possible_cpu(cpu) - __blkcg_rstat_flush(blkcg, cpu); /* release the blkcg and parent blkg refs this blkg has been holding */ css_put(&blkg->blkcg->css); @@ -195,6 +185,17 @@ static void __blkg_release(struct rcu_head *rcu) static void blkg_release(struct percpu_ref *ref) { struct blkcg_gq *blkg = container_of(ref, struct blkcg_gq, refcnt); + struct blkcg *blkcg = blkg->blkcg; + int cpu; + + /* + * Flush all the non-empty percpu lockless lists before releasing + * us, given these stat belongs to us. + * + * blkg_stat_lock is for serializing blkg stat update + */ + for_each_possible_cpu(cpu) + __blkcg_rstat_flush(blkcg, cpu); call_rcu(&blkg->rcu_head, __blkg_release); } diff --git a/drivers/crypto/intel/qat/qat_common/adf_accel_devices.h b/drivers/crypto/intel/qat/qat_common/adf_accel_devices.h index 03a4e9690208..cbd1d1eda5a3 100644 --- a/drivers/crypto/intel/qat/qat_common/adf_accel_devices.h +++ b/drivers/crypto/intel/qat/qat_common/adf_accel_devices.h @@ -28,15 +28,10 @@ #define ADF_4XXX_DEVICE_NAME "4xxx" #define ADF_420XX_DEVICE_NAME "420xx" #define ADF_6XXX_DEVICE_NAME "6xxx" -#define PCI_DEVICE_ID_INTEL_QAT_4XXX 0x4940 #define PCI_DEVICE_ID_INTEL_QAT_4XXXIOV 0x4941 -#define PCI_DEVICE_ID_INTEL_QAT_401XX 0x4942 #define PCI_DEVICE_ID_INTEL_QAT_401XXIOV 0x4943 -#define PCI_DEVICE_ID_INTEL_QAT_402XX 0x4944 #define PCI_DEVICE_ID_INTEL_QAT_402XXIOV 0x4945 -#define PCI_DEVICE_ID_INTEL_QAT_420XX 0x4946 #define PCI_DEVICE_ID_INTEL_QAT_420XXIOV 0x4947 -#define PCI_DEVICE_ID_INTEL_QAT_6XXX 0x4948 #define PCI_DEVICE_ID_INTEL_QAT_6XXX_IOV 0x4949 #define ADF_DEVICE_FUSECTL_OFFSET 0x40 diff --git a/drivers/crypto/nx/nx.c b/drivers/crypto/nx/nx.c index 78135fb13f5c..1b7509e2ce44 100644 --- a/drivers/crypto/nx/nx.c +++ b/drivers/crypto/nx/nx.c @@ -714,15 +714,13 @@ int nx_crypto_ctx_aes_xcbc_init(struct crypto_shash *tfm) /** * nx_crypto_ctx_exit - destroy a crypto api context * - * @tfm: the crypto transform pointer for the context + * @nx_ctx: the crypto api context * * As crypto API contexts are destroyed, this exit hook is called to free the * memory associated with it. */ -void nx_crypto_ctx_exit(struct crypto_tfm *tfm) +void nx_crypto_ctx_exit(struct nx_crypto_ctx *nx_ctx) { - struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(tfm); - kfree_sensitive(nx_ctx->kmem); nx_ctx->csbcpb = NULL; nx_ctx->csbcpb_aead = NULL; diff --git a/drivers/crypto/nx/nx.h b/drivers/crypto/nx/nx.h index 36974f08490a..6dfabfbf8192 100644 --- a/drivers/crypto/nx/nx.h +++ b/drivers/crypto/nx/nx.h @@ -153,7 +153,7 @@ int nx_crypto_ctx_aes_ctr_init(struct crypto_skcipher *tfm); int nx_crypto_ctx_aes_cbc_init(struct crypto_skcipher *tfm); int nx_crypto_ctx_aes_ecb_init(struct crypto_skcipher *tfm); int nx_crypto_ctx_sha_init(struct crypto_shash *tfm); -void nx_crypto_ctx_exit(struct crypto_tfm *tfm); +void nx_crypto_ctx_exit(struct nx_crypto_ctx *nx_ctx); void nx_crypto_ctx_skcipher_exit(struct crypto_skcipher *tfm); void nx_crypto_ctx_aead_exit(struct crypto_aead *tfm); void nx_crypto_ctx_shash_exit(struct crypto_shash *tfm); diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index f95411363ea9..1dce26d4da83 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -10,9 +10,6 @@ #endif /* PCI Config */ -#define PCI_DEVICE_ID_INTEL_DSA_GNRD 0x11fb -#define PCI_DEVICE_ID_INTEL_DSA_DMR 0x1212 -#define PCI_DEVICE_ID_INTEL_IAA_DMR 0x1216 #define PCI_DEVICE_ID_INTEL_IAA_PTL 0xb02d #define PCI_DEVICE_ID_INTEL_IAA_WCL 0xfd2d diff --git a/drivers/fpga/of-fpga-region.c b/drivers/fpga/of-fpga-region.c index caa091224dc5..9107a5b461d3 100644 --- a/drivers/fpga/of-fpga-region.c +++ b/drivers/fpga/of-fpga-region.c @@ -168,11 +168,10 @@ static int child_regions_with_firmware(struct device_node *overlay) fpga_region_of_match); } - of_node_put(child_region); - if (ret) pr_err("firmware-name not allowed in child FPGA region: %pOF", child_region); + of_node_put(child_region); return ret; } diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index a2132d70fb36..4039d1175c4c 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -1569,6 +1569,10 @@ static int i2c_register_adapter(struct i2c_adapter *adap) pm_suspend_ignore_children(&adap->dev, true); pm_runtime_enable(&adap->dev); + mutex_lock(&core_lock); + idr_replace(&i2c_adapter_idr, adap, adap->nr); + mutex_unlock(&core_lock); + res = device_add(&adap->dev); if (res) { pr_err("adapter '%s': can't register device (%d)\n", adap->name, res); @@ -1627,7 +1631,7 @@ static int __i2c_add_numbered_adapter(struct i2c_adapter *adap) int id; mutex_lock(&core_lock); - id = idr_alloc(&i2c_adapter_idr, adap, adap->nr, adap->nr + 1, GFP_KERNEL); + id = idr_alloc(&i2c_adapter_idr, NULL, adap->nr, adap->nr + 1, GFP_KERNEL); mutex_unlock(&core_lock); if (WARN(id < 0, "couldn't get idr")) return id == -ENOSPC ? -EBUSY : id; @@ -1661,7 +1665,7 @@ int i2c_add_adapter(struct i2c_adapter *adapter) } mutex_lock(&core_lock); - id = idr_alloc(&i2c_adapter_idr, adapter, + id = idr_alloc(&i2c_adapter_idr, NULL, __i2c_first_dynamic_bus_num, 0, GFP_KERNEL); mutex_unlock(&core_lock); if (WARN(id < 0, "couldn't get idr")) diff --git a/drivers/irqchip/irq-imgpdc.c b/drivers/irqchip/irq-imgpdc.c index e9ef2f5a7207..4feef4ab5fec 100644 --- a/drivers/irqchip/irq-imgpdc.c +++ b/drivers/irqchip/irq-imgpdc.c @@ -378,6 +378,7 @@ static int pdc_intc_probe(struct platform_device *pdev) dev_err(&pdev->dev, "cannot add IRQ domain\n"); return -ENOMEM; } + priv->domain->flags |= IRQ_DOMAIN_FLAG_DESTROY_GC; /* * Set up 2 generic irq chips with 2 chip types. @@ -465,6 +466,11 @@ static void pdc_intc_remove(struct platform_device *pdev) { struct pdc_intc_priv *priv = platform_get_drvdata(pdev); + for (unsigned int i = 0; i < priv->nr_perips; ++i) + irq_set_chained_handler_and_data(priv->perip_irqs[i], NULL, NULL); + + irq_set_chained_handler_and_data(priv->syswake_irq, NULL, NULL); + irq_domain_remove(priv->domain); } diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c index 159295c4bd6d..302ed27944e7 100644 --- a/drivers/net/wan/hdlc_ppp.c +++ b/drivers/net/wan/hdlc_ppp.c @@ -619,7 +619,6 @@ static void ppp_start(struct net_device *dev) struct proto *proto = &ppp->protos[i]; proto->dev = dev; - timer_setup(&proto->timer, ppp_timer, 0); proto->state = CLOSED; } ppp->protos[IDX_LCP].pid = PID_LCP; @@ -639,6 +638,15 @@ static void ppp_close(struct net_device *dev) ppp_tx_flush(); } +static void ppp_timer_release(struct net_device *dev) +{ + struct ppp *ppp = get_ppp(dev); + int i; + + for (i = 0; i < IDX_COUNT; i++) + timer_shutdown_sync(&ppp->protos[i].timer); +} + static struct hdlc_proto proto = { .start = ppp_start, .stop = ppp_stop, @@ -647,6 +655,7 @@ static struct hdlc_proto proto = { .ioctl = ppp_ioctl, .netif_rx = ppp_rx, .module = THIS_MODULE, + .detach = ppp_timer_release, }; static const struct header_ops ppp_header_ops = { @@ -657,7 +666,7 @@ static int ppp_ioctl(struct net_device *dev, struct if_settings *ifs) { hdlc_device *hdlc = dev_to_hdlc(dev); struct ppp *ppp; - int result; + int i, result; switch (ifs->type) { case IF_GET_PROTO: @@ -685,6 +694,8 @@ static int ppp_ioctl(struct net_device *dev, struct if_settings *ifs) return result; ppp = get_ppp(dev); + for (i = 0; i < IDX_COUNT; i++) + timer_setup(&ppp->protos[i].timer, ppp_timer, 0); spin_lock_init(&ppp->lock); ppp->req_timeout = 2; ppp->cr_retries = 10; diff --git a/drivers/net/wireless/ath/ath11k/dp.c b/drivers/net/wireless/ath/ath11k/dp.c index bbb86f165141..5a50b623bd07 100644 --- a/drivers/net/wireless/ath/ath11k/dp.c +++ b/drivers/net/wireless/ath/ath11k/dp.c @@ -1040,6 +1040,7 @@ void ath11k_dp_free(struct ath11k_base *ab) idr_destroy(&dp->tx_ring[i].txbuf_idr); spin_unlock_bh(&dp->tx_ring[i].tx_idr_lock); kfree(dp->tx_ring[i].tx_status); + dp->tx_ring[i].tx_status = NULL; } /* Deinit any SOC level resource */ diff --git a/drivers/net/wireless/intel/iwlwifi/mld/agg.c b/drivers/net/wireless/intel/iwlwifi/mld/agg.c index 3bf36f8f6874..e3627ad0321c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/agg.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/agg.c @@ -64,6 +64,9 @@ static void iwl_mld_release_frames_from_notif(struct iwl_mld *mld, } /* pick any STA ID to find the pointer */ + if (WARN_ON_ONCE(!ba_data->sta_mask)) + goto out_unlock; + sta_id = ffs(ba_data->sta_mask) - 1; link_sta = rcu_dereference(mld->fw_id_to_link_sta[sta_id]); if (WARN_ON_ONCE(IS_ERR_OR_NULL(link_sta) || !link_sta->sta)) @@ -166,6 +169,9 @@ void iwl_mld_del_ba(struct iwl_mld *mld, int queue, goto out_unlock; /* pick any STA ID to find the pointer */ + if (WARN_ON_ONCE(!ba_data->sta_mask)) + goto out_unlock; + sta_id = ffs(ba_data->sta_mask) - 1; link_sta = rcu_dereference(mld->fw_id_to_link_sta[sta_id]); if (WARN_ON_ONCE(IS_ERR_OR_NULL(link_sta) || !link_sta->sta)) @@ -347,6 +353,9 @@ static void iwl_mld_rx_agg_session_expired(struct timer_list *t) } /* timer expired, pick any STA ID to find the pointer */ + if (WARN_ON_ONCE(!ba_data->sta_mask)) + goto unlock; + sta_id = ffs(ba_data->sta_mask) - 1; link_sta = rcu_dereference(ba_data->mld->fw_id_to_link_sta[sta_id]); diff --git a/drivers/net/wireless/intel/iwlwifi/mld/ptp.c b/drivers/net/wireless/intel/iwlwifi/mld/ptp.c index c65f4b56a327..20ae338e5696 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/ptp.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/ptp.c @@ -321,10 +321,10 @@ void iwl_mld_ptp_remove(struct iwl_mld *mld) mld->ptp_data.ptp_clock_info.name, ptp_clock_index(mld->ptp_data.ptp_clock)); + cancel_delayed_work_sync(&mld->ptp_data.dwork); ptp_clock_unregister(mld->ptp_data.ptp_clock); mld->ptp_data.ptp_clock = NULL; mld->ptp_data.last_gp2 = 0; mld->ptp_data.wrap_counter = 0; - cancel_delayed_work_sync(&mld->ptp_data.dwork); } } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c b/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c index f7b620136c85..e05e531b09f0 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ptp.c @@ -325,11 +325,11 @@ void iwl_mvm_ptp_remove(struct iwl_mvm *mvm) mvm->ptp_data.ptp_clock_info.name, ptp_clock_index(mvm->ptp_data.ptp_clock)); + cancel_delayed_work_sync(&mvm->ptp_data.dwork); ptp_clock_unregister(mvm->ptp_data.ptp_clock); mvm->ptp_data.ptp_clock = NULL; memset(&mvm->ptp_data.ptp_clock_info, 0, sizeof(mvm->ptp_data.ptp_clock_info)); mvm->ptp_data.last_gp2 = 0; - cancel_delayed_work_sync(&mvm->ptp_data.dwork); } } diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index 4ae5e4715a9c..b78b4cd206e0 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -1576,6 +1576,7 @@ mt76_sta_add(struct mt76_phy *phy, struct ieee80211_vif *vif, { struct mt76_wcid *wcid = (struct mt76_wcid *)sta->drv_priv; struct mt76_dev *dev = phy->dev; + struct mt76_wcid *published; int ret; int i; @@ -1595,11 +1596,19 @@ mt76_sta_add(struct mt76_phy *phy, struct ieee80211_vif *vif, mtxq->wcid = wcid->idx; } - ewma_signal_init(&wcid->rssi); - rcu_assign_pointer(dev->wcid[wcid->idx], wcid); + published = rcu_dereference_protected(dev->wcid[wcid->idx], + lockdep_is_held(&dev->mutex)); + if (published != wcid) { + WARN_ON_ONCE(published); + ewma_signal_init(&wcid->rssi); + rcu_assign_pointer(dev->wcid[wcid->idx], wcid); + mt76_wcid_init(wcid, phy->band_idx); + } else { + wcid->phy_idx = phy->band_idx; + } + phy->num_sta++; - mt76_wcid_init(wcid, phy->band_idx); out: mutex_unlock(&dev->mutex); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c index 01cb3b2830f3..459c4044f0d1 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c @@ -16,6 +16,7 @@ static const struct usb_device_id mt76x2u_device_table[] = { { USB_DEVICE(0x0e8d, 0x7612) }, /* Aukey USBAC1200 - Alfa AWUS036ACM */ { USB_DEVICE(0x057c, 0x8503) }, /* Avm FRITZ!WLAN AC860 */ { USB_DEVICE(0x7392, 0xb711) }, /* Edimax EW 7722 UAC */ + { USB_DEVICE(0x056e, 0x400a) }, /* ELECOM WDC-867SU3S */ { USB_DEVICE(0x0e8d, 0x7632) }, /* HC-M7662BU1 */ { USB_DEVICE(0x0471, 0x2126) }, /* LiteOn WN4516R module, nonstandard USB connector */ { USB_DEVICE(0x0471, 0x7600) }, /* LiteOn WN4519R module, nonstandard USB connector */ diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c index 73d3722739d0..79cc30a3b29e 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c @@ -1265,6 +1265,9 @@ mt7925_mac_sta_remove_links(struct mt792x_dev *dev, struct ieee80211_vif *vif, if (vif->type == NL80211_IFTYPE_AP) break; + if (vif->type == NL80211_IFTYPE_STATION && sta->tdls) + continue; + link_sta = mt792x_sta_to_link_sta(vif, sta, link_id); if (!link_sta) continue; diff --git a/drivers/net/wireless/realtek/rtl8xxxu/8188e.c b/drivers/net/wireless/realtek/rtl8xxxu/8188e.c index 766a7a7c7d28..fea5aec9ced9 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/8188e.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/8188e.c @@ -1866,6 +1866,7 @@ struct rtl8xxxu_fileops rtl8188eu_fops = { .has_tx_report = 1, .init_reg_pkt_life_time = 1, .gen2_thermal_meter = 1, + .hw_feature_report = 0, .max_sec_cam_num = 32, .adda_1t_init = 0x0b1b25a0, .adda_1t_path_on = 0x0bdb25a0, diff --git a/drivers/net/wireless/realtek/rtl8xxxu/8188f.c b/drivers/net/wireless/realtek/rtl8xxxu/8188f.c index 3abf14d7044f..5556aad1a7ad 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/8188f.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/8188f.c @@ -1745,6 +1745,7 @@ struct rtl8xxxu_fileops rtl8188fu_fops = { .init_reg_rxfltmap = 1, .init_reg_pkt_life_time = 1, .init_reg_hmtfr = 1, + .hw_feature_report = 1, .ampdu_max_time = 0x70, .ustime_tsf_edca = 0x28, .max_aggr_num = 0x0c14, diff --git a/drivers/net/wireless/realtek/rtl8xxxu/8192c.c b/drivers/net/wireless/realtek/rtl8xxxu/8192c.c index 444872131c66..508322a8f310 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/8192c.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/8192c.c @@ -723,6 +723,7 @@ struct rtl8xxxu_fileops rtl8192cu_fops = { .tx_desc_size = sizeof(struct rtl8xxxu_txdesc32), .rx_desc_size = sizeof(struct rtl8xxxu_rxdesc16), .supports_ap = 1, + .hw_feature_report = 0, .max_macid_num = 32, .max_sec_cam_num = 32, .adda_1t_init = 0x0b1b25a0, diff --git a/drivers/net/wireless/realtek/rtl8xxxu/8192e.c b/drivers/net/wireless/realtek/rtl8xxxu/8192e.c index 8e123bbfc665..690ace303150 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/8192e.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/8192e.c @@ -1751,6 +1751,7 @@ struct rtl8xxxu_fileops rtl8192eu_fops = { .has_s0s1 = 0, .gen2_thermal_meter = 1, .needs_full_init = 1, + .hw_feature_report = 0, .supports_ap = 1, .max_macid_num = 128, .max_sec_cam_num = 64, diff --git a/drivers/net/wireless/realtek/rtl8xxxu/8192f.c b/drivers/net/wireless/realtek/rtl8xxxu/8192f.c index cd2156b7a57a..5f076da4b550 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/8192f.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/8192f.c @@ -2074,6 +2074,7 @@ struct rtl8xxxu_fileops rtl8192fu_fops = { .init_reg_rxfltmap = 1, .init_reg_pkt_life_time = 1, .init_reg_hmtfr = 1, + .hw_feature_report = 1, .ampdu_max_time = 0x5e, .ustime_tsf_edca = 0x50, .max_aggr_num = 0x1f1f, diff --git a/drivers/net/wireless/realtek/rtl8xxxu/8710b.c b/drivers/net/wireless/realtek/rtl8xxxu/8710b.c index 11c63c320eae..a87e692bfc81 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/8710b.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/8710b.c @@ -1852,6 +1852,7 @@ struct rtl8xxxu_fileops rtl8710bu_fops = { .init_reg_rxfltmap = 1, .init_reg_pkt_life_time = 1, .init_reg_hmtfr = 1, + .hw_feature_report = 0, /* TODO, it's different */ .ampdu_max_time = 0x5e, /* * The RTL8710BU vendor driver uses 0x50 here and it works fine, diff --git a/drivers/net/wireless/realtek/rtl8xxxu/8723a.c b/drivers/net/wireless/realtek/rtl8xxxu/8723a.c index 4f4493d0bfc2..18e038b82f49 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/8723a.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/8723a.c @@ -632,6 +632,7 @@ struct rtl8xxxu_fileops rtl8723au_fops = { .rx_agg_buf_size = 16000, .tx_desc_size = sizeof(struct rtl8xxxu_txdesc32), .rx_desc_size = sizeof(struct rtl8xxxu_rxdesc16), + .hw_feature_report = 0, .max_sec_cam_num = 32, .adda_1t_init = 0x0b1b25a0, .adda_1t_path_on = 0x0bdb25a0, diff --git a/drivers/net/wireless/realtek/rtl8xxxu/8723b.c b/drivers/net/wireless/realtek/rtl8xxxu/8723b.c index cc2e60b06f64..e314ef991b38 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/8723b.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/8723b.c @@ -1746,6 +1746,7 @@ struct rtl8xxxu_fileops rtl8723bu_fops = { .gen2_thermal_meter = 1, .needs_full_init = 1, .init_reg_hmtfr = 1, + .hw_feature_report = 0, .ampdu_max_time = 0x5e, .ustime_tsf_edca = 0x50, .max_aggr_num = 0x0c14, diff --git a/drivers/net/wireless/realtek/rtl8xxxu/core.c b/drivers/net/wireless/realtek/rtl8xxxu/core.c index f20fade0c099..40af324f5f0a 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/core.c @@ -14,6 +14,7 @@ */ #include <linux/firmware.h> +#include <linux/iopoll.h> #include "regs.h" #include "rtl8xxxu.h" @@ -3915,6 +3916,46 @@ static inline u8 rtl8xxxu_get_macid(struct rtl8xxxu_priv *priv, return sta_info->macid; } +static void rtl8xxxu_request_hw_feature(struct rtl8xxxu_priv *priv) +{ + if (!priv->fops->hw_feature_report) + return; + + rtl8xxxu_write8(priv, REG_C2HEVT_MSG_NORMAL, C2H_HW_FEATURE_DUMP); +} + +static int rtl8xxxu_dump_hw_feature(struct rtl8xxxu_priv *priv) +{ + static const u8 bw_map[8] = { 0, 0, 160, 5, 10, 20, 40, 80 }; + struct rtl8xxxu_hw_feature *hw_feature = &priv->hw_feature; + u8 feature[13]; + int i, ret; + u8 id, bw; + + if (!priv->fops->hw_feature_report) { + hw_feature->max_bw = 40; + return 0; + } + + ret = read_poll_timeout(rtl8xxxu_read8, id, + id == C2H_HW_FEATURE_REPORT, + 10000, 800000, false, + priv, REG_C2HEVT_MSG_NORMAL); + if (ret) + return ret; + + for (i = 0; i < ARRAY_SIZE(feature); i++) + feature[i] = rtl8xxxu_read8(priv, REG_C2HEVT_MSG_NORMAL + 2 + i); + + rtl8xxxu_write8(priv, REG_C2HEVT_MSG_NORMAL, 0); + + bw = u8_get_bits(feature[6], GENMASK(2, 0)); + + hw_feature->max_bw = bw_map[bw]; + + return 0; +} + static int rtl8xxxu_init_device(struct ieee80211_hw *hw) { struct rtl8xxxu_priv *priv = hw->priv; @@ -3961,6 +4002,8 @@ static int rtl8xxxu_init_device(struct ieee80211_hw *hw) */ rtl8xxxu_write16(priv, REG_TRXFF_BNDY + 2, fops->trxff_boundary); + rtl8xxxu_request_hw_feature(priv); + for (int retry = 5; retry >= 0 ; retry--) { ret = rtl8xxxu_download_firmware(priv); dev_dbg(dev, "%s: download_firmware %i\n", __func__, ret); @@ -3976,6 +4019,12 @@ static int rtl8xxxu_init_device(struct ieee80211_hw *hw) if (ret) goto exit; + ret = rtl8xxxu_dump_hw_feature(priv); + if (ret) { + dev_err(dev, "failed to dump hw feature\n"); + goto exit; + } + if (fops->phy_init_antenna_selection) fops->phy_init_antenna_selection(priv); @@ -7835,15 +7884,20 @@ static int rtl8xxxu_probe(struct usb_interface *interface, sband->ht_cap.ht_supported = true; sband->ht_cap.ampdu_factor = IEEE80211_HT_MAX_AMPDU_64K; sband->ht_cap.ampdu_density = IEEE80211_HT_MPDU_DENSITY_16; - sband->ht_cap.cap = IEEE80211_HT_CAP_SGI_20 | IEEE80211_HT_CAP_SGI_40 | - IEEE80211_HT_CAP_SUP_WIDTH_20_40; + sband->ht_cap.cap = IEEE80211_HT_CAP_SGI_20; + + if (priv->hw_feature.max_bw >= 40) { + sband->ht_cap.cap |= IEEE80211_HT_CAP_SGI_40; + sband->ht_cap.cap |= IEEE80211_HT_CAP_SUP_WIDTH_20_40; + } else { + dev_info(&udev->dev, "hardware doesn't support HT40\n"); + } + memset(&sband->ht_cap.mcs, 0, sizeof(sband->ht_cap.mcs)); sband->ht_cap.mcs.rx_mask[0] = 0xff; sband->ht_cap.mcs.rx_mask[4] = 0x01; - if (priv->rf_paths > 1) { + if (priv->rf_paths > 1) sband->ht_cap.mcs.rx_mask[1] = 0xff; - sband->ht_cap.cap |= IEEE80211_HT_CAP_SGI_40; - } sband->ht_cap.mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED; hw->wiphy->bands[NL80211_BAND_2GHZ] = sband; diff --git a/drivers/net/wireless/realtek/rtl8xxxu/regs.h b/drivers/net/wireless/realtek/rtl8xxxu/regs.h index 0741db8d08bf..eafaef1438b9 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/regs.h +++ b/drivers/net/wireless/realtek/rtl8xxxu/regs.h @@ -447,6 +447,8 @@ /* 8188EU */ #define REG_32K_CTRL 0x0194 #define REG_C2HEVT_MSG_NORMAL 0x01a0 +#define C2H_HW_FEATURE_REPORT 0x19 +#define C2H_HW_FEATURE_DUMP 0xfd /* 8192EU/8723BU/8812 */ #define REG_C2HEVT_CMD_ID_8723B 0x01ae #define REG_C2HEVT_CLEAR 0x01af diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h index 9fb2583ffffc..eeb18eb0e4c0 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h @@ -1789,11 +1789,17 @@ struct rtl8xxxu_cfo_tracking { #define RTL8XXXU_BC_MC_MACID1 1 #define RTL8XXXU_MAX_SEC_CAM_NUM 64 +struct rtl8xxxu_hw_feature { + u8 max_bw; +}; + struct rtl8xxxu_priv { struct ieee80211_hw *hw; struct usb_device *udev; struct rtl8xxxu_fileops *fops; + struct rtl8xxxu_hw_feature hw_feature; + spinlock_t tx_urb_lock; struct list_head tx_urb_free_list; int tx_urb_free_count; @@ -2009,6 +2015,7 @@ struct rtl8xxxu_fileops { u8 init_reg_pkt_life_time:1; u8 init_reg_hmtfr:1; u8 supports_concurrent:1; + u8 hw_feature_report:1; u8 ampdu_max_time; u8 ustime_tsf_edca; u16 max_aggr_num; diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.h b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.h index 1155365348f3..d5de09d75f45 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.h +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/trx.h @@ -291,7 +291,7 @@ static inline int get_rx_desc_paggr(__le32 *__pdesc) static inline int get_rx_status_desc_rpt_sel(__le32 *__pdesc) { - return le32_get_bits(*(__pdesc + 1), BIT(28)); + return le32_get_bits(*(__pdesc + 2), BIT(28)); } static inline int get_rx_desc_rxmcs(__le32 *__pdesc) diff --git a/drivers/net/wireless/realtek/rtw88/tx.c b/drivers/net/wireless/realtek/rtw88/tx.c index 3106edb84fb4..a6e43314a4e9 100644 --- a/drivers/net/wireless/realtek/rtw88/tx.c +++ b/drivers/net/wireless/realtek/rtw88/tx.c @@ -196,6 +196,7 @@ void rtw_tx_report_purge_timer(struct timer_list *t) void rtw_tx_report_enqueue(struct rtw_dev *rtwdev, struct sk_buff *skb, u8 sn) { struct rtw_tx_report *tx_report = &rtwdev->tx_report; + unsigned long timeout = RTW_TX_PROBE_TIMEOUT; unsigned long flags; u8 *drv_data; @@ -207,7 +208,11 @@ void rtw_tx_report_enqueue(struct rtw_dev *rtwdev, struct sk_buff *skb, u8 sn) __skb_queue_tail(&tx_report->queue, skb); spin_unlock_irqrestore(&tx_report->q_lock, flags); - mod_timer(&tx_report->purge_timer, jiffies + RTW_TX_PROBE_TIMEOUT); + if (rtwdev->chip->id == RTW_CHIP_TYPE_8723D && + rtwdev->hci.type == RTW_HCI_TYPE_USB) + timeout = msecs_to_jiffies(2500); + + mod_timer(&tx_report->purge_timer, jiffies + timeout); } EXPORT_SYMBOL(rtw_tx_report_enqueue); diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c index 718940ebba31..1a0bdbf52cb0 100644 --- a/drivers/net/wireless/realtek/rtw88/usb.c +++ b/drivers/net/wireless/realtek/rtw88/usb.c @@ -399,6 +399,7 @@ static bool rtw_usb_tx_agg_skb(struct rtw_usb *rtwusb, struct sk_buff_head *list int agg_num = 0; unsigned int align_next = 0; u8 qsel; + int ret; if (skb_queue_empty(list)) return false; @@ -456,7 +457,13 @@ queue: tx_desc = (struct rtw_tx_desc *)skb_head->data; qsel = le32_get_bits(tx_desc->w1, RTW_TX_DESC_W1_QSEL); - rtw_usb_write_port(rtwdev, qsel, skb_head, rtw_usb_write_port_tx_complete, txcb); + ret = rtw_usb_write_port(rtwdev, qsel, skb_head, + rtw_usb_write_port_tx_complete, txcb); + if (ret) { + ieee80211_purge_tx_queue(rtwdev->hw, &txcb->tx_ack_queue); + kfree(txcb); + return false; + } return true; } @@ -518,8 +525,10 @@ static int rtw_usb_write_data(struct rtw_dev *rtwdev, ret = rtw_usb_write_port(rtwdev, qsel, skb, rtw_usb_write_port_complete, skb); - if (unlikely(ret)) + if (unlikely(ret)) { rtw_err(rtwdev, "failed to do USB write, ret=%d\n", ret); + dev_kfree_skb_any(skb); + } return ret; } diff --git a/drivers/ntb/hw/epf/ntb_hw_epf.c b/drivers/ntb/hw/epf/ntb_hw_epf.c index d3ecf25a5162..9935da48a52e 100644 --- a/drivers/ntb/hw/epf/ntb_hw_epf.c +++ b/drivers/ntb/hw/epf/ntb_hw_epf.c @@ -646,7 +646,8 @@ static void ntb_epf_deinit_pci(struct ntb_epf_dev *ndev) struct pci_dev *pdev = ndev->ntb.pdev; pci_iounmap(pdev, ndev->ctrl_reg); - pci_iounmap(pdev, ndev->peer_spad_reg); + if (ndev->barno_map[BAR_PEER_SPAD] != ndev->barno_map[BAR_CONFIG]) + pci_iounmap(pdev, ndev->peer_spad_reg); pci_iounmap(pdev, ndev->db_reg); pci_release_regions(pdev); diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index 7c898542af8d..206e3feb9636 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -548,6 +548,16 @@ static const struct pci_p2pdma_whitelist_entry { {PCI_VENDOR_ID_INTEL, 0x2033, 0}, {PCI_VENDOR_ID_INTEL, 0x2020, 0}, {PCI_VENDOR_ID_INTEL, 0x09a2, 0}, + {PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_DSA_SPR0, 0}, + {PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IAX_SPR0, 0}, + {PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_DSA_GNRD, 0}, + {PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_DSA_DMR, 0}, + {PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IAA_DMR, 0}, + {PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_QAT_4XXX, 0}, + {PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_QAT_401XX, 0}, + {PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_QAT_402XX, 0}, + {PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_QAT_420XX, 0}, + {PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_QAT_6XXX, 0}, /* Google SoCs. */ {PCI_VENDOR_ID_GOOGLE, PCI_ANY_ID, 0}, {} diff --git a/drivers/power/reset/linkstation-poweroff.c b/drivers/power/reset/linkstation-poweroff.c index 02f5fdb8ffc4..e56d75bfcc43 100644 --- a/drivers/power/reset/linkstation-poweroff.c +++ b/drivers/power/reset/linkstation-poweroff.c @@ -163,10 +163,10 @@ static int __init linkstation_poweroff_init(void) dn = of_find_matching_node(NULL, ls_poweroff_of_match); if (!dn) return -ENODEV; - of_node_put(dn); match = of_match_node(ls_poweroff_of_match, dn); cfg = match->data; + of_node_put(dn); dn = of_find_node_by_name(NULL, cfg->mdio_node_name); if (!dn) diff --git a/drivers/power/sequencing/core.c b/drivers/power/sequencing/core.c index 4dff71be11b6..9b512a055b5a 100644 --- a/drivers/power/sequencing/core.c +++ b/drivers/power/sequencing/core.c @@ -989,8 +989,9 @@ static void *pwrseq_debugfs_seq_start(struct seq_file *seq, loff_t *pos) ctx.index = *pos; /* - * We're holding the lock for the entire printout so no need to fiddle - * with device reference count. + * Hold the lock for the entire printout to prevent device removal. + * Reference counts are managed by start()/next()/stop() as required + * by the seq_file contract. */ down_read(&pwrseq_sem); @@ -998,7 +999,7 @@ static void *pwrseq_debugfs_seq_start(struct seq_file *seq, loff_t *pos) if (!ctx.index) return NULL; - return ctx.dev; + return get_device(ctx.dev); } static void *pwrseq_debugfs_seq_next(struct seq_file *seq, void *data, @@ -1008,8 +1009,9 @@ static void *pwrseq_debugfs_seq_next(struct seq_file *seq, void *data, ++*pos; - struct device *next __free(put_device) = - bus_find_next_device(&pwrseq_bus, curr); + struct device *next = bus_find_next_device(&pwrseq_bus, curr); + + put_device(curr); return next; } @@ -1058,6 +1060,8 @@ static int pwrseq_debugfs_seq_show(struct seq_file *seq, void *data) static void pwrseq_debugfs_seq_stop(struct seq_file *seq, void *data) { + if (data) + put_device(data); up_read(&pwrseq_sem); } diff --git a/drivers/rpmsg/rpmsg_char.c b/drivers/rpmsg/rpmsg_char.c index ca9cf8858a5e..bff5aefee212 100644 --- a/drivers/rpmsg/rpmsg_char.c +++ b/drivers/rpmsg/rpmsg_char.c @@ -104,6 +104,9 @@ static int rpmsg_ept_cb(struct rpmsg_device *rpdev, void *buf, int len, struct rpmsg_eptdev *eptdev = priv; struct sk_buff *skb; + if (!eptdev) + return 0; + skb = alloc_skb(len, GFP_ATOMIC); if (!skb) return -ENOMEM; @@ -124,6 +127,9 @@ static int rpmsg_ept_flow_cb(struct rpmsg_device *rpdev, void *priv, bool enable { struct rpmsg_eptdev *eptdev = priv; + if (!eptdev) + return 0; + eptdev->remote_flow_restricted = enable; eptdev->remote_flow_updated = true; @@ -490,6 +496,7 @@ static int rpmsg_chrdev_probe(struct rpmsg_device *rpdev) struct rpmsg_channel_info chinfo; struct rpmsg_eptdev *eptdev; struct device *dev = &rpdev->dev; + int ret; memcpy(chinfo.name, rpdev->id.name, RPMSG_NAME_SIZE); chinfo.src = rpdev->src; @@ -502,13 +509,17 @@ static int rpmsg_chrdev_probe(struct rpmsg_device *rpdev) /* Set the default_ept to the rpmsg device endpoint */ eptdev->default_ept = rpdev->ept; + ret = rpmsg_chrdev_eptdev_add(eptdev, chinfo); + + if (ret) + return ret; /* * The rpmsg_ept_cb uses *priv parameter to get its rpmsg_eptdev context. - * Storedit in default_ept *priv field. + * Stored it in default_ept *priv field. */ eptdev->default_ept->priv = eptdev; - return rpmsg_chrdev_eptdev_add(eptdev, chinfo); + return 0; } static void rpmsg_chrdev_remove(struct rpmsg_device *rpdev) diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index b0e3e765360d..3f4a850d0e5b 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2407,6 +2407,7 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount, int resize, ret, old_width, old_height, old_charcount; font_data_t *old_fontdata = p->fontdata; const u8 *old_data = vc->vc_font.data; + unsigned short old_hi_font_mask = vc->vc_hi_font_mask; font_data_get(data); @@ -2453,6 +2454,12 @@ err_out: vc->vc_font.height = old_height; vc->vc_font.charcount = old_charcount; + /* Restore the hi_font state and screen buffer */ + if (old_hi_font_mask && !vc->vc_hi_font_mask) + set_vc_hi_font(vc, true); + else if (!old_hi_font_mask && vc->vc_hi_font_mask) + set_vc_hi_font(vc, false); + font_data_put(data); return ret; diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 30f2b59c47bf..0929deb95218 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -734,6 +734,18 @@ int fb_new_modelist(struct fb_info *info) if (list_empty(&info->modelist)) return 1; + /* + * The new modelist may not contain the current mode (info->var), and + * fbcon_new_modelist() below only re-points consoles mapped to this + * framebuffer. Add the current mode here so info->var keeps a match + * even when fbcon is unbound. + */ + if (!fb_match_mode(&info->var, &info->modelist)) { + fb_var_to_videomode(&mode, &info->var); + if (fb_add_videomode(&mode, &info->modelist)) + return 1; + } + fbcon_new_modelist(info); return 0; diff --git a/drivers/video/fbdev/core/fbsysfs.c b/drivers/video/fbdev/core/fbsysfs.c index baa2bae0fb5b..fe8bd33e64ab 100644 --- a/drivers/video/fbdev/core/fbsysfs.c +++ b/drivers/video/fbdev/core/fbsysfs.c @@ -11,6 +11,7 @@ #include <linux/major.h> #include "fb_internal.h" +#include "fbcon.h" static int activate(struct fb_info *fb_info, struct fb_var_screeninfo *var) { @@ -111,8 +112,15 @@ static ssize_t store_modes(struct device *device, if (fb_new_modelist(fb_info)) { fb_destroy_modelist(&fb_info->modelist); list_splice(&old_list, &fb_info->modelist); - } else + } else { + /* + * fb_display[i].mode and fb_info->mode both point into the old + * list. Clear them before it is freed. + */ + fbcon_delete_modelist(&old_list); + fb_info->mode = NULL; fb_destroy_modelist(&old_list); + } unlock_fb_info(fb_info); console_unlock(); diff --git a/drivers/video/fbdev/core/modedb.c b/drivers/video/fbdev/core/modedb.c index 703d0b7aec32..e1fd9298a702 100644 --- a/drivers/video/fbdev/core/modedb.c +++ b/drivers/video/fbdev/core/modedb.c @@ -259,7 +259,7 @@ static const struct fb_videomode modedb[] = { FB_VMODE_DOUBLE }, /* 1920x1080 @ 60 Hz, 67.3 kHz hsync */ - { NULL, 60, 1920, 1080, 6734, 148, 88, 36, 4, 44, 5, 0, + { NULL, 60, 1920, 1080, 6734, 148, 88, 36, 4, 44, 5, FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT, FB_VMODE_NONINTERLACED }, @@ -626,7 +626,7 @@ int fb_find_mode(struct fb_var_screeninfo *var, const struct fb_videomode *default_mode, unsigned int default_bpp) { - char *mode_option_buf = NULL; + char *mode_option_buf __free(kfree) = NULL; int i; /* Set up defaults */ @@ -724,7 +724,6 @@ int fb_find_mode(struct fb_var_screeninfo *var, res_specified = 1; } done: - kfree(mode_option_buf); if (cvt) { struct fb_videomode cvt_mode; int ret; diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-main.c b/drivers/video/fbdev/omap2/omapfb/omapfb-main.c index d70deb6a9150..046892682fc6 100644 --- a/drivers/video/fbdev/omap2/omapfb/omapfb-main.c +++ b/drivers/video/fbdev/omap2/omapfb/omapfb-main.c @@ -1099,7 +1099,11 @@ static int omapfb_mmap(struct fb_info *fbi, struct vm_area_struct *vma) rg = omapfb_get_mem_region(ofbi->region); - start = omapfb_get_region_paddr(ofbi); + if (ofbi->rotation_type == OMAP_DSS_ROT_VRFB) + start = rg->vrfb.paddr[0]; + else + start = rg->paddr; + len = fix->smem_len; DBG("user mmap region start %lx, len %d, off %lx\n", start, len, @@ -1109,6 +1113,8 @@ static int omapfb_mmap(struct fb_info *fbi, struct vm_area_struct *vma) vma->vm_ops = &mmap_user_ops; vma->vm_private_data = rg; + atomic_inc(&rg->map_count); + r = vm_iomap_memory(vma, start, len); if (r) goto error; @@ -1121,6 +1127,7 @@ static int omapfb_mmap(struct fb_info *fbi, struct vm_area_struct *vma) return 0; error: + atomic_dec(&rg->map_count); omapfb_put_mem_region(rg); return r; diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 8d3c278a7591..4263cac24b32 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -236,7 +236,7 @@ struct fscrypt_symlink_data { * @tfm: crypto API transform object * @blk_key: key for blk-crypto * - * Normally only one of the fields will be non-NULL. + * Only one of the fields is non-NULL. */ struct fscrypt_prepared_key { struct crypto_sync_skcipher *tfm; @@ -245,6 +245,15 @@ struct fscrypt_prepared_key { #endif }; +/* An entry in the linked list ->mk_mode_keys */ +struct fscrypt_mode_key { + struct fscrypt_prepared_key key; + struct list_head link; + u8 hkdf_context; + u8 mode_num; + u8 data_unit_bits; +}; + /* * fscrypt_inode_info - the "encryption key" for an inode * @@ -430,20 +439,12 @@ int fscrypt_derive_sw_secret(struct super_block *sb, * @prep_key, depending on which encryption implementation the file will use. */ static inline bool -fscrypt_is_key_prepared(struct fscrypt_prepared_key *prep_key, +fscrypt_is_key_prepared(const struct fscrypt_prepared_key *prep_key, const struct fscrypt_inode_info *ci) { - /* - * The two smp_load_acquire()'s here pair with the smp_store_release()'s - * in fscrypt_prepare_inline_crypt_key() and fscrypt_prepare_key(). - * I.e., in some cases (namely, if this prep_key is a per-mode - * encryption key) another task can publish blk_key or tfm concurrently, - * executing a RELEASE barrier. We need to use smp_load_acquire() here - * to safely ACQUIRE the memory the other task published. - */ if (fscrypt_using_inline_encryption(ci)) - return smp_load_acquire(&prep_key->blk_key) != NULL; - return smp_load_acquire(&prep_key->tfm) != NULL; + return prep_key->blk_key != NULL; + return prep_key->tfm != NULL; } #else /* CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ @@ -486,10 +487,10 @@ fscrypt_derive_sw_secret(struct super_block *sb, } static inline bool -fscrypt_is_key_prepared(struct fscrypt_prepared_key *prep_key, +fscrypt_is_key_prepared(const struct fscrypt_prepared_key *prep_key, const struct fscrypt_inode_info *ci) { - return smp_load_acquire(&prep_key->tfm) != NULL; + return prep_key->tfm != NULL; } #endif /* !CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ @@ -577,8 +578,8 @@ struct fscrypt_master_key { /* * Active and structural reference counts. An active ref guarantees * that the struct continues to exist, continues to be in the keyring - * ->s_master_keys, and that any embedded subkeys (e.g. - * ->mk_direct_keys) that have been prepared continue to exist. + * ->s_master_keys, and that any non-file-scoped subkeys (e.g. + * ->mk_mode_keys) that have been prepared continue to exist. * A structural ref only guarantees that the struct continues to exist. * * There is one active ref associated with ->mk_present being true, and @@ -632,12 +633,21 @@ struct fscrypt_master_key { spinlock_t mk_decrypted_inodes_lock; /* - * Per-mode encryption keys for the various types of encryption policies - * that use them. Allocated and derived on-demand. + * A list of 'struct fscrypt_mode_key' for the (hkdf_context, mode_num, + * data_unit_bits, inlinecrypt) combinations that are in use for this + * master key, for hkdf_context in [HKDF_CONTEXT_DIRECT_KEY, + * HKDF_CONTEXT_IV_INO_LBLK_32_KEY, HKDF_CONTEXT_IV_INO_LBLK_64_KEY]. + * + * This is a linked list and not a hash table because in practice + * there's just a single encryption policy per master key, using + * _at most_ 2 nodes in this list. Per-file keys don't use this at all. + * + * This list is append-only until the master key is fully removed, at + * which time the list is cleared. Before then, + * fscrypt_mode_key_setup_mutex synchronizes appends, and searches use + * the RCU read lock together with ->mk_sem held for read. */ - struct fscrypt_prepared_key mk_direct_keys[FSCRYPT_MODE_MAX + 1]; - struct fscrypt_prepared_key mk_iv_ino_lblk_64_keys[FSCRYPT_MODE_MAX + 1]; - struct fscrypt_prepared_key mk_iv_ino_lblk_32_keys[FSCRYPT_MODE_MAX + 1]; + struct list_head mk_mode_keys; /* Hash key for inode numbers. Initialized only when needed. */ siphash_key_t mk_ino_hash_key; diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c index 37d42d357925..47324062fee5 100644 --- a/fs/crypto/inline_crypt.c +++ b/fs/crypto/inline_crypt.c @@ -198,13 +198,7 @@ int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key, goto fail; } - /* - * Pairs with the smp_load_acquire() in fscrypt_is_key_prepared(). - * I.e., here we publish ->blk_key with a RELEASE barrier so that - * concurrent tasks can ACQUIRE it. Note that this concurrency is only - * possible for per-mode keys, not for per-file keys. - */ - smp_store_release(&prep_key->blk_key, blk_key); + prep_key->blk_key = blk_key; return 0; fail: diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index be8e6e8011f2..5fe0d985a58d 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -87,14 +87,14 @@ void fscrypt_put_master_key(struct fscrypt_master_key *mk) void fscrypt_put_master_key_activeref(struct super_block *sb, struct fscrypt_master_key *mk) { - size_t i; + struct fscrypt_mode_key *node, *tmp; if (!refcount_dec_and_test(&mk->mk_active_refs)) return; /* * No active references left, so complete the full removal of this * fscrypt_master_key struct by removing it from the keyring and - * destroying any subkeys embedded in it. + * destroying any non-file-scoped subkeys. */ if (WARN_ON_ONCE(!sb->s_master_keys)) @@ -110,13 +110,16 @@ void fscrypt_put_master_key_activeref(struct super_block *sb, WARN_ON_ONCE(mk->mk_present); WARN_ON_ONCE(!list_empty(&mk->mk_decrypted_inodes)); - for (i = 0; i <= FSCRYPT_MODE_MAX; i++) { - fscrypt_destroy_prepared_key( - sb, &mk->mk_direct_keys[i]); - fscrypt_destroy_prepared_key( - sb, &mk->mk_iv_ino_lblk_64_keys[i]); - fscrypt_destroy_prepared_key( - sb, &mk->mk_iv_ino_lblk_32_keys[i]); + /* + * Destroy any non-file-scoped subkeys. Since ->mk_active_refs == 0, + * they're no longer referenced by any inodes. Nor can key setup run + * and use them again. So they're no longer needed. (This implies no + * concurrent readers, so we don't need list_del_rcu() for example.) + */ + list_for_each_entry_safe(node, tmp, &mk->mk_mode_keys, link) { + fscrypt_destroy_prepared_key(sb, &node->key); + list_del(&node->link); + kfree(node); } memzero_explicit(&mk->mk_ino_hash_key, sizeof(mk->mk_ino_hash_key)); @@ -445,6 +448,8 @@ static int add_new_master_key(struct super_block *sb, INIT_LIST_HEAD(&mk->mk_decrypted_inodes); spin_lock_init(&mk->mk_decrypted_inodes_lock); + INIT_LIST_HEAD(&mk->mk_mode_keys); + if (mk_spec->type == FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER) { err = allocate_master_key_users_keyring(mk); if (err) diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index ce327bfdada4..f905f9f94bdd 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -163,13 +163,7 @@ int fscrypt_prepare_key(struct fscrypt_prepared_key *prep_key, tfm = fscrypt_allocate_skcipher(ci->ci_mode, raw_key, ci->ci_inode); if (IS_ERR(tfm)) return PTR_ERR(tfm); - /* - * Pairs with the smp_load_acquire() in fscrypt_is_key_prepared(). - * I.e., here we publish ->tfm with a RELEASE barrier so that - * concurrent tasks can ACQUIRE it. Note that this concurrency is only - * possible for per-mode keys, not for per-file keys. - */ - smp_store_release(&prep_key->tfm, tfm); + prep_key->tfm = tfm; return 0; } @@ -190,9 +184,37 @@ int fscrypt_set_per_file_enc_key(struct fscrypt_inode_info *ci, return fscrypt_prepare_key(&ci->ci_enc_key, raw_key, ci); } +/* + * Find the fscrypt_prepared_key (if any) for a particular (mk, hkdf_context, + * mode_num, data_unit_bits, inlinecrypt) combination. + * + * The caller must hold ->mk_sem for reading and ->mk_present must be true, + * ensuring that ->mk_mode_keys is still append-only. + */ +static struct fscrypt_prepared_key * +fscrypt_find_mode_key(struct fscrypt_master_key *mk, u8 hkdf_context, + u8 mode_num, const struct fscrypt_inode_info *ci) +{ + struct fscrypt_mode_key *node; + + /* + * The RCU read lock here is used only to synchronize with concurrent + * list_add_tail_rcu(). Concurrent deletions are impossible here, so + * returning a pointer to a node without taking any refcount is safe. + */ + guard(rcu)(); + list_for_each_entry_rcu(node, &mk->mk_mode_keys, link) { + if (node->hkdf_context == hkdf_context && + node->mode_num == mode_num && + node->data_unit_bits == ci->ci_data_unit_bits && + fscrypt_is_key_prepared(&node->key, ci)) + return &node->key; + } + return NULL; +} + static int setup_per_mode_enc_key(struct fscrypt_inode_info *ci, struct fscrypt_master_key *mk, - struct fscrypt_prepared_key *keys, u8 hkdf_context, bool include_fs_uuid) { const struct inode *inode = ci->ci_inode; @@ -200,7 +222,8 @@ static int setup_per_mode_enc_key(struct fscrypt_inode_info *ci, struct fscrypt_mode *mode = ci->ci_mode; const u8 mode_num = mode - fscrypt_modes; struct fscrypt_prepared_key *prep_key; - u8 mode_key[FSCRYPT_MAX_RAW_KEY_SIZE]; + struct fscrypt_mode_key *new_node; + u8 raw_mode_key[FSCRYPT_MAX_RAW_KEY_SIZE]; u8 hkdf_info[sizeof(mode_num) + sizeof(sb->s_uuid)]; unsigned int hkdf_infolen = 0; bool use_hw_wrapped_key = false; @@ -223,48 +246,56 @@ static int setup_per_mode_enc_key(struct fscrypt_inode_info *ci, use_hw_wrapped_key = true; } - prep_key = &keys[mode_num]; - if (fscrypt_is_key_prepared(prep_key, ci)) { + prep_key = fscrypt_find_mode_key(mk, hkdf_context, mode_num, ci); + if (prep_key) { ci->ci_enc_key = *prep_key; return 0; } - mutex_lock(&fscrypt_mode_key_setup_mutex); + guard(mutex)(&fscrypt_mode_key_setup_mutex); - if (fscrypt_is_key_prepared(prep_key, ci)) - goto done_unlock; + prep_key = fscrypt_find_mode_key(mk, hkdf_context, mode_num, ci); + if (prep_key) { + ci->ci_enc_key = *prep_key; + return 0; + } + + new_node = kzalloc_obj(*new_node); + if (!new_node) + return -ENOMEM; + new_node->hkdf_context = hkdf_context; + new_node->mode_num = mode_num; + new_node->data_unit_bits = ci->ci_data_unit_bits; + prep_key = &new_node->key; if (use_hw_wrapped_key) { err = fscrypt_prepare_inline_crypt_key(prep_key, mk->mk_secret.bytes, mk->mk_secret.size, true, ci); - if (err) - goto out_unlock; - goto done_unlock; + } else { + static_assert(sizeof(mode_num) == 1); + static_assert(sizeof(sb->s_uuid) == 16); + static_assert(sizeof(hkdf_info) == 17); + hkdf_info[hkdf_infolen++] = mode_num; + if (include_fs_uuid) { + memcpy(&hkdf_info[hkdf_infolen], &sb->s_uuid, + sizeof(sb->s_uuid)); + hkdf_infolen += sizeof(sb->s_uuid); + } + fscrypt_hkdf_expand(&mk->mk_secret.hkdf, hkdf_context, + hkdf_info, hkdf_infolen, raw_mode_key, + mode->keysize); + err = fscrypt_prepare_key(prep_key, raw_mode_key, ci); + memzero_explicit(raw_mode_key, mode->keysize); } - - BUILD_BUG_ON(sizeof(mode_num) != 1); - BUILD_BUG_ON(sizeof(sb->s_uuid) != 16); - BUILD_BUG_ON(sizeof(hkdf_info) != 17); - hkdf_info[hkdf_infolen++] = mode_num; - if (include_fs_uuid) { - memcpy(&hkdf_info[hkdf_infolen], &sb->s_uuid, - sizeof(sb->s_uuid)); - hkdf_infolen += sizeof(sb->s_uuid); + if (err) { + kfree(new_node); + return err; } - fscrypt_hkdf_expand(&mk->mk_secret.hkdf, hkdf_context, hkdf_info, - hkdf_infolen, mode_key, mode->keysize); - err = fscrypt_prepare_key(prep_key, mode_key, ci); - memzero_explicit(mode_key, mode->keysize); - if (err) - goto out_unlock; -done_unlock: + list_add_tail_rcu(&new_node->link, &mk->mk_mode_keys); ci->ci_enc_key = *prep_key; - err = 0; -out_unlock: - mutex_unlock(&fscrypt_mode_key_setup_mutex); - return err; + return 0; } /* @@ -311,8 +342,8 @@ static int fscrypt_setup_iv_ino_lblk_32_key(struct fscrypt_inode_info *ci, { int err; - err = setup_per_mode_enc_key(ci, mk, mk->mk_iv_ino_lblk_32_keys, - HKDF_CONTEXT_IV_INO_LBLK_32_KEY, true); + err = setup_per_mode_enc_key(ci, mk, HKDF_CONTEXT_IV_INO_LBLK_32_KEY, + true); if (err) return err; @@ -364,8 +395,8 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_inode_info *ci, * encryption key. This ensures that the master key is * consistently used only for HKDF, avoiding key reuse issues. */ - err = setup_per_mode_enc_key(ci, mk, mk->mk_direct_keys, - HKDF_CONTEXT_DIRECT_KEY, false); + err = setup_per_mode_enc_key(ci, mk, HKDF_CONTEXT_DIRECT_KEY, + false); } else if (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) { /* @@ -374,9 +405,8 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_inode_info *ci, * the IVs. This format is optimized for use with inline * encryption hardware compliant with the UFS standard. */ - err = setup_per_mode_enc_key(ci, mk, mk->mk_iv_ino_lblk_64_keys, - HKDF_CONTEXT_IV_INO_LBLK_64_KEY, - true); + err = setup_per_mode_enc_key( + ci, mk, HKDF_CONTEXT_IV_INO_LBLK_64_KEY, true); } else if (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) { err = fscrypt_setup_iv_ino_lblk_32_key(ci, mk); diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index ac008ccaa97d..561fd2349218 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -1027,12 +1027,12 @@ rewind: continue; } - brelse(bh); if (entry_type == TYPE_EXTEND) { unsigned short entry_uniname[16], unichar; if (step != DIRENT_STEP_NAME || name_len >= MAX_NAME_LENGTH) { + brelse(bh); step = DIRENT_STEP_FILE; continue; } @@ -1043,6 +1043,7 @@ rewind: uniname += EXFAT_FILE_NAME_LEN; len = exfat_extract_uni_name(ep, entry_uniname); + brelse(bh); name_len += len; unichar = *(uniname+len); @@ -1061,6 +1062,7 @@ rewind: continue; } + brelse(bh); if (entry_type & (TYPE_CRITICAL_SEC | TYPE_BENIGN_SEC)) { if (step == DIRENT_STEP_SECD) { diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index fa8d81a30fb9..d3253549173e 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -47,6 +47,7 @@ static inline int f2fs_acl_count(size_t size) static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size) { int i, count; + int err = -EINVAL; struct posix_acl *acl; struct f2fs_acl_header *hdr = (struct f2fs_acl_header *)value; struct f2fs_acl_entry *entry = (struct f2fs_acl_entry *)(hdr + 1); @@ -70,8 +71,11 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size) for (i = 0; i < count; i++) { - if ((char *)entry > end) + if (unlikely((char *)entry + + sizeof(struct f2fs_acl_entry_short) > end)) { + err = -EFSCORRUPTED; goto fail; + } acl->a_entries[i].e_tag = le16_to_cpu(entry->e_tag); acl->a_entries[i].e_perm = le16_to_cpu(entry->e_perm); @@ -86,6 +90,11 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size) break; case ACL_USER: + if (unlikely((char *)entry + + sizeof(struct f2fs_acl_entry) > end)) { + err = -EFSCORRUPTED; + goto fail; + } acl->a_entries[i].e_uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id)); @@ -93,6 +102,11 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size) sizeof(struct f2fs_acl_entry)); break; case ACL_GROUP: + if (unlikely((char *)entry + + sizeof(struct f2fs_acl_entry) > end)) { + err = -EFSCORRUPTED; + goto fail; + } acl->a_entries[i].e_gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id)); @@ -108,7 +122,7 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size) return acl; fail: posix_acl_release(acl); - return ERR_PTR(-EINVAL); + return ERR_PTR(err); } static void *f2fs_acl_to_disk(struct f2fs_sb_info *sbi, diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index c00a6b6ebcbd..064f5b537423 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -943,6 +943,7 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi) for (i = 0; i < orphan_blocks; i++) { struct folio *folio; struct f2fs_orphan_block *orphan_blk; + unsigned int entry_count; folio = f2fs_get_meta_folio(sbi, start_blk + i); if (IS_ERR(folio)) { @@ -951,7 +952,18 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi) } orphan_blk = folio_address(folio); - for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) { + entry_count = le32_to_cpu(orphan_blk->entry_count); + if (entry_count > F2FS_ORPHANS_PER_BLOCK) { + f2fs_err(sbi, "invalid orphan inode entry count %u", + entry_count); + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_handle_error(sbi, ERROR_INCONSISTENT_ORPHAN); + err = -EFSCORRUPTED; + f2fs_folio_put(folio, true); + goto out; + } + + for (j = 0; j < entry_count; j++) { nid_t ino = le32_to_cpu(orphan_blk->ino[j]); err = recover_orphan_inode(sbi, ino); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 8d4f1e75dee3..e24b74859427 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2495,7 +2495,7 @@ static int f2fs_read_data_large_folio(struct inode *inode, unsigned nrpages; struct f2fs_folio_state *ffs; int ret = 0; - bool folio_in_bio; + bool folio_in_bio = false; if (!IS_IMMUTABLE(inode) || f2fs_compressed_file(inode)) { if (folio) @@ -2611,18 +2611,17 @@ submit_and_realloc: } trace_f2fs_read_folio(folio, DATA); err_out: - if (!folio_in_bio) { + if (!folio_in_bio) folio_end_read(folio, !ret); - if (ret) - return ret; - } + if (ret) + goto out; if (rac) { folio = readahead_folio(rac); goto next_folio; } out: f2fs_submit_read_bio(F2FS_I_SB(inode), bio, DATA); - if (ret) { + if (ret && folio_in_bio) { /* Wait bios and clear uptodate. */ folio_lock(folio); folio_clear_uptodate(folio); @@ -3822,13 +3821,14 @@ unlock_out: static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi, struct folio *folio, loff_t pos, unsigned int len, - block_t *blk_addr, bool *node_changed, bool *use_cow) + block_t *blk_addr, bool *node_changed) { struct inode *inode = folio->mapping->host; struct inode *cow_inode = F2FS_I(inode)->cow_inode; pgoff_t index = folio->index; int err = 0; block_t ori_blk_addr = NULL_ADDR; + bool cow_has_reserved_block = false; /* If pos is beyond the end of file, reserve a new block in COW inode */ if ((pos & PAGE_MASK) >= i_size_read(inode)) @@ -3836,12 +3836,14 @@ static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi, /* Look for the block in COW inode first */ err = __find_data_block(cow_inode, index, blk_addr); - if (err) { + if (err) return err; - } else if (*blk_addr != NULL_ADDR) { - *use_cow = true; + + if (__is_valid_data_blkaddr(*blk_addr)) return 0; - } + + if (*blk_addr == NEW_ADDR) + cow_has_reserved_block = true; if (is_inode_flag_set(inode, FI_ATOMIC_REPLACE)) goto reserve_block; @@ -3853,10 +3855,13 @@ static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi, reserve_block: /* Finally, we should reserve a new block in COW inode for the update */ - err = __reserve_data_block(cow_inode, index, blk_addr, node_changed); - if (err) - return err; - inc_atomic_write_cnt(inode); + if (!cow_has_reserved_block) { + err = __reserve_data_block(cow_inode, index, blk_addr, + node_changed); + if (err) + return err; + inc_atomic_write_cnt(inode); + } if (ori_blk_addr != NULL_ADDR) *blk_addr = ori_blk_addr; @@ -3873,7 +3878,6 @@ static int f2fs_write_begin(const struct kiocb *iocb, struct folio *folio; pgoff_t index = pos >> PAGE_SHIFT; bool need_balance = false; - bool use_cow = false; block_t blkaddr = NULL_ADDR; int err = 0; @@ -3936,7 +3940,7 @@ repeat: if (f2fs_is_atomic_file(inode)) err = prepare_atomic_write_begin(sbi, folio, pos, len, - &blkaddr, &need_balance, &use_cow); + &blkaddr, &need_balance); else err = prepare_write_begin(sbi, folio, pos, len, &blkaddr, &need_balance); @@ -3976,8 +3980,15 @@ repeat: err = -EFSCORRUPTED; goto put_folio; } - f2fs_submit_page_read(use_cow ? F2FS_I(inode)->cow_inode : - inode, + /* + * Although the block may be stored in the COW inode, the folio + * belongs to @inode and its data was encrypted (or not) using + * @inode's context (see f2fs_encrypt_one_page()). Read with + * @inode so the post-read decryption decision matches the + * folio's owner; otherwise an unencrypted @inode whose COW inode + * is encrypted hits a NULL ->i_crypt_info on decryption. + */ + f2fs_submit_page_read(inode, NULL, /* can't write to fsverity files */ folio, blkaddr, 0, true); diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index d2e006420f04..61f6b9714366 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -119,10 +119,9 @@ static bool __may_extent_tree(struct inode *inode, enum extent_type type) if (!__init_may_extent_tree(inode, type)) return false; - if (is_inode_flag_set(inode, FI_NO_EXTENT)) - return false; - if (type == EX_READ) { + if (is_inode_flag_set(inode, FI_NO_EXTENT)) + return false; if (is_inode_flag_set(inode, FI_COMPRESSED_FILE) && !f2fs_sb_has_readonly(F2FS_I_SB(inode))) return false; @@ -645,14 +644,10 @@ static unsigned int __destroy_extent_node(struct inode *inode, while (atomic_read(&et->node_cnt)) { write_lock(&et->lock); - if (!is_inode_flag_set(inode, FI_NO_EXTENT)) - set_inode_flag(inode, FI_NO_EXTENT); node_cnt += __free_extent_tree(sbi, et, nr_shrink); write_unlock(&et->lock); } - f2fs_bug_on(sbi, atomic_read(&et->node_cnt)); - return node_cnt; } @@ -691,12 +686,12 @@ static void __update_extent_tree_range(struct inode *inode, write_lock(&et->lock); - if (is_inode_flag_set(inode, FI_NO_EXTENT)) { - write_unlock(&et->lock); - return; - } - if (type == EX_READ) { + if (is_inode_flag_set(inode, FI_NO_EXTENT)) { + write_unlock(&et->lock); + return; + } + prev = et->largest; dei.len = 0; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 91f506e7c9cf..069595fc5e1a 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1583,6 +1583,7 @@ enum node_type { NODE_TYPE_INODE, NODE_TYPE_XATTR, NODE_TYPE_NON_INODE, + NODE_TYPE_NON_IXNODE, /* non inode and xnode */ }; /* a threshold of maximum elapsed time in critical region to print tracepoint */ diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index fb12c5c9affd..ade4fde2ef0e 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1098,6 +1098,8 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, return -EPERM; if ((attr->ia_valid & ATTR_SIZE)) { + if (mapping_large_folio_support(inode->i_mapping)) + return -EOPNOTSUPP; if (!f2fs_is_compress_backend_ready(inode) || IS_DEVICE_ALIASING(inode)) return -EOPNOTSUPP; @@ -1914,8 +1916,15 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset, if (f2fs_is_pinned_file(inode)) { block_t sec_blks = CAP_BLKS_PER_SEC(sbi); - block_t sec_len = roundup(map.m_len, sec_blks); + block_t sec_len; + if (map.m_lblk % sec_blks) { + map.m_lblk = rounddown(map.m_lblk, sec_blks); + map.m_len = pg_end - map.m_lblk; + if (off_end) + map.m_len++; + } + sec_len = roundup(map.m_len, sec_blks); map.m_len = sec_blks; next_alloc: f2fs_down_write(&sbi->pin_sem); diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index ba93010924c0..11228349b003 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1220,8 +1220,8 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, static int ra_data_block(struct inode *inode, pgoff_t index) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct address_space *mapping = f2fs_is_cow_file(inode) ? - F2FS_I(inode)->atomic_inode->i_mapping : inode->i_mapping; + struct address_space *mapping = inode->i_mapping; + struct inode *atomic_inode = NULL; struct dnode_of_data dn; struct folio *folio, *efolio; struct f2fs_io_info fio = { @@ -1236,9 +1236,22 @@ static int ra_data_block(struct inode *inode, pgoff_t index) }; int err = 0; + f2fs_down_read(&F2FS_I(inode)->i_sem); + if (f2fs_is_cow_file(inode)) { + atomic_inode = igrab(F2FS_I(inode)->atomic_inode); + if (!atomic_inode) { + f2fs_up_read(&F2FS_I(inode)->i_sem); + return -EBUSY; + } + mapping = atomic_inode->i_mapping; + } + f2fs_up_read(&F2FS_I(inode)->i_sem); + folio = f2fs_grab_cache_folio(mapping, index, true); - if (IS_ERR(folio)) - return PTR_ERR(folio); + if (IS_ERR(folio)) { + err = PTR_ERR(folio); + goto out_iput; + } if (f2fs_lookup_read_extent_cache_block(inode, index, &dn.data_blkaddr)) { @@ -1299,11 +1312,16 @@ got_it: f2fs_update_iostat(sbi, inode, FS_DATA_READ_IO, F2FS_BLKSIZE); f2fs_update_iostat(sbi, NULL, FS_GDATA_READ_IO, F2FS_BLKSIZE); + if (atomic_inode) + iput(atomic_inode); return 0; put_encrypted_page: f2fs_put_page(fio.encrypted_page, true); put_folio: f2fs_folio_put(folio, true); +out_iput: + if (atomic_inode) + iput(atomic_inode); return err; } @@ -1314,8 +1332,8 @@ put_folio: static int move_data_block(struct inode *inode, block_t bidx, int gc_type, unsigned int segno, int off) { - struct address_space *mapping = f2fs_is_cow_file(inode) ? - F2FS_I(inode)->atomic_inode->i_mapping : inode->i_mapping; + struct address_space *mapping = inode->i_mapping; + struct inode *atomic_inode = NULL; struct f2fs_io_info fio = { .sbi = F2FS_I_SB(inode), .ino = inode->i_ino, @@ -1337,10 +1355,23 @@ static int move_data_block(struct inode *inode, block_t bidx, (fio.sbi->gc_mode != GC_URGENT_HIGH) ? CURSEG_ALL_DATA_ATGC : CURSEG_COLD_DATA; + f2fs_down_read(&F2FS_I(inode)->i_sem); + if (f2fs_is_cow_file(inode)) { + atomic_inode = igrab(F2FS_I(inode)->atomic_inode); + if (!atomic_inode) { + f2fs_up_read(&F2FS_I(inode)->i_sem); + return -EBUSY; + } + mapping = atomic_inode->i_mapping; + } + f2fs_up_read(&F2FS_I(inode)->i_sem); + /* do not read out */ folio = f2fs_grab_cache_folio(mapping, bidx, false); - if (IS_ERR(folio)) - return PTR_ERR(folio); + if (IS_ERR(folio)) { + err = PTR_ERR(folio); + goto out_iput; + } if (!check_valid_map(F2FS_I_SB(inode), segno, off)) { err = -ENOENT; @@ -1468,11 +1499,10 @@ up_out: put_out: f2fs_put_dnode(&dn); out: - if (!folio_test_uptodate(folio)) - __folio_set_dropbehind(folio); - folio_unlock(folio); - folio_end_dropbehind(folio); - folio_put(folio); + f2fs_folio_put(folio, true); +out_iput: + if (atomic_inode) + iput(atomic_inode); return err; } diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index c6dcda447882..5f0cf81e49f0 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -324,9 +324,9 @@ static bool sanity_check_inode(struct inode *inode, struct folio *node_folio) } if (f2fs_sb_has_flexible_inline_xattr(sbi) && - f2fs_has_inline_xattr(inode) && - (fi->i_inline_xattr_size < MIN_INLINE_XATTR_SIZE || - fi->i_inline_xattr_size > MAX_INLINE_XATTR_SIZE)) { + (fi->i_inline_xattr_size > MAX_INLINE_XATTR_SIZE || + (f2fs_has_inline_xattr(inode) && + fi->i_inline_xattr_size < MIN_INLINE_XATTR_SIZE))) { f2fs_warn(sbi, "%s: inode (ino=%llx) has corrupted i_inline_xattr_size: %d, min: %zu, max: %lu", __func__, inode->i_ino, fi->i_inline_xattr_size, MIN_INLINE_XATTR_SIZE, MAX_INLINE_XATTR_SIZE); @@ -561,8 +561,13 @@ static int do_read_inode(struct inode *inode) static bool is_meta_ino(struct f2fs_sb_info *sbi, unsigned int ino) { - return ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi) || - ino == F2FS_COMPRESS_INO(sbi); + if (ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi)) + return true; +#ifdef CONFIG_F2FS_FS_COMPRESSION + if (test_opt(sbi, COMPRESS_CACHE) && ino == F2FS_COMPRESS_INO(sbi)) + return true; +#endif + return false; } struct inode *f2fs_iget(struct super_block *sb, unsigned long ino) @@ -858,10 +863,15 @@ void f2fs_evict_inode(struct inode *inode) f2fs_abort_atomic_write(inode, true); if (fi->cow_inode && f2fs_is_cow_file(fi->cow_inode)) { - clear_inode_flag(fi->cow_inode, FI_COW_FILE); - F2FS_I(fi->cow_inode)->atomic_inode = NULL; - iput(fi->cow_inode); + struct inode *cow_inode = fi->cow_inode; + + f2fs_down_write(&F2FS_I(cow_inode)->i_sem); + clear_inode_flag(cow_inode, FI_COW_FILE); + F2FS_I(cow_inode)->atomic_inode = NULL; fi->cow_inode = NULL; + f2fs_up_write(&F2FS_I(cow_inode)->i_sem); + + iput(cow_inode); } trace_f2fs_evict_inode(inode); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 4e5bd9e4cfc3..01d860e7e169 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1541,6 +1541,10 @@ int f2fs_sanity_check_node_footer(struct f2fs_sb_info *sbi, if (is_inode) goto out_err; break; + case NODE_TYPE_NON_IXNODE: + if (is_inode || is_xnode) + goto out_err; + break; default: break; } @@ -1634,7 +1638,7 @@ static struct folio *f2fs_get_node_folio_ra(struct folio *parent, int start) struct f2fs_sb_info *sbi = F2FS_F_SB(parent); nid_t nid = get_nid(parent, start, false); - return __get_node_folio(sbi, nid, parent, start, NODE_TYPE_REGULAR); + return __get_node_folio(sbi, nid, parent, start, NODE_TYPE_NON_IXNODE); } static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino) @@ -1875,7 +1879,7 @@ int f2fs_write_single_node_folio(struct folio *node_folio, int sync_mode, } if (!__write_node_folio(node_folio, false, false, NULL, - &wbc, false, FS_GC_NODE_IO, NULL)) + &wbc, false, io_type, NULL)) err = -EAGAIN; goto release_folio; out_folio: diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index a2ea121331f1..4d854556b529 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -643,6 +643,7 @@ restart: gfs2_delete_debugfs_file(sdp); gfs2_sys_fs_del(sdp); + rcu_barrier(); free_sbd(sdp); } diff --git a/fs/nfs/client.c b/fs/nfs/client.c index be02bb227741..0781b15e7e05 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -1074,6 +1074,7 @@ struct nfs_server *nfs_alloc_server(void) server->io_stats = nfs_alloc_iostats(); if (!server->io_stats) { + ida_free(&s_sysfs_ids, server->s_sysfs_id); kfree(server); return NULL; } diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 8b1559171fe3..e22a8e0daf2c 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -551,6 +551,10 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh, if (!p) goto out_err_free; fh_count = be32_to_cpup(p); + if (fh_count == 0) { + rc = -EINVAL; + goto out_err_free; + } dss_info->fh_versions = kzalloc_objs(struct nfs_fh, fh_count, gfp_flags); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index a9b8d482d289..c354b7b90293 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5302,10 +5302,9 @@ static struct dentry *nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry, do { alias = _nfs4_proc_mkdir(dir, dentry, sattr, label, &err); trace_nfs4_mkdir(dir, &dentry->d_name, err); + err = nfs4_handle_exception(NFS_SERVER(dir), err, &exception); if (err) - alias = ERR_PTR(nfs4_handle_exception(NFS_SERVER(dir), - err, - &exception)); + alias = ERR_PTR(err); } while (exception.retry); nfs4_label_release_security(label); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 743467e9ba20..aee523134c0f 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2229,11 +2229,11 @@ lookup_again: dprintk("%s wait for layoutreturn\n", __func__); lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo)); if (!IS_ERR(lseg)) { - pnfs_put_layout_hdr(lo); dprintk("%s retrying\n", __func__); trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg, PNFS_UPDATE_LAYOUT_RETRY); + pnfs_put_layout_hdr(lo); goto lookup_again; } trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg, diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 12632a706da8..0ff43dbcb7cd 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -1075,14 +1075,14 @@ nfs4_decode_mp_ds_addr(struct net *net, struct xdr_stream *xdr, gfp_t gfp_flags) /* r_netid */ nlen = xdr_stream_decode_string_dup(xdr, &netid, XDR_MAX_NETOBJ, gfp_flags); - if (unlikely(nlen < 0)) + if (unlikely(nlen <= 0)) goto out_err; /* r_addr: ip/ip6addr with port in dec octets - see RFC 5665 */ /* port is ".ABC.DEF", 8 chars max */ rlen = xdr_stream_decode_string_dup(xdr, &buf, INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN + 8, gfp_flags); - if (unlikely(rlen < 0)) + if (unlikely(rlen <= 0)) goto out_free_netid; /* replace port '.' with '-' */ diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 0ac538c76180..76305b86c1a9 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -131,10 +131,7 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp) resp->status = fh_getattr(fh, &resp->stat); out: - /* argp->acl_{access,default} may have been allocated in - nfssvc_decode_setaclargs. */ - posix_acl_release(argp->acl_access); - posix_acl_release(argp->acl_default); + /* argp->acl_{access,default} are released in nfsaclsvc_release_setacl. */ return rpc_success; out_drop_lock: @@ -310,6 +307,16 @@ static void nfsaclsvc_release_access(struct svc_rqst *rqstp) fh_put(&resp->fh); } +static void nfsaclsvc_release_setacl(struct svc_rqst *rqstp) +{ + struct nfsd3_setaclargs *argp = rqstp->rq_argp; + struct nfsd_attrstat *resp = rqstp->rq_resp; + + fh_put(&resp->fh); + posix_acl_release(argp->acl_access); + posix_acl_release(argp->acl_default); +} + #define ST 1 /* status*/ #define AT 21 /* attributes */ #define pAT (1+AT) /* post attributes - conditional */ @@ -343,7 +350,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { .pc_func = nfsacld_proc_setacl, .pc_decode = nfsaclsvc_decode_setaclargs, .pc_encode = nfssvc_encode_attrstatres, - .pc_release = nfssvc_release_attrstat, + .pc_release = nfsaclsvc_release_setacl, .pc_argsize = sizeof(struct nfsd3_setaclargs), .pc_argzero = sizeof(struct nfsd3_setaclargs), .pc_ressize = sizeof(struct nfsd_attrstat), diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 7b5433bd3019..e87731380be8 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -118,10 +118,7 @@ out_drop_lock: out_errno: resp->status = nfserrno(error); out: - /* argp->acl_{access,default} may have been allocated in - nfs3svc_decode_setaclargs. */ - posix_acl_release(argp->acl_access); - posix_acl_release(argp->acl_default); + /* argp->acl_{access,default} are released in nfs3svc_release_setacl. */ return rpc_success; } @@ -223,6 +220,16 @@ static void nfs3svc_release_getacl(struct svc_rqst *rqstp) posix_acl_release(resp->acl_default); } +static void nfs3svc_release_setacl(struct svc_rqst *rqstp) +{ + struct nfsd3_setaclargs *argp = rqstp->rq_argp; + struct nfsd3_attrstat *resp = rqstp->rq_resp; + + fh_put(&resp->fh); + posix_acl_release(argp->acl_access); + posix_acl_release(argp->acl_default); +} + #define ST 1 /* status*/ #define AT 21 /* attributes */ #define pAT (1+AT) /* post attributes - conditional */ @@ -256,7 +263,7 @@ static const struct svc_procedure nfsd_acl_procedures3[3] = { .pc_func = nfsd3_proc_setacl, .pc_decode = nfs3svc_decode_setaclargs, .pc_encode = nfs3svc_encode_setaclres, - .pc_release = nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_setacl, .pc_argsize = sizeof(struct nfsd3_setaclargs), .pc_argzero = sizeof(struct nfsd3_setaclargs), .pc_ressize = sizeof(struct nfsd3_attrstat), diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 69e41105efdd..8e2929cffa7c 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -264,10 +264,12 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, ls->ls_file = find_any_file(fp); BUG_ON(!ls->ls_file); + ls->ls_fenced = false; + ls->ls_fence_delay = 0; + INIT_DELAYED_WORK(&ls->ls_fence_work, nfsd4_layout_fence_worker); + if (nfsd4_layout_setlease(ls)) { - nfsd_file_put(ls->ls_file); - put_nfs4_file(fp); - kmem_cache_free(nfs4_layout_stateid_cache, ls); + nfs4_put_stid(stp); return NULL; } @@ -280,10 +282,6 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, list_add(&ls->ls_perfile, &fp->fi_lo_states); spin_unlock(&fp->fi_lock); - ls->ls_fenced = false; - ls->ls_fence_delay = 0; - INIT_DELAYED_WORK(&ls->ls_fence_work, nfsd4_layout_fence_worker); - trace_nfsd_layoutstate_alloc(&ls->ls_stid.sc_stateid); return ls; } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index ab39ec885440..8561540ab2db 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -253,7 +253,7 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, .na_iattr = iap, .na_seclabel = &open->op_label, }; - struct dentry *parent, *child; + struct dentry *parent, *child = ERR_PTR(-EINVAL); __u32 v_mtime, v_atime; struct inode *inode; __be32 status; @@ -277,10 +277,14 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, if (open->op_acl) { if (open->op_dpacl || open->op_pacl) { status = nfserr_inval; - goto out_write; + goto out; + } + if (is_create_with_attrs(open)) { + status = nfsd4_acl_to_attr(NF4REG, open->op_acl, + &attrs); + if (status) + goto out; } - if (is_create_with_attrs(open)) - nfsd4_acl_to_attr(NF4REG, open->op_acl, &attrs); } else if (is_create_with_attrs(open)) { /* The dpacl and pacl will get released by nfsd_attrs_free(). */ attrs.na_dpacl = open->op_dpacl; @@ -293,7 +297,7 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, &QSTR_LEN(open->op_fname, open->op_fnamelen)); if (IS_ERR(child)) { status = nfserrno(PTR_ERR(child)); - goto out_write; + goto out; } if (d_really_is_negative(child)) { @@ -407,7 +411,6 @@ set_attr: out: end_creating(child); nfsd_attrs_free(&attrs); -out_write: fh_drop_write(fhp); return status; } @@ -837,7 +840,7 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out_aftermask; if (create->cr_acl) { - if (create->cr_dpacl || create->cr_pacl) { + if (attrs.na_dpacl || attrs.na_pacl) { status = nfserr_inval; goto out_aftermask; } @@ -1470,7 +1473,7 @@ void nfsd4_async_copy_reaper(struct nfsd_net *nn) list_for_each_safe(pos, next, &clp->async_copies) { copy = list_entry(pos, struct nfsd4_copy, copies); if (test_bit(NFSD4_COPY_F_OFFLOAD_DONE, ©->cp_flags)) { - if (--copy->cp_ttl) { + if (!--copy->cp_ttl) { list_del_init(©->copies); list_add(©->copies, &reaplist); } diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index b338473d6e52..6ea25a52d2f4 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -718,7 +718,8 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg, return PTR_ERR(namecopy); name.data = namecopy; name.len = namelen; - get_user(princhashlen, &ci->cc_princhash.cp_len); + if (get_user(princhashlen, &ci->cc_princhash.cp_len)) + return -EFAULT; if (princhashlen > 0) { princhashcopy = memdup_user( &ci->cc_princhash.cp_data, diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 6837b63d9864..d875e98d4dcb 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -5169,6 +5169,7 @@ retry: /* Replace unconfirmed owners without checking for replay. */ release_openowner(oo); oo = NULL; + goto retry; } if (oo) { if (new) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 2a0946c630e1..2da83053fa10 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2008,10 +2008,11 @@ static __be32 nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { struct nfsd4_secinfo_no_name *sin = &u->secinfo_no_name; + + sin->sin_exp = NULL; if (xdr_stream_decode_u32(argp->xdr, &sin->sin_style) < 0) return nfserr_bad_xdr; - sin->sin_exp = NULL; return nfs_ok; } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index eafdf7b7890f..2c557a998961 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1508,8 +1508,10 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, nfsd_stats_io_write_add(nn, exp, *cnt); fsnotify_modify(file); host_err = filemap_check_wb_err(file->f_mapping, since); - if (host_err < 0) + if (host_err < 0) { + commit_reset_write_verifier(nn, rqstp, host_err); goto out_nfserr; + } if (stable && fhp->fh_use_wgather) { host_err = wait_for_concurrent_writes(file); @@ -1689,6 +1691,8 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, nfsd_copy_write_verifier(verf, nn); err2 = filemap_check_wb_err(nf->nf_file->f_mapping, since); + if (err2 < 0) + commit_reset_write_verifier(nn, rqstp, err2); err = nfserrno(err2); break; case -EINVAL: diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index e8bea22b81a7..264cf8404385 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -707,12 +707,21 @@ static int ntfs_ioctl_get_volume_label(struct file *filp, unsigned long arg) { struct ntfs_volume *vol = NTFS_SB(file_inode(filp)->i_sb); char __user *buf = (char __user *)arg; + char label[FSLABEL_MAX]; + ssize_t len; + mutex_lock(&vol->volume_label_lock); if (!vol->volume_label) { - if (copy_to_user(buf, "", 1)) - return -EFAULT; - } else if (copy_to_user(buf, vol->volume_label, - MIN(FSLABEL_MAX, strlen(vol->volume_label) + 1))) + label[0] = '\0'; + len = 0; + } else { + len = strscpy(label, vol->volume_label, sizeof(label)); + if (len == -E2BIG) + len = FSLABEL_MAX - 1; + } + mutex_unlock(&vol->volume_label_lock); + + if (copy_to_user(buf, label, len + 1)) return -EFAULT; return 0; } diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 9e321cc2febe..cb880cb6e388 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -460,17 +460,23 @@ int ntfs_write_volume_label(struct ntfs_volume *vol, char *label) ret = ntfs_resident_attr_record_add(vol_ni, AT_VOLUME_NAME, AT_UNNAMED, 0, (u8 *)uname, uname_len * sizeof(__le16), 0); out: - mutex_unlock(&vol_ni->mrec_lock); - kvfree(uname); - if (ret >= 0) { - kfree(vol->volume_label); + char *old_label; + + mutex_lock(&vol->volume_label_lock); + old_label = vol->volume_label; vol->volume_label = new_label; + mutex_unlock(&vol->volume_label_lock); + + kfree(old_label); mark_inode_dirty_sync(vol->vol_ino); ret = 0; - } else { - kfree(new_label); } + mutex_unlock(&vol_ni->mrec_lock); + kvfree(uname); + + if (ret < 0) + kfree(new_label); return ret; } @@ -2631,6 +2637,7 @@ static int ntfs_init_fs_context(struct fs_context *fc) NVolSetCaseSensitive(vol); init_rwsem(&vol->mftbmp_lock); init_rwsem(&vol->lcnbmp_lock); + mutex_init(&vol->volume_label_lock); fc->s_fs_info = vol; fc->ops = &ntfs_context_ops; diff --git a/fs/ntfs/volume.h b/fs/ntfs/volume.h index af41427ec622..99e642f475f7 100644 --- a/fs/ntfs/volume.h +++ b/fs/ntfs/volume.h @@ -72,6 +72,7 @@ * @vol_flags: Volume flags. * @major_ver: Ntfs major version of volume. * @minor_ver: Ntfs minor version of volume. + * @volume_label_lock: protects @volume_label. * @volume_label: volume label. * @root_ino: The VFS inode of the root directory. * @secure_ino: The VFS inode of $Secure (NTFS3.0+ only, otherwise NULL). @@ -133,6 +134,7 @@ struct ntfs_volume { struct inode *logfile_ino; struct inode *lcnbmp_ino; struct rw_semaphore lcnbmp_lock; + struct mutex volume_label_lock; struct inode *vol_ino; __le16 vol_flags; u8 major_ver; diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index 9eeac0ab2b71..372cf2f2e89b 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -851,6 +851,12 @@ out: return err; } +static bool ntfs_is_reserved_lxattr(const char *name) +{ + return !strcmp(name, "$LXUID") || !strcmp(name, "$LXGID") || + !strcmp(name, "$LXMOD") || !strcmp(name, "$LXDEV"); +} + /* * ntfs_setxattr - inode_operations::setxattr */ @@ -955,6 +961,12 @@ set_new_fa: goto out; } + /* Do not allow non privileged users to change $LXUID/$LXGID... */ + if (ntfs_is_reserved_lxattr(name) && !capable(CAP_SYS_ADMIN)) { + err = -EPERM; + goto out; + } + /* Deal with NTFS extended attribute. */ err = ntfs_set_ea(inode, name, strlen(name), value, size, flags, 0, NULL); diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index d284e0e37252..a4a2b87a45fe 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -231,8 +231,16 @@ static int ocfs2_validate_gd_parent(struct super_block *sb, int resize) { unsigned int max_bits; + unsigned int max_bitmap_bits; + unsigned int max_bitmap_size; + int suballocator; struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data; + suballocator = le64_to_cpu(di->i_blkno) != OCFS2_SB(sb)->bitmap_blkno; + max_bitmap_size = ocfs2_group_bitmap_size(sb, suballocator, + OCFS2_SB(sb)->s_feature_incompat); + max_bitmap_bits = max_bitmap_size * 8; + if (di->i_blkno != gd->bg_parent_dinode) { do_error("Group descriptor #%llu has bad parent pointer (%llu, expected %llu)\n", (unsigned long long)bh->b_blocknr, @@ -240,6 +248,20 @@ static int ocfs2_validate_gd_parent(struct super_block *sb, (unsigned long long)le64_to_cpu(di->i_blkno)); } + if (le16_to_cpu(gd->bg_size) > max_bitmap_size) { + do_error("Group descriptor #%llu has bitmap size %u but physical max of %u\n", + (unsigned long long)bh->b_blocknr, + le16_to_cpu(gd->bg_size), + max_bitmap_size); + } + + if (le16_to_cpu(gd->bg_bits) > max_bitmap_bits) { + do_error("Group descriptor #%llu has bit count %u but physical max of %u\n", + (unsigned long long)bh->b_blocknr, + le16_to_cpu(gd->bg_bits), + max_bitmap_bits); + } + max_bits = le16_to_cpu(di->id2.i_chain.cl_cpg) * le16_to_cpu(di->id2.i_chain.cl_bpc); if (le16_to_cpu(gd->bg_bits) > max_bits) { do_error("Group descriptor #%llu has bit count of %u\n", diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index 664b1b4a3233..340ea98fa494 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -1477,7 +1477,9 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path, break; aces_size -= ace_size; - if (ace->sid.num_subauth > SID_MAX_SUB_AUTHORITIES) + if (ace->sid.num_subauth > SID_MAX_SUB_AUTHORITIES || + ace_size < offsetof(struct smb_ace, sid) + CIFS_SID_BASE_SIZE + + sizeof(__le32) * ace->sid.num_subauth) break; if (!compare_sids(&sid, &ace->sid) || diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 4b53dc4a3266..390e4b7d9cb9 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -786,6 +786,8 @@ void mremap_userfaultfd_fail(struct vm_userfaultfd_ctx *vm_ctx) if (!ctx) return; + atomic_dec(&ctx->mmap_changing); + VM_WARN_ON_ONCE(atomic_read(&ctx->mmap_changing) < 0); userfaultfd_ctx_put(ctx); } diff --git a/include/keys/request_key_auth-type.h b/include/keys/request_key_auth-type.h index 36b89a933310..01e42ee5f409 100644 --- a/include/keys/request_key_auth-type.h +++ b/include/keys/request_key_auth-type.h @@ -9,12 +9,14 @@ #define _KEYS_REQUEST_KEY_AUTH_TYPE_H #include <linux/key.h> +#include <linux/refcount.h> /* * Authorisation record for request_key(). */ struct request_key_auth { struct rcu_head rcu; + refcount_t usage; struct key *target_key; struct key *dest_keyring; const struct cred *cred; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 890128cdea1c..dda80803740f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1214,16 +1214,12 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async) __blk_flush_plug(plug, async); } -/* - * tsk == current here - */ -static inline void blk_plug_invalidate_ts(struct task_struct *tsk) +static __always_inline void blk_plug_invalidate_ts(void) { - struct blk_plug *plug = tsk->plug; - - if (plug) - plug->cur_ktime = 0; - current->flags &= ~PF_BLOCK_TS; + if (unlikely(current->flags & PF_BLOCK_TS)) { + current->plug->cur_ktime = 0; + current->flags &= ~PF_BLOCK_TS; + } } int blkdev_issue_flush(struct block_device *bdev); @@ -1249,7 +1245,7 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async) { } -static inline void blk_plug_invalidate_ts(struct task_struct *tsk) +static inline void blk_plug_invalidate_ts(void) { } diff --git a/include/linux/err.h b/include/linux/err.h index 8c37be0620ab..d3e38d5b3a98 100644 --- a/include/linux/err.h +++ b/include/linux/err.h @@ -36,7 +36,7 @@ * * Return: A pointer with @error encoded within its value. */ -static inline void * __must_check ERR_PTR(long error) +static __always_inline void * __must_check ERR_PTR(long error) { return (void *) error; } @@ -60,7 +60,7 @@ static inline void * __must_check ERR_PTR(long error) * @ptr: An error pointer. * Return: The error code within @ptr. */ -static inline long __must_check PTR_ERR(__force const void *ptr) +static __always_inline long __must_check PTR_ERR(__force const void *ptr) { return (long) ptr; } @@ -73,7 +73,7 @@ static inline long __must_check PTR_ERR(__force const void *ptr) * @ptr: The pointer to check. * Return: true if @ptr is an error pointer, false otherwise. */ -static inline bool __must_check IS_ERR(__force const void *ptr) +static __always_inline bool __must_check IS_ERR(__force const void *ptr) { return IS_ERR_VALUE((unsigned long)ptr); } @@ -87,7 +87,7 @@ static inline bool __must_check IS_ERR(__force const void *ptr) * * Like IS_ERR(), but also returns true for a null pointer. */ -static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr) +static __always_inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr) { return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr); } @@ -99,7 +99,7 @@ static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr) * Explicitly cast an error-valued pointer to another pointer type in such a * way as to make it clear that's what's going on. */ -static inline void * __must_check ERR_CAST(__force const void *ptr) +static __always_inline void * __must_check ERR_CAST(__force const void *ptr) { /* cast away the const */ return (void *) ptr; @@ -122,7 +122,7 @@ static inline void * __must_check ERR_CAST(__force const void *ptr) * * Return: The error code within @ptr if it is an error pointer; 0 otherwise. */ -static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr) +static __always_inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr) { if (IS_ERR(ptr)) return PTR_ERR(ptr); diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 829a59399dac..bb2b6cd5d507 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -107,6 +107,7 @@ enum f2fs_error { ERROR_CORRUPTED_XATTR, ERROR_INVALID_NODE_REFERENCE, ERROR_INCONSISTENT_NAT, + ERROR_INCONSISTENT_ORPHAN, ERROR_MAX, }; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4c14aee1fb06..0135c1c6ff06 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1815,6 +1815,11 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm, struct kvm_irq_ack_notifier *kian); bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args); +static inline bool is_gfn_in_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) +{ + return gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages; +} + /* * Returns a pointer to the memslot if it contains gfn. * Otherwise returns NULL. @@ -1825,7 +1830,7 @@ try_get_memslot(struct kvm_memory_slot *slot, gfn_t gfn) if (!slot) return NULL; - if (gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages) + if (is_gfn_in_memslot(slot, gfn)) return slot; else return NULL; diff --git a/include/linux/mm.h b/include/linux/mm.h index fc2acedf0b76..80fce2515930 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -496,6 +496,21 @@ enum { #else #define VM_UFFD_MINOR VM_NONE #endif + +/* + * vma_flags_t masks for the userfaultfd VMA flags. VMA_UFFD_MINOR is gated on + * the same config as VM_UFFD_MINOR -- which implies 64BIT, where the bit fits + * -- so an out-of-range bit is never fed to mk_vma_flags() on a build whose + * bitmap cannot hold it. + */ +#define VMA_UFFD_MISSING mk_vma_flags(VMA_UFFD_MISSING_BIT) +#define VMA_UFFD_WP mk_vma_flags(VMA_UFFD_WP_BIT) +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR +#define VMA_UFFD_MINOR mk_vma_flags(VMA_UFFD_MINOR_BIT) +#else +#define VMA_UFFD_MINOR EMPTY_VMA_FLAGS +#endif + #ifdef CONFIG_64BIT #define VM_ALLOW_ANY_UNCACHED INIT_VM_FLAG(ALLOW_ANY_UNCACHED) #define VM_SEALED INIT_VM_FLAG(SEALED) @@ -1238,6 +1253,30 @@ static __always_inline void vma_flags_set_mask(vma_flags_t *flags, #define vma_flags_set(flags, ...) \ vma_flags_set_mask(flags, mk_vma_flags(__VA_ARGS__)) +static __always_inline vma_flags_t __mk_vma_flags_from_masks(size_t count, + const vma_flags_t *masks) +{ + vma_flags_t flags = EMPTY_VMA_FLAGS; + size_t i; + + for (i = 0; i < count; i++) + vma_flags_set_mask(&flags, masks[i]); + return flags; +} + +/* + * Combine pre-computed vma_flags_t masks into one value, e.g.: + * + * vma_flags_t flags = mk_vma_flags_from_masks(VMA_UFFD_WP, VMA_UFFD_MINOR); + * + * Unlike mk_vma_flags(), which takes bit numbers, this takes whole masks -- + * each of which may be EMPTY_VMA_FLAGS when its feature is unavailable -- so a + * bit that does not exist on the current build is never materialised. + */ +#define mk_vma_flags_from_masks(...) \ + __mk_vma_flags_from_masks(COUNT_ARGS(__VA_ARGS__), \ + (const vma_flags_t []){__VA_ARGS__}) + /* Clear all of the to-clear flags in flags, non-atomically. */ static __always_inline void vma_flags_clear_mask(vma_flags_t *flags, vma_flags_t to_clear) diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 24cb42f66e4b..1c9d40e09107 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2732,6 +2732,9 @@ #define PCI_DEVICE_ID_INTEL_82815_MC 0x1130 #define PCI_DEVICE_ID_INTEL_82815_CGC 0x1132 #define PCI_DEVICE_ID_INTEL_SST_TNG 0x119a +#define PCI_DEVICE_ID_INTEL_DSA_GNRD 0x11fb +#define PCI_DEVICE_ID_INTEL_DSA_DMR 0x1212 +#define PCI_DEVICE_ID_INTEL_IAA_DMR 0x1216 #define PCI_DEVICE_ID_INTEL_82092AA_0 0x1221 #define PCI_DEVICE_ID_INTEL_82437 0x122d #define PCI_DEVICE_ID_INTEL_82371FB_0 0x122e @@ -3052,6 +3055,11 @@ #define PCI_DEVICE_ID_INTEL_5400_FBD1 0x4036 #define PCI_DEVICE_ID_INTEL_HDA_TGL_H 0x43c8 #define PCI_DEVICE_ID_INTEL_HDA_DG1 0x490d +#define PCI_DEVICE_ID_INTEL_QAT_4XXX 0x4940 +#define PCI_DEVICE_ID_INTEL_QAT_401XX 0x4942 +#define PCI_DEVICE_ID_INTEL_QAT_402XX 0x4944 +#define PCI_DEVICE_ID_INTEL_QAT_420XX 0x4946 +#define PCI_DEVICE_ID_INTEL_QAT_6XXX 0x4948 #define PCI_DEVICE_ID_INTEL_HDA_EHL_0 0x4b55 #define PCI_DEVICE_ID_INTEL_HDA_EHL_3 0x4b58 #define PCI_DEVICE_ID_INTEL_HDA_WCL 0x4d28 diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 19f4f253b4f9..937823856de5 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -4,6 +4,7 @@ #ifndef _LINUX_SKMSG_H #define _LINUX_SKMSG_H +#include <linux/bitops.h> #include <linux/bpf.h> #include <linux/filter.h> #include <linux/scatterlist.h> @@ -199,11 +200,14 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, int which, u32 size) { dst->sg.data[which] = src->sg.data[which]; + __assign_bit(which, dst->sg.copy, test_bit(which, src->sg.copy)); dst->sg.data[which].length = size; dst->sg.size += size; src->sg.size -= size; src->sg.data[which].length -= size; src->sg.data[which].offset += size; + if (!src->sg.data[which].length) + __clear_bit(which, src->sg.copy); } static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src) @@ -273,16 +277,19 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state) { do { - if (copy_state) - __set_bit(i, msg->sg.copy); - else - __clear_bit(i, msg->sg.copy); + __assign_bit(i, msg->sg.copy, copy_state); sk_msg_iter_var_next(i); if (i == msg->sg.end) break; } while (1); } +static inline void sk_msg_sg_copy_assign(struct sk_msg *dst, u32 dst_i, + const struct sk_msg *src, u32 src_i) +{ + __assign_bit(dst_i, dst->sg.copy, test_bit(src_i, src->sg.copy)); +} + static inline void sk_msg_sg_copy_set(struct sk_msg *msg, u32 start) { sk_msg_sg_copy(msg, start, true); diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index d2920f98ab86..8d2bfae6b4e6 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -23,8 +23,8 @@ /* The set of all possible UFFD-related VM flags. */ #define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR) -#define __VMA_UFFD_FLAGS mk_vma_flags(VMA_UFFD_MISSING_BIT, VMA_UFFD_WP_BIT, \ - VMA_UFFD_MINOR_BIT) +#define __VMA_UFFD_FLAGS mk_vma_flags_from_masks(VMA_UFFD_MISSING, VMA_UFFD_WP, \ + VMA_UFFD_MINOR) /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index ec65a8cebb99..2bff41aacc98 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -256,6 +256,8 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm, int rtnl_nla_parse_ifinfomsg(struct nlattr **tb, const struct nlattr *nla_peer, struct netlink_ext_ack *exterr); struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid); +bool rtnl_dev_link_net_capable(const struct net_device *dev, + const struct net *link_net); #define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind) diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 876f6a81a9b6..faadcfb9b5e5 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1936,7 +1936,7 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, kfree(ctx.cur_val); if (ret == 1 && ctx.new_updated) { - kfree(*buf); + kvfree(*buf); *buf = ctx.new_val; *pcount = ctx.new_len; } else { diff --git a/kernel/fork.c b/kernel/fork.c index 8ac38beae360..145bcc4c8e12 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2314,6 +2314,7 @@ __latent_entropy struct task_struct *copy_process( #ifdef CONFIG_BLOCK p->plug = NULL; + p->flags &= ~PF_BLOCK_TS; #endif futex_init_task(p); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b8871449d3c6..091ee8d2b17a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5252,6 +5252,12 @@ static struct rq *finish_task_switch(struct task_struct *prev) */ kmap_local_sched_in(); + /* + * Any cached block-layer timestamp (plug->cur_ktime) is stale now, + * invalidate it. + */ + blk_plug_invalidate_ts(); + fire_sched_in_preempt_notifiers(current); /* * When switching through a kernel thread, the loop in @@ -7251,12 +7257,10 @@ static inline void sched_submit_work(struct task_struct *tsk) static void sched_update_worker(struct task_struct *tsk) { - if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER | PF_BLOCK_TS)) { - if (tsk->flags & PF_BLOCK_TS) - blk_plug_invalidate_ts(tsk); + if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) { if (tsk->flags & PF_WQ_WORKER) wq_worker_running(tsk); - else if (tsk->flags & PF_IO_WORKER) + else io_wq_worker_running(tsk); } } @@ -10876,8 +10880,19 @@ static void mm_cid_fixup_cpus_to_tasks(struct mm_struct *mm) } else if (rq->curr->mm == mm && rq->curr->mm_cid.active) { unsigned int cid = rq->curr->mm_cid.cid; - /* Ensure it has the transition bit set */ - if (!cid_in_transit(cid)) { + /* + * Set the transition bit only on a genuine task-owned + * CID. A running active task can legitimately have + * MM_CID_UNSET here: in per-CPU mode CIDs are assigned + * lazily on schedule-in, so the fork()/execve() window + * leaves the task active with no owned CID. Setting the + * transition bit on MM_CID_UNSET would later feed + * clear_bit() an out-of-bounds bit number via + * mm_cid_schedout(), so exclude it. A CPU-owned + * (MM_CID_ONCPU) CID is handled by the cid_on_cpu() + * branch above and never reaches here. + */ + if (cid != MM_CID_UNSET && !cid_in_transit(cid)) { cid = cid_to_transit_cid(cid); rq->curr->mm_cid.cid = cid; pcp->cid = cid; diff --git a/net/9p/client.c b/net/9p/client.c index f0dcf252af7e..4b942d02c29c 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -1092,7 +1092,8 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname, clunk_fid: kfree(wqids); - p9_fid_put(fid); + if (fid != oldfid) + p9_fid_put(fid); fid = NULL; error: diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index b8b1b997960a..6e79f69c2fed 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -311,14 +311,23 @@ batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len, const struct batadv_ogm_packet *ogm_packet) { int next_buff_pos = 0; + u16 tvlv_len; /* check if there is enough space for the header */ next_buff_pos += buff_pos + sizeof(*ogm_packet); if (next_buff_pos > packet_len) return false; + tvlv_len = ntohs(ogm_packet->tvlv_len); + + /* the fields of an aggregated OGM are accessed assuming (at least) + * 2-byte alignment, so a following OGM must start at an even offset. + */ + if (tvlv_len & 1) + return false; + /* check if there is enough space for the optional TVLV */ - next_buff_pos += ntohs(ogm_packet->tvlv_len); + next_buff_pos += tvlv_len; return next_buff_pos <= packet_len; } diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index de9444714264..17d2a1ccdce6 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -817,6 +817,7 @@ void batadv_v_hardif_init(struct batadv_hard_iface *hard_iface) hard_iface->bat_v.aggr_len = 0; skb_queue_head_init(&hard_iface->bat_v.aggr_list); + hard_iface->bat_v.aggr_list_enabled = false; INIT_DELAYED_WORK(&hard_iface->bat_v.aggr_wq, batadv_v_ogm_aggr_work); } diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index d66ca77b1aaa..1f9b2d2b4831 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -252,11 +252,18 @@ static void batadv_v_ogm_queue_on_if(struct batadv_priv *bat_priv, } spin_lock_bh(&hard_iface->bat_v.aggr_list.lock); + if (!hard_iface->bat_v.aggr_list_enabled) { + kfree_skb(skb); + goto unlock; + } + if (!batadv_v_ogm_queue_left(skb, hard_iface)) batadv_v_ogm_aggr_send(bat_priv, hard_iface); hard_iface->bat_v.aggr_len += batadv_v_ogm_len(skb); __skb_queue_tail(&hard_iface->bat_v.aggr_list, skb); + +unlock: spin_unlock_bh(&hard_iface->bat_v.aggr_list.lock); } @@ -417,6 +424,10 @@ int batadv_v_ogm_iface_enable(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface); + spin_lock_bh(&hard_iface->bat_v.aggr_list.lock); + hard_iface->bat_v.aggr_list_enabled = true; + spin_unlock_bh(&hard_iface->bat_v.aggr_list.lock); + batadv_v_ogm_start_queue_timer(hard_iface); batadv_v_ogm_start_timer(bat_priv); @@ -432,6 +443,7 @@ void batadv_v_ogm_iface_disable(struct batadv_hard_iface *hard_iface) cancel_delayed_work_sync(&hard_iface->bat_v.aggr_wq); spin_lock_bh(&hard_iface->bat_v.aggr_list.lock); + hard_iface->bat_v.aggr_list_enabled = false; batadv_v_ogm_aggr_list_free(hard_iface); spin_unlock_bh(&hard_iface->bat_v.aggr_list.lock); } @@ -837,14 +849,23 @@ batadv_v_ogm_aggr_packet(int buff_pos, int packet_len, const struct batadv_ogm2_packet *ogm2_packet) { int next_buff_pos = 0; + u16 tvlv_len; /* check if there is enough space for the header */ next_buff_pos += buff_pos + sizeof(*ogm2_packet); if (next_buff_pos > packet_len) return false; + tvlv_len = ntohs(ogm2_packet->tvlv_len); + + /* the fields of an aggregated OGMv2 are accessed assuming (at least) + * 2-byte alignment, so a following OGMv2 must start at an even offset. + */ + if (tvlv_len & 1) + return false; + /* check if there is enough space for the optional TVLV */ - next_buff_pos += ntohs(ogm2_packet->tvlv_len); + next_buff_pos += tvlv_len; return next_buff_pos <= packet_len; } diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index ffe854018bd3..7f643de42579 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -512,7 +512,7 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, const u8 *orig, return NULL; entry->vid = vid; - entry->lasttime = jiffies; + WRITE_ONCE(entry->lasttime, jiffies); entry->crc = BATADV_BLA_CRC_INIT; entry->bat_priv = bat_priv; spin_lock_init(&entry->crc_lock); @@ -580,7 +580,7 @@ batadv_bla_update_own_backbone_gw(struct batadv_priv *bat_priv, if (unlikely(!backbone_gw)) return; - backbone_gw->lasttime = jiffies; + WRITE_ONCE(backbone_gw->lasttime, jiffies); batadv_backbone_gw_put(backbone_gw); } @@ -714,7 +714,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, ether_addr_copy(claim->addr, mac); spin_lock_init(&claim->backbone_lock); claim->vid = vid; - claim->lasttime = jiffies; + WRITE_ONCE(claim->lasttime, jiffies); kref_get(&backbone_gw->refcount); claim->backbone_gw = backbone_gw; kref_init(&claim->refcount); @@ -736,7 +736,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, return; } } else { - claim->lasttime = jiffies; + WRITE_ONCE(claim->lasttime, jiffies); if (claim->backbone_gw == backbone_gw) /* no need to register a new backbone */ goto claim_free_ref; @@ -769,7 +769,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, spin_lock_bh(&backbone_gw->crc_lock); backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); spin_unlock_bh(&backbone_gw->crc_lock); - backbone_gw->lasttime = jiffies; + WRITE_ONCE(backbone_gw->lasttime, jiffies); claim_free_ref: batadv_claim_put(claim); @@ -858,7 +858,7 @@ static bool batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr, return true; /* handle as ANNOUNCE frame */ - backbone_gw->lasttime = jiffies; + WRITE_ONCE(backbone_gw->lasttime, jiffies); crc = ntohs(*((__force __be16 *)(&an_addr[4]))); batadv_dbg(BATADV_DBG_BLA, bat_priv, @@ -1253,7 +1253,7 @@ static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now) head, hash_entry) { if (now) goto purge_now; - if (!batadv_has_timed_out(backbone_gw->lasttime, + if (!batadv_has_timed_out(READ_ONCE(backbone_gw->lasttime), BATADV_BLA_BACKBONE_TIMEOUT)) continue; @@ -1334,7 +1334,7 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, primary_if->net_dev->dev_addr)) goto skip; - if (!batadv_has_timed_out(claim->lasttime, + if (!batadv_has_timed_out(READ_ONCE(claim->lasttime), BATADV_BLA_CLAIM_TIMEOUT)) goto skip; @@ -1494,7 +1494,7 @@ static void batadv_bla_periodic_work(struct work_struct *work) eth_random_addr(bat_priv->bla.loopdetect_addr); bat_priv->bla.loopdetect_addr[0] = 0xba; bat_priv->bla.loopdetect_addr[1] = 0xbe; - bat_priv->bla.loopdetect_lasttime = jiffies; + WRITE_ONCE(bat_priv->bla.loopdetect_lasttime, jiffies); atomic_set(&bat_priv->bla.loopdetect_next, BATADV_BLA_LOOPDETECT_PERIODS); @@ -1515,7 +1515,7 @@ static void batadv_bla_periodic_work(struct work_struct *work) primary_if->net_dev->dev_addr)) continue; - backbone_gw->lasttime = jiffies; + WRITE_ONCE(backbone_gw->lasttime, jiffies); batadv_bla_send_announce(bat_priv, backbone_gw); if (send_loopdetect) @@ -1899,7 +1899,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, /* If the packet came too late, don't forward it on the mesh * but don't consider that as loop. It might be a coincidence. */ - if (batadv_has_timed_out(bat_priv->bla.loopdetect_lasttime, + if (batadv_has_timed_out(READ_ONCE(bat_priv->bla.loopdetect_lasttime), BATADV_BLA_LOOPDETECT_TIMEOUT)) return true; @@ -2014,7 +2014,7 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, if (own_claim) { /* ... allow it in any case */ - claim->lasttime = jiffies; + WRITE_ONCE(claim->lasttime, jiffies); goto allow; } @@ -2116,7 +2116,7 @@ bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, /* if yes, the client has roamed and we have * to unclaim it. */ - if (batadv_has_timed_out(claim->lasttime, 100)) { + if (batadv_has_timed_out(READ_ONCE(claim->lasttime), 100)) { /* only unclaim if the last claim entry is * older than 100 ms to make sure we really * have a roaming client here. @@ -2361,7 +2361,7 @@ batadv_bla_backbone_dump_entry(struct sk_buff *msg, u32 portid, backbone_crc = backbone_gw->crc; spin_unlock_bh(&backbone_gw->crc_lock); - msecs = jiffies_to_msecs(jiffies - backbone_gw->lasttime); + msecs = jiffies_to_msecs(jiffies - READ_ONCE(backbone_gw->lasttime)); if (is_own) if (nla_put_flag(msg, BATADV_ATTR_BLA_OWN)) { diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 0a8bd95e2f99..86fb5de5022a 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -214,10 +214,13 @@ static void batadv_dat_purge(struct work_struct *work) */ static bool batadv_compare_dat(const struct hlist_node *node, const void *data2) { - const void *data1 = container_of(node, struct batadv_dat_entry, - hash_entry); + const struct batadv_dat_entry *entry1; + const struct batadv_dat_entry *entry2; - return memcmp(data1, data2, sizeof(__be32)) == 0; + entry1 = container_of(node, struct batadv_dat_entry, hash_entry); + entry2 = data2; + + return entry1->ip == entry2->ip && entry1->vid == entry2->vid; } /** @@ -344,6 +347,9 @@ batadv_dat_entry_hash_find(struct batadv_priv *bat_priv, __be32 ip, if (dat_entry->ip != ip) continue; + if (dat_entry->vid != vid) + continue; + if (!kref_get_unless_zero(&dat_entry->refcount)) continue; diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index e9553db42349..9a5927ecc474 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -384,6 +384,8 @@ out_err: * @skb: skb to forward * @recv_if: interface that the skb is received on * @orig_node_src: originator that the skb is received from + * @rx_result: set to NET_RX_SUCCESS when the fragment was forwarded and + * NET_RX_DROP when it was dropped; only valid when true is returned * * Look up the next-hop of the fragments payload and check if the merged packet * will exceed the MTU towards the next-hop. If so, the fragment is forwarded @@ -393,7 +395,8 @@ out_err: */ bool batadv_frag_skb_fwd(struct sk_buff *skb, struct batadv_hard_iface *recv_if, - struct batadv_orig_node *orig_node_src) + struct batadv_orig_node *orig_node_src, + int *rx_result) { struct batadv_priv *bat_priv = netdev_priv(recv_if->mesh_iface); struct batadv_neigh_node *neigh_node = NULL; @@ -412,12 +415,29 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb, */ total_size = ntohs(packet->total_size); if (total_size > neigh_node->if_incoming->net_dev->mtu) { + if (packet->ttl < 2) { + kfree_skb(skb); + *rx_result = NET_RX_DROP; + ret = true; + goto out; + } + + if (skb_cow(skb, ETH_HLEN) < 0) { + kfree_skb(skb); + *rx_result = NET_RX_DROP; + ret = true; + goto out; + } + + packet = (struct batadv_frag_packet *)skb->data; + batadv_inc_counter(bat_priv, BATADV_CNT_FRAG_FWD); batadv_add_counter(bat_priv, BATADV_CNT_FRAG_FWD_BYTES, skb->len + ETH_HLEN); packet->ttl--; batadv_send_unicast_skb(skb, neigh_node); + *rx_result = NET_RX_SUCCESS; ret = true; } diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h index dbf0871f8703..51e281027ab6 100644 --- a/net/batman-adv/fragmentation.h +++ b/net/batman-adv/fragmentation.h @@ -19,7 +19,8 @@ void batadv_frag_purge_orig(struct batadv_orig_node *orig, bool (*check_cb)(struct batadv_frag_table_entry *)); bool batadv_frag_skb_fwd(struct sk_buff *skb, struct batadv_hard_iface *recv_if, - struct batadv_orig_node *orig_node_src); + struct batadv_orig_node *orig_node_src, + int *rx_result); bool batadv_frag_skb_buffer(struct sk_buff **skb, struct batadv_orig_node *orig_node); int batadv_frag_send_packet(struct sk_buff *skb, diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index d6732c34aeaf..c7dbd24ea199 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -787,30 +787,6 @@ err_dev: } /** - * batadv_hardif_cnt() - get number of interfaces enslaved to mesh interface - * @mesh_iface: mesh interface to check - * - * This function is only using RCU for locking - the result can therefore be - * off when another function is modifying the list at the same time. The - * caller can use the rtnl_lock to make sure that the count is accurate. - * - * Return: number of connected/enslaved hard interfaces - */ -static size_t batadv_hardif_cnt(struct net_device *mesh_iface) -{ - struct batadv_hard_iface *hard_iface; - struct list_head *iter; - size_t count = 0; - - rcu_read_lock(); - netdev_for_each_lower_private_rcu(mesh_iface, hard_iface, iter) - count++; - rcu_read_unlock(); - - return count; -} - -/** * batadv_hardif_disable_interface() - Remove hard interface from mesh interface * @hard_iface: hard interface to be removed */ @@ -850,8 +826,8 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface) netdev_upper_dev_unlink(hard_iface->net_dev, hard_iface->mesh_iface); batadv_hardif_recalc_extra_skbroom(hard_iface->mesh_iface); - /* nobody uses this interface anymore */ - if (batadv_hardif_cnt(hard_iface->mesh_iface) <= 1) + /* nobody uses this mesh interface anymore */ + if (list_empty(&hard_iface->mesh_iface->adj_list.lower)) batadv_gw_check_client_stop(bat_priv); hard_iface->mesh_iface = NULL; diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 78c651f634cd..1d144d8cc092 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -917,9 +917,15 @@ static int batadv_netlink_set_hardif(struct sk_buff *skb, #ifdef CONFIG_BATMAN_ADV_BATMAN_V if (info->attrs[BATADV_ATTR_ELP_INTERVAL]) { + u32 elp_interval; + attr = info->attrs[BATADV_ATTR_ELP_INTERVAL]; + elp_interval = nla_get_u32(attr); + + elp_interval = min_t(u32, elp_interval, INT_MAX); + elp_interval = max_t(u32, elp_interval, BATADV_JITTER); - atomic_set(&hard_iface->bat_v.elp_interval, nla_get_u32(attr)); + atomic_set(&hard_iface->bat_v.elp_interval, elp_interval); } if (info->attrs[BATADV_ATTR_THROUGHPUT_OVERRIDE]) { diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 12c16f81cc51..41951c7a1c50 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -8,6 +8,7 @@ #include "main.h" #include <linux/atomic.h> +#include <linux/build_bug.h> #include <linux/byteorder/generic.h> #include <linux/compiler.h> #include <linux/errno.h> @@ -205,6 +206,59 @@ bool batadv_check_management_packet(struct sk_buff *skb, } /** + * batadv_skb_decrement_ttl() - decrement ttl in a batman-adv header, csum-safe + * @skb: the received packet with @skb->data pointing to the batman-adv header + * + * Supports the following packet types, all of which carry the TTL at offset 2: + * + * - batadv_ogm_packet + * - batadv_ogm2_packet + * - batadv_icmp_header + * - batadv_icmp_packet + * - batadv_icmp_tp_packet + * - batadv_icmp_packet_rr + * - batadv_unicast_packet + * - batadv_frag_packet + * - batadv_bcast_packet + * - batadv_mcast_packet + * - batadv_coded_packet + * - batadv_unicast_tvlv_packet + * + * Return: true if the packet may be forwarded (ttl decremented), + * false if it must be dropped (ttl would expire) + */ +static bool batadv_skb_decrement_ttl(struct sk_buff *skb) +{ + static const size_t ttl_offset = 2; + u8 *ttl_pos; + + BUILD_BUG_ON(offsetof(struct batadv_ogm_packet, ttl) != ttl_offset); + BUILD_BUG_ON(offsetof(struct batadv_ogm2_packet, ttl) != ttl_offset); + BUILD_BUG_ON(offsetof(struct batadv_icmp_header, ttl) != ttl_offset); + BUILD_BUG_ON(offsetof(struct batadv_icmp_packet, ttl) != ttl_offset); + BUILD_BUG_ON(offsetof(struct batadv_icmp_tp_packet, ttl) != ttl_offset); + BUILD_BUG_ON(offsetof(struct batadv_icmp_packet_rr, ttl) != ttl_offset); + BUILD_BUG_ON(offsetof(struct batadv_unicast_packet, ttl) != ttl_offset); + BUILD_BUG_ON(offsetof(struct batadv_frag_packet, ttl) != ttl_offset); + BUILD_BUG_ON(offsetof(struct batadv_bcast_packet, ttl) != ttl_offset); + BUILD_BUG_ON(offsetof(struct batadv_mcast_packet, ttl) != ttl_offset); + BUILD_BUG_ON(offsetof(struct batadv_coded_packet, ttl) != ttl_offset); + BUILD_BUG_ON(offsetof(struct batadv_unicast_tvlv_packet, ttl) != ttl_offset); + + ttl_pos = skb->data + ttl_offset; + + /* would expire on this hop -> drop, leave header + csum untouched */ + if (*ttl_pos < 2) + return false; + + skb_postpull_rcsum(skb, ttl_pos, 1); + (*ttl_pos)--; + skb_postpush_rcsum(skb, ttl_pos, 1); + + return true; +} + +/** * batadv_recv_my_icmp_packet() - receive an icmp packet locally * @bat_priv: the bat priv with all the mesh interface information * @skb: icmp packet to process @@ -1114,10 +1168,9 @@ int batadv_recv_frag_packet(struct sk_buff *skb, /* Route the fragment if it is not for us and too big to be merged. */ if (!batadv_is_my_mac(bat_priv, frag_packet->dest) && - batadv_frag_skb_fwd(skb, recv_if, orig_node_src)) { + batadv_frag_skb_fwd(skb, recv_if, orig_node_src, &ret)) { /* skb was consumed */ skb = NULL; - ret = NET_RX_SUCCESS; goto put_orig_node; } @@ -1191,7 +1244,13 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, if (batadv_is_my_mac(bat_priv, bcast_packet->orig)) goto free_skb; - if (bcast_packet->ttl-- < 2) + /* create a copy of the skb, if needed, to modify it. */ + if (skb_cow(skb, ETH_HLEN) < 0) + goto free_skb; + + bcast_packet = (struct batadv_bcast_packet *)skb->data; + + if (!batadv_skb_decrement_ttl(skb)) goto free_skb; orig_node = batadv_orig_hash_find(bat_priv, bcast_packet->orig); @@ -1298,7 +1357,7 @@ int batadv_recv_mcast_packet(struct sk_buff *skb, goto free_skb; mcast_packet = (struct batadv_mcast_packet *)skb->data; - if (mcast_packet->ttl-- < 2) + if (!batadv_skb_decrement_ttl(skb)) goto free_skb; tvlv_buff = (unsigned char *)(skb->data + hdr_size); @@ -1307,6 +1366,12 @@ int batadv_recv_mcast_packet(struct sk_buff *skb, if (tvlv_buff_len > skb->len - hdr_size) goto free_skb; + /* the fields of an multicast payload are accessed assuming (at least) + * 2-byte alignment, so a following packet must start at an even offset. + */ + if (tvlv_buff_len & 1) + goto free_skb; + ret = batadv_tvlv_containers_process(bat_priv, BATADV_MCAST, NULL, skb, tvlv_buff, tvlv_buff_len); if (ret >= 0) { diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 0fc4ca78e84e..dbaae33db0f1 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -87,6 +87,11 @@ #define BATADV_TP_PLEN (BATADV_TP_PACKET_LEN - ETH_HLEN - \ sizeof(struct batadv_unicast_packet)) +/** + * BATADV_TP_MAX_UNACKED - maximum number of packets a receiver didn't yet ack + */ +#define BATADV_TP_MAX_UNACKED 100 + static u8 batadv_tp_prerandom[4096] __read_mostly; /** @@ -154,9 +159,12 @@ static void batadv_tp_update_cwnd(struct batadv_tp_vars *tp_vars, u32 mss) return; } + /* prevent overflow in (mss * mss) << 3 */ + mss = min_t(u32, mss, (1U << 14) - 1); + /* increment CWND at least of 1 (section 3.1 of RFC5681) */ tp_vars->dec_cwnd += max_t(u32, 1U << 3, - ((mss * mss) << 6) / (tp_vars->cwnd << 3)); + ((mss * mss) << 3) / tp_vars->cwnd); if (tp_vars->dec_cwnd < (mss << 3)) { spin_unlock_bh(&tp_vars->cwnd_lock); return; @@ -730,7 +738,7 @@ static void batadv_tp_recv_ack(struct batadv_priv *bat_priv, if (atomic_read(&tp_vars->dup_acks) != 3) goto out; - if (recv_ack >= tp_vars->recover) + if (!batadv_seq_before(tp_vars->recover, recv_ack)) goto out; /* if this is the third duplicate ACK do Fast Retransmit */ @@ -817,10 +825,15 @@ out: static bool batadv_tp_avail(struct batadv_tp_vars *tp_vars, size_t payload_len) { + u32 last_sent = READ_ONCE(tp_vars->last_sent); u32 win_left, win_limit; win_limit = atomic_read(&tp_vars->last_acked) + tp_vars->cwnd; - win_left = win_limit - tp_vars->last_sent; + + if (batadv_seq_before(last_sent, win_limit)) + win_left = win_limit - last_sent; + else + win_left = 0; return win_left >= payload_len; } @@ -1045,6 +1058,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, tp_vars->icmp_uid = icmp_uid; tp_vars->last_sent = BATADV_TP_FIRST_SEQ; + atomic_set(&tp_vars->dup_acks, 0); atomic_set(&tp_vars->last_acked, BATADV_TP_FIRST_SEQ); tp_vars->fast_recovery = false; tp_vars->recover = BATADV_TP_FIRST_SEQ; @@ -1054,6 +1068,8 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, * mesh_interface, hence its MTU */ tp_vars->cwnd = BATADV_TP_PLEN * 3; + tp_vars->dec_cwnd = 0; + /* at the beginning initialise the SS threshold to the biggest possible * window size, hence the AWND size */ @@ -1085,21 +1101,21 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, tp_vars->prerandom_offset = 0; spin_lock_init(&tp_vars->prerandom_lock); - kref_get(&tp_vars->refcount); - hlist_add_head_rcu(&tp_vars->list, &bat_priv->tp_list); - spin_unlock_bh(&bat_priv->tp_list_lock); - tp_vars->test_length = test_length; if (!tp_vars->test_length) tp_vars->test_length = BATADV_TP_DEF_TEST_LENGTH; + /* init work item for finished tp tests */ + INIT_DELAYED_WORK(&tp_vars->finish_work, batadv_tp_sender_finish); + + kref_get(&tp_vars->refcount); + hlist_add_head_rcu(&tp_vars->list, &bat_priv->tp_list); + spin_unlock_bh(&bat_priv->tp_list_lock); + batadv_dbg(BATADV_DBG_TP_METER, bat_priv, "Meter: starting throughput meter towards %pM (length=%ums)\n", dst, test_length); - /* init work item for finished tp tests */ - INIT_DELAYED_WORK(&tp_vars->finish_work, batadv_tp_sender_finish); - /* start tp kthread. This way the write() call issued from userspace can * happily return and avoid to block */ @@ -1167,7 +1183,7 @@ static void batadv_tp_receiver_shutdown(struct timer_list *t) bat_priv = tp_vars->bat_priv; /* if there is recent activity rearm the timer */ - if (!batadv_has_timed_out(tp_vars->last_recv_time, + if (!batadv_has_timed_out(READ_ONCE(tp_vars->last_recv_time), BATADV_TP_RECV_TIMEOUT)) { /* reset the receiver shutdown timer */ batadv_tp_reset_receiver_timer(tp_vars); @@ -1184,6 +1200,7 @@ static void batadv_tp_receiver_shutdown(struct timer_list *t) list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) { list_del(&un->list); kfree(un); + tp_vars->unacked_count--; } spin_unlock_bh(&tp_vars->unacked_lock); @@ -1267,7 +1284,8 @@ out: /** * batadv_tp_handle_out_of_order() - store an out of order packet * @tp_vars: the private data of the current TP meter session - * @skb: the buffer containing the received packet + * @seqno: sequence number of new received packet + * @payload_len: length of the received packet * * Store the out of order packet in the unacked list for late processing. This * packets are kept in this list so that they can be ACKed at once as soon as @@ -1276,28 +1294,24 @@ out: * Return: true if the packed has been successfully processed, false otherwise */ static bool batadv_tp_handle_out_of_order(struct batadv_tp_vars *tp_vars, - const struct sk_buff *skb) + u32 seqno, u32 payload_len) + __must_hold(&tp_vars->unacked_lock) { - const struct batadv_icmp_tp_packet *icmp; struct batadv_tp_unacked *un, *new; - u32 payload_len; bool added = false; new = kmalloc_obj(*new, GFP_ATOMIC); if (unlikely(!new)) return false; - icmp = (struct batadv_icmp_tp_packet *)skb->data; - - new->seqno = ntohl(icmp->seqno); - payload_len = skb->len - sizeof(struct batadv_unicast_packet); + new->seqno = seqno; new->len = payload_len; - spin_lock_bh(&tp_vars->unacked_lock); /* if the list is empty immediately attach this new object */ if (list_empty(&tp_vars->unacked_list)) { list_add(&new->list, &tp_vars->unacked_list); - goto out; + tp_vars->unacked_count++; + return true; } /* otherwise loop over the list and either drop the packet because this @@ -1325,17 +1339,26 @@ static bool batadv_tp_handle_out_of_order(struct batadv_tp_vars *tp_vars, * one is attached _after_ it. In this way the list is kept in * ascending order */ - list_add_tail(&new->list, &un->list); + list_add(&new->list, &un->list); added = true; + tp_vars->unacked_count++; break; } /* received packet with smallest seqno out of order; add it to front */ - if (!added) + if (!added) { list_add(&new->list, &tp_vars->unacked_list); + tp_vars->unacked_count++; + } -out: - spin_unlock_bh(&tp_vars->unacked_lock); + /* remove the last (biggest) unacked seqno when list is too large */ + if (tp_vars->unacked_count > BATADV_TP_MAX_UNACKED) { + un = list_last_entry(&tp_vars->unacked_list, + struct batadv_tp_unacked, list); + list_del(&un->list); + kfree(un); + tp_vars->unacked_count--; + } return true; } @@ -1346,6 +1369,7 @@ out: * @tp_vars: the private data of the current TP meter session */ static void batadv_tp_ack_unordered(struct batadv_tp_vars *tp_vars) + __must_hold(&tp_vars->unacked_lock) { struct batadv_tp_unacked *un, *safe; u32 to_ack; @@ -1353,7 +1377,6 @@ static void batadv_tp_ack_unordered(struct batadv_tp_vars *tp_vars) /* go through the unacked packet list and possibly ACK them as * well */ - spin_lock_bh(&tp_vars->unacked_lock); list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) { /* the list is ordered, therefore it is possible to stop as soon * there is a gap between the last acked seqno and the seqno of @@ -1369,8 +1392,8 @@ static void batadv_tp_ack_unordered(struct batadv_tp_vars *tp_vars) list_del(&un->list); kfree(un); + tp_vars->unacked_count--; } - spin_unlock_bh(&tp_vars->unacked_lock); } /** @@ -1392,8 +1415,10 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv, tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig, icmp->session, BATADV_TP_RECEIVER); - if (tp_vars) + if (tp_vars) { + WRITE_ONCE(tp_vars->last_recv_time, jiffies); goto out_unlock; + } if (!atomic_add_unless(&bat_priv->tp_num, 1, BATADV_TP_MAX_NUM)) { batadv_dbg(BATADV_DBG_TP_METER, bat_priv, @@ -1417,12 +1442,15 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv, spin_lock_init(&tp_vars->unacked_lock); INIT_LIST_HEAD(&tp_vars->unacked_list); + tp_vars->unacked_count = 0; kref_get(&tp_vars->refcount); - hlist_add_head_rcu(&tp_vars->list, &bat_priv->tp_list); + timer_setup(&tp_vars->timer, batadv_tp_receiver_shutdown, 0); + + WRITE_ONCE(tp_vars->last_recv_time, jiffies); kref_get(&tp_vars->refcount); - timer_setup(&tp_vars->timer, batadv_tp_receiver_shutdown, 0); + hlist_add_head_rcu(&tp_vars->list, &bat_priv->tp_list); batadv_tp_reset_receiver_timer(tp_vars); @@ -1444,7 +1472,8 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv, { const struct batadv_icmp_tp_packet *icmp; struct batadv_tp_vars *tp_vars; - size_t packet_size; + u32 payload_len; + u32 to_ack; u32 seqno; icmp = (struct batadv_icmp_tp_packet *)skb->data; @@ -1469,41 +1498,49 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv, icmp->orig); goto out; } + + WRITE_ONCE(tp_vars->last_recv_time, jiffies); } - tp_vars->last_recv_time = jiffies; + spin_lock_bh(&tp_vars->unacked_lock); /* if the packet is a duplicate, it may be the case that an ACK has been * lost. Resend the ACK */ - if (batadv_seq_before(seqno, tp_vars->last_recv)) + payload_len = skb->len - sizeof(struct batadv_unicast_packet); + to_ack = seqno + payload_len; + if (batadv_seq_before(to_ack, tp_vars->last_recv)) goto send_ack; /* if the packet is out of order enqueue it */ - if (ntohl(icmp->seqno) != tp_vars->last_recv) { + if (batadv_seq_before(tp_vars->last_recv, seqno)) { /* exit immediately (and do not send any ACK) if the packet has * not been enqueued correctly */ - if (!batadv_tp_handle_out_of_order(tp_vars, skb)) + if (!batadv_tp_handle_out_of_order(tp_vars, seqno, payload_len)) { + spin_unlock_bh(&tp_vars->unacked_lock); goto out; + } /* send a duplicate ACK */ goto send_ack; } /* if everything was fine count the ACKed bytes */ - packet_size = skb->len - sizeof(struct batadv_unicast_packet); - tp_vars->last_recv += packet_size; + tp_vars->last_recv = to_ack; /* check if this ordered message filled a gap.... */ batadv_tp_ack_unordered(tp_vars); send_ack: + to_ack = tp_vars->last_recv; + spin_unlock_bh(&tp_vars->unacked_lock); + /* send the ACK. If the received packet was out of order, the ACK that * is going to be sent is a duplicate (the sender will count them and * possibly enter Fast Retransmit as soon as it has reached 3) */ - batadv_tp_send_ack(bat_priv, icmp->orig, tp_vars->last_recv, + batadv_tp_send_ack(bat_priv, icmp->orig, to_ack, icmp->timestamp, icmp->session, icmp->uid); out: batadv_tp_vars_put(tp_vars); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 9f6e67771ffa..83dfd804a143 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -446,6 +446,9 @@ static void batadv_tt_local_event(struct batadv_priv *bat_priv, if (!batadv_compare_eth(entry->change.addr, common->addr)) continue; + if (entry->change.vid != tt_change_node->change.vid) + continue; + del_op_entry = entry->change.flags & BATADV_TT_CLIENT_DEL; if (del_op_requested != del_op_entry) { /* DEL+ADD in the same orig interval have no effect and @@ -3439,6 +3442,7 @@ static void batadv_tt_roam_purge(struct batadv_priv *bat_priv) * batadv_tt_check_roam_count() - check if a client has roamed too frequently * @bat_priv: the bat priv with all the mesh interface information * @client: mac address of the roaming client + * @vid: VLAN identifier * * This function checks whether the client already reached the * maximum number of possible roaming phases. In this case the ROAMING_ADV @@ -3446,7 +3450,7 @@ static void batadv_tt_roam_purge(struct batadv_priv *bat_priv) * * Return: true if the ROAMING_ADV can be sent, false otherwise */ -static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, u8 *client) +static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, u8 *client, u16 vid) { struct batadv_tt_roam_node *tt_roam_node; bool ret = false; @@ -3459,6 +3463,9 @@ static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, u8 *client) if (!batadv_compare_eth(tt_roam_node->addr, client)) continue; + if (tt_roam_node->vid != vid) + continue; + if (batadv_has_timed_out(tt_roam_node->first_time, BATADV_ROAMING_MAX_TIME)) continue; @@ -3480,6 +3487,7 @@ static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, u8 *client) atomic_set(&tt_roam_node->counter, BATADV_ROAMING_MAX_COUNT - 1); ether_addr_copy(tt_roam_node->addr, client); + tt_roam_node->vid = vid; list_add(&tt_roam_node->list, &bat_priv->tt.roam_list); ret = true; @@ -3516,7 +3524,7 @@ static void batadv_send_roam_adv(struct batadv_priv *bat_priv, u8 *client, /* before going on we have to check whether the client has * already roamed to us too many times */ - if (!batadv_tt_check_roam_count(bat_priv, client)) + if (!batadv_tt_check_roam_count(bat_priv, client, vid)) goto out; batadv_dbg(BATADV_DBG_TT, bat_priv, diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index cc6ac580c620..afb61a46d7a6 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -398,7 +398,6 @@ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv, tvlv_handler->ogm_handler(bat_priv, orig_node, BATADV_NO_FLAGS, tvlv_value, tvlv_value_len); - tvlv_handler->flags |= BATADV_TVLV_HANDLER_OGM_CALLED; break; case BATADV_UNICAST_TVLV: if (!skb) @@ -431,6 +430,48 @@ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv, } /** + * batadv_tvlv_containers_contain() - check if a tvlv buffer holds a container + * @tvlv_value: tvlv content + * @tvlv_value_len: tvlv content length + * @type: tvlv container type to look for + * @version: tvlv container version to look for + * + * Return: true if a container of the given type and version is present in the + * tvlv buffer, false otherwise. + */ +static bool batadv_tvlv_containers_contain(void *tvlv_value, + u16 tvlv_value_len, u8 type, + u8 version) +{ + struct batadv_tvlv_hdr *tvlv_hdr; + u16 tvlv_value_cont_len; + + while (tvlv_value_len >= sizeof(*tvlv_hdr)) { + tvlv_hdr = tvlv_value; + tvlv_value_cont_len = ntohs(tvlv_hdr->len); + tvlv_value = tvlv_hdr + 1; + tvlv_value_len -= sizeof(*tvlv_hdr); + + if (tvlv_value_cont_len > tvlv_value_len) + break; + + /* the next tvlv header is accessed assuming (at least) 2-byte + * alignment, so it must start at an even offset. + */ + if (tvlv_value_cont_len & 1) + break; + + if (tvlv_hdr->type == type && tvlv_hdr->version == version) + return true; + + tvlv_value = (u8 *)tvlv_value + tvlv_value_cont_len; + tvlv_value_len -= tvlv_value_cont_len; + } + + return false; +} + +/** * batadv_tvlv_containers_process() - parse the given tvlv buffer to call the * appropriate handlers * @bat_priv: the bat priv with all the mesh interface information @@ -449,7 +490,9 @@ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv, struct sk_buff *skb, void *tvlv_value, u16 tvlv_value_len) { + u16 tvlv_value_start_len = tvlv_value_len; struct batadv_tvlv_handler *tvlv_handler; + void *tvlv_value_start = tvlv_value; struct batadv_tvlv_hdr *tvlv_hdr; u16 tvlv_value_cont_len; u8 cifnotfound = BATADV_TVLV_HANDLER_OGM_CIFNOTFND; @@ -464,6 +507,12 @@ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv, if (tvlv_value_cont_len > tvlv_value_len) break; + /* the next tvlv header is accessed assuming (at least) 2-byte + * alignment, so it must start at an even offset. + */ + if (tvlv_value_cont_len & 1) + break; + tvlv_handler = batadv_tvlv_handler_get(bat_priv, tvlv_hdr->type, tvlv_hdr->version); @@ -487,12 +536,20 @@ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv, if (!tvlv_handler->ogm_handler) continue; - if ((tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) && - !(tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CALLED)) - tvlv_handler->ogm_handler(bat_priv, orig_node, - cifnotfound, NULL, 0); + if (!(tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND)) + continue; + + /* if the corresponding container was present then the handler + * was already called from the loop above + */ + if (batadv_tvlv_containers_contain(tvlv_value_start, + tvlv_value_start_len, + tvlv_handler->type, + tvlv_handler->version)) + continue; - tvlv_handler->flags &= ~BATADV_TVLV_HANDLER_OGM_CALLED; + tvlv_handler->ogm_handler(bat_priv, orig_node, + cifnotfound, NULL, 0); } rcu_read_unlock(); diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index a01ee46d97f3..30c870cacf43 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -130,6 +130,12 @@ struct batadv_hard_iface_bat_v { /** @aggr_list: queue for to be aggregated OGM packets */ struct sk_buff_head aggr_list; + /** + * @aggr_list_enabled: aggr_list is active and new skbs can be + * enqueued. Protected by aggr_list.lock after initialization + */ + bool aggr_list_enabled:1; + /** @aggr_len: size of the OGM aggregate (excluding ethernet header) */ unsigned int aggr_len; @@ -1417,9 +1423,12 @@ struct batadv_tp_vars { /** @unacked_list: list of unacked packets (meta-info only) */ struct list_head unacked_list; - /** @unacked_lock: protect unacked_list */ + /** @unacked_lock: protect unacked_list + &batadv_tp_receiver.last_recv */ spinlock_t unacked_lock; + /** @unacked_count: number of unacked entries */ + size_t unacked_count; + /** @last_recv_time: time (jiffies) a msg was received */ unsigned long last_recv_time; @@ -1903,6 +1912,9 @@ struct batadv_tt_roam_node { /** @addr: mac address of the client in the roaming phase */ u8 addr[ETH_ALEN]; + /** @vid: VLAN identifier */ + u16 vid; + /** * @counter: number of allowed roaming events per client within a single * OGM interval (changes are committed with each OGM) @@ -2233,13 +2245,6 @@ enum batadv_tvlv_handler_flags { * will call this handler even if its type was not found (with no data) */ BATADV_TVLV_HANDLER_OGM_CIFNOTFND = BIT(1), - - /** - * @BATADV_TVLV_HANDLER_OGM_CALLED: interval tvlv handling flag - the - * API marks a handler as being called, so it won't be called if the - * BATADV_TVLV_HANDLER_OGM_CIFNOTFND flag was set - */ - BATADV_TVLV_HANDLER_OGM_CALLED = BIT(2), }; #endif /* _NET_BATMAN_ADV_TYPES_H_ */ diff --git a/net/core/filter.c b/net/core/filter.c index 80439767e0ee..40037413dd4e 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2733,11 +2733,13 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, poffset += len; sge->length = 0; put_page(sg_page(sge)); + __clear_bit(i, msg->sg.copy); sk_msg_iter_var_next(i); } while (i != last_sge); sg_set_page(&msg->sg.data[first_sge], page, copy, 0); + __clear_bit(first_sge, msg->sg.copy); /* To repair sg ring we need to shift entries. If we only * had a single entry though we can just replace it and @@ -2763,9 +2765,11 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, break; msg->sg.data[i] = msg->sg.data[move_from]; + sk_msg_sg_copy_assign(msg, i, msg, move_from); msg->sg.data[move_from].length = 0; msg->sg.data[move_from].page_link = 0; msg->sg.data[move_from].offset = 0; + __clear_bit(move_from, msg->sg.copy); sk_msg_iter_var_next(i); } while (1); @@ -2794,6 +2798,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, { struct scatterlist sge, nsge, nnsge, rsge = {0}, *psge; u32 new, i = 0, l = 0, space, copy = 0, offset = 0; + bool sge_copy, nsge_copy, nnsge_copy, rsge_copy = false; u8 *raw, *to, *from; struct page *page; @@ -2866,6 +2871,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, sk_msg_iter_var_prev(i); psge = sk_msg_elem(msg, i); rsge = sk_msg_elem_cpy(msg, i); + rsge_copy = test_bit(i, msg->sg.copy); psge->length = start - offset; rsge.length -= psge->length; @@ -2890,24 +2896,32 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, /* Shift one or two slots as needed */ sge = sk_msg_elem_cpy(msg, new); + sge_copy = test_bit(new, msg->sg.copy); sg_unmark_end(&sge); nsge = sk_msg_elem_cpy(msg, i); + nsge_copy = test_bit(i, msg->sg.copy); if (rsge.length) { sk_msg_iter_var_next(i); nnsge = sk_msg_elem_cpy(msg, i); + nnsge_copy = test_bit(i, msg->sg.copy); sk_msg_iter_next(msg, end); } while (i != msg->sg.end) { msg->sg.data[i] = sge; + __assign_bit(i, msg->sg.copy, sge_copy); sge = nsge; + sge_copy = nsge_copy; sk_msg_iter_var_next(i); if (rsge.length) { nsge = nnsge; + nsge_copy = nnsge_copy; nnsge = sk_msg_elem_cpy(msg, i); + nnsge_copy = test_bit(i, msg->sg.copy); } else { nsge = sk_msg_elem_cpy(msg, i); + nsge_copy = test_bit(i, msg->sg.copy); } } @@ -2921,6 +2935,7 @@ place_new: get_page(sg_page(&rsge)); sk_msg_iter_var_next(new); msg->sg.data[new] = rsge; + __assign_bit(new, msg->sg.copy, rsge_copy); } sk_msg_reset_curr(msg); @@ -2948,25 +2963,33 @@ static void sk_msg_shift_left(struct sk_msg *msg, int i) prev = i; sk_msg_iter_var_next(i); msg->sg.data[prev] = msg->sg.data[i]; + sk_msg_sg_copy_assign(msg, prev, msg, i); } while (i != msg->sg.end); sk_msg_iter_prev(msg, end); + __clear_bit(msg->sg.end, msg->sg.copy); } static void sk_msg_shift_right(struct sk_msg *msg, int i) { struct scatterlist tmp, sge; + bool tmp_copy, sge_copy; sk_msg_iter_next(msg, end); sge = sk_msg_elem_cpy(msg, i); + sge_copy = test_bit(i, msg->sg.copy); sk_msg_iter_var_next(i); tmp = sk_msg_elem_cpy(msg, i); + tmp_copy = test_bit(i, msg->sg.copy); while (i != msg->sg.end) { msg->sg.data[i] = sge; + __assign_bit(i, msg->sg.copy, sge_copy); sk_msg_iter_var_next(i); sge = tmp; + sge_copy = tmp_copy; tmp = sk_msg_elem_cpy(msg, i); + tmp_copy = test_bit(i, msg->sg.copy); } } @@ -3026,6 +3049,8 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, struct scatterlist *nsge, *sge = sk_msg_elem(msg, i); int a = start - offset; int b = sge->length - pop - a; + u32 sge_i = i; + bool sge_copy = test_bit(i, msg->sg.copy); sk_msg_iter_var_next(i); @@ -3038,6 +3063,7 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, sg_set_page(nsge, sg_page(sge), b, sge->offset + pop + a); + __assign_bit(i, msg->sg.copy, sge_copy); } else { struct page *page, *orig; u8 *to, *from; @@ -3054,6 +3080,7 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, memcpy(to, from, a); memcpy(to + a, from + a + pop, b); sg_set_page(sge, page, a + b, 0); + __clear_bit(sge_i, msg->sg.copy); put_page(orig); } pop = 0; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 511c25bf6f2a..3be5f264f5ad 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2421,6 +2421,14 @@ struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid) } EXPORT_SYMBOL_GPL(rtnl_get_net_ns_capable); +bool rtnl_dev_link_net_capable(const struct net_device *dev, + const struct net *link_net) +{ + return net_eq(link_net, dev_net(dev)) || + ns_capable(link_net->user_ns, CAP_NET_ADMIN); +} +EXPORT_SYMBOL_GPL(rtnl_dev_link_net_capable); + static int rtnl_valid_dump_ifinfo_req(const struct nlmsghdr *nlh, bool strict_check, struct nlattr **tb, struct netlink_ext_ack *extack) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index e1850caf1a71..30c3b9a2681c 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -66,6 +66,7 @@ int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len, sge = &msg->sg.data[msg->sg.end]; sg_unmark_end(sge); sg_set_page(sge, pfrag->page, use, orig_offset); + __clear_bit(msg->sg.end, msg->sg.copy); get_page(pfrag->page); sk_msg_iter_next(msg, end); } @@ -186,6 +187,7 @@ static int sk_msg_free_elem(struct sock *sk, struct sk_msg *msg, u32 i, sk_mem_uncharge(sk, len); put_page(sg_page(sge)); } + __clear_bit(i, msg->sg.copy); memset(sge, 0, sizeof(*sge)); return len; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 169e2921a851..0ebed1438f6c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1457,6 +1457,9 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], __u32 fwmark = t->fwmark; int err; + if (!rtnl_dev_link_net_capable(dev, t->net)) + return -EPERM; + err = ipgre_newlink_encap_setup(dev, data); if (err) return err; @@ -1486,6 +1489,9 @@ static int erspan_changelink(struct net_device *dev, struct nlattr *tb[], __u32 fwmark = t->fwmark; int err; + if (!rtnl_dev_link_net_capable(dev, t->net)) + return -EPERM; + err = ipgre_newlink_encap_setup(dev, data); if (err) return err; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 5bcd73cbdb41..ec790bad1679 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1117,8 +1117,8 @@ alloc_new_skb: !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; else { - alloclen = fragheaderlen + transhdrlen; - pagedlen = datalen - transhdrlen; + alloclen = fragheaderlen + transhdrlen + fraggap; + pagedlen = datalen - transhdrlen - fraggap; } alloclen += alloc_extra; @@ -1165,9 +1165,6 @@ alloc_new_skb: } copy = datalen - transhdrlen - fraggap - pagedlen; - /* [!] NOTE: copy will be negative if pagedlen>0 - * because then the equation reduces to -fraggap. - */ if (copy > 0 && INDIRECT_CALL_1(getfrag, ip_generic_getfrag, from, data + transhdrlen, offset, diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 0a4b38b315fe..36984e905070 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -1776,6 +1776,10 @@ static int tcp_ao_delete_key(struct sock *sk, struct tcp_ao_info *ao_info, * them and we can just free all resources in RCU fashion. */ if (del_async) { + if (ao_info->current_key == key) + WRITE_ONCE(ao_info->current_key, NULL); + if (ao_info->rnext_key == key) + WRITE_ONCE(ao_info->rnext_key, NULL); atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc); call_rcu(&key->rcu, tcp_ao_key_free_rcu); return 0; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index c14adcdd4396..b5d9c57fe439 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1668,8 +1668,8 @@ alloc_new_skb: !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; else { - alloclen = fragheaderlen + transhdrlen; - pagedlen = datalen - transhdrlen; + alloclen = fragheaderlen + transhdrlen + fraggap; + pagedlen = datalen - transhdrlen - fraggap; } alloclen += alloc_extra; @@ -1684,10 +1684,7 @@ alloc_new_skb: fraglen = datalen + fragheaderlen; copy = datalen - transhdrlen - fraggap - pagedlen; - /* [!] NOTE: copy may be negative if pagedlen>0 - * because then the equation may reduces to -fraggap. - */ - if (copy < 0 && !(flags & MSG_SPLICE_PAGES)) { + if (copy < 0) { err = -EINVAL; goto error; } diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c index e8512578398e..5e7cc11fab3a 100644 --- a/net/mac802154/llsec.c +++ b/net/mac802154/llsec.c @@ -710,6 +710,7 @@ int mac802154_llsec_encrypt(struct mac802154_llsec *sec, struct sk_buff *skb) { struct ieee802154_hdr hdr; int rc, authlen, hlen; + struct sk_buff *trailer; struct mac802154_llsec_key *key; u32 frame_ctr; @@ -769,6 +770,12 @@ int mac802154_llsec_encrypt(struct mac802154_llsec *sec, struct sk_buff *skb) skb->mac_len = ieee802154_hdr_push(skb, &hdr); skb_reset_mac_header(skb); + rc = skb_cow_data(skb, 0, &trailer); + if (rc < 0) { + llsec_key_put(key); + return rc; + } + rc = llsec_do_encrypt(skb, sec, &hdr, key); llsec_key_put(key); @@ -908,6 +915,13 @@ llsec_do_decrypt(struct sk_buff *skb, const struct mac802154_llsec *sec, const struct ieee802154_hdr *hdr, struct mac802154_llsec_key *key, __le64 dev_addr) { + struct sk_buff *trailer; + int err; + + err = skb_cow_data(skb, 0, &trailer); + if (err < 0) + return err; + if (hdr->sec.level == IEEE802154_SCF_SECLEVEL_ENC) return llsec_do_decrypt_unauth(skb, sec, hdr, key, dev_addr); else diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index 6d3b6b89b1d1..16f1ed1f6b1b 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -941,12 +941,20 @@ static int tipc_aead_decrypt(struct net *net, struct tipc_aead *aead, goto exit; } + /* Get net to avoid freed tipc_crypto when delete namespace */ + if (!maybe_get_net(net)) { + tipc_bearer_put(b); + rc = -ENODEV; + goto exit; + } + /* Now, do decrypt */ rc = crypto_aead_decrypt(req); if (rc == -EINPROGRESS || rc == -EBUSY) return rc; tipc_bearer_put(b); + put_net(net); exit: kfree(ctx); @@ -984,6 +992,7 @@ static void tipc_aead_decrypt_done(void *data, int err) } tipc_bearer_put(b); + put_net(net); } static inline int tipc_ehdr_size(struct tipc_ehdr *ehdr) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 964ebc268ee4..a47f6a1e2c77 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -623,6 +623,7 @@ static int tls_split_open_record(struct sock *sk, struct tls_rec *from, struct scatterlist *sge, *osge, *nsge; u32 orig_size = msg_opl->sg.size; struct scatterlist tmp = { }; + u32 tmp_i = 0; struct sk_msg *msg_npl; struct tls_rec *new; int ret; @@ -644,6 +645,7 @@ static int tls_split_open_record(struct sock *sk, struct tls_rec *from, if (sge->length > apply) { u32 len = sge->length - apply; + tmp_i = i; get_page(sg_page(sge)); sg_set_page(&tmp, sg_page(sge), len, sge->offset + apply); @@ -675,6 +677,7 @@ static int tls_split_open_record(struct sock *sk, struct tls_rec *from, nsge = sk_msg_elem(msg_npl, j); if (tmp.length) { memcpy(nsge, &tmp, sizeof(*nsge)); + sk_msg_sg_copy_assign(msg_npl, j, msg_opl, tmp_i); sk_msg_iter_var_next(j); nsge = sk_msg_elem(msg_npl, j); } @@ -682,6 +685,7 @@ static int tls_split_open_record(struct sock *sk, struct tls_rec *from, osge = sk_msg_elem(msg_opl, i); while (osge->length) { memcpy(nsge, osge, sizeof(*nsge)); + sk_msg_sg_copy_assign(msg_npl, j, msg_opl, i); sg_unmark_end(nsge); sk_msg_iter_var_next(i); sk_msg_iter_var_next(j); diff --git a/security/apparmor/include/policy_unpack.h b/security/apparmor/include/policy_unpack.h index e5a95dc4da1f..b9de0fdf9ee5 100644 --- a/security/apparmor/include/policy_unpack.h +++ b/security/apparmor/include/policy_unpack.h @@ -163,6 +163,25 @@ aa_get_profile_loaddata(struct aa_loaddata *data) return data; } +/** + * aa_get_profile_loaddata_not0 - get a profile reference count if not zero + * @data: reference to get a count on + * + * Like aa_get_profile_loaddata(), but safe to call on an entry that may + * be on a list (e.g. ns->rawdata_list) where the last pcount has already + * dropped and the deferred cleanup has not yet run. + * + * Returns: pointer to reference, or %NULL if @data is NULL or its + * profile refcount has already reached zero. + */ +static inline struct aa_loaddata * +aa_get_profile_loaddata_not0(struct aa_loaddata *data) +{ + if (data && kref_get_unless_zero(&data->pcount)) + return data; + return NULL; +} + void __aa_loaddata_update(struct aa_loaddata *data, long revision); bool aa_rawdata_eq(struct aa_loaddata *l, struct aa_loaddata *r); void aa_loaddata_kref(struct kref *kref); diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 3491e9f60194..e01efdf50efa 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1422,7 +1422,21 @@ static int aa_sock_msg_perm(const char *op, u32 request, struct socket *sock, static int apparmor_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { - return aa_sock_msg_perm(OP_SENDMSG, AA_MAY_SEND, sock, msg, size); + int error = aa_sock_msg_perm(OP_SENDMSG, AA_MAY_SEND, sock, msg, size); + + if (error) + return error; + + /* TCP fast open carries connect() semantics in sendmsg(); mediate + * the implicit connect so it cannot bypass the connect permission. + */ + if ((msg->msg_flags & MSG_FASTOPEN) && msg->msg_name && + (sk_is_tcp(sock->sk) || + (sk_is_inet(sock->sk) && sock->sk->sk_type == SOCK_STREAM && + sock->sk->sk_protocol == IPPROTO_MPTCP))) + error = aa_sk_perm(OP_CONNECT, AA_MAY_CONNECT, sock->sk); + + return error; } static int apparmor_socket_recvmsg(struct socket *sock, diff --git a/security/apparmor/net.c b/security/apparmor/net.c index 44c04102062f..1fc6145ccbb8 100644 --- a/security/apparmor/net.c +++ b/security/apparmor/net.c @@ -22,12 +22,14 @@ struct aa_sfs_entry aa_sfs_entry_network[] = { AA_SFS_FILE_STRING("af_mask", AA_SFS_AF_MASK), + AA_SFS_FILE_BOOLEAN("tcp-fast-open", 1), { } }; struct aa_sfs_entry aa_sfs_entry_networkv9[] = { AA_SFS_FILE_STRING("af_mask", AA_SFS_AF_MASK), AA_SFS_FILE_BOOLEAN("af_unix", 1), + AA_SFS_FILE_BOOLEAN("tcp-fast-open", 1), { } }; diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index b6a5eb4021db..e103cce6f4af 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -1223,8 +1223,12 @@ ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label, if (aa_rawdata_eq(rawdata_ent, udata)) { struct aa_loaddata *tmp; - tmp = aa_get_profile_loaddata(rawdata_ent); - /* check we didn't fail the race */ + /* + * Entries remain on rawdata_list with + * pcount == 0 until do_ploaddata_rmfs() + * runs; only take a live profile ref. + */ + tmp = aa_get_profile_loaddata_not0(rawdata_ent); if (tmp) { aa_put_profile_loaddata(udata); udata = tmp; diff --git a/security/keys/internal.h b/security/keys/internal.h index 2cffa6dc8255..b7b622bc36a1 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -208,6 +208,8 @@ extern struct key *request_key_auth_new(struct key *target, const void *callout_info, size_t callout_len, struct key *dest_keyring); +struct request_key_auth *request_key_auth_get(struct key *authkey); +void request_key_auth_put(struct request_key_auth *rka); extern struct key *key_get_instantiation_authkey(key_serial_t target_id); diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index ef855d69c97a..d14ace88e529 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -1197,9 +1197,13 @@ static long keyctl_instantiate_key_common(key_serial_t id, if (!instkey) goto error; - rka = instkey->payload.data[0]; - if (rka->target_key->serial != id) + rka = request_key_auth_get(instkey); + if (!rka) { + ret = -EKEYREVOKED; goto error; + } + if (rka->target_key->serial != id) + goto error_put_rka; /* pull the payload in if one was supplied */ payload = NULL; @@ -1208,7 +1212,7 @@ static long keyctl_instantiate_key_common(key_serial_t id, ret = -ENOMEM; payload = kvmalloc(plen, GFP_KERNEL); if (!payload) - goto error; + goto error_put_rka; ret = -EFAULT; if (!copy_from_iter_full(payload, plen, from)) @@ -1234,6 +1238,8 @@ static long keyctl_instantiate_key_common(key_serial_t id, error2: kvfree_sensitive(payload, plen); +error_put_rka: + request_key_auth_put(rka); error: return ret; } @@ -1358,15 +1364,19 @@ long keyctl_reject_key(key_serial_t id, unsigned timeout, unsigned error, if (!instkey) goto error; - rka = instkey->payload.data[0]; - if (rka->target_key->serial != id) + rka = request_key_auth_get(instkey); + if (!rka) { + ret = -EKEYREVOKED; goto error; + } + if (rka->target_key->serial != id) + goto error_put_rka; /* find the destination keyring if present (which must also be * writable) */ ret = get_instantiation_keyring(ringid, rka, &dest_keyring); if (ret < 0) - goto error; + goto error_put_rka; /* instantiate the key and link it into a keyring */ ret = key_reject_and_link(rka->target_key, timeout, error, @@ -1379,6 +1389,8 @@ long keyctl_reject_key(key_serial_t id, unsigned timeout, unsigned error, if (ret == 0) keyctl_change_reqkey_auth(NULL); +error_put_rka: + request_key_auth_put(rka); error: return ret; } diff --git a/security/keys/keyctl_pkey.c b/security/keys/keyctl_pkey.c index 97bc27bbf079..ba150ee2d4a3 100644 --- a/security/keys/keyctl_pkey.c +++ b/security/keys/keyctl_pkey.c @@ -138,28 +138,35 @@ static int keyctl_pkey_params_get_2(const struct keyctl_pkey_params __user *_par if (uparams.in_len > info.max_dec_size || uparams.out_len > info.max_enc_size) return -EINVAL; + + params->out_len = info.max_enc_size; break; case KEYCTL_PKEY_DECRYPT: if (uparams.in_len > info.max_enc_size || uparams.out_len > info.max_dec_size) return -EINVAL; + + params->out_len = info.max_dec_size; break; case KEYCTL_PKEY_SIGN: if (uparams.in_len > info.max_data_size || uparams.out_len > info.max_sig_size) return -EINVAL; + + params->out_len = info.max_sig_size; break; case KEYCTL_PKEY_VERIFY: if (uparams.in_len > info.max_data_size || uparams.in2_len > info.max_sig_size) return -EINVAL; + + params->out_len = info.max_sig_size; break; default: BUG(); } params->in_len = uparams.in_len; - params->out_len = uparams.out_len; /* Note: same as in2_len */ return 0; } diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c index a7d7538c1f70..282e09d8fa46 100644 --- a/security/keys/request_key_auth.c +++ b/security/keys/request_key_auth.c @@ -23,6 +23,7 @@ static void request_key_auth_describe(const struct key *, struct seq_file *); static void request_key_auth_revoke(struct key *); static void request_key_auth_destroy(struct key *); static long request_key_auth_read(const struct key *, char *, size_t); +static void request_key_auth_rcu_disposal(struct rcu_head *); /* * The request-key authorisation key type definition. @@ -116,6 +117,31 @@ static void free_request_key_auth(struct request_key_auth *rka) } /* + * Take a reference to the request-key authorisation payload so callers can + * drop authkey->sem before doing operations that may sleep. + */ +struct request_key_auth *request_key_auth_get(struct key *authkey) +{ + struct request_key_auth *rka; + + down_read(&authkey->sem); + rka = dereference_key_locked(authkey); + if (rka && !test_bit(KEY_FLAG_REVOKED, &authkey->flags)) + refcount_inc(&rka->usage); + else + rka = NULL; + up_read(&authkey->sem); + + return rka; +} + +void request_key_auth_put(struct request_key_auth *rka) +{ + if (rka && refcount_dec_and_test(&rka->usage)) + call_rcu(&rka->rcu, request_key_auth_rcu_disposal); +} + +/* * Dispose of the request_key_auth record under RCU conditions */ static void request_key_auth_rcu_disposal(struct rcu_head *rcu) @@ -136,8 +162,10 @@ static void request_key_auth_revoke(struct key *key) struct request_key_auth *rka = dereference_key_locked(key); kenter("{%d}", key->serial); + if (!rka) + return; rcu_assign_keypointer(key, NULL); - call_rcu(&rka->rcu, request_key_auth_rcu_disposal); + request_key_auth_put(rka); } /* @@ -150,7 +178,7 @@ static void request_key_auth_destroy(struct key *key) kenter("{%d}", key->serial); if (rka) { rcu_assign_keypointer(key, NULL); - call_rcu(&rka->rcu, request_key_auth_rcu_disposal); + request_key_auth_put(rka); } } @@ -174,6 +202,7 @@ struct key *request_key_auth_new(struct key *target, const char *op, rka = kzalloc_obj(*rka); if (!rka) goto error; + refcount_set(&rka->usage, 1); rka->callout_info = kmemdup(callout_info, callout_len, GFP_KERNEL); if (!rka->callout_info) goto error_free_rka; diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 0e8b8a2c5b79..93ad2ebc963f 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -24,6 +24,7 @@ #include <linux/slab.h> #include <linux/seqlock.h> #include <linux/irqbypass.h> +#include <linux/unaligned.h> #include <trace/events/kvm.h> #include <kvm/iodev.h> @@ -779,21 +780,18 @@ ioeventfd_in_range(struct _ioeventfd *p, gpa_t addr, int len, const void *val) return true; /* otherwise, we have to actually compare the data */ - - BUG_ON(!IS_ALIGNED((unsigned long)val, len)); - switch (len) { case 1: - _val = *(u8 *)val; + _val = get_unaligned((u8 *)val); break; case 2: - _val = *(u16 *)val; + _val = get_unaligned((u16 *)val); break; case 4: - _val = *(u32 *)val; + _val = get_unaligned((u32 *)val); break; case 8: - _val = *(u64 *)val; + _val = get_unaligned((u64 *)val); break; default: return false; |
