Re: [Linux-stable-mirror] Linux 4.9.79

diff --git a/Makefile b/Makefile index 8a6f158a1176..4a7e6dff1c2e 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 9 -SUBLEVEL = 78 +SUBLEVEL = 79 EXTRAVERSION = NAME = Roaring Lionus

diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 2206e0e00934..2a35c1963f6d 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1284,7 +1284,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, return -EFAULT; }

- if (is_vm_hugetlb_page(vma) && !logging_active) { + if (vma_kernel_pagesize(vma) && !logging_active) { hugetlb = true; gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT; } else { diff --git a/arch/um/Makefile b/arch/um/Makefile index 0ca46ededfc7..9c150ccb35d2 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -117,7 +117,7 @@ archheaders: archprepare: include/generated/user_constants.h

LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static -LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib +LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib $(call cc-option, -no-pie)

CFLAGS_NO_HARDENING := $(call cc-option, -fno-PIC,) $(call cc-option, -fno-pic,) \ $(call cc-option, -fno-stack-protector,) \ diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 6bb7e92c6d50..0174290b2857 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -46,6 +46,7 @@ static enum { EMULATE, NATIVE, NONE } vsyscall_mode = #else EMULATE; #endif +unsigned long vsyscall_pgprot = __PAGE_KERNEL_VSYSCALL;

static int __init vsyscall_setup(char *str) { @@ -336,11 +337,11 @@ void __init map_vsyscall(void) extern char __vsyscall_page; unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);

+ if (vsyscall_mode != NATIVE) + vsyscall_pgprot = __PAGE_KERNEL_VVAR; if (vsyscall_mode != NONE) __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, - vsyscall_mode == NATIVE - ? PAGE_KERNEL_VSYSCALL - : PAGE_KERNEL_VVAR); + __pgprot(vsyscall_pgprot));

BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) != (unsigned long)VSYSCALL_ADDR); diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c index 9842270ed2f2..21a4e4127f43 100644 --- a/arch/x86/events/amd/power.c +++ b/arch/x86/events/amd/power.c @@ -277,7 +277,7 @@ static int __init amd_power_pmu_init(void) int ret;

if (!x86_match_cpu(cpu_match)) - return 0; + return -ENODEV;

if (!boot_cpu_has(X86_FEATURE_ACC_POWER)) return -ENODEV; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index e40b19ca486e..353f038ec645 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -596,7 +596,7 @@ static inline void sync_core(void) { int tmp;

-#ifdef CONFIG_M486 +#ifdef CONFIG_X86_32 /* * Do a CPUID if available, otherwise do a jump. The jump * can conveniently enough be the jump around CPUID. diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index 4865e10dbb55..9ee85066f407 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -13,6 +13,7 @@ extern void map_vsyscall(void); */ extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address); extern bool vsyscall_enabled(void); +extern unsigned long vsyscall_pgprot; #else static inline void map_vsyscall(void) {} static inline bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index de6626c18e42..be6337156502 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -934,6 +934,8 @@ static int __populate_cache_leaves(unsigned int cpu) ci_leaf_init(this_leaf++, &id4_regs); __cache_cpumap_setup(cpu, idx, &id4_regs); } + this_cpu_ci->cpu_map_populated = true; + return 0; }

diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index ac3e636ad586..f90f17610f62 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -40,6 +40,9 @@ #include <asm/setup.h> #include <asm/msr.h>

+/* last level cache size per core */ +static int llc_size_per_core; + /* * Temporary microcode blobs pointers storage. We note here during early load * the pointers to microcode blobs we've got from whatever storage (detached @@ -1053,12 +1056,14 @@ static bool is_blacklisted(unsigned int cpu)

/* * Late loading on model 79 with microcode revision less than 0x0b000021 - * may result in a system hang. This behavior is documented in item - * BDF90, #334165 (Intel Xeon Processor E7-8800/4800 v4 Product Family). + * and LLC size per core bigger than 2.5MB may result in a system hang. + * This behavior is documented in item BDF90, #334165 (Intel Xeon + * Processor E7-8800/4800 v4 Product Family). */ if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X && c->x86_mask == 0x01 && + llc_size_per_core > 2621440 && c->microcode < 0x0b000021) { pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode); pr_err_once("Please consider either early loading through initrd/built-in or a potential BIOS update.\n"); @@ -1125,6 +1130,15 @@ static struct microcode_ops microcode_intel_ops = { .microcode_fini_cpu = microcode_fini_cpu, };

+static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c) +{ + u64 llc_size = c->x86_cache_size * 1024; + + do_div(llc_size, c->x86_max_cores); + + return (int)llc_size; +} + struct microcode_ops * __init init_intel_microcode(void) { struct cpuinfo_x86 *c = &boot_cpu_data; @@ -1135,6 +1149,8 @@ struct microcode_ops * __init init_intel_microcode(void) return NULL; }

+ llc_size_per_core = calc_llc_size_per_core(c); + return &microcode_intel_ops; }

diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 073d1f1a620b..9758524ee99f 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -93,6 +93,13 @@ static void delay_mwaitx(unsigned long __loops) { u64 start, end, delay, loops = __loops;

+ /* + * Timer value of 0 causes MWAITX to wait indefinitely, unless there + * is a store on the memory monitored by MONITORX. + */ + if (loops == 0) + return; + start = rdtsc_ordered();

for (;;) { diff --git a/arch/x86/mm/kaiser.c b/arch/x86/mm/kaiser.c index a8ade08a9bf5..ec678aafa3f8 100644 --- a/arch/x86/mm/kaiser.c +++ b/arch/x86/mm/kaiser.c @@ -344,7 +344,7 @@ void __init kaiser_init(void) if (vsyscall_enabled()) kaiser_add_user_map_early((void *)VSYSCALL_ADDR, PAGE_SIZE, - __PAGE_KERNEL_VSYSCALL); + vsyscall_pgprot);

for_each_possible_cpu(cpu) { void *percpu_vaddr = __per_cpu_user_mapped_start + diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 15f743615923..7840331d3056 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -278,10 +278,10 @@ static void emit_bpf_tail_call(u8 **pprog) /* if (index >= array->map.max_entries) * goto out; */ - EMIT4(0x48, 0x8B, 0x46, /* mov rax, qword ptr [rsi + 16] */ + EMIT2(0x89, 0xD2); /* mov edx, edx */ + EMIT3(0x39, 0x56, /* cmp dword ptr [rsi + 16], edx */ offsetof(struct bpf_array, map.max_entries)); - EMIT3(0x48, 0x39, 0xD0); /* cmp rax, rdx */ -#define OFFSET1 47 /* number of bytes to jump */ +#define OFFSET1 43 /* number of bytes to jump */ EMIT2(X86_JBE, OFFSET1); /* jbe out */ label1 = cnt;

@@ -290,21 +290,20 @@ static void emit_bpf_tail_call(u8 **pprog) */ EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ -#define OFFSET2 36 +#define OFFSET2 32 EMIT2(X86_JA, OFFSET2); /* ja out */ label2 = cnt; EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */

/* prog = array->ptrs[index]; */ - EMIT4_off32(0x48, 0x8D, 0x84, 0xD6, /* lea rax, [rsi + rdx * 8 + offsetof(...)] */ + EMIT4_off32(0x48, 0x8B, 0x84, 0xD6, /* mov rax, [rsi + rdx * 8 + offsetof(...)] */ offsetof(struct bpf_array, ptrs)); - EMIT3(0x48, 0x8B, 0x00); /* mov rax, qword ptr [rax] */

/* if (prog == NULL) * goto out; */ - EMIT4(0x48, 0x83, 0xF8, 0x00); /* cmp rax, 0 */ + EMIT3(0x48, 0x85, 0xC0); /* test rax,rax */ #define OFFSET3 10 EMIT2(X86_JE, OFFSET3); /* je out */ label3 = cnt; diff --git a/drivers/acpi/acpica/nsutils.c b/drivers/acpi/acpica/nsutils.c index 691814dfed31..943702dd9517 100644 --- a/drivers/acpi/acpica/nsutils.c +++ b/drivers/acpi/acpica/nsutils.c @@ -594,25 +594,20 @@ struct acpi_namespace_node *acpi_ns_validate_handle(acpi_handle handle) void acpi_ns_terminate(void) { acpi_status status; + union acpi_operand_object *prev; + union acpi_operand_object *next;

ACPI_FUNCTION_TRACE(ns_terminate);

-#ifdef ACPI_EXEC_APP - { - union acpi_operand_object *prev; - union acpi_operand_object *next; + /* Delete any module-level code blocks */

- /* Delete any module-level code blocks */ - - next = acpi_gbl_module_code_list; - while (next) { - prev = next; - next = next->method.mutex; - prev->method.mutex = NULL; /* Clear the Mutex (cheated) field */ - acpi_ut_remove_reference(prev); - } + next = acpi_gbl_module_code_list; + while (next) { + prev = next; + next = next->method.mutex; + prev->method.mutex = NULL; /* Clear the Mutex (cheated) field */ + acpi_ut_remove_reference(prev); } -#endif

/* * Free the entire namespace -- all nodes and all objects diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c index 73c9c7fa9001..f06317d6fc38 100644 --- a/drivers/acpi/glue.c +++ b/drivers/acpi/glue.c @@ -99,13 +99,13 @@ static int find_child_checks(struct acpi_device *adev, bool check_children) return -ENODEV;

/* - * If the device has a _HID (or _CID) returning a valid ACPI/PNP - * device ID, it is better to make it look less attractive here, so that - * the other device with the same _ADR value (that may not have a valid - * device ID) can be matched going forward. [This means a second spec - * violation in a row, so whatever we do here is best effort anyway.] + * If the device has a _HID returning a valid ACPI/PNP device ID, it is + * better to make it look less attractive here, so that the other device + * with the same _ADR value (that may not have a valid device ID) can be + * matched going forward. [This means a second spec violation in a row, + * so whatever we do here is best effort anyway.] */ - return sta_present && list_empty(&adev->pnp.ids) ? + return sta_present && !adev->pnp.type.platform_id ? FIND_CHILD_MAX_SCORE : FIND_CHILD_MIN_SCORE; }

diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c index e9fd32e91668..70e13cf06ed0 100644 --- a/drivers/base/cacheinfo.c +++ b/drivers/base/cacheinfo.c @@ -16,6 +16,7 @@ * You should have received a copy of the GNU General Public License * along with this program. If not, see http://www.gnu.org/licenses/. */ +#include <linux/acpi.h> #include <linux/bitops.h> #include <linux/cacheinfo.h> #include <linux/compiler.h> @@ -104,9 +105,16 @@ static int cache_shared_cpu_map_setup(unsigned int cpu) struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); struct cacheinfo *this_leaf, *sib_leaf; unsigned int index; - int ret; + int ret = 0; + + if (this_cpu_ci->cpu_map_populated) + return 0;

- ret = cache_setup_of_node(cpu); + if (of_have_populated_dt()) + ret = cache_setup_of_node(cpu); + else if (!acpi_disabled) + /* No cache property/hierarchy support yet in ACPI */ + ret = -ENOTSUPP; if (ret) return ret;

@@ -203,8 +211,7 @@ static int detect_cache_attributes(unsigned int cpu) */ ret = cache_shared_cpu_map_setup(cpu); if (ret) { - pr_warn("Unable to detect cache hierarchy from DT for CPU %d\n", - cpu); + pr_warn("Unable to detect cache hierarchy for CPU %d\n", cpu); goto free_ci; } return 0; diff --git a/drivers/input/mouse/trackpoint.c b/drivers/input/mouse/trackpoint.c index 7e2dc5e56632..0b49f29bf0da 100644 --- a/drivers/input/mouse/trackpoint.c +++ b/drivers/input/mouse/trackpoint.c @@ -383,6 +383,9 @@ int trackpoint_detect(struct psmouse *psmouse, bool set_properties) if (trackpoint_read(&psmouse->ps2dev, TP_EXT_BTN, &button_info)) { psmouse_warn(psmouse, "failed to get extended button data, assuming 3 buttons\n"); button_info = 0x33; + } else if (!button_info) { + psmouse_warn(psmouse, "got 0 in extended button data, assuming 3 buttons\n"); + button_info = 0x33; }

psmouse->private = kzalloc(sizeof(struct trackpoint_data), GFP_KERNEL); diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 1644896568c4..b2eeecb26939 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -4733,6 +4733,15 @@ int be_update_queues(struct be_adapter *adapter)

be_schedule_worker(adapter);

+ /* + * The IF was destroyed and re-created. We need to clear + * all promiscuous flags valid for the destroyed IF. + * Without this promisc mode is not restored during + * be_open() because the driver thinks that it is + * already enabled in HW. + */ + adapter->if_flags &= ~BE_IF_FLAGS_ALL_PROMISCUOUS; + if (netif_running(netdev)) status = be_open(netdev);

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 8aa91ddff287..16556011d571 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -765,11 +765,8 @@ static void mlxsw_sp_router_neigh_ent_ipv4_process(struct mlxsw_sp *mlxsw_sp, dipn = htonl(dip); dev = mlxsw_sp->rifs[rif]->dev; n = neigh_lookup(&arp_tbl, &dipn, dev); - if (!n) { - netdev_err(dev, "Failed to find matching neighbour for IP=%pI4h\n", - &dip); + if (!n) return; - }

netdev_dbg(dev, "Updating neighbour with IP=%pI4h\n", &dip); neigh_event_send(n, NULL); diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 2c4350a1c629..298b74ebc1e9 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -2222,19 +2222,14 @@ static bool rtl8169_do_counters(struct net_device *dev, u32 counter_cmd) void __iomem *ioaddr = tp->mmio_addr; dma_addr_t paddr = tp->counters_phys_addr; u32 cmd; - bool ret;

RTL_W32(CounterAddrHigh, (u64)paddr >> 32); + RTL_R32(CounterAddrHigh); cmd = (u64)paddr & DMA_BIT_MASK(32); RTL_W32(CounterAddrLow, cmd); RTL_W32(CounterAddrLow, cmd | counter_cmd);

- ret = rtl_udelay_loop_wait_low(tp, &rtl_counters_cond, 10, 1000); - - RTL_W32(CounterAddrLow, 0); - RTL_W32(CounterAddrHigh, 0); - - return ret; + return rtl_udelay_loop_wait_low(tp, &rtl_counters_cond, 10, 1000); }

static bool rtl8169_reset_counters(struct net_device *dev) diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index b883af93929c..fc4c2ccc3d22 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1002,17 +1002,18 @@ static int ppp_unit_register(struct ppp *ppp, int unit, bool ifname_is_set) if (!ifname_is_set) snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ppp->file.index);

+ mutex_unlock(&pn->all_ppp_mutex); + ret = register_netdevice(ppp->dev); if (ret < 0) goto err_unit;

atomic_inc(&ppp_unit_count);

- mutex_unlock(&pn->all_ppp_mutex); - return 0;

err_unit: + mutex_lock(&pn->all_ppp_mutex); unit_put(&pn->units_idr, ppp->file.index); err: mutex_unlock(&pn->all_ppp_mutex); diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 4ddae8118c85..dc36c2ec1d10 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -842,6 +842,7 @@ static int pppoe_sendmsg(struct socket *sock, struct msghdr *m, struct pppoe_hdr *ph; struct net_device *dev; char *start; + int hlen;

lock_sock(sk); if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED)) { @@ -860,16 +861,16 @@ static int pppoe_sendmsg(struct socket *sock, struct msghdr *m, if (total_len > (dev->mtu + dev->hard_header_len)) goto end;

- - skb = sock_wmalloc(sk, total_len + dev->hard_header_len + 32, - 0, GFP_KERNEL); + hlen = LL_RESERVED_SPACE(dev); + skb = sock_wmalloc(sk, hlen + sizeof(*ph) + total_len + + dev->needed_tailroom, 0, GFP_KERNEL); if (!skb) { error = -ENOMEM; goto end; }

/* Reserve space for headers. */ - skb_reserve(skb, dev->hard_header_len); + skb_reserve(skb, hlen); skb_reset_network_header(skb);

skb->dev = dev; @@ -930,7 +931,7 @@ static int __pppoe_xmit(struct sock *sk, struct sk_buff *skb) /* Copy the data if there is no space for the header or if it's * read-only. */ - if (skb_cow_head(skb, sizeof(*ph) + dev->hard_header_len)) + if (skb_cow_head(skb, LL_RESERVED_SPACE(dev) + sizeof(*ph))) goto abort;

__skb_push(skb, sizeof(*ph)); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 518cbfbc8b65..eb6dc28e5e52 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -525,6 +525,14 @@ static void tun_queue_purge(struct tun_file *tfile) skb_queue_purge(&tfile->sk.sk_error_queue); }

+static void tun_cleanup_tx_array(struct tun_file *tfile) +{ + if (tfile->tx_array.ring.queue) { + skb_array_cleanup(&tfile->tx_array); + memset(&tfile->tx_array, 0, sizeof(tfile->tx_array)); + } +} + static void __tun_detach(struct tun_file *tfile, bool clean) { struct tun_file *ntfile; @@ -566,8 +574,7 @@ static void __tun_detach(struct tun_file *tfile, bool clean) tun->dev->reg_state == NETREG_REGISTERED) unregister_netdevice(tun->dev); } - if (tun) - skb_array_cleanup(&tfile->tx_array); + tun_cleanup_tx_array(tfile); sock_put(&tfile->sk); } } @@ -606,11 +613,13 @@ static void tun_detach_all(struct net_device *dev) /* Drop read queue */ tun_queue_purge(tfile); sock_put(&tfile->sk); + tun_cleanup_tx_array(tfile); } list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) { tun_enable_queue(tfile); tun_queue_purge(tfile); sock_put(&tfile->sk); + tun_cleanup_tx_array(tfile); } BUG_ON(tun->numdisabled != 0);

@@ -2363,6 +2372,8 @@ static int tun_chr_open(struct inode *inode, struct file * file)

sock_set_flag(&tfile->sk, SOCK_ZEROCOPY);

+ memset(&tfile->tx_array, 0, sizeof(tfile->tx_array)); + return 0; }

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 9c257ffedb15..c53385a0052f 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -2197,6 +2197,7 @@ static int lan78xx_reset(struct lan78xx_net *dev) buf = DEFAULT_BURST_CAP_SIZE / FS_USB_PKT_SIZE; dev->rx_urb_size = DEFAULT_BURST_CAP_SIZE; dev->rx_qlen = 4; + dev->tx_qlen = 4; }

ret = lan78xx_write_reg(dev, BURST_CAP, buf); diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index ef83ae3b0a44..4afba17e2403 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -1616,7 +1616,6 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq, rq->rx_ring[i].basePA); rq->rx_ring[i].base = NULL; } - rq->buf_info[i] = NULL; }

if (rq->data_ring.base) { @@ -1638,6 +1637,7 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq, (rq->rx_ring[0].size + rq->rx_ring[1].size); dma_free_coherent(&adapter->pdev->dev, sz, rq->buf_info[0], rq->buf_info_pa); + rq->buf_info[0] = rq->buf_info[1] = NULL; } }

diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index a530f08592cd..4abd3fce5ab6 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -1727,7 +1727,7 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc)

if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) { reason = FAILURE_SESSION_IN_RECOVERY; - sc->result = DID_REQUEUE; + sc->result = DID_REQUEUE << 16; goto fault; }

diff --git a/drivers/usb/usbip/usbip_common.h b/drivers/usb/usbip/usbip_common.h index 9f490375ac92..f0b955f8504e 100644 --- a/drivers/usb/usbip/usbip_common.h +++ b/drivers/usb/usbip/usbip_common.h @@ -271,6 +271,7 @@ struct usbip_device { /* lock for status */ spinlock_t lock;

+ int sockfd; struct socket *tcp_socket;

struct task_struct *tcp_rx; diff --git a/drivers/usb/usbip/vhci_sysfs.c b/drivers/usb/usbip/vhci_sysfs.c index b96e5b189269..c287ccc78fde 100644 --- a/drivers/usb/usbip/vhci_sysfs.c +++ b/drivers/usb/usbip/vhci_sysfs.c @@ -49,13 +49,17 @@ static ssize_t status_show_vhci(int pdev_nr, char *out)

/* * output example: - * port sta spd dev socket local_busid - * 0000 004 000 00000000 c5a7bb80 1-2.3 - * 0001 004 000 00000000 d8cee980 2-3.4 + * port sta spd dev sockfd local_busid + * 0000 004 000 00000000 000003 1-2.3 + * 0001 004 000 00000000 000004 2-3.4 * - * IP address can be retrieved from a socket pointer address by looking - * up /proc/net/{tcp,tcp6}. Also, a userland program may remember a - * port number and its peer IP address. + * Output includes socket fd instead of socket pointer address to + * avoid leaking kernel memory address in: + * /sys/devices/platform/vhci_hcd.0/status and in debug output. + * The socket pointer address is not used at the moment and it was + * made visible as a convenient way to find IP address from socket + * pointer address by looking up /proc/net/{tcp,tcp6}. As this opens + * a security hole, the change is made to use sockfd instead. */ for (i = 0; i < VHCI_HC_PORTS; i++) { struct vhci_device *vdev = &vhci->vdev[i]; @@ -68,13 +72,13 @@ static ssize_t status_show_vhci(int pdev_nr, char *out) if (vdev->ud.status == VDEV_ST_USED) { out += sprintf(out, "%03u %08x ", vdev->speed, vdev->devid); - out += sprintf(out, "%16p %s", - vdev->ud.tcp_socket, + out += sprintf(out, "%06u %s", + vdev->ud.sockfd, dev_name(&vdev->udev->dev));

} else { out += sprintf(out, "000 00000000 "); - out += sprintf(out, "0000000000000000 0-0"); + out += sprintf(out, "000000 0-0"); }

out += sprintf(out, "\n"); @@ -125,7 +129,7 @@ static ssize_t status_show(struct device *dev, int pdev_nr;

out += sprintf(out, - "port sta spd dev socket local_busid\n"); + "port sta spd dev sockfd local_busid\n");

pdev_nr = status_name_to_id(attr->attr.name); if (pdev_nr < 0) @@ -324,6 +328,7 @@ static ssize_t store_attach(struct device *dev, struct device_attribute *attr,

vdev->devid = devid; vdev->speed = speed; + vdev->ud.sockfd = sockfd; vdev->ud.tcp_socket = socket; vdev->ud.status = VDEV_ST_NOTASSIGNED;

diff --git a/fs/fcntl.c b/fs/fcntl.c index 1493ceb0477d..ec03cf620fd7 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -114,6 +114,10 @@ void f_setown(struct file *filp, unsigned long arg, int force) int who = arg; type = PIDTYPE_PID; if (who < 0) { + /* avoid overflow below */ + if (who == INT_MIN) + return; + type = PIDTYPE_PGID; who = -who; } diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index 75f942ae5176..81c018e5c31e 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -59,10 +59,10 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) gi->gid[i] = exp->ex_anon_gid; else gi->gid[i] = rqgi->gid[i]; - - /* Each thread allocates its own gi, no race */ - groups_sort(gi); } + + /* Each thread allocates its own gi, no race */ + groups_sort(gi); } else { gi = get_group_info(rqgi); } diff --git a/fs/orangefs/devorangefs-req.c b/fs/orangefs/devorangefs-req.c index fe2cbeb90772..939aa066e1ca 100644 --- a/fs/orangefs/devorangefs-req.c +++ b/fs/orangefs/devorangefs-req.c @@ -161,7 +161,7 @@ static ssize_t orangefs_devreq_read(struct file *file, struct orangefs_kernel_op_s *op, *temp; __s32 proto_ver = ORANGEFS_KERNEL_PROTO_VERSION; static __s32 magic = ORANGEFS_DEVREQ_MAGIC; - struct orangefs_kernel_op_s *cur_op = NULL; + struct orangefs_kernel_op_s *cur_op; unsigned long ret;

/* We do not support blocking IO. */ @@ -181,6 +181,7 @@ static ssize_t orangefs_devreq_read(struct file *file, }

restart: + cur_op = NULL; /* Get next op (if any) from top of list. */ spin_lock(&orangefs_request_list_lock); list_for_each_entry_safe(op, temp, &orangefs_request_list, list) { diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c index 02cc6139ec90..5b2cbe567365 100644 --- a/fs/orangefs/file.c +++ b/fs/orangefs/file.c @@ -446,7 +446,7 @@ ssize_t orangefs_inode_read(struct inode *inode, static ssize_t orangefs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; - loff_t pos = *(&iocb->ki_pos); + loff_t pos = iocb->ki_pos; ssize_t rc = 0;

BUG_ON(iocb->private); @@ -485,9 +485,6 @@ static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *ite } }

- if (file->f_pos > i_size_read(file->f_mapping->host)) - orangefs_i_size_write(file->f_mapping->host, file->f_pos); - rc = generic_write_checks(iocb, iter);

if (rc <= 0) { @@ -501,7 +498,7 @@ static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *ite * pos to the end of the file, so we will wait till now to set * pos... */ - pos = *(&iocb->ki_pos); + pos = iocb->ki_pos;

rc = do_readv_writev(ORANGEFS_IO_WRITE, file, diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h index 45dd8f27b2ac..f28381a7cd12 100644 --- a/fs/orangefs/orangefs-kernel.h +++ b/fs/orangefs/orangefs-kernel.h @@ -570,17 +570,6 @@ do { \ sys_attr.mask = ORANGEFS_ATTR_SYS_ALL_SETABLE; \ } while (0)

-static inline void orangefs_i_size_write(struct inode *inode, loff_t i_size) -{ -#if BITS_PER_LONG == 32 && defined(CONFIG_SMP) - inode_lock(inode); -#endif - i_size_write(inode, i_size); -#if BITS_PER_LONG == 32 && defined(CONFIG_SMP) - inode_unlock(inode); -#endif -} - static inline void orangefs_set_timeout(struct dentry *dentry) { unsigned long time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000; diff --git a/fs/orangefs/waitqueue.c b/fs/orangefs/waitqueue.c index abcfa3fa9992..f61b00887481 100644 --- a/fs/orangefs/waitqueue.c +++ b/fs/orangefs/waitqueue.c @@ -28,10 +28,10 @@ static void orangefs_clean_up_interrupted_operation(struct orangefs_kernel_op_s */ void purge_waiting_ops(void) { - struct orangefs_kernel_op_s *op; + struct orangefs_kernel_op_s *op, *tmp;

spin_lock(&orangefs_request_list_lock); - list_for_each_entry(op, &orangefs_request_list, list) { + list_for_each_entry_safe(op, tmp, &orangefs_request_list, list) { gossip_debug(GOSSIP_WAIT_DEBUG, "pvfs2-client-core: purging op tag %llu %s\n", llu(op->tag), diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c index dc198bc64c61..edc8ef78b63f 100644 --- a/fs/reiserfs/bitmap.c +++ b/fs/reiserfs/bitmap.c @@ -513,9 +513,17 @@ static void __discard_prealloc(struct reiserfs_transaction_handle *th, "inode has negative prealloc blocks count."); #endif while (ei->i_prealloc_count > 0) { - reiserfs_free_prealloc_block(th, inode, ei->i_prealloc_block); - ei->i_prealloc_block++; + b_blocknr_t block_to_free; + + /* + * reiserfs_free_prealloc_block can drop the write lock, + * which could allow another caller to free the same block. + * We can protect against it by modifying the prealloc + * state before calling it. + */ + block_to_free = ei->i_prealloc_block++; ei->i_prealloc_count--; + reiserfs_free_prealloc_block(th, inode, block_to_free); dirty = 1; } if (dirty) @@ -1128,7 +1136,7 @@ static int determine_prealloc_size(reiserfs_blocknr_hint_t * hint) hint->prealloc_size = 0;

if (!hint->formatted_node && hint->preallocate) { - if (S_ISREG(hint->inode->i_mode) + if (S_ISREG(hint->inode->i_mode) && !IS_PRIVATE(hint->inode) && hint->inode->i_size >= REISERFS_SB(hint->th->t_super)->s_alloc_options. preallocmin * hint->inode->i_sb->s_blocksize) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 75ffd3b2149e..7995940d4187 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -36,7 +36,10 @@ struct bpf_map_ops { };

struct bpf_map { - atomic_t refcnt; + /* 1st cacheline with read-mostly members of which some + * are also accessed in fast-path (e.g. ops, max_entries). + */ + const struct bpf_map_ops *ops ____cacheline_aligned; enum bpf_map_type map_type; u32 key_size; u32 value_size; @@ -44,10 +47,15 @@ struct bpf_map { u32 map_flags; u32 pages; bool unpriv_array; - struct user_struct *user; - const struct bpf_map_ops *ops; - struct work_struct work; + /* 7 bytes hole */ + + /* 2nd cacheline with misc members to avoid false sharing + * particularly with refcounting. + */ + struct user_struct *user ____cacheline_aligned; + atomic_t refcnt; atomic_t usercnt; + struct work_struct work; };

struct bpf_map_type_list { diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 2189935075b4..a951fd10aaaa 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -71,6 +71,7 @@ struct cpu_cacheinfo { struct cacheinfo *info_list; unsigned int num_levels; unsigned int num_leaves; + bool cpu_map_populated; };

/* diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 490f5a83f947..e3d7754f25f0 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -633,6 +633,8 @@ typedef struct pglist_data { int kswapd_order; enum zone_type kswapd_classzone_idx;

+ int kswapd_failures; /* Number of 'reclaimed == 0' runs */ + #ifdef CONFIG_COMPACTION int kcompactd_max_order; enum zone_type kcompactd_classzone_idx; diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index a3d04934aa96..6f8fbcf10dfb 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -24,16 +24,10 @@ #ifndef MODULE_ARCH_VERMAGIC #define MODULE_ARCH_VERMAGIC "" #endif -#ifdef RETPOLINE -#define MODULE_VERMAGIC_RETPOLINE "retpoline " -#else -#define MODULE_VERMAGIC_RETPOLINE "" -#endif

#define VERMAGIC_STRING \ UTS_RELEASE " " \ MODULE_VERMAGIC_SMP MODULE_VERMAGIC_PREEMPT \ MODULE_VERMAGIC_MODULE_UNLOAD MODULE_VERMAGIC_MODVERSIONS \ - MODULE_ARCH_VERMAGIC \ - MODULE_VERMAGIC_RETPOLINE + MODULE_ARCH_VERMAGIC

diff --git a/include/net/arp.h b/include/net/arp.h index 5e0f891d476c..1b3f86981757 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -19,6 +19,9 @@ static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32

static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { + if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) + key = INADDR_ANY; + return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev); }

diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 615ce0abba9c..e64210c98c2b 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -290,6 +290,7 @@ int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq, int flags); int ip6_flowlabel_init(void); void ip6_flowlabel_cleanup(void); +bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np);

static inline void fl6_sock_release(struct ip6_flowlabel *fl) { diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 0940598c002f..23102da24dd9 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -213,6 +213,11 @@ int net_eq(const struct net *net1, const struct net *net2) return net1 == net2; }

+static inline int check_net(const struct net *net) +{ + return atomic_read(&net->count) != 0; +} + void net_drop_ns(void *);

#else @@ -237,6 +242,11 @@ int net_eq(const struct net *net1, const struct net *net2) return 1; }

+static inline int check_net(const struct net *net) +{ + return 1; +} + #define net_drop_ns NULL #endif

diff --git a/include/uapi/linux/eventpoll.h b/include/uapi/linux/eventpoll.h index 1c3154913a39..bc96b14dfb2c 100644 --- a/include/uapi/linux/eventpoll.h +++ b/include/uapi/linux/eventpoll.h @@ -26,6 +26,19 @@ #define EPOLL_CTL_DEL 2 #define EPOLL_CTL_MOD 3

+/* Epoll event masks */ +#define EPOLLIN 0x00000001 +#define EPOLLPRI 0x00000002 +#define EPOLLOUT 0x00000004 +#define EPOLLERR 0x00000008 +#define EPOLLHUP 0x00000010 +#define EPOLLRDNORM 0x00000040 +#define EPOLLRDBAND 0x00000080 +#define EPOLLWRNORM 0x00000100 +#define EPOLLWRBAND 0x00000200 +#define EPOLLMSG 0x00000400 +#define EPOLLRDHUP 0x00002000 + /* Set exclusive wakeup mode for the target file descriptor */ #define EPOLLEXCLUSIVE (1 << 28)

diff --git a/init/Kconfig b/init/Kconfig index 34407f15e6d3..b331feeabda4 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1609,6 +1609,13 @@ config BPF_SYSCALL Enable the bpf() system call that allows to manipulate eBPF programs and maps via file descriptors.

+config BPF_JIT_ALWAYS_ON + bool "Permanently enable BPF JIT and remove BPF interpreter" + depends on BPF_SYSCALL && HAVE_EBPF_JIT && BPF_JIT + help + Enables BPF JIT and removes BPF interpreter to avoid + speculative execution of BPF instructions by the interpreter + config SHMEM bool "Use full shmem filesystem" if EXPERT default y diff --git a/ipc/msg.c b/ipc/msg.c index e12307d0c920..ff10d43b5184 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -763,7 +763,10 @@ static inline int convert_mode(long *msgtyp, int msgflg) if (*msgtyp == 0) return SEARCH_ANY; if (*msgtyp < 0) { - *msgtyp = -*msgtyp; + if (*msgtyp == LONG_MIN) /* -LONG_MIN is undefined */ + *msgtyp = LONG_MAX; + else + *msgtyp = -*msgtyp; return SEARCH_LESSEQUAL; } if (msgflg & MSG_EXCEPT) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index aa6d98154106..879ca844ba1d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -458,6 +458,7 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) } EXPORT_SYMBOL_GPL(__bpf_call_base);

+#ifndef CONFIG_BPF_JIT_ALWAYS_ON /** * __bpf_prog_run - run eBPF program on a given context * @ctx: is the data we are operating on @@ -641,7 +642,7 @@ static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn) DST = tmp; CONT; ALU_MOD_X: - if (unlikely(SRC == 0)) + if (unlikely((u32)SRC == 0)) return 0; tmp = (u32) DST; DST = do_div(tmp, (u32) SRC); @@ -660,7 +661,7 @@ static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn) DST = div64_u64(DST, SRC); CONT; ALU_DIV_X: - if (unlikely(SRC == 0)) + if (unlikely((u32)SRC == 0)) return 0; tmp = (u32) DST; do_div(tmp, (u32) SRC); @@ -715,7 +716,7 @@ static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn) struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2; struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_prog *prog; - u64 index = BPF_R3; + u32 index = BPF_R3;

if (unlikely(index >= array->map.max_entries)) goto out; @@ -923,6 +924,13 @@ static unsigned int __bpf_prog_run(void *ctx, const struct bpf_insn *insn) } STACK_FRAME_NON_STANDARD(__bpf_prog_run); /* jump table */

+#else +static unsigned int __bpf_prog_ret0(void *ctx, const struct bpf_insn *insn) +{ + return 0; +} +#endif + bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp) { @@ -970,7 +978,11 @@ static int bpf_check_tail_call(const struct bpf_prog *fp) */ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) { +#ifndef CONFIG_BPF_JIT_ALWAYS_ON fp->bpf_func = (void *) __bpf_prog_run; +#else + fp->bpf_func = (void *) __bpf_prog_ret0; +#endif

/* eBPF JITs can rewrite the program in case constant * blinding is active. However, in case of error during @@ -979,6 +991,12 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) * be JITed, but falls back to the interpreter. */ fp = bpf_int_jit_compile(fp); +#ifdef CONFIG_BPF_JIT_ALWAYS_ON + if (!fp->jited) { + *err = -ENOTSUPP; + return fp; + } +#endif bpf_prog_lock_ro(fp);

/* The tail call compatibility check can only be done at diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 19c44cf59bb2..076e4a0ff95e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -702,6 +702,13 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno) return __is_pointer_value(env->allow_ptr_leaks, &env->cur_state.regs[regno]); }

+static bool is_ctx_reg(struct bpf_verifier_env *env, int regno) +{ + const struct bpf_reg_state *reg = &env->cur_state.regs[regno]; + + return reg->type == PTR_TO_CTX; +} + static int check_ptr_alignment(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int off, int size) { @@ -896,6 +903,12 @@ static int check_xadd(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EACCES; }

+ if (is_ctx_reg(env, insn->dst_reg)) { + verbose("BPF_XADD stores into R%d context is not allowed\n", + insn->dst_reg); + return -EACCES; + } + /* check whether atomic_add can read the memory */ err = check_mem_access(env, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, -1); @@ -1843,6 +1856,11 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; }

+ if (opcode == BPF_ARSH && BPF_CLASS(insn->code) != BPF_ALU64) { + verbose("BPF_ARSH not supported for 32 bit ALU\n"); + return -EINVAL; + } + if ((opcode == BPF_LSH || opcode == BPF_RSH || opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) { int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32; @@ -3007,6 +3025,12 @@ static int do_check(struct bpf_verifier_env *env) if (err) return err;

+ if (is_ctx_reg(env, insn->dst_reg)) { + verbose("BPF_ST stores into R%d context is not allowed\n", + insn->dst_reg); + return -EACCES; + } + /* check that memory (dst_reg + off) is writeable */ err = check_mem_access(env, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, @@ -3386,6 +3410,24 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)

for (i = 0; i < insn_cnt; i++, insn++) { + if (insn->code == (BPF_ALU | BPF_MOD | BPF_X) || + insn->code == (BPF_ALU | BPF_DIV | BPF_X)) { + /* due to JIT bugs clear upper 32-bits of src register + * before div/mod operation + */ + insn_buf[0] = BPF_MOV32_REG(insn->src_reg, insn->src_reg); + insn_buf[1] = *insn; + cnt = 2; + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + if (insn->code != (BPF_JMP | BPF_CALL)) continue;

diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index eeb7f2f5698d..54fd2fed36e9 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -652,7 +652,9 @@ static void hrtimer_reprogram(struct hrtimer *timer, static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { base->expires_next.tv64 = KTIME_MAX; + base->hang_detected = 0; base->hres_active = 0; + base->next_timer = NULL; }

/* @@ -1610,6 +1612,7 @@ int hrtimers_prepare_cpu(unsigned int cpu) timerqueue_init_head(&cpu_base->clock_base[i].active); }

+ cpu_base->active_bases = 0; cpu_base->cpu = cpu; hrtimer_init_hres(cpu_base); return 0; diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 2e385026915c..98da7520a6aa 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -5646,9 +5646,8 @@ static struct bpf_prog *generate_filter(int which, int *err) return NULL; } } - /* We don't expect to fail. */ if (*err) { - pr_cont("FAIL to attach err=%d len=%d\n", + pr_cont("FAIL to prog_create err=%d len=%d\n", *err, fprog.len); return NULL; } @@ -5671,6 +5670,10 @@ static struct bpf_prog *generate_filter(int which, int *err) * checks. */ fp = bpf_prog_select_runtime(fp, err); + if (*err) { + pr_cont("FAIL to select_runtime err=%d\n", *err); + return NULL; + } break; }

@@ -5856,8 +5859,8 @@ static __init int test_bpf(void) pass_cnt++; continue; } - - return err; + err_cnt++; + continue; }

pr_cont("jited:%u ", fp->jited); diff --git a/mm/cma.c b/mm/cma.c index c960459eda7e..397687fc51f9 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -54,7 +54,7 @@ unsigned long cma_get_size(const struct cma *cma) }

static unsigned long cma_bitmap_aligned_mask(const struct cma *cma, - int align_order) + unsigned int align_order) { if (align_order <= cma->order_per_bit) return 0; @@ -62,17 +62,14 @@ static unsigned long cma_bitmap_aligned_mask(const struct cma *cma, }

/* - * Find a PFN aligned to the specified order and return an offset represented in - * order_per_bits. + * Find the offset of the base PFN from the specified align_order. + * The value returned is represented in order_per_bits. */ static unsigned long cma_bitmap_aligned_offset(const struct cma *cma, - int align_order) + unsigned int align_order) { - if (align_order <= cma->order_per_bit) - return 0; - - return (ALIGN(cma->base_pfn, (1UL << align_order)) - - cma->base_pfn) >> cma->order_per_bit; + return (cma->base_pfn & ((1UL << align_order) - 1)) + >> cma->order_per_bit; }

static unsigned long cma_bitmap_pages_to_bits(const struct cma *cma, diff --git a/mm/internal.h b/mm/internal.h index 34a5459e5989..3e2d01694747 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -73,6 +73,12 @@ static inline void set_page_refcounted(struct page *page)

extern unsigned long highest_memmap_pfn;

+/* + * Maximum number of reclaim retries without progress before the OOM + * killer is consider the only way forward. + */ +#define MAX_RECLAIM_RETRIES 16 + /* * in mm/vmscan.c: */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2a800c4a39bd..50088150fc17 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5531,7 +5531,7 @@ static void uncharge_list(struct list_head *page_list) next = page->lru.next;

VM_BUG_ON_PAGE(PageLRU(page), page); - VM_BUG_ON_PAGE(page_count(page), page); + VM_BUG_ON_PAGE(!PageHWPoison(page) && page_count(page), page);

if (!page->mem_cgroup) continue; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index ce7d416edab7..5aa71a82ca73 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -535,6 +535,13 @@ static int delete_from_lru_cache(struct page *p) */ ClearPageActive(p); ClearPageUnevictable(p); + + /* + * Poisoned page might never drop its ref count to 0 so we have + * to uncharge it manually from its memcg. + */ + mem_cgroup_uncharge(p); + /* * drop the page count elevated by isolate_lru_page() */ diff --git a/mm/mmap.c b/mm/mmap.c index 5b48adb4aa56..45ac5b973459 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2240,7 +2240,8 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) gap_addr = TASK_SIZE;

next = vma->vm_next; - if (next && next->vm_start < gap_addr) { + if (next && next->vm_start < gap_addr && + (next->vm_flags & (VM_WRITE|VM_READ|VM_EXEC))) { if (!(next->vm_flags & VM_GROWSUP)) return -ENOMEM; /* Check that both stack segments have the same anon_vma? */ @@ -2324,7 +2325,8 @@ int expand_downwards(struct vm_area_struct *vma, if (gap_addr > address) return -ENOMEM; prev = vma->vm_prev; - if (prev && prev->vm_end > gap_addr) { + if (prev && prev->vm_end > gap_addr && + (prev->vm_flags & (VM_WRITE|VM_READ|VM_EXEC))) { if (!(prev->vm_flags & VM_GROWSDOWN)) return -ENOMEM; /* Check that both stack segments have the same anon_vma? */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index fbc38888252b..94018ea5f935 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2821,9 +2821,6 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, if (!area->nr_free) continue;

- if (alloc_harder) - return true; - for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) { if (!list_empty(&area->free_list[mt])) return true; @@ -2835,6 +2832,9 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, return true; } #endif + if (alloc_harder && + !list_empty(&area->free_list[MIGRATE_HIGHATOMIC])) + return true; } return false; } @@ -3421,12 +3421,6 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask) return false; }

-/* - * Maximum number of reclaim retries without any progress before OOM killer - * is consider as the only way to move forward. - */ -#define MAX_RECLAIM_RETRIES 16 - /* * Checks whether it makes sense to retry the reclaim to make a forward progress * for the given allocation request. @@ -4385,7 +4379,8 @@ void show_free_areas(unsigned int filter) K(node_page_state(pgdat, NR_WRITEBACK_TEMP)), K(node_page_state(pgdat, NR_UNSTABLE_NFS)), node_page_state(pgdat, NR_PAGES_SCANNED), - !pgdat_reclaimable(pgdat) ? "yes" : "no"); + pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ? + "yes" : "no"); }

for_each_populated_zone(zone) { diff --git a/mm/vmscan.c b/mm/vmscan.c index 30a88b945a44..f118dc23f662 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2606,6 +2606,15 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) } while (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, sc->nr_scanned - nr_scanned, sc));

+ /* + * Kswapd gives up on balancing particular nodes after too + * many failures to reclaim anything from them and goes to + * sleep. On reclaim progress, reset the failure counter. A + * successful direct reclaim run will revive a dormant kswapd. + */ + if (reclaimable) + pgdat->kswapd_failures = 0; + return reclaimable; }

@@ -2680,10 +2689,6 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) GFP_KERNEL | __GFP_HARDWALL)) continue;

- if (sc->priority != DEF_PRIORITY && - !pgdat_reclaimable(zone->zone_pgdat)) - continue; /* Let kswapd poll it */ - /* * If we already have plenty of memory free for * compaction in this zone, don't free any more. @@ -2820,7 +2825,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, return 0; }

-static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) +static bool allow_direct_reclaim(pg_data_t *pgdat) { struct zone *zone; unsigned long pfmemalloc_reserve = 0; @@ -2828,6 +2833,9 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) int i; bool wmark_ok;

+ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) + return true; + for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; if (!managed_zone(zone) || @@ -2908,7 +2916,7 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,

/* Throttle based on the first usable node */ pgdat = zone->zone_pgdat; - if (pfmemalloc_watermark_ok(pgdat)) + if (allow_direct_reclaim(pgdat)) goto out; break; } @@ -2930,14 +2938,14 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, */ if (!(gfp_mask & __GFP_FS)) { wait_event_interruptible_timeout(pgdat->pfmemalloc_wait, - pfmemalloc_watermark_ok(pgdat), HZ); + allow_direct_reclaim(pgdat), HZ);

goto check_pending; }

/* Throttle until kswapd wakes the process */ wait_event_killable(zone->zone_pgdat->pfmemalloc_wait, - pfmemalloc_watermark_ok(pgdat)); + allow_direct_reclaim(pgdat));

check_pending: if (fatal_signal_pending(current)) @@ -3116,7 +3124,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx)

/* * The throttled processes are normally woken up in balance_pgdat() as - * soon as pfmemalloc_watermark_ok() is true. But there is a potential + * soon as allow_direct_reclaim() is true. But there is a potential * race between when kswapd checks the watermarks and a process gets * throttled. There is also a potential race if processes get * throttled, kswapd wakes, a large process exits thereby balancing the @@ -3130,6 +3138,10 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx) if (waitqueue_active(&pgdat->pfmemalloc_wait)) wake_up_all(&pgdat->pfmemalloc_wait);

+ /* Hopeless node, leave it to direct reclaim */ + if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) + return true; + for (i = 0; i <= classzone_idx; i++) { struct zone *zone = pgdat->node_zones + i;

@@ -3216,9 +3228,9 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) count_vm_event(PAGEOUTRUN);

do { + unsigned long nr_reclaimed = sc.nr_reclaimed; bool raise_priority = true;

- sc.nr_reclaimed = 0; sc.reclaim_idx = classzone_idx;

/* @@ -3297,7 +3309,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) * able to safely make forward progress. Wake them */ if (waitqueue_active(&pgdat->pfmemalloc_wait) && - pfmemalloc_watermark_ok(pgdat)) + allow_direct_reclaim(pgdat)) wake_up_all(&pgdat->pfmemalloc_wait);

/* Check if kswapd should be suspending */ @@ -3308,10 +3320,14 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) * Raise priority if scanning rate is too low or there was no * progress in reclaiming pages */ - if (raise_priority || !sc.nr_reclaimed) + nr_reclaimed = sc.nr_reclaimed - nr_reclaimed; + if (raise_priority || !nr_reclaimed) sc.priority--; } while (sc.priority >= 1);

+ if (!sc.nr_reclaimed) + pgdat->kswapd_failures++; + out: /* * Return the order kswapd stopped reclaiming at as @@ -3511,6 +3527,10 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx) if (!waitqueue_active(&pgdat->kswapd_wait)) return;

+ /* Hopeless node, leave it to direct reclaim */ + if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) + return; + /* Only wake kswapd if all zones are unbalanced */ for (z = 0; z <= classzone_idx; z++) { zone = pgdat->node_zones + z; @@ -3781,9 +3801,6 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) sum_zone_node_page_state(pgdat->node_id, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages) return NODE_RECLAIM_FULL;

- if (!pgdat_reclaimable(pgdat)) - return NODE_RECLAIM_FULL; - /* * Do not scan if the allocation should not be delayed. */ diff --git a/mm/vmstat.c b/mm/vmstat.c index 6a088df04b29..3863b5d6d598 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1421,7 +1421,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, "\n node_unreclaimable: %u" "\n start_pfn: %lu" "\n node_inactive_ratio: %u", - !pgdat_reclaimable(zone->zone_pgdat), + pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES, zone->zone_start_pfn, zone->zone_pgdat->inactive_ratio); seq_putc(m, '\n'); diff --git a/net/can/af_can.c b/net/can/af_can.c index 5488e4a6ccd0..ac1552d8b4ad 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -722,13 +722,12 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, if (unlikely(!net_eq(dev_net(dev), &init_net))) goto drop;

- if (WARN_ONCE(dev->type != ARPHRD_CAN || - skb->len != CAN_MTU || - cfd->len > CAN_MAX_DLEN, - "PF_CAN: dropped non conform CAN skbuf: " - "dev type %d, len %d, datalen %d\n", - dev->type, skb->len, cfd->len)) + if (unlikely(dev->type != ARPHRD_CAN || skb->len != CAN_MTU || + cfd->len > CAN_MAX_DLEN)) { + pr_warn_once("PF_CAN: dropped non conform CAN skbuf: dev type %d, len %d, datalen %d\n", + dev->type, skb->len, cfd->len); goto drop; + }

can_receive(skb, dev); return NET_RX_SUCCESS; @@ -746,13 +745,12 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, if (unlikely(!net_eq(dev_net(dev), &init_net))) goto drop;

- if (WARN_ONCE(dev->type != ARPHRD_CAN || - skb->len != CANFD_MTU || - cfd->len > CANFD_MAX_DLEN, - "PF_CAN: dropped non conform CAN FD skbuf: " - "dev type %d, len %d, datalen %d\n", - dev->type, skb->len, cfd->len)) + if (unlikely(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU || + cfd->len > CANFD_MAX_DLEN)) { + pr_warn_once("PF_CAN: dropped non conform CAN FD skbuf: dev type %d, len %d, datalen %d\n", + dev->type, skb->len, cfd->len); goto drop; + }

can_receive(skb, dev); return NET_RX_SUCCESS; diff --git a/net/core/dev.c b/net/core/dev.c index 09007a71c8dd..67b5d4d8acb1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3083,10 +3083,21 @@ static void qdisc_pkt_len_init(struct sk_buff *skb) hdr_len = skb_transport_header(skb) - skb_mac_header(skb);

/* + transport layer */ - if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) - hdr_len += tcp_hdrlen(skb); - else - hdr_len += sizeof(struct udphdr); + if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { + const struct tcphdr *th; + struct tcphdr _tcphdr; + + th = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_tcphdr), &_tcphdr); + if (likely(th)) + hdr_len += __tcp_hdrlen(th); + } else { + struct udphdr _udphdr; + + if (skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_udphdr), &_udphdr)) + hdr_len += sizeof(struct udphdr); + }

if (shinfo->gso_type & SKB_GSO_DODGY) gso_segs = DIV_ROUND_UP(skb->len - hdr_len, diff --git a/net/core/filter.c b/net/core/filter.c index 4eb4ce0aeef4..e8c89d2d2bc0 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -441,6 +441,10 @@ static int bpf_convert_filter(struct sock_filter *prog, int len, convert_bpf_extensions(fp, &insn)) break;

+ if (fp->code == (BPF_ALU | BPF_DIV | BPF_X) || + fp->code == (BPF_ALU | BPF_MOD | BPF_X)) + *insn++ = BPF_MOV32_REG(BPF_REG_X, BPF_REG_X); + *insn = BPF_RAW_INSN(fp->code, BPF_REG_A, BPF_REG_X, 0, fp->k); break;

@@ -1005,11 +1009,9 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) */ goto out_err_free;

- /* We are guaranteed to never error here with cBPF to eBPF - * transitions, since there's no issue with type compatibility - * checks on program arrays. - */ fp = bpf_prog_select_runtime(fp, &err); + if (err) + goto out_err_free;

kfree(old_prog); return fp; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 32e4e0158846..862d63ec56e4 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -550,8 +550,8 @@ bool __skb_flow_dissect(const struct sk_buff *skb, out_good: ret = true;

- key_control->thoff = (u16)nhoff; out: + key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen); key_basic->n_proto = proto; key_basic->ip_proto = ip_proto;

@@ -559,7 +559,6 @@ bool __skb_flow_dissect(const struct sk_buff *skb,

out_bad: ret = false; - key_control->thoff = min_t(u16, nhoff, skb ? skb->len : hlen); goto out; } EXPORT_SYMBOL(__skb_flow_dissect); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index f45f6198851f..7b315663f840 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -496,7 +496,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, if (atomic_read(&tbl->entries) > (1 << nht->hash_shift)) nht = neigh_hash_grow(tbl, nht->hash_shift + 1);

- hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); + hash_val = tbl->hash(n->primary_key, dev, nht->hash_rnd) >> (32 - nht->hash_shift);

if (n->parms->dead) { rc = ERR_PTR(-EINVAL); @@ -508,7 +508,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, n1 != NULL; n1 = rcu_dereference_protected(n1->next, lockdep_is_held(&tbl->lock))) { - if (dev == n1->dev && !memcmp(n1->primary_key, pkey, key_len)) { + if (dev == n1->dev && !memcmp(n1->primary_key, n->primary_key, key_len)) { if (want_ref) neigh_hold(n1); rc = n1; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index a7f05f0130e8..1b4619008c4e 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -292,7 +292,13 @@ static struct ctl_table net_core_table[] = { .data = &bpf_jit_enable, .maxlen = sizeof(int), .mode = 0644, +#ifndef CONFIG_BPF_JIT_ALWAYS_ON .proc_handler = proc_dointvec +#else + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &one, +#endif }, # ifdef CONFIG_HAVE_EBPF_JIT { diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index 5e3a7302f774..7753681195c1 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -140,6 +140,9 @@ static void ccid2_hc_tx_rto_expire(unsigned long data)

ccid2_pr_debug("RTO_EXPIRE\n");

+ if (sk->sk_state == DCCP_CLOSED) + goto out; + /* back-off timer */ hc->tx_rto <<= 1; if (hc->tx_rto > DCCP_RTO_MAX) diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 51b27ae09fbd..e60517eb1c3a 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -223,11 +223,16 @@ static bool arp_key_eq(const struct neighbour *neigh, const void *pkey)

static int arp_constructor(struct neighbour *neigh) { - __be32 addr = *(__be32 *)neigh->primary_key; + __be32 addr; struct net_device *dev = neigh->dev; struct in_device *in_dev; struct neigh_parms *parms; + u32 inaddr_any = INADDR_ANY;

+ if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) + memcpy(neigh->primary_key, &inaddr_any, arp_tbl.key_len); + + addr = *(__be32 *)neigh->primary_key; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (!in_dev) { diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 7bff0c65046f..9c7a4cea1628 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -332,7 +332,7 @@ static __be32 igmpv3_get_srcaddr(struct net_device *dev, return htonl(INADDR_ANY);

for_ifa(in_dev) { - if (inet_ifa_match(fl4->saddr, ifa)) + if (fl4->saddr == ifa->ifa_local) return fl4->saddr; } endfor_ifa(in_dev);

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 05d2bde00864..7efa6b062049 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2215,6 +2215,9 @@ void tcp_close(struct sock *sk, long timeout) tcp_send_active_reset(sk, GFP_ATOMIC); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); + } else if (!check_net(sock_net(sk))) { + /* Not possible to send reset; just close */ + tcp_set_state(sk, TCP_CLOSE); } }

diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index bc68da38ea86..366b1becff9d 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -32,6 +32,9 @@ static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq, static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb, netdev_features_t features) { + if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)) + return ERR_PTR(-EINVAL); + if (!pskb_may_pull(skb, sizeof(struct tcphdr))) return ERR_PTR(-EINVAL);

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 74db43b47917..69523389f067 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -50,11 +50,19 @@ static void tcp_write_err(struct sock *sk) * to prevent DoS attacks. It is called when a retransmission timeout * or zero probe timeout occurs on orphaned socket. * + * Also close if our net namespace is exiting; in that case there is no + * hope of ever communicating again since all netns interfaces are already + * down (or about to be down), and we need to release our dst references, + * which have been moved to the netns loopback interface, so the namespace + * can finish exiting. This condition is only possible if we are a kernel + * socket, as those do not hold references to the namespace. + * * Criteria is still not confirmed experimentally and may change. * We kill the socket, if: * 1. If number of orphaned sockets exceeds an administratively configured * limit. * 2. If we have strong memory pressure. + * 3. If our net namespace is exiting. */ static int tcp_out_of_resources(struct sock *sk, bool do_reset) { @@ -83,6 +91,13 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); return 1; } + + if (!check_net(sock_net(sk))) { + /* Not possible to send reset; just close */ + tcp_done(sk); + return 1; + } + return 0; }

diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 6401574cd638..f4f616eaaeb8 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -205,6 +205,9 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, goto out; }

+ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP)) + goto out; + if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out;

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c46066c5dc27..db2613b4a049 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -337,11 +337,12 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net,

nt->dev = dev; nt->net = dev_net(dev); - ip6gre_tnl_link_config(nt, 1);

if (register_netdevice(dev) < 0) goto failed_free;

+ ip6gre_tnl_link_config(nt, 1); + /* Can use a lockless transmit, unless we generate output sequences */ if (!(nt->parms.o_flags & TUNNEL_SEQ)) dev->features |= NETIF_F_LLTX; @@ -1263,7 +1264,6 @@ static void ip6gre_netlink_parms(struct nlattr *data[],

static int ip6gre_tap_init(struct net_device *dev) { - struct ip6_tnl *tunnel; int ret;

ret = ip6gre_tunnel_init_common(dev); @@ -1272,10 +1272,6 @@ static int ip6gre_tap_init(struct net_device *dev)

dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;

- tunnel = netdev_priv(dev); - - ip6gre_tnl_link_config(tunnel, 1); - return 0; }

@@ -1370,7 +1366,6 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,

nt->dev = dev; nt->net = dev_net(dev); - ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);

dev->features |= GRE6_FEATURES; dev->hw_features |= GRE6_FEATURES; @@ -1396,6 +1391,11 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev, if (err) goto out;

+ ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]); + + if (tb[IFLA_MTU]) + ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); + dev_hold(dev); ip6gre_tunnel_link(ign, nt);

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 388584b8ff31..2e3db3619858 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -156,7 +156,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) !(IP6CB(skb)->flags & IP6SKB_REROUTED)); }

-static bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np) +bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np) { if (!np->autoflowlabel_set) return ip6_default_np_autolabel(net); @@ -1260,14 +1260,16 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, v6_cork->tclass = ipc6->tclass; if (rt->dst.flags & DST_XFRM_TUNNEL) mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? - rt->dst.dev->mtu : dst_mtu(&rt->dst); + READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst); else mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? - rt->dst.dev->mtu : dst_mtu(rt->dst.path); + READ_ONCE(rt->dst.dev->mtu) : dst_mtu(rt->dst.path); if (np->frag_size < mtu) { if (np->frag_size) mtu = np->frag_size; } + if (mtu < IPV6_MIN_MTU) + return -EINVAL; cork->base.fragsize = mtu; if (dst_allfrag(rt->dst.path)) cork->base.flags |= IPCORK_ALLFRAG; @@ -1798,6 +1800,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk, cork.base.flags = 0; cork.base.addr = 0; cork.base.opt = NULL; + cork.base.dst = NULL; v6_cork.opt = NULL; err = ip6_setup_cork(sk, &cork, &v6_cork, ipc6, rt, fl6); if (err) { diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 6e3871c7f8f7..bcea985dd76b 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -1316,7 +1316,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, break;

case IPV6_AUTOFLOWLABEL: - val = np->autoflowlabel; + val = ip6_autoflowlabel(sock_net(sk), np); break;

default: diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index d883c9204c01..278e49cd67d4 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -46,6 +46,9 @@ static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, { struct tcphdr *th;

+ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)) + return ERR_PTR(-EINVAL); + if (!pskb_may_pull(skb, sizeof(*th))) return ERR_PTR(-EINVAL);

diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index e7d378c032cb..2bd2087bd105 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -55,6 +55,9 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, const struct ipv6hdr *ipv6h; struct udphdr *uh;

+ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP)) + goto out; + if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out;

diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 28d065394c09..3f499126727c 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -17,6 +17,7 @@ #include <linux/types.h> #include <linux/list.h> #include <linux/errno.h> +#include <linux/capability.h> #include <net/netlink.h> #include <net/sock.h>

@@ -392,6 +393,9 @@ static int nfnl_cthelper_new(struct net *net, struct sock *nfnl, struct nfnl_cthelper *nlcth; int ret = 0;

+ if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (!tb[NFCTH_NAME] || !tb[NFCTH_TUPLE]) return -EINVAL;

@@ -595,6 +599,9 @@ static int nfnl_cthelper_get(struct net *net, struct sock *nfnl, struct nfnl_cthelper *nlcth; bool tuple_set = false;

+ if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nfnl_cthelper_dump_table, @@ -661,6 +668,9 @@ static int nfnl_cthelper_del(struct net *net, struct sock *nfnl, struct nfnl_cthelper *nlcth, *n; int j = 0, ret;

+ if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (tb[NFCTH_NAME]) helper_name = nla_data(tb[NFCTH_NAME]);

diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index 2455b69b5810..b589a62e68a2 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -19,6 +19,7 @@ #include <linux/module.h> #include <linux/kernel.h>

+#include <linux/capability.h> #include <linux/if.h> #include <linux/inetdevice.h> #include <linux/ip.h> @@ -69,6 +70,9 @@ static int xt_osf_add_callback(struct net *net, struct sock *ctnl, struct xt_osf_finger *kf = NULL, *sf; int err = 0;

+ if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (!osf_attrs[OSF_ATTR_FINGER]) return -EINVAL;

@@ -113,6 +117,9 @@ static int xt_osf_remove_callback(struct net *net, struct sock *ctnl, struct xt_osf_finger *sf; int err = -ENOENT;

+ if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (!osf_attrs[OSF_ATTR_FINGER]) return -EINVAL;

diff --git a/net/sctp/offload.c b/net/sctp/offload.c index 4f5a2b580aa5..6300f28c9588 100644 --- a/net/sctp/offload.c +++ b/net/sctp/offload.c @@ -44,6 +44,9 @@ static struct sk_buff *sctp_gso_segment(struct sk_buff *skb, struct sk_buff *segs = ERR_PTR(-EINVAL); struct sctphdr *sh;

+ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP)) + goto out; + sh = sctp_hdr(skb); if (!pskb_may_pull(skb, sizeof(*sh))) goto out; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 7181ce6c62bf..c472b8391dde 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -83,7 +83,7 @@ static int sctp_writeable(struct sock *sk); static void sctp_wfree(struct sk_buff *skb); static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, - size_t msg_len, struct sock **orig_sk); + size_t msg_len); static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p); static int sctp_wait_for_connect(struct sctp_association *, long *timeo_p); static int sctp_wait_for_accept(struct sock *sk, long timeo); @@ -332,16 +332,14 @@ static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt, if (len < sizeof (struct sockaddr)) return NULL;

+ if (!opt->pf->af_supported(addr->sa.sa_family, opt)) + return NULL; + /* V4 mapped address are really of AF_INET family */ if (addr->sa.sa_family == AF_INET6 && - ipv6_addr_v4mapped(&addr->v6.sin6_addr)) { - if (!opt->pf->af_supported(AF_INET, opt)) - return NULL; - } else { - /* Does this PF support this AF? */ - if (!opt->pf->af_supported(addr->sa.sa_family, opt)) - return NULL; - } + ipv6_addr_v4mapped(&addr->v6.sin6_addr) && + !opt->pf->af_supported(AF_INET, opt)) + return NULL;

/* If we get this far, af is valid. */ af = sctp_get_af_specific(addr->sa.sa_family); @@ -1958,7 +1956,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); if (!sctp_wspace(asoc)) { /* sk can be changed by peel off when waiting for buf. */ - err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len, &sk); + err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); if (err) { if (err == -ESRCH) { /* asoc is already dead. */ @@ -7441,12 +7439,12 @@ void sctp_sock_rfree(struct sk_buff *skb)

/* Helper function to wait for space in the sndbuf. */ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, - size_t msg_len, struct sock **orig_sk) + size_t msg_len) { struct sock *sk = asoc->base.sk; - int err = 0; long current_timeo = *timeo_p; DEFINE_WAIT(wait); + int err = 0;

pr_debug("%s: asoc:%p, timeo:%ld, msg_len:%zu\n", __func__, asoc, *timeo_p, msg_len); @@ -7475,17 +7473,13 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, release_sock(sk); current_timeo = schedule_timeout(current_timeo); lock_sock(sk); - if (sk != asoc->base.sk) { - release_sock(sk); - sk = asoc->base.sk; - lock_sock(sk); - } + if (sk != asoc->base.sk) + goto do_error;

*timeo_p = current_timeo; }

out: - *orig_sk = sk; finish_wait(&asoc->wait, &wait);

/* Release the association's refcnt. */ diff --git a/net/socket.c b/net/socket.c index 05f13b24572c..bd3b33988ee0 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2548,6 +2548,15 @@ static int __init sock_init(void)

core_initcall(sock_init); /* early initcall */

+static int __init jit_init(void) +{ +#ifdef CONFIG_BPF_JIT_ALWAYS_ON + bpf_jit_enable = 1; +#endif + return 0; +} +pure_initcall(jit_init); + #ifdef CONFIG_PROC_FS void socket_seq_show(struct seq_file *seq) { diff --git a/net/tipc/node.c b/net/tipc/node.c index 27753325e06e..5b3e1ea37b6d 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1848,36 +1848,38 @@ int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info)

if (strcmp(name, tipc_bclink_name) == 0) { err = tipc_nl_add_bc_link(net, &msg); - if (err) { - nlmsg_free(msg.skb); - return err; - } + if (err) + goto err_free; } else { int bearer_id; struct tipc_node *node; struct tipc_link *link;

node = tipc_node_find_by_name(net, name, &bearer_id); - if (!node) - return -EINVAL; + if (!node) { + err = -EINVAL; + goto err_free; + }

tipc_node_read_lock(node); link = node->links[bearer_id].link; if (!link) { tipc_node_read_unlock(node); - nlmsg_free(msg.skb); - return -EINVAL; + err = -EINVAL; + goto err_free; }

err = __tipc_nl_add_link(net, &msg, link, 0); tipc_node_read_unlock(node); - if (err) { - nlmsg_free(msg.skb); - return err; - } + if (err) + goto err_free; }

return genlmsg_reply(msg.skb, info); + +err_free: + nlmsg_free(msg.skb); + return err; }

int tipc_nl_node_reset_link_stats(struct sk_buff *skb, struct genl_info *info) diff --git a/tools/usb/usbip/libsrc/usbip_common.c b/tools/usb/usbip/libsrc/usbip_common.c index ac73710473de..1517a232ab18 100644 --- a/tools/usb/usbip/libsrc/usbip_common.c +++ b/tools/usb/usbip/libsrc/usbip_common.c @@ -215,9 +215,16 @@ int read_usb_interface(struct usbip_usb_device *udev, int i, struct usbip_usb_interface *uinf) { char busid[SYSFS_BUS_ID_SIZE]; + int size; struct udev_device *sif;

- sprintf(busid, "%s:%d.%d", udev->busid, udev->bConfigurationValue, i); + size = snprintf(busid, sizeof(busid), "%s:%d.%d", + udev->busid, udev->bConfigurationValue, i); + if (size < 0 || (unsigned int)size >= sizeof(busid)) { + err("busid length %i >= %lu or < 0", size, + (long unsigned)sizeof(busid)); + return -1; + }

sif = udev_device_new_from_subsystem_sysname(udev_context, "usb", busid); if (!sif) { diff --git a/tools/usb/usbip/libsrc/usbip_host_common.c b/tools/usb/usbip/libsrc/usbip_host_common.c index 9d415228883d..6ff7b601f854 100644 --- a/tools/usb/usbip/libsrc/usbip_host_common.c +++ b/tools/usb/usbip/libsrc/usbip_host_common.c @@ -40,13 +40,20 @@ struct udev *udev_context; static int32_t read_attr_usbip_status(struct usbip_usb_device *udev) { char status_attr_path[SYSFS_PATH_MAX]; + int size; int fd; int length; char status; int value = 0;

- snprintf(status_attr_path, SYSFS_PATH_MAX, "%s/usbip_status", - udev->path); + size = snprintf(status_attr_path, sizeof(status_attr_path), + "%s/usbip_status", udev->path); + if (size < 0 || (unsigned int)size >= sizeof(status_attr_path)) { + err("usbip_status path length %i >= %lu or < 0", size, + (long unsigned)sizeof(status_attr_path)); + return -1; + } +

fd = open(status_attr_path, O_RDONLY); if (fd < 0) { @@ -218,6 +225,7 @@ int usbip_export_device(struct usbip_exported_device *edev, int sockfd) { char attr_name[] = "usbip_sockfd"; char sockfd_attr_path[SYSFS_PATH_MAX]; + int size; char sockfd_buff[30]; int ret;

@@ -237,10 +245,20 @@ int usbip_export_device(struct usbip_exported_device *edev, int sockfd) }

/* only the first interface is true */ - snprintf(sockfd_attr_path, sizeof(sockfd_attr_path), "%s/%s", - edev->udev.path, attr_name); + size = snprintf(sockfd_attr_path, sizeof(sockfd_attr_path), "%s/%s", + edev->udev.path, attr_name); + if (size < 0 || (unsigned int)size >= sizeof(sockfd_attr_path)) { + err("exported device path length %i >= %lu or < 0", size, + (long unsigned)sizeof(sockfd_attr_path)); + return -1; + }

- snprintf(sockfd_buff, sizeof(sockfd_buff), "%d\n", sockfd); + size = snprintf(sockfd_buff, sizeof(sockfd_buff), "%d\n", sockfd); + if (size < 0 || (unsigned int)size >= sizeof(sockfd_buff)) { + err("socket length %i >= %lu or < 0", size, + (long unsigned)sizeof(sockfd_buff)); + return -1; + }

ret = write_sysfs_attribute(sockfd_attr_path, sockfd_buff, strlen(sockfd_buff)); diff --git a/tools/usb/usbip/libsrc/vhci_driver.c b/tools/usb/usbip/libsrc/vhci_driver.c index ad9204773533..1274f326242c 100644 --- a/tools/usb/usbip/libsrc/vhci_driver.c +++ b/tools/usb/usbip/libsrc/vhci_driver.c @@ -55,12 +55,12 @@ static int parse_status(const char *value)

while (*c != '\0') { int port, status, speed, devid; - unsigned long socket; + int sockfd; char lbusid[SYSFS_BUS_ID_SIZE];

- ret = sscanf(c, "%d %d %d %x %lx %31s\n", + ret = sscanf(c, "%d %d %d %x %u %31s\n", &port, &status, &speed, - &devid, &socket, lbusid); + &devid, &sockfd, lbusid);

if (ret < 5) { dbg("sscanf failed: %d", ret); @@ -69,7 +69,7 @@ static int parse_status(const char *value)

dbg("port %d status %d speed %d devid %x", port, status, speed, devid); - dbg("socket %lx lbusid %s", socket, lbusid); + dbg("sockfd %u lbusid %s", sockfd, lbusid);

/* if a device is connected, look at it */ diff --git a/tools/usb/usbip/src/usbip.c b/tools/usb/usbip/src/usbip.c index d7599d943529..73d8eee8130b 100644 --- a/tools/usb/usbip/src/usbip.c +++ b/tools/usb/usbip/src/usbip.c @@ -176,6 +176,8 @@ int main(int argc, char *argv[]) break; case '?': printf("usbip: invalid option\n"); + /* Terminate after printing error */ + /* FALLTHRU */ default: usbip_usage(); goto out;