diff options
316 files changed, 3420 insertions, 2086 deletions
diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt index d515d58962b9..2a3904030dea 100644 --- a/Documentation/block/queue-sysfs.txt +++ b/Documentation/block/queue-sysfs.txt @@ -14,6 +14,12 @@ add_random (RW) This file allows to turn off the disk entropy contribution. Default value of this file is '1'(on). +dax (RO) +-------- +This file indicates whether the device supports Direct Access (DAX), +used by CPU-addressable storage to bypass the pagecache. It shows '1' +if true, '0' if not. + discard_granularity (RO) ----------------------- This shows the size of internal allocation of the device in bytes, if @@ -46,6 +52,12 @@ hw_sector_size (RO) ------------------- This is the hardware sector size of the device, in bytes. +io_poll (RW) +------------ +When read, this file shows the total number of block IO polls and how +many returned success. Writing '0' to this file will disable polling +for this device. Writing any non-zero value will enable this feature. + iostats (RW) ------------- This file is used to control (on/off) the iostats accounting of the @@ -151,5 +163,11 @@ device state. This means that it might not be safe to toggle the setting from "write back" to "write through", since that will also eliminate cache flushes issued by the kernel. +write_same_max_bytes (RO) +------------------------- +This is the number of bytes the device can write in a single write-same +command. A value of '0' means write-same is not supported by this +device. + Jens Axboe <jens.axboe@oracle.com>, February 2009 diff --git a/Documentation/networking/rxrpc.txt b/Documentation/networking/rxrpc.txt index 16a924c486bf..70c926ae212d 100644 --- a/Documentation/networking/rxrpc.txt +++ b/Documentation/networking/rxrpc.txt @@ -790,13 +790,12 @@ The kernel interface functions are as follows: Data messages can have their contents extracted with the usual bunch of socket buffer manipulation functions. A data message can be determined to be the last one in a sequence with rxrpc_kernel_is_data_last(). When a - data message has been used up, rxrpc_kernel_data_delivered() should be - called on it.. + data message has been used up, rxrpc_kernel_data_consumed() should be + called on it. - Non-data messages should be handled to rxrpc_kernel_free_skb() to dispose - of. It is possible to get extra refs on all types of message for later - freeing, but this may pin the state of a call until the message is finally - freed. + Messages should be handled to rxrpc_kernel_free_skb() to dispose of. It + is possible to get extra refs on all types of message for later freeing, + but this may pin the state of a call until the message is finally freed. (*) Accept an incoming call. @@ -821,12 +820,14 @@ The kernel interface functions are as follows: Other errors may be returned if the call had been aborted (-ECONNABORTED) or had timed out (-ETIME). - (*) Record the delivery of a data message and free it. + (*) Record the delivery of a data message. - void rxrpc_kernel_data_delivered(struct sk_buff *skb); + void rxrpc_kernel_data_consumed(struct rxrpc_call *call, + struct sk_buff *skb); - This is used to record a data message as having been delivered and to - update the ACK state for the call. The socket buffer will be freed. + This is used to record a data message as having been consumed and to + update the ACK state for the call. The message must still be passed to + rxrpc_kernel_free_skb() for disposal by the caller. (*) Free a message. @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 8 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Psychotic Stoned Sheep # *DOCUMENTATION* diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index d94bb9093ead..75f130ef6504 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -1009,9 +1009,13 @@ long kvm_arch_vm_ioctl(struct file *filp, switch (ioctl) { case KVM_CREATE_IRQCHIP: { + int ret; if (!vgic_present) return -ENXIO; - return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); + mutex_lock(&kvm->lock); + ret = kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); + mutex_unlock(&kvm->lock); + return ret; } case KVM_ARM_SET_DEVICE_ADDR: { struct kvm_arm_device_addr dev_addr; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 0555b7caaf2c..eadf4855ad2d 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -1,4 +1,3 @@ -# CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_AUDIT=y @@ -15,10 +14,14 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_MEMCG=y CONFIG_MEMCG_SWAP=y +CONFIG_BLK_CGROUP=y +CONFIG_CGROUP_PIDS=y CONFIG_CGROUP_HUGETLB=y -# CONFIG_UTS_NS is not set -# CONFIG_IPC_NS is not set -# CONFIG_NET_NS is not set +CONFIG_CPUSETS=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_PERF=y +CONFIG_USER_NS=y CONFIG_SCHED_AUTOGROUP=y CONFIG_BLK_DEV_INITRD=y CONFIG_KALLSYMS_ALL=y @@ -71,6 +74,7 @@ CONFIG_PREEMPT=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CMA=y +CONFIG_SECCOMP=y CONFIG_XEN=y CONFIG_KEXEC=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set @@ -84,10 +88,37 @@ CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y CONFIG_INET=y +CONFIG_IP_MULTICAST=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_IPV6 is not set +CONFIG_IPV6=m +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=m +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m +CONFIG_NETFILTER_XT_TARGET_LOG=m +CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m +CONFIG_NF_CONNTRACK_IPV4=m +CONFIG_IP_NF_IPTABLES=m +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP_NF_NAT=m +CONFIG_IP_NF_TARGET_MASQUERADE=m +CONFIG_IP_NF_MANGLE=m +CONFIG_NF_CONNTRACK_IPV6=m +CONFIG_IP6_NF_IPTABLES=m +CONFIG_IP6_NF_FILTER=m +CONFIG_IP6_NF_TARGET_REJECT=m +CONFIG_IP6_NF_MANGLE=m +CONFIG_IP6_NF_NAT=m +CONFIG_IP6_NF_TARGET_MASQUERADE=m +CONFIG_BRIDGE=m +CONFIG_BRIDGE_VLAN_FILTERING=y +CONFIG_VLAN_8021Q=m +CONFIG_VLAN_8021Q_GVRP=y +CONFIG_VLAN_8021Q_MVRP=y CONFIG_BPF_JIT=y CONFIG_CFG80211=m CONFIG_MAC80211=m @@ -103,6 +134,7 @@ CONFIG_MTD=y CONFIG_MTD_M25P80=y CONFIG_MTD_SPI_NOR=y CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_NBD=m CONFIG_VIRTIO_BLK=y CONFIG_SRAM=y # CONFIG_SCSI_PROC_FS is not set @@ -120,7 +152,10 @@ CONFIG_SATA_SIL24=y CONFIG_PATA_PLATFORM=y CONFIG_PATA_OF_PLATFORM=y CONFIG_NETDEVICES=y +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m CONFIG_TUN=y +CONFIG_VETH=m CONFIG_VIRTIO_NET=y CONFIG_AMD_XGBE=y CONFIG_NET_XGENE=y @@ -350,12 +385,16 @@ CONFIG_EXYNOS_ADC=y CONFIG_PWM_SAMSUNG=y CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_BTRFS_FS=m +CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_FANOTIFY=y CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y CONFIG_QUOTA=y CONFIG_AUTOFS4_FS=y -CONFIG_FUSE_FS=y -CONFIG_CUSE=y +CONFIG_FUSE_FS=m +CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_VFAT_FS=y CONFIG_TMPFS=y CONFIG_HUGETLBFS=y diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h index 61b49150dfa3..1737aecfcc5e 100644 --- a/arch/arm64/include/asm/kprobes.h +++ b/arch/arm64/include/asm/kprobes.h @@ -22,7 +22,6 @@ #define __ARCH_WANT_KPROBES_INSN_SLOT #define MAX_INSN_SIZE 1 -#define MAX_STACK_SIZE 128 #define flush_insn_slot(p) do { } while (0) #define kretprobe_blacklist_size 0 @@ -47,7 +46,6 @@ struct kprobe_ctlblk { struct prev_kprobe prev_kprobe; struct kprobe_step_ctx ss_ctx; struct pt_regs jprobe_saved_regs; - char jprobes_stack[MAX_STACK_SIZE]; }; void arch_remove_kprobe(struct kprobe *); diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 96e4a2b64cc1..441420ca7d08 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -353,6 +353,8 @@ el1_sync: lsr x24, x1, #ESR_ELx_EC_SHIFT // exception class cmp x24, #ESR_ELx_EC_DABT_CUR // data abort in EL1 b.eq el1_da + cmp x24, #ESR_ELx_EC_IABT_CUR // instruction abort in EL1 + b.eq el1_ia cmp x24, #ESR_ELx_EC_SYS64 // configurable trap b.eq el1_undef cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception @@ -364,6 +366,11 @@ el1_sync: cmp x24, #ESR_ELx_EC_BREAKPT_CUR // debug exception in EL1 b.ge el1_dbg b el1_inv + +el1_ia: + /* + * Fall through to the Data abort case + */ el1_da: /* * Data abort handling diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 21ab5df9fa76..65d81f965e74 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -35,6 +35,7 @@ #include <asm/sections.h> #include <asm/smp.h> #include <asm/suspend.h> +#include <asm/sysreg.h> #include <asm/virt.h> /* @@ -217,12 +218,22 @@ static int create_safe_exec_page(void *src_start, size_t length, set_pte(pte, __pte(virt_to_phys((void *)dst) | pgprot_val(PAGE_KERNEL_EXEC))); - /* Load our new page tables */ - asm volatile("msr ttbr0_el1, %0;" - "isb;" - "tlbi vmalle1is;" - "dsb ish;" - "isb" : : "r"(virt_to_phys(pgd))); + /* + * Load our new page tables. A strict BBM approach requires that we + * ensure that TLBs are free of any entries that may overlap with the + * global mappings we are about to install. + * + * For a real hibernate/resume cycle TTBR0 currently points to a zero + * page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI + * runtime services), while for a userspace-driven test_resume cycle it + * points to userspace page tables (and we must point it at a zero page + * ourselves). Elsewhere we only (un)install the idmap with preemption + * disabled, so T0SZ should be as required regardless. + */ + cpu_set_reserved_ttbr0(); + local_flush_tlb_all(); + write_sysreg(virt_to_phys(pgd), ttbr0_el1); + isb(); *phys_dst_addr = virt_to_phys((void *)dst); @@ -394,6 +405,38 @@ int swsusp_arch_resume(void) void *, phys_addr_t, phys_addr_t); /* + * Restoring the memory image will overwrite the ttbr1 page tables. + * Create a second copy of just the linear map, and use this when + * restoring. + */ + tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC); + if (!tmp_pg_dir) { + pr_err("Failed to allocate memory for temporary page tables."); + rc = -ENOMEM; + goto out; + } + rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0); + if (rc) + goto out; + + /* + * Since we only copied the linear map, we need to find restore_pblist's + * linear map address. + */ + lm_restore_pblist = LMADDR(restore_pblist); + + /* + * We need a zero page that is zero before & after resume in order to + * to break before make on the ttbr1 page tables. + */ + zero_page = (void *)get_safe_page(GFP_ATOMIC); + if (!zero_page) { + pr_err("Failed to allocate zero page."); + rc = -ENOMEM; + goto out; + } + + /* * Locate the exit code in the bottom-but-one page, so that *NULL * still has disastrous affects. */ @@ -419,27 +462,6 @@ int swsusp_arch_resume(void) __flush_dcache_area(hibernate_exit, exit_size); /* - * Restoring the memory image will overwrite the ttbr1 page tables. - * Create a second copy of just the linear map, and use this when - * restoring. - */ - tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC); - if (!tmp_pg_dir) { - pr_err("Failed to allocate memory for temporary page tables."); - rc = -ENOMEM; - goto out; - } - rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0); - if (rc) - goto out; - - /* - * Since we only copied the linear map, we need to find restore_pblist's - * linear map address. - */ - lm_restore_pblist = LMADDR(restore_pblist); - - /* * KASLR will cause the el2 vectors to be in a different location in * the resumed kernel. Load hibernate's temporary copy into el2. * @@ -453,12 +475,6 @@ int swsusp_arch_resume(void) __hyp_set_vectors(el2_vectors); } - /* - * We need a zero page that is zero before & after resume in order to - * to break before make on the ttbr1 page tables. - */ - zero_page = (void *)get_safe_page(GFP_ATOMIC); - hibernate_exit(virt_to_phys(tmp_pg_dir), resume_hdr.ttbr1_el1, resume_hdr.reenter_kernel, lm_restore_pblist, resume_hdr.__hyp_stub_vectors, virt_to_phys(zero_page)); diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index bf9768588288..c6b0f40620d8 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -41,18 +41,6 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); static void __kprobes post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *); -static inline unsigned long min_stack_size(unsigned long addr) -{ - unsigned long size; - - if (on_irq_stack(addr, raw_smp_processor_id())) - size = IRQ_STACK_PTR(raw_smp_processor_id()) - addr; - else - size = (unsigned long)current_thread_info() + THREAD_START_SP - addr; - - return min(size, FIELD_SIZEOF(struct kprobe_ctlblk, jprobes_stack)); -} - static void __kprobes arch_prepare_ss_slot(struct kprobe *p) { /* prepare insn slot */ @@ -489,20 +477,15 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct jprobe *jp = container_of(p, struct jprobe, kp); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - long stack_ptr = kernel_stack_pointer(regs); kcb->jprobe_saved_regs = *regs; /* - * As Linus pointed out, gcc assumes that the callee - * owns the argument space and could overwrite it, e.g. - * tailcall optimization. So, to be absolutely safe - * we also save and restore enough stack bytes to cover - * the argument area. + * Since we can't be sure where in the stack frame "stacked" + * pass-by-value arguments are stored we just don't try to + * duplicate any of the stack. Do not use jprobes on functions that + * use more than 64 bytes (after padding each to an 8 byte boundary) + * of arguments, or pass individual arguments larger than 16 bytes. */ - kasan_disable_current(); - memcpy(kcb->jprobes_stack, (void *)stack_ptr, - min_stack_size(stack_ptr)); - kasan_enable_current(); instruction_pointer_set(regs, (unsigned long) jp->entry); preempt_disable(); @@ -554,10 +537,6 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) } unpause_graph_tracing(); *regs = kcb->jprobe_saved_regs; - kasan_disable_current(); - memcpy((void *)stack_addr, kcb->jprobes_stack, - min_stack_size(stack_addr)); - kasan_enable_current(); preempt_enable_no_resched(); return 1; } diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 76a6d9263908..d93d43352504 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -661,9 +661,9 @@ void __init smp_init_cpus(void) acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, acpi_parse_gic_cpu_interface, 0); - if (cpu_count > NR_CPUS) - pr_warn("no. of cores (%d) greater than configured maximum of %d - clipping\n", - cpu_count, NR_CPUS); + if (cpu_count > nr_cpu_ids) + pr_warn("Number of cores (%d) exceeds configured maximum of %d - clipping\n", + cpu_count, nr_cpu_ids); if (!bootcpu_valid) { pr_err("missing boot CPU MPIDR, not enabling secondaries\n"); @@ -677,7 +677,7 @@ void __init smp_init_cpus(void) * with entries in cpu_logical_map while initializing the cpus. * If the cpu set-up fails, invalidate the cpu_logical_map entry. */ - for (i = 1; i < NR_CPUS; i++) { + for (i = 1; i < nr_cpu_ids; i++) { if (cpu_logical_map(i) != INVALID_HWID) { if (smp_cpu_setup(i)) cpu_logical_map(i) = INVALID_HWID; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index c8beaa0da7df..05d2bd776c69 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -153,6 +153,11 @@ int ptep_set_access_flags(struct vm_area_struct *vma, } #endif +static bool is_el1_instruction_abort(unsigned int esr) +{ + return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR; +} + /* * The kernel tried to access some page that wasn't present. */ @@ -161,8 +166,9 @@ static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr, { /* * Are we prepared to handle this kernel fault? + * We are almost certainly not prepared to handle instruction faults. */ - if (fixup_exception(regs)) + if (!is_el1_instruction_abort(esr) && fixup_exception(regs)) return; /* @@ -267,7 +273,8 @@ static inline bool is_permission_fault(unsigned int esr) unsigned int ec = ESR_ELx_EC(esr); unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE; - return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM); + return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM) || + (ec == ESR_ELx_EC_IABT_CUR && fsc_type == ESR_ELx_FSC_PERM); } static bool is_el0_instruction_abort(unsigned int esr) @@ -312,6 +319,9 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, if (regs->orig_addr_limit == KERNEL_DS) die("Accessing user space memory with fs=KERNEL_DS", regs, esr); + if (is_el1_instruction_abort(esr)) + die("Attempting to execute userspace memory", regs, esr); + if (!search_exception_tables(regs->pc)) die("Accessing user space memory outside uaccess.h routines", regs, esr); } diff --git a/arch/h8300/include/asm/io.h b/arch/h8300/include/asm/io.h index 2e221c5f0203..f86918aed9e1 100644 --- a/arch/h8300/include/asm/io.h +++ b/arch/h8300/include/asm/io.h @@ -3,6 +3,8 @@ #ifdef __KERNEL__ +#include <linux/types.h> + /* H8/300 internal I/O functions */ #define __raw_readb __raw_readb diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index 2dcee3a88867..9202f82dfce6 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -213,7 +213,6 @@ static inline int frame_extra_sizes(int f) static inline void adjustformat(struct pt_regs *regs) { - ((struct switch_stack *)regs - 1)->a5 = current->mm->start_data; /* * set format byte to make stack appear modulo 4, which it will * be when doing the rte diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 6eb52b9c9818..e788515f766b 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -1642,8 +1642,14 @@ enum emulation_result kvm_mips_emulate_cache(union mips_instruction inst, preempt_disable(); if (KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG0) { - if (kvm_mips_host_tlb_lookup(vcpu, va) < 0) - kvm_mips_handle_kseg0_tlb_fault(va, vcpu); + if (kvm_mips_host_tlb_lookup(vcpu, va) < 0 && + kvm_mips_handle_kseg0_tlb_fault(va, vcpu)) { + kvm_err("%s: handling mapped kseg0 tlb fault for %lx, vcpu: %p, ASID: %#lx\n", + __func__, va, vcpu, read_c0_entryhi()); + er = EMULATE_FAIL; + preempt_enable(); + goto done; + } } else if ((KVM_GUEST_KSEGX(va) < KVM_GUEST_KSEG0) || KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG23) { int index; @@ -1680,12 +1686,18 @@ enum emulation_result kvm_mips_emulate_cache(union mips_instruction inst, run, vcpu); preempt_enable(); goto dont_update_pc; - } else { - /* - * We fault an entry from the guest tlb to the - * shadow host TLB - */ - kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb); + } + /* + * We fault an entry from the guest tlb to the + * shadow host TLB + */ + if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb)) { + kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n", + __func__, va, index, vcpu, + read_c0_entryhi()); + er = EMULATE_FAIL; + preempt_enable(); + goto done; } } } else { @@ -2659,7 +2671,12 @@ enum emulation_result kvm_mips_handle_tlbmiss(u32 cause, * OK we have a Guest TLB entry, now inject it into the * shadow host TLB */ - kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb); + if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb)) { + kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n", + __func__, va, index, vcpu, + read_c0_entryhi()); + er = EMULATE_FAIL; + } } } diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index 57319ee57c4f..6cfdcf55572d 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -99,7 +99,7 @@ int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr, } gfn = (KVM_GUEST_CPHYSADDR(badvaddr) >> PAGE_SHIFT); - if (gfn >= kvm->arch.guest_pmap_npages) { + if ((gfn | 1) >= kvm->arch.guest_pmap_npages) { kvm_err("%s: Invalid gfn: %#llx, BadVaddr: %#lx\n", __func__, gfn, badvaddr); kvm_mips_dump_host_tlbs(); @@ -138,35 +138,49 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu, unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0; struct kvm *kvm = vcpu->kvm; kvm_pfn_t pfn0, pfn1; + gfn_t gfn0, gfn1; + long tlb_lo[2]; int ret; - if ((tlb->tlb_hi & VPN2_MASK) == 0) { - pfn0 = 0; - pfn1 = 0; - } else { - if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo[0]) - >> PAGE_SHIFT) < 0) - return -1; - - if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo[1]) - >> PAGE_SHIFT) < 0) - return -1; - - pfn0 = kvm->arch.guest_pmap[ - mips3_tlbpfn_to_paddr(tlb->tlb_lo[0]) >> PAGE_SHIFT]; - pfn1 = kvm->arch.guest_pmap[ - mips3_tlbpfn_to_paddr(tlb->tlb_lo[1]) >> PAGE_SHIFT]; + tlb_lo[0] = tlb->tlb_lo[0]; + tlb_lo[1] = tlb->tlb_lo[1]; + + /* + * The commpage address must not be mapped to anything else if the guest + * TLB contains entries nearby, or commpage accesses will break. + */ + if (!((tlb->tlb_hi ^ KVM_GUEST_COMMPAGE_ADDR) & + VPN2_MASK & (PAGE_MASK << 1))) + tlb_lo[(KVM_GUEST_COMMPAGE_ADDR >> PAGE_SHIFT) & 1] = 0; + + gfn0 = mips3_tlbpfn_to_paddr(tlb_lo[0]) >> PAGE_SHIFT; + gfn1 = mips3_tlbpfn_to_paddr(tlb_lo[1]) >> PAGE_SHIFT; + if (gfn0 >= kvm->arch.guest_pmap_npages || + gfn1 >= kvm->arch.guest_pmap_npages) { + kvm_err("%s: Invalid gfn: [%#llx, %#llx], EHi: %#lx\n", + __func__, gfn0, gfn1, tlb->tlb_hi); + kvm_mips_dump_guest_tlbs(vcpu); + return -1; } + if (kvm_mips_map_page(kvm, gfn0) < 0) + return -1; + + if (kvm_mips_map_page(kvm, gfn1) < 0) + return -1; + + pfn0 = kvm->arch.guest_pmap[gfn0]; + pfn1 = kvm->arch.guest_pmap[gfn1]; + /* Get attributes from the Guest TLB */ entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | ((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) | - (tlb->tlb_lo[0] & ENTRYLO_D) | - (tlb->tlb_lo[0] & ENTRYLO_V); + (tlb_lo[0] & ENTRYLO_D) | + (tlb_lo[0] & ENTRYLO_V); entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | ((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) | - (tlb->tlb_lo[1] & ENTRYLO_D) | - (tlb->tlb_lo[1] & ENTRYLO_V); + (tlb_lo[1] & ENTRYLO_D) | + (tlb_lo[1] & ENTRYLO_V); kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc, tlb->tlb_lo[0], tlb->tlb_lo[1]); @@ -354,9 +368,15 @@ u32 kvm_get_inst(u32 *opc, struct kvm_vcpu *vcpu) local_irq_restore(flags); return KVM_INVALID_INST; } - kvm_mips_handle_mapped_seg_tlb_fault(vcpu, - &vcpu->arch. - guest_tlb[index]); + if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, + &vcpu->arch.guest_tlb[index])) { + kvm_err("%s: handling mapped seg tlb fault failed for %p, index: %u, vcpu: %p, ASID: %#lx\n", + __func__, opc, index, vcpu, + read_c0_entryhi()); + kvm_mips_dump_guest_tlbs(vcpu); + local_irq_restore(flags); + return KVM_INVALID_INST; + } inst = *(opc); } local_irq_restore(flags); diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index ca254546cd05..1934707bf321 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -66,29 +66,28 @@ endif UTS_MACHINE := $(OLDARCH) ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y) -override CC += -mlittle-endian -ifneq ($(cc-name),clang) -override CC += -mno-strict-align -endif -override AS += -mlittle-endian override LD += -EL -override CROSS32CC += -mlittle-endian override CROSS32AS += -mlittle-endian LDEMULATION := lppc GNUTARGET := powerpcle MULTIPLEWORD := -mno-multiple KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-save-toc-indirect) else -ifeq ($(call cc-option-yn,-mbig-endian),y) -override CC += -mbig-endian -override AS += -mbig-endian -endif override LD += -EB LDEMULATION := ppc GNUTARGET := powerpc MULTIPLEWORD := -mmultiple endif +cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian) +cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mlittle-endian +ifneq ($(cc-name),clang) + cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mno-strict-align +endif + +aflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian) +aflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mlittle-endian + ifeq ($(HAS_BIARCH),y) override AS += -a$(CONFIG_WORD_SIZE) override LD += -m elf$(CONFIG_WORD_SIZE)$(LDEMULATION) @@ -232,6 +231,9 @@ cpu-as-$(CONFIG_E200) += -Wa,-me200 KBUILD_AFLAGS += $(cpu-as-y) KBUILD_CFLAGS += $(cpu-as-y) +KBUILD_AFLAGS += $(aflags-y) +KBUILD_CFLAGS += $(cflags-y) + head-y := arch/powerpc/kernel/head_$(CONFIG_WORD_SIZE).o head-$(CONFIG_8xx) := arch/powerpc/kernel/head_8xx.o head-$(CONFIG_40x) := arch/powerpc/kernel/head_40x.o diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c index bfe3d37a24ef..9fa046d56eba 100644 --- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c +++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c @@ -4,6 +4,7 @@ #include <linux/module.h> #include <linux/string.h> #include <linux/kernel.h> +#include <linux/cpufeature.h> #include <asm/switch_to.h> #define CHKSUM_BLOCK_SIZE 1 @@ -157,7 +158,7 @@ static void __exit crc32c_vpmsum_mod_fini(void) crypto_unregister_shash(&alg); } -module_init(crc32c_vpmsum_mod_init); +module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, crc32c_vpmsum_mod_init); module_exit(crc32c_vpmsum_mod_fini); MODULE_AUTHOR("Anton Blanchard <anton@samba.org>"); diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h index 3d7fc06532a1..01b8a13f0224 100644 --- a/arch/powerpc/include/asm/cpuidle.h +++ b/arch/powerpc/include/asm/cpuidle.h @@ -19,4 +19,17 @@ extern u64 pnv_first_deep_stop_state; #endif +/* Idle state entry routines */ +#ifdef CONFIG_PPC_P7_NAP +#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \ + /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \ + std r0,0(r1); \ + ptesync; \ + ld r0,0(r1); \ +1: cmp cr0,r0,r0; \ + bne 1b; \ + IDLE_INST; \ + b . +#endif /* CONFIG_PPC_P7_NAP */ + #endif diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index 57fec8ac7b92..ddf54f5bbdd1 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -186,6 +186,7 @@ label##3: \ #ifndef __ASSEMBLY__ void apply_feature_fixups(void); +void setup_feature_keys(void); #endif #endif /* __ASM_POWERPC_FEATURE_FIXUPS_H */ diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h index 0a74ebe934e1..17c8380673a6 100644 --- a/arch/powerpc/include/asm/switch_to.h +++ b/arch/powerpc/include/asm/switch_to.h @@ -75,14 +75,6 @@ static inline void disable_kernel_spe(void) static inline void __giveup_spe(struct task_struct *t) { } #endif -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -extern void flush_tmregs_to_thread(struct task_struct *); -#else -static inline void flush_tmregs_to_thread(struct task_struct *t) -{ -} -#endif - static inline void clear_task_ebb(struct task_struct *t) { #ifdef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h index f5f729c11578..f0b238516e9b 100644 --- a/arch/powerpc/include/asm/xics.h +++ b/arch/powerpc/include/asm/xics.h @@ -159,6 +159,8 @@ extern void xics_teardown_cpu(void); extern void xics_kexec_teardown_cpu(int secondary); extern void xics_migrate_irqs_away(void); extern void icp_native_eoi(struct irq_data *d); +extern int xics_set_irq_type(struct irq_data *d, unsigned int flow_type); +extern int xics_retrigger(struct irq_data *data); #ifdef CONFIG_SMP extern int xics_get_irq_server(unsigned int virq, const struct cpumask *cpumask, unsigned int strict_check); diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index c9bc78e9c610..7429556eb8df 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -168,10 +168,10 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len) int n = 0, l = 0; char buffer[128]; - n += scnprintf(buf+n, len-n, "%04x:%02x:%02x:%01x\n", + n += scnprintf(buf+n, len-n, "%04x:%02x:%02x.%01x\n", edev->phb->global_number, pdn->busno, PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); - pr_warn("EEH: of node=%04x:%02x:%02x:%01x\n", + pr_warn("EEH: of node=%04x:%02x:%02x.%01x\n", edev->phb->global_number, pdn->busno, PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 41091fdf9bd8..df6d45eb4115 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -144,29 +144,14 @@ machine_check_pSeries_1: * vector */ SET_SCRATCH0(r13) /* save r13 */ -#ifdef CONFIG_PPC_P7_NAP -BEGIN_FTR_SECTION - /* Running native on arch 2.06 or later, check if we are - * waking up from nap. We only handle no state loss and - * supervisor state loss. We do -not- handle hypervisor - * state loss at this time. + /* + * Running native on arch 2.06 or later, we may wakeup from winkle + * inside machine check. If yes, then last bit of HSPGR0 would be set + * to 1. Hence clear it unconditionally. */ - mfspr r13,SPRN_SRR1 - rlwinm. r13,r13,47-31,30,31 - OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR) - beq 9f - - mfspr r13,SPRN_SRR1 - rlwinm. r13,r13,47-31,30,31 - /* waking up from powersave (nap) state */ - cmpwi cr1,r13,2 - /* Total loss of HV state is fatal. let's just stay stuck here */ - OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR) - bgt cr1,. -9: - OPT_SET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR) -END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) -#endif /* CONFIG_PPC_P7_NAP */ + GET_PACA(r13) + clrrdi r13,r13,1 + SET_PACA(r13) EXCEPTION_PROLOG_0(PACA_EXMC) BEGIN_FTR_SECTION b machine_check_powernv_early @@ -1273,25 +1258,51 @@ machine_check_handle_early: * Check if thread was in power saving mode. We come here when any * of the following is true: * a. thread wasn't in power saving mode - * b. thread was in power saving mode with no state loss or - * supervisor state loss + * b. thread was in power saving mode with no state loss, + * supervisor state loss or hypervisor state loss. * - * Go back to nap again if (b) is true. + * Go back to nap/sleep/winkle mode again if (b) is true. */ rlwinm. r11,r12,47-31,30,31 /* Was it in power saving mode? */ beq 4f /* No, it wasn;t */ /* Thread was in power saving mode. Go back to nap again. */ cmpwi r11,2 - bne 3f - /* Supervisor state loss */ + blt 3f + /* Supervisor/Hypervisor state loss */ li r0,1 stb r0,PACA_NAPSTATELOST(r13) 3: bl machine_check_queue_event MACHINE_CHECK_HANDLER_WINDUP GET_PACA(r13) ld r1,PACAR1(r13) - li r3,PNV_THREAD_NAP - b pnv_enter_arch207_idle_mode + /* + * Check what idle state this CPU was in and go back to same mode + * again. + */ + lbz r3,PACA_THREAD_IDLE_STATE(r13) + cmpwi r3,PNV_THREAD_NAP + bgt 10f + IDLE_STATE_ENTER_SEQ(PPC_NAP) + /* No return */ +10: + cmpwi r3,PNV_THREAD_SLEEP + bgt 2f + IDLE_STATE_ENTER_SEQ(PPC_SLEEP) + /* No return */ + +2: + /* + * Go back to winkle. Please note that this thread was woken up in + * machine check from winkle and have not restored the per-subcore + * state. Hence before going back to winkle, set last bit of HSPGR0 + * to 1. This will make sure that if this thread gets woken up + * again at reset vector 0x100 then it will get chance to restore + * the subcore state. + */ + ori r13,r13,1 + SET_PACA(r13) + IDLE_STATE_ENTER_SEQ(PPC_WINKLE) + /* No return */ 4: #endif /* diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index ba79d15f4ddd..2265c6398a17 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -44,18 +44,6 @@ PSSCR_PSLL_MASK | PSSCR_TR_MASK | \ PSSCR_MTL_MASK -/* Idle state entry routines */ - -#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \ - /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \ - std r0,0(r1); \ - ptesync; \ - ld r0,0(r1); \ -1: cmp cr0,r0,r0; \ - bne 1b; \ - IDLE_INST; \ - b . - .text /* @@ -363,8 +351,8 @@ _GLOBAL(power9_idle_stop) * cr3 - set to gt if waking up with partial/complete hypervisor state loss */ _GLOBAL(pnv_restore_hyp_resource) - ld r2,PACATOC(r13); BEGIN_FTR_SECTION + ld r2,PACATOC(r13); /* * POWER ISA 3. Use PSSCR to determine if we * are waking up from deep idle state @@ -395,6 +383,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) */ clrldi r5,r13,63 clrrdi r13,r13,1 + + /* Now that we are sure r13 is corrected, load TOC */ + ld r2,PACATOC(r13); cmpwi cr4,r5,1 mtspr SPRN_HSPRG0,r13 diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index ef267fd9dd22..5e7ece0fda9f 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -92,7 +92,8 @@ void save_mce_event(struct pt_regs *regs, long handled, mce->in_use = 1; mce->initiator = MCE_INITIATOR_CPU; - if (handled) + /* Mark it recovered if we have handled it and MSR(RI=1). */ + if (handled && (regs->msr & MSR_RI)) mce->disposition = MCE_DISPOSITION_RECOVERED; else mce->disposition = MCE_DISPOSITION_NOT_RECOVERED; diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index a5c0153ede37..7fdf324d5b51 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -78,6 +78,7 @@ EXPORT_SYMBOL(get_pci_dma_ops); static int get_phb_number(struct device_node *dn) { int ret, phb_id = -1; + u32 prop_32; u64 prop; /* @@ -86,8 +87,10 @@ static int get_phb_number(struct device_node *dn) * reading "ibm,opal-phbid", only present in OPAL environment. */ ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop); - if (ret) - ret = of_property_read_u32_index(dn, "reg", 1, (u32 *)&prop); + if (ret) { + ret = of_property_read_u32_index(dn, "reg", 1, &prop_32); + prop = prop_32; + } if (!ret) phb_id = (int)(prop & (MAX_PHBS - 1)); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 58ccf86415b4..9ee2623e0f67 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1074,26 +1074,6 @@ static inline void restore_sprs(struct thread_struct *old_thread, #endif } -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -void flush_tmregs_to_thread(struct task_struct *tsk) -{ - /* - * Process self tracing is not yet supported through - * ptrace interface. Ptrace generic code should have - * prevented this from happening in the first place. - * Warn once here with the message, if some how it - * is attempted. - */ - WARN_ONCE(tsk == current, - "Not expecting ptrace on self: TM regs may be incorrect\n"); - - /* - * If task is not current, it should have been flushed - * already to it's thread_struct during __switch_to(). - */ -} -#endif - struct task_struct *__switch_to(struct task_struct *prev, struct task_struct *new) { diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 6ee4b72cda42..4e74fc588a3f 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2940,7 +2940,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, /* Don't print anything after quiesce under OPAL, it crashes OFW */ if (of_platform != PLATFORM_OPAL) { - prom_printf("Booting Linux via __start() ...\n"); + prom_printf("Booting Linux via __start() @ 0x%lx ...\n", kbase); prom_debug("->dt_header_start=0x%x\n", hdr); } diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 4f3c5756cc09..bf91658a8a40 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -38,6 +38,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/switch_to.h> +#include <asm/tm.h> #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> @@ -118,6 +119,24 @@ static const struct pt_regs_offset regoffset_table[] = { REG_OFFSET_END, }; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +static void flush_tmregs_to_thread(struct task_struct *tsk) +{ + /* + * If task is not current, it will have been flushed already to + * it's thread_struct during __switch_to(). + * + * A reclaim flushes ALL the state. + */ + + if (tsk == current && MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(TM_CAUSE_SIGNAL); + +} +#else +static inline void flush_tmregs_to_thread(struct task_struct *tsk) { } +#endif + /** * regs_query_register_offset() - query register offset from its name * @name: the name of a register diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index c3e861df4b20..24ec3ea4b3a2 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -93,15 +93,16 @@ notrace unsigned long __init early_init(unsigned long dt_ptr) * and we are running with enough of the MMU enabled to have our * proper kernel virtual addresses * - * Find out what kind of machine we're on and save any data we need - * from the early boot process (devtree is copied on pmac by prom_init()). - * This is called very early on the boot process, after a minimal - * MMU environment has been set up but before MMU_init is called. + * We do the initial parsing of the flat device-tree and prepares + * for the MMU to be fully initialized. */ extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */ notrace void __init machine_init(u64 dt_ptr) { + /* Configure static keys first, now that we're relocated. */ + setup_feature_keys(); + /* Enable early debugging if any specified (see udbg.h) */ udbg_early_init(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index eafb9a79e011..7ac8e6eaab5b 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -300,6 +300,7 @@ void __init early_setup(unsigned long dt_ptr) /* Apply all the dynamic patching */ apply_feature_fixups(); + setup_feature_keys(); /* Initialize the hash table or TLB handling */ early_init_mmu(); diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 6767605ea8da..4111d30badfa 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -22,6 +22,7 @@ #include <linux/security.h> #include <linux/memblock.h> +#include <asm/cpu_has_feature.h> #include <asm/pgtable.h> #include <asm/processor.h> #include <asm/mmu.h> diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile index cbabd143acae..78a7449bf489 100644 --- a/arch/powerpc/kernel/vdso32/Makefile +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -30,7 +30,7 @@ CPPFLAGS_vdso32.lds += -P -C -Upowerpc $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so # link rule for the .so file, .lds has to be first -$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) +$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE $(call if_changed,vdso32ld) # strip rule for the .so file @@ -39,12 +39,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # assembly rules for the .S files -$(obj-vdso32): %.o: %.S +$(obj-vdso32): %.o: %.S FORCE $(call if_changed_dep,vdso32as) # actual build commands quiet_cmd_vdso32ld = VDSO32L $@ - cmd_vdso32ld = $(CROSS32CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdso32ld = $(CROSS32CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) quiet_cmd_vdso32as = VDSO32A $@ cmd_vdso32as = $(CROSS32CC) $(a_flags) -c -o $@ $< diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index c710802b8fb6..366ae09b14c1 100644 --- a/arch/powerpc/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -23,7 +23,7 @@ CPPFLAGS_vdso64.lds += -P -C -U$(ARCH) $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so # link rule for the .so file, .lds has to be first -$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) +$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE $(call if_changed,vdso64ld) # strip rule for the .so file @@ -32,12 +32,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # assembly rules for the .S files -$(obj-vdso64): %.o: %.S +$(obj-vdso64): %.o: %.S FORCE $(call if_changed_dep,vdso64as) # actual build commands quiet_cmd_vdso64ld = VDSO64L $@ - cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) quiet_cmd_vdso64as = VDSO64A $@ cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index a75ba38a2d81..05aa11399a78 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -1329,20 +1329,16 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type) xics->kvm = kvm; /* Already there ? */ - mutex_lock(&kvm->lock); if (kvm->arch.xics) ret = -EEXIST; else kvm->arch.xics = xics; - mutex_unlock(&kvm->lock); if (ret) { kfree(xics); return ret; } - xics_debugfs_init(xics); - #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE if (cpu_has_feature(CPU_FTR_ARCH_206)) { /* Enable real mode support */ @@ -1354,9 +1350,17 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type) return 0; } +static void kvmppc_xics_init(struct kvm_device *dev) +{ + struct kvmppc_xics *xics = (struct kvmppc_xics *)dev->private; + + xics_debugfs_init(xics); +} + struct kvm_device_ops kvm_xics_ops = { .name = "kvm-xics", .create = kvmppc_xics_create, + .init = kvmppc_xics_init, .destroy = kvmppc_xics_free, .set_attr = xics_set_attr, .get_attr = xics_get_attr, diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S index d90870a66b60..0a57fe6d49cc 100644 --- a/arch/powerpc/lib/checksum_32.S +++ b/arch/powerpc/lib/checksum_32.S @@ -127,8 +127,9 @@ _GLOBAL(csum_partial_copy_generic) stw r7,12(r1) stw r8,8(r1) - andi. r0,r4,1 /* is destination address even ? */ - cmplwi cr7,r0,0 + rlwinm r0,r4,3,0x8 + rlwnm r6,r6,r0,0,31 /* odd destination address: rotate one byte */ + cmplwi cr7,r0,0 /* is destination address even ? */ addic r12,r6,0 addi r6,r4,-4 neg r0,r4 @@ -237,7 +238,7 @@ _GLOBAL(csum_partial_copy_generic) 66: addze r3,r12 addi r1,r1,16 beqlr+ cr7 - rlwinm r3,r3,8,0,31 /* swap bytes for odd destination */ + rlwinm r3,r3,8,0,31 /* odd destination address: rotate one byte */ blr /* read fault */ diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 74145f02ad41..043415f0bdb1 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -188,7 +188,10 @@ void __init apply_feature_fixups(void) &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup); #endif do_final_fixups(); +} +void __init setup_feature_keys(void) +{ /* * Initialise jump label. This causes all the cpu/mmu_has_feature() * checks to take on their correct polarity based on the current set of diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 5be15cff758d..2975754c65ea 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -496,8 +496,10 @@ spufs_mkgang(struct inode *dir, struct dentry *dentry, umode_t mode) gang = alloc_spu_gang(); SPUFS_I(inode)->i_ctx = NULL; SPUFS_I(inode)->i_gang = gang; - if (!gang) + if (!gang) { + ret = -ENOMEM; goto out_iput; + } inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index 309d9ccccd50..c61667e8bb06 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -187,6 +187,11 @@ static void pci_dma_dev_setup_pasemi(struct pci_dev *dev) if (dev->vendor == 0x1959 && dev->device == 0xa007 && !firmware_has_feature(FW_FEATURE_LPAR)) { dev->dev.archdata.dma_ops = &dma_direct_ops; + /* + * Set the coherent DMA mask to prevent the iommu + * being used unnecessarily + */ + dev->dev.coherent_dma_mask = DMA_BIT_MASK(44); return; } #endif diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c index e505223b4ec5..ed8bba68a162 100644 --- a/arch/powerpc/platforms/powernv/opal-irqchip.c +++ b/arch/powerpc/platforms/powernv/opal-irqchip.c @@ -228,7 +228,8 @@ int __init opal_event_init(void) } /* Install interrupt handler */ - rc = request_irq(virq, opal_interrupt, 0, "opal", NULL); + rc = request_irq(virq, opal_interrupt, IRQF_TRIGGER_LOW, + "opal", NULL); if (rc) { irq_dispose_mapping(virq); pr_warn("Error %d requesting irq %d (0x%x)\n", diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 8b4fc68cebcb..6c9a65b52e63 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -399,6 +399,7 @@ static int opal_recover_mce(struct pt_regs *regs, if (!(regs->msr & MSR_RI)) { /* If MSR_RI isn't set, we cannot recover */ + pr_err("Machine check interrupt unrecoverable: MSR(RI=0)\n"); recovered = 0; } else if (evt->disposition == MCE_DISPOSITION_RECOVERED) { /* Platform corrected itself */ diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 6b9528307f62..fd9444f9fb0c 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -111,10 +111,17 @@ static int __init iommu_setup(char *str) } early_param("iommu", iommu_setup); -static inline bool pnv_pci_is_mem_pref_64(unsigned long flags) +static inline bool pnv_pci_is_m64(struct pnv_phb *phb, struct resource *r) { - return ((flags & (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH)) == - (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH)); + /* + * WARNING: We cannot rely on the resource flags. The Linux PCI + * allocation code sometimes decides to put a 64-bit prefetchable + * BAR in the 32-bit window, so we have to compare the addresses. + * + * For simplicity we only test resource start. + */ + return (r->start >= phb->ioda.m64_base && + r->start < (phb->ioda.m64_base + phb->ioda.m64_size)); } static struct pnv_ioda_pe *pnv_ioda_init_pe(struct pnv_phb *phb, int pe_no) @@ -229,7 +236,7 @@ static void pnv_ioda_reserve_dev_m64_pe(struct pci_dev *pdev, sgsz = phb->ioda.m64_segsize; for (i = 0; i <= PCI_ROM_RESOURCE; i++) { r = &pdev->resource[i]; - if (!r->parent || !pnv_pci_is_mem_pref_64(r->flags)) + if (!r->parent || !pnv_pci_is_m64(phb, r)) continue; start = _ALIGN_DOWN(r->start - base, sgsz); @@ -1877,7 +1884,7 @@ static void pnv_pci_phb3_tce_invalidate(struct pnv_ioda_pe *pe, bool rm, unsigned shift, unsigned long index, unsigned long npages) { - __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, false); + __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, rm); unsigned long start, end, inc; /* We'll invalidate DMA address in PE scope */ @@ -2863,7 +2870,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) res = &pdev->resource[i + PCI_IOV_RESOURCES]; if (!res->flags || res->parent) continue; - if (!pnv_pci_is_mem_pref_64(res->flags)) { + if (!pnv_pci_is_m64(phb, res)) { dev_warn(&pdev->dev, "Don't support SR-IOV with" " non M64 VF BAR%d: %pR. \n", i, res); @@ -2958,7 +2965,7 @@ static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe, index++; } } else if ((res->flags & IORESOURCE_MEM) && - !pnv_pci_is_mem_pref_64(res->flags)) { + !pnv_pci_is_m64(phb, res)) { region.start = res->start - phb->hose->mem_offset[0] - phb->ioda.m32_pci_base; @@ -3083,9 +3090,12 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus, bridge = bridge->bus->self; } - /* We fail back to M32 if M64 isn't supported */ - if (phb->ioda.m64_segsize && - pnv_pci_is_mem_pref_64(type)) + /* + * We fall back to M32 if M64 isn't supported. We enforce the M64 + * alignment for any 64-bit resource, PCIe doesn't care and + * bridges only do 64-bit prefetchable anyway. + */ + if (phb->ioda.m64_segsize && (type & IORESOURCE_MEM_64)) return phb->ioda.m64_segsize; if (type & IORESOURCE_MEM) return phb->ioda.m32_segsize; @@ -3125,7 +3135,7 @@ static void pnv_pci_fixup_bridge_resources(struct pci_bus *bus, w = NULL; if (r->flags & type & IORESOURCE_IO) w = &hose->io_resource; - else if (pnv_pci_is_mem_pref_64(r->flags) && + else if (pnv_pci_is_m64(phb, r) && (type & IORESOURCE_PREFETCH) && phb->ioda.m64_segsize) w = &hose->mem_resources[1]; diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 43f7beb2902d..76ec104e88be 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -320,19 +320,6 @@ static int dlpar_remove_device_tree_lmb(struct of_drconf_cell *lmb) return dlpar_update_device_tree_lmb(lmb); } -static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb) -{ - unsigned long section_nr; - struct mem_section *mem_sect; - struct memory_block *mem_block; - - section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr)); - mem_sect = __nr_to_section(section_nr); - - mem_block = find_memory_block(mem_sect); - return mem_block; -} - #ifdef CONFIG_MEMORY_HOTREMOVE static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) { @@ -420,6 +407,19 @@ static bool lmb_is_removable(struct of_drconf_cell *lmb) static int dlpar_add_lmb(struct of_drconf_cell *); +static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb) +{ + unsigned long section_nr; + struct mem_section *mem_sect; + struct memory_block *mem_block; + + section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr)); + mem_sect = __nr_to_section(section_nr); + + mem_block = find_memory_block(mem_sect); + return mem_block; +} + static int dlpar_remove_lmb(struct of_drconf_cell *lmb) { struct memory_block *mem_block; diff --git a/arch/powerpc/sysdev/xics/Kconfig b/arch/powerpc/sysdev/xics/Kconfig index 0031eda320c3..385e7aa9e273 100644 --- a/arch/powerpc/sysdev/xics/Kconfig +++ b/arch/powerpc/sysdev/xics/Kconfig @@ -1,6 +1,7 @@ config PPC_XICS def_bool n select PPC_SMP_MUXED_IPI + select HARDIRQS_SW_RESEND config PPC_ICP_NATIVE def_bool n diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c index 27c936c080a6..1c6bf4b66f56 100644 --- a/arch/powerpc/sysdev/xics/ics-opal.c +++ b/arch/powerpc/sysdev/xics/ics-opal.c @@ -156,7 +156,9 @@ static struct irq_chip ics_opal_irq_chip = { .irq_mask = ics_opal_mask_irq, .irq_unmask = ics_opal_unmask_irq, .irq_eoi = NULL, /* Patched at init time */ - .irq_set_affinity = ics_opal_set_affinity + .irq_set_affinity = ics_opal_set_affinity, + .irq_set_type = xics_set_irq_type, + .irq_retrigger = xics_retrigger, }; static int ics_opal_map(struct ics *ics, unsigned int virq); diff --git a/arch/powerpc/sysdev/xics/ics-rtas.c b/arch/powerpc/sysdev/xics/ics-rtas.c index 3854dd41558d..78ee5c778ef8 100644 --- a/arch/powerpc/sysdev/xics/ics-rtas.c +++ b/arch/powerpc/sysdev/xics/ics-rtas.c @@ -163,7 +163,9 @@ static struct irq_chip ics_rtas_irq_chip = { .irq_mask = ics_rtas_mask_irq, .irq_unmask = ics_rtas_unmask_irq, .irq_eoi = NULL, /* Patched at init time */ - .irq_set_affinity = ics_rtas_set_affinity + .irq_set_affinity = ics_rtas_set_affinity, + .irq_set_type = xics_set_irq_type, + .irq_retrigger = xics_retrigger, }; static int ics_rtas_map(struct ics *ics, unsigned int virq) diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c index a795a5f0301c..9d530f479588 100644 --- a/arch/powerpc/sysdev/xics/xics-common.c +++ b/arch/powerpc/sysdev/xics/xics-common.c @@ -328,8 +328,12 @@ static int xics_host_map(struct irq_domain *h, unsigned int virq, pr_devel("xics: map virq %d, hwirq 0x%lx\n", virq, hw); - /* They aren't all level sensitive but we just don't really know */ - irq_set_status_flags(virq, IRQ_LEVEL); + /* + * Mark interrupts as edge sensitive by default so that resend + * actually works. The device-tree parsing will turn the LSIs + * back to level. + */ + irq_clear_status_flags(virq, IRQ_LEVEL); /* Don't call into ICS for IPIs */ if (hw == XICS_IPI) { @@ -351,13 +355,54 @@ static int xics_host_xlate(struct irq_domain *h, struct device_node *ct, irq_hw_number_t *out_hwirq, unsigned int *out_flags) { - /* Current xics implementation translates everything - * to level. It is not technically right for MSIs but this - * is irrelevant at this point. We might get smarter in the future - */ *out_hwirq = intspec[0]; - *out_flags = IRQ_TYPE_LEVEL_LOW; + /* + * If intsize is at least 2, we look for the type in the second cell, + * we assume the LSB indicates a level interrupt. + */ + if (intsize > 1) { + if (intspec[1] & 1) + *out_flags = IRQ_TYPE_LEVEL_LOW; + else + *out_flags = IRQ_TYPE_EDGE_RISING; + } else + *out_flags = IRQ_TYPE_LEVEL_LOW; + + return 0; +} + +int xics_set_irq_type(struct irq_data *d, unsigned int flow_type) +{ + /* + * We only support these. This has really no effect other than setting + * the corresponding descriptor bits mind you but those will in turn + * affect the resend function when re-enabling an edge interrupt. + * + * Set set the default to edge as explained in map(). + */ + if (flow_type == IRQ_TYPE_DEFAULT || flow_type == IRQ_TYPE_NONE) + flow_type = IRQ_TYPE_EDGE_RISING; + + if (flow_type != IRQ_TYPE_EDGE_RISING && + flow_type != IRQ_TYPE_LEVEL_LOW) + return -EINVAL; + + irqd_set_trigger_type(d, flow_type); + + return IRQ_SET_MASK_OK_NOCOPY; +} + +int xics_retrigger(struct irq_data *data) +{ + /* + * We need to push a dummy CPPR when retriggering, since the subsequent + * EOI will try to pop it. Passing 0 works, as the function hard codes + * the priority value anyway. + */ + xics_push_cppr(0); + + /* Tell the core to do a soft retrigger */ return 0; } diff --git a/arch/s390/boot/compressed/head.S b/arch/s390/boot/compressed/head.S index f86a4eef28a9..28c4f96a2d9c 100644 --- a/arch/s390/boot/compressed/head.S +++ b/arch/s390/boot/compressed/head.S @@ -21,16 +21,21 @@ ENTRY(startup_continue) lg %r15,.Lstack-.LPG1(%r13) aghi %r15,-160 brasl %r14,decompress_kernel - # setup registers for memory mover & branch to target + # Set up registers for memory mover. We move the decompressed image to + # 0x11000, starting at offset 0x11000 in the decompressed image so + # that code living at 0x11000 in the image will end up at 0x11000 in + # memory. lgr %r4,%r2 lg %r2,.Loffset-.LPG1(%r13) la %r4,0(%r2,%r4) lg %r3,.Lmvsize-.LPG1(%r13) lgr %r5,%r3 - # move the memory mover someplace safe + # Move the memory mover someplace safe so it doesn't overwrite itself. la %r1,0x200 mvc 0(mover_end-mover,%r1),mover-.LPG1(%r13) - # decompress image is started at 0x11000 + # When the memory mover is done we pass control to + # arch/s390/kernel/head64.S:startup_continue which lives at 0x11000 in + # the decompressed image. lgr %r6,%r2 br %r1 mover: diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig index 889ea3450210..26e0c7f08814 100644 --- a/arch/s390/configs/default_defconfig +++ b/arch/s390/configs/default_defconfig @@ -678,7 +678,7 @@ CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m -CONFIG_CRYPTO_CRC32_S390=m +CONFIG_CRYPTO_CRC32_S390=y CONFIG_ASYMMETRIC_KEY_TYPE=y CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m CONFIG_X509_CERTIFICATE_PARSER=m diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig index 1bcfd764910a..24879dab47bc 100644 --- a/arch/s390/configs/gcov_defconfig +++ b/arch/s390/configs/gcov_defconfig @@ -616,7 +616,7 @@ CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m -CONFIG_CRYPTO_CRC32_S390=m +CONFIG_CRYPTO_CRC32_S390=y CONFIG_ASYMMETRIC_KEY_TYPE=y CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m CONFIG_X509_CERTIFICATE_PARSER=m diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index 13ff090139c8..a5c1e5f2a0ca 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -615,7 +615,7 @@ CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m -CONFIG_CRYPTO_CRC32_S390=m +CONFIG_CRYPTO_CRC32_S390=y CONFIG_ASYMMETRIC_KEY_TYPE=y CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m CONFIG_X509_CERTIFICATE_PARSER=m diff --git a/arch/s390/crypto/crc32-vx.c b/arch/s390/crypto/crc32-vx.c index 577ae1d4ae89..2bad9d837029 100644 --- a/arch/s390/crypto/crc32-vx.c +++ b/arch/s390/crypto/crc32-vx.c @@ -51,6 +51,9 @@ u32 crc32c_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size); struct kernel_fpu vxstate; \ unsigned long prealign, aligned, remaining; \ \ + if (datalen < VX_MIN_LEN + VX_ALIGN_MASK) \ + return ___crc32_sw(crc, data, datalen); \ + \ if ((unsigned long)data & VX_ALIGN_MASK) { \ prealign = VX_ALIGNMENT - \ ((unsigned long)data & VX_ALIGN_MASK); \ @@ -59,9 +62,6 @@ u32 crc32c_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size); data = (void *)((unsigned long)data + prealign); \ } \ \ - if (datalen < VX_MIN_LEN) \ - return ___crc32_sw(crc, data, datalen); \ - \ aligned = datalen & ~VX_ALIGN_MASK; \ remaining = datalen & VX_ALIGN_MASK; \ \ diff --git a/arch/s390/defconfig b/arch/s390/defconfig index ccccebeeaaf6..73610f2e3b4f 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -234,7 +234,7 @@ CONFIG_CRYPTO_SHA256_S390=m CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m -CONFIG_CRYPTO_CRC32_S390=m +CONFIG_CRYPTO_CRC32_S390=y CONFIG_CRC7=m # CONFIG_XZ_DEC_X86 is not set # CONFIG_XZ_DEC_POWERPC is not set diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S index 56e4d8234ef2..4431905f8cfa 100644 --- a/arch/s390/kernel/head.S +++ b/arch/s390/kernel/head.S @@ -309,7 +309,9 @@ ENTRY(startup_kdump) l %r15,.Lstack-.LPG0(%r13) ahi %r15,-STACK_FRAME_OVERHEAD brasl %r14,verify_facilities - /* Continue with startup code in head64.S */ +# For uncompressed images, continue in +# arch/s390/kernel/head64.S. For compressed images, continue in +# arch/s390/boot/compressed/head.S. jg startup_continue .Lstack: diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 3f3ae4865d57..f142215ed30d 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1672,6 +1672,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) KVM_SYNC_CRS | KVM_SYNC_ARCH0 | KVM_SYNC_PFAULT; + kvm_s390_set_prefix(vcpu, 0); if (test_kvm_facility(vcpu->kvm, 64)) vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB; /* fprs can be synchronized via vrs, even if the guest has no vx. With @@ -2361,8 +2362,10 @@ retry: rc = gmap_mprotect_notify(vcpu->arch.gmap, kvm_s390_get_prefix(vcpu), PAGE_SIZE * 2, PROT_WRITE); - if (rc) + if (rc) { + kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); return rc; + } goto retry; } diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c index e390bbb16443..48352bffbc92 100644 --- a/arch/s390/lib/string.c +++ b/arch/s390/lib/string.c @@ -237,11 +237,10 @@ char * strrchr(const char * s, int c) EXPORT_SYMBOL(strrchr); static inline int clcle(const char *s1, unsigned long l1, - const char *s2, unsigned long l2, - int *diff) + const char *s2, unsigned long l2) { register unsigned long r2 asm("2") = (unsigned long) s1; - register unsigned long r3 asm("3") = (unsigned long) l2; + register unsigned long r3 asm("3") = (unsigned long) l1; register unsigned long r4 asm("4") = (unsigned long) s2; register unsigned long r5 asm("5") = (unsigned long) l2; int cc; @@ -252,7 +251,6 @@ static inline int clcle(const char *s1, unsigned long l1, " srl %0,28" : "=&d" (cc), "+a" (r2), "+a" (r3), "+a" (r4), "+a" (r5) : : "cc"); - *diff = *(char *)r2 - *(char *)r4; return cc; } @@ -270,9 +268,9 @@ char * strstr(const char * s1,const char * s2) return (char *) s1; l1 = __strend(s1) - s1; while (l1-- >= l2) { - int cc, dummy; + int cc; - cc = clcle(s1, l1, s2, l2, &dummy); + cc = clcle(s1, l2, s2, l2); if (!cc) return (char *) s1; s1++; @@ -313,11 +311,11 @@ EXPORT_SYMBOL(memchr); */ int memcmp(const void *cs, const void *ct, size_t n) { - int ret, diff; + int ret; - ret = clcle(cs, n, ct, n, &diff); + ret = clcle(cs, n, ct, n); if (ret) - ret = diff; + ret = ret == 1 ? -1 : 1; return ret; } EXPORT_SYMBOL(memcmp); diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 7104ffb5a67f..af7cf28cf97e 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -252,6 +252,8 @@ static int change_page_attr(unsigned long addr, unsigned long end, int rc = -EINVAL; pgd_t *pgdp; + if (addr == end) + return 0; if (end >= MODULES_END) return -EINVAL; mutex_lock(&cpa_mutex); diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h index e35632ef23c7..62dfc644c908 100644 --- a/arch/unicore32/include/asm/mmu_context.h +++ b/arch/unicore32/include/asm/mmu_context.h @@ -98,7 +98,7 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm, } static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, - bool write, bool foreign) + bool write, bool execute, bool foreign) { /* by default, allow everything */ return true; diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index fe91c25092da..77f28ce9c646 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -5,6 +5,8 @@ OBJECT_FILES_NON_STANDARD_entry_$(BITS).o := y OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y +CFLAGS_syscall_64.o += -Wno-override-init +CFLAGS_syscall_32.o += -Wno-override-init obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o obj-y += common.o diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index b846875aeea6..d172c619c449 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -288,11 +288,15 @@ return_from_SYSCALL_64: jne opportunistic_sysret_failed /* - * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET, - * restoring TF results in a trap from userspace immediately after - * SYSRET. This would cause an infinite loop whenever #DB happens - * with register state that satisfies the opportunistic SYSRET - * conditions. For example, single-stepping this user code: + * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot + * restore RF properly. If the slowpath sets it for whatever reason, we + * need to restore it correctly. + * + * SYSRET can restore TF, but unlike IRET, restoring TF results in a + * trap from userspace immediately after SYSRET. This would cause an + * infinite loop whenever #DB happens with register state that satisfies + * the opportunistic SYSRET conditions. For example, single-stepping + * this user code: * * movq $stuck_here, %rcx * pushfq @@ -601,9 +605,20 @@ apicinterrupt3 \num trace(\sym) smp_trace(\sym) .endm #endif +/* Make sure APIC interrupt handlers end up in the irqentry section: */ +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN) +# define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax" +# define POP_SECTION_IRQENTRY .popsection +#else +# define PUSH_SECTION_IRQENTRY +# define POP_SECTION_IRQENTRY +#endif + .macro apicinterrupt num sym do_sym +PUSH_SECTION_IRQENTRY apicinterrupt3 \num \sym \do_sym trace_apicinterrupt \num \sym +POP_SECTION_IRQENTRY .endm #ifdef CONFIG_SMP diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 97a69dbba649..9d35ec0cb8fc 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -100,6 +100,12 @@ static void snb_uncore_msr_init_box(struct intel_uncore_box *box) } } +static void snb_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + wrmsrl(SNB_UNC_PERF_GLOBAL_CTL, + SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL); +} + static void snb_uncore_msr_exit_box(struct intel_uncore_box *box) { if (box->pmu->pmu_idx == 0) @@ -127,6 +133,7 @@ static struct attribute_group snb_uncore_format_group = { static struct intel_uncore_ops snb_uncore_msr_ops = { .init_box = snb_uncore_msr_init_box, + .enable_box = snb_uncore_msr_enable_box, .exit_box = snb_uncore_msr_exit_box, .disable_event = snb_uncore_msr_disable_event, .enable_event = snb_uncore_msr_enable_event, @@ -192,6 +199,12 @@ static void skl_uncore_msr_init_box(struct intel_uncore_box *box) } } +static void skl_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + wrmsrl(SKL_UNC_PERF_GLOBAL_CTL, + SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL); +} + static void skl_uncore_msr_exit_box(struct intel_uncore_box *box) { if (box->pmu->pmu_idx == 0) @@ -200,6 +213,7 @@ static void skl_uncore_msr_exit_box(struct intel_uncore_box *box) static struct intel_uncore_ops skl_uncore_msr_ops = { .init_box = skl_uncore_msr_init_box, + .enable_box = skl_uncore_msr_enable_box, .exit_box = skl_uncore_msr_exit_box, .disable_event = snb_uncore_msr_disable_event, .enable_event = snb_uncore_msr_enable_event, diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 824e54086e07..8aee83bcf71f 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -2626,7 +2626,7 @@ void hswep_uncore_cpu_init(void) static struct intel_uncore_type hswep_uncore_ha = { .name = "ha", - .num_counters = 5, + .num_counters = 4, .num_boxes = 2, .perf_ctr_bits = 48, SNBEP_UNCORE_PCI_COMMON_INIT(), @@ -2645,7 +2645,7 @@ static struct uncore_event_desc hswep_uncore_imc_events[] = { static struct intel_uncore_type hswep_uncore_imc = { .name = "imc", - .num_counters = 5, + .num_counters = 4, .num_boxes = 8, .perf_ctr_bits = 48, .fixed_ctr_bits = 48, @@ -2691,7 +2691,7 @@ static struct intel_uncore_type hswep_uncore_irp = { static struct intel_uncore_type hswep_uncore_qpi = { .name = "qpi", - .num_counters = 5, + .num_counters = 4, .num_boxes = 3, .perf_ctr_bits = 48, .perf_ctr = SNBEP_PCI_PMON_CTR0, @@ -2773,7 +2773,7 @@ static struct event_constraint hswep_uncore_r3qpi_constraints[] = { static struct intel_uncore_type hswep_uncore_r3qpi = { .name = "r3qpi", - .num_counters = 4, + .num_counters = 3, .num_boxes = 3, .perf_ctr_bits = 44, .constraints = hswep_uncore_r3qpi_constraints, @@ -2972,7 +2972,7 @@ static struct intel_uncore_type bdx_uncore_ha = { static struct intel_uncore_type bdx_uncore_imc = { .name = "imc", - .num_counters = 5, + .num_counters = 4, .num_boxes = 8, .perf_ctr_bits = 48, .fixed_ctr_bits = 48, diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index f5befd4945f2..124357773ffa 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -135,6 +135,7 @@ extern void init_apic_mappings(void); void register_lapic_address(unsigned long address); extern void setup_boot_APIC_clock(void); extern void setup_secondary_APIC_clock(void); +extern void lapic_update_tsc_freq(void); extern int APIC_init_uniprocessor(void); #ifdef CONFIG_X86_64 @@ -170,6 +171,7 @@ static inline void init_apic_mappings(void) { } static inline void disable_local_APIC(void) { } # define setup_boot_APIC_clock x86_init_noop # define setup_secondary_APIC_clock x86_init_noop +static inline void lapic_update_tsc_freq(void) { } #endif /* !CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_X2APIC diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 7178043b0e1d..59405a248fc2 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -22,10 +22,6 @@ typedef struct { #ifdef CONFIG_SMP unsigned int irq_resched_count; unsigned int irq_call_count; - /* - * irq_tlb_count is double-counted in irq_call_count, so it must be - * subtracted from irq_call_count when displaying irq_call_count - */ unsigned int irq_tlb_count; #endif #ifdef CONFIG_X86_THERMAL_VECTOR diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h index 223042086f4e..737da62bfeb0 100644 --- a/arch/x86/include/asm/init.h +++ b/arch/x86/include/asm/init.h @@ -5,10 +5,10 @@ struct x86_mapping_info { void *(*alloc_pgt_page)(void *); /* allocate buf for page table */ void *context; /* context for alloc_pgt_page */ unsigned long pmd_flag; /* page flag for PMD entry */ - bool kernel_mapping; /* kernel mapping or ident mapping */ + unsigned long offset; /* ident mapping offset */ }; int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, - unsigned long addr, unsigned long end); + unsigned long pstart, unsigned long pend); #endif /* _ASM_X86_INIT_H */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 7e8ec7ae10fa..1cc82ece9ac1 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -145,7 +145,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; } * * | ... | 11| 10| 9|8|7|6|5| 4| 3|2|1|0| <- bit number * | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U|W|P| <- bit names - * | OFFSET (14->63) | TYPE (10-13) |0|X|X|X| X| X|X|X|0| <- swp entry + * | OFFSET (14->63) | TYPE (9-13) |0|X|X|X| X| X|X|X|0| <- swp entry * * G (8) is aliased and used as a PROT_NONE indicator for * !present ptes. We need to start storing swap entries above @@ -156,7 +156,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; } #define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) #define SWP_TYPE_BITS 5 /* Place the offset above the type: */ -#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS + 1) +#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS) #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index 9c6b890d5e7a..b2988c0ed829 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -58,7 +58,15 @@ extern unsigned char boot_gdt[]; extern unsigned char secondary_startup_64[]; #endif +static inline size_t real_mode_size_needed(void) +{ + if (real_mode_header) + return 0; /* already allocated. */ + + return ALIGN(real_mode_blob_end - real_mode_blob, PAGE_SIZE); +} + +void set_real_mode_mem(phys_addr_t mem, size_t size); void reserve_real_mode(void); -void setup_real_mode(void); #endif /* _ARCH_X86_REALMODE_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 4e5be94e079a..6fa85944af83 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -135,7 +135,14 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask) static inline void __native_flush_tlb(void) { + /* + * If current->mm == NULL then we borrow a mm which may change during a + * task switch and therefore we must not be preempted while we write CR3 + * back: + */ + preempt_disable(); native_write_cr3(native_read_cr3()); + preempt_enable(); } static inline void __native_flush_tlb_global_irq_disabled(void) diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h index c852590254d5..e652a7cc6186 100644 --- a/arch/x86/include/asm/uv/bios.h +++ b/arch/x86/include/asm/uv/bios.h @@ -79,7 +79,7 @@ struct uv_gam_range_entry { u16 nasid; /* HNasid */ u16 sockid; /* Socket ID, high bits of APIC ID */ u16 pnode; /* Index to MMR and GRU spaces */ - u32 pxm; /* ACPI proximity domain number */ + u32 unused2; u32 limit; /* PA bits 56:26 (UV_GAM_RANGE_SHFT) */ }; @@ -88,7 +88,8 @@ struct uv_gam_range_entry { #define UV_SYSTAB_VERSION_UV4 0x400 /* UV4 BIOS base version */ #define UV_SYSTAB_VERSION_UV4_1 0x401 /* + gpa_shift */ #define UV_SYSTAB_VERSION_UV4_2 0x402 /* + TYPE_NVRAM/WINDOW/MBOX */ -#define UV_SYSTAB_VERSION_UV4_LATEST UV_SYSTAB_VERSION_UV4_2 +#define UV_SYSTAB_VERSION_UV4_3 0x403 /* - GAM Range PXM Value */ +#define UV_SYSTAB_VERSION_UV4_LATEST UV_SYSTAB_VERSION_UV4_3 #define UV_SYSTAB_TYPE_UNUSED 0 /* End of table (offset == 0) */ #define UV_SYSTAB_TYPE_GAM_PARAMS 1 /* GAM PARAM conversions */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 20abd912f0e4..cea4fc19e844 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -313,7 +313,7 @@ int lapic_get_maxlvt(void) /* Clock divisor */ #define APIC_DIVISOR 16 -#define TSC_DIVISOR 32 +#define TSC_DIVISOR 8 /* * This function sets up the local APIC timer, with a timeout of @@ -565,13 +565,37 @@ static void setup_APIC_timer(void) CLOCK_EVT_FEAT_DUMMY); levt->set_next_event = lapic_next_deadline; clockevents_config_and_register(levt, - (tsc_khz / TSC_DIVISOR) * 1000, + tsc_khz * (1000 / TSC_DIVISOR), 0xF, ~0UL); } else clockevents_register_device(levt); } /* + * Install the updated TSC frequency from recalibration at the TSC + * deadline clockevent devices. + */ +static void __lapic_update_tsc_freq(void *info) +{ + struct clock_event_device *levt = this_cpu_ptr(&lapic_events); + + if (!this_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + return; + + clockevents_update_freq(levt, tsc_khz * (1000 / TSC_DIVISOR)); +} + +void lapic_update_tsc_freq(void) +{ + /* + * The clockevent device's ->mult and ->shift can both be + * changed. In order to avoid races, schedule the frequency + * update code on each CPU. + */ + on_each_cpu(__lapic_update_tsc_freq, NULL, 0); +} + +/* * In this functions we calibrate APIC bus clocks to the external timer. * * We want to do the calibration only once since we want to have local timer diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 6368fa69d2af..54f35d988025 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -155,7 +155,7 @@ static void init_x2apic_ldr(void) /* * At CPU state changes, update the x2apic cluster sibling info. */ -int x2apic_prepare_cpu(unsigned int cpu) +static int x2apic_prepare_cpu(unsigned int cpu) { if (!zalloc_cpumask_var(&per_cpu(cpus_in_cluster, cpu), GFP_KERNEL)) return -ENOMEM; @@ -168,7 +168,7 @@ int x2apic_prepare_cpu(unsigned int cpu) return 0; } -int x2apic_dead_cpu(unsigned int this_cpu) +static int x2apic_dead_cpu(unsigned int this_cpu) { int cpu; @@ -186,13 +186,18 @@ int x2apic_dead_cpu(unsigned int this_cpu) static int x2apic_cluster_probe(void) { int cpu = smp_processor_id(); + int ret; if (!x2apic_mode) return 0; + ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE", + x2apic_prepare_cpu, x2apic_dead_cpu); + if (ret < 0) { + pr_err("Failed to register X2APIC_PREPARE\n"); + return 0; + } cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, cpu)); - cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE", - x2apic_prepare_cpu, x2apic_dead_cpu); return 1; } diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 09b59adaea3f..cb0673c1e940 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -223,6 +223,11 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) if (strncmp(oem_id, "SGI", 3) != 0) return 0; + if (numa_off) { + pr_err("UV: NUMA is off, disabling UV support\n"); + return 0; + } + /* Setup early hub type field in uv_hub_info for Node 0 */ uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0; @@ -325,7 +330,7 @@ static __init void build_uv_gr_table(void) struct uv_gam_range_entry *gre = uv_gre_table; struct uv_gam_range_s *grt; unsigned long last_limit = 0, ram_limit = 0; - int bytes, i, sid, lsid = -1; + int bytes, i, sid, lsid = -1, indx = 0, lindx = -1; if (!gre) return; @@ -356,11 +361,12 @@ static __init void build_uv_gr_table(void) } sid = gre->sockid - _min_socket; if (lsid < sid) { /* new range */ - grt = &_gr_table[sid]; - grt->base = lsid; + grt = &_gr_table[indx]; + grt->base = lindx; grt->nasid = gre->nasid; grt->limit = last_limit = gre->limit; lsid = sid; + lindx = indx++; continue; } if (lsid == sid && !ram_limit) { /* update range */ @@ -371,7 +377,7 @@ static __init void build_uv_gr_table(void) } if (!ram_limit) { /* non-contiguous ram range */ grt++; - grt->base = sid - 1; + grt->base = lindx; grt->nasid = gre->nasid; grt->limit = last_limit = gre->limit; continue; @@ -1155,19 +1161,18 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) { if (!index) { pr_info("UV: GAM Range Table...\n"); - pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s %3s\n", + pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", - "SID", "PN", "PXM"); + "SID", "PN"); } pr_info( - "UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x %3d\n", + "UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x\n", index++, (unsigned long)lgre << UV_GAM_RANGE_SHFT, (unsigned long)gre->limit << UV_GAM_RANGE_SHFT, ((unsigned long)(gre->limit - lgre)) >> (30 - UV_GAM_RANGE_SHFT), /* 64M -> 1G */ - gre->type, gre->nasid, gre->sockid, - gre->pnode, gre->pxm); + gre->type, gre->nasid, gre->sockid, gre->pnode); lgre = gre->limit; if (sock_min > gre->sockid) @@ -1286,7 +1291,7 @@ static void __init build_socket_tables(void) _pnode_to_socket[i] = SOCK_EMPTY; /* fill in pnode/node/addr conversion list values */ - pr_info("UV: GAM Building socket/pnode/pxm conversion tables\n"); + pr_info("UV: GAM Building socket/pnode conversion tables\n"); for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) { if (gre->type == UV_GAM_RANGE_TYPE_HOLE) continue; @@ -1294,20 +1299,18 @@ static void __init build_socket_tables(void) if (_socket_to_pnode[i] != SOCK_EMPTY) continue; /* duplicate */ _socket_to_pnode[i] = gre->pnode; - _socket_to_node[i] = gre->pxm; i = gre->pnode - minpnode; _pnode_to_socket[i] = gre->sockid; pr_info( - "UV: sid:%02x type:%d nasid:%04x pn:%02x pxm:%2d pn2s:%2x\n", + "UV: sid:%02x type:%d nasid:%04x pn:%02x pn2s:%2x\n", gre->sockid, gre->type, gre->nasid, _socket_to_pnode[gre->sockid - minsock], - _socket_to_node[gre->sockid - minsock], _pnode_to_socket[gre->pnode - minpnode]); } - /* check socket -> node values */ + /* Set socket -> node values */ lnid = -1; for_each_present_cpu(cpu) { int nid = cpu_to_node(cpu); @@ -1318,14 +1321,9 @@ static void __init build_socket_tables(void) lnid = nid; apicid = per_cpu(x86_cpu_to_apicid, cpu); sockid = apicid >> uv_cpuid.socketid_shift; - i = sockid - minsock; - - if (nid != _socket_to_node[i]) { - pr_warn( - "UV: %02x: type:%d socket:%02x PXM:%02x != node:%2d\n", - i, sockid, gre->type, _socket_to_node[i], nid); - _socket_to_node[i] = nid; - } + _socket_to_node[sockid - minsock] = nid; + pr_info("UV: sid:%02x: apicid:%04x node:%2d\n", + sockid, apicid, nid); } /* Setup physical blade to pnode translation from GAM Range Table */ diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 680049aa4593..01567aa87503 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -866,105 +866,17 @@ const void *get_xsave_field_ptr(int xsave_state) return get_xsave_addr(&fpu->state.xsave, xsave_state); } - -/* - * Set xfeatures (aka XSTATE_BV) bit for a feature that we want - * to take out of its "init state". This will ensure that an - * XRSTOR actually restores the state. - */ -static void fpu__xfeature_set_non_init(struct xregs_state *xsave, - int xstate_feature_mask) -{ - xsave->header.xfeatures |= xstate_feature_mask; -} - -/* - * This function is safe to call whether the FPU is in use or not. - * - * Note that this only works on the current task. - * - * Inputs: - * @xsave_state: state which is defined in xsave.h (e.g. XFEATURE_MASK_FP, - * XFEATURE_MASK_SSE, etc...) - * @xsave_state_ptr: a pointer to a copy of the state that you would - * like written in to the current task's FPU xsave state. This pointer - * must not be located in the current tasks's xsave area. - * Output: - * address of the state in the xsave area or NULL if the state - * is not present or is in its 'init state'. - */ -static void fpu__xfeature_set_state(int xstate_feature_mask, - void *xstate_feature_src, size_t len) -{ - struct xregs_state *xsave = ¤t->thread.fpu.state.xsave; - struct fpu *fpu = ¤t->thread.fpu; - void *dst; - - if (!boot_cpu_has(X86_FEATURE_XSAVE)) { - WARN_ONCE(1, "%s() attempted with no xsave support", __func__); - return; - } - - /* - * Tell the FPU code that we need the FPU state to be in - * 'fpu' (not in the registers), and that we need it to - * be stable while we write to it. - */ - fpu__current_fpstate_write_begin(); - - /* - * This method *WILL* *NOT* work for compact-format - * buffers. If the 'xstate_feature_mask' is unset in - * xcomp_bv then we may need to move other feature state - * "up" in the buffer. - */ - if (xsave->header.xcomp_bv & xstate_feature_mask) { - WARN_ON_ONCE(1); - goto out; - } - - /* find the location in the xsave buffer of the desired state */ - dst = __raw_xsave_addr(&fpu->state.xsave, xstate_feature_mask); - - /* - * Make sure that the pointer being passed in did not - * come from the xsave buffer itself. - */ - WARN_ONCE(xstate_feature_src == dst, "set from xsave buffer itself"); - - /* put the caller-provided data in the location */ - memcpy(dst, xstate_feature_src, len); - - /* - * Mark the xfeature so that the CPU knows there is state - * in the buffer now. - */ - fpu__xfeature_set_non_init(xsave, xstate_feature_mask); -out: - /* - * We are done writing to the 'fpu'. Reenable preeption - * and (possibly) move the fpstate back in to the fpregs. - */ - fpu__current_fpstate_write_end(); -} - #define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2) #define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1) /* - * This will go out and modify the XSAVE buffer so that PKRU is - * set to a particular state for access to 'pkey'. - * - * PKRU state does affect kernel access to user memory. We do - * not modfiy PKRU *itself* here, only the XSAVE state that will - * be restored in to PKRU when we return back to userspace. + * This will go out and modify PKRU register to set the access + * rights for @pkey to @init_val. */ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val) { - struct xregs_state *xsave = &tsk->thread.fpu.state.xsave; - struct pkru_state *old_pkru_state; - struct pkru_state new_pkru_state; + u32 old_pkru; int pkey_shift = (pkey * PKRU_BITS_PER_PKEY); u32 new_pkru_bits = 0; @@ -974,6 +886,15 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, */ if (!boot_cpu_has(X86_FEATURE_OSPKE)) return -EINVAL; + /* + * For most XSAVE components, this would be an arduous task: + * brining fpstate up to date with fpregs, updating fpstate, + * then re-populating fpregs. But, for components that are + * never lazily managed, we can just access the fpregs + * directly. PKRU is never managed lazily, so we can just + * manipulate it directly. Make sure it stays that way. + */ + WARN_ON_ONCE(!use_eager_fpu()); /* Set the bits we need in PKRU: */ if (init_val & PKEY_DISABLE_ACCESS) @@ -984,37 +905,12 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, /* Shift the bits in to the correct place in PKRU for pkey: */ new_pkru_bits <<= pkey_shift; - /* Locate old copy of the state in the xsave buffer: */ - old_pkru_state = get_xsave_addr(xsave, XFEATURE_MASK_PKRU); - - /* - * When state is not in the buffer, it is in the init - * state, set it manually. Otherwise, copy out the old - * state. - */ - if (!old_pkru_state) - new_pkru_state.pkru = 0; - else - new_pkru_state.pkru = old_pkru_state->pkru; - - /* Mask off any old bits in place: */ - new_pkru_state.pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift); - - /* Set the newly-requested bits: */ - new_pkru_state.pkru |= new_pkru_bits; - - /* - * We could theoretically live without zeroing pkru.pad. - * The current XSAVE feature state definition says that - * only bytes 0->3 are used. But we do not want to - * chance leaking kernel stack out to userspace in case a - * memcpy() of the whole xsave buffer was done. - * - * They're in the same cacheline anyway. - */ - new_pkru_state.pad = 0; + /* Get old PKRU and mask off any old bits in place: */ + old_pkru = read_pkru(); + old_pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift); - fpu__xfeature_set_state(XFEATURE_MASK_PKRU, &new_pkru_state, sizeof(new_pkru_state)); + /* Write old part along with new part: */ + write_pkru(old_pkru | new_pkru_bits); return 0; } diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 2dda0bc4576e..f16c55bfc090 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -25,8 +25,6 @@ static void __init i386_default_early_setup(void) /* Initialize 32bit specific setup functions */ x86_init.resources.reserve_resources = i386_reserve_resources; x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc; - - reserve_bios_regions(); } asmlinkage __visible void __init i386_start_kernel(void) diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 99d48e7d2974..54a2372f5dbb 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -183,7 +183,6 @@ void __init x86_64_start_reservations(char *real_mode_data) copy_bootdata(__va(real_mode_data)); x86_early_init_platform_quirks(); - reserve_bios_regions(); switch (boot_params.hdr.hardware_subarch) { case X86_SUBARCH_INTEL_MID: diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index ed16e58658a4..c6dfd801df97 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -1242,7 +1242,7 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id) memset(&curr_time, 0, sizeof(struct rtc_time)); if (hpet_rtc_flags & (RTC_UIE | RTC_AIE)) - mc146818_set_time(&curr_time); + mc146818_get_time(&curr_time); if (hpet_rtc_flags & RTC_UIE && curr_time.tm_sec != hpet_prev_update_sec) { diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 61521dc19c10..9f669fdd2010 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -102,8 +102,7 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_puts(p, " Rescheduling interrupts\n"); seq_printf(p, "%*s: ", prec, "CAL"); for_each_online_cpu(j) - seq_printf(p, "%10u ", irq_stats(j)->irq_call_count - - irq_stats(j)->irq_tlb_count); + seq_printf(p, "%10u ", irq_stats(j)->irq_call_count); seq_puts(p, " Function call interrupts\n"); seq_printf(p, "%*s: ", prec, "TLB"); for_each_online_cpu(j) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 991b77986d57..0fa60f5f5a16 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -936,8 +936,6 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.arch_setup(); - kernel_randomize_memory(); - iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1; setup_memory_map(); parse_setup_data(); @@ -1055,6 +1053,12 @@ void __init setup_arch(char **cmdline_p) max_possible_pfn = max_pfn; + /* + * Define random base addresses for memory sections after max_pfn is + * defined and before each memory section base is used. + */ + kernel_randomize_memory(); + #ifdef CONFIG_X86_32 /* max_low_pfn get updated here */ find_low_pfn_range(); @@ -1097,6 +1101,8 @@ void __init setup_arch(char **cmdline_p) efi_find_mirror(); } + reserve_bios_regions(); + /* * The EFI specification says that boot service code won't be called * after ExitBootServices(). This is, in fact, a lie. @@ -1125,7 +1131,15 @@ void __init setup_arch(char **cmdline_p) early_trap_pf_init(); - setup_real_mode(); + /* + * Update mmu_cr4_features (and, indirectly, trampoline_cr4_features) + * with the current CR4 value. This may not be necessary, but + * auditing all the early-boot CR4 manipulation would be needed to + * rule it out. + */ + if (boot_cpu_data.cpuid_level >= 0) + /* A CPU has %cr4 if and only if it has CPUID. */ + mmu_cr4_features = __read_cr4(); memblock_set_current_limit(get_max_mapped()); @@ -1174,13 +1188,6 @@ void __init setup_arch(char **cmdline_p) kasan_init(); - if (boot_cpu_data.cpuid_level >= 0) { - /* A CPU has %cr4 if and only if it has CPUID */ - mmu_cr4_features = __read_cr4(); - if (trampoline_cr4_features) - *trampoline_cr4_features = mmu_cr4_features; - } - #ifdef CONFIG_X86_32 /* sync back kernel address range */ clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 1ef87e887051..78b9cb5a26af 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -22,6 +22,7 @@ #include <asm/nmi.h> #include <asm/x86_init.h> #include <asm/geode.h> +#include <asm/apic.h> unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); @@ -1249,6 +1250,9 @@ static void tsc_refine_calibration_work(struct work_struct *work) (unsigned long)tsc_khz / 1000, (unsigned long)tsc_khz % 1000); + /* Inform the TSC deadline clockevent devices about the recalibration */ + lapic_update_tsc_freq(); + out: if (boot_cpu_has(X86_FEATURE_ART)) art_related_clocksource = &clocksource_tsc; diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 6c1ff31d99ff..495c776de4b4 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -357,20 +357,22 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn) *cursor &= 0xfe; } /* - * Similar treatment for VEX3 prefix. - * TODO: add XOP/EVEX treatment when insn decoder supports them + * Similar treatment for VEX3/EVEX prefix. + * TODO: add XOP treatment when insn decoder supports them */ - if (insn->vex_prefix.nbytes == 3) { + if (insn->vex_prefix.nbytes >= 3) { /* * vex2: c5 rvvvvLpp (has no b bit) * vex3/xop: c4/8f rxbmmmmm wvvvvLpp * evex: 62 rxbR00mm wvvvv1pp zllBVaaa - * (evex will need setting of both b and x since - * in non-sib encoding evex.x is 4th bit of MODRM.rm) - * Setting VEX3.b (setting because it has inverted meaning): + * Setting VEX3.b (setting because it has inverted meaning). + * Setting EVEX.x since (in non-SIB encoding) EVEX.x + * is the 4th bit of MODRM.rm, and needs the same treatment. + * For VEX3-encoded insns, VEX3.x value has no effect in + * non-SIB encoding, the change is superfluous but harmless. */ cursor = auprobe->insn + insn_offset_vex_prefix(insn) + 1; - *cursor |= 0x20; + *cursor |= 0x60; } /* @@ -415,12 +417,10 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn) reg = MODRM_REG(insn); /* Fetch modrm.reg */ reg2 = 0xff; /* Fetch vex.vvvv */ - if (insn->vex_prefix.nbytes == 2) - reg2 = insn->vex_prefix.bytes[1]; - else if (insn->vex_prefix.nbytes == 3) + if (insn->vex_prefix.nbytes) reg2 = insn->vex_prefix.bytes[2]; /* - * TODO: add XOP, EXEV vvvv reading. + * TODO: add XOP vvvv reading. * * vex.vvvv field is in bits 6-3, bits are inverted. * But in 32-bit mode, high-order bit may be ignored. diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c index f7dfeda83e5c..121f59c6ee54 100644 --- a/arch/x86/lib/kaslr.c +++ b/arch/x86/lib/kaslr.c @@ -19,7 +19,7 @@ #include <asm/cpufeature.h> #include <asm/setup.h> -#define debug_putstr(v) early_printk(v) +#define debug_putstr(v) early_printk("%s", v) #define has_cpuflag(f) boot_cpu_has(f) #define get_boot_seed() kaslr_offset() #endif diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index ec21796ac5fd..4473cb4f8b90 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -3,15 +3,17 @@ * included by both the compressed kernel and the regular kernel. */ -static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page, +static void ident_pmd_init(struct x86_mapping_info *info, pmd_t *pmd_page, unsigned long addr, unsigned long end) { addr &= PMD_MASK; for (; addr < end; addr += PMD_SIZE) { pmd_t *pmd = pmd_page + pmd_index(addr); - if (!pmd_present(*pmd)) - set_pmd(pmd, __pmd(addr | pmd_flag)); + if (pmd_present(*pmd)) + continue; + + set_pmd(pmd, __pmd((addr - info->offset) | info->pmd_flag)); } } @@ -30,13 +32,13 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, if (pud_present(*pud)) { pmd = pmd_offset(pud, 0); - ident_pmd_init(info->pmd_flag, pmd, addr, next); + ident_pmd_init(info, pmd, addr, next); continue; } pmd = (pmd_t *)info->alloc_pgt_page(info->context); if (!pmd) return -ENOMEM; - ident_pmd_init(info->pmd_flag, pmd, addr, next); + ident_pmd_init(info, pmd, addr, next); set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); } @@ -44,14 +46,15 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, } int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, - unsigned long addr, unsigned long end) + unsigned long pstart, unsigned long pend) { + unsigned long addr = pstart + info->offset; + unsigned long end = pend + info->offset; unsigned long next; int result; - int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0; for (; addr < end; addr = next) { - pgd_t *pgd = pgd_page + pgd_index(addr) + off; + pgd_t *pgd = pgd_page + pgd_index(addr); pud_t *pud; next = (addr & PGDIR_MASK) + PGDIR_SIZE; diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 620928903be3..d28a2d741f9e 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -122,8 +122,18 @@ __ref void *alloc_low_pages(unsigned int num) return __va(pfn << PAGE_SHIFT); } -/* need 3 4k for initial PMD_SIZE, 3 4k for 0-ISA_END_ADDRESS */ -#define INIT_PGT_BUF_SIZE (6 * PAGE_SIZE) +/* + * By default need 3 4k for initial PMD_SIZE, 3 4k for 0-ISA_END_ADDRESS. + * With KASLR memory randomization, depending on the machine e820 memory + * and the PUD alignment. We may need twice more pages when KASLR memory + * randomization is enabled. + */ +#ifndef CONFIG_RANDOMIZE_MEMORY +#define INIT_PGD_PAGE_COUNT 6 +#else +#define INIT_PGD_PAGE_COUNT 12 +#endif +#define INIT_PGT_BUF_SIZE (INIT_PGD_PAGE_COUNT * PAGE_SIZE) RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE); void __init early_alloc_pgt_buf(void) { diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 26dccd6c0df1..ec8654f117d8 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -97,7 +97,7 @@ void __init kernel_randomize_memory(void) * add padding if needed (especially for memory hotplug support). */ BUG_ON(kaslr_regions[0].base != &page_offset_base); - memory_tb = ((max_pfn << PAGE_SHIFT) >> TB_SHIFT) + + memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) + CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING; /* Adapt phyiscal memory region size based on available memory */ diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 4480c06cade7..89d1146f5a6f 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -254,6 +254,7 @@ void __init efi_free_boot_services(void) for_each_efi_memory_desc(md) { unsigned long long start = md->phys_addr; unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; + size_t rm_size; if (md->type != EFI_BOOT_SERVICES_CODE && md->type != EFI_BOOT_SERVICES_DATA) @@ -263,6 +264,26 @@ void __init efi_free_boot_services(void) if (md->attribute & EFI_MEMORY_RUNTIME) continue; + /* + * Nasty quirk: if all sub-1MB memory is used for boot + * services, we can get here without having allocated the + * real mode trampoline. It's too late to hand boot services + * memory back to the memblock allocator, so instead + * try to manually allocate the trampoline if needed. + * + * I've seen this on a Dell XPS 13 9350 with firmware + * 1.4.4 with SGX enabled booting Linux via Fedora 24's + * grub2-efi on a hard disk. (And no, I don't know why + * this happened, but Linux should still try to boot rather + * panicing early.) + */ + rm_size = real_mode_size_needed(); + if (rm_size && (start + rm_size) < (1<<20) && size >= rm_size) { + set_real_mode_mem(start, rm_size); + start += rm_size; + size -= rm_size; + } + free_bootmem_late(start, size); } diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c index 66b2166ea4a1..23f2f3e41c7f 100644 --- a/arch/x86/platform/uv/bios_uv.c +++ b/arch/x86/platform/uv/bios_uv.c @@ -187,7 +187,8 @@ EXPORT_SYMBOL_GPL(uv_bios_set_legacy_vga_target); void uv_bios_init(void) { uv_systab = NULL; - if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || !efi.uv_systab) { + if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || + !efi.uv_systab || efi_runtime_disabled()) { pr_crit("UV: UVsystab: missing\n"); return; } @@ -199,12 +200,14 @@ void uv_bios_init(void) return; } + /* Starting with UV4 the UV systab size is variable */ if (uv_systab->revision >= UV_SYSTAB_VERSION_UV4) { + int size = uv_systab->size; + iounmap(uv_systab); - uv_systab = ioremap(efi.uv_systab, uv_systab->size); + uv_systab = ioremap(efi.uv_systab, size); if (!uv_systab) { - pr_err("UV: UVsystab: ioremap(%d) failed!\n", - uv_systab->size); + pr_err("UV: UVsystab: ioremap(%d) failed!\n", size); return; } } diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index f0b5f2d402af..a3e3ccc87138 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -87,7 +87,7 @@ static int set_up_temporary_mappings(void) struct x86_mapping_info info = { .alloc_pgt_page = alloc_pgt_page, .pmd_flag = __PAGE_KERNEL_LARGE_EXEC, - .kernel_mapping = true, + .offset = __PAGE_OFFSET, }; unsigned long mstart, mend; pgd_t *pgd; diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 705e3fffb4a1..5db706f14111 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -1,9 +1,11 @@ #include <linux/io.h> +#include <linux/slab.h> #include <linux/memblock.h> #include <asm/cacheflush.h> #include <asm/pgtable.h> #include <asm/realmode.h> +#include <asm/tlbflush.h> struct real_mode_header *real_mode_header; u32 *trampoline_cr4_features; @@ -11,25 +13,37 @@ u32 *trampoline_cr4_features; /* Hold the pgd entry used on booting additional CPUs */ pgd_t trampoline_pgd_entry; +void __init set_real_mode_mem(phys_addr_t mem, size_t size) +{ + void *base = __va(mem); + + real_mode_header = (struct real_mode_header *) base; + printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n", + base, (unsigned long long)mem, size); +} + void __init reserve_real_mode(void) { phys_addr_t mem; - unsigned char *base; - size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob); + size_t size = real_mode_size_needed(); + + if (!size) + return; + + WARN_ON(slab_is_available()); /* Has to be under 1M so we can execute real-mode AP code. */ mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE); - if (!mem) - panic("Cannot allocate trampoline\n"); + if (!mem) { + pr_info("No sub-1M memory is available for the trampoline\n"); + return; + } - base = __va(mem); memblock_reserve(mem, size); - real_mode_header = (struct real_mode_header *) base; - printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n", - base, (unsigned long long)mem, size); + set_real_mode_mem(mem, size); } -void __init setup_real_mode(void) +static void __init setup_real_mode(void) { u16 real_mode_seg; const u32 *rel; @@ -84,7 +98,7 @@ void __init setup_real_mode(void) trampoline_header->start = (u64) secondary_startup_64; trampoline_cr4_features = &trampoline_header->cr4; - *trampoline_cr4_features = __read_cr4(); + *trampoline_cr4_features = mmu_cr4_features; trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd); trampoline_pgd[0] = trampoline_pgd_entry.pgd; @@ -100,7 +114,7 @@ void __init setup_real_mode(void) * need to mark it executable at do_pre_smp_initcalls() at least, * thus run it as a early_initcall(). */ -static int __init set_real_mode_permissions(void) +static void __init set_real_mode_permissions(void) { unsigned char *base = (unsigned char *) real_mode_header; size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob); @@ -119,7 +133,16 @@ static int __init set_real_mode_permissions(void) set_memory_nx((unsigned long) base, size >> PAGE_SHIFT); set_memory_ro((unsigned long) base, ro_size >> PAGE_SHIFT); set_memory_x((unsigned long) text_start, text_size >> PAGE_SHIFT); +} + +static int __init init_real_mode(void) +{ + if (!real_mode_header) + panic("Real mode trampoline was not allocated"); + + setup_real_mode(); + set_real_mode_permissions(); return 0; } -early_initcall(set_real_mode_permissions); +early_initcall(init_real_mode); diff --git a/crypto/Kconfig b/crypto/Kconfig index a9377bef25e3..84d71482bf08 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -439,7 +439,7 @@ config CRYPTO_CRC32C_INTEL config CRYPT_CRC32C_VPMSUM tristate "CRC32c CRC algorithm (powerpc64)" - depends on PPC64 + depends on PPC64 && ALTIVEC select CRYPTO_HASH select CRC32 help diff --git a/crypto/sha3_generic.c b/crypto/sha3_generic.c index 62264397a2d2..7e8ed96236ce 100644 --- a/crypto/sha3_generic.c +++ b/crypto/sha3_generic.c @@ -24,14 +24,14 @@ #define ROTL64(x, y) (((x) << (y)) | ((x) >> (64 - (y)))) static const u64 keccakf_rndc[24] = { - 0x0000000000000001, 0x0000000000008082, 0x800000000000808a, - 0x8000000080008000, 0x000000000000808b, 0x0000000080000001, - 0x8000000080008081, 0x8000000000008009, 0x000000000000008a, - 0x0000000000000088, 0x0000000080008009, 0x000000008000000a, - 0x000000008000808b, 0x800000000000008b, 0x8000000000008089, - 0x8000000000008003, 0x8000000000008002, 0x8000000000000080, - 0x000000000000800a, 0x800000008000000a, 0x8000000080008081, - 0x8000000000008080, 0x0000000080000001, 0x8000000080008008 + 0x0000000000000001ULL, 0x0000000000008082ULL, 0x800000000000808aULL, + 0x8000000080008000ULL, 0x000000000000808bULL, 0x0000000080000001ULL, + 0x8000000080008081ULL, 0x8000000000008009ULL, 0x000000000000008aULL, + 0x0000000000000088ULL, 0x0000000080008009ULL, 0x000000008000000aULL, + 0x000000008000808bULL, 0x800000000000008bULL, 0x8000000000008089ULL, + 0x8000000000008003ULL, 0x8000000000008002ULL, 0x8000000000000080ULL, + 0x000000000000800aULL, 0x800000008000000aULL, 0x8000000080008081ULL, + 0x8000000000008080ULL, 0x0000000080000001ULL, 0x8000000080008008ULL }; static const int keccakf_rotc[24] = { diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 8c234dd9b8bc..80cc7c089a15 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -1527,11 +1527,12 @@ static u32 read_blk_stat(struct nfit_blk *nfit_blk, unsigned int bw) { struct nfit_blk_mmio *mmio = &nfit_blk->mmio[DCR]; u64 offset = nfit_blk->stat_offset + mmio->size * bw; + const u32 STATUS_MASK = 0x80000037; if (mmio->num_lines) offset = to_interleave_offset(offset, mmio); - return readl(mmio->addr.base + offset); + return readl(mmio->addr.base + offset) & STATUS_MASK; } static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw, diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index 28bce3f4f81d..57700541f951 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -8,6 +8,9 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ + +#define pr_fmt(fmt) "arm_arch_timer: " fmt + #include <linux/init.h> #include <linux/kernel.h> #include <linux/device.h> @@ -370,16 +373,33 @@ static bool arch_timer_has_nonsecure_ppi(void) arch_timer_ppi[PHYS_NONSECURE_PPI]); } +static u32 check_ppi_trigger(int irq) +{ + u32 flags = irq_get_trigger_type(irq); + + if (flags != IRQF_TRIGGER_HIGH && flags != IRQF_TRIGGER_LOW) { + pr_warn("WARNING: Invalid trigger for IRQ%d, assuming level low\n", irq); + pr_warn("WARNING: Please fix your firmware\n"); + flags = IRQF_TRIGGER_LOW; + } + + return flags; +} + static int arch_timer_starting_cpu(unsigned int cpu) { struct clock_event_device *clk = this_cpu_ptr(arch_timer_evt); + u32 flags; __arch_timer_setup(ARCH_CP15_TIMER, clk); - enable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], 0); + flags = check_ppi_trigger(arch_timer_ppi[arch_timer_uses_ppi]); + enable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], flags); - if (arch_timer_has_nonsecure_ppi()) - enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], 0); + if (arch_timer_has_nonsecure_ppi()) { + flags = check_ppi_trigger(arch_timer_ppi[PHYS_NONSECURE_PPI]); + enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], flags); + } arch_counter_set_user_access(); if (evtstrm_enable) diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 87796e0864e9..d3ffde806629 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -145,11 +145,30 @@ static struct powernv_pstate_info { /* Use following macros for conversions between pstate_id and index */ static inline int idx_to_pstate(unsigned int i) { + if (unlikely(i >= powernv_pstate_info.nr_pstates)) { + pr_warn_once("index %u is out of bound\n", i); + return powernv_freqs[powernv_pstate_info.nominal].driver_data; + } + return powernv_freqs[i].driver_data; } static inline unsigned int pstate_to_idx(int pstate) { + int min = powernv_freqs[powernv_pstate_info.min].driver_data; + int max = powernv_freqs[powernv_pstate_info.max].driver_data; + + if (min > 0) { + if (unlikely((pstate < max) || (pstate > min))) { + pr_warn_once("pstate %d is out of bound\n", pstate); + return powernv_pstate_info.nominal; + } + } else { + if (unlikely((pstate > max) || (pstate < min))) { + pr_warn_once("pstate %d is out of bound\n", pstate); + return powernv_pstate_info.nominal; + } + } /* * abs() is deliberately used so that is works with * both monotonically increasing and decreasing @@ -593,7 +612,7 @@ void gpstate_timer_handler(unsigned long data) } else { gpstate_idx = calc_global_pstate(gpstates->elapsed_time, gpstates->highest_lpstate_idx, - freq_data.pstate_id); + gpstates->last_lpstate_idx); } /* diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c index ea8189f4b021..6dc597126b79 100644 --- a/drivers/crypto/caam/caamalg.c +++ b/drivers/crypto/caam/caamalg.c @@ -441,6 +441,9 @@ static int aead_set_sh_desc(struct crypto_aead *aead) OP_ALG_AAI_CTR_MOD128); const bool is_rfc3686 = alg->caam.rfc3686; + if (!ctx->authsize) + return 0; + /* NULL encryption / decryption */ if (!ctx->enckeylen) return aead_null_set_sh_desc(aead); @@ -614,7 +617,7 @@ skip_enc: keys_fit_inline = true; /* aead_givencrypt shared descriptor */ - desc = ctx->sh_desc_givenc; + desc = ctx->sh_desc_enc; /* Note: Context registers are saved. */ init_sh_desc_key_aead(desc, ctx, keys_fit_inline, is_rfc3686); @@ -645,13 +648,13 @@ copy_iv: append_operation(desc, ctx->class2_alg_type | OP_ALG_AS_INITFINAL | OP_ALG_ENCRYPT); - /* ivsize + cryptlen = seqoutlen - authsize */ - append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize); - /* Read and write assoclen bytes */ append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ); append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ); + /* ivsize + cryptlen = seqoutlen - authsize */ + append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize); + /* Skip assoc data */ append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF); @@ -697,7 +700,7 @@ copy_iv: ctx->sh_desc_enc_dma = dma_map_single(jrdev, desc, desc_bytes(desc), DMA_TO_DEVICE); - if (dma_mapping_error(jrdev, ctx->sh_desc_givenc_dma)) { + if (dma_mapping_error(jrdev, ctx->sh_desc_enc_dma)) { dev_err(jrdev, "unable to map shared descriptor\n"); return -ENOMEM; } diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c index f1ecc8df8d41..36365b3efdfd 100644 --- a/drivers/crypto/caam/caamhash.c +++ b/drivers/crypto/caam/caamhash.c @@ -1898,6 +1898,7 @@ caam_hash_alloc(struct caam_hash_template *template, template->name); snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s", template->driver_name); + t_alg->ahash_alg.setkey = NULL; } alg->cra_module = THIS_MODULE; alg->cra_init = caam_hash_cra_init; diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index 4fb2eb7c800d..ce0067b7a2f6 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -552,9 +552,9 @@ static const struct pci_id_table pci_dev_descr_haswell_table[] = { /* Knight's Landing Support */ /* * KNL's memory channels are swizzled between memory controllers. - * MC0 is mapped to CH3,5,6 and MC1 is mapped to CH0,1,2 + * MC0 is mapped to CH3,4,5 and MC1 is mapped to CH0,1,2 */ -#define knl_channel_remap(channel) ((channel + 3) % 6) +#define knl_channel_remap(mc, chan) ((mc) ? (chan) : (chan) + 3) /* Memory controller, TAD tables, error injection - 2-8-0, 2-9-0 (2 of these) */ #define PCI_DEVICE_ID_INTEL_KNL_IMC_MC 0x7840 @@ -1286,7 +1286,7 @@ static u32 knl_get_mc_route(int entry, u32 reg) mc = GET_BITFIELD(reg, entry*3, (entry*3)+2); chan = GET_BITFIELD(reg, (entry*2) + 18, (entry*2) + 18 + 1); - return knl_channel_remap(mc*3 + chan); + return knl_channel_remap(mc, chan); } /* @@ -2997,8 +2997,15 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci, } else { char A = *("A"); - channel = knl_channel_remap(channel); + /* + * Reported channel is in range 0-2, so we can't map it + * back to mc. To figure out mc we check machine check + * bank register that reported this error. + * bank15 means mc0 and bank16 means mc1. + */ + channel = knl_channel_remap(m->bank == 16, channel); channel_mask = 1 << channel; + snprintf(msg, sizeof(msg), "%s%s err_code:%04x:%04x channel:%d (DIMM_%c)", overflow ? " OVERFLOW" : "", diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c index c99c24bc79b0..9ae6c116c474 100644 --- a/drivers/firmware/efi/capsule-loader.c +++ b/drivers/firmware/efi/capsule-loader.c @@ -16,6 +16,7 @@ #include <linux/slab.h> #include <linux/mutex.h> #include <linux/efi.h> +#include <linux/vmalloc.h> #define NO_FURTHER_WRITE_ACTION -1 @@ -108,14 +109,15 @@ static ssize_t efi_capsule_submit_update(struct capsule_info *cap_info) int ret; void *cap_hdr_temp; - cap_hdr_temp = kmap(cap_info->pages[0]); + cap_hdr_temp = vmap(cap_info->pages, cap_info->index, + VM_MAP, PAGE_KERNEL); if (!cap_hdr_temp) { - pr_debug("%s: kmap() failed\n", __func__); + pr_debug("%s: vmap() failed\n", __func__); return -EFAULT; } ret = efi_capsule_update(cap_hdr_temp, cap_info->pages); - kunmap(cap_info->pages[0]); + vunmap(cap_hdr_temp); if (ret) { pr_err("%s: efi_capsule_update() failed\n", __func__); return ret; diff --git a/drivers/firmware/efi/capsule.c b/drivers/firmware/efi/capsule.c index 53b9fd2293ee..6eedff45e6d7 100644 --- a/drivers/firmware/efi/capsule.c +++ b/drivers/firmware/efi/capsule.c @@ -190,9 +190,9 @@ efi_capsule_update_locked(efi_capsule_header_t *capsule, * map the capsule described by @capsule with its data in @pages and * send it to the firmware via the UpdateCapsule() runtime service. * - * @capsule must be a virtual mapping of the first page in @pages - * (@pages[0]) in the kernel address space. That is, a - * capsule_header_t that describes the entire contents of the capsule + * @capsule must be a virtual mapping of the complete capsule update in the + * kernel address space, as the capsule can be consumed immediately. + * A capsule_header_t that describes the entire contents of the capsule * must be at the start of the first data page. * * Even though this function will validate that the firmware supports diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 08a1e2f3690f..00c8a08d56e7 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -68,7 +68,8 @@ void iommu_put_dma_cookie(struct iommu_domain *domain) if (!iovad) return; - put_iova_domain(iovad); + if (iovad->granule) + put_iova_domain(iovad); kfree(iovad); domain->iova_cookie = NULL; } @@ -151,12 +152,15 @@ int dma_direction_to_prot(enum dma_data_direction dir, bool coherent) } } -static struct iova *__alloc_iova(struct iova_domain *iovad, size_t size, +static struct iova *__alloc_iova(struct iommu_domain *domain, size_t size, dma_addr_t dma_limit) { + struct iova_domain *iovad = domain->iova_cookie; unsigned long shift = iova_shift(iovad); unsigned long length = iova_align(iovad, size) >> shift; + if (domain->geometry.force_aperture) + dma_limit = min(dma_limit, domain->geometry.aperture_end); /* * Enforce size-alignment to be safe - there could perhaps be an * attribute to control this per-device, or at least per-domain... @@ -314,7 +318,7 @@ struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp, if (!pages) return NULL; - iova = __alloc_iova(iovad, size, dev->coherent_dma_mask); + iova = __alloc_iova(domain, size, dev->coherent_dma_mask); if (!iova) goto out_free_pages; @@ -386,7 +390,7 @@ dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, phys_addr_t phys = page_to_phys(page) + offset; size_t iova_off = iova_offset(iovad, phys); size_t len = iova_align(iovad, size + iova_off); - struct iova *iova = __alloc_iova(iovad, len, dma_get_mask(dev)); + struct iova *iova = __alloc_iova(domain, len, dma_get_mask(dev)); if (!iova) return DMA_ERROR_CODE; @@ -538,7 +542,7 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, prev = s; } - iova = __alloc_iova(iovad, iova_len, dma_get_mask(dev)); + iova = __alloc_iova(domain, iova_len, dma_get_mask(dev)); if (!iova) goto out_restore_sg; diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h index 9ed0a8462ccf..3dab13b4a211 100644 --- a/drivers/iommu/mtk_iommu.h +++ b/drivers/iommu/mtk_iommu.h @@ -55,19 +55,19 @@ struct mtk_iommu_data { bool enable_4GB; }; -static int compare_of(struct device *dev, void *data) +static inline int compare_of(struct device *dev, void *data) { return dev->of_node == data; } -static int mtk_iommu_bind(struct device *dev) +static inline int mtk_iommu_bind(struct device *dev) { struct mtk_iommu_data *data = dev_get_drvdata(dev); return component_bind_all(dev, &data->smi_imu); } -static void mtk_iommu_unbind(struct device *dev) +static inline void mtk_iommu_unbind(struct device *dev) { struct mtk_iommu_data *data = dev_get_drvdata(dev); diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c index bdee9a01ef35..c466ee2b0c97 100644 --- a/drivers/misc/cxl/context.c +++ b/drivers/misc/cxl/context.c @@ -90,8 +90,7 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master, */ mutex_lock(&afu->contexts_lock); idr_preload(GFP_KERNEL); - i = idr_alloc(&ctx->afu->contexts_idr, ctx, - ctx->afu->adapter->native->sl_ops->min_pe, + i = idr_alloc(&ctx->afu->contexts_idr, ctx, ctx->afu->adapter->min_pe, ctx->afu->num_procs, GFP_NOWAIT); idr_preload_end(); mutex_unlock(&afu->contexts_lock); diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h index de090533f18c..344a0ff8f8c7 100644 --- a/drivers/misc/cxl/cxl.h +++ b/drivers/misc/cxl/cxl.h @@ -561,7 +561,6 @@ struct cxl_service_layer_ops { u64 (*timebase_read)(struct cxl *adapter); int capi_mode; bool needs_reset_before_disable; - int min_pe; }; struct cxl_native { @@ -603,6 +602,7 @@ struct cxl { struct bin_attribute cxl_attr; int adapter_num; int user_irqs; + int min_pe; u64 ps_size; u16 psl_rev; u16 base_image; diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c index 3bcdaee11ba1..e606fdc4bc9c 100644 --- a/drivers/misc/cxl/native.c +++ b/drivers/misc/cxl/native.c @@ -924,7 +924,7 @@ static irqreturn_t native_irq_multiplexed(int irq, void *data) return fail_psl_irq(afu, &irq_info); } -void native_irq_wait(struct cxl_context *ctx) +static void native_irq_wait(struct cxl_context *ctx) { u64 dsisr; int timeout = 1000; diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index d152e2de8c93..6f0c4ac4b649 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -379,7 +379,7 @@ static int calc_capp_routing(struct pci_dev *dev, u64 *chipid, u64 *capp_unit_id static int init_implementation_adapter_psl_regs(struct cxl *adapter, struct pci_dev *dev) { - u64 psl_dsnctl; + u64 psl_dsnctl, psl_fircntl; u64 chipid; u64 capp_unit_id; int rc; @@ -398,8 +398,11 @@ static int init_implementation_adapter_psl_regs(struct cxl *adapter, struct pci_ cxl_p1_write(adapter, CXL_PSL_RESLCKTO, 0x20000000200ULL); /* snoop write mask */ cxl_p1_write(adapter, CXL_PSL_SNWRALLOC, 0x00000000FFFFFFFFULL); - /* set fir_accum */ - cxl_p1_write(adapter, CXL_PSL_FIR_CNTL, 0x0800000000000000ULL); + /* set fir_cntl to recommended value for production env */ + psl_fircntl = (0x2ULL << (63-3)); /* ce_report */ + psl_fircntl |= (0x1ULL << (63-6)); /* FIR_report */ + psl_fircntl |= 0x1ULL; /* ce_thresh */ + cxl_p1_write(adapter, CXL_PSL_FIR_CNTL, psl_fircntl); /* for debugging with trace arrays */ cxl_p1_write(adapter, CXL_PSL_TRACE, 0x0000FF7C00000000ULL); @@ -1521,14 +1524,15 @@ static const struct cxl_service_layer_ops xsl_ops = { .write_timebase_ctrl = write_timebase_ctrl_xsl, .timebase_read = timebase_read_xsl, .capi_mode = OPAL_PHB_CAPI_MODE_DMA, - .min_pe = 1, /* Workaround for Mellanox CX4 HW bug */ }; static void set_sl_ops(struct cxl *adapter, struct pci_dev *dev) { if (dev->vendor == PCI_VENDOR_ID_MELLANOX && dev->device == 0x1013) { + /* Mellanox CX-4 */ dev_info(&adapter->dev, "Device uses an XSL\n"); adapter->native->sl_ops = &xsl_ops; + adapter->min_pe = 1; /* Workaround for CX-4 hardware bug */ } else { dev_info(&adapter->dev, "Device uses a PSL\n"); adapter->native->sl_ops = &psl_ops; diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c index dee8def1c193..7ada5f1b7bb6 100644 --- a/drivers/misc/cxl/vphb.c +++ b/drivers/misc/cxl/vphb.c @@ -221,7 +221,7 @@ int cxl_pci_vphb_add(struct cxl_afu *afu) /* Setup the PHB using arch provided callback */ phb->ops = &cxl_pcie_pci_ops; phb->cfg_addr = NULL; - phb->cfg_data = 0; + phb->cfg_data = NULL; phb->private_data = afu; phb->controller_ops = cxl_pci_controller_ops; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 1f276fa30ba6..217e8da0628c 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -152,7 +152,7 @@ module_param(lacp_rate, charp, 0); MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner; " "0 for slow, 1 for fast"); module_param(ad_select, charp, 0); -MODULE_PARM_DESC(ad_select, "803.ad aggregation selection logic; " +MODULE_PARM_DESC(ad_select, "802.3ad aggregation selection logic; " "0 for stable (default), 1 for bandwidth, " "2 for count"); module_param(min_links, int, 0); diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h index 8f12bddd5dc9..a0b453ea34c9 100644 --- a/drivers/net/dsa/b53/b53_regs.h +++ b/drivers/net/dsa/b53/b53_regs.h @@ -258,7 +258,7 @@ * BCM5325 and BCM5365 share most definitions below */ #define B53_ARLTBL_MAC_VID_ENTRY(n) (0x10 * (n)) -#define ARLTBL_MAC_MASK 0xffffffffffff +#define ARLTBL_MAC_MASK 0xffffffffffffULL #define ARLTBL_VID_S 48 #define ARLTBL_VID_MASK_25 0xff #define ARLTBL_VID_MASK 0xfff diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index d36aedde8cb9..d1d9d3cf9139 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3187,6 +3187,7 @@ static int mv88e6xxx_set_addr(struct dsa_switch *ds, u8 *addr) return err; } +#ifdef CONFIG_NET_DSA_HWMON static int mv88e6xxx_mdio_page_read(struct dsa_switch *ds, int port, int page, int reg) { @@ -3212,6 +3213,7 @@ static int mv88e6xxx_mdio_page_write(struct dsa_switch *ds, int port, int page, return ret; } +#endif static int mv88e6xxx_port_to_mdio_addr(struct mv88e6xxx_chip *chip, int port) { diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index 37a0f463b8de..18bb9556dd00 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -793,6 +793,8 @@ int xgene_enet_phy_connect(struct net_device *ndev) netdev_err(ndev, "Could not connect to PHY\n"); return -ENODEV; } +#else + return -ENODEV; #endif } diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index 4bff0f3040df..b0da9693f28a 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -771,8 +771,10 @@ int arc_emac_probe(struct net_device *ndev, int interface) priv->dev = dev; priv->regs = devm_ioremap_resource(dev, &res_regs); - if (IS_ERR(priv->regs)) - return PTR_ERR(priv->regs); + if (IS_ERR(priv->regs)) { + err = PTR_ERR(priv->regs); + goto out_put_node; + } dev_dbg(dev, "Registers base address is 0x%p\n", priv->regs); diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index ff300f7cf529..659261218d9f 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -12552,10 +12552,6 @@ static int tg3_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, info->data = TG3_RSS_MAX_NUM_QS; } - /* The first interrupt vector only - * handles link interrupts. - */ - info->data -= 1; return 0; default: @@ -14014,6 +14010,7 @@ static int tg3_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) } if ((ec->rx_coalesce_usecs > MAX_RXCOL_TICKS) || + (!ec->rx_coalesce_usecs) || (ec->tx_coalesce_usecs > MAX_TXCOL_TICKS) || (ec->rx_max_coalesced_frames > MAX_RXMAX_FRAMES) || (ec->tx_max_coalesced_frames > MAX_TXMAX_FRAMES) || diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 36893d8958d4..b6fcf10621b6 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -403,11 +403,11 @@ #define MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII 0x00000004 #define MACB_CAPS_NO_GIGABIT_HALF 0x00000008 #define MACB_CAPS_USRIO_DISABLED 0x00000010 +#define MACB_CAPS_JUMBO 0x00000020 #define MACB_CAPS_FIFO_MODE 0x10000000 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000 #define MACB_CAPS_SG_DISABLED 0x40000000 #define MACB_CAPS_MACB_IS_GEM 0x80000000 -#define MACB_CAPS_JUMBO 0x00000010 /* Bit manipulation macros */ #define MACB_BIT(name) \ diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index 1471e16ba719..f45385f5c6e5 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -1299,6 +1299,7 @@ static int dm9000_open(struct net_device *dev) { struct board_info *db = netdev_priv(dev); + unsigned int irq_flags = irq_get_trigger_type(dev->irq); if (netif_msg_ifup(db)) dev_dbg(db->dev, "enabling %s\n", dev->name); @@ -1306,9 +1307,11 @@ dm9000_open(struct net_device *dev) /* If there is no IRQ type specified, tell the user that this is a * problem */ - if (irq_get_trigger_type(dev->irq) == IRQF_TRIGGER_NONE) + if (irq_flags == IRQF_TRIGGER_NONE) dev_warn(db->dev, "WARNING: no IRQ resource flags set.\n"); + irq_flags |= IRQF_SHARED; + /* GPIO0 on pre-activate PHY, Reg 1F is not set by reset */ iow(db, DM9000_GPR, 0); /* REG_1F bit0 activate phyxcer */ mdelay(1); /* delay needs by DM9000B */ @@ -1316,8 +1319,7 @@ dm9000_open(struct net_device *dev) /* Initialize DM9000 board */ dm9000_init_dm9000(dev); - if (request_irq(dev->irq, dm9000_interrupt, IRQF_SHARED, - dev->name, dev)) + if (request_irq(dev->irq, dm9000_interrupt, irq_flags, dev->name, dev)) return -EAGAIN; /* Now that we have an interrupt handler hooked up we can unmask * our interrupts diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c index 1235c7f2564b..1e1eb92998fb 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c @@ -17,7 +17,7 @@ static const struct mac_stats_string g_gmac_stats_string[] = { {"gmac_rx_octets_total_ok", MAC_STATS_FIELD_OFF(rx_good_bytes)}, {"gmac_rx_octets_bad", MAC_STATS_FIELD_OFF(rx_bad_bytes)}, {"gmac_rx_uc_pkts", MAC_STATS_FIELD_OFF(rx_uc_pkts)}, - {"gamc_rx_mc_pkts", MAC_STATS_FIELD_OFF(rx_mc_pkts)}, + {"gmac_rx_mc_pkts", MAC_STATS_FIELD_OFF(rx_mc_pkts)}, {"gmac_rx_bc_pkts", MAC_STATS_FIELD_OFF(rx_bc_pkts)}, {"gmac_rx_pkts_64octets", MAC_STATS_FIELD_OFF(rx_64bytes)}, {"gmac_rx_pkts_65to127", MAC_STATS_FIELD_OFF(rx_65to127)}, diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c index 7fd4d54599e4..6b03c8553e59 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.c +++ b/drivers/net/ethernet/intel/e1000e/82571.c @@ -2032,7 +2032,8 @@ const struct e1000_info e1000_82574_info = { | FLAG2_DISABLE_ASPM_L0S | FLAG2_DISABLE_ASPM_L1 | FLAG2_NO_DISABLE_RX - | FLAG2_DMA_BURST, + | FLAG2_DMA_BURST + | FLAG2_CHECK_SYSTIM_OVERFLOW, .pba = 32, .max_hw_frame_size = DEFAULT_JUMBO, .get_variants = e1000_get_variants_82571, @@ -2053,7 +2054,8 @@ const struct e1000_info e1000_82583_info = { | FLAG_HAS_CTRLEXT_ON_LOAD, .flags2 = FLAG2_DISABLE_ASPM_L0S | FLAG2_DISABLE_ASPM_L1 - | FLAG2_NO_DISABLE_RX, + | FLAG2_NO_DISABLE_RX + | FLAG2_CHECK_SYSTIM_OVERFLOW, .pba = 32, .max_hw_frame_size = DEFAULT_JUMBO, .get_variants = e1000_get_variants_82571, diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index ef96cd11d6d2..879cca47b021 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -452,6 +452,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca); #define FLAG2_PCIM2PCI_ARBITER_WA BIT(11) #define FLAG2_DFLT_CRC_STRIPPING BIT(12) #define FLAG2_CHECK_RX_HWTSTAMP BIT(13) +#define FLAG2_CHECK_SYSTIM_OVERFLOW BIT(14) #define E1000_RX_DESC_PS(R, i) \ (&(((union e1000_rx_desc_packet_split *)((R).desc))[i])) diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 3e11322d8d58..f3aaca743ea3 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -5885,7 +5885,8 @@ const struct e1000_info e1000_pch_lpt_info = { | FLAG_HAS_JUMBO_FRAMES | FLAG_APME_IN_WUC, .flags2 = FLAG2_HAS_PHY_STATS - | FLAG2_HAS_EEE, + | FLAG2_HAS_EEE + | FLAG2_CHECK_SYSTIM_OVERFLOW, .pba = 26, .max_hw_frame_size = 9022, .get_variants = e1000_get_variants_ich8lan, diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 02f443958f31..7017281ba2dc 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -4303,6 +4303,42 @@ void e1000e_reinit_locked(struct e1000_adapter *adapter) } /** + * e1000e_sanitize_systim - sanitize raw cycle counter reads + * @hw: pointer to the HW structure + * @systim: cycle_t value read, sanitized and returned + * + * Errata for 82574/82583 possible bad bits read from SYSTIMH/L: + * check to see that the time is incrementing at a reasonable + * rate and is a multiple of incvalue. + **/ +static cycle_t e1000e_sanitize_systim(struct e1000_hw *hw, cycle_t systim) +{ + u64 time_delta, rem, temp; + cycle_t systim_next; + u32 incvalue; + int i; + + incvalue = er32(TIMINCA) & E1000_TIMINCA_INCVALUE_MASK; + for (i = 0; i < E1000_MAX_82574_SYSTIM_REREADS; i++) { + /* latch SYSTIMH on read of SYSTIML */ + systim_next = (cycle_t)er32(SYSTIML); + systim_next |= (cycle_t)er32(SYSTIMH) << 32; + + time_delta = systim_next - systim; + temp = time_delta; + /* VMWare users have seen incvalue of zero, don't div / 0 */ + rem = incvalue ? do_div(temp, incvalue) : (time_delta != 0); + + systim = systim_next; + + if ((time_delta < E1000_82574_SYSTIM_EPSILON) && (rem == 0)) + break; + } + + return systim; +} + +/** * e1000e_cyclecounter_read - read raw cycle counter (used by time counter) * @cc: cyclecounter structure **/ @@ -4312,7 +4348,7 @@ static cycle_t e1000e_cyclecounter_read(const struct cyclecounter *cc) cc); struct e1000_hw *hw = &adapter->hw; u32 systimel, systimeh; - cycle_t systim, systim_next; + cycle_t systim; /* SYSTIMH latching upon SYSTIML read does not work well. * This means that if SYSTIML overflows after we read it but before * we read SYSTIMH, the value of SYSTIMH has been incremented and we @@ -4335,33 +4371,9 @@ static cycle_t e1000e_cyclecounter_read(const struct cyclecounter *cc) systim = (cycle_t)systimel; systim |= (cycle_t)systimeh << 32; - if ((hw->mac.type == e1000_82574) || (hw->mac.type == e1000_82583)) { - u64 time_delta, rem, temp; - u32 incvalue; - int i; - - /* errata for 82574/82583 possible bad bits read from SYSTIMH/L - * check to see that the time is incrementing at a reasonable - * rate and is a multiple of incvalue - */ - incvalue = er32(TIMINCA) & E1000_TIMINCA_INCVALUE_MASK; - for (i = 0; i < E1000_MAX_82574_SYSTIM_REREADS; i++) { - /* latch SYSTIMH on read of SYSTIML */ - systim_next = (cycle_t)er32(SYSTIML); - systim_next |= (cycle_t)er32(SYSTIMH) << 32; - - time_delta = systim_next - systim; - temp = time_delta; - /* VMWare users have seen incvalue of zero, don't div / 0 */ - rem = incvalue ? do_div(temp, incvalue) : (time_delta != 0); - - systim = systim_next; + if (adapter->flags2 & FLAG2_CHECK_SYSTIM_OVERFLOW) + systim = e1000e_sanitize_systim(hw, systim); - if ((time_delta < E1000_82574_SYSTIM_EPSILON) && - (rem == 0)) - break; - } - } return systim; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 81c99e1be708..c6ac7a61812f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -4554,23 +4554,38 @@ static u8 i40e_get_iscsi_tc_map(struct i40e_pf *pf) **/ static u8 i40e_dcb_get_num_tc(struct i40e_dcbx_config *dcbcfg) { + int i, tc_unused = 0; u8 num_tc = 0; - int i; + u8 ret = 0; /* Scan the ETS Config Priority Table to find * traffic class enabled for a given priority - * and use the traffic class index to get the - * number of traffic classes enabled + * and create a bitmask of enabled TCs */ - for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) { - if (dcbcfg->etscfg.prioritytable[i] > num_tc) - num_tc = dcbcfg->etscfg.prioritytable[i]; - } + for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) + num_tc |= BIT(dcbcfg->etscfg.prioritytable[i]); - /* Traffic class index starts from zero so - * increment to return the actual count + /* Now scan the bitmask to check for + * contiguous TCs starting with TC0 */ - return num_tc + 1; + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { + if (num_tc & BIT(i)) { + if (!tc_unused) { + ret++; + } else { + pr_err("Non-contiguous TC - Disabling DCB\n"); + return 1; + } + } else { + tc_unused = 1; + } + } + + /* There is always at least TC0 */ + if (!ret) + ret = 1; + + return ret; } /** diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index e61b647f5f2a..336c103ae374 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -744,7 +744,8 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter) } } - shhwtstamps.hwtstamp = ktime_sub_ns(shhwtstamps.hwtstamp, adjust); + shhwtstamps.hwtstamp = + ktime_add_ns(shhwtstamps.hwtstamp, adjust); skb_tstamp_tx(adapter->ptp_tx_skb, &shhwtstamps); dev_kfree_skb_any(adapter->ptp_tx_skb); @@ -767,13 +768,32 @@ void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, struct sk_buff *skb) { __le64 *regval = (__le64 *)va; + struct igb_adapter *adapter = q_vector->adapter; + int adjust = 0; /* The timestamp is recorded in little endian format. * DWORD: 0 1 2 3 * Field: Reserved Reserved SYSTIML SYSTIMH */ - igb_ptp_systim_to_hwtstamp(q_vector->adapter, skb_hwtstamps(skb), + igb_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), le64_to_cpu(regval[1])); + + /* adjust timestamp for the RX latency based on link speed */ + if (adapter->hw.mac.type == e1000_i210) { + switch (adapter->link_speed) { + case SPEED_10: + adjust = IGB_I210_RX_LATENCY_10; + break; + case SPEED_100: + adjust = IGB_I210_RX_LATENCY_100; + break; + case SPEED_1000: + adjust = IGB_I210_RX_LATENCY_1000; + break; + } + } + skb_hwtstamps(skb)->hwtstamp = + ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust); } /** @@ -825,7 +845,7 @@ void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, } } skb_hwtstamps(skb)->hwtstamp = - ktime_add_ns(skb_hwtstamps(skb)->hwtstamp, adjust); + ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust); /* Update the last_rx_timestamp timer in order to enable watchdog check * for error case of latched timestamp on a dropped packet. diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 5418c69a7463..b4f03748adc0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -4100,6 +4100,8 @@ static void ixgbe_vlan_promisc_enable(struct ixgbe_adapter *adapter) struct ixgbe_hw *hw = &adapter->hw; u32 vlnctrl, i; + vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); + switch (hw->mac.type) { case ixgbe_mac_82599EB: case ixgbe_mac_X540: @@ -4112,8 +4114,7 @@ static void ixgbe_vlan_promisc_enable(struct ixgbe_adapter *adapter) /* fall through */ case ixgbe_mac_82598EB: /* legacy case, we can just disable VLAN filtering */ - vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); - vlnctrl &= ~(IXGBE_VLNCTRL_VFE | IXGBE_VLNCTRL_CFIEN); + vlnctrl &= ~IXGBE_VLNCTRL_VFE; IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); return; } @@ -4125,6 +4126,10 @@ static void ixgbe_vlan_promisc_enable(struct ixgbe_adapter *adapter) /* Set flag so we don't redo unnecessary work */ adapter->flags2 |= IXGBE_FLAG2_VLAN_PROMISC; + /* For VMDq and SR-IOV we must leave VLAN filtering enabled */ + vlnctrl |= IXGBE_VLNCTRL_VFE; + IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); + /* Add PF to all active pools */ for (i = IXGBE_VLVF_ENTRIES; --i;) { u32 reg_offset = IXGBE_VLVFB(i * 2 + VMDQ_P(0) / 32); @@ -4191,6 +4196,11 @@ static void ixgbe_vlan_promisc_disable(struct ixgbe_adapter *adapter) struct ixgbe_hw *hw = &adapter->hw; u32 vlnctrl, i; + /* Set VLAN filtering to enabled */ + vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); + vlnctrl |= IXGBE_VLNCTRL_VFE; + IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); + switch (hw->mac.type) { case ixgbe_mac_82599EB: case ixgbe_mac_X540: @@ -4202,10 +4212,6 @@ static void ixgbe_vlan_promisc_disable(struct ixgbe_adapter *adapter) break; /* fall through */ case ixgbe_mac_82598EB: - vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); - vlnctrl &= ~IXGBE_VLNCTRL_CFIEN; - vlnctrl |= IXGBE_VLNCTRL_VFE; - IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); return; } @@ -8390,12 +8396,14 @@ static int parse_tc_actions(struct ixgbe_adapter *adapter, struct tcf_exts *exts, u64 *action, u8 *queue) { const struct tc_action *a; + LIST_HEAD(actions); int err; if (tc_no_actions(exts)) return -EINVAL; - tc_for_each_action(a, exts) { + tcf_exts_to_list(exts, &actions); + list_for_each_entry(a, &actions, list) { /* Drop action */ if (is_tcf_gact_shot(a)) { @@ -9517,6 +9525,7 @@ skip_sriov: /* copy netdev features into list of user selectable features */ netdev->hw_features |= netdev->features | + NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_RXALL | diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index b57ae3afb994..f1609542adf1 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -245,12 +245,16 @@ static int mtk_phy_connect(struct mtk_mac *mac) case PHY_INTERFACE_MODE_MII: ge_mode = 1; break; - case PHY_INTERFACE_MODE_RMII: + case PHY_INTERFACE_MODE_REVMII: ge_mode = 2; break; + case PHY_INTERFACE_MODE_RMII: + if (!mac->id) + goto err_phy; + ge_mode = 3; + break; default: - dev_err(eth->dev, "invalid phy_mode\n"); - return -1; + goto err_phy; } /* put the gmac into the right mode */ @@ -263,13 +267,25 @@ static int mtk_phy_connect(struct mtk_mac *mac) mac->phy_dev->autoneg = AUTONEG_ENABLE; mac->phy_dev->speed = 0; mac->phy_dev->duplex = 0; + + if (of_phy_is_fixed_link(mac->of_node)) + mac->phy_dev->supported |= + SUPPORTED_Pause | SUPPORTED_Asym_Pause; + mac->phy_dev->supported &= PHY_GBIT_FEATURES | SUPPORTED_Pause | SUPPORTED_Asym_Pause; mac->phy_dev->advertising = mac->phy_dev->supported | ADVERTISED_Autoneg; phy_start_aneg(mac->phy_dev); + of_node_put(np); + return 0; + +err_phy: + of_node_put(np); + dev_err(eth->dev, "invalid phy_mode\n"); + return -EINVAL; } static int mtk_mdio_init(struct mtk_eth *eth) @@ -542,15 +558,15 @@ static inline struct mtk_tx_buf *mtk_desc_to_tx_buf(struct mtk_tx_ring *ring, return &ring->buf[idx]; } -static void mtk_tx_unmap(struct device *dev, struct mtk_tx_buf *tx_buf) +static void mtk_tx_unmap(struct mtk_eth *eth, struct mtk_tx_buf *tx_buf) { if (tx_buf->flags & MTK_TX_FLAGS_SINGLE0) { - dma_unmap_single(dev, + dma_unmap_single(eth->dev, dma_unmap_addr(tx_buf, dma_addr0), dma_unmap_len(tx_buf, dma_len0), DMA_TO_DEVICE); } else if (tx_buf->flags & MTK_TX_FLAGS_PAGE0) { - dma_unmap_page(dev, + dma_unmap_page(eth->dev, dma_unmap_addr(tx_buf, dma_addr0), dma_unmap_len(tx_buf, dma_len0), DMA_TO_DEVICE); @@ -595,9 +611,9 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, if (skb_vlan_tag_present(skb)) txd4 |= TX_DMA_INS_VLAN | skb_vlan_tag_get(skb); - mapped_addr = dma_map_single(&dev->dev, skb->data, + mapped_addr = dma_map_single(eth->dev, skb->data, skb_headlen(skb), DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(&dev->dev, mapped_addr))) + if (unlikely(dma_mapping_error(eth->dev, mapped_addr))) return -ENOMEM; WRITE_ONCE(itxd->txd1, mapped_addr); @@ -623,10 +639,10 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, n_desc++; frag_map_size = min(frag_size, MTK_TX_DMA_BUF_LEN); - mapped_addr = skb_frag_dma_map(&dev->dev, frag, offset, + mapped_addr = skb_frag_dma_map(eth->dev, frag, offset, frag_map_size, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(&dev->dev, mapped_addr))) + if (unlikely(dma_mapping_error(eth->dev, mapped_addr))) goto err_dma; if (i == nr_frags - 1 && @@ -679,7 +695,7 @@ err_dma: tx_buf = mtk_desc_to_tx_buf(ring, itxd); /* unmap dma */ - mtk_tx_unmap(&dev->dev, tx_buf); + mtk_tx_unmap(eth, tx_buf); itxd->txd3 = TX_DMA_LS0 | TX_DMA_OWNER_CPU; itxd = mtk_qdma_phys_to_virt(ring, itxd->txd2); @@ -836,11 +852,11 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, netdev->stats.rx_dropped++; goto release_desc; } - dma_addr = dma_map_single(ð->netdev[mac]->dev, + dma_addr = dma_map_single(eth->dev, new_data + NET_SKB_PAD, ring->buf_size, DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(&netdev->dev, dma_addr))) { + if (unlikely(dma_mapping_error(eth->dev, dma_addr))) { skb_free_frag(new_data); netdev->stats.rx_dropped++; goto release_desc; @@ -855,7 +871,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, } skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); - dma_unmap_single(&netdev->dev, trxd.rxd1, + dma_unmap_single(eth->dev, trxd.rxd1, ring->buf_size, DMA_FROM_DEVICE); pktlen = RX_DMA_GET_PLEN0(trxd.rxd2); skb->dev = netdev; @@ -937,7 +953,7 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget) done[mac]++; budget--; } - mtk_tx_unmap(eth->dev, tx_buf); + mtk_tx_unmap(eth, tx_buf); ring->last_free = desc; atomic_inc(&ring->free_count); @@ -1092,7 +1108,7 @@ static void mtk_tx_clean(struct mtk_eth *eth) if (ring->buf) { for (i = 0; i < MTK_DMA_SIZE; i++) - mtk_tx_unmap(eth->dev, &ring->buf[i]); + mtk_tx_unmap(eth, &ring->buf[i]); kfree(ring->buf); ring->buf = NULL; } @@ -1751,6 +1767,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) goto free_netdev; } spin_lock_init(&mac->hw_stats->stats_lock); + u64_stats_init(&mac->hw_stats->syncp); mac->hw_stats->reg_offset = id * MTK_STAT_OFFSET; SET_NETDEV_DEV(eth->netdev[id], eth->dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 0f19b01e3fff..dc8b1cb0fdc8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -318,6 +318,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, u32 *action, u32 *flow_tag) { const struct tc_action *a; + LIST_HEAD(actions); if (tc_no_actions(exts)) return -EINVAL; @@ -325,7 +326,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, *flow_tag = MLX5_FS_DEFAULT_FLOW_TAG; *action = 0; - tc_for_each_action(a, exts) { + tcf_exts_to_list(exts, &actions); + list_for_each_entry(a, &actions, list) { /* Only support a single action per rule */ if (*action) return -EINVAL; @@ -362,13 +364,15 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, u32 *action, u32 *dest_vport) { const struct tc_action *a; + LIST_HEAD(actions); if (tc_no_actions(exts)) return -EINVAL; *action = 0; - tc_for_each_action(a, exts) { + tcf_exts_to_list(exts, &actions); + list_for_each_entry(a, &actions, list) { /* Only support a single action per rule */ if (*action) return -EINVAL; @@ -503,6 +507,7 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow; struct tc_action *a; struct mlx5_fc *counter; + LIST_HEAD(actions); u64 bytes; u64 packets; u64 lastuse; @@ -518,7 +523,8 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv, mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse); - tc_for_each_action(a, f->exts) + tcf_exts_to_list(f->exts, &actions); + list_for_each_entry(a, &actions, list) tcf_action_stats_update(a, bytes, packets, lastuse); return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 7ca9201f7dcb..1721098eef13 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -3383,6 +3383,15 @@ MLXSW_ITEM32(reg, ritr, ipv4_fe, 0x04, 29, 1); */ MLXSW_ITEM32(reg, ritr, ipv6_fe, 0x04, 28, 1); +/* reg_ritr_lb_en + * Loop-back filter enable for unicast packets. + * If the flag is set then loop-back filter for unicast packets is + * implemented on the RIF. Multicast packets are always subject to + * loop-back filtering. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, lb_en, 0x04, 24, 1); + /* reg_ritr_virtual_router * Virtual router ID associated with the router interface. * Access: RW @@ -3484,6 +3493,7 @@ static inline void mlxsw_reg_ritr_pack(char *payload, bool enable, mlxsw_reg_ritr_op_set(payload, op); mlxsw_reg_ritr_rif_set(payload, rif); mlxsw_reg_ritr_ipv4_fe_set(payload, 1); + mlxsw_reg_ritr_lb_en_set(payload, 1); mlxsw_reg_ritr_mtu_set(payload, mtu); mlxsw_reg_ritr_if_mac_memcpy_to(payload, mac); } @@ -4000,6 +4010,7 @@ static inline void mlxsw_reg_ralue_pack(char *payload, { MLXSW_REG_ZERO(ralue, payload); mlxsw_reg_ralue_protocol_set(payload, protocol); + mlxsw_reg_ralue_op_set(payload, op); mlxsw_reg_ralue_virtual_router_set(payload, virtual_router); mlxsw_reg_ralue_prefix_len_set(payload, prefix_len); mlxsw_reg_ralue_entry_type_set(payload, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index c3e61500819d..1f8168906811 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -942,8 +942,8 @@ static void mlxsw_sp_port_vport_destroy(struct mlxsw_sp_port *mlxsw_sp_vport) kfree(mlxsw_sp_vport); } -int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto, - u16 vid) +static int mlxsw_sp_port_add_vid(struct net_device *dev, + __be16 __always_unused proto, u16 vid) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); struct mlxsw_sp_port *mlxsw_sp_vport; @@ -956,16 +956,12 @@ int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto, if (!vid) return 0; - if (mlxsw_sp_port_vport_find(mlxsw_sp_port, vid)) { - netdev_warn(dev, "VID=%d already configured\n", vid); + if (mlxsw_sp_port_vport_find(mlxsw_sp_port, vid)) return 0; - } mlxsw_sp_vport = mlxsw_sp_port_vport_create(mlxsw_sp_port, vid); - if (!mlxsw_sp_vport) { - netdev_err(dev, "Failed to create vPort for VID=%d\n", vid); + if (!mlxsw_sp_vport) return -ENOMEM; - } /* When adding the first VLAN interface on a bridged port we need to * transition all the active 802.1Q bridge VLANs to use explicit @@ -973,24 +969,17 @@ int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto, */ if (list_is_singular(&mlxsw_sp_port->vports_list)) { err = mlxsw_sp_port_vp_mode_trans(mlxsw_sp_port); - if (err) { - netdev_err(dev, "Failed to set to Virtual mode\n"); + if (err) goto err_port_vp_mode_trans; - } } err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, false); - if (err) { - netdev_err(dev, "Failed to disable learning for VID=%d\n", vid); + if (err) goto err_port_vid_learning_set; - } err = mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, true, untagged); - if (err) { - netdev_err(dev, "Failed to set VLAN membership for VID=%d\n", - vid); + if (err) goto err_port_add_vid; - } return 0; @@ -1010,7 +999,6 @@ static int mlxsw_sp_port_kill_vid(struct net_device *dev, struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); struct mlxsw_sp_port *mlxsw_sp_vport; struct mlxsw_sp_fid *f; - int err; /* VLAN 0 is removed from HW filter when device goes down, but * it is reserved in our case, so simply return. @@ -1019,23 +1007,12 @@ static int mlxsw_sp_port_kill_vid(struct net_device *dev, return 0; mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid); - if (!mlxsw_sp_vport) { - netdev_warn(dev, "VID=%d does not exist\n", vid); + if (WARN_ON(!mlxsw_sp_vport)) return 0; - } - err = mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, false, false); - if (err) { - netdev_err(dev, "Failed to set VLAN membership for VID=%d\n", - vid); - return err; - } + mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, false, false); - err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, true); - if (err) { - netdev_err(dev, "Failed to enable learning for VID=%d\n", vid); - return err; - } + mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, true); /* Drop FID reference. If this was the last reference the * resources will be freed. @@ -1048,13 +1025,8 @@ static int mlxsw_sp_port_kill_vid(struct net_device *dev, * transition all active 802.1Q bridge VLANs to use VID to FID * mappings and set port's mode to VLAN mode. */ - if (list_is_singular(&mlxsw_sp_port->vports_list)) { - err = mlxsw_sp_port_vlan_mode_trans(mlxsw_sp_port); - if (err) { - netdev_err(dev, "Failed to set to VLAN mode\n"); - return err; - } - } + if (list_is_singular(&mlxsw_sp_port->vports_list)) + mlxsw_sp_port_vlan_mode_trans(mlxsw_sp_port); mlxsw_sp_port_vport_destroy(mlxsw_sp_vport); @@ -1149,6 +1121,7 @@ static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress) { const struct tc_action *a; + LIST_HEAD(actions); int err; if (!tc_single_action(cls->exts)) { @@ -1156,7 +1129,8 @@ static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, return -ENOTSUPP; } - tc_for_each_action(a, cls->exts) { + tcf_exts_to_list(cls->exts, &actions); + list_for_each_entry(a, &actions, list) { if (!is_tcf_mirred_mirror(a) || protocol != htons(ETH_P_ALL)) return -ENOTSUPP; @@ -2076,6 +2050,18 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port) return 0; } +static int mlxsw_sp_port_pvid_vport_create(struct mlxsw_sp_port *mlxsw_sp_port) +{ + mlxsw_sp_port->pvid = 1; + + return mlxsw_sp_port_add_vid(mlxsw_sp_port->dev, 0, 1); +} + +static int mlxsw_sp_port_pvid_vport_destroy(struct mlxsw_sp_port *mlxsw_sp_port) +{ + return mlxsw_sp_port_kill_vid(mlxsw_sp_port->dev, 0, 1); +} + static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, bool split, u8 module, u8 width, u8 lane) { @@ -2191,7 +2177,15 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, goto err_port_dcb_init; } + err = mlxsw_sp_port_pvid_vport_create(mlxsw_sp_port); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to create PVID vPort\n", + mlxsw_sp_port->local_port); + goto err_port_pvid_vport_create; + } + mlxsw_sp_port_switchdev_init(mlxsw_sp_port); + mlxsw_sp->ports[local_port] = mlxsw_sp_port; err = register_netdev(dev); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to register netdev\n", @@ -2208,24 +2202,23 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, goto err_core_port_init; } - err = mlxsw_sp_port_vlan_init(mlxsw_sp_port); - if (err) - goto err_port_vlan_init; - - mlxsw_sp->ports[local_port] = mlxsw_sp_port; return 0; -err_port_vlan_init: - mlxsw_core_port_fini(&mlxsw_sp_port->core_port); err_core_port_init: unregister_netdev(dev); err_register_netdev: + mlxsw_sp->ports[local_port] = NULL; + mlxsw_sp_port_switchdev_fini(mlxsw_sp_port); + mlxsw_sp_port_pvid_vport_destroy(mlxsw_sp_port); +err_port_pvid_vport_create: + mlxsw_sp_port_dcb_fini(mlxsw_sp_port); err_port_dcb_init: err_port_ets_init: err_port_buffers_init: err_port_admin_status_set: err_port_mtu_set: err_port_speed_by_width_set: + mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT); err_port_swid_set: err_port_system_port_mapping_set: err_dev_addr_init: @@ -2245,12 +2238,12 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port) if (!mlxsw_sp_port) return; - mlxsw_sp->ports[local_port] = NULL; mlxsw_core_port_fini(&mlxsw_sp_port->core_port); unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */ - mlxsw_sp_port_dcb_fini(mlxsw_sp_port); - mlxsw_sp_port_kill_vid(mlxsw_sp_port->dev, 0, 1); + mlxsw_sp->ports[local_port] = NULL; mlxsw_sp_port_switchdev_fini(mlxsw_sp_port); + mlxsw_sp_port_pvid_vport_destroy(mlxsw_sp_port); + mlxsw_sp_port_dcb_fini(mlxsw_sp_port); mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT); mlxsw_sp_port_module_unmap(mlxsw_sp, mlxsw_sp_port->local_port); free_percpu(mlxsw_sp_port->pcpu_stats); @@ -2662,6 +2655,26 @@ static const struct mlxsw_rx_listener mlxsw_sp_rx_listener[] = { { .func = mlxsw_sp_rx_listener_func, .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_MTUERROR, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_TTLERROR, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_LBERROR, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_OSPF, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, .trap_id = MLXSW_TRAP_ID_IP2ME, }, { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index f69aa37d1521..ab3feb81bd43 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -536,8 +536,6 @@ int mlxsw_sp_port_vid_to_fid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid); int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin, u16 vid_end, bool is_member, bool untagged); -int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto, - u16 vid); int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 fid, bool set); void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 074cdda7b6f3..237418a0e6e0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -330,7 +330,7 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_cpu_port_sb_cms[] = { MLXSW_SP_CPU_PORT_SB_CM, MLXSW_SP_CPU_PORT_SB_CM, MLXSW_SP_CPU_PORT_SB_CM, - MLXSW_SP_CPU_PORT_SB_CM, + MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(10000), 0, 0), MLXSW_SP_CPU_PORT_SB_CM, MLXSW_SP_CPU_PORT_SB_CM, MLXSW_SP_CPU_PORT_SB_CM, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c index 01cfb7512827..b6ed7f7c531e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c @@ -341,6 +341,8 @@ static int mlxsw_sp_port_pfc_set(struct mlxsw_sp_port *mlxsw_sp_port, char pfcc_pl[MLXSW_REG_PFCC_LEN]; mlxsw_reg_pfcc_pack(pfcc_pl, mlxsw_sp_port->local_port); + mlxsw_reg_pfcc_pprx_set(pfcc_pl, mlxsw_sp_port->link.rx_pause); + mlxsw_reg_pfcc_pptx_set(pfcc_pl, mlxsw_sp_port->link.tx_pause); mlxsw_reg_pfcc_prio_pack(pfcc_pl, pfc->pfc_en); return mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core, MLXSW_REG(pfcc), @@ -351,17 +353,17 @@ static int mlxsw_sp_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + bool pause_en = mlxsw_sp_port_is_pause_en(mlxsw_sp_port); int err; - if ((mlxsw_sp_port->link.tx_pause || mlxsw_sp_port->link.rx_pause) && - pfc->pfc_en) { + if (pause_en && pfc->pfc_en) { netdev_err(dev, "PAUSE frames already enabled on port\n"); return -EINVAL; } err = __mlxsw_sp_port_headroom_set(mlxsw_sp_port, dev->mtu, mlxsw_sp_port->dcb.ets->prio_tc, - false, pfc); + pause_en, pfc); if (err) { netdev_err(dev, "Failed to configure port's headroom for PFC\n"); return err; @@ -380,7 +382,7 @@ static int mlxsw_sp_dcbnl_ieee_setpfc(struct net_device *dev, err_port_pfc_set: __mlxsw_sp_port_headroom_set(mlxsw_sp_port, dev->mtu, - mlxsw_sp_port->dcb.ets->prio_tc, false, + mlxsw_sp_port->dcb.ets->prio_tc, pause_en, mlxsw_sp_port->dcb.pfc); return err; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 81418d629231..90bb93b037ec 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1651,9 +1651,10 @@ static void mlxsw_sp_router_fib4_add_info_destroy(void const *data) const struct mlxsw_sp_router_fib4_add_info *info = data; struct mlxsw_sp_fib_entry *fib_entry = info->fib_entry; struct mlxsw_sp *mlxsw_sp = info->mlxsw_sp; + struct mlxsw_sp_vr *vr = fib_entry->vr; mlxsw_sp_fib_entry_destroy(fib_entry); - mlxsw_sp_vr_put(mlxsw_sp, fib_entry->vr); + mlxsw_sp_vr_put(mlxsw_sp, vr); kfree(info); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index a1ad5e6bdfa8..d1b59cdfacc1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -450,6 +450,8 @@ void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *f) kfree(f); + mlxsw_sp_fid_map(mlxsw_sp, fid, false); + mlxsw_sp_fid_op(mlxsw_sp, fid, false); } @@ -997,13 +999,13 @@ static int mlxsw_sp_port_obj_add(struct net_device *dev, } static int __mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port, - u16 vid_begin, u16 vid_end, bool init) + u16 vid_begin, u16 vid_end) { struct net_device *dev = mlxsw_sp_port->dev; u16 vid, pvid; int err; - if (!init && !mlxsw_sp_port->bridged) + if (!mlxsw_sp_port->bridged) return -EINVAL; err = __mlxsw_sp_port_vlans_set(mlxsw_sp_port, vid_begin, vid_end, @@ -1014,9 +1016,6 @@ static int __mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port, return err; } - if (init) - goto out; - pvid = mlxsw_sp_port->pvid; if (pvid >= vid_begin && pvid <= vid_end) { err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, 0); @@ -1028,7 +1027,6 @@ static int __mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_port_fid_leave(mlxsw_sp_port, vid_begin, vid_end); -out: /* Changing activity bits only if HW operation succeded */ for (vid = vid_begin; vid <= vid_end; vid++) clear_bit(vid, mlxsw_sp_port->active_vlans); @@ -1039,8 +1037,8 @@ out: static int mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port, const struct switchdev_obj_port_vlan *vlan) { - return __mlxsw_sp_port_vlans_del(mlxsw_sp_port, - vlan->vid_begin, vlan->vid_end, false); + return __mlxsw_sp_port_vlans_del(mlxsw_sp_port, vlan->vid_begin, + vlan->vid_end); } void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port) @@ -1048,7 +1046,7 @@ void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port) u16 vid; for_each_set_bit(vid, mlxsw_sp_port->active_vlans, VLAN_N_VID) - __mlxsw_sp_port_vlans_del(mlxsw_sp_port, vid, vid, false); + __mlxsw_sp_port_vlans_del(mlxsw_sp_port, vid, vid); } static int @@ -1546,32 +1544,6 @@ void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp) mlxsw_sp_fdb_fini(mlxsw_sp); } -int mlxsw_sp_port_vlan_init(struct mlxsw_sp_port *mlxsw_sp_port) -{ - struct net_device *dev = mlxsw_sp_port->dev; - int err; - - /* Allow only untagged packets to ingress and tag them internally - * with VID 1. - */ - mlxsw_sp_port->pvid = 1; - err = __mlxsw_sp_port_vlans_del(mlxsw_sp_port, 0, VLAN_N_VID - 1, - true); - if (err) { - netdev_err(dev, "Unable to init VLANs\n"); - return err; - } - - /* Add implicit VLAN interface in the device, so that untagged - * packets will be classified to the default vFID. - */ - err = mlxsw_sp_port_add_vid(dev, 0, 1); - if (err) - netdev_err(dev, "Failed to configure default vFID\n"); - - return err; -} - void mlxsw_sp_port_switchdev_init(struct mlxsw_sp_port *mlxsw_sp_port) { mlxsw_sp_port->dev->switchdev_ops = &mlxsw_sp_port_switchdev_ops; diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index 470d7696e9fe..ed8e30186400 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -56,6 +56,10 @@ enum { MLXSW_TRAP_ID_IGMP_V3_REPORT = 0x34, MLXSW_TRAP_ID_ARPBC = 0x50, MLXSW_TRAP_ID_ARPUC = 0x51, + MLXSW_TRAP_ID_MTUERROR = 0x52, + MLXSW_TRAP_ID_TTLERROR = 0x53, + MLXSW_TRAP_ID_LBERROR = 0x54, + MLXSW_TRAP_ID_OSPF = 0x55, MLXSW_TRAP_ID_IP2ME = 0x5F, MLXSW_TRAP_ID_RTR_INGRESS0 = 0x70, MLXSW_TRAP_ID_HOST_MISS_IPV4 = 0x90, diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index d0dc28f93c0e..226cb08cc055 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -52,40 +52,94 @@ static bool qed_dcbx_app_ethtype(u32 app_info_bitmap) DCBX_APP_SF_ETHTYPE); } +static bool qed_dcbx_ieee_app_ethtype(u32 app_info_bitmap) +{ + u8 mfw_val = QED_MFW_GET_FIELD(app_info_bitmap, DCBX_APP_SF_IEEE); + + /* Old MFW */ + if (mfw_val == DCBX_APP_SF_IEEE_RESERVED) + return qed_dcbx_app_ethtype(app_info_bitmap); + + return !!(mfw_val == DCBX_APP_SF_IEEE_ETHTYPE); +} + static bool qed_dcbx_app_port(u32 app_info_bitmap) { return !!(QED_MFW_GET_FIELD(app_info_bitmap, DCBX_APP_SF) == DCBX_APP_SF_PORT); } -static bool qed_dcbx_default_tlv(u32 app_info_bitmap, u16 proto_id) +static bool qed_dcbx_ieee_app_port(u32 app_info_bitmap, u8 type) { - return !!(qed_dcbx_app_ethtype(app_info_bitmap) && - proto_id == QED_ETH_TYPE_DEFAULT); + u8 mfw_val = QED_MFW_GET_FIELD(app_info_bitmap, DCBX_APP_SF_IEEE); + + /* Old MFW */ + if (mfw_val == DCBX_APP_SF_IEEE_RESERVED) + return qed_dcbx_app_port(app_info_bitmap); + + return !!(mfw_val == type || mfw_val == DCBX_APP_SF_IEEE_TCP_UDP_PORT); } -static bool qed_dcbx_iscsi_tlv(u32 app_info_bitmap, u16 proto_id) +static bool qed_dcbx_default_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee) { - return !!(qed_dcbx_app_port(app_info_bitmap) && - proto_id == QED_TCP_PORT_ISCSI); + bool ethtype; + + if (ieee) + ethtype = qed_dcbx_ieee_app_ethtype(app_info_bitmap); + else + ethtype = qed_dcbx_app_ethtype(app_info_bitmap); + + return !!(ethtype && (proto_id == QED_ETH_TYPE_DEFAULT)); } -static bool qed_dcbx_fcoe_tlv(u32 app_info_bitmap, u16 proto_id) +static bool qed_dcbx_iscsi_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee) { - return !!(qed_dcbx_app_ethtype(app_info_bitmap) && - proto_id == QED_ETH_TYPE_FCOE); + bool port; + + if (ieee) + port = qed_dcbx_ieee_app_port(app_info_bitmap, + DCBX_APP_SF_IEEE_TCP_PORT); + else + port = qed_dcbx_app_port(app_info_bitmap); + + return !!(port && (proto_id == QED_TCP_PORT_ISCSI)); } -static bool qed_dcbx_roce_tlv(u32 app_info_bitmap, u16 proto_id) +static bool qed_dcbx_fcoe_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee) { - return !!(qed_dcbx_app_ethtype(app_info_bitmap) && - proto_id == QED_ETH_TYPE_ROCE); + bool ethtype; + + if (ieee) + ethtype = qed_dcbx_ieee_app_ethtype(app_info_bitmap); + else + ethtype = qed_dcbx_app_ethtype(app_info_bitmap); + + return !!(ethtype && (proto_id == QED_ETH_TYPE_FCOE)); } -static bool qed_dcbx_roce_v2_tlv(u32 app_info_bitmap, u16 proto_id) +static bool qed_dcbx_roce_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee) { - return !!(qed_dcbx_app_port(app_info_bitmap) && - proto_id == QED_UDP_PORT_TYPE_ROCE_V2); + bool ethtype; + + if (ieee) + ethtype = qed_dcbx_ieee_app_ethtype(app_info_bitmap); + else + ethtype = qed_dcbx_app_ethtype(app_info_bitmap); + + return !!(ethtype && (proto_id == QED_ETH_TYPE_ROCE)); +} + +static bool qed_dcbx_roce_v2_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee) +{ + bool port; + + if (ieee) + port = qed_dcbx_ieee_app_port(app_info_bitmap, + DCBX_APP_SF_IEEE_UDP_PORT); + else + port = qed_dcbx_app_port(app_info_bitmap); + + return !!(port && (proto_id == QED_UDP_PORT_TYPE_ROCE_V2)); } static void @@ -164,17 +218,17 @@ qed_dcbx_update_app_info(struct qed_dcbx_results *p_data, static bool qed_dcbx_get_app_protocol_type(struct qed_hwfn *p_hwfn, u32 app_prio_bitmap, - u16 id, enum dcbx_protocol_type *type) + u16 id, enum dcbx_protocol_type *type, bool ieee) { - if (qed_dcbx_fcoe_tlv(app_prio_bitmap, id)) { + if (qed_dcbx_fcoe_tlv(app_prio_bitmap, id, ieee)) { *type = DCBX_PROTOCOL_FCOE; - } else if (qed_dcbx_roce_tlv(app_prio_bitmap, id)) { + } else if (qed_dcbx_roce_tlv(app_prio_bitmap, id, ieee)) { *type = DCBX_PROTOCOL_ROCE; - } else if (qed_dcbx_iscsi_tlv(app_prio_bitmap, id)) { + } else if (qed_dcbx_iscsi_tlv(app_prio_bitmap, id, ieee)) { *type = DCBX_PROTOCOL_ISCSI; - } else if (qed_dcbx_default_tlv(app_prio_bitmap, id)) { + } else if (qed_dcbx_default_tlv(app_prio_bitmap, id, ieee)) { *type = DCBX_PROTOCOL_ETH; - } else if (qed_dcbx_roce_v2_tlv(app_prio_bitmap, id)) { + } else if (qed_dcbx_roce_v2_tlv(app_prio_bitmap, id, ieee)) { *type = DCBX_PROTOCOL_ROCE_V2; } else { *type = DCBX_MAX_PROTOCOL_TYPE; @@ -194,17 +248,18 @@ static int qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn, struct qed_dcbx_results *p_data, struct dcbx_app_priority_entry *p_tbl, - u32 pri_tc_tbl, int count, bool dcbx_enabled) + u32 pri_tc_tbl, int count, u8 dcbx_version) { u8 tc, priority_map; enum dcbx_protocol_type type; + bool enable, ieee; u16 protocol_id; int priority; - bool enable; int i; DP_VERBOSE(p_hwfn, QED_MSG_DCB, "Num APP entries = %d\n", count); + ieee = (dcbx_version == DCBX_CONFIG_VERSION_IEEE); /* Parse APP TLV */ for (i = 0; i < count; i++) { protocol_id = QED_MFW_GET_FIELD(p_tbl[i].entry, @@ -219,7 +274,7 @@ qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn, tc = QED_DCBX_PRIO2TC(pri_tc_tbl, priority); if (qed_dcbx_get_app_protocol_type(p_hwfn, p_tbl[i].entry, - protocol_id, &type)) { + protocol_id, &type, ieee)) { /* ETH always have the enable bit reset, as it gets * vlan information per packet. For other protocols, * should be set according to the dcbx_enabled @@ -275,15 +330,12 @@ static int qed_dcbx_process_mib_info(struct qed_hwfn *p_hwfn) struct dcbx_ets_feature *p_ets; struct qed_hw_info *p_info; u32 pri_tc_tbl, flags; - bool dcbx_enabled; + u8 dcbx_version; int num_entries; int rc = 0; - /* If DCBx version is non zero, then negotiation was - * successfuly performed - */ flags = p_hwfn->p_dcbx_info->operational.flags; - dcbx_enabled = !!QED_MFW_GET_FIELD(flags, DCBX_CONFIG_VERSION); + dcbx_version = QED_MFW_GET_FIELD(flags, DCBX_CONFIG_VERSION); p_app = &p_hwfn->p_dcbx_info->operational.features.app; p_tbl = p_app->app_pri_tbl; @@ -295,13 +347,13 @@ static int qed_dcbx_process_mib_info(struct qed_hwfn *p_hwfn) num_entries = QED_MFW_GET_FIELD(p_app->flags, DCBX_APP_NUM_ENTRIES); rc = qed_dcbx_process_tlv(p_hwfn, &data, p_tbl, pri_tc_tbl, - num_entries, dcbx_enabled); + num_entries, dcbx_version); if (rc) return rc; p_info->num_tc = QED_MFW_GET_FIELD(p_ets->flags, DCBX_ETS_MAX_TCS); data.pf_id = p_hwfn->rel_pf_id; - data.dcbx_enabled = dcbx_enabled; + data.dcbx_enabled = !!dcbx_version; qed_dcbx_dp_protocol(p_hwfn, &data); @@ -400,7 +452,7 @@ static void qed_dcbx_get_app_data(struct qed_hwfn *p_hwfn, struct dcbx_app_priority_feature *p_app, struct dcbx_app_priority_entry *p_tbl, - struct qed_dcbx_params *p_params) + struct qed_dcbx_params *p_params, bool ieee) { struct qed_app_entry *entry; u8 pri_map; @@ -414,15 +466,46 @@ qed_dcbx_get_app_data(struct qed_hwfn *p_hwfn, DCBX_APP_NUM_ENTRIES); for (i = 0; i < DCBX_MAX_APP_PROTOCOL; i++) { entry = &p_params->app_entry[i]; - entry->ethtype = !(QED_MFW_GET_FIELD(p_tbl[i].entry, - DCBX_APP_SF)); + if (ieee) { + u8 sf_ieee; + u32 val; + + sf_ieee = QED_MFW_GET_FIELD(p_tbl[i].entry, + DCBX_APP_SF_IEEE); + switch (sf_ieee) { + case DCBX_APP_SF_IEEE_RESERVED: + /* Old MFW */ + val = QED_MFW_GET_FIELD(p_tbl[i].entry, + DCBX_APP_SF); + entry->sf_ieee = val ? + QED_DCBX_SF_IEEE_TCP_UDP_PORT : + QED_DCBX_SF_IEEE_ETHTYPE; + break; + case DCBX_APP_SF_IEEE_ETHTYPE: + entry->sf_ieee = QED_DCBX_SF_IEEE_ETHTYPE; + break; + case DCBX_APP_SF_IEEE_TCP_PORT: + entry->sf_ieee = QED_DCBX_SF_IEEE_TCP_PORT; + break; + case DCBX_APP_SF_IEEE_UDP_PORT: + entry->sf_ieee = QED_DCBX_SF_IEEE_UDP_PORT; + break; + case DCBX_APP_SF_IEEE_TCP_UDP_PORT: + entry->sf_ieee = QED_DCBX_SF_IEEE_TCP_UDP_PORT; + break; + } + } else { + entry->ethtype = !(QED_MFW_GET_FIELD(p_tbl[i].entry, + DCBX_APP_SF)); + } + pri_map = QED_MFW_GET_FIELD(p_tbl[i].entry, DCBX_APP_PRI_MAP); entry->prio = ffs(pri_map) - 1; entry->proto_id = QED_MFW_GET_FIELD(p_tbl[i].entry, DCBX_APP_PROTOCOL_ID); qed_dcbx_get_app_protocol_type(p_hwfn, p_tbl[i].entry, entry->proto_id, - &entry->proto_type); + &entry->proto_type, ieee); } DP_VERBOSE(p_hwfn, QED_MSG_DCB, @@ -483,7 +566,7 @@ qed_dcbx_get_ets_data(struct qed_hwfn *p_hwfn, bw_map[1] = be32_to_cpu(p_ets->tc_bw_tbl[1]); tsa_map[0] = be32_to_cpu(p_ets->tc_tsa_tbl[0]); tsa_map[1] = be32_to_cpu(p_ets->tc_tsa_tbl[1]); - pri_map = be32_to_cpu(p_ets->pri_tc_tbl[0]); + pri_map = p_ets->pri_tc_tbl[0]; for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++) { p_params->ets_tc_bw_tbl[i] = ((u8 *)bw_map)[i]; p_params->ets_tc_tsa_tbl[i] = ((u8 *)tsa_map)[i]; @@ -500,9 +583,9 @@ qed_dcbx_get_common_params(struct qed_hwfn *p_hwfn, struct dcbx_app_priority_feature *p_app, struct dcbx_app_priority_entry *p_tbl, struct dcbx_ets_feature *p_ets, - u32 pfc, struct qed_dcbx_params *p_params) + u32 pfc, struct qed_dcbx_params *p_params, bool ieee) { - qed_dcbx_get_app_data(p_hwfn, p_app, p_tbl, p_params); + qed_dcbx_get_app_data(p_hwfn, p_app, p_tbl, p_params, ieee); qed_dcbx_get_ets_data(p_hwfn, p_ets, p_params); qed_dcbx_get_pfc_data(p_hwfn, pfc, p_params); } @@ -516,7 +599,7 @@ qed_dcbx_get_local_params(struct qed_hwfn *p_hwfn, p_feat = &p_hwfn->p_dcbx_info->local_admin.features; qed_dcbx_get_common_params(p_hwfn, &p_feat->app, p_feat->app.app_pri_tbl, &p_feat->ets, - p_feat->pfc, ¶ms->local.params); + p_feat->pfc, ¶ms->local.params, false); params->local.valid = true; } @@ -529,7 +612,7 @@ qed_dcbx_get_remote_params(struct qed_hwfn *p_hwfn, p_feat = &p_hwfn->p_dcbx_info->remote.features; qed_dcbx_get_common_params(p_hwfn, &p_feat->app, p_feat->app.app_pri_tbl, &p_feat->ets, - p_feat->pfc, ¶ms->remote.params); + p_feat->pfc, ¶ms->remote.params, false); params->remote.valid = true; } @@ -574,7 +657,8 @@ qed_dcbx_get_operational_params(struct qed_hwfn *p_hwfn, qed_dcbx_get_common_params(p_hwfn, &p_feat->app, p_feat->app.app_pri_tbl, &p_feat->ets, - p_feat->pfc, ¶ms->operational.params); + p_feat->pfc, ¶ms->operational.params, + p_operational->ieee); qed_dcbx_get_priority_info(p_hwfn, &p_operational->app_prio, p_results); err = QED_MFW_GET_FIELD(p_feat->app.flags, DCBX_APP_ERROR); p_operational->err = err; @@ -944,7 +1028,6 @@ qed_dcbx_set_ets_data(struct qed_hwfn *p_hwfn, val = (((u32)p_params->ets_pri_tc_tbl[i]) << ((7 - i) * 4)); p_ets->pri_tc_tbl[0] |= val; } - p_ets->pri_tc_tbl[0] = cpu_to_be32(p_ets->pri_tc_tbl[0]); for (i = 0; i < 2; i++) { p_ets->tc_bw_tbl[i] = cpu_to_be32(p_ets->tc_bw_tbl[i]); p_ets->tc_tsa_tbl[i] = cpu_to_be32(p_ets->tc_tsa_tbl[i]); @@ -954,7 +1037,7 @@ qed_dcbx_set_ets_data(struct qed_hwfn *p_hwfn, static void qed_dcbx_set_app_data(struct qed_hwfn *p_hwfn, struct dcbx_app_priority_feature *p_app, - struct qed_dcbx_params *p_params) + struct qed_dcbx_params *p_params, bool ieee) { u32 *entry; int i; @@ -975,12 +1058,36 @@ qed_dcbx_set_app_data(struct qed_hwfn *p_hwfn, for (i = 0; i < DCBX_MAX_APP_PROTOCOL; i++) { entry = &p_app->app_pri_tbl[i].entry; - *entry &= ~DCBX_APP_SF_MASK; - if (p_params->app_entry[i].ethtype) - *entry |= ((u32)DCBX_APP_SF_ETHTYPE << - DCBX_APP_SF_SHIFT); - else - *entry |= ((u32)DCBX_APP_SF_PORT << DCBX_APP_SF_SHIFT); + if (ieee) { + *entry &= ~DCBX_APP_SF_IEEE_MASK; + switch (p_params->app_entry[i].sf_ieee) { + case QED_DCBX_SF_IEEE_ETHTYPE: + *entry |= ((u32)DCBX_APP_SF_IEEE_ETHTYPE << + DCBX_APP_SF_IEEE_SHIFT); + break; + case QED_DCBX_SF_IEEE_TCP_PORT: + *entry |= ((u32)DCBX_APP_SF_IEEE_TCP_PORT << + DCBX_APP_SF_IEEE_SHIFT); + break; + case QED_DCBX_SF_IEEE_UDP_PORT: + *entry |= ((u32)DCBX_APP_SF_IEEE_UDP_PORT << + DCBX_APP_SF_IEEE_SHIFT); + break; + case QED_DCBX_SF_IEEE_TCP_UDP_PORT: + *entry |= ((u32)DCBX_APP_SF_IEEE_TCP_UDP_PORT << + DCBX_APP_SF_IEEE_SHIFT); + break; + } + } else { + *entry &= ~DCBX_APP_SF_MASK; + if (p_params->app_entry[i].ethtype) + *entry |= ((u32)DCBX_APP_SF_ETHTYPE << + DCBX_APP_SF_SHIFT); + else + *entry |= ((u32)DCBX_APP_SF_PORT << + DCBX_APP_SF_SHIFT); + } + *entry &= ~DCBX_APP_PROTOCOL_ID_MASK; *entry |= ((u32)p_params->app_entry[i].proto_id << DCBX_APP_PROTOCOL_ID_SHIFT); @@ -995,15 +1102,19 @@ qed_dcbx_set_local_params(struct qed_hwfn *p_hwfn, struct dcbx_local_params *local_admin, struct qed_dcbx_set *params) { + bool ieee = false; + local_admin->flags = 0; memcpy(&local_admin->features, &p_hwfn->p_dcbx_info->operational.features, sizeof(local_admin->features)); - if (params->enabled) + if (params->enabled) { local_admin->config = params->ver_num; - else + ieee = !!(params->ver_num & DCBX_CONFIG_VERSION_IEEE); + } else { local_admin->config = DCBX_CONFIG_VERSION_DISABLED; + } if (params->override_flags & QED_DCBX_OVERRIDE_PFC_CFG) qed_dcbx_set_pfc_data(p_hwfn, &local_admin->features.pfc, @@ -1015,7 +1126,7 @@ qed_dcbx_set_local_params(struct qed_hwfn *p_hwfn, if (params->override_flags & QED_DCBX_OVERRIDE_APP_CFG) qed_dcbx_set_app_data(p_hwfn, &local_admin->features.app, - ¶ms->config.params); + ¶ms->config.params, ieee); } int qed_dcbx_config_params(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -1596,8 +1707,10 @@ static int qed_dcbnl_setapp(struct qed_dev *cdev, if ((entry->ethtype == ethtype) && (entry->proto_id == idval)) break; /* First empty slot */ - if (!entry->proto_id) + if (!entry->proto_id) { + dcbx_set.config.params.num_app_entries++; break; + } } if (i == QED_DCBX_MAX_APP_PROTOCOL) { @@ -2117,8 +2230,10 @@ int qed_dcbnl_ieee_setapp(struct qed_dev *cdev, struct dcb_app *app) (entry->proto_id == app->protocol)) break; /* First empty slot */ - if (!entry->proto_id) + if (!entry->proto_id) { + dcbx_set.config.params.num_app_entries++; break; + } } if (i == QED_DCBX_MAX_APP_PROTOCOL) { diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 592784019994..6f9d3b831a2a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -6850,6 +6850,14 @@ struct dcbx_app_priority_entry { #define DCBX_APP_SF_SHIFT 8 #define DCBX_APP_SF_ETHTYPE 0 #define DCBX_APP_SF_PORT 1 +#define DCBX_APP_SF_IEEE_MASK 0x0000f000 +#define DCBX_APP_SF_IEEE_SHIFT 12 +#define DCBX_APP_SF_IEEE_RESERVED 0 +#define DCBX_APP_SF_IEEE_ETHTYPE 1 +#define DCBX_APP_SF_IEEE_TCP_PORT 2 +#define DCBX_APP_SF_IEEE_UDP_PORT 3 +#define DCBX_APP_SF_IEEE_TCP_UDP_PORT 4 + #define DCBX_APP_PROTOCOL_ID_MASK 0xffff0000 #define DCBX_APP_PROTOCOL_ID_SHIFT 16 }; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index fd973f4f16c7..49bad00a0f8f 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -37,8 +37,8 @@ #define _QLCNIC_LINUX_MAJOR 5 #define _QLCNIC_LINUX_MINOR 3 -#define _QLCNIC_LINUX_SUBVERSION 64 -#define QLCNIC_LINUX_VERSIONID "5.3.64" +#define _QLCNIC_LINUX_SUBVERSION 65 +#define QLCNIC_LINUX_VERSIONID "5.3.65" #define QLCNIC_DRV_IDC_VER 0x01 #define QLCNIC_DRIVER_VERSION ((_QLCNIC_LINUX_MAJOR << 16) |\ (_QLCNIC_LINUX_MINOR << 8) | (_QLCNIC_LINUX_SUBVERSION)) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 87c642d3b075..fedd7366713c 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -102,7 +102,6 @@ #define QLCNIC_RESPONSE_DESC 0x05 #define QLCNIC_LRO_DESC 0x12 -#define QLCNIC_TX_POLL_BUDGET 128 #define QLCNIC_TCP_HDR_SIZE 20 #define QLCNIC_TCP_TS_OPTION_SIZE 12 #define QLCNIC_FETCH_RING_ID(handle) ((handle) >> 63) @@ -2008,7 +2007,6 @@ static int qlcnic_83xx_msix_tx_poll(struct napi_struct *napi, int budget) struct qlcnic_host_tx_ring *tx_ring; struct qlcnic_adapter *adapter; - budget = QLCNIC_TX_POLL_BUDGET; tx_ring = container_of(napi, struct qlcnic_host_tx_ring, napi); adapter = tx_ring->adapter; work_done = qlcnic_process_cmd_ring(adapter, tx_ring, budget); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h index 017d8c2c8285..24061b9b92e8 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h @@ -156,10 +156,8 @@ struct qlcnic_vf_info { spinlock_t vlan_list_lock; /* Lock for VLAN list */ }; -struct qlcnic_async_work_list { +struct qlcnic_async_cmd { struct list_head list; - struct work_struct work; - void *ptr; struct qlcnic_cmd_args *cmd; }; @@ -168,7 +166,10 @@ struct qlcnic_back_channel { struct workqueue_struct *bc_trans_wq; struct workqueue_struct *bc_async_wq; struct workqueue_struct *bc_flr_wq; - struct list_head async_list; + struct qlcnic_adapter *adapter; + struct list_head async_cmd_list; + struct work_struct vf_async_work; + spinlock_t queue_lock; /* async_cmd_list queue lock */ }; struct qlcnic_sriov { diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c index 7327b729ba2e..d7107055ec60 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c @@ -29,6 +29,7 @@ #define QLC_83XX_VF_RESET_FAIL_THRESH 8 #define QLC_BC_CMD_MAX_RETRY_CNT 5 +static void qlcnic_sriov_handle_async_issue_cmd(struct work_struct *work); static void qlcnic_sriov_vf_free_mac_list(struct qlcnic_adapter *); static int qlcnic_sriov_alloc_bc_mbx_args(struct qlcnic_cmd_args *, u32); static void qlcnic_sriov_vf_poll_dev_state(struct work_struct *); @@ -177,7 +178,10 @@ int qlcnic_sriov_init(struct qlcnic_adapter *adapter, int num_vfs) } bc->bc_async_wq = wq; - INIT_LIST_HEAD(&bc->async_list); + INIT_LIST_HEAD(&bc->async_cmd_list); + INIT_WORK(&bc->vf_async_work, qlcnic_sriov_handle_async_issue_cmd); + spin_lock_init(&bc->queue_lock); + bc->adapter = adapter; for (i = 0; i < num_vfs; i++) { vf = &sriov->vf_info[i]; @@ -1517,17 +1521,21 @@ static void qlcnic_vf_add_mc_list(struct net_device *netdev, const u8 *mac, void qlcnic_sriov_cleanup_async_list(struct qlcnic_back_channel *bc) { - struct list_head *head = &bc->async_list; - struct qlcnic_async_work_list *entry; + struct list_head *head = &bc->async_cmd_list; + struct qlcnic_async_cmd *entry; flush_workqueue(bc->bc_async_wq); + cancel_work_sync(&bc->vf_async_work); + + spin_lock(&bc->queue_lock); while (!list_empty(head)) { - entry = list_entry(head->next, struct qlcnic_async_work_list, + entry = list_entry(head->next, struct qlcnic_async_cmd, list); - cancel_work_sync(&entry->work); list_del(&entry->list); + kfree(entry->cmd); kfree(entry); } + spin_unlock(&bc->queue_lock); } void qlcnic_sriov_vf_set_multi(struct net_device *netdev) @@ -1587,57 +1595,64 @@ void qlcnic_sriov_vf_set_multi(struct net_device *netdev) static void qlcnic_sriov_handle_async_issue_cmd(struct work_struct *work) { - struct qlcnic_async_work_list *entry; - struct qlcnic_adapter *adapter; + struct qlcnic_async_cmd *entry, *tmp; + struct qlcnic_back_channel *bc; struct qlcnic_cmd_args *cmd; + struct list_head *head; + LIST_HEAD(del_list); + + bc = container_of(work, struct qlcnic_back_channel, vf_async_work); + head = &bc->async_cmd_list; + + spin_lock(&bc->queue_lock); + list_splice_init(head, &del_list); + spin_unlock(&bc->queue_lock); + + list_for_each_entry_safe(entry, tmp, &del_list, list) { + list_del(&entry->list); + cmd = entry->cmd; + __qlcnic_sriov_issue_cmd(bc->adapter, cmd); + kfree(entry); + } + + if (!list_empty(head)) + queue_work(bc->bc_async_wq, &bc->vf_async_work); - entry = container_of(work, struct qlcnic_async_work_list, work); - adapter = entry->ptr; - cmd = entry->cmd; - __qlcnic_sriov_issue_cmd(adapter, cmd); return; } -static struct qlcnic_async_work_list * -qlcnic_sriov_get_free_node_async_work(struct qlcnic_back_channel *bc) +static struct qlcnic_async_cmd * +qlcnic_sriov_alloc_async_cmd(struct qlcnic_back_channel *bc, + struct qlcnic_cmd_args *cmd) { - struct list_head *node; - struct qlcnic_async_work_list *entry = NULL; - u8 empty = 0; + struct qlcnic_async_cmd *entry = NULL; - list_for_each(node, &bc->async_list) { - entry = list_entry(node, struct qlcnic_async_work_list, list); - if (!work_pending(&entry->work)) { - empty = 1; - break; - } - } + entry = kzalloc(sizeof(*entry), GFP_ATOMIC); + if (!entry) + return NULL; - if (!empty) { - entry = kzalloc(sizeof(struct qlcnic_async_work_list), - GFP_ATOMIC); - if (entry == NULL) - return NULL; - list_add_tail(&entry->list, &bc->async_list); - } + entry->cmd = cmd; + + spin_lock(&bc->queue_lock); + list_add_tail(&entry->list, &bc->async_cmd_list); + spin_unlock(&bc->queue_lock); return entry; } static void qlcnic_sriov_schedule_async_cmd(struct qlcnic_back_channel *bc, - work_func_t func, void *data, struct qlcnic_cmd_args *cmd) { - struct qlcnic_async_work_list *entry = NULL; + struct qlcnic_async_cmd *entry = NULL; - entry = qlcnic_sriov_get_free_node_async_work(bc); - if (!entry) + entry = qlcnic_sriov_alloc_async_cmd(bc, cmd); + if (!entry) { + qlcnic_free_mbx_args(cmd); + kfree(cmd); return; + } - entry->ptr = data; - entry->cmd = cmd; - INIT_WORK(&entry->work, func); - queue_work(bc->bc_async_wq, &entry->work); + queue_work(bc->bc_async_wq, &bc->vf_async_work); } static int qlcnic_sriov_async_issue_cmd(struct qlcnic_adapter *adapter, @@ -1649,8 +1664,8 @@ static int qlcnic_sriov_async_issue_cmd(struct qlcnic_adapter *adapter, if (adapter->need_fw_reset) return -EIO; - qlcnic_sriov_schedule_async_cmd(bc, qlcnic_sriov_handle_async_issue_cmd, - adapter, cmd); + qlcnic_sriov_schedule_async_cmd(bc, cmd); + return 0; } diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index c51f34693eae..f85d605e4560 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -734,6 +734,7 @@ static void cpsw_rx_handler(void *token, int len, int status) netif_receive_skb(skb); ndev->stats.rx_bytes += len; ndev->stats.rx_packets++; + kmemleak_not_leak(new_skb); } else { ndev->stats.rx_dropped++; new_skb = skb; @@ -1325,6 +1326,7 @@ static int cpsw_ndo_open(struct net_device *ndev) kfree_skb(skb); goto err_cleanup; } + kmemleak_not_leak(skb); } /* continue even if we didn't manage to submit all * receive descs diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c index 01a77145a0fa..8fd131207ee1 100644 --- a/drivers/net/ethernet/tundra/tsi108_eth.c +++ b/drivers/net/ethernet/tundra/tsi108_eth.c @@ -166,6 +166,7 @@ static struct platform_driver tsi_eth_driver = { static void tsi108_timed_checker(unsigned long dev_ptr); +#ifdef DEBUG static void dump_eth_one(struct net_device *dev) { struct tsi108_prv_data *data = netdev_priv(dev); @@ -190,6 +191,7 @@ static void dump_eth_one(struct net_device *dev) TSI_READ(TSI108_EC_RXESTAT), TSI_READ(TSI108_EC_RXERR), data->rxpending); } +#endif /* Synchronization is needed between the thread and up/down events. * Note that the PHY is accessed through the same registers for both diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 467fb8b4d083..591af71eae56 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -644,12 +644,6 @@ struct netvsc_reconfig { u32 event; }; -struct garp_wrk { - struct work_struct dwrk; - struct net_device *netdev; - struct netvsc_device *netvsc_dev; -}; - /* The context of the netvsc device */ struct net_device_context { /* point back to our device context */ @@ -667,7 +661,6 @@ struct net_device_context { struct work_struct work; u32 msg_enable; /* debug level */ - struct garp_wrk gwrk; struct netvsc_stats __percpu *tx_stats; struct netvsc_stats __percpu *rx_stats; @@ -678,6 +671,15 @@ struct net_device_context { /* the device is going away */ bool start_remove; + + /* State to manage the associated VF interface. */ + struct net_device *vf_netdev; + bool vf_inject; + atomic_t vf_use_cnt; + /* 1: allocated, serial number is valid. 0: not allocated */ + u32 vf_alloc; + /* Serial number of the VF to team with */ + u32 vf_serial; }; /* Per netvsc device */ @@ -733,15 +735,7 @@ struct netvsc_device { u32 max_pkt; /* max number of pkt in one send, e.g. 8 */ u32 pkt_align; /* alignment bytes, e.g. 8 */ - /* 1: allocated, serial number is valid. 0: not allocated */ - u32 vf_alloc; - /* Serial number of the VF to team with */ - u32 vf_serial; atomic_t open_cnt; - /* State to manage the associated VF interface. */ - bool vf_inject; - struct net_device *vf_netdev; - atomic_t vf_use_cnt; }; static inline struct netvsc_device * diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 20e09174ff62..410fb8e81376 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -77,13 +77,9 @@ static struct netvsc_device *alloc_net_device(void) init_waitqueue_head(&net_device->wait_drain); net_device->destroy = false; atomic_set(&net_device->open_cnt, 0); - atomic_set(&net_device->vf_use_cnt, 0); net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT; net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT; - net_device->vf_netdev = NULL; - net_device->vf_inject = false; - return net_device; } @@ -1106,16 +1102,16 @@ static void netvsc_send_table(struct hv_device *hdev, nvscdev->send_table[i] = tab[i]; } -static void netvsc_send_vf(struct netvsc_device *nvdev, +static void netvsc_send_vf(struct net_device_context *net_device_ctx, struct nvsp_message *nvmsg) { - nvdev->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated; - nvdev->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial; + net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated; + net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial; } static inline void netvsc_receive_inband(struct hv_device *hdev, - struct netvsc_device *nvdev, - struct nvsp_message *nvmsg) + struct net_device_context *net_device_ctx, + struct nvsp_message *nvmsg) { switch (nvmsg->hdr.msg_type) { case NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE: @@ -1123,7 +1119,7 @@ static inline void netvsc_receive_inband(struct hv_device *hdev, break; case NVSP_MSG4_TYPE_SEND_VF_ASSOCIATION: - netvsc_send_vf(nvdev, nvmsg); + netvsc_send_vf(net_device_ctx, nvmsg); break; } } @@ -1136,6 +1132,7 @@ static void netvsc_process_raw_pkt(struct hv_device *device, struct vmpacket_descriptor *desc) { struct nvsp_message *nvmsg; + struct net_device_context *net_device_ctx = netdev_priv(ndev); nvmsg = (struct nvsp_message *)((unsigned long) desc + (desc->offset8 << 3)); @@ -1150,7 +1147,7 @@ static void netvsc_process_raw_pkt(struct hv_device *device, break; case VM_PKT_DATA_INBAND: - netvsc_receive_inband(device, net_device, nvmsg); + netvsc_receive_inband(device, net_device_ctx, nvmsg); break; default: diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 41bd952cc28d..3ba29fc80d05 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -658,20 +658,19 @@ int netvsc_recv_callback(struct hv_device *device_obj, struct sk_buff *skb; struct sk_buff *vf_skb; struct netvsc_stats *rx_stats; - struct netvsc_device *netvsc_dev = net_device_ctx->nvdev; u32 bytes_recvd = packet->total_data_buflen; int ret = 0; if (!net || net->reg_state != NETREG_REGISTERED) return NVSP_STAT_FAIL; - if (READ_ONCE(netvsc_dev->vf_inject)) { - atomic_inc(&netvsc_dev->vf_use_cnt); - if (!READ_ONCE(netvsc_dev->vf_inject)) { + if (READ_ONCE(net_device_ctx->vf_inject)) { + atomic_inc(&net_device_ctx->vf_use_cnt); + if (!READ_ONCE(net_device_ctx->vf_inject)) { /* * We raced; just move on. */ - atomic_dec(&netvsc_dev->vf_use_cnt); + atomic_dec(&net_device_ctx->vf_use_cnt); goto vf_injection_done; } @@ -683,17 +682,19 @@ int netvsc_recv_callback(struct hv_device *device_obj, * the host). Deliver these via the VF interface * in the guest. */ - vf_skb = netvsc_alloc_recv_skb(netvsc_dev->vf_netdev, packet, - csum_info, *data, vlan_tci); + vf_skb = netvsc_alloc_recv_skb(net_device_ctx->vf_netdev, + packet, csum_info, *data, + vlan_tci); if (vf_skb != NULL) { - ++netvsc_dev->vf_netdev->stats.rx_packets; - netvsc_dev->vf_netdev->stats.rx_bytes += bytes_recvd; + ++net_device_ctx->vf_netdev->stats.rx_packets; + net_device_ctx->vf_netdev->stats.rx_bytes += + bytes_recvd; netif_receive_skb(vf_skb); } else { ++net->stats.rx_dropped; ret = NVSP_STAT_FAIL; } - atomic_dec(&netvsc_dev->vf_use_cnt); + atomic_dec(&net_device_ctx->vf_use_cnt); return ret; } @@ -1150,17 +1151,6 @@ static void netvsc_free_netdev(struct net_device *netdev) free_netdev(netdev); } -static void netvsc_notify_peers(struct work_struct *wrk) -{ - struct garp_wrk *gwrk; - - gwrk = container_of(wrk, struct garp_wrk, dwrk); - - netdev_notify_peers(gwrk->netdev); - - atomic_dec(&gwrk->netvsc_dev->vf_use_cnt); -} - static struct net_device *get_netvsc_net_device(char *mac) { struct net_device *dev, *found = NULL; @@ -1203,7 +1193,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev) net_device_ctx = netdev_priv(ndev); netvsc_dev = net_device_ctx->nvdev; - if (netvsc_dev == NULL) + if (!netvsc_dev || net_device_ctx->vf_netdev) return NOTIFY_DONE; netdev_info(ndev, "VF registering: %s\n", vf_netdev->name); @@ -1211,10 +1201,23 @@ static int netvsc_register_vf(struct net_device *vf_netdev) * Take a reference on the module. */ try_module_get(THIS_MODULE); - netvsc_dev->vf_netdev = vf_netdev; + net_device_ctx->vf_netdev = vf_netdev; return NOTIFY_OK; } +static void netvsc_inject_enable(struct net_device_context *net_device_ctx) +{ + net_device_ctx->vf_inject = true; +} + +static void netvsc_inject_disable(struct net_device_context *net_device_ctx) +{ + net_device_ctx->vf_inject = false; + + /* Wait for currently active users to drain out. */ + while (atomic_read(&net_device_ctx->vf_use_cnt) != 0) + udelay(50); +} static int netvsc_vf_up(struct net_device *vf_netdev) { @@ -1233,11 +1236,11 @@ static int netvsc_vf_up(struct net_device *vf_netdev) net_device_ctx = netdev_priv(ndev); netvsc_dev = net_device_ctx->nvdev; - if ((netvsc_dev == NULL) || (netvsc_dev->vf_netdev == NULL)) + if (!netvsc_dev || !net_device_ctx->vf_netdev) return NOTIFY_DONE; netdev_info(ndev, "VF up: %s\n", vf_netdev->name); - netvsc_dev->vf_inject = true; + netvsc_inject_enable(net_device_ctx); /* * Open the device before switching data path. @@ -1252,15 +1255,8 @@ static int netvsc_vf_up(struct net_device *vf_netdev) netif_carrier_off(ndev); - /* - * Now notify peers. We are scheduling work to - * notify peers; take a reference to prevent - * the VF interface from vanishing. - */ - atomic_inc(&netvsc_dev->vf_use_cnt); - net_device_ctx->gwrk.netdev = vf_netdev; - net_device_ctx->gwrk.netvsc_dev = netvsc_dev; - schedule_work(&net_device_ctx->gwrk.dwrk); + /* Now notify peers through VF device. */ + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, vf_netdev); return NOTIFY_OK; } @@ -1283,29 +1279,18 @@ static int netvsc_vf_down(struct net_device *vf_netdev) net_device_ctx = netdev_priv(ndev); netvsc_dev = net_device_ctx->nvdev; - if ((netvsc_dev == NULL) || (netvsc_dev->vf_netdev == NULL)) + if (!netvsc_dev || !net_device_ctx->vf_netdev) return NOTIFY_DONE; netdev_info(ndev, "VF down: %s\n", vf_netdev->name); - netvsc_dev->vf_inject = false; - /* - * Wait for currently active users to - * drain out. - */ - - while (atomic_read(&netvsc_dev->vf_use_cnt) != 0) - udelay(50); + netvsc_inject_disable(net_device_ctx); netvsc_switch_datapath(ndev, false); netdev_info(ndev, "Data path switched from VF: %s\n", vf_netdev->name); rndis_filter_close(netvsc_dev); netif_carrier_on(ndev); - /* - * Notify peers. - */ - atomic_inc(&netvsc_dev->vf_use_cnt); - net_device_ctx->gwrk.netdev = ndev; - net_device_ctx->gwrk.netvsc_dev = netvsc_dev; - schedule_work(&net_device_ctx->gwrk.dwrk); + + /* Now notify peers through netvsc device. */ + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, ndev); return NOTIFY_OK; } @@ -1327,11 +1312,11 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev) net_device_ctx = netdev_priv(ndev); netvsc_dev = net_device_ctx->nvdev; - if (netvsc_dev == NULL) + if (!netvsc_dev || !net_device_ctx->vf_netdev) return NOTIFY_DONE; netdev_info(ndev, "VF unregistering: %s\n", vf_netdev->name); - - netvsc_dev->vf_netdev = NULL; + netvsc_inject_disable(net_device_ctx); + net_device_ctx->vf_netdev = NULL; module_put(THIS_MODULE); return NOTIFY_OK; } @@ -1377,11 +1362,14 @@ static int netvsc_probe(struct hv_device *dev, INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change); INIT_WORK(&net_device_ctx->work, do_set_multicast); - INIT_WORK(&net_device_ctx->gwrk.dwrk, netvsc_notify_peers); spin_lock_init(&net_device_ctx->lock); INIT_LIST_HEAD(&net_device_ctx->reconfig_events); + atomic_set(&net_device_ctx->vf_use_cnt, 0); + net_device_ctx->vf_netdev = NULL; + net_device_ctx->vf_inject = false; + net->netdev_ops = &device_ops; net->hw_features = NETVSC_HW_FEATURES; @@ -1494,8 +1482,13 @@ static int netvsc_netdev_event(struct notifier_block *this, { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); - /* Avoid Vlan, Bonding dev with same MAC registering as VF */ - if (event_dev->priv_flags & (IFF_802_1Q_VLAN | IFF_BONDING)) + /* Avoid Vlan dev with same MAC registering as VF */ + if (event_dev->priv_flags & IFF_802_1Q_VLAN) + return NOTIFY_DONE; + + /* Avoid Bonding master dev with same MAC registering as VF */ + if (event_dev->priv_flags & IFF_BONDING && + event_dev->flags & IFF_MASTER) return NOTIFY_DONE; switch (event) { diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index d13e6e15d7b5..351e701eb043 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -270,6 +270,7 @@ struct macsec_dev { struct pcpu_secy_stats __percpu *stats; struct list_head secys; struct gro_cells gro_cells; + unsigned int nest_level; }; /** @@ -2699,6 +2700,8 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, #define MACSEC_FEATURES \ (NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST) +static struct lock_class_key macsec_netdev_addr_lock_key; + static int macsec_dev_init(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); @@ -2910,6 +2913,13 @@ static int macsec_get_iflink(const struct net_device *dev) return macsec_priv(dev)->real_dev->ifindex; } + +static int macsec_get_nest_level(struct net_device *dev) +{ + return macsec_priv(dev)->nest_level; +} + + static const struct net_device_ops macsec_netdev_ops = { .ndo_init = macsec_dev_init, .ndo_uninit = macsec_dev_uninit, @@ -2923,6 +2933,7 @@ static const struct net_device_ops macsec_netdev_ops = { .ndo_start_xmit = macsec_start_xmit, .ndo_get_stats64 = macsec_get_stats64, .ndo_get_iflink = macsec_get_iflink, + .ndo_get_lock_subclass = macsec_get_nest_level, }; static const struct device_type macsec_type = { @@ -3047,22 +3058,31 @@ static void macsec_del_dev(struct macsec_dev *macsec) } } +static void macsec_common_dellink(struct net_device *dev, struct list_head *head) +{ + struct macsec_dev *macsec = macsec_priv(dev); + struct net_device *real_dev = macsec->real_dev; + + unregister_netdevice_queue(dev, head); + list_del_rcu(&macsec->secys); + macsec_del_dev(macsec); + netdev_upper_dev_unlink(real_dev, dev); + + macsec_generation++; +} + static void macsec_dellink(struct net_device *dev, struct list_head *head) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev); - macsec_generation++; + macsec_common_dellink(dev, head); - unregister_netdevice_queue(dev, head); - list_del_rcu(&macsec->secys); if (list_empty(&rxd->secys)) { netdev_rx_handler_unregister(real_dev); kfree(rxd); } - - macsec_del_dev(macsec); } static int register_macsec_dev(struct net_device *real_dev, @@ -3181,6 +3201,16 @@ static int macsec_newlink(struct net *net, struct net_device *dev, dev_hold(real_dev); + macsec->nest_level = dev_get_nest_level(real_dev) + 1; + netdev_lockdep_set_classes(dev); + lockdep_set_class_and_subclass(&dev->addr_list_lock, + &macsec_netdev_addr_lock_key, + macsec_get_nest_level(dev)); + + err = netdev_upper_dev_link(real_dev, dev); + if (err < 0) + goto unregister; + /* need to be already registered so that ->init has run and * the MAC addr is set */ @@ -3193,12 +3223,12 @@ static int macsec_newlink(struct net *net, struct net_device *dev, if (rx_handler && sci_exists(real_dev, sci)) { err = -EBUSY; - goto unregister; + goto unlink; } err = macsec_add_dev(dev, sci, icv_len); if (err) - goto unregister; + goto unlink; if (data) macsec_changelink_common(dev, data); @@ -3213,6 +3243,8 @@ static int macsec_newlink(struct net *net, struct net_device *dev, del_dev: macsec_del_dev(macsec); +unlink: + netdev_upper_dev_unlink(real_dev, dev); unregister: unregister_netdevice(dev); return err; @@ -3382,8 +3414,12 @@ static int macsec_notify(struct notifier_block *this, unsigned long event, rxd = macsec_data_rtnl(real_dev); list_for_each_entry_safe(m, n, &rxd->secys, secys) { - macsec_dellink(m->secy.netdev, &head); + macsec_common_dellink(m->secy.netdev, &head); } + + netdev_rx_handler_unregister(real_dev); + kfree(rxd); + unregister_netdevice_many(&head); break; } diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index cd9b53834bf6..3234fcdea317 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1315,7 +1315,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, vlan->dev = dev; vlan->port = port; vlan->set_features = MACVLAN_FEATURES; - vlan->nest_level = dev_get_nest_level(lowerdev, netif_is_macvlan) + 1; + vlan->nest_level = dev_get_nest_level(lowerdev) + 1; vlan->mode = MACVLAN_MODE_VEPA; if (data && data[IFLA_MACVLAN_MODE]) diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index a38c0dac514b..070e3290aa6e 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -275,7 +275,6 @@ static void macvtap_put_queue(struct macvtap_queue *q) rtnl_unlock(); synchronize_rcu(); - skb_array_cleanup(&q->skb_array); sock_put(&q->sk); } @@ -533,10 +532,8 @@ static void macvtap_sock_write_space(struct sock *sk) static void macvtap_sock_destruct(struct sock *sk) { struct macvtap_queue *q = container_of(sk, struct macvtap_queue, sk); - struct sk_buff *skb; - while ((skb = skb_array_consume(&q->skb_array)) != NULL) - kfree_skb(skb); + skb_array_cleanup(&q->skb_array); } static int macvtap_open(struct inode *inode, struct file *file) diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 1882d9828c99..053e87905b94 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -677,17 +677,28 @@ static void kszphy_get_stats(struct phy_device *phydev, data[i] = kszphy_get_stat(phydev, i); } -static int kszphy_resume(struct phy_device *phydev) +static int kszphy_suspend(struct phy_device *phydev) { - int value; + /* Disable PHY Interrupts */ + if (phy_interrupt_is_valid(phydev)) { + phydev->interrupts = PHY_INTERRUPT_DISABLED; + if (phydev->drv->config_intr) + phydev->drv->config_intr(phydev); + } - mutex_lock(&phydev->lock); + return genphy_suspend(phydev); +} - value = phy_read(phydev, MII_BMCR); - phy_write(phydev, MII_BMCR, value & ~BMCR_PDOWN); +static int kszphy_resume(struct phy_device *phydev) +{ + genphy_resume(phydev); - kszphy_config_intr(phydev); - mutex_unlock(&phydev->lock); + /* Enable PHY Interrupts */ + if (phy_interrupt_is_valid(phydev)) { + phydev->interrupts = PHY_INTERRUPT_ENABLED; + if (phydev->drv->config_intr) + phydev->drv->config_intr(phydev); + } return 0; } @@ -900,7 +911,7 @@ static struct phy_driver ksphy_driver[] = { .get_sset_count = kszphy_get_sset_count, .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, - .suspend = genphy_suspend, + .suspend = kszphy_suspend, .resume = kszphy_resume, }, { .phy_id = PHY_ID_KSZ8061, diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index da4e3d6632f6..c0dda6fc0921 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1811,7 +1811,7 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, fl4.flowi4_mark = skb->mark; fl4.flowi4_proto = IPPROTO_UDP; fl4.daddr = daddr; - fl4.saddr = vxlan->cfg.saddr.sin.sin_addr.s_addr; + fl4.saddr = *saddr; rt = ip_route_output_key(vxlan->net, &fl4); if (!IS_ERR(rt)) { @@ -1847,7 +1847,7 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = oif; fl6.daddr = *daddr; - fl6.saddr = vxlan->cfg.saddr.sin6.sin6_addr; + fl6.saddr = *saddr; fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tos), label); fl6.flowi6_mark = skb->mark; fl6.flowi6_proto = IPPROTO_UDP; @@ -1920,7 +1920,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct rtable *rt = NULL; const struct iphdr *old_iph; union vxlan_addr *dst; - union vxlan_addr remote_ip; + union vxlan_addr remote_ip, local_ip; + union vxlan_addr *src; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; __be16 src_port = 0, dst_port; @@ -1938,6 +1939,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port; vni = rdst->remote_vni; dst = &rdst->remote_ip; + src = &vxlan->cfg.saddr; dst_cache = &rdst->dst_cache; } else { if (!info) { @@ -1948,11 +1950,15 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port; vni = vxlan_tun_id_to_vni(info->key.tun_id); remote_ip.sa.sa_family = ip_tunnel_info_af(info); - if (remote_ip.sa.sa_family == AF_INET) + if (remote_ip.sa.sa_family == AF_INET) { remote_ip.sin.sin_addr.s_addr = info->key.u.ipv4.dst; - else + local_ip.sin.sin_addr.s_addr = info->key.u.ipv4.src; + } else { remote_ip.sin6.sin6_addr = info->key.u.ipv6.dst; + local_ip.sin6.sin6_addr = info->key.u.ipv6.src; + } dst = &remote_ip; + src = &local_ip; dst_cache = &info->dst_cache; } @@ -1992,15 +1998,14 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, } if (dst->sa.sa_family == AF_INET) { - __be32 saddr; - if (!vxlan->vn4_sock) goto drop; sk = vxlan->vn4_sock->sock->sk; rt = vxlan_get_route(vxlan, skb, rdst ? rdst->remote_ifindex : 0, tos, - dst->sin.sin_addr.s_addr, &saddr, + dst->sin.sin_addr.s_addr, + &src->sin.sin_addr.s_addr, dst_cache, info); if (IS_ERR(rt)) { netdev_dbg(dev, "no route to %pI4\n", @@ -2017,7 +2022,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, } /* Bypass encapsulation if the destination is local */ - if (rt->rt_flags & RTCF_LOCAL && + if (!info && rt->rt_flags & RTCF_LOCAL && !(rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) { struct vxlan_dev *dst_vxlan; @@ -2043,13 +2048,12 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, if (err < 0) goto xmit_tx_error; - udp_tunnel_xmit_skb(rt, sk, skb, saddr, + udp_tunnel_xmit_skb(rt, sk, skb, src->sin.sin_addr.s_addr, dst->sin.sin_addr.s_addr, tos, ttl, df, src_port, dst_port, xnet, !udp_sum); #if IS_ENABLED(CONFIG_IPV6) } else { struct dst_entry *ndst; - struct in6_addr saddr; u32 rt6i_flags; if (!vxlan->vn6_sock) @@ -2058,7 +2062,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, ndst = vxlan6_get_route(vxlan, skb, rdst ? rdst->remote_ifindex : 0, tos, - label, &dst->sin6.sin6_addr, &saddr, + label, &dst->sin6.sin6_addr, + &src->sin6.sin6_addr, dst_cache, info); if (IS_ERR(ndst)) { netdev_dbg(dev, "no route to %pI6\n", @@ -2077,7 +2082,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, /* Bypass encapsulation if the destination is local */ rt6i_flags = ((struct rt6_info *)ndst)->rt6i_flags; - if (rt6i_flags & RTF_LOCAL && + if (!info && rt6i_flags & RTF_LOCAL && !(rt6i_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) { struct vxlan_dev *dst_vxlan; @@ -2104,7 +2109,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, return; } udp_tunnel6_xmit_skb(ndst, sk, skb, dev, - &saddr, &dst->sin6.sin6_addr, tos, ttl, + &src->sin6.sin6_addr, + &dst->sin6.sin6_addr, tos, ttl, label, src_port, dst_port, !udp_sum); #endif } diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c index 1d689169da76..9e1f2d9c9865 100644 --- a/drivers/net/wireless/ti/wlcore/main.c +++ b/drivers/net/wireless/ti/wlcore/main.c @@ -5700,10 +5700,11 @@ out: mutex_unlock(&wl->mutex); } -static u32 wlcore_op_get_expected_throughput(struct ieee80211_sta *sta) +static u32 wlcore_op_get_expected_throughput(struct ieee80211_hw *hw, + struct ieee80211_sta *sta) { struct wl1271_station *wl_sta = (struct wl1271_station *)sta->drv_priv; - struct wl1271 *wl = wl_sta->wl; + struct wl1271 *wl = hw->priv; u8 hlid = wl_sta->hlid; /* return in units of Kbps */ diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 88e91666f145..368795aad5c9 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1269,6 +1269,7 @@ static int btt_blk_init(struct btt *btt) } } set_capacity(btt->btt_disk, btt->nlba * btt->sector_size >> 9); + btt->nd_btt->size = btt->nlba * (u64)btt->sector_size; revalidate_disk(btt->btt_disk); return 0; diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c index 3fa7919f94a8..97dd2925ed6e 100644 --- a/drivers/nvdimm/btt_devs.c +++ b/drivers/nvdimm/btt_devs.c @@ -140,10 +140,30 @@ static ssize_t namespace_store(struct device *dev, } static DEVICE_ATTR_RW(namespace); +static ssize_t size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_btt *nd_btt = to_nd_btt(dev); + ssize_t rc; + + device_lock(dev); + if (dev->driver) + rc = sprintf(buf, "%llu\n", nd_btt->size); + else { + /* no size to convey if the btt instance is disabled */ + rc = -ENXIO; + } + device_unlock(dev); + + return rc; +} +static DEVICE_ATTR_RO(size); + static struct attribute *nd_btt_attributes[] = { &dev_attr_sector_size.attr, &dev_attr_namespace.attr, &dev_attr_uuid.attr, + &dev_attr_size.attr, NULL, }; diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index 40476399d227..8024a0ef86d3 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -143,6 +143,7 @@ struct nd_btt { struct nd_namespace_common *ndns; struct btt *btt; unsigned long lbasize; + u64 size; u8 *uuid; int id; }; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index d7c33f9361aa..8dcf5a960951 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1543,15 +1543,10 @@ static void nvme_disable_io_queues(struct nvme_dev *dev) reinit_completion(&dev->ioq_wait); retry: timeout = ADMIN_TIMEOUT; - for (; i > 0; i--) { - struct nvme_queue *nvmeq = dev->queues[i]; - - if (!pass) - nvme_suspend_queue(nvmeq); - if (nvme_delete_queue(nvmeq, opcode)) + for (; i > 0; i--, sent++) + if (nvme_delete_queue(dev->queues[i], opcode)) break; - ++sent; - } + while (sent--) { timeout = wait_for_completion_io_timeout(&dev->ioq_wait, timeout); if (timeout == 0) @@ -1693,11 +1688,12 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) nvme_stop_queues(&dev->ctrl); csts = readl(dev->bar + NVME_REG_CSTS); } + + for (i = dev->queue_count - 1; i > 0; i--) + nvme_suspend_queue(dev->queues[i]); + if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) { - for (i = dev->queue_count - 1; i >= 0; i--) { - struct nvme_queue *nvmeq = dev->queues[i]; - nvme_suspend_queue(nvmeq); - } + nvme_suspend_queue(dev->queues[0]); } else { nvme_disable_io_queues(dev); nvme_disable_admin_queue(dev, shutdown); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 3e3ce2b0424e..8d2875b4c56d 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -12,13 +12,11 @@ * more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/delay.h> #include <linux/module.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/err.h> #include <linux/string.h> -#include <linux/jiffies.h> #include <linux/atomic.h> #include <linux/blk-mq.h> #include <linux/types.h> @@ -26,7 +24,6 @@ #include <linux/mutex.h> #include <linux/scatterlist.h> #include <linux/nvme.h> -#include <linux/t10-pi.h> #include <asm/unaligned.h> #include <rdma/ib_verbs.h> @@ -169,7 +166,6 @@ MODULE_PARM_DESC(register_always, static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, struct rdma_cm_event *event); static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc); -static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl); /* XXX: really should move to a generic header sooner or later.. */ static inline void put_unaligned_le24(u32 val, u8 *p) @@ -687,11 +683,6 @@ static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl) list_del(&ctrl->list); mutex_unlock(&nvme_rdma_ctrl_mutex); - if (ctrl->ctrl.tagset) { - blk_cleanup_queue(ctrl->ctrl.connect_q); - blk_mq_free_tag_set(&ctrl->tag_set); - nvme_rdma_dev_put(ctrl->device); - } kfree(ctrl->queues); nvmf_free_options(nctrl->opts); free_ctrl: @@ -748,8 +739,11 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); WARN_ON_ONCE(!changed); - if (ctrl->queue_count > 1) + if (ctrl->queue_count > 1) { nvme_start_queues(&ctrl->ctrl); + nvme_queue_scan(&ctrl->ctrl); + nvme_queue_async_events(&ctrl->ctrl); + } dev_info(ctrl->ctrl.device, "Successfully reconnected\n"); @@ -1269,7 +1263,7 @@ static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue) { struct nvme_rdma_ctrl *ctrl = queue->ctrl; struct rdma_conn_param param = { }; - struct nvme_rdma_cm_req priv; + struct nvme_rdma_cm_req priv = { }; int ret; param.qp_num = queue->qp->qp_num; @@ -1318,37 +1312,39 @@ out_destroy_queue_ib: * that caught the event. Since we hold the callout until the controller * deletion is completed, we'll deadlock if the controller deletion will * call rdma_destroy_id on this queue's cm_id. Thus, we claim ownership - * of destroying this queue before-hand, destroy the queue resources - * after the controller deletion completed with the exception of destroying - * the cm_id implicitely by returning a non-zero rc to the callout. + * of destroying this queue before-hand, destroy the queue resources, + * then queue the controller deletion which won't destroy this queue and + * we destroy the cm_id implicitely by returning a non-zero rc to the callout. */ static int nvme_rdma_device_unplug(struct nvme_rdma_queue *queue) { struct nvme_rdma_ctrl *ctrl = queue->ctrl; - int ret, ctrl_deleted = 0; + int ret; - /* First disable the queue so ctrl delete won't free it */ - if (!test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags)) - goto out; + /* Own the controller deletion */ + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING)) + return 0; - /* delete the controller */ - ret = __nvme_rdma_del_ctrl(ctrl); - if (!ret) { - dev_warn(ctrl->ctrl.device, - "Got rdma device removal event, deleting ctrl\n"); - flush_work(&ctrl->delete_work); + dev_warn(ctrl->ctrl.device, + "Got rdma device removal event, deleting ctrl\n"); - /* Return non-zero so the cm_id will destroy implicitly */ - ctrl_deleted = 1; + /* Get rid of reconnect work if its running */ + cancel_delayed_work_sync(&ctrl->reconnect_work); + /* Disable the queue so ctrl delete won't free it */ + if (test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags)) { /* Free this queue ourselves */ - rdma_disconnect(queue->cm_id); - ib_drain_qp(queue->qp); + nvme_rdma_stop_queue(queue); nvme_rdma_destroy_queue_ib(queue); + + /* Return non-zero so the cm_id will destroy implicitly */ + ret = 1; } -out: - return ctrl_deleted; + /* Queue controller deletion */ + queue_work(nvme_rdma_wq, &ctrl->delete_work); + flush_work(&ctrl->delete_work); + return ret; } static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, @@ -1648,7 +1644,7 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl) nvme_rdma_free_io_queues(ctrl); } - if (ctrl->ctrl.state == NVME_CTRL_LIVE) + if (test_bit(NVME_RDMA_Q_CONNECTED, &ctrl->queues[0].flags)) nvme_shutdown_ctrl(&ctrl->ctrl); blk_mq_stop_hw_queues(ctrl->ctrl.admin_q); @@ -1657,15 +1653,27 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl) nvme_rdma_destroy_admin_queue(ctrl); } +static void __nvme_rdma_remove_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown) +{ + nvme_uninit_ctrl(&ctrl->ctrl); + if (shutdown) + nvme_rdma_shutdown_ctrl(ctrl); + + if (ctrl->ctrl.tagset) { + blk_cleanup_queue(ctrl->ctrl.connect_q); + blk_mq_free_tag_set(&ctrl->tag_set); + nvme_rdma_dev_put(ctrl->device); + } + + nvme_put_ctrl(&ctrl->ctrl); +} + static void nvme_rdma_del_ctrl_work(struct work_struct *work) { struct nvme_rdma_ctrl *ctrl = container_of(work, struct nvme_rdma_ctrl, delete_work); - nvme_remove_namespaces(&ctrl->ctrl); - nvme_rdma_shutdown_ctrl(ctrl); - nvme_uninit_ctrl(&ctrl->ctrl); - nvme_put_ctrl(&ctrl->ctrl); + __nvme_rdma_remove_ctrl(ctrl, true); } static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl) @@ -1698,9 +1706,7 @@ static void nvme_rdma_remove_ctrl_work(struct work_struct *work) struct nvme_rdma_ctrl *ctrl = container_of(work, struct nvme_rdma_ctrl, delete_work); - nvme_remove_namespaces(&ctrl->ctrl); - nvme_uninit_ctrl(&ctrl->ctrl); - nvme_put_ctrl(&ctrl->ctrl); + __nvme_rdma_remove_ctrl(ctrl, false); } static void nvme_rdma_reset_ctrl_work(struct work_struct *work) @@ -1739,6 +1745,7 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work) if (ctrl->queue_count > 1) { nvme_start_queues(&ctrl->ctrl); nvme_queue_scan(&ctrl->ctrl); + nvme_queue_async_events(&ctrl->ctrl); } return; diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 2fac17a5ad53..47c564b5a289 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -13,7 +13,6 @@ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> -#include <linux/random.h> #include <generated/utsrelease.h> #include "nvmet.h" @@ -83,7 +82,6 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; struct nvme_id_ctrl *id; - u64 serial; u16 status = 0; id = kzalloc(sizeof(*id), GFP_KERNEL); @@ -96,10 +94,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) id->vid = 0; id->ssvid = 0; - /* generate a random serial number as our controllers are ephemeral: */ - get_random_bytes(&serial, sizeof(serial)); memset(id->sn, ' ', sizeof(id->sn)); - snprintf(id->sn, sizeof(id->sn), "%llx", serial); + snprintf(id->sn, sizeof(id->sn), "%llx", ctrl->serial); memset(id->mn, ' ', sizeof(id->mn)); strncpy((char *)id->mn, "Linux", sizeof(id->mn)); diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 8a891ca53367..6559d5afa7bf 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -13,6 +13,7 @@ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> +#include <linux/random.h> #include "nvmet.h" static struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX]; @@ -728,6 +729,9 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, memcpy(ctrl->subsysnqn, subsysnqn, NVMF_NQN_SIZE); memcpy(ctrl->hostnqn, hostnqn, NVMF_NQN_SIZE); + /* generate a random serial number as our controllers are ephemeral: */ + get_random_bytes(&ctrl->serial, sizeof(ctrl->serial)); + kref_init(&ctrl->ref); ctrl->subsys = subsys; diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 94e782987cc9..7affd40a6b33 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -414,9 +414,8 @@ static void nvme_loop_del_ctrl_work(struct work_struct *work) struct nvme_loop_ctrl *ctrl = container_of(work, struct nvme_loop_ctrl, delete_work); - nvme_remove_namespaces(&ctrl->ctrl); - nvme_loop_shutdown_ctrl(ctrl); nvme_uninit_ctrl(&ctrl->ctrl); + nvme_loop_shutdown_ctrl(ctrl); nvme_put_ctrl(&ctrl->ctrl); } @@ -501,7 +500,6 @@ out_free_queues: nvme_loop_destroy_admin_queue(ctrl); out_disable: dev_warn(ctrl->ctrl.device, "Removing after reset failure\n"); - nvme_remove_namespaces(&ctrl->ctrl); nvme_uninit_ctrl(&ctrl->ctrl); nvme_put_ctrl(&ctrl->ctrl); } diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 57dd6d834c28..76b6eedccaf9 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -113,6 +113,7 @@ struct nvmet_ctrl { struct mutex lock; u64 cap; + u64 serial; u32 cc; u32 csts; diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index e06d504bdf0c..b4d648536c3e 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -77,6 +77,7 @@ enum nvmet_rdma_queue_state { NVMET_RDMA_Q_CONNECTING, NVMET_RDMA_Q_LIVE, NVMET_RDMA_Q_DISCONNECTING, + NVMET_RDMA_IN_DEVICE_REMOVAL, }; struct nvmet_rdma_queue { @@ -615,15 +616,10 @@ static u16 nvmet_rdma_map_sgl_keyed(struct nvmet_rdma_rsp *rsp, if (!len) return 0; - /* use the already allocated data buffer if possible */ - if (len <= NVMET_RDMA_INLINE_DATA_SIZE && rsp->queue->host_qid) { - nvmet_rdma_use_inline_sg(rsp, len, 0); - } else { - status = nvmet_rdma_alloc_sgl(&rsp->req.sg, &rsp->req.sg_cnt, - len); - if (status) - return status; - } + status = nvmet_rdma_alloc_sgl(&rsp->req.sg, &rsp->req.sg_cnt, + len); + if (status) + return status; ret = rdma_rw_ctx_init(&rsp->rw, cm_id->qp, cm_id->port_num, rsp->req.sg, rsp->req.sg_cnt, 0, addr, key, @@ -984,7 +980,10 @@ static void nvmet_rdma_release_queue_work(struct work_struct *w) struct nvmet_rdma_device *dev = queue->dev; nvmet_rdma_free_queue(queue); - rdma_destroy_id(cm_id); + + if (queue->state != NVMET_RDMA_IN_DEVICE_REMOVAL) + rdma_destroy_id(cm_id); + kref_put(&dev->ref, nvmet_rdma_free_dev); } @@ -1233,8 +1232,9 @@ static void __nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue) switch (queue->state) { case NVMET_RDMA_Q_CONNECTING: case NVMET_RDMA_Q_LIVE: - disconnect = true; queue->state = NVMET_RDMA_Q_DISCONNECTING; + case NVMET_RDMA_IN_DEVICE_REMOVAL: + disconnect = true; break; case NVMET_RDMA_Q_DISCONNECTING: break; @@ -1272,6 +1272,62 @@ static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id, schedule_work(&queue->release_work); } +/** + * nvme_rdma_device_removal() - Handle RDMA device removal + * @queue: nvmet rdma queue (cm id qp_context) + * @addr: nvmet address (cm_id context) + * + * DEVICE_REMOVAL event notifies us that the RDMA device is about + * to unplug so we should take care of destroying our RDMA resources. + * This event will be generated for each allocated cm_id. + * + * Note that this event can be generated on a normal queue cm_id + * and/or a device bound listener cm_id (where in this case + * queue will be null). + * + * we claim ownership on destroying the cm_id. For queues we move + * the queue state to NVMET_RDMA_IN_DEVICE_REMOVAL and for port + * we nullify the priv to prevent double cm_id destruction and destroying + * the cm_id implicitely by returning a non-zero rc to the callout. + */ +static int nvmet_rdma_device_removal(struct rdma_cm_id *cm_id, + struct nvmet_rdma_queue *queue) +{ + unsigned long flags; + + if (!queue) { + struct nvmet_port *port = cm_id->context; + + /* + * This is a listener cm_id. Make sure that + * future remove_port won't invoke a double + * cm_id destroy. use atomic xchg to make sure + * we don't compete with remove_port. + */ + if (xchg(&port->priv, NULL) != cm_id) + return 0; + } else { + /* + * This is a queue cm_id. Make sure that + * release queue will not destroy the cm_id + * and schedule all ctrl queues removal (only + * if the queue is not disconnecting already). + */ + spin_lock_irqsave(&queue->state_lock, flags); + if (queue->state != NVMET_RDMA_Q_DISCONNECTING) + queue->state = NVMET_RDMA_IN_DEVICE_REMOVAL; + spin_unlock_irqrestore(&queue->state_lock, flags); + nvmet_rdma_queue_disconnect(queue); + flush_scheduled_work(); + } + + /* + * We need to return 1 so that the core will destroy + * it's own ID. What a great API design.. + */ + return 1; +} + static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id, struct rdma_cm_event *event) { @@ -1294,20 +1350,11 @@ static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_ADDR_CHANGE: case RDMA_CM_EVENT_DISCONNECTED: - case RDMA_CM_EVENT_DEVICE_REMOVAL: case RDMA_CM_EVENT_TIMEWAIT_EXIT: - /* - * We can get the device removal callback even for a - * CM ID that we aren't actually using. In that case - * the context pointer is NULL, so we shouldn't try - * to disconnect a non-existing queue. But we also - * need to return 1 so that the core will destroy - * it's own ID. What a great API design.. - */ - if (queue) - nvmet_rdma_queue_disconnect(queue); - else - ret = 1; + nvmet_rdma_queue_disconnect(queue); + break; + case RDMA_CM_EVENT_DEVICE_REMOVAL: + ret = nvmet_rdma_device_removal(cm_id, queue); break; case RDMA_CM_EVENT_REJECTED: case RDMA_CM_EVENT_UNREACHABLE: @@ -1396,9 +1443,10 @@ out_destroy_id: static void nvmet_rdma_remove_port(struct nvmet_port *port) { - struct rdma_cm_id *cm_id = port->priv; + struct rdma_cm_id *cm_id = xchg(&port->priv, NULL); - rdma_destroy_id(cm_id); + if (cm_id) + rdma_destroy_id(cm_id); } static struct nvmet_fabrics_ops nvmet_rdma_ops = { diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index a02981efdad5..eafa6138a6b8 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -1411,6 +1411,8 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) pci_msi_domain_update_chip_ops(info); + info->flags |= MSI_FLAG_ACTIVATE_EARLY; + domain = msi_create_irq_domain(fwnode, info, parent); if (!domain) return NULL; diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 6ccb994bdfcb..c494613c1909 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -688,7 +688,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) return 0; } -static DEFINE_MUTEX(arm_pmu_mutex); +static DEFINE_SPINLOCK(arm_pmu_lock); static LIST_HEAD(arm_pmu_list); /* @@ -701,7 +701,7 @@ static int arm_perf_starting_cpu(unsigned int cpu) { struct arm_pmu *pmu; - mutex_lock(&arm_pmu_mutex); + spin_lock(&arm_pmu_lock); list_for_each_entry(pmu, &arm_pmu_list, entry) { if (!cpumask_test_cpu(cpu, &pmu->supported_cpus)) @@ -709,7 +709,7 @@ static int arm_perf_starting_cpu(unsigned int cpu) if (pmu->reset) pmu->reset(pmu); } - mutex_unlock(&arm_pmu_mutex); + spin_unlock(&arm_pmu_lock); return 0; } @@ -821,9 +821,9 @@ static int cpu_pmu_init(struct arm_pmu *cpu_pmu) if (!cpu_hw_events) return -ENOMEM; - mutex_lock(&arm_pmu_mutex); + spin_lock(&arm_pmu_lock); list_add_tail(&cpu_pmu->entry, &arm_pmu_list); - mutex_unlock(&arm_pmu_mutex); + spin_unlock(&arm_pmu_lock); err = cpu_pm_pmu_register(cpu_pmu); if (err) @@ -859,9 +859,9 @@ static int cpu_pmu_init(struct arm_pmu *cpu_pmu) return 0; out_unregister: - mutex_lock(&arm_pmu_mutex); + spin_lock(&arm_pmu_lock); list_del(&cpu_pmu->entry); - mutex_unlock(&arm_pmu_mutex); + spin_unlock(&arm_pmu_lock); free_percpu(cpu_hw_events); return err; } @@ -869,9 +869,9 @@ out_unregister: static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu) { cpu_pm_pmu_unregister(cpu_pmu); - mutex_lock(&arm_pmu_mutex); + spin_lock(&arm_pmu_lock); list_del(&cpu_pmu->entry); - mutex_unlock(&arm_pmu_mutex); + spin_unlock(&arm_pmu_lock); free_percpu(cpu_pmu->hw_events); } @@ -967,11 +967,12 @@ static int of_pmu_irq_cfg(struct arm_pmu *pmu) /* If we didn't manage to parse anything, try the interrupt affinity */ if (cpumask_weight(&pmu->supported_cpus) == 0) { - if (!using_spi) { + int irq = platform_get_irq(pdev, 0); + + if (irq_is_percpu(irq)) { /* If using PPIs, check the affinity of the partition */ - int ret, irq; + int ret; - irq = platform_get_irq(pdev, 0); ret = irq_get_percpu_devid_partition(irq, &pmu->supported_cpus); if (ret) { kfree(irqs); diff --git a/drivers/pinctrl/intel/pinctrl-merrifield.c b/drivers/pinctrl/intel/pinctrl-merrifield.c index eb4990ff26ca..7fb765642ee7 100644 --- a/drivers/pinctrl/intel/pinctrl-merrifield.c +++ b/drivers/pinctrl/intel/pinctrl-merrifield.c @@ -11,6 +11,7 @@ #include <linux/bitops.h> #include <linux/err.h> +#include <linux/io.h> #include <linux/module.h> #include <linux/platform_device.h> #include <linux/pinctrl/pinconf.h> diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c index 11623c6b0cb3..44e69c963f5d 100644 --- a/drivers/pinctrl/meson/pinctrl-meson.c +++ b/drivers/pinctrl/meson/pinctrl-meson.c @@ -727,13 +727,7 @@ static int meson_pinctrl_probe(struct platform_device *pdev) return PTR_ERR(pc->pcdev); } - ret = meson_gpiolib_register(pc); - if (ret) { - pinctrl_unregister(pc->pcdev); - return ret; - } - - return 0; + return meson_gpiolib_register(pc); } static struct platform_driver meson_pinctrl_driver = { diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 634b4d30eefb..b3e772390ab6 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -43,17 +43,6 @@ static int amd_gpio_direction_input(struct gpio_chip *gc, unsigned offset) spin_lock_irqsave(&gpio_dev->lock, flags); pin_reg = readl(gpio_dev->base + offset * 4); - /* - * Suppose BIOS or Bootloader sets specific debounce for the - * GPIO. if not, set debounce to be 2.75ms and remove glitch. - */ - if ((pin_reg & DB_TMR_OUT_MASK) == 0) { - pin_reg |= 0xf; - pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF); - pin_reg |= DB_TYPE_REMOVE_GLITCH << DB_CNTRL_OFF; - pin_reg &= ~BIT(DB_TMR_LARGE_OFF); - } - pin_reg &= ~BIT(OUTPUT_ENABLE_OFF); writel(pin_reg, gpio_dev->base + offset * 4); spin_unlock_irqrestore(&gpio_dev->lock, flags); @@ -326,15 +315,6 @@ static void amd_gpio_irq_enable(struct irq_data *d) spin_lock_irqsave(&gpio_dev->lock, flags); pin_reg = readl(gpio_dev->base + (d->hwirq)*4); - /* - Suppose BIOS or Bootloader sets specific debounce for the - GPIO. if not, set debounce to be 2.75ms. - */ - if ((pin_reg & DB_TMR_OUT_MASK) == 0) { - pin_reg |= 0xf; - pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF); - pin_reg &= ~BIT(DB_TMR_LARGE_OFF); - } pin_reg |= BIT(INTERRUPT_ENABLE_OFF); pin_reg |= BIT(INTERRUPT_MASK_OFF); writel(pin_reg, gpio_dev->base + (d->hwirq)*4); diff --git a/drivers/pinctrl/pinctrl-pistachio.c b/drivers/pinctrl/pinctrl-pistachio.c index c6d410ef8de0..7bad200bd67c 100644 --- a/drivers/pinctrl/pinctrl-pistachio.c +++ b/drivers/pinctrl/pinctrl-pistachio.c @@ -1432,7 +1432,6 @@ static int pistachio_pinctrl_probe(struct platform_device *pdev) { struct pistachio_pinctrl *pctl; struct resource *res; - int ret; pctl = devm_kzalloc(&pdev->dev, sizeof(*pctl), GFP_KERNEL); if (!pctl) @@ -1464,13 +1463,7 @@ static int pistachio_pinctrl_probe(struct platform_device *pdev) return PTR_ERR(pctl->pctldev); } - ret = pistachio_gpio_register(pctl); - if (ret < 0) { - pinctrl_unregister(pctl->pctldev); - return ret; - } - - return 0; + return pistachio_gpio_register(pctl); } static struct platform_driver pistachio_pinctrl_driver = { diff --git a/drivers/power/max17042_battery.c b/drivers/power/max17042_battery.c index 9c65f134d447..da7a75f82489 100644 --- a/drivers/power/max17042_battery.c +++ b/drivers/power/max17042_battery.c @@ -457,13 +457,16 @@ static inline void max17042_write_model_data(struct max17042_chip *chip, } static inline void max17042_read_model_data(struct max17042_chip *chip, - u8 addr, u32 *data, int size) + u8 addr, u16 *data, int size) { struct regmap *map = chip->regmap; int i; + u32 tmp; - for (i = 0; i < size; i++) - regmap_read(map, addr + i, &data[i]); + for (i = 0; i < size; i++) { + regmap_read(map, addr + i, &tmp); + data[i] = (u16)tmp; + } } static inline int max17042_model_data_compare(struct max17042_chip *chip, @@ -486,7 +489,7 @@ static int max17042_init_model(struct max17042_chip *chip) { int ret; int table_size = ARRAY_SIZE(chip->pdata->config_data->cell_char_tbl); - u32 *temp_data; + u16 *temp_data; temp_data = kcalloc(table_size, sizeof(*temp_data), GFP_KERNEL); if (!temp_data) @@ -501,7 +504,7 @@ static int max17042_init_model(struct max17042_chip *chip) ret = max17042_model_data_compare( chip, chip->pdata->config_data->cell_char_tbl, - (u16 *)temp_data, + temp_data, table_size); max10742_lock_model(chip); @@ -514,7 +517,7 @@ static int max17042_verify_model_lock(struct max17042_chip *chip) { int i; int table_size = ARRAY_SIZE(chip->pdata->config_data->cell_char_tbl); - u32 *temp_data; + u16 *temp_data; int ret = 0; temp_data = kcalloc(table_size, sizeof(*temp_data), GFP_KERNEL); diff --git a/drivers/power/reset/Kconfig b/drivers/power/reset/Kconfig index 3bfac539334b..c74c3f67b8da 100644 --- a/drivers/power/reset/Kconfig +++ b/drivers/power/reset/Kconfig @@ -200,8 +200,8 @@ config REBOOT_MODE config SYSCON_REBOOT_MODE tristate "Generic SYSCON regmap reboot mode driver" depends on OF + depends on MFD_SYSCON select REBOOT_MODE - select MFD_SYSCON help Say y here will enable reboot mode driver. This will get reboot mode arguments and store it in SYSCON mapped diff --git a/drivers/power/reset/hisi-reboot.c b/drivers/power/reset/hisi-reboot.c index 9ab7f562a83b..f69387e12c1e 100644 --- a/drivers/power/reset/hisi-reboot.c +++ b/drivers/power/reset/hisi-reboot.c @@ -53,13 +53,16 @@ static int hisi_reboot_probe(struct platform_device *pdev) if (of_property_read_u32(np, "reboot-offset", &reboot_offset) < 0) { pr_err("failed to find reboot-offset property\n"); + iounmap(base); return -EINVAL; } err = register_restart_handler(&hisi_restart_nb); - if (err) + if (err) { dev_err(&pdev->dev, "cannot register restart handler (err=%d)\n", err); + iounmap(base); + } return err; } diff --git a/drivers/power/tps65217_charger.c b/drivers/power/tps65217_charger.c index 73dfae41def8..4c56e54af6ac 100644 --- a/drivers/power/tps65217_charger.c +++ b/drivers/power/tps65217_charger.c @@ -206,6 +206,7 @@ static int tps65217_charger_probe(struct platform_device *pdev) if (!charger) return -ENOMEM; + platform_set_drvdata(pdev, charger); charger->tps = tps; charger->dev = &pdev->dev; diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 8973d34ce5ba..fb1b56a71475 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -1643,9 +1643,18 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, u8 *sense = NULL; int expires; + cqr = (struct dasd_ccw_req *) intparm; if (IS_ERR(irb)) { switch (PTR_ERR(irb)) { case -EIO: + if (cqr && cqr->status == DASD_CQR_CLEAR_PENDING) { + device = (struct dasd_device *) cqr->startdev; + cqr->status = DASD_CQR_CLEARED; + dasd_device_clear_timer(device); + wake_up(&dasd_flush_wq); + dasd_schedule_device_bh(device); + return; + } break; case -ETIMEDOUT: DBF_EVENT_DEVID(DBF_WARNING, cdev, "%s: " @@ -1661,7 +1670,6 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, } now = get_tod_clock(); - cqr = (struct dasd_ccw_req *) intparm; /* check for conditions that should be handled immediately */ if (!cqr || !(scsw_dstat(&irb->scsw) == (DEV_STAT_CHN_END | DEV_STAT_DEV_END) && diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index fd2eff440098..98bbec44bcd0 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -5078,6 +5078,8 @@ static int dasd_eckd_read_message_buffer(struct dasd_device *device, return PTR_ERR(cqr); } + cqr->lpm = lpum; +retry: cqr->startdev = device; cqr->memdev = device; cqr->block = NULL; @@ -5122,6 +5124,14 @@ static int dasd_eckd_read_message_buffer(struct dasd_device *device, (prssdp + 1); memcpy(messages, message_buf, sizeof(struct dasd_rssd_messages)); + } else if (cqr->lpm) { + /* + * on z/VM we might not be able to do I/O on the requested path + * but instead we get the required information on any path + * so retry with open path mask + */ + cqr->lpm = 0; + goto retry; } else DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "Reading messages failed with rc=%d\n" diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index 7ada078ffdd0..6a58bc8f46e2 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -762,7 +762,6 @@ static int io_subchannel_initialize_dev(struct subchannel *sch, priv->state = DEV_STATE_NOT_OPER; priv->dev_id.devno = sch->schib.pmcw.dev; priv->dev_id.ssid = sch->schid.ssid; - priv->schid = sch->schid; INIT_WORK(&priv->todo_work, ccw_device_todo); INIT_LIST_HEAD(&priv->cmb_list); @@ -1000,7 +999,6 @@ static int ccw_device_move_to_sch(struct ccw_device *cdev, put_device(&old_sch->dev); /* Initialize new subchannel. */ spin_lock_irq(sch->lock); - cdev->private->schid = sch->schid; cdev->ccwlock = sch->lock; if (!sch_is_pseudo_sch(sch)) sch_set_cdev(sch, cdev); diff --git a/drivers/s390/cio/device_status.c b/drivers/s390/cio/device_status.c index 15b56a15db15..9bc3512374c9 100644 --- a/drivers/s390/cio/device_status.c +++ b/drivers/s390/cio/device_status.c @@ -26,6 +26,7 @@ static void ccw_device_msg_control_check(struct ccw_device *cdev, struct irb *irb) { + struct subchannel *sch = to_subchannel(cdev->dev.parent); char dbf_text[15]; if (!scsw_is_valid_cstat(&irb->scsw) || @@ -36,10 +37,10 @@ ccw_device_msg_control_check(struct ccw_device *cdev, struct irb *irb) "received" " ... device %04x on subchannel 0.%x.%04x, dev_stat " ": %02X sch_stat : %02X\n", - cdev->private->dev_id.devno, cdev->private->schid.ssid, - cdev->private->schid.sch_no, + cdev->private->dev_id.devno, sch->schid.ssid, + sch->schid.sch_no, scsw_dstat(&irb->scsw), scsw_cstat(&irb->scsw)); - sprintf(dbf_text, "chk%x", cdev->private->schid.sch_no); + sprintf(dbf_text, "chk%x", sch->schid.sch_no); CIO_TRACE_EVENT(0, dbf_text); CIO_HEX_EVENT(0, irb, sizeof(struct irb)); } diff --git a/drivers/s390/cio/io_sch.h b/drivers/s390/cio/io_sch.h index 8975060af96c..220f49145b2f 100644 --- a/drivers/s390/cio/io_sch.h +++ b/drivers/s390/cio/io_sch.h @@ -120,7 +120,6 @@ struct ccw_device_private { int state; /* device state */ atomic_t onoff; struct ccw_dev_id dev_id; /* device id */ - struct subchannel_id schid; /* subchannel number */ struct ccw_request req; /* internal I/O request */ int iretry; u8 pgid_valid_mask; /* mask of valid PGIDs */ diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 4bb5262f7aee..71bf9bded485 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -686,6 +686,15 @@ static void qdio_kick_handler(struct qdio_q *q) q->qdio_error = 0; } +static inline int qdio_tasklet_schedule(struct qdio_q *q) +{ + if (likely(q->irq_ptr->state == QDIO_IRQ_STATE_ACTIVE)) { + tasklet_schedule(&q->tasklet); + return 0; + } + return -EPERM; +} + static void __qdio_inbound_processing(struct qdio_q *q) { qperf_inc(q, tasklet_inbound); @@ -698,10 +707,8 @@ static void __qdio_inbound_processing(struct qdio_q *q) if (!qdio_inbound_q_done(q)) { /* means poll time is not yet over */ qperf_inc(q, tasklet_inbound_resched); - if (likely(q->irq_ptr->state != QDIO_IRQ_STATE_STOPPED)) { - tasklet_schedule(&q->tasklet); + if (!qdio_tasklet_schedule(q)) return; - } } qdio_stop_polling(q); @@ -711,8 +718,7 @@ static void __qdio_inbound_processing(struct qdio_q *q) */ if (!qdio_inbound_q_done(q)) { qperf_inc(q, tasklet_inbound_resched2); - if (likely(q->irq_ptr->state != QDIO_IRQ_STATE_STOPPED)) - tasklet_schedule(&q->tasklet); + qdio_tasklet_schedule(q); } } @@ -869,16 +875,15 @@ static void __qdio_outbound_processing(struct qdio_q *q) * is noticed and outbound_handler is called after some time. */ if (qdio_outbound_q_done(q)) - del_timer(&q->u.out.timer); + del_timer_sync(&q->u.out.timer); else - if (!timer_pending(&q->u.out.timer)) + if (!timer_pending(&q->u.out.timer) && + likely(q->irq_ptr->state == QDIO_IRQ_STATE_ACTIVE)) mod_timer(&q->u.out.timer, jiffies + 10 * HZ); return; sched: - if (unlikely(q->irq_ptr->state == QDIO_IRQ_STATE_STOPPED)) - return; - tasklet_schedule(&q->tasklet); + qdio_tasklet_schedule(q); } /* outbound tasklet */ @@ -892,9 +897,7 @@ void qdio_outbound_timer(unsigned long data) { struct qdio_q *q = (struct qdio_q *)data; - if (unlikely(q->irq_ptr->state == QDIO_IRQ_STATE_STOPPED)) - return; - tasklet_schedule(&q->tasklet); + qdio_tasklet_schedule(q); } static inline void qdio_check_outbound_after_thinint(struct qdio_q *q) @@ -907,7 +910,7 @@ static inline void qdio_check_outbound_after_thinint(struct qdio_q *q) for_each_output_queue(q->irq_ptr, out, i) if (!qdio_outbound_q_done(out)) - tasklet_schedule(&out->tasklet); + qdio_tasklet_schedule(out); } static void __tiqdio_inbound_processing(struct qdio_q *q) @@ -929,10 +932,8 @@ static void __tiqdio_inbound_processing(struct qdio_q *q) if (!qdio_inbound_q_done(q)) { qperf_inc(q, tasklet_inbound_resched); - if (likely(q->irq_ptr->state != QDIO_IRQ_STATE_STOPPED)) { - tasklet_schedule(&q->tasklet); + if (!qdio_tasklet_schedule(q)) return; - } } qdio_stop_polling(q); @@ -942,8 +943,7 @@ static void __tiqdio_inbound_processing(struct qdio_q *q) */ if (!qdio_inbound_q_done(q)) { qperf_inc(q, tasklet_inbound_resched2); - if (likely(q->irq_ptr->state != QDIO_IRQ_STATE_STOPPED)) - tasklet_schedule(&q->tasklet); + qdio_tasklet_schedule(q); } } @@ -977,7 +977,7 @@ static void qdio_int_handler_pci(struct qdio_irq *irq_ptr) int i; struct qdio_q *q; - if (unlikely(irq_ptr->state == QDIO_IRQ_STATE_STOPPED)) + if (unlikely(irq_ptr->state != QDIO_IRQ_STATE_ACTIVE)) return; for_each_input_queue(irq_ptr, q, i) { @@ -1003,7 +1003,7 @@ static void qdio_int_handler_pci(struct qdio_irq *irq_ptr) continue; if (need_siga_sync(q) && need_siga_sync_out_after_pci(q)) qdio_siga_sync_q(q); - tasklet_schedule(&q->tasklet); + qdio_tasklet_schedule(q); } } @@ -1066,10 +1066,12 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm, struct irb *irb) { struct qdio_irq *irq_ptr = cdev->private->qdio_data; + struct subchannel_id schid; int cstat, dstat; if (!intparm || !irq_ptr) { - DBF_ERROR("qint:%4x", cdev->private->schid.sch_no); + ccw_device_get_schid(cdev, &schid); + DBF_ERROR("qint:%4x", schid.sch_no); return; } @@ -1122,12 +1124,14 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm, int qdio_get_ssqd_desc(struct ccw_device *cdev, struct qdio_ssqd_desc *data) { + struct subchannel_id schid; if (!cdev || !cdev->private) return -EINVAL; - DBF_EVENT("get ssqd:%4x", cdev->private->schid.sch_no); - return qdio_setup_get_ssqd(NULL, &cdev->private->schid, data); + ccw_device_get_schid(cdev, &schid); + DBF_EVENT("get ssqd:%4x", schid.sch_no); + return qdio_setup_get_ssqd(NULL, &schid, data); } EXPORT_SYMBOL_GPL(qdio_get_ssqd_desc); @@ -1141,7 +1145,7 @@ static void qdio_shutdown_queues(struct ccw_device *cdev) tasklet_kill(&q->tasklet); for_each_output_queue(irq_ptr, q, i) { - del_timer(&q->u.out.timer); + del_timer_sync(&q->u.out.timer); tasklet_kill(&q->tasklet); } } @@ -1154,14 +1158,15 @@ static void qdio_shutdown_queues(struct ccw_device *cdev) int qdio_shutdown(struct ccw_device *cdev, int how) { struct qdio_irq *irq_ptr = cdev->private->qdio_data; + struct subchannel_id schid; int rc; - unsigned long flags; if (!irq_ptr) return -ENODEV; WARN_ON_ONCE(irqs_disabled()); - DBF_EVENT("qshutdown:%4x", cdev->private->schid.sch_no); + ccw_device_get_schid(cdev, &schid); + DBF_EVENT("qshutdown:%4x", schid.sch_no); mutex_lock(&irq_ptr->setup_mutex); /* @@ -1184,7 +1189,7 @@ int qdio_shutdown(struct ccw_device *cdev, int how) qdio_shutdown_debug_entries(irq_ptr); /* cleanup subchannel */ - spin_lock_irqsave(get_ccwdev_lock(cdev), flags); + spin_lock_irq(get_ccwdev_lock(cdev)); if (how & QDIO_FLAG_CLEANUP_USING_CLEAR) rc = ccw_device_clear(cdev, QDIO_DOING_CLEANUP); @@ -1198,12 +1203,12 @@ int qdio_shutdown(struct ccw_device *cdev, int how) } qdio_set_state(irq_ptr, QDIO_IRQ_STATE_CLEANUP); - spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); + spin_unlock_irq(get_ccwdev_lock(cdev)); wait_event_interruptible_timeout(cdev->private->wait_q, irq_ptr->state == QDIO_IRQ_STATE_INACTIVE || irq_ptr->state == QDIO_IRQ_STATE_ERR, 10 * HZ); - spin_lock_irqsave(get_ccwdev_lock(cdev), flags); + spin_lock_irq(get_ccwdev_lock(cdev)); no_cleanup: qdio_shutdown_thinint(irq_ptr); @@ -1211,7 +1216,7 @@ no_cleanup: /* restore interrupt handler */ if ((void *)cdev->handler == (void *)qdio_int_handler) cdev->handler = irq_ptr->orig_handler; - spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); + spin_unlock_irq(get_ccwdev_lock(cdev)); qdio_set_state(irq_ptr, QDIO_IRQ_STATE_INACTIVE); mutex_unlock(&irq_ptr->setup_mutex); @@ -1228,11 +1233,13 @@ EXPORT_SYMBOL_GPL(qdio_shutdown); int qdio_free(struct ccw_device *cdev) { struct qdio_irq *irq_ptr = cdev->private->qdio_data; + struct subchannel_id schid; if (!irq_ptr) return -ENODEV; - DBF_EVENT("qfree:%4x", cdev->private->schid.sch_no); + ccw_device_get_schid(cdev, &schid); + DBF_EVENT("qfree:%4x", schid.sch_no); DBF_DEV_EVENT(DBF_ERR, irq_ptr, "dbf abandoned"); mutex_lock(&irq_ptr->setup_mutex); @@ -1251,9 +1258,11 @@ EXPORT_SYMBOL_GPL(qdio_free); */ int qdio_allocate(struct qdio_initialize *init_data) { + struct subchannel_id schid; struct qdio_irq *irq_ptr; - DBF_EVENT("qallocate:%4x", init_data->cdev->private->schid.sch_no); + ccw_device_get_schid(init_data->cdev, &schid); + DBF_EVENT("qallocate:%4x", schid.sch_no); if ((init_data->no_input_qs && !init_data->input_handler) || (init_data->no_output_qs && !init_data->output_handler)) @@ -1331,20 +1340,18 @@ static void qdio_detect_hsicq(struct qdio_irq *irq_ptr) */ int qdio_establish(struct qdio_initialize *init_data) { - struct qdio_irq *irq_ptr; struct ccw_device *cdev = init_data->cdev; - unsigned long saveflags; + struct subchannel_id schid; + struct qdio_irq *irq_ptr; int rc; - DBF_EVENT("qestablish:%4x", cdev->private->schid.sch_no); + ccw_device_get_schid(cdev, &schid); + DBF_EVENT("qestablish:%4x", schid.sch_no); irq_ptr = cdev->private->qdio_data; if (!irq_ptr) return -ENODEV; - if (cdev->private->state != DEV_STATE_ONLINE) - return -EINVAL; - mutex_lock(&irq_ptr->setup_mutex); qdio_setup_irq(init_data); @@ -1361,17 +1368,14 @@ int qdio_establish(struct qdio_initialize *init_data) irq_ptr->ccw.count = irq_ptr->equeue.count; irq_ptr->ccw.cda = (u32)((addr_t)irq_ptr->qdr); - spin_lock_irqsave(get_ccwdev_lock(cdev), saveflags); + spin_lock_irq(get_ccwdev_lock(cdev)); ccw_device_set_options_mask(cdev, 0); rc = ccw_device_start(cdev, &irq_ptr->ccw, QDIO_DOING_ESTABLISH, 0, 0); + spin_unlock_irq(get_ccwdev_lock(cdev)); if (rc) { DBF_ERROR("%4x est IO ERR", irq_ptr->schid.sch_no); DBF_ERROR("rc:%4x", rc); - } - spin_unlock_irqrestore(get_ccwdev_lock(cdev), saveflags); - - if (rc) { mutex_unlock(&irq_ptr->setup_mutex); qdio_shutdown(cdev, QDIO_FLAG_CLEANUP_USING_CLEAR); return rc; @@ -1407,19 +1411,17 @@ EXPORT_SYMBOL_GPL(qdio_establish); */ int qdio_activate(struct ccw_device *cdev) { + struct subchannel_id schid; struct qdio_irq *irq_ptr; int rc; - unsigned long saveflags; - DBF_EVENT("qactivate:%4x", cdev->private->schid.sch_no); + ccw_device_get_schid(cdev, &schid); + DBF_EVENT("qactivate:%4x", schid.sch_no); irq_ptr = cdev->private->qdio_data; if (!irq_ptr) return -ENODEV; - if (cdev->private->state != DEV_STATE_ONLINE) - return -EINVAL; - mutex_lock(&irq_ptr->setup_mutex); if (irq_ptr->state == QDIO_IRQ_STATE_INACTIVE) { rc = -EBUSY; @@ -1431,19 +1433,17 @@ int qdio_activate(struct ccw_device *cdev) irq_ptr->ccw.count = irq_ptr->aqueue.count; irq_ptr->ccw.cda = 0; - spin_lock_irqsave(get_ccwdev_lock(cdev), saveflags); + spin_lock_irq(get_ccwdev_lock(cdev)); ccw_device_set_options(cdev, CCWDEV_REPORT_ALL); rc = ccw_device_start(cdev, &irq_ptr->ccw, QDIO_DOING_ACTIVATE, 0, DOIO_DENY_PREFETCH); + spin_unlock_irq(get_ccwdev_lock(cdev)); if (rc) { DBF_ERROR("%4x act IO ERR", irq_ptr->schid.sch_no); DBF_ERROR("rc:%4x", rc); - } - spin_unlock_irqrestore(get_ccwdev_lock(cdev), saveflags); - - if (rc) goto out; + } if (is_thinint_irq(irq_ptr)) tiqdio_add_input_queues(irq_ptr); @@ -1585,10 +1585,11 @@ static int handle_outbound(struct qdio_q *q, unsigned int callflags, /* in case of SIGA errors we must process the error immediately */ if (used >= q->u.out.scan_threshold || rc) - tasklet_schedule(&q->tasklet); + qdio_tasklet_schedule(q); else /* free the SBALs in case of no further traffic */ - if (!timer_pending(&q->u.out.timer)) + if (!timer_pending(&q->u.out.timer) && + likely(q->irq_ptr->state == QDIO_IRQ_STATE_ACTIVE)) mod_timer(&q->u.out.timer, jiffies + HZ); return rc; } diff --git a/drivers/thermal/clock_cooling.c b/drivers/thermal/clock_cooling.c index 1b4ff0f4c716..ed5dd0e88657 100644 --- a/drivers/thermal/clock_cooling.c +++ b/drivers/thermal/clock_cooling.c @@ -426,6 +426,7 @@ clock_cooling_register(struct device *dev, const char *clock_name) if (!ccdev) return ERR_PTR(-ENOMEM); + mutex_init(&ccdev->lock); ccdev->dev = dev; ccdev->clk = devm_clk_get(dev, clock_name); if (IS_ERR(ccdev->clk)) diff --git a/drivers/thermal/fair_share.c b/drivers/thermal/fair_share.c index 34fe36504a55..68bd1b569118 100644 --- a/drivers/thermal/fair_share.c +++ b/drivers/thermal/fair_share.c @@ -116,7 +116,9 @@ static int fair_share_throttle(struct thermal_zone_device *tz, int trip) instance->target = get_target_state(tz, cdev, percentage, cur_trip_level); + mutex_lock(&instance->cdev->lock); instance->cdev->updated = false; + mutex_unlock(&instance->cdev->lock); thermal_cdev_update(cdev); } return 0; diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c index fc52016d4e85..bb118a152cbb 100644 --- a/drivers/thermal/gov_bang_bang.c +++ b/drivers/thermal/gov_bang_bang.c @@ -71,7 +71,9 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip) dev_dbg(&instance->cdev->device, "target=%d\n", (int)instance->target); + mutex_lock(&instance->cdev->lock); instance->cdev->updated = false; /* cdev needs update */ + mutex_unlock(&instance->cdev->lock); } mutex_unlock(&tz->lock); diff --git a/drivers/thermal/intel_pch_thermal.c b/drivers/thermal/intel_pch_thermal.c index 6a6ec1c95a7a..9b4815e81b0d 100644 --- a/drivers/thermal/intel_pch_thermal.c +++ b/drivers/thermal/intel_pch_thermal.c @@ -21,6 +21,7 @@ #include <linux/init.h> #include <linux/pci.h> #include <linux/thermal.h> +#include <linux/pm.h> /* Intel PCH thermal Device IDs */ #define PCH_THERMAL_DID_WPT 0x9CA4 /* Wildcat Point */ @@ -65,6 +66,7 @@ struct pch_thermal_device { unsigned long crt_temp; int hot_trip_id; unsigned long hot_temp; + bool bios_enabled; }; static int pch_wpt_init(struct pch_thermal_device *ptd, int *nr_trips) @@ -75,8 +77,10 @@ static int pch_wpt_init(struct pch_thermal_device *ptd, int *nr_trips) *nr_trips = 0; /* Check if BIOS has already enabled thermal sensor */ - if (WPT_TSS_TSDSS & readb(ptd->hw_base + WPT_TSS)) + if (WPT_TSS_TSDSS & readb(ptd->hw_base + WPT_TSS)) { + ptd->bios_enabled = true; goto read_trips; + } tsel = readb(ptd->hw_base + WPT_TSEL); /* @@ -130,9 +134,39 @@ static int pch_wpt_get_temp(struct pch_thermal_device *ptd, int *temp) return 0; } +static int pch_wpt_suspend(struct pch_thermal_device *ptd) +{ + u8 tsel; + + if (ptd->bios_enabled) + return 0; + + tsel = readb(ptd->hw_base + WPT_TSEL); + + writeb(tsel & 0xFE, ptd->hw_base + WPT_TSEL); + + return 0; +} + +static int pch_wpt_resume(struct pch_thermal_device *ptd) +{ + u8 tsel; + + if (ptd->bios_enabled) + return 0; + + tsel = readb(ptd->hw_base + WPT_TSEL); + + writeb(tsel | WPT_TSEL_ETS, ptd->hw_base + WPT_TSEL); + + return 0; +} + struct pch_dev_ops { int (*hw_init)(struct pch_thermal_device *ptd, int *nr_trips); int (*get_temp)(struct pch_thermal_device *ptd, int *temp); + int (*suspend)(struct pch_thermal_device *ptd); + int (*resume)(struct pch_thermal_device *ptd); }; @@ -140,6 +174,8 @@ struct pch_dev_ops { static const struct pch_dev_ops pch_dev_ops_wpt = { .hw_init = pch_wpt_init, .get_temp = pch_wpt_get_temp, + .suspend = pch_wpt_suspend, + .resume = pch_wpt_resume, }; static int pch_thermal_get_temp(struct thermal_zone_device *tzd, int *temp) @@ -269,6 +305,22 @@ static void intel_pch_thermal_remove(struct pci_dev *pdev) pci_disable_device(pdev); } +static int intel_pch_thermal_suspend(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct pch_thermal_device *ptd = pci_get_drvdata(pdev); + + return ptd->ops->suspend(ptd); +} + +static int intel_pch_thermal_resume(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct pch_thermal_device *ptd = pci_get_drvdata(pdev); + + return ptd->ops->resume(ptd); +} + static struct pci_device_id intel_pch_thermal_id[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_WPT) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_SKL) }, @@ -276,11 +328,17 @@ static struct pci_device_id intel_pch_thermal_id[] = { }; MODULE_DEVICE_TABLE(pci, intel_pch_thermal_id); +static const struct dev_pm_ops intel_pch_pm_ops = { + .suspend = intel_pch_thermal_suspend, + .resume = intel_pch_thermal_resume, +}; + static struct pci_driver intel_pch_thermal_driver = { .name = "intel_pch_thermal", .id_table = intel_pch_thermal_id, .probe = intel_pch_thermal_probe, .remove = intel_pch_thermal_remove, + .driver.pm = &intel_pch_pm_ops, }; module_pci_driver(intel_pch_thermal_driver); diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c index 015ce2eb6eb7..0e4dc0afcfd2 100644 --- a/drivers/thermal/intel_powerclamp.c +++ b/drivers/thermal/intel_powerclamp.c @@ -388,7 +388,7 @@ static int clamp_thread(void *arg) int sleeptime; unsigned long target_jiffies; unsigned int guard; - unsigned int compensation = 0; + unsigned int compensated_ratio; int interval; /* jiffies to sleep for each attempt */ unsigned int duration_jiffies = msecs_to_jiffies(duration); unsigned int window_size_now; @@ -409,8 +409,11 @@ static int clamp_thread(void *arg) * c-states, thus we need to compensate the injected idle ratio * to achieve the actual target reported by the HW. */ - compensation = get_compensation(target_ratio); - interval = duration_jiffies*100/(target_ratio+compensation); + compensated_ratio = target_ratio + + get_compensation(target_ratio); + if (compensated_ratio <= 0) + compensated_ratio = 1; + interval = duration_jiffies * 100 / compensated_ratio; /* align idle time */ target_jiffies = roundup(jiffies, interval); @@ -647,8 +650,8 @@ static int powerclamp_set_cur_state(struct thermal_cooling_device *cdev, goto exit_set; } else if (set_target_ratio > 0 && new_target_ratio == 0) { pr_info("Stop forced idle injection\n"); - set_target_ratio = 0; end_power_clamp(); + set_target_ratio = 0; } else /* adjust currently running */ { set_target_ratio = new_target_ratio; /* make new set_target_ratio visible to other cpus */ diff --git a/drivers/thermal/power_allocator.c b/drivers/thermal/power_allocator.c index 2f1a863a8e15..b4d3116cfdaf 100644 --- a/drivers/thermal/power_allocator.c +++ b/drivers/thermal/power_allocator.c @@ -529,7 +529,9 @@ static void allow_maximum_power(struct thermal_zone_device *tz) continue; instance->target = 0; + mutex_lock(&instance->cdev->lock); instance->cdev->updated = false; + mutex_unlock(&instance->cdev->lock); thermal_cdev_update(instance->cdev); } } diff --git a/drivers/thermal/step_wise.c b/drivers/thermal/step_wise.c index ea9366ad3e6b..bcef2e7c4ec9 100644 --- a/drivers/thermal/step_wise.c +++ b/drivers/thermal/step_wise.c @@ -175,7 +175,9 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip) update_passive_instance(tz, trip_type, -1); instance->initialized = true; + mutex_lock(&instance->cdev->lock); instance->cdev->updated = false; /* cdev needs update */ + mutex_unlock(&instance->cdev->lock); } mutex_unlock(&tz->lock); diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 5133cd1e10b7..e2fc6161dded 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1093,7 +1093,9 @@ int power_actor_set_power(struct thermal_cooling_device *cdev, return ret; instance->target = state; + mutex_lock(&cdev->lock); cdev->updated = false; + mutex_unlock(&cdev->lock); thermal_cdev_update(cdev); return 0; @@ -1623,11 +1625,13 @@ void thermal_cdev_update(struct thermal_cooling_device *cdev) struct thermal_instance *instance; unsigned long target = 0; + mutex_lock(&cdev->lock); /* cooling device is updated*/ - if (cdev->updated) + if (cdev->updated) { + mutex_unlock(&cdev->lock); return; + } - mutex_lock(&cdev->lock); /* Make sure cdev enters the deepest cooling state */ list_for_each_entry(instance, &cdev->thermal_instances, cdev_node) { dev_dbg(&cdev->device, "zone%d->target=%lu\n", @@ -1637,9 +1641,9 @@ void thermal_cdev_update(struct thermal_cooling_device *cdev) if (instance->target > target) target = instance->target; } - mutex_unlock(&cdev->lock); cdev->ops->set_cur_state(cdev, target); cdev->updated = true; + mutex_unlock(&cdev->lock); trace_cdev_update(cdev, target); dev_dbg(&cdev->device, "set to state %lu\n", target); } diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c index 06fd2ed9ef9d..c41c7742903a 100644 --- a/drivers/thermal/thermal_hwmon.c +++ b/drivers/thermal/thermal_hwmon.c @@ -232,6 +232,7 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz) return result; } +EXPORT_SYMBOL_GPL(thermal_add_hwmon_sysfs); void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz) { @@ -270,3 +271,4 @@ void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz) hwmon_device_unregister(hwmon->device); kfree(hwmon); } +EXPORT_SYMBOL_GPL(thermal_remove_hwmon_sysfs); diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 15ecfc9c5f6c..152b43822ef1 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -564,67 +564,80 @@ static int vfio_pci_set_msi_trigger(struct vfio_pci_device *vdev, } static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx, - uint32_t flags, void *data) + unsigned int count, uint32_t flags, + void *data) { - int32_t fd = *(int32_t *)data; - - if (!(flags & VFIO_IRQ_SET_DATA_TYPE_MASK)) - return -EINVAL; - /* DATA_NONE/DATA_BOOL enables loopback testing */ if (flags & VFIO_IRQ_SET_DATA_NONE) { - if (*ctx) - eventfd_signal(*ctx, 1); - return 0; + if (*ctx) { + if (count) { + eventfd_signal(*ctx, 1); + } else { + eventfd_ctx_put(*ctx); + *ctx = NULL; + } + return 0; + } } else if (flags & VFIO_IRQ_SET_DATA_BOOL) { - uint8_t trigger = *(uint8_t *)data; + uint8_t trigger; + + if (!count) + return -EINVAL; + + trigger = *(uint8_t *)data; if (trigger && *ctx) eventfd_signal(*ctx, 1); - return 0; - } - /* Handle SET_DATA_EVENTFD */ - if (fd == -1) { - if (*ctx) - eventfd_ctx_put(*ctx); - *ctx = NULL; return 0; - } else if (fd >= 0) { - struct eventfd_ctx *efdctx; - efdctx = eventfd_ctx_fdget(fd); - if (IS_ERR(efdctx)) - return PTR_ERR(efdctx); - if (*ctx) - eventfd_ctx_put(*ctx); - *ctx = efdctx; + } else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { + int32_t fd; + + if (!count) + return -EINVAL; + + fd = *(int32_t *)data; + if (fd == -1) { + if (*ctx) + eventfd_ctx_put(*ctx); + *ctx = NULL; + } else if (fd >= 0) { + struct eventfd_ctx *efdctx; + + efdctx = eventfd_ctx_fdget(fd); + if (IS_ERR(efdctx)) + return PTR_ERR(efdctx); + + if (*ctx) + eventfd_ctx_put(*ctx); + + *ctx = efdctx; + } return 0; - } else - return -EINVAL; + } + + return -EINVAL; } static int vfio_pci_set_err_trigger(struct vfio_pci_device *vdev, unsigned index, unsigned start, unsigned count, uint32_t flags, void *data) { - if (index != VFIO_PCI_ERR_IRQ_INDEX) + if (index != VFIO_PCI_ERR_IRQ_INDEX || start != 0 || count > 1) return -EINVAL; - /* - * We should sanitize start & count, but that wasn't caught - * originally, so this IRQ index must forever ignore them :-( - */ - - return vfio_pci_set_ctx_trigger_single(&vdev->err_trigger, flags, data); + return vfio_pci_set_ctx_trigger_single(&vdev->err_trigger, + count, flags, data); } static int vfio_pci_set_req_trigger(struct vfio_pci_device *vdev, unsigned index, unsigned start, unsigned count, uint32_t flags, void *data) { - if (index != VFIO_PCI_REQ_IRQ_INDEX || start != 0 || count != 1) + if (index != VFIO_PCI_REQ_IRQ_INDEX || start != 0 || count > 1) return -EINVAL; - return vfio_pci_set_ctx_trigger_single(&vdev->req_trigger, flags, data); + return vfio_pci_set_ctx_trigger_single(&vdev->req_trigger, + count, flags, data); } int vfio_pci_set_irqs_ioctl(struct vfio_pci_device *vdev, uint32_t flags, diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c index 388eec4e1a90..97fb2f8fa930 100644 --- a/drivers/vhost/test.c +++ b/drivers/vhost/test.c @@ -220,20 +220,20 @@ static long vhost_test_reset_owner(struct vhost_test *n) { void *priv = NULL; long err; - struct vhost_memory *memory; + struct vhost_umem *umem; mutex_lock(&n->dev.mutex); err = vhost_dev_check_owner(&n->dev); if (err) goto done; - memory = vhost_dev_reset_owner_prepare(); - if (!memory) { + umem = vhost_dev_reset_owner_prepare(); + if (!umem) { err = -ENOMEM; goto done; } vhost_test_stop(n, &priv); vhost_test_flush(n); - vhost_dev_reset_owner(&n->dev, memory); + vhost_dev_reset_owner(&n->dev, umem); done: mutex_unlock(&n->dev.mutex); return err; diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 4b0eff6da674..85737e96ab8b 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -189,11 +189,8 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb, case 1: _debug("extract FID count"); ret = afs_extract_data(call, skb, last, &call->tmp, 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; call->count = ntohl(call->tmp); _debug("FID count: %u", call->count); @@ -210,11 +207,8 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb, _debug("extract FID array"); ret = afs_extract_data(call, skb, last, call->buffer, call->count * 3 * 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; _debug("unmarshall FID array"); call->request = kcalloc(call->count, @@ -239,11 +233,8 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb, case 3: _debug("extract CB count"); ret = afs_extract_data(call, skb, last, &call->tmp, 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; tmp = ntohl(call->tmp); _debug("CB count: %u", tmp); @@ -258,11 +249,8 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb, _debug("extract CB array"); ret = afs_extract_data(call, skb, last, call->request, call->count * 3 * 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; _debug("unmarshall CB array"); cb = call->request; @@ -278,9 +266,9 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb, call->unmarshall++; case 5: - _debug("trailer"); - if (skb->len != 0) - return -EBADMSG; + ret = afs_data_complete(call, skb, last); + if (ret < 0) + return ret; /* Record that the message was unmarshalled successfully so * that the call destructor can know do the callback breaking @@ -294,8 +282,6 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb, break; } - if (!last) - return 0; call->state = AFS_CALL_REPLYING; @@ -335,13 +321,13 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call, { struct afs_server *server; struct in_addr addr; + int ret; _enter(",{%u},%d", skb->len, last); - if (skb->len > 0) - return -EBADMSG; - if (!last) - return 0; + ret = afs_data_complete(call, skb, last); + if (ret < 0) + return ret; /* no unmarshalling required */ call->state = AFS_CALL_REPLYING; @@ -371,8 +357,10 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call, _enter(",{%u},%d", skb->len, last); + /* There are some arguments that we ignore */ + afs_data_consumed(call, skb); if (!last) - return 0; + return -EAGAIN; /* no unmarshalling required */ call->state = AFS_CALL_REPLYING; @@ -408,12 +396,13 @@ static void SRXAFSCB_Probe(struct work_struct *work) static int afs_deliver_cb_probe(struct afs_call *call, struct sk_buff *skb, bool last) { + int ret; + _enter(",{%u},%d", skb->len, last); - if (skb->len > 0) - return -EBADMSG; - if (!last) - return 0; + ret = afs_data_complete(call, skb, last); + if (ret < 0) + return ret; /* no unmarshalling required */ call->state = AFS_CALL_REPLYING; @@ -460,10 +449,9 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call, struct sk_buff *skb, _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); - if (skb->len > 0) - return -EBADMSG; - if (!last) - return 0; + ret = afs_data_complete(call, skb, last); + if (ret < 0) + return ret; switch (call->unmarshall) { case 0: @@ -509,8 +497,9 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call, struct sk_buff *skb, break; } - if (!last) - return 0; + ret = afs_data_complete(call, skb, last); + if (ret < 0) + return ret; call->state = AFS_CALL_REPLYING; @@ -588,12 +577,13 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work) static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *call, struct sk_buff *skb, bool last) { + int ret; + _enter(",{%u},%d", skb->len, last); - if (skb->len > 0) - return -EBADMSG; - if (!last) - return 0; + ret = afs_data_complete(call, skb, last); + if (ret < 0) + return ret; /* no unmarshalling required */ call->state = AFS_CALL_REPLYING; diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index c2e930ec2888..9312b92e54be 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -240,15 +240,13 @@ static int afs_deliver_fs_fetch_status(struct afs_call *call, { struct afs_vnode *vnode = call->reply; const __be32 *bp; + int ret; _enter(",,%u", last); - afs_transfer_reply(call, skb); - if (!last) - return 0; - - if (call->reply_size != call->reply_max) - return -EBADMSG; + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; @@ -335,11 +333,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call, case 1: _debug("extract data length (MSW)"); ret = afs_extract_data(call, skb, last, &call->tmp, 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; call->count = ntohl(call->tmp); _debug("DATA length MSW: %u", call->count); @@ -353,11 +348,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call, case 2: _debug("extract data length"); ret = afs_extract_data(call, skb, last, &call->tmp, 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; call->count = ntohl(call->tmp); _debug("DATA length: %u", call->count); @@ -375,11 +367,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call, ret = afs_extract_data(call, skb, last, buffer, call->count); kunmap_atomic(buffer); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; } call->offset = 0; @@ -389,11 +378,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call, case 4: ret = afs_extract_data(call, skb, last, call->buffer, (21 + 3 + 6) * 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; bp = call->buffer; xdr_decode_AFSFetchStatus(&bp, &vnode->status, vnode, NULL); @@ -405,15 +391,12 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call, call->unmarshall++; case 5: - _debug("trailer"); - if (skb->len != 0) - return -EBADMSG; + ret = afs_data_complete(call, skb, last); + if (ret < 0) + return ret; break; } - if (!last) - return 0; - if (call->count < PAGE_SIZE) { _debug("clear"); page = call->reply3; @@ -537,9 +520,8 @@ static int afs_deliver_fs_give_up_callbacks(struct afs_call *call, { _enter(",{%u},%d", skb->len, last); - if (skb->len > 0) - return -EBADMSG; /* shouldn't be any reply data */ - return 0; + /* shouldn't be any reply data */ + return afs_data_complete(call, skb, last); } /* @@ -622,15 +604,13 @@ static int afs_deliver_fs_create_vnode(struct afs_call *call, { struct afs_vnode *vnode = call->reply; const __be32 *bp; + int ret; _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); - afs_transfer_reply(call, skb); - if (!last) - return 0; - - if (call->reply_size != call->reply_max) - return -EBADMSG; + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; @@ -721,15 +701,13 @@ static int afs_deliver_fs_remove(struct afs_call *call, { struct afs_vnode *vnode = call->reply; const __be32 *bp; + int ret; _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); - afs_transfer_reply(call, skb); - if (!last) - return 0; - - if (call->reply_size != call->reply_max) - return -EBADMSG; + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; @@ -804,15 +782,13 @@ static int afs_deliver_fs_link(struct afs_call *call, { struct afs_vnode *dvnode = call->reply, *vnode = call->reply2; const __be32 *bp; + int ret; _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); - afs_transfer_reply(call, skb); - if (!last) - return 0; - - if (call->reply_size != call->reply_max) - return -EBADMSG; + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; @@ -892,15 +868,13 @@ static int afs_deliver_fs_symlink(struct afs_call *call, { struct afs_vnode *vnode = call->reply; const __be32 *bp; + int ret; _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); - afs_transfer_reply(call, skb); - if (!last) - return 0; - - if (call->reply_size != call->reply_max) - return -EBADMSG; + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; @@ -999,15 +973,13 @@ static int afs_deliver_fs_rename(struct afs_call *call, { struct afs_vnode *orig_dvnode = call->reply, *new_dvnode = call->reply2; const __be32 *bp; + int ret; _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); - afs_transfer_reply(call, skb); - if (!last) - return 0; - - if (call->reply_size != call->reply_max) - return -EBADMSG; + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; @@ -1105,20 +1077,13 @@ static int afs_deliver_fs_store_data(struct afs_call *call, { struct afs_vnode *vnode = call->reply; const __be32 *bp; + int ret; _enter(",,%u", last); - afs_transfer_reply(call, skb); - if (!last) { - _leave(" = 0 [more]"); - return 0; - } - - if (call->reply_size != call->reply_max) { - _leave(" = -EBADMSG [%u != %u]", - call->reply_size, call->reply_max); - return -EBADMSG; - } + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; @@ -1292,20 +1257,13 @@ static int afs_deliver_fs_store_status(struct afs_call *call, afs_dataversion_t *store_version; struct afs_vnode *vnode = call->reply; const __be32 *bp; + int ret; _enter(",,%u", last); - afs_transfer_reply(call, skb); - if (!last) { - _leave(" = 0 [more]"); - return 0; - } - - if (call->reply_size != call->reply_max) { - _leave(" = -EBADMSG [%u != %u]", - call->reply_size, call->reply_max); - return -EBADMSG; - } + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ store_version = NULL; @@ -1504,11 +1462,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, _debug("extract status"); ret = afs_extract_data(call, skb, last, call->buffer, 12 * 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; bp = call->buffer; xdr_decode_AFSFetchVolumeStatus(&bp, call->reply2); @@ -1518,11 +1473,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, /* extract the volume name length */ case 2: ret = afs_extract_data(call, skb, last, &call->tmp, 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; call->count = ntohl(call->tmp); _debug("volname length: %u", call->count); @@ -1537,11 +1489,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, if (call->count > 0) { ret = afs_extract_data(call, skb, last, call->reply3, call->count); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; } p = call->reply3; @@ -1561,11 +1510,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, case 4: ret = afs_extract_data(call, skb, last, call->buffer, call->count); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; call->offset = 0; call->unmarshall++; @@ -1574,11 +1520,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, /* extract the offline message length */ case 5: ret = afs_extract_data(call, skb, last, &call->tmp, 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; call->count = ntohl(call->tmp); _debug("offline msg length: %u", call->count); @@ -1593,11 +1536,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, if (call->count > 0) { ret = afs_extract_data(call, skb, last, call->reply3, call->count); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; } p = call->reply3; @@ -1617,11 +1557,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, case 7: ret = afs_extract_data(call, skb, last, call->buffer, call->count); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; call->offset = 0; call->unmarshall++; @@ -1630,11 +1567,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, /* extract the message of the day length */ case 8: ret = afs_extract_data(call, skb, last, &call->tmp, 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; call->count = ntohl(call->tmp); _debug("motd length: %u", call->count); @@ -1649,11 +1583,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, if (call->count > 0) { ret = afs_extract_data(call, skb, last, call->reply3, call->count); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; } p = call->reply3; @@ -1673,26 +1604,20 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, case 10: ret = afs_extract_data(call, skb, last, call->buffer, call->count); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; call->offset = 0; call->unmarshall++; no_motd_padding: case 11: - _debug("trailer %d", skb->len); - if (skb->len != 0) - return -EBADMSG; + ret = afs_data_complete(call, skb, last); + if (ret < 0) + return ret; break; } - if (!last) - return 0; - _leave(" = 0 [done]"); return 0; } @@ -1764,15 +1689,13 @@ static int afs_deliver_fs_xxxx_lock(struct afs_call *call, struct sk_buff *skb, bool last) { const __be32 *bp; + int ret; _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); - afs_transfer_reply(call, skb); - if (!last) - return 0; - - if (call->reply_size != call->reply_max) - return -EBADMSG; + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 71d5982312f3..df976b2a7f40 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -609,17 +609,29 @@ extern void afs_proc_cell_remove(struct afs_cell *); */ extern int afs_open_socket(void); extern void afs_close_socket(void); +extern void afs_data_consumed(struct afs_call *, struct sk_buff *); extern int afs_make_call(struct in_addr *, struct afs_call *, gfp_t, const struct afs_wait_mode *); extern struct afs_call *afs_alloc_flat_call(const struct afs_call_type *, size_t, size_t); extern void afs_flat_call_destructor(struct afs_call *); -extern void afs_transfer_reply(struct afs_call *, struct sk_buff *); +extern int afs_transfer_reply(struct afs_call *, struct sk_buff *, bool); extern void afs_send_empty_reply(struct afs_call *); extern void afs_send_simple_reply(struct afs_call *, const void *, size_t); extern int afs_extract_data(struct afs_call *, struct sk_buff *, bool, void *, size_t); +static inline int afs_data_complete(struct afs_call *call, struct sk_buff *skb, + bool last) +{ + if (skb->len > 0) + return -EBADMSG; + afs_data_consumed(call, skb); + if (!last) + return -EAGAIN; + return 0; +} + /* * security.c */ diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 4832de84d52c..14d04c848465 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -150,10 +150,9 @@ void afs_close_socket(void) } /* - * note that the data in a socket buffer is now delivered and that the buffer - * should be freed + * Note that the data in a socket buffer is now consumed. */ -static void afs_data_delivered(struct sk_buff *skb) +void afs_data_consumed(struct afs_call *call, struct sk_buff *skb) { if (!skb) { _debug("DLVR NULL [%d]", atomic_read(&afs_outstanding_skbs)); @@ -161,9 +160,7 @@ static void afs_data_delivered(struct sk_buff *skb) } else { _debug("DLVR %p{%u} [%d]", skb, skb->mark, atomic_read(&afs_outstanding_skbs)); - if (atomic_dec_return(&afs_outstanding_skbs) == -1) - BUG(); - rxrpc_kernel_data_delivered(skb); + rxrpc_kernel_data_consumed(call->rxcall, skb); } } @@ -489,9 +486,15 @@ static void afs_deliver_to_call(struct afs_call *call) last = rxrpc_kernel_is_data_last(skb); ret = call->type->deliver(call, skb, last); switch (ret) { + case -EAGAIN: + if (last) { + _debug("short data"); + goto unmarshal_error; + } + break; case 0: - if (last && - call->state == AFS_CALL_AWAIT_REPLY) + ASSERT(last); + if (call->state == AFS_CALL_AWAIT_REPLY) call->state = AFS_CALL_COMPLETE; break; case -ENOTCONN: @@ -501,6 +504,7 @@ static void afs_deliver_to_call(struct afs_call *call) abort_code = RX_INVALID_OPERATION; goto do_abort; default: + unmarshal_error: abort_code = RXGEN_CC_UNMARSHAL; if (call->state != AFS_CALL_AWAIT_REPLY) abort_code = RXGEN_SS_UNMARSHAL; @@ -511,9 +515,7 @@ static void afs_deliver_to_call(struct afs_call *call) call->state = AFS_CALL_ERROR; break; } - afs_data_delivered(skb); - skb = NULL; - continue; + break; case RXRPC_SKB_MARK_FINAL_ACK: _debug("Rcv ACK"); call->state = AFS_CALL_COMPLETE; @@ -685,15 +687,35 @@ static void afs_process_async_call(struct afs_call *call) } /* - * empty a socket buffer into a flat reply buffer + * Empty a socket buffer into a flat reply buffer. */ -void afs_transfer_reply(struct afs_call *call, struct sk_buff *skb) +int afs_transfer_reply(struct afs_call *call, struct sk_buff *skb, bool last) { size_t len = skb->len; - if (skb_copy_bits(skb, 0, call->buffer + call->reply_size, len) < 0) - BUG(); - call->reply_size += len; + if (len > call->reply_max - call->reply_size) { + _leave(" = -EBADMSG [%zu > %u]", + len, call->reply_max - call->reply_size); + return -EBADMSG; + } + + if (len > 0) { + if (skb_copy_bits(skb, 0, call->buffer + call->reply_size, + len) < 0) + BUG(); + call->reply_size += len; + } + + afs_data_consumed(call, skb); + if (!last) + return -EAGAIN; + + if (call->reply_size != call->reply_max) { + _leave(" = -EBADMSG [%u != %u]", + call->reply_size, call->reply_max); + return -EBADMSG; + } + return 0; } /* @@ -745,7 +767,8 @@ static void afs_collect_incoming_call(struct work_struct *work) } /* - * grab the operation ID from an incoming cache manager call + * Grab the operation ID from an incoming cache manager call. The socket + * buffer is discarded on error or if we don't yet have sufficient data. */ static int afs_deliver_cm_op_id(struct afs_call *call, struct sk_buff *skb, bool last) @@ -766,12 +789,9 @@ static int afs_deliver_cm_op_id(struct afs_call *call, struct sk_buff *skb, call->offset += len; if (call->offset < 4) { - if (last) { - _leave(" = -EBADMSG [op ID short]"); - return -EBADMSG; - } - _leave(" = 0 [incomplete]"); - return 0; + afs_data_consumed(call, skb); + _leave(" = -EAGAIN"); + return -EAGAIN; } call->state = AFS_CALL_AWAIT_REQUEST; @@ -855,7 +875,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) } /* - * extract a piece of data from the received data socket buffers + * Extract a piece of data from the received data socket buffers. */ int afs_extract_data(struct afs_call *call, struct sk_buff *skb, bool last, void *buf, size_t count) @@ -873,10 +893,7 @@ int afs_extract_data(struct afs_call *call, struct sk_buff *skb, call->offset += len; if (call->offset < count) { - if (last) { - _leave(" = -EBADMSG [%d < %zu]", call->offset, count); - return -EBADMSG; - } + afs_data_consumed(call, skb); _leave(" = -EAGAIN"); return -EAGAIN; } diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index 340afd0cd182..f94d1abdc3eb 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -64,16 +64,13 @@ static int afs_deliver_vl_get_entry_by_xxx(struct afs_call *call, struct afs_cache_vlocation *entry; __be32 *bp; u32 tmp; - int loop; + int loop, ret; _enter(",,%u", last); - afs_transfer_reply(call, skb); - if (!last) - return 0; - - if (call->reply_size != call->reply_max) - return -EBADMSG; + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ entry = call->reply; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 4d09d4441e3e..05713a5da083 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1949,6 +1949,12 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason) { struct backing_dev_info *bdi; + /* + * If we are expecting writeback progress we must submit plugged IO. + */ + if (blk_needs_flush_plug(current)) + blk_schedule_flush_plug(current); + if (!nr_pages) nr_pages = get_nr_dirty_pages(); diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 33da841a21bb..6f4752734804 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -338,6 +338,8 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata) case 0: break; case -NFS4ERR_EXPIRED: + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_DELEG_REVOKED: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_OLD_STATEID: case -NFS4ERR_BAD_STATEID: diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 324bfdc21250..9bf64eacba5b 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -396,6 +396,10 @@ extern void nfs4_schedule_state_renewal(struct nfs_client *); extern void nfs4_renewd_prepare_shutdown(struct nfs_server *); extern void nfs4_kill_renewd(struct nfs_client *); extern void nfs4_renew_state(struct work_struct *); +extern void nfs4_set_lease_period(struct nfs_client *clp, + unsigned long lease, + unsigned long lastrenewed); + /* nfs4state.c */ struct rpc_cred *nfs4_get_clid_cred(struct nfs_client *clp); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index a036e93bdf96..1949bbd806eb 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -4237,12 +4237,9 @@ static int nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, str err = _nfs4_do_fsinfo(server, fhandle, fsinfo); trace_nfs4_fsinfo(server, fhandle, fsinfo->fattr, err); if (err == 0) { - struct nfs_client *clp = server->nfs_client; - - spin_lock(&clp->cl_lock); - clp->cl_lease_time = fsinfo->lease_time * HZ; - clp->cl_last_renewal = now; - spin_unlock(&clp->cl_lock); + nfs4_set_lease_period(server->nfs_client, + fsinfo->lease_time * HZ, + now); break; } err = nfs4_handle_exception(server, err, &exception); diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c index e1ba58c3d1ad..82e77198d17e 100644 --- a/fs/nfs/nfs4renewd.c +++ b/fs/nfs/nfs4renewd.c @@ -136,6 +136,26 @@ nfs4_kill_renewd(struct nfs_client *clp) cancel_delayed_work_sync(&clp->cl_renewd); } +/** + * nfs4_set_lease_period - Sets the lease period on a nfs_client + * + * @clp: pointer to nfs_client + * @lease: new value for lease period + * @lastrenewed: time at which lease was last renewed + */ +void nfs4_set_lease_period(struct nfs_client *clp, + unsigned long lease, + unsigned long lastrenewed) +{ + spin_lock(&clp->cl_lock); + clp->cl_lease_time = lease; + clp->cl_last_renewal = lastrenewed; + spin_unlock(&clp->cl_lock); + + /* Cap maximum reconnect timeout at 1/2 lease period */ + rpc_cap_max_reconnect_timeout(clp->cl_rpcclient, lease >> 1); +} + /* * Local variables: * c-basic-offset: 8 diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 834b875900d6..cada00aa5096 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -277,20 +277,17 @@ static int nfs41_setup_state_renewal(struct nfs_client *clp) { int status; struct nfs_fsinfo fsinfo; + unsigned long now; if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) { nfs4_schedule_state_renewal(clp); return 0; } + now = jiffies; status = nfs4_proc_get_lease_time(clp, &fsinfo); if (status == 0) { - /* Update lease time and schedule renewal */ - spin_lock(&clp->cl_lock); - clp->cl_lease_time = fsinfo.lease_time * HZ; - clp->cl_last_renewal = jiffies; - spin_unlock(&clp->cl_lock); - + nfs4_set_lease_period(clp, fsinfo.lease_time * HZ, now); nfs4_schedule_state_renewal(clp); } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 8410ca275db1..a204d7e109d4 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4903,6 +4903,32 @@ nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfs_ok; } +static __be32 +nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s) +{ + struct nfs4_ol_stateid *stp = openlockstateid(s); + __be32 ret; + + mutex_lock(&stp->st_mutex); + + ret = check_stateid_generation(stateid, &s->sc_stateid, 1); + if (ret) + goto out; + + ret = nfserr_locks_held; + if (check_for_locks(stp->st_stid.sc_file, + lockowner(stp->st_stateowner))) + goto out; + + release_lock_stateid(stp); + ret = nfs_ok; + +out: + mutex_unlock(&stp->st_mutex); + nfs4_put_stid(s); + return ret; +} + __be32 nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_free_stateid *free_stateid) @@ -4910,7 +4936,6 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stateid_t *stateid = &free_stateid->fr_stateid; struct nfs4_stid *s; struct nfs4_delegation *dp; - struct nfs4_ol_stateid *stp; struct nfs4_client *cl = cstate->session->se_client; __be32 ret = nfserr_bad_stateid; @@ -4929,18 +4954,9 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, ret = nfserr_locks_held; break; case NFS4_LOCK_STID: - ret = check_stateid_generation(stateid, &s->sc_stateid, 1); - if (ret) - break; - stp = openlockstateid(s); - ret = nfserr_locks_held; - if (check_for_locks(stp->st_stid.sc_file, - lockowner(stp->st_stateowner))) - break; - WARN_ON(!unhash_lock_stateid(stp)); + atomic_inc(&s->sc_count); spin_unlock(&cl->cl_lock); - nfs4_put_stid(s); - ret = nfs_ok; + ret = nfsd4_free_lock_stateid(stateid, s); goto out; case NFS4_REVOKED_DELEG_STID: dp = delegstateid(s); @@ -5507,7 +5523,7 @@ static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, struct nfs4_ol_stateid *ost, struct nfsd4_lock *lock, - struct nfs4_ol_stateid **lst, bool *new) + struct nfs4_ol_stateid **plst, bool *new) { __be32 status; struct nfs4_file *fi = ost->st_stid.sc_file; @@ -5515,7 +5531,9 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, struct nfs4_client *cl = oo->oo_owner.so_client; struct inode *inode = d_inode(cstate->current_fh.fh_dentry); struct nfs4_lockowner *lo; + struct nfs4_ol_stateid *lst; unsigned int strhashval; + bool hashed; lo = find_lockowner_str(cl, &lock->lk_new_owner); if (!lo) { @@ -5531,12 +5549,27 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, goto out; } - *lst = find_or_create_lock_stateid(lo, fi, inode, ost, new); - if (*lst == NULL) { +retry: + lst = find_or_create_lock_stateid(lo, fi, inode, ost, new); + if (lst == NULL) { status = nfserr_jukebox; goto out; } + + mutex_lock(&lst->st_mutex); + + /* See if it's still hashed to avoid race with FREE_STATEID */ + spin_lock(&cl->cl_lock); + hashed = !list_empty(&lst->st_perfile); + spin_unlock(&cl->cl_lock); + + if (!hashed) { + mutex_unlock(&lst->st_mutex); + nfs4_put_stid(&lst->st_stid); + goto retry; + } status = nfs_ok; + *plst = lst; out: nfs4_put_stateowner(&lo->lo_owner); return status; @@ -5603,8 +5636,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; status = lookup_or_create_lock_state(cstate, open_stp, lock, &lock_stp, &new); - if (status == nfs_ok) - mutex_lock(&lock_stp->st_mutex); } else { status = nfs4_preprocess_seqid_op(cstate, lock->lk_old_lock_seqid, diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index ba944123167b..ff476e654b8f 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1252,10 +1252,13 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, if (IS_ERR(dchild)) return nfserrno(host_err); err = fh_compose(resfhp, fhp->fh_export, dchild, fhp); - if (err) { - dput(dchild); + /* + * We unconditionally drop our ref to dchild as fh_compose will have + * already grabbed its own ref for it. + */ + dput(dchild); + if (err) return err; - } return nfsd_create_locked(rqstp, fhp, fname, flen, iap, type, rdev, resfhp); } diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h index 54a8e65e18b6..7d026bf27713 100644 --- a/include/asm-generic/qrwlock.h +++ b/include/asm-generic/qrwlock.h @@ -25,7 +25,20 @@ #include <asm-generic/qrwlock_types.h> /* - * Writer states & reader shift and bias + * Writer states & reader shift and bias. + * + * | +0 | +1 | +2 | +3 | + * ----+----+----+----+----+ + * LE | 78 | 56 | 34 | 12 | 0x12345678 + * ----+----+----+----+----+ + * | wr | rd | + * +----+----+----+----+ + * + * ----+----+----+----+----+ + * BE | 12 | 34 | 56 | 78 | 0x12345678 + * ----+----+----+----+----+ + * | rd | wr | + * +----+----+----+----+ */ #define _QW_WAITING 1 /* A writer is waiting */ #define _QW_LOCKED 0xff /* A writer holds the lock */ @@ -134,12 +147,22 @@ static inline void queued_read_unlock(struct qrwlock *lock) } /** + * __qrwlock_write_byte - retrieve the write byte address of a queue rwlock + * @lock : Pointer to queue rwlock structure + * Return: the write byte address of a queue rwlock + */ +static inline u8 *__qrwlock_write_byte(struct qrwlock *lock) +{ + return (u8 *)lock + 3 * IS_BUILTIN(CONFIG_CPU_BIG_ENDIAN); +} + +/** * queued_write_unlock - release write lock of a queue rwlock * @lock : Pointer to queue rwlock structure */ static inline void queued_write_unlock(struct qrwlock *lock) { - smp_store_release((u8 *)&lock->cnts, 0); + smp_store_release(__qrwlock_write_byte(lock), 0); } /* diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 701b64a3b7c5..89b65b82d98f 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -74,7 +74,8 @@ static inline void bvec_iter_advance(const struct bio_vec *bv, "Attempted to advance past end of bvec iter\n"); while (bytes) { - unsigned len = min(bytes, bvec_iter_len(bv, *iter)); + unsigned iter_len = bvec_iter_len(bv, *iter); + unsigned len = min(bytes, iter_len); bytes -= len; iter->bi_size -= len; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 01e908ac4a39..9c28b4d4c90b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1113,9 +1113,21 @@ struct kvm_device { /* create, destroy, and name are mandatory */ struct kvm_device_ops { const char *name; + + /* + * create is called holding kvm->lock and any operations not suitable + * to do while holding the lock should be deferred to init (see + * below). + */ int (*create)(struct kvm_device *dev, u32 type); /* + * init is called after create if create is successful and is called + * outside of holding kvm->lock. + */ + void (*init)(struct kvm_device *dev); + + /* * Destroy is responsible for freeing dev. * * Destroy may be called before or after destructors are called diff --git a/include/linux/msi.h b/include/linux/msi.h index 4f0bfe5912b2..e8c81fbd5f9c 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -270,6 +270,8 @@ enum { MSI_FLAG_MULTI_PCI_MSI = (1 << 2), /* Support PCI MSIX interrupts */ MSI_FLAG_PCI_MSIX = (1 << 3), + /* Needs early activate, required for PCI */ + MSI_FLAG_ACTIVATE_EARLY = (1 << 4), }; int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 076df5360ba5..3a788bf0affd 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3891,8 +3891,7 @@ void netdev_default_l2upper_neigh_destroy(struct net_device *dev, extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly; void netdev_rss_key_fill(void *buffer, size_t len); -int dev_get_nest_level(struct net_device *dev, - bool (*type_check)(const struct net_device *dev)); +int dev_get_nest_level(struct net_device *dev); int skb_checksum_help(struct sk_buff *skb); struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 8ed4326164cc..2b6b43cc0dd5 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -743,7 +743,9 @@ struct perf_event_context { u64 parent_gen; u64 generation; int pin_count; +#ifdef CONFIG_CGROUP_PERF int nr_cgroups; /* cgroup evts */ +#endif void *task_ctx_data; /* pmu specific data */ struct rcu_head rcu_head; }; @@ -769,7 +771,9 @@ struct perf_cpu_context { unsigned int hrtimer_active; struct pmu *unique_pmu; +#ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; +#endif }; struct perf_output_handle { diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index b1e3c57c7117..d6c4177df7cb 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -70,8 +70,16 @@ struct qed_dbcx_pfc_params { u8 max_tc; }; +enum qed_dcbx_sf_ieee_type { + QED_DCBX_SF_IEEE_ETHTYPE, + QED_DCBX_SF_IEEE_TCP_PORT, + QED_DCBX_SF_IEEE_UDP_PORT, + QED_DCBX_SF_IEEE_TCP_UDP_PORT +}; + struct qed_app_entry { bool ethtype; + enum qed_dcbx_sf_ieee_type sf_ieee; bool enabled; u8 prio; u16 proto_id; diff --git a/include/linux/sctp.h b/include/linux/sctp.h index de1f64318fc4..fcb4c3646173 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -705,70 +705,6 @@ typedef struct sctp_auth_chunk { sctp_authhdr_t auth_hdr; } __packed sctp_auth_chunk_t; -struct sctp_info { - __u32 sctpi_tag; - __u32 sctpi_state; - __u32 sctpi_rwnd; - __u16 sctpi_unackdata; - __u16 sctpi_penddata; - __u16 sctpi_instrms; - __u16 sctpi_outstrms; - __u32 sctpi_fragmentation_point; - __u32 sctpi_inqueue; - __u32 sctpi_outqueue; - __u32 sctpi_overall_error; - __u32 sctpi_max_burst; - __u32 sctpi_maxseg; - __u32 sctpi_peer_rwnd; - __u32 sctpi_peer_tag; - __u8 sctpi_peer_capable; - __u8 sctpi_peer_sack; - __u16 __reserved1; - - /* assoc status info */ - __u64 sctpi_isacks; - __u64 sctpi_osacks; - __u64 sctpi_opackets; - __u64 sctpi_ipackets; - __u64 sctpi_rtxchunks; - __u64 sctpi_outofseqtsns; - __u64 sctpi_idupchunks; - __u64 sctpi_gapcnt; - __u64 sctpi_ouodchunks; - __u64 sctpi_iuodchunks; - __u64 sctpi_oodchunks; - __u64 sctpi_iodchunks; - __u64 sctpi_octrlchunks; - __u64 sctpi_ictrlchunks; - - /* primary transport info */ - struct sockaddr_storage sctpi_p_address; - __s32 sctpi_p_state; - __u32 sctpi_p_cwnd; - __u32 sctpi_p_srtt; - __u32 sctpi_p_rto; - __u32 sctpi_p_hbinterval; - __u32 sctpi_p_pathmaxrxt; - __u32 sctpi_p_sackdelay; - __u32 sctpi_p_sackfreq; - __u32 sctpi_p_ssthresh; - __u32 sctpi_p_partial_bytes_acked; - __u32 sctpi_p_flight_size; - __u16 sctpi_p_error; - __u16 __reserved2; - - /* sctp sock info */ - __u32 sctpi_s_autoclose; - __u32 sctpi_s_adaptation_ind; - __u32 sctpi_s_pd_point; - __u8 sctpi_s_nodelay; - __u8 sctpi_s_disable_fragments; - __u8 sctpi_s_v4mapped; - __u8 sctpi_s_frag_interleave; - __u32 sctpi_s_type; - __u32 __reserved3; -}; - struct sctp_infox { struct sctp_info *sctpinfo; struct sctp_association *asoc; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6f0b3e0adc73..0f665cb26b50 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2847,6 +2847,18 @@ static inline int skb_linearize_cow(struct sk_buff *skb) __skb_linearize(skb) : 0; } +static __always_inline void +__skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len, + unsigned int off) +{ + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_block_sub(skb->csum, + csum_partial(start, len, 0), off); + else if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_start_offset(skb) < 0) + skb->ip_summed = CHECKSUM_NONE; +} + /** * skb_postpull_rcsum - update checksum for received skb after pull * @skb: buffer to update @@ -2857,36 +2869,38 @@ static inline int skb_linearize_cow(struct sk_buff *skb) * update the CHECKSUM_COMPLETE checksum, or set ip_summed to * CHECKSUM_NONE so that it can be recomputed from scratch. */ - static inline void skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { - if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0)); - else if (skb->ip_summed == CHECKSUM_PARTIAL && - skb_checksum_start_offset(skb) < 0) - skb->ip_summed = CHECKSUM_NONE; + __skb_postpull_rcsum(skb, start, len, 0); } -unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); +static __always_inline void +__skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len, + unsigned int off) +{ + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_block_add(skb->csum, + csum_partial(start, len, 0), off); +} +/** + * skb_postpush_rcsum - update checksum for received skb after push + * @skb: buffer to update + * @start: start of data after push + * @len: length of data pushed + * + * After doing a push on a received packet, you need to call this to + * update the CHECKSUM_COMPLETE checksum. + */ static inline void skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { - /* For performing the reverse operation to skb_postpull_rcsum(), - * we can instead of ... - * - * skb->csum = csum_add(skb->csum, csum_partial(start, len, 0)); - * - * ... just use this equivalent version here to save a few - * instructions. Feeding csum of 0 in csum_partial() and later - * on adding skb->csum is equivalent to feed skb->csum in the - * first place. - */ - if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->csum = csum_partial(start, len, skb->csum); + __skb_postpush_rcsum(skb, start, len, 0); } +unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); + /** * skb_push_rcsum - push skb and update receive checksum * @skb: buffer to update diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index b6810c92b8bb..5c02b0691587 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -195,6 +195,8 @@ int rpc_clnt_add_xprt(struct rpc_clnt *, struct xprt_create *, struct rpc_xprt *, void *), void *data); +void rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt, + unsigned long timeo); const char *rpc_proc_name(const struct rpc_task *task); #endif /* __KERNEL__ */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 5e3e1b63dbb3..a16070dd03ee 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -218,7 +218,8 @@ struct rpc_xprt { struct work_struct task_cleanup; struct timer_list timer; unsigned long last_used, - idle_timeout; + idle_timeout, + max_reconnect_timeout; /* * Send stuff diff --git a/include/net/act_api.h b/include/net/act_api.h index 41e6a24a44b9..82f3c912a5b1 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -176,8 +176,8 @@ int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops); int tcf_unregister_action(struct tc_action_ops *a, struct pernet_operations *ops); int tcf_action_destroy(struct list_head *actions, int bind); -int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions, - struct tcf_result *res); +int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, + int nr_actions, struct tcf_result *res); int tcf_action_init(struct net *net, struct nlattr *nla, struct nlattr *est, char *n, int ovr, int bind, struct list_head *); @@ -189,30 +189,17 @@ int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int); -#define tc_no_actions(_exts) \ - (list_empty(&(_exts)->actions)) - -#define tc_for_each_action(_a, _exts) \ - list_for_each_entry(a, &(_exts)->actions, list) - -#define tc_single_action(_exts) \ - (list_is_singular(&(_exts)->actions)) +#endif /* CONFIG_NET_CLS_ACT */ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 lastuse) { +#ifdef CONFIG_NET_CLS_ACT if (!a->ops->stats_update) return; a->ops->stats_update(a, bytes, packets, lastuse); +#endif } -#else /* CONFIG_NET_CLS_ACT */ - -#define tc_no_actions(_exts) true -#define tc_for_each_action(_a, _exts) while ((void)(_a), 0) -#define tc_single_action(_exts) false -#define tcf_action_stats_update(a, bytes, packets, lastuse) - -#endif /* CONFIG_NET_CLS_ACT */ #endif diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index ac1bc3c49fbd..7b0f88699b25 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -40,12 +40,12 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *, unsigned long, gfp_t); int rxrpc_kernel_send_data(struct rxrpc_call *, struct msghdr *, size_t); +void rxrpc_kernel_data_consumed(struct rxrpc_call *, struct sk_buff *); void rxrpc_kernel_abort_call(struct rxrpc_call *, u32); void rxrpc_kernel_end_call(struct rxrpc_call *); bool rxrpc_kernel_is_data_last(struct sk_buff *); u32 rxrpc_kernel_get_abort_code(struct sk_buff *); int rxrpc_kernel_get_error_number(struct sk_buff *); -void rxrpc_kernel_data_delivered(struct sk_buff *); void rxrpc_kernel_free_skb(struct sk_buff *); struct rxrpc_call *rxrpc_kernel_accept_call(struct socket *, unsigned long); int rxrpc_kernel_reject_call(struct socket *); diff --git a/include/net/gre.h b/include/net/gre.h index 7a54a31d1d4c..73ea256eb7d7 100644 --- a/include/net/gre.h +++ b/include/net/gre.h @@ -104,6 +104,7 @@ static inline void gre_build_header(struct sk_buff *skb, int hdr_len, skb_push(skb, hdr_len); + skb_set_inner_protocol(skb, proto); skb_reset_transport_header(skb); greh = (struct gre_base_hdr *)skb->data; greh->flags = gre_tnl_flags_to_gre_flags(flags); diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index 0dc0a51da38f..dce2d586d9ce 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -128,7 +128,8 @@ static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph) to = from | htonl(INET_ECN_CE << 20); *(__be32 *)iph = to; if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->csum = csum_add(csum_sub(skb->csum, from), to); + skb->csum = csum_add(csum_sub(skb->csum, (__force __wsum)from), + (__force __wsum)to); return 1; } diff --git a/include/net/mac80211.h b/include/net/mac80211.h index b4faadbb4e01..cca510a585c3 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -3620,7 +3620,8 @@ struct ieee80211_ops { int (*join_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); void (*leave_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); - u32 (*get_expected_throughput)(struct ieee80211_sta *sta); + u32 (*get_expected_throughput)(struct ieee80211_hw *hw, + struct ieee80211_sta *sta); int (*get_txpower)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, int *dbm); diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 6f8d65342d3a..c99508d426cc 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -59,7 +59,8 @@ tcf_unbind_filter(struct tcf_proto *tp, struct tcf_result *r) struct tcf_exts { #ifdef CONFIG_NET_CLS_ACT __u32 type; /* for backward compat(TCA_OLD_COMPAT) */ - struct list_head actions; + int nr_actions; + struct tc_action **actions; #endif /* Map to export classifier specific extension TLV types to the * generic extensions API. Unsupported extensions must be set to 0. @@ -72,7 +73,10 @@ static inline void tcf_exts_init(struct tcf_exts *exts, int action, int police) { #ifdef CONFIG_NET_CLS_ACT exts->type = 0; - INIT_LIST_HEAD(&exts->actions); + exts->nr_actions = 0; + exts->actions = kcalloc(TCA_ACT_MAX_PRIO, sizeof(struct tc_action *), + GFP_KERNEL); + WARN_ON(!exts->actions); /* TODO: propagate the error to callers */ #endif exts->action = action; exts->police = police; @@ -89,7 +93,7 @@ static inline int tcf_exts_is_predicative(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT - return !list_empty(&exts->actions); + return exts->nr_actions; #else return 0; #endif @@ -108,6 +112,20 @@ tcf_exts_is_available(struct tcf_exts *exts) return tcf_exts_is_predicative(exts); } +static inline void tcf_exts_to_list(const struct tcf_exts *exts, + struct list_head *actions) +{ +#ifdef CONFIG_NET_CLS_ACT + int i; + + for (i = 0; i < exts->nr_actions; i++) { + struct tc_action *a = exts->actions[i]; + + list_add(&a->list, actions); + } +#endif +} + /** * tcf_exts_exec - execute tc filter extensions * @skb: socket buffer @@ -124,12 +142,25 @@ tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts, struct tcf_result *res) { #ifdef CONFIG_NET_CLS_ACT - if (!list_empty(&exts->actions)) - return tcf_action_exec(skb, &exts->actions, res); + if (exts->nr_actions) + return tcf_action_exec(skb, exts->actions, exts->nr_actions, + res); #endif return 0; } +#ifdef CONFIG_NET_CLS_ACT + +#define tc_no_actions(_exts) ((_exts)->nr_actions == 0) +#define tc_single_action(_exts) ((_exts)->nr_actions == 1) + +#else /* CONFIG_NET_CLS_ACT */ + +#define tc_no_actions(_exts) true +#define tc_single_action(_exts) false + +#endif /* CONFIG_NET_CLS_ACT */ + int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index da218fec6056..9e5fc168c8a3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -339,7 +339,7 @@ enum bpf_func_id { BPF_FUNC_skb_change_type, /** - * bpf_skb_in_cgroup(skb, map, index) - Check cgroup2 membership of skb + * bpf_skb_under_cgroup(skb, map, index) - Check cgroup2 membership of skb * @skb: pointer to skb * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type * @index: index of the cgroup in the bpf_map @@ -348,7 +348,7 @@ enum bpf_func_id { * == 1 skb succeeded the cgroup2 descendant test * < 0 error */ - BPF_FUNC_skb_in_cgroup, + BPF_FUNC_skb_under_cgroup, /** * bpf_get_hash_recalc(skb) diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 01751faccaf8..c674ba2563b7 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -24,7 +24,7 @@ enum nft_registers { __NFT_REG_MAX, NFT_REG32_00 = 8, - MFT_REG32_01, + NFT_REG32_01, NFT_REG32_02, NFT_REG32_03, NFT_REG32_04, diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index d304f4c9792c..a406adcc0793 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -944,4 +944,68 @@ struct sctp_default_prinfo { __u16 pr_policy; }; +struct sctp_info { + __u32 sctpi_tag; + __u32 sctpi_state; + __u32 sctpi_rwnd; + __u16 sctpi_unackdata; + __u16 sctpi_penddata; + __u16 sctpi_instrms; + __u16 sctpi_outstrms; + __u32 sctpi_fragmentation_point; + __u32 sctpi_inqueue; + __u32 sctpi_outqueue; + __u32 sctpi_overall_error; + __u32 sctpi_max_burst; + __u32 sctpi_maxseg; + __u32 sctpi_peer_rwnd; + __u32 sctpi_peer_tag; + __u8 sctpi_peer_capable; + __u8 sctpi_peer_sack; + __u16 __reserved1; + + /* assoc status info */ + __u64 sctpi_isacks; + __u64 sctpi_osacks; + __u64 sctpi_opackets; + __u64 sctpi_ipackets; + __u64 sctpi_rtxchunks; + __u64 sctpi_outofseqtsns; + __u64 sctpi_idupchunks; + __u64 sctpi_gapcnt; + __u64 sctpi_ouodchunks; + __u64 sctpi_iuodchunks; + __u64 sctpi_oodchunks; + __u64 sctpi_iodchunks; + __u64 sctpi_octrlchunks; + __u64 sctpi_ictrlchunks; + + /* primary transport info */ + struct sockaddr_storage sctpi_p_address; + __s32 sctpi_p_state; + __u32 sctpi_p_cwnd; + __u32 sctpi_p_srtt; + __u32 sctpi_p_rto; + __u32 sctpi_p_hbinterval; + __u32 sctpi_p_pathmaxrxt; + __u32 sctpi_p_sackdelay; + __u32 sctpi_p_sackfreq; + __u32 sctpi_p_ssthresh; + __u32 sctpi_p_partial_bytes_acked; + __u32 sctpi_p_flight_size; + __u16 sctpi_p_error; + __u16 __reserved2; + + /* sctp sock info */ + __u32 sctpi_s_autoclose; + __u32 sctpi_s_adaptation_ind; + __u32 sctpi_s_pd_point; + __u8 sctpi_s_nodelay; + __u8 sctpi_s_disable_fragments; + __u8 sctpi_s_v4mapped; + __u8 sctpi_s_frag_interleave; + __u32 sctpi_s_type; + __u32 __reserved3; +}; + #endif /* _UAPI_SCTP_H */ diff --git a/include/uapi/misc/cxl.h b/include/uapi/misc/cxl.h index cbae529b7ce0..180d526a55c3 100644 --- a/include/uapi/misc/cxl.h +++ b/include/uapi/misc/cxl.h @@ -136,8 +136,8 @@ struct cxl_event_afu_driver_reserved { * * Of course the contents will be ABI, but that's up the AFU driver. */ - size_t data_size; - u8 data[]; + __u32 data_size; + __u8 data[]; }; struct cxl_event { diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index fff3650d52fc..570eeca7bdfa 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -26,11 +26,18 @@ struct bpf_htab { struct bucket *buckets; void *elems; struct pcpu_freelist freelist; + void __percpu *extra_elems; atomic_t count; /* number of elements in this hashtable */ u32 n_buckets; /* number of hash buckets */ u32 elem_size; /* size of each element in bytes */ }; +enum extra_elem_state { + HTAB_NOT_AN_EXTRA_ELEM = 0, + HTAB_EXTRA_ELEM_FREE, + HTAB_EXTRA_ELEM_USED +}; + /* each htab element is struct htab_elem + key + value */ struct htab_elem { union { @@ -38,7 +45,10 @@ struct htab_elem { struct bpf_htab *htab; struct pcpu_freelist_node fnode; }; - struct rcu_head rcu; + union { + struct rcu_head rcu; + enum extra_elem_state state; + }; u32 hash; char key[0] __aligned(8); }; @@ -113,6 +123,23 @@ free_elems: return err; } +static int alloc_extra_elems(struct bpf_htab *htab) +{ + void __percpu *pptr; + int cpu; + + pptr = __alloc_percpu_gfp(htab->elem_size, 8, GFP_USER | __GFP_NOWARN); + if (!pptr) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + ((struct htab_elem *)per_cpu_ptr(pptr, cpu))->state = + HTAB_EXTRA_ELEM_FREE; + } + htab->extra_elems = pptr; + return 0; +} + /* Called from syscall */ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) { @@ -185,6 +212,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (percpu) cost += (u64) round_up(htab->map.value_size, 8) * num_possible_cpus() * htab->map.max_entries; + else + cost += (u64) htab->elem_size * num_possible_cpus(); if (cost >= U32_MAX - PAGE_SIZE) /* make sure page count doesn't overflow */ @@ -212,14 +241,22 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) raw_spin_lock_init(&htab->buckets[i].lock); } + if (!percpu) { + err = alloc_extra_elems(htab); + if (err) + goto free_buckets; + } + if (!(attr->map_flags & BPF_F_NO_PREALLOC)) { err = prealloc_elems_and_freelist(htab); if (err) - goto free_buckets; + goto free_extra_elems; } return &htab->map; +free_extra_elems: + free_percpu(htab->extra_elems); free_buckets: kvfree(htab->buckets); free_htab: @@ -349,7 +386,6 @@ static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l) if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) free_percpu(htab_elem_get_ptr(l, htab->map.key_size)); kfree(l); - } static void htab_elem_free_rcu(struct rcu_head *head) @@ -370,6 +406,11 @@ static void htab_elem_free_rcu(struct rcu_head *head) static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) { + if (l->state == HTAB_EXTRA_ELEM_USED) { + l->state = HTAB_EXTRA_ELEM_FREE; + return; + } + if (!(htab->map.map_flags & BPF_F_NO_PREALLOC)) { pcpu_freelist_push(&htab->freelist, &l->fnode); } else { @@ -381,25 +422,44 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, void *value, u32 key_size, u32 hash, - bool percpu, bool onallcpus) + bool percpu, bool onallcpus, + bool old_elem_exists) { u32 size = htab->map.value_size; bool prealloc = !(htab->map.map_flags & BPF_F_NO_PREALLOC); struct htab_elem *l_new; void __percpu *pptr; + int err = 0; if (prealloc) { l_new = (struct htab_elem *)pcpu_freelist_pop(&htab->freelist); if (!l_new) - return ERR_PTR(-E2BIG); + err = -E2BIG; } else { if (atomic_inc_return(&htab->count) > htab->map.max_entries) { atomic_dec(&htab->count); - return ERR_PTR(-E2BIG); + err = -E2BIG; + } else { + l_new = kmalloc(htab->elem_size, + GFP_ATOMIC | __GFP_NOWARN); + if (!l_new) + return ERR_PTR(-ENOMEM); } - l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN); - if (!l_new) - return ERR_PTR(-ENOMEM); + } + + if (err) { + if (!old_elem_exists) + return ERR_PTR(err); + + /* if we're updating the existing element and the hash table + * is full, use per-cpu extra elems + */ + l_new = this_cpu_ptr(htab->extra_elems); + if (l_new->state != HTAB_EXTRA_ELEM_FREE) + return ERR_PTR(-E2BIG); + l_new->state = HTAB_EXTRA_ELEM_USED; + } else { + l_new->state = HTAB_NOT_AN_EXTRA_ELEM; } memcpy(l_new->key, key, key_size); @@ -489,7 +549,8 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, if (ret) goto err; - l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false); + l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false, + !!l_old); if (IS_ERR(l_new)) { /* all pre-allocated elements are in use or memory exhausted */ ret = PTR_ERR(l_new); @@ -563,7 +624,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, } } else { l_new = alloc_htab_elem(htab, key, value, key_size, - hash, true, onallcpus); + hash, true, onallcpus, false); if (IS_ERR(l_new)) { ret = PTR_ERR(l_new); goto err; @@ -652,6 +713,7 @@ static void htab_map_free(struct bpf_map *map) htab_free_elems(htab); pcpu_freelist_destroy(&htab->freelist); } + free_percpu(htab->extra_elems); kvfree(htab->buckets); kfree(htab); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f72f23b8fdab..daea765d72e6 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -194,6 +194,7 @@ struct verifier_env { struct verifier_state_list **explored_states; /* search pruning optimization */ struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ u32 used_map_cnt; /* number of used maps */ + u32 id_gen; /* used to generate unique reg IDs */ bool allow_ptr_leaks; }; @@ -1052,7 +1053,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) goto error; break; case BPF_MAP_TYPE_CGROUP_ARRAY: - if (func_id != BPF_FUNC_skb_in_cgroup) + if (func_id != BPF_FUNC_skb_under_cgroup) goto error; break; default: @@ -1074,7 +1075,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) if (map->map_type != BPF_MAP_TYPE_STACK_TRACE) goto error; break; - case BPF_FUNC_skb_in_cgroup: + case BPF_FUNC_skb_under_cgroup: if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY) goto error; break; @@ -1301,7 +1302,7 @@ add_imm: /* dst_reg stays as pkt_ptr type and since some positive * integer value was added to the pointer, increment its 'id' */ - dst_reg->id++; + dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range and off to zero */ dst_reg->off = 0; diff --git a/kernel/events/core.c b/kernel/events/core.c index a19550d80ab1..1903b8f3a705 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -843,6 +843,32 @@ perf_cgroup_mark_enabled(struct perf_event *event, } } } + +/* + * Update cpuctx->cgrp so that it is set when first cgroup event is added and + * cleared when last cgroup event is removed. + */ +static inline void +list_update_cgroup_event(struct perf_event *event, + struct perf_event_context *ctx, bool add) +{ + struct perf_cpu_context *cpuctx; + + if (!is_cgroup_event(event)) + return; + + if (add && ctx->nr_cgroups++) + return; + else if (!add && --ctx->nr_cgroups) + return; + /* + * Because cgroup events are always per-cpu events, + * this will always be called from the right CPU. + */ + cpuctx = __get_cpu_context(ctx); + cpuctx->cgrp = add ? event->cgrp : NULL; +} + #else /* !CONFIG_CGROUP_PERF */ static inline bool @@ -920,6 +946,13 @@ perf_cgroup_mark_enabled(struct perf_event *event, struct perf_event_context *ctx) { } + +static inline void +list_update_cgroup_event(struct perf_event *event, + struct perf_event_context *ctx, bool add) +{ +} + #endif /* @@ -1392,6 +1425,7 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx) static void list_add_event(struct perf_event *event, struct perf_event_context *ctx) { + lockdep_assert_held(&ctx->lock); WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT); @@ -1412,8 +1446,7 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx) list_add_tail(&event->group_entry, list); } - if (is_cgroup_event(event)) - ctx->nr_cgroups++; + list_update_cgroup_event(event, ctx, true); list_add_rcu(&event->event_entry, &ctx->event_list); ctx->nr_events++; @@ -1581,8 +1614,6 @@ static void perf_group_attach(struct perf_event *event) static void list_del_event(struct perf_event *event, struct perf_event_context *ctx) { - struct perf_cpu_context *cpuctx; - WARN_ON_ONCE(event->ctx != ctx); lockdep_assert_held(&ctx->lock); @@ -1594,20 +1625,7 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) event->attach_state &= ~PERF_ATTACH_CONTEXT; - if (is_cgroup_event(event)) { - ctx->nr_cgroups--; - /* - * Because cgroup events are always per-cpu events, this will - * always be called from the right CPU. - */ - cpuctx = __get_cpu_context(ctx); - /* - * If there are no more cgroup events then clear cgrp to avoid - * stale pointer in update_cgrp_time_from_cpuctx(). - */ - if (!ctx->nr_cgroups) - cpuctx->cgrp = NULL; - } + list_update_cgroup_event(event, ctx, false); ctx->nr_events--; if (event->attr.inherit_stat) @@ -1716,8 +1734,8 @@ static inline int pmu_filter_match(struct perf_event *event) static inline int event_filter_match(struct perf_event *event) { - return (event->cpu == -1 || event->cpu == smp_processor_id()) - && perf_cgroup_match(event) && pmu_filter_match(event); + return (event->cpu == -1 || event->cpu == smp_processor_id()) && + perf_cgroup_match(event) && pmu_filter_match(event); } static void @@ -1737,8 +1755,8 @@ event_sched_out(struct perf_event *event, * maintained, otherwise bogus information is return * via read() for time_enabled, time_running: */ - if (event->state == PERF_EVENT_STATE_INACTIVE - && !event_filter_match(event)) { + if (event->state == PERF_EVENT_STATE_INACTIVE && + !event_filter_match(event)) { delta = tstamp - event->tstamp_stopped; event->tstamp_running += delta; event->tstamp_stopped = tstamp; @@ -2236,10 +2254,15 @@ perf_install_in_context(struct perf_event_context *ctx, lockdep_assert_held(&ctx->mutex); - event->ctx = ctx; if (event->cpu != -1) event->cpu = cpu; + /* + * Ensures that if we can observe event->ctx, both the event and ctx + * will be 'complete'. See perf_iterate_sb_cpu(). + */ + smp_store_release(&event->ctx, ctx); + if (!task) { cpu_function_call(cpu, __perf_install_in_context, event); return; @@ -5969,6 +5992,14 @@ static void perf_iterate_sb_cpu(perf_iterate_f output, void *data) struct perf_event *event; list_for_each_entry_rcu(event, &pel->list, sb_list) { + /* + * Skip events that are not fully formed yet; ensure that + * if we observe event->ctx, both event and ctx will be + * complete enough. See perf_install_in_context(). + */ + if (!smp_load_acquire(&event->ctx)) + continue; + if (event->state < PERF_EVENT_STATE_INACTIVE) continue; if (!event_filter_match(event)) diff --git a/kernel/futex.c b/kernel/futex.c index 33664f70e2d2..46cb3a301bc1 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -179,7 +179,15 @@ int __read_mostly futex_cmpxchg_enabled; * Futex flags used to encode options to functions and preserve them across * restarts. */ -#define FLAGS_SHARED 0x01 +#ifdef CONFIG_MMU +# define FLAGS_SHARED 0x01 +#else +/* + * NOMMU does not have per process address space. Let the compiler optimize + * code away. + */ +# define FLAGS_SHARED 0x00 +#endif #define FLAGS_CLOCKRT 0x02 #define FLAGS_HAS_TIMEOUT 0x04 @@ -405,6 +413,16 @@ static void get_futex_key_refs(union futex_key *key) if (!key->both.ptr) return; + /* + * On MMU less systems futexes are always "private" as there is no per + * process address space. We need the smp wmb nevertheless - yes, + * arch/blackfin has MMU less SMP ... + */ + if (!IS_ENABLED(CONFIG_MMU)) { + smp_mb(); /* explicit smp_mb(); (B) */ + return; + } + switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { case FUT_OFF_INODE: ihold(key->shared.inode); /* implies smp_mb(); (B) */ @@ -436,6 +454,9 @@ static void drop_futex_key_refs(union futex_key *key) return; } + if (!IS_ENABLED(CONFIG_MMU)) + return; + switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { case FUT_OFF_INODE: iput(key->shared.inode); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 54999350162c..19e9dfbe97fa 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -359,6 +359,17 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, else dev_dbg(dev, "irq [%d-%d] for MSI\n", virq, virq + desc->nvec_used - 1); + /* + * This flag is set by the PCI layer as we need to activate + * the MSI entries before the PCI layer enables MSI in the + * card. Otherwise the card latches a random msi message. + */ + if (info->flags & MSI_FLAG_ACTIVATE_EARLY) { + struct irq_data *irq_data; + + irq_data = irq_domain_get_irq_data(domain, desc->irq); + irq_domain_activate_irq(irq_data); + } } return 0; diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index 37649e69056c..8a99abf58080 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -450,7 +450,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node) goto gotlock; } } - WRITE_ONCE(pn->state, vcpu_halted); + WRITE_ONCE(pn->state, vcpu_hashed); qstat_inc(qstat_pv_wait_head, true); qstat_inc(qstat_pv_wait_again, waitcnt); pv_wait(&l->locked, _Q_SLOW_VAL); diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h index 22e025309845..b9d031516254 100644 --- a/kernel/locking/qspinlock_stat.h +++ b/kernel/locking/qspinlock_stat.h @@ -153,7 +153,6 @@ static ssize_t qstat_read(struct file *file, char __user *user_buf, */ if ((counter == qstat_pv_latency_kick) || (counter == qstat_pv_latency_wake)) { - stat = 0; if (kicks) stat = DIV_ROUND_CLOSEST_ULL(stat, kicks); } diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index a881c6a7ba74..33c79b6105c5 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -300,12 +300,12 @@ static int create_image(int platform_mode) save_processor_state(); trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, true); error = swsusp_arch_suspend(); + /* Restore control flow magically appears here */ + restore_processor_state(); trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false); if (error) printk(KERN_ERR "PM: Error %d creating hibernation image\n", error); - /* Restore control flow magically appears here */ - restore_processor_state(); if (!in_suspend) events_check_enabled = false; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5c883fe8e440..2a906f20fba7 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -74,6 +74,7 @@ #include <linux/context_tracking.h> #include <linux/compiler.h> #include <linux/frame.h> +#include <linux/prefetch.h> #include <asm/switch_to.h> #include <asm/tlb.h> @@ -2972,6 +2973,23 @@ EXPORT_PER_CPU_SYMBOL(kstat); EXPORT_PER_CPU_SYMBOL(kernel_cpustat); /* + * The function fair_sched_class.update_curr accesses the struct curr + * and its field curr->exec_start; when called from task_sched_runtime(), + * we observe a high rate of cache misses in practice. + * Prefetching this data results in improved performance. + */ +static inline void prefetch_curr_exec_start(struct task_struct *p) +{ +#ifdef CONFIG_FAIR_GROUP_SCHED + struct sched_entity *curr = (&p->se)->cfs_rq->curr; +#else + struct sched_entity *curr = (&task_rq(p)->cfs)->curr; +#endif + prefetch(curr); + prefetch(&curr->exec_start); +} + +/* * Return accounted runtime for the task. * In case the task is currently running, return the runtime plus current's * pending runtime that have not been accounted yet. @@ -3005,6 +3023,7 @@ unsigned long long task_sched_runtime(struct task_struct *p) * thread, breaking clock_gettime(). */ if (task_current(rq, p) && task_on_rq_queued(p)) { + prefetch_curr_exec_start(p); update_rq_clock(rq); p->sched_class->update_curr(rq); } diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c index 5be58820465c..d4184498c9f5 100644 --- a/kernel/sched/cpudeadline.c +++ b/kernel/sched/cpudeadline.c @@ -168,7 +168,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid) if (old_idx == IDX_INVALID) { cp->size++; - cp->elements[cp->size - 1].dl = 0; + cp->elements[cp->size - 1].dl = dl; cp->elements[cp->size - 1].cpu = cpu; cp->elements[cpu].idx = cp->size - 1; cpudl_change_key(cp, cp->size - 1, dl); diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 1934f658c036..9858266fb0b3 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -508,13 +508,21 @@ void account_process_tick(struct task_struct *p, int user_tick) */ void account_idle_ticks(unsigned long ticks) { + cputime_t cputime, steal; if (sched_clock_irqtime) { irqtime_account_idle_ticks(ticks); return; } - account_idle_time(jiffies_to_cputime(ticks)); + cputime = jiffies_to_cputime(ticks); + steal = steal_account_process_time(cputime); + + if (steal >= cputime) + return; + + cputime -= steal; + account_idle_time(cputime); } /* diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index fcb7f0217ff4..1ce8867283dc 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -658,8 +658,11 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * * XXX figure out if select_task_rq_dl() deals with offline cpus. */ - if (unlikely(!rq->online)) + if (unlikely(!rq->online)) { + lockdep_unpin_lock(&rq->lock, rf.cookie); rq = dl_task_offline_migration(rq, p); + rf.cookie = lockdep_pin_lock(&rq->lock); + } /* * Queueing this task back might have overloaded rq, check if we need diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 4088eedea763..039de34f1521 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4269,7 +4269,7 @@ static void sync_throttle(struct task_group *tg, int cpu) pcfs_rq = tg->parent->cfs_rq[cpu]; cfs_rq->throttle_count = pcfs_rq->throttle_count; - pcfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu)); + cfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu)); } /* conditionally throttle active cfs_rq's from put_prev_entity() */ diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 555670a5143c..32bf6f75a8fe 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1496,6 +1496,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); u64 expires = KTIME_MAX; unsigned long nextevt; + bool is_max_delta; /* * Pretend that there is no timer pending if the cpu is offline. @@ -1506,6 +1507,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) spin_lock(&base->lock); nextevt = __next_timer_interrupt(base); + is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA); base->next_expiry = nextevt; /* * We have a fresh next event. Check whether we can forward the base: @@ -1519,7 +1521,8 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) expires = basem; base->is_idle = false; } else { - expires = basem + (nextevt - basej) * TICK_NSEC; + if (!is_max_delta) + expires = basem + (nextevt - basej) * TICK_NSEC; /* * If we expect to sleep more than a tick, mark the base idle: */ diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 5d845ffd7982..5ba520b544d7 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -30,7 +30,7 @@ #define HASH_DEFAULT_SIZE 64UL #define HASH_MIN_SIZE 4U -#define BUCKET_LOCKS_PER_CPU 128UL +#define BUCKET_LOCKS_PER_CPU 32UL static u32 head_hashfn(struct rhashtable *ht, const struct bucket_table *tbl, @@ -70,7 +70,7 @@ static int alloc_bucket_locks(struct rhashtable *ht, struct bucket_table *tbl, unsigned int nr_pcpus = num_possible_cpus(); #endif - nr_pcpus = min_t(unsigned int, nr_pcpus, 32UL); + nr_pcpus = min_t(unsigned int, nr_pcpus, 64UL); size = roundup_pow_of_two(nr_pcpus * ht->p.locks_mul); /* Never allocate more than 0.5 locks per bucket */ @@ -83,6 +83,9 @@ static int alloc_bucket_locks(struct rhashtable *ht, struct bucket_table *tbl, tbl->locks = vmalloc(size * sizeof(spinlock_t)); else #endif + if (gfp != GFP_KERNEL) + gfp |= __GFP_NOWARN | __GFP_NORETRY; + tbl->locks = kmalloc_array(size, sizeof(spinlock_t), gfp); if (!tbl->locks) @@ -321,12 +324,14 @@ static int rhashtable_expand(struct rhashtable *ht) static int rhashtable_shrink(struct rhashtable *ht) { struct bucket_table *new_tbl, *old_tbl = rht_dereference(ht->tbl, ht); - unsigned int size; + unsigned int nelems = atomic_read(&ht->nelems); + unsigned int size = 0; int err; ASSERT_RHT_MUTEX(ht); - size = roundup_pow_of_two(atomic_read(&ht->nelems) * 3 / 2); + if (nelems) + size = roundup_pow_of_two(nelems * 3 / 2); if (size < ht->p.min_size) size = ht->p.min_size; diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index 297fdb5e74bd..64e899b63337 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -38,7 +38,7 @@ MODULE_PARM_DESC(runs, "Number of test runs per variant (default: 4)"); static int max_size = 0; module_param(max_size, int, 0); -MODULE_PARM_DESC(runs, "Maximum table size (default: calculated)"); +MODULE_PARM_DESC(max_size, "Maximum table size (default: calculated)"); static bool shrinking = false; module_param(shrinking, bool, 0); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 82a116ba590e..8de138d3306b 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -169,7 +169,7 @@ int register_vlan_dev(struct net_device *dev) if (err < 0) goto out_uninit_mvrp; - vlan->nest_level = dev_get_nest_level(real_dev, is_vlan_dev) + 1; + vlan->nest_level = dev_get_nest_level(real_dev) + 1; err = register_netdevice(dev); if (err < 0) goto out_uninit_mvrp; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index c18080ad4085..cd620fab41b0 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -267,7 +267,7 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) /* If old entry was unassociated with any port, then delete it. */ f = __br_fdb_get(br, br->dev->dev_addr, 0); - if (f && f->is_local && !f->dst) + if (f && f->is_local && !f->dst && !f->added_by_user) fdb_delete_local(br, NULL, f); fdb_insert(br, NULL, newaddr, 0); @@ -282,7 +282,7 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) if (!br_vlan_should_use(v)) continue; f = __br_fdb_get(br, br->dev->dev_addr, v->vid); - if (f && f->is_local && !f->dst) + if (f && f->is_local && !f->dst && !f->added_by_user) fdb_delete_local(br, NULL, f); fdb_insert(br, NULL, newaddr, v->vid); } @@ -764,20 +764,25 @@ out: } /* Update (create or replace) forwarding database entry */ -static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, - __u16 state, __u16 flags, __u16 vid) +static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, + const __u8 *addr, __u16 state, __u16 flags, __u16 vid) { - struct net_bridge *br = source->br; struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)]; struct net_bridge_fdb_entry *fdb; bool modified = false; /* If the port cannot learn allow only local and static entries */ - if (!(state & NUD_PERMANENT) && !(state & NUD_NOARP) && + if (source && !(state & NUD_PERMANENT) && !(state & NUD_NOARP) && !(source->state == BR_STATE_LEARNING || source->state == BR_STATE_FORWARDING)) return -EPERM; + if (!source && !(state & NUD_PERMANENT)) { + pr_info("bridge: RTM_NEWNEIGH %s without NUD_PERMANENT\n", + br->dev->name); + return -EINVAL; + } + fdb = fdb_find(head, addr, vid); if (fdb == NULL) { if (!(flags & NLM_F_CREATE)) @@ -832,22 +837,28 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, return 0; } -static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p, - const unsigned char *addr, u16 nlh_flags, u16 vid) +static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, + struct net_bridge_port *p, const unsigned char *addr, + u16 nlh_flags, u16 vid) { int err = 0; if (ndm->ndm_flags & NTF_USE) { + if (!p) { + pr_info("bridge: RTM_NEWNEIGH %s with NTF_USE is not supported\n", + br->dev->name); + return -EINVAL; + } local_bh_disable(); rcu_read_lock(); - br_fdb_update(p->br, p, addr, vid, true); + br_fdb_update(br, p, addr, vid, true); rcu_read_unlock(); local_bh_enable(); } else { - spin_lock_bh(&p->br->hash_lock); - err = fdb_add_entry(p, addr, ndm->ndm_state, + spin_lock_bh(&br->hash_lock); + err = fdb_add_entry(br, p, addr, ndm->ndm_state, nlh_flags, vid); - spin_unlock_bh(&p->br->hash_lock); + spin_unlock_bh(&br->hash_lock); } return err; @@ -884,6 +895,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], dev->name); return -EINVAL; } + br = p->br; vg = nbp_vlan_group(p); } @@ -895,15 +907,9 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], } /* VID was specified, so use it. */ - if (dev->priv_flags & IFF_EBRIDGE) - err = br_fdb_insert(br, NULL, addr, vid); - else - err = __br_fdb_add(ndm, p, addr, nlh_flags, vid); + err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid); } else { - if (dev->priv_flags & IFF_EBRIDGE) - err = br_fdb_insert(br, NULL, addr, 0); - else - err = __br_fdb_add(ndm, p, addr, nlh_flags, 0); + err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0); if (err || !vg || !vg->num_vlans) goto out; @@ -914,11 +920,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], list_for_each_entry(v, &vg->vlan_list, vlist) { if (!br_vlan_should_use(v)) continue; - if (dev->priv_flags & IFF_EBRIDGE) - err = br_fdb_insert(br, NULL, addr, v->vid); - else - err = __br_fdb_add(ndm, p, addr, nlh_flags, - v->vid); + err = __br_fdb_add(ndm, br, p, addr, nlh_flags, v->vid); if (err) goto out; } diff --git a/net/core/dev.c b/net/core/dev.c index 4ce07dc25573..dd6ce598de89 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6045,8 +6045,7 @@ void *netdev_lower_dev_get_private(struct net_device *dev, EXPORT_SYMBOL(netdev_lower_dev_get_private); -int dev_get_nest_level(struct net_device *dev, - bool (*type_check)(const struct net_device *dev)) +int dev_get_nest_level(struct net_device *dev) { struct net_device *lower = NULL; struct list_head *iter; @@ -6056,15 +6055,12 @@ int dev_get_nest_level(struct net_device *dev, ASSERT_RTNL(); netdev_for_each_lower_dev(dev, lower, iter) { - nest = dev_get_nest_level(lower, type_check); + nest = dev_get_nest_level(lower); if (max_nest < nest) max_nest = nest; } - if (type_check(dev)) - max_nest++; - - return max_nest; + return max_nest + 1; } EXPORT_SYMBOL(dev_get_nest_level); diff --git a/net/core/filter.c b/net/core/filter.c index 5708999f8a79..cb06aceb512a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1355,56 +1355,47 @@ static inline int bpf_try_make_writable(struct sk_buff *skb, { int err; - if (!skb_cloned(skb)) - return 0; - if (skb_clone_writable(skb, write_len)) - return 0; - err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); - if (!err) - bpf_compute_data_end(skb); + err = skb_ensure_writable(skb, write_len); + bpf_compute_data_end(skb); + return err; } +static inline void bpf_push_mac_rcsum(struct sk_buff *skb) +{ + if (skb_at_tc_ingress(skb)) + skb_postpush_rcsum(skb, skb_mac_header(skb), skb->mac_len); +} + +static inline void bpf_pull_mac_rcsum(struct sk_buff *skb) +{ + if (skb_at_tc_ingress(skb)) + skb_postpull_rcsum(skb, skb_mac_header(skb), skb->mac_len); +} + static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) { - struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp); struct sk_buff *skb = (struct sk_buff *) (long) r1; - int offset = (int) r2; + unsigned int offset = (unsigned int) r2; void *from = (void *) (long) r3; unsigned int len = (unsigned int) r4; void *ptr; if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH))) return -EINVAL; - - /* bpf verifier guarantees that: - * 'from' pointer points to bpf program stack - * 'len' bytes of it were initialized - * 'len' > 0 - * 'skb' is a valid pointer to 'struct sk_buff' - * - * so check for invalid 'offset' and too large 'len' - */ - if (unlikely((u32) offset > 0xffff || len > sizeof(sp->buff))) + if (unlikely(offset > 0xffff)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + len))) return -EFAULT; - ptr = skb_header_pointer(skb, offset, len, sp->buff); - if (unlikely(!ptr)) - return -EFAULT; - + ptr = skb->data + offset; if (flags & BPF_F_RECOMPUTE_CSUM) - skb_postpull_rcsum(skb, ptr, len); + __skb_postpull_rcsum(skb, ptr, len, offset); memcpy(ptr, from, len); - if (ptr == sp->buff) - /* skb_store_bits cannot return -EFAULT here */ - skb_store_bits(skb, offset, ptr, len); - if (flags & BPF_F_RECOMPUTE_CSUM) - skb_postpush_rcsum(skb, ptr, len); + __skb_postpush_rcsum(skb, ptr, len, offset); if (flags & BPF_F_INVALIDATE_HASH) skb_clear_hash(skb); @@ -1425,12 +1416,12 @@ static const struct bpf_func_proto bpf_skb_store_bytes_proto = { static u64 bpf_skb_load_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { const struct sk_buff *skb = (const struct sk_buff *)(unsigned long) r1; - int offset = (int) r2; + unsigned int offset = (unsigned int) r2; void *to = (void *)(unsigned long) r3; unsigned int len = (unsigned int) r4; void *ptr; - if (unlikely((u32) offset > 0xffff)) + if (unlikely(offset > 0xffff)) goto err_clear; ptr = skb_header_pointer(skb, offset, len, to); @@ -1458,20 +1449,17 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = { static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) { struct sk_buff *skb = (struct sk_buff *) (long) r1; - int offset = (int) r2; - __sum16 sum, *ptr; + unsigned int offset = (unsigned int) r2; + __sum16 *ptr; if (unlikely(flags & ~(BPF_F_HDR_FIELD_MASK))) return -EINVAL; - if (unlikely((u32) offset > 0xffff)) + if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; - if (unlikely(bpf_try_make_writable(skb, offset + sizeof(sum)))) - return -EFAULT; - - ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); - if (unlikely(!ptr)) + if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr)))) return -EFAULT; + ptr = (__sum16 *)(skb->data + offset); switch (flags & BPF_F_HDR_FIELD_MASK) { case 0: if (unlikely(from != 0)) @@ -1489,10 +1477,6 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return -EINVAL; } - if (ptr == &sum) - /* skb_store_bits guaranteed to not return -EFAULT here */ - skb_store_bits(skb, offset, ptr, sizeof(sum)); - return 0; } @@ -1512,20 +1496,18 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) struct sk_buff *skb = (struct sk_buff *) (long) r1; bool is_pseudo = flags & BPF_F_PSEUDO_HDR; bool is_mmzero = flags & BPF_F_MARK_MANGLED_0; - int offset = (int) r2; - __sum16 sum, *ptr; + unsigned int offset = (unsigned int) r2; + __sum16 *ptr; if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK))) return -EINVAL; - if (unlikely((u32) offset > 0xffff)) + if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; - if (unlikely(bpf_try_make_writable(skb, offset + sizeof(sum)))) + if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr)))) return -EFAULT; - ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); - if (unlikely(!ptr)) - return -EFAULT; + ptr = (__sum16 *)(skb->data + offset); if (is_mmzero && !*ptr) return 0; @@ -1548,10 +1530,6 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) if (is_mmzero && !*ptr) *ptr = CSUM_MANGLED_0; - if (ptr == &sum) - /* skb_store_bits guaranteed to not return -EFAULT here */ - skb_store_bits(skb, offset, ptr, sizeof(sum)); - return 0; } @@ -1607,9 +1585,6 @@ static const struct bpf_func_proto bpf_csum_diff_proto = { static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb) { - if (skb_at_tc_ingress(skb)) - skb_postpush_rcsum(skb, skb_mac_header(skb), skb->mac_len); - return dev_forward_skb(dev, skb); } @@ -1648,6 +1623,8 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) if (unlikely(!skb)) return -ENOMEM; + bpf_push_mac_rcsum(skb); + return flags & BPF_F_INGRESS ? __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb); } @@ -1693,6 +1670,8 @@ int skb_do_redirect(struct sk_buff *skb) return -EINVAL; } + bpf_push_mac_rcsum(skb); + return ri->flags & BPF_F_INGRESS ? __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb); } @@ -1756,7 +1735,10 @@ static u64 bpf_skb_vlan_push(u64 r1, u64 r2, u64 vlan_tci, u64 r4, u64 r5) vlan_proto != htons(ETH_P_8021AD))) vlan_proto = htons(ETH_P_8021Q); + bpf_push_mac_rcsum(skb); ret = skb_vlan_push(skb, vlan_proto, vlan_tci); + bpf_pull_mac_rcsum(skb); + bpf_compute_data_end(skb); return ret; } @@ -1776,7 +1758,10 @@ static u64 bpf_skb_vlan_pop(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) struct sk_buff *skb = (struct sk_buff *) (long) r1; int ret; + bpf_push_mac_rcsum(skb); ret = skb_vlan_pop(skb); + bpf_pull_mac_rcsum(skb); + bpf_compute_data_end(skb); return ret; } @@ -2298,7 +2283,7 @@ bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) } #ifdef CONFIG_SOCK_CGROUP_DATA -static u64 bpf_skb_in_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +static u64 bpf_skb_under_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { struct sk_buff *skb = (struct sk_buff *)(long)r1; struct bpf_map *map = (struct bpf_map *)(long)r2; @@ -2321,8 +2306,8 @@ static u64 bpf_skb_in_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) return cgroup_is_descendant(sock_cgroup_ptr(&sk->sk_cgrp_data), cgrp); } -static const struct bpf_func_proto bpf_skb_in_cgroup_proto = { - .func = bpf_skb_in_cgroup, +static const struct bpf_func_proto bpf_skb_under_cgroup_proto = { + .func = bpf_skb_under_cgroup, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, @@ -2402,8 +2387,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; #ifdef CONFIG_SOCK_CGROUP_DATA - case BPF_FUNC_skb_in_cgroup: - return &bpf_skb_in_cgroup_proto; + case BPF_FUNC_skb_under_cgroup: + return &bpf_skb_under_cgroup_proto; #endif default: return sk_filter_func_proto(func_id); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index d07fc076bea0..febca0f1008c 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2452,9 +2452,7 @@ struct fib_route_iter { static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, loff_t pos) { - struct fib_table *tb = iter->main_tb; struct key_vector *l, **tp = &iter->tnode; - struct trie *t; t_key key; /* use cache location of next-to-find key */ @@ -2462,8 +2460,6 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, pos -= iter->pos; key = iter->key; } else { - t = (struct trie *)tb->tb_data; - iter->tnode = t->kv; iter->pos = 0; key = 0; } @@ -2504,12 +2500,12 @@ static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos) return NULL; iter->main_tb = tb; + t = (struct trie *)tb->tb_data; + iter->tnode = t->kv; if (*pos != 0) return fib_route_get_idx(iter, *pos); - t = (struct trie *)tb->tb_data; - iter->tnode = t->kv; iter->pos = 0; iter->key = 0; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 5b1481be0282..113cc43df789 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -370,7 +370,6 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, tunnel->parms.o_flags, proto, tunnel->parms.o_key, htonl(tunnel->o_seqno)); - skb_set_inner_protocol(skb, proto); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index a917903d5e97..cc701fa70b12 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -557,6 +557,33 @@ static struct rtnl_link_ops vti_link_ops __read_mostly = { .get_link_net = ip_tunnel_get_link_net, }; +static bool is_vti_tunnel(const struct net_device *dev) +{ + return dev->netdev_ops == &vti_netdev_ops; +} + +static int vti_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct ip_tunnel *tunnel = netdev_priv(dev); + + if (!is_vti_tunnel(dev)) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_DOWN: + if (!net_eq(tunnel->net, dev_net(dev))) + xfrm_garbage_collect(tunnel->net); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block vti_notifier_block __read_mostly = { + .notifier_call = vti_device_event, +}; + static int __init vti_init(void) { const char *msg; @@ -564,6 +591,8 @@ static int __init vti_init(void) pr_info("IPv4 over IPsec tunneling driver\n"); + register_netdevice_notifier(&vti_notifier_block); + msg = "tunnel device"; err = register_pernet_device(&vti_net_ops); if (err < 0) @@ -596,6 +625,7 @@ xfrm_proto_ah_failed: xfrm_proto_esp_failed: unregister_pernet_device(&vti_net_ops); pernet_dev_failed: + unregister_netdevice_notifier(&vti_notifier_block); pr_err("vti init: failed to register %s\n", msg); return err; } @@ -607,6 +637,7 @@ static void __exit vti_fini(void) xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); unregister_pernet_device(&vti_net_ops); + unregister_netdevice_notifier(&vti_notifier_block); } module_init(vti_init); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ab3e796596b1..df8425fcbc2c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3543,7 +3543,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) /* combine the user config with event to determine if permanent * addresses are to be removed from address hash table */ - keep_addr = !(how || _keep_addr <= 0); + keep_addr = !(how || _keep_addr <= 0 || idev->cnf.disable_ipv6); /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { @@ -3599,7 +3599,7 @@ restart: /* re-combine the user config with event to determine if permanent * addresses are to be removed from the interface list */ - keep_addr = (!how && _keep_addr > 0); + keep_addr = (!how && _keep_addr > 0 && !idev->cnf.disable_ipv6); INIT_LIST_HEAD(&del_list); list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index c53b92c617c5..37ac9de713c6 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -952,8 +952,10 @@ calipso_opt_insert(struct ipv6_opt_hdr *hop, memcpy(new, hop, start); ret_val = calipso_genopt((unsigned char *)new, start, buf_len, doi_def, secattr); - if (ret_val < 0) + if (ret_val < 0) { + kfree(new); return ERR_PTR(ret_val); + } buf_len = start + ret_val; /* At this point buf_len aligns to 4n, so (buf_len & 4) pads to 8n */ diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 776d145113e1..704274cbd495 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -519,8 +519,6 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, protocol, tunnel->parms.o_key, htonl(tunnel->o_seqno)); - skb_set_inner_protocol(skb, protocol); - return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, NEXTHDR_GRE); } diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index fed40d1ec29b..0900352c924c 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -55,7 +55,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct icmp6hdr user_icmph; int addr_type; struct in6_addr *daddr; - int iif = 0; + int oif = 0; struct flowi6 fl6; int err; struct dst_entry *dst; @@ -78,25 +78,30 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (u->sin6_family != AF_INET6) { return -EAFNOSUPPORT; } - if (sk->sk_bound_dev_if && - sk->sk_bound_dev_if != u->sin6_scope_id) { - return -EINVAL; - } daddr = &(u->sin6_addr); - iif = u->sin6_scope_id; + if (__ipv6_addr_needs_scope_id(ipv6_addr_type(daddr))) + oif = u->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = &sk->sk_v6_daddr; } - if (!iif) - iif = sk->sk_bound_dev_if; + if (!oif) + oif = sk->sk_bound_dev_if; + + if (!oif) + oif = np->sticky_pktinfo.ipi6_ifindex; + + if (!oif && ipv6_addr_is_multicast(daddr)) + oif = np->mcast_oif; + else if (!oif) + oif = np->ucast_oif; addr_type = ipv6_addr_type(daddr); - if (__ipv6_addr_needs_scope_id(addr_type) && !iif) - return -EINVAL; - if (addr_type & IPV6_ADDR_MAPPED) + if ((__ipv6_addr_needs_scope_id(addr_type) && !oif) || + (addr_type & IPV6_ADDR_MAPPED) || + (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if)) return -EINVAL; /* TODO: use ip6_datagram_send_ctl to get options from cmsg */ @@ -106,16 +111,12 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowi6_proto = IPPROTO_ICMPV6; fl6.saddr = np->saddr; fl6.daddr = *daddr; + fl6.flowi6_oif = oif; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_icmp_type = user_icmph.icmp6_type; fl6.fl6_icmp_code = user_icmph.icmp6_code; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) - fl6.flowi6_oif = np->mcast_oif; - else if (!fl6.flowi6_oif) - fl6.flowi6_oif = np->ucast_oif; - ipc6.tclass = np->tclass; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); diff --git a/net/irda/iriap.c b/net/irda/iriap.c index 4a7ae32afa09..1138eaf5c682 100644 --- a/net/irda/iriap.c +++ b/net/irda/iriap.c @@ -185,8 +185,12 @@ struct iriap_cb *iriap_open(__u8 slsap_sel, int mode, void *priv, self->magic = IAS_MAGIC; self->mode = mode; - if (mode == IAS_CLIENT) - iriap_register_lsap(self, slsap_sel, mode); + if (mode == IAS_CLIENT) { + if (iriap_register_lsap(self, slsap_sel, mode)) { + kfree(self); + return NULL; + } + } self->confirm = callback; self->priv = priv; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 47e99ab8d97a..543b1d4fc33d 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -869,7 +869,7 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) /* free all potentially still buffered bcast frames */ local->total_ps_buffered -= skb_queue_len(&sdata->u.ap.ps.bc_buf); - skb_queue_purge(&sdata->u.ap.ps.bc_buf); + ieee80211_purge_tx_queue(&local->hw, &sdata->u.ap.ps.bc_buf); mutex_lock(&local->mtx); ieee80211_vif_copy_chanctx_to_vlans(sdata, true); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 184473c257eb..ba5fc1f01e53 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1094,7 +1094,7 @@ static inline u32 drv_get_expected_throughput(struct ieee80211_local *local, trace_drv_get_expected_throughput(sta); if (local->ops->get_expected_throughput) - ret = local->ops->get_expected_throughput(sta); + ret = local->ops->get_expected_throughput(&local->hw, sta); trace_drv_return_u32(local, ret); return ret; diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index c66411df9863..42120d965263 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -881,20 +881,22 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata) netif_carrier_off(sdata->dev); + /* flush STAs and mpaths on this iface */ + sta_info_flush(sdata); + mesh_path_flush_by_iface(sdata); + /* stop the beacon */ ifmsh->mesh_id_len = 0; sdata->vif.bss_conf.enable_beacon = false; clear_bit(SDATA_STATE_OFFCHANNEL_BEACON_STOPPED, &sdata->state); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED); + + /* remove beacon */ bcn = rcu_dereference_protected(ifmsh->beacon, lockdep_is_held(&sdata->wdev.mtx)); RCU_INIT_POINTER(ifmsh->beacon, NULL); kfree_rcu(bcn, rcu_head); - /* flush STAs and mpaths on this iface */ - sta_info_flush(sdata); - mesh_path_flush_by_iface(sdata); - /* free all potentially still buffered group-addressed frames */ local->total_ps_buffered -= skb_queue_len(&ifmsh->ps.bc_buf); skb_queue_purge(&ifmsh->ps.bc_buf); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 2e8a9024625a..9dce3b157908 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1268,7 +1268,7 @@ static void sta_ps_start(struct sta_info *sta) for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) { struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]); - if (!txqi->tin.backlog_packets) + if (txqi->tin.backlog_packets) set_bit(tid, &sta->txq_buffered_tids); else clear_bit(tid, &sta->txq_buffered_tids); diff --git a/net/mac80211/status.c b/net/mac80211/status.c index c6d5c724e032..a2a68269675d 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -771,6 +771,13 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) clear_sta_flag(sta, WLAN_STA_SP); acked = !!(info->flags & IEEE80211_TX_STAT_ACK); + + /* mesh Peer Service Period support */ + if (ieee80211_vif_is_mesh(&sta->sdata->vif) && + ieee80211_is_data_qos(fc)) + ieee80211_mpsp_trigger_process( + ieee80211_get_qos_ctl(hdr), sta, true, acked); + if (!acked && test_sta_flag(sta, WLAN_STA_PS_STA)) { /* * The STA is in power save mode, so assume @@ -781,13 +788,6 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) return; } - /* mesh Peer Service Period support */ - if (ieee80211_vif_is_mesh(&sta->sdata->vif) && - ieee80211_is_data_qos(fc)) - ieee80211_mpsp_trigger_process( - ieee80211_get_qos_ctl(hdr), - sta, true, acked); - if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL) && (ieee80211_is_data(hdr->frame_control)) && (rates_idx != -1)) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 91461c415525..502396694f47 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -368,7 +368,7 @@ static void purge_old_ps_buffers(struct ieee80211_local *local) skb = skb_dequeue(&ps->bc_buf); if (skb) { purged++; - dev_kfree_skb(skb); + ieee80211_free_txskb(&local->hw, skb); } total += skb_queue_len(&ps->bc_buf); } @@ -451,7 +451,7 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx) if (skb_queue_len(&ps->bc_buf) >= AP_MAX_BC_BUFFER) { ps_dbg(tx->sdata, "BC TX buffer full - dropping the oldest frame\n"); - dev_kfree_skb(skb_dequeue(&ps->bc_buf)); + ieee80211_free_txskb(&tx->local->hw, skb_dequeue(&ps->bc_buf)); } else tx->local->total_ps_buffered++; @@ -4275,7 +4275,7 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw, sdata = IEEE80211_DEV_TO_SUB_IF(skb->dev); if (!ieee80211_tx_prepare(sdata, &tx, NULL, skb)) break; - dev_kfree_skb_any(skb); + ieee80211_free_txskb(hw, skb); } info = IEEE80211_SKB_CB(skb); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 9e3693128313..f8dbacf66795 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -574,7 +574,7 @@ static int exp_seq_show(struct seq_file *s, void *v) helper = rcu_dereference(nfct_help(expect->master)->helper); if (helper) { seq_printf(s, "%s%s", expect->flags ? " " : "", helper->name); - if (helper->expect_policy[expect->class].name) + if (helper->expect_policy[expect->class].name[0]) seq_printf(s, "/%s", helper->expect_policy[expect->class].name); } diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index bb77a97961bf..5c0db5c64734 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -1473,7 +1473,8 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, "timeout to %u seconds for", info->timeout); nf_ct_dump_tuple(&exp->tuple); - mod_timer(&exp->timeout, jiffies + info->timeout * HZ); + mod_timer_pending(&exp->timeout, + jiffies + info->timeout * HZ); } spin_unlock_bh(&nf_conntrack_expect_lock); } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 050bb3420a6b..fdfc71f416b7 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1894,6 +1894,8 @@ static int ctnetlink_new_conntrack(struct net *net, struct sock *ctnl, if (!cda[CTA_TUPLE_ORIG] || !cda[CTA_TUPLE_REPLY]) return -EINVAL; + if (otuple.dst.protonum != rtuple.dst.protonum) + return -EINVAL; ct = ctnetlink_create_conntrack(net, &zone, cda, &otuple, &rtuple, u3); @@ -2362,12 +2364,8 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, return PTR_ERR(exp); err = nf_ct_expect_related_report(exp, portid, report); - if (err < 0) { - nf_ct_expect_put(exp); - return err; - } - - return 0; + nf_ct_expect_put(exp); + return err; } static void ctnetlink_glue_seqadj(struct sk_buff *skb, struct nf_conn *ct, diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 8d9db9d4702b..7d77217de6a3 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1383,7 +1383,7 @@ static int process_sip_response(struct sk_buff *skb, unsigned int protoff, return NF_DROP; } cseq = simple_strtoul(*dptr + matchoff, NULL, 10); - if (!cseq) { + if (!cseq && *(*dptr + matchoff) != '0') { nf_ct_helper_log(skb, ct, "cannot get cseq"); return NF_DROP; } @@ -1446,7 +1446,7 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff, return NF_DROP; } cseq = simple_strtoul(*dptr + matchoff, NULL, 10); - if (!cseq) { + if (!cseq && *(*dptr + matchoff) != '0') { nf_ct_helper_log(skb, ct, "cannot get cseq"); return NF_DROP; } diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 5d36a0926b4a..f49f45081acb 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1145,10 +1145,8 @@ static int nfqnl_recv_verdict(struct net *net, struct sock *ctnl, struct nfnl_queue_net *q = nfnl_queue_pernet(net); int err; - queue = instance_lookup(q, queue_num); - if (!queue) - queue = verdict_instance_lookup(q, queue_num, - NETLINK_CB(skb).portid); + queue = verdict_instance_lookup(q, queue_num, + NETLINK_CB(skb).portid); if (IS_ERR(queue)) return PTR_ERR(queue); diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index ba7aed13e174..82c264e40278 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -59,6 +59,7 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_exthdr *priv = nft_expr_priv(expr); + u32 offset, len; if (tb[NFTA_EXTHDR_DREG] == NULL || tb[NFTA_EXTHDR_TYPE] == NULL || @@ -66,9 +67,15 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, tb[NFTA_EXTHDR_LEN] == NULL) return -EINVAL; + offset = ntohl(nla_get_be32(tb[NFTA_EXTHDR_OFFSET])); + len = ntohl(nla_get_be32(tb[NFTA_EXTHDR_LEN])); + + if (offset > U8_MAX || len > U8_MAX) + return -ERANGE; + priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]); - priv->offset = ntohl(nla_get_be32(tb[NFTA_EXTHDR_OFFSET])); - priv->len = ntohl(nla_get_be32(tb[NFTA_EXTHDR_LEN])); + priv->offset = offset; + priv->len = len; priv->dreg = nft_parse_register(tb[NFTA_EXTHDR_DREG]); return nft_validate_register_store(ctx, priv->dreg, NULL, diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c index 6473936d05c6..ffe9ae062d23 100644 --- a/net/netfilter/nft_rbtree.c +++ b/net/netfilter/nft_rbtree.c @@ -70,7 +70,6 @@ static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, } else if (d > 0) parent = parent->rb_right; else { -found: if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = parent->rb_left; continue; @@ -84,9 +83,12 @@ found: } } - if (set->flags & NFT_SET_INTERVAL && interval != NULL) { - rbe = interval; - goto found; + if (set->flags & NFT_SET_INTERVAL && interval != NULL && + nft_set_elem_active(&interval->ext, genmask) && + !nft_rbtree_interval_end(interval)) { + spin_unlock_bh(&nft_rbtree_lock); + *ext = &interval->ext; + return true; } out: spin_unlock_bh(&nft_rbtree_lock); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index c644c78ed485..e054a748ff25 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -433,7 +433,6 @@ ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone, struct nf_conntrack_l4proto *l4proto; struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; - enum ip_conntrack_info ctinfo; struct nf_conn *ct; unsigned int dataoff; u8 protonum; @@ -458,13 +457,8 @@ ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone, ct = nf_ct_tuplehash_to_ctrack(h); - ctinfo = ovs_ct_get_info(h); - if (ctinfo == IP_CT_NEW) { - /* This should not happen. */ - WARN_ONCE(1, "ovs_ct_find_existing: new packet for %p\n", ct); - } skb->nfct = &ct->ct_general; - skb->nfctinfo = ctinfo; + skb->nfctinfo = ovs_ct_get_info(h); return ct; } diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index 1a1fcec88695..5aaf3babfc3f 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -93,7 +93,14 @@ static struct vport *geneve_tnl_create(const struct vport_parms *parms) return ERR_CAST(dev); } - dev_change_flags(dev, dev->flags | IFF_UP); + err = dev_change_flags(dev, dev->flags | IFF_UP); + if (err < 0) { + rtnl_delete_link(dev); + rtnl_unlock(); + ovs_vport_free(vport); + goto error; + } + rtnl_unlock(); return vport; error: diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index 7f8897f33a67..0e72d95b0e8f 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -54,6 +54,7 @@ static struct vport *gre_tnl_create(const struct vport_parms *parms) struct net *net = ovs_dp_get_net(parms->dp); struct net_device *dev; struct vport *vport; + int err; vport = ovs_vport_alloc(0, &ovs_gre_vport_ops, parms); if (IS_ERR(vport)) @@ -67,9 +68,15 @@ static struct vport *gre_tnl_create(const struct vport_parms *parms) return ERR_CAST(dev); } - dev_change_flags(dev, dev->flags | IFF_UP); - rtnl_unlock(); + err = dev_change_flags(dev, dev->flags | IFF_UP); + if (err < 0) { + rtnl_delete_link(dev); + rtnl_unlock(); + ovs_vport_free(vport); + return ERR_PTR(err); + } + rtnl_unlock(); return vport; } diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 434e04c3a189..95c36147a6e1 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -140,7 +140,7 @@ internal_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) static void internal_set_rx_headroom(struct net_device *dev, int new_hr) { - dev->needed_headroom = new_hr; + dev->needed_headroom = new_hr < 0 ? 0 : new_hr; } static const struct net_device_ops internal_dev_netdev_ops = { diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 5eb7694348b5..7eb955e453e6 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -130,7 +130,14 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms) return ERR_CAST(dev); } - dev_change_flags(dev, dev->flags | IFF_UP); + err = dev_change_flags(dev, dev->flags | IFF_UP); + if (err < 0) { + rtnl_delete_link(dev); + rtnl_unlock(); + ovs_vport_free(vport); + goto error; + } + rtnl_unlock(); return vport; error: diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 1bb9e7ac9e14..ff83fb1ddd47 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -425,6 +425,7 @@ struct rxrpc_call { spinlock_t lock; rwlock_t state_lock; /* lock for state transition */ atomic_t usage; + atomic_t skb_count; /* Outstanding packets on this call */ atomic_t sequence; /* Tx data packet sequence counter */ u32 local_abort; /* local abort code */ u32 remote_abort; /* remote abort code */ diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 0b2832141bd0..9bae21e66d65 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -130,6 +130,7 @@ static int rxrpc_accept_incoming_call(struct rxrpc_local *local, call->state = RXRPC_CALL_SERVER_ACCEPTING; list_add_tail(&call->accept_link, &rx->acceptq); rxrpc_get_call(call); + atomic_inc(&call->skb_count); nsp = rxrpc_skb(notification); nsp->call = call; diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index fc32aa5764a2..e60cf65c2232 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -460,6 +460,7 @@ static void rxrpc_insert_oos_packet(struct rxrpc_call *call, ASSERTCMP(sp->call, ==, NULL); sp->call = call; rxrpc_get_call(call); + atomic_inc(&call->skb_count); /* insert into the buffer in sequence order */ spin_lock_bh(&call->lock); @@ -734,6 +735,7 @@ all_acked: skb->mark = RXRPC_SKB_MARK_FINAL_ACK; sp->call = call; rxrpc_get_call(call); + atomic_inc(&call->skb_count); spin_lock_bh(&call->lock); if (rxrpc_queue_rcv_skb(call, skb, true, true) < 0) BUG(); @@ -793,6 +795,7 @@ static int rxrpc_post_message(struct rxrpc_call *call, u32 mark, u32 error, sp->error = error; sp->call = call; rxrpc_get_call(call); + atomic_inc(&call->skb_count); spin_lock_bh(&call->lock); ret = rxrpc_queue_rcv_skb(call, skb, true, fatal); @@ -834,6 +837,9 @@ void rxrpc_process_call(struct work_struct *work) return; } + if (!call->conn) + goto skip_msg_init; + /* there's a good chance we're going to have to send a message, so set * one up in advance */ msg.msg_name = &call->conn->params.peer->srx.transport; @@ -856,6 +862,7 @@ void rxrpc_process_call(struct work_struct *work) memset(iov, 0, sizeof(iov)); iov[0].iov_base = &whdr; iov[0].iov_len = sizeof(whdr); +skip_msg_init: /* deal with events of a final nature */ if (test_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events)) { diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 91287c9d01bb..ae057e0740f3 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -275,6 +275,7 @@ error: list_del_init(&call->link); write_unlock_bh(&rxrpc_call_lock); + set_bit(RXRPC_CALL_RELEASED, &call->flags); call->state = RXRPC_CALL_DEAD; rxrpc_put_call(call); _leave(" = %d", ret); @@ -287,6 +288,7 @@ error: */ found_user_ID_now_present: write_unlock(&rx->call_lock); + set_bit(RXRPC_CALL_RELEASED, &call->flags); call->state = RXRPC_CALL_DEAD; rxrpc_put_call(call); _leave(" = -EEXIST [%p]", call); @@ -491,15 +493,9 @@ void rxrpc_release_call(struct rxrpc_call *call) spin_lock_bh(&call->lock); while ((skb = skb_dequeue(&call->rx_queue)) || (skb = skb_dequeue(&call->rx_oos_queue))) { - sp = rxrpc_skb(skb); - if (sp->call) { - ASSERTCMP(sp->call, ==, call); - rxrpc_put_call(call); - sp->call = NULL; - } - skb->destructor = NULL; spin_unlock_bh(&call->lock); + sp = rxrpc_skb(skb); _debug("- zap %s %%%u #%u", rxrpc_pkts[sp->hdr.type], sp->hdr.serial, sp->hdr.seq); @@ -605,6 +601,7 @@ void __rxrpc_put_call(struct rxrpc_call *call) if (atomic_dec_and_test(&call->usage)) { _debug("call %d dead", call->debug_id); + WARN_ON(atomic_read(&call->skb_count) != 0); ASSERTCMP(call->state, ==, RXRPC_CALL_DEAD); rxrpc_queue_work(&call->destroyer); } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 991a20d25093..70bb77818dea 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -55,9 +55,6 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb, if (test_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags)) { _debug("already terminated"); ASSERTCMP(call->state, >=, RXRPC_CALL_COMPLETE); - skb->destructor = NULL; - sp->call = NULL; - rxrpc_put_call(call); rxrpc_free_skb(skb); return 0; } @@ -111,13 +108,7 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb, ret = 0; out: - /* release the socket buffer */ - if (skb) { - skb->destructor = NULL; - sp->call = NULL; - rxrpc_put_call(call); - rxrpc_free_skb(skb); - } + rxrpc_free_skb(skb); _leave(" = %d", ret); return ret; @@ -133,11 +124,15 @@ static int rxrpc_fast_process_data(struct rxrpc_call *call, struct rxrpc_skb_priv *sp; bool terminal; int ret, ackbit, ack; + u32 serial; + u8 flags; _enter("{%u,%u},,{%u}", call->rx_data_post, call->rx_first_oos, seq); sp = rxrpc_skb(skb); ASSERTCMP(sp->call, ==, NULL); + flags = sp->hdr.flags; + serial = sp->hdr.serial; spin_lock(&call->lock); @@ -200,8 +195,9 @@ static int rxrpc_fast_process_data(struct rxrpc_call *call, sp->call = call; rxrpc_get_call(call); - terminal = ((sp->hdr.flags & RXRPC_LAST_PACKET) && - !(sp->hdr.flags & RXRPC_CLIENT_INITIATED)); + atomic_inc(&call->skb_count); + terminal = ((flags & RXRPC_LAST_PACKET) && + !(flags & RXRPC_CLIENT_INITIATED)); ret = rxrpc_queue_rcv_skb(call, skb, false, terminal); if (ret < 0) { if (ret == -ENOMEM || ret == -ENOBUFS) { @@ -213,12 +209,13 @@ static int rxrpc_fast_process_data(struct rxrpc_call *call, } skb = NULL; + sp = NULL; _debug("post #%u", seq); ASSERTCMP(call->rx_data_post, ==, seq); call->rx_data_post++; - if (sp->hdr.flags & RXRPC_LAST_PACKET) + if (flags & RXRPC_LAST_PACKET) set_bit(RXRPC_CALL_RCVD_LAST, &call->flags); /* if we've reached an out of sequence packet then we need to drain @@ -234,7 +231,7 @@ static int rxrpc_fast_process_data(struct rxrpc_call *call, spin_unlock(&call->lock); atomic_inc(&call->ackr_not_idle); - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, sp->hdr.serial, false); + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, false); _leave(" = 0 [posted]"); return 0; @@ -247,7 +244,7 @@ out: discard_and_ack: _debug("discard and ACK packet %p", skb); - __rxrpc_propose_ACK(call, ack, sp->hdr.serial, true); + __rxrpc_propose_ACK(call, ack, serial, true); discard: spin_unlock(&call->lock); rxrpc_free_skb(skb); @@ -255,7 +252,7 @@ discard: return 0; enqueue_and_ack: - __rxrpc_propose_ACK(call, ack, sp->hdr.serial, true); + __rxrpc_propose_ACK(call, ack, serial, true); enqueue_packet: _net("defer skb %p", skb); spin_unlock(&call->lock); @@ -575,13 +572,13 @@ done: * post connection-level events to the connection * - this includes challenges, responses and some aborts */ -static bool rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, +static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, struct sk_buff *skb) { _enter("%p,%p", conn, skb); skb_queue_tail(&conn->rx_queue, skb); - return rxrpc_queue_conn(conn); + rxrpc_queue_conn(conn); } /* @@ -702,7 +699,6 @@ void rxrpc_data_ready(struct sock *sk) rcu_read_lock(); -retry_find_conn: conn = rxrpc_find_connection_rcu(local, skb); if (!conn) goto cant_route_call; @@ -710,8 +706,7 @@ retry_find_conn: if (sp->hdr.callNumber == 0) { /* Connection-level packet */ _debug("CONN %p {%d}", conn, conn->debug_id); - if (!rxrpc_post_packet_to_conn(conn, skb)) - goto retry_find_conn; + rxrpc_post_packet_to_conn(conn, skb); } else { /* Call-bound packets are routed by connection channel. */ unsigned int channel = sp->hdr.cid & RXRPC_CHANNELMASK; @@ -749,6 +744,8 @@ cant_route_call: if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) { _debug("reject type %d",sp->hdr.type); rxrpc_reject_packet(local, skb); + } else { + rxrpc_free_skb(skb); } _leave(" [no call]"); return; diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index a3fa2ed85d63..9ed66d533002 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -203,6 +203,9 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, } /* we transferred the whole data packet */ + if (!(flags & MSG_PEEK)) + rxrpc_kernel_data_consumed(call, skb); + if (sp->hdr.flags & RXRPC_LAST_PACKET) { _debug("last"); if (rxrpc_conn_is_client(call->conn)) { @@ -360,28 +363,6 @@ wait_error: } /** - * rxrpc_kernel_data_delivered - Record delivery of data message - * @skb: Message holding data - * - * Record the delivery of a data message. This permits RxRPC to keep its - * tracking correct. The socket buffer will be deleted. - */ -void rxrpc_kernel_data_delivered(struct sk_buff *skb) -{ - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxrpc_call *call = sp->call; - - ASSERTCMP(sp->hdr.seq, >=, call->rx_data_recv); - ASSERTCMP(sp->hdr.seq, <=, call->rx_data_recv + 1); - call->rx_data_recv = sp->hdr.seq; - - ASSERTCMP(sp->hdr.seq, >, call->rx_data_eaten); - rxrpc_free_skb(skb); -} - -EXPORT_SYMBOL(rxrpc_kernel_data_delivered); - -/** * rxrpc_kernel_is_data_last - Determine if data message is last one * @skb: Message holding data * diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c index eee0cfd9ac8c..06c51d4b622d 100644 --- a/net/rxrpc/skbuff.c +++ b/net/rxrpc/skbuff.c @@ -98,11 +98,39 @@ static void rxrpc_hard_ACK_data(struct rxrpc_call *call, spin_unlock_bh(&call->lock); } +/** + * rxrpc_kernel_data_consumed - Record consumption of data message + * @call: The call to which the message pertains. + * @skb: Message holding data + * + * Record the consumption of a data message and generate an ACK if appropriate. + * The call state is shifted if this was the final packet. The caller must be + * in process context with no spinlocks held. + * + * TODO: Actually generate the ACK here rather than punting this to the + * workqueue. + */ +void rxrpc_kernel_data_consumed(struct rxrpc_call *call, struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + _enter("%d,%p{%u}", call->debug_id, skb, sp->hdr.seq); + + ASSERTCMP(sp->call, ==, call); + ASSERTCMP(sp->hdr.type, ==, RXRPC_PACKET_TYPE_DATA); + + /* TODO: Fix the sequence number tracking */ + ASSERTCMP(sp->hdr.seq, >=, call->rx_data_recv); + ASSERTCMP(sp->hdr.seq, <=, call->rx_data_recv + 1); + ASSERTCMP(sp->hdr.seq, >, call->rx_data_eaten); + + call->rx_data_recv = sp->hdr.seq; + rxrpc_hard_ACK_data(call, sp); +} +EXPORT_SYMBOL(rxrpc_kernel_data_consumed); + /* - * destroy a packet that has an RxRPC control buffer - * - advance the hard-ACK state of the parent call (done here in case something - * in the kernel bypasses recvmsg() and steals the packet directly off of the - * socket receive queue) + * Destroy a packet that has an RxRPC control buffer */ void rxrpc_packet_destructor(struct sk_buff *skb) { @@ -112,9 +140,8 @@ void rxrpc_packet_destructor(struct sk_buff *skb) _enter("%p{%p}", skb, call); if (call) { - /* send the final ACK on a client call */ - if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA) - rxrpc_hard_ACK_data(call, sp); + if (atomic_dec_return(&call->skb_count) < 0) + BUG(); rxrpc_put_call(call); sp->call = NULL; } diff --git a/net/sched/act_api.c b/net/sched/act_api.c index e4a5f2607ffa..d09d0687594b 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -64,7 +64,6 @@ int __tcf_hash_release(struct tc_action *p, bool bind, bool strict) if (p->tcfa_bindcnt <= 0 && p->tcfa_refcnt <= 0) { if (p->ops->cleanup) p->ops->cleanup(p, bind); - list_del(&p->list); tcf_hash_destroy(p->hinfo, p); ret = ACT_P_DELETED; } @@ -421,18 +420,19 @@ static struct tc_action_ops *tc_lookup_action(struct nlattr *kind) return res; } -int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions, - struct tcf_result *res) +int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, + int nr_actions, struct tcf_result *res) { - const struct tc_action *a; - int ret = -1; + int ret = -1, i; if (skb->tc_verd & TC_NCLS) { skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); ret = TC_ACT_OK; goto exec_done; } - list_for_each_entry(a, actions, list) { + for (i = 0; i < nr_actions; i++) { + const struct tc_action *a = actions[i]; + repeat: ret = a->ops->act(skb, a, res); if (ret == TC_ACT_REPEAT) @@ -754,16 +754,6 @@ err_out: return ERR_PTR(err); } -static void cleanup_a(struct list_head *actions) -{ - struct tc_action *a, *tmp; - - list_for_each_entry_safe(a, tmp, actions, list) { - list_del(&a->list); - kfree(a); - } -} - static int tca_action_flush(struct net *net, struct nlattr *nla, struct nlmsghdr *n, u32 portid) { @@ -905,7 +895,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, return ret; } err: - cleanup_a(&actions); + tcf_action_destroy(&actions, 0); return ret; } @@ -942,15 +932,9 @@ tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n, ret = tcf_action_init(net, nla, NULL, NULL, ovr, 0, &actions); if (ret) - goto done; + return ret; - /* dump then free all the actions after update; inserted policy - * stays intact - */ - ret = tcf_add_notify(net, n, &actions, portid); - cleanup_a(&actions); -done: - return ret; + return tcf_add_notify(net, n, &actions, portid); } static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n) diff --git a/net/sched/act_police.c b/net/sched/act_police.c index b3c7e975fc9e..8a3be1d99775 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -63,49 +63,8 @@ static int tcf_act_police_walker(struct net *net, struct sk_buff *skb, const struct tc_action_ops *ops) { struct tc_action_net *tn = net_generic(net, police_net_id); - struct tcf_hashinfo *hinfo = tn->hinfo; - int err = 0, index = -1, i = 0, s_i = 0, n_i = 0; - struct nlattr *nest; - - spin_lock_bh(&hinfo->lock); - - s_i = cb->args[0]; - - for (i = 0; i < (POL_TAB_MASK + 1); i++) { - struct hlist_head *head; - struct tc_action *p; - - head = &hinfo->htab[tcf_hash(i, POL_TAB_MASK)]; - - hlist_for_each_entry_rcu(p, head, tcfa_head) { - index++; - if (index < s_i) - continue; - nest = nla_nest_start(skb, index); - if (nest == NULL) - goto nla_put_failure; - if (type == RTM_DELACTION) - err = tcf_action_dump_1(skb, p, 0, 1); - else - err = tcf_action_dump_1(skb, p, 0, 0); - if (err < 0) { - index--; - nla_nest_cancel(skb, nest); - goto done; - } - nla_nest_end(skb, nest); - n_i++; - } - } -done: - spin_unlock_bh(&hinfo->lock); - if (n_i) - cb->args[0] += n_i; - return n_i; -nla_put_failure: - nla_nest_cancel(skb, nest); - goto done; + return tcf_generic_walker(tn, skb, cb, type, ops); } static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { @@ -125,6 +84,7 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla, struct tcf_police *police; struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL; struct tc_action_net *tn = net_generic(net, police_net_id); + bool exists = false; int size; if (nla == NULL) @@ -139,24 +99,24 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla, size = nla_len(tb[TCA_POLICE_TBF]); if (size != sizeof(*parm) && size != sizeof(struct tc_police_compat)) return -EINVAL; + parm = nla_data(tb[TCA_POLICE_TBF]); + exists = tcf_hash_check(tn, parm->index, a, bind); + if (exists && bind) + return 0; - if (parm->index) { - if (tcf_hash_check(tn, parm->index, a, bind)) { - if (ovr) - goto override; - /* not replacing */ - return -EEXIST; - } - } else { + if (!exists) { ret = tcf_hash_create(tn, parm->index, NULL, a, &act_police_ops, bind, false); if (ret) return ret; ret = ACT_P_CREATED; + } else { + tcf_hash_release(*a, bind); + if (!ovr) + return -EEXIST; } -override: police = to_police(*a); if (parm->rate.rate) { err = -ENOMEM; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 843a716a4303..a7c5645373af 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -541,8 +541,12 @@ out: void tcf_exts_destroy(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT - tcf_action_destroy(&exts->actions, TCA_ACT_UNBIND); - INIT_LIST_HEAD(&exts->actions); + LIST_HEAD(actions); + + tcf_exts_to_list(exts, &actions); + tcf_action_destroy(&actions, TCA_ACT_UNBIND); + kfree(exts->actions); + exts->nr_actions = 0; #endif } EXPORT_SYMBOL(tcf_exts_destroy); @@ -554,7 +558,6 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, { struct tc_action *act; - INIT_LIST_HEAD(&exts->actions); if (exts->police && tb[exts->police]) { act = tcf_action_init_1(net, tb[exts->police], rate_tlv, "police", ovr, @@ -563,14 +566,20 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, return PTR_ERR(act); act->type = exts->type = TCA_OLD_COMPAT; - list_add(&act->list, &exts->actions); + exts->actions[0] = act; + exts->nr_actions = 1; } else if (exts->action && tb[exts->action]) { - int err; + LIST_HEAD(actions); + int err, i = 0; + err = tcf_action_init(net, tb[exts->action], rate_tlv, NULL, ovr, - TCA_ACT_BIND, &exts->actions); + TCA_ACT_BIND, &actions); if (err) return err; + list_for_each_entry(act, &actions, list) + exts->actions[i++] = act; + exts->nr_actions = i; } } #else @@ -587,37 +596,49 @@ void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst, struct tcf_exts *src) { #ifdef CONFIG_NET_CLS_ACT - LIST_HEAD(tmp); + struct tcf_exts old = *dst; + tcf_tree_lock(tp); - list_splice_init(&dst->actions, &tmp); - list_splice(&src->actions, &dst->actions); + dst->nr_actions = src->nr_actions; + dst->actions = src->actions; dst->type = src->type; tcf_tree_unlock(tp); - tcf_action_destroy(&tmp, TCA_ACT_UNBIND); + + tcf_exts_destroy(&old); #endif } EXPORT_SYMBOL(tcf_exts_change); -#define tcf_exts_first_act(ext) \ - list_first_entry_or_null(&(exts)->actions, \ - struct tc_action, list) +#ifdef CONFIG_NET_CLS_ACT +static struct tc_action *tcf_exts_first_act(struct tcf_exts *exts) +{ + if (exts->nr_actions == 0) + return NULL; + else + return exts->actions[0]; +} +#endif int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT struct nlattr *nest; - if (exts->action && !list_empty(&exts->actions)) { + if (exts->action && exts->nr_actions) { /* * again for backward compatible mode - we want * to work with both old and new modes of entering * tc data even if iproute2 was newer - jhs */ if (exts->type != TCA_OLD_COMPAT) { + LIST_HEAD(actions); + nest = nla_nest_start(skb, exts->action); if (nest == NULL) goto nla_put_failure; - if (tcf_action_dump(skb, &exts->actions, 0, 0) < 0) + + tcf_exts_to_list(exts, &actions); + if (tcf_action_dump(skb, &actions, 0, 0) < 0) goto nla_put_failure; nla_nest_end(skb, nest); } else if (exts->police) { diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 4cb5aedfe3ee..ef8ba77a5bea 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -293,6 +293,7 @@ static void *sctp_transport_seq_start(struct seq_file *seq, loff_t *pos) return ERR_PTR(err); } + iter->start_fail = 0; return sctp_transport_get_idx(seq_file_net(seq), &iter->hti, *pos); } diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c index f69edcf219e5..bb691538adc8 100644 --- a/net/sctp/sctp_diag.c +++ b/net/sctp/sctp_diag.c @@ -13,6 +13,7 @@ static void inet_diag_msg_sctpasoc_fill(struct inet_diag_msg *r, { union sctp_addr laddr, paddr; struct dst_entry *dst; + struct timer_list *t3_rtx = &asoc->peer.primary_path->T3_rtx_timer; laddr = list_entry(asoc->base.bind_addr.address_list.next, struct sctp_sockaddr_entry, list)->a; @@ -40,10 +41,15 @@ static void inet_diag_msg_sctpasoc_fill(struct inet_diag_msg *r, } r->idiag_state = asoc->state; - r->idiag_timer = SCTP_EVENT_TIMEOUT_T3_RTX; - r->idiag_retrans = asoc->rtx_data_chunks; - r->idiag_expires = jiffies_to_msecs( - asoc->timeouts[SCTP_EVENT_TIMEOUT_T3_RTX] - jiffies); + if (timer_pending(t3_rtx)) { + r->idiag_timer = SCTP_EVENT_TIMEOUT_T3_RTX; + r->idiag_retrans = asoc->rtx_data_chunks; + r->idiag_expires = jiffies_to_msecs(t3_rtx->expires - jiffies); + } else { + r->idiag_timer = 0; + r->idiag_retrans = 0; + r->idiag_expires = 0; + } } static int inet_diag_msg_sctpladdrs_fill(struct sk_buff *skb, @@ -350,7 +356,7 @@ static int sctp_ep_dump(struct sctp_endpoint *ep, void *p) if (cb->args[4] < cb->args[1]) goto next; - if ((r->idiag_states & ~TCPF_LISTEN) && !list_empty(&ep->asocs)) + if (!(r->idiag_states & TCPF_LISTEN) && !list_empty(&ep->asocs)) goto next; if (r->sdiag_family != AF_UNSPEC && @@ -465,7 +471,7 @@ skip: * 3 : to mark if we have dumped the ep info of the current asoc * 4 : to work as a temporary variable to traversal list */ - if (!(idiag_states & ~TCPF_LISTEN)) + if (!(idiag_states & ~(TCPF_LISTEN | TCPF_CLOSE))) goto done; sctp_for_each_transport(sctp_tsp_dump, net, cb->args[2], &commp); done: diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 1bc4f71aaba8..d85b803da11d 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -702,14 +702,14 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, */ sctp_ulpevent_init(event, 0, skb->len + sizeof(struct sk_buff)); - sctp_ulpevent_receive_data(event, asoc); - /* And hold the chunk as we need it for getting the IP headers * later in recvmsg */ sctp_chunk_hold(chunk); event->chunk = chunk; + sctp_ulpevent_receive_data(event, asoc); + event->stream = ntohs(chunk->subh.data_hdr->stream); event->ssn = ntohs(chunk->subh.data_hdr->ssn); event->ppid = chunk->subh.data_hdr->ppid; diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 23c8e7c39656..976c7812bbd5 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -340,12 +340,14 @@ gss_release_msg(struct gss_upcall_msg *gss_msg) } static struct gss_upcall_msg * -__gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid) +__gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid, const struct gss_auth *auth) { struct gss_upcall_msg *pos; list_for_each_entry(pos, &pipe->in_downcall, list) { if (!uid_eq(pos->uid, uid)) continue; + if (auth && pos->auth->service != auth->service) + continue; atomic_inc(&pos->count); dprintk("RPC: %s found msg %p\n", __func__, pos); return pos; @@ -365,7 +367,7 @@ gss_add_msg(struct gss_upcall_msg *gss_msg) struct gss_upcall_msg *old; spin_lock(&pipe->lock); - old = __gss_find_upcall(pipe, gss_msg->uid); + old = __gss_find_upcall(pipe, gss_msg->uid, gss_msg->auth); if (old == NULL) { atomic_inc(&gss_msg->count); list_add(&gss_msg->list, &pipe->in_downcall); @@ -714,7 +716,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) err = -ENOENT; /* Find a matching upcall */ spin_lock(&pipe->lock); - gss_msg = __gss_find_upcall(pipe, uid); + gss_msg = __gss_find_upcall(pipe, uid, NULL); if (gss_msg == NULL) { spin_unlock(&pipe->lock); goto err_put_ctx; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index cb49898a5a58..7f79fb7dc6a0 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2638,6 +2638,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, { struct rpc_xprt_switch *xps; struct rpc_xprt *xprt; + unsigned long reconnect_timeout; unsigned char resvport; int ret = 0; @@ -2649,6 +2650,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, return -EAGAIN; } resvport = xprt->resvport; + reconnect_timeout = xprt->max_reconnect_timeout; rcu_read_unlock(); xprt = xprt_create_transport(xprtargs); @@ -2657,6 +2659,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, goto out_put_switch; } xprt->resvport = resvport; + xprt->max_reconnect_timeout = reconnect_timeout; rpc_xprt_switch_set_roundrobin(xps); if (setup) { @@ -2673,6 +2676,27 @@ out_put_switch: } EXPORT_SYMBOL_GPL(rpc_clnt_add_xprt); +static int +rpc_xprt_cap_max_reconnect_timeout(struct rpc_clnt *clnt, + struct rpc_xprt *xprt, + void *data) +{ + unsigned long timeout = *((unsigned long *)data); + + if (timeout < xprt->max_reconnect_timeout) + xprt->max_reconnect_timeout = timeout; + return 0; +} + +void +rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt, unsigned long timeo) +{ + rpc_clnt_iterate_for_each_xprt(clnt, + rpc_xprt_cap_max_reconnect_timeout, + &timeo); +} +EXPORT_SYMBOL_GPL(rpc_cap_max_reconnect_timeout); + #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static void rpc_show_header(void) { diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 8313960cac52..ea244b29138b 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -680,6 +680,20 @@ out: spin_unlock_bh(&xprt->transport_lock); } +static bool +xprt_has_timer(const struct rpc_xprt *xprt) +{ + return xprt->idle_timeout != 0; +} + +static void +xprt_schedule_autodisconnect(struct rpc_xprt *xprt) + __must_hold(&xprt->transport_lock) +{ + if (list_empty(&xprt->recv) && xprt_has_timer(xprt)) + mod_timer(&xprt->timer, xprt->last_used + xprt->idle_timeout); +} + static void xprt_init_autodisconnect(unsigned long data) { @@ -688,6 +702,8 @@ xprt_init_autodisconnect(unsigned long data) spin_lock(&xprt->transport_lock); if (!list_empty(&xprt->recv)) goto out_abort; + /* Reset xprt->last_used to avoid connect/autodisconnect cycling */ + xprt->last_used = jiffies; if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) goto out_abort; spin_unlock(&xprt->transport_lock); @@ -725,6 +741,7 @@ void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie) goto out; xprt->snd_task =NULL; xprt->ops->release_xprt(xprt, NULL); + xprt_schedule_autodisconnect(xprt); out: spin_unlock_bh(&xprt->transport_lock); wake_up_bit(&xprt->state, XPRT_LOCKED); @@ -888,11 +905,6 @@ static void xprt_timer(struct rpc_task *task) spin_unlock_bh(&xprt->transport_lock); } -static inline int xprt_has_timer(struct rpc_xprt *xprt) -{ - return xprt->idle_timeout != 0; -} - /** * xprt_prepare_transmit - reserve the transport before sending a request * @task: RPC task about to send a request @@ -1280,9 +1292,7 @@ void xprt_release(struct rpc_task *task) if (!list_empty(&req->rq_list)) list_del(&req->rq_list); xprt->last_used = jiffies; - if (list_empty(&xprt->recv) && xprt_has_timer(xprt)) - mod_timer(&xprt->timer, - xprt->last_used + xprt->idle_timeout); + xprt_schedule_autodisconnect(xprt); spin_unlock_bh(&xprt->transport_lock); if (req->rq_buffer) xprt->ops->buf_free(req->rq_buffer); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 111767ab124a..8ede3bc52481 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -177,7 +177,6 @@ static struct ctl_table sunrpc_table[] = { * increase over time if the server is down or not responding. */ #define XS_TCP_INIT_REEST_TO (3U * HZ) -#define XS_TCP_MAX_REEST_TO (5U * 60 * HZ) /* * TCP idle timeout; client drops the transport socket if it is idle @@ -2173,6 +2172,8 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) write_unlock_bh(&sk->sk_callback_lock); } xs_udp_do_set_buffer_size(xprt); + + xprt->stat.connect_start = jiffies; } static void xs_udp_setup_socket(struct work_struct *work) @@ -2236,6 +2237,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) unsigned int keepcnt = xprt->timeout->to_retries + 1; unsigned int opt_on = 1; unsigned int timeo; + unsigned int addr_pref = IPV6_PREFER_SRC_PUBLIC; /* TCP Keepalive options */ kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE, @@ -2247,6 +2249,16 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT, (char *)&keepcnt, sizeof(keepcnt)); + /* Avoid temporary address, they are bad for long-lived + * connections such as NFS mounts. + * RFC4941, section 3.6 suggests that: + * Individual applications, which have specific + * knowledge about the normal duration of connections, + * MAY override this as appropriate. + */ + kernel_setsockopt(sock, SOL_IPV6, IPV6_ADDR_PREFERENCES, + (char *)&addr_pref, sizeof(addr_pref)); + /* TCP user timeout (see RFC5482) */ timeo = jiffies_to_msecs(xprt->timeout->to_initval) * (xprt->timeout->to_retries + 1); @@ -2295,6 +2307,10 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) /* SYN_SENT! */ if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; + break; + case -EADDRNOTAVAIL: + /* Source port number is unavailable. Try a new one! */ + transport->srcport = 0; } out: return ret; @@ -2369,6 +2385,25 @@ out: xprt_wake_pending_tasks(xprt, status); } +static unsigned long xs_reconnect_delay(const struct rpc_xprt *xprt) +{ + unsigned long start, now = jiffies; + + start = xprt->stat.connect_start + xprt->reestablish_timeout; + if (time_after(start, now)) + return start - now; + return 0; +} + +static void xs_reconnect_backoff(struct rpc_xprt *xprt) +{ + xprt->reestablish_timeout <<= 1; + if (xprt->reestablish_timeout > xprt->max_reconnect_timeout) + xprt->reestablish_timeout = xprt->max_reconnect_timeout; + if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) + xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; +} + /** * xs_connect - connect a socket to a remote endpoint * @xprt: pointer to transport structure @@ -2386,6 +2421,7 @@ out: static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + unsigned long delay = 0; WARN_ON_ONCE(!xprt_lock_connect(xprt, task, transport)); @@ -2397,19 +2433,15 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) /* Start by resetting any existing state */ xs_reset_transport(transport); - queue_delayed_work(xprtiod_workqueue, - &transport->connect_worker, - xprt->reestablish_timeout); - xprt->reestablish_timeout <<= 1; - if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) - xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; - if (xprt->reestablish_timeout > XS_TCP_MAX_REEST_TO) - xprt->reestablish_timeout = XS_TCP_MAX_REEST_TO; - } else { + delay = xs_reconnect_delay(xprt); + xs_reconnect_backoff(xprt); + + } else dprintk("RPC: xs_connect scheduled xprt %p\n", xprt); - queue_delayed_work(xprtiod_workqueue, - &transport->connect_worker, 0); - } + + queue_delayed_work(xprtiod_workqueue, + &transport->connect_worker, + delay); } /** @@ -2961,6 +2993,8 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args) xprt->ops = &xs_tcp_ops; xprt->timeout = &xs_tcp_default_timeout; + xprt->max_reconnect_timeout = xprt->timeout->to_maxval; + INIT_WORK(&transport->recv_worker, xs_tcp_data_receive_workfn); INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_setup_socket); diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index b62caa1c770c..ed97a5876ebe 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -728,12 +728,13 @@ int tipc_nl_add_monitor_peer(struct net *net, struct tipc_nl_msg *msg, u32 bearer_id, u32 *prev_node) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); - struct tipc_peer *peer = mon->self; + struct tipc_peer *peer; if (!mon) return -EINVAL; read_lock_bh(&mon->lock); + peer = mon->self; do { if (*prev_node) { if (peer->addr == *prev_node) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index c49b8df438cb..f9f5f3c3dab5 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2180,7 +2180,8 @@ restart: TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode, onode, dport, oport, TIPC_CONN_SHUTDOWN); - tipc_node_xmit_skb(net, skb, dnode, tsk->portid); + if (skb) + tipc_node_xmit_skb(net, skb, dnode, tsk->portid); } tsk->connected = 0; sock->state = SS_DISCONNECTING; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 699dfabdbccd..936d7eee62d0 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -87,9 +87,6 @@ virtio_transport_send_pkt_work(struct work_struct *work) vq = vsock->vqs[VSOCK_VQ_TX]; - /* Avoid unnecessary interrupts while we're processing the ring */ - virtqueue_disable_cb(vq); - for (;;) { struct virtio_vsock_pkt *pkt; struct scatterlist hdr, buf, *sgs[2]; @@ -99,7 +96,6 @@ virtio_transport_send_pkt_work(struct work_struct *work) spin_lock_bh(&vsock->send_pkt_list_lock); if (list_empty(&vsock->send_pkt_list)) { spin_unlock_bh(&vsock->send_pkt_list_lock); - virtqueue_enable_cb(vq); break; } @@ -118,13 +114,13 @@ virtio_transport_send_pkt_work(struct work_struct *work) } ret = virtqueue_add_sgs(vq, sgs, out_sg, in_sg, pkt, GFP_KERNEL); + /* Usually this means that there is no more space available in + * the vq + */ if (ret < 0) { spin_lock_bh(&vsock->send_pkt_list_lock); list_add(&pkt->list, &vsock->send_pkt_list); spin_unlock_bh(&vsock->send_pkt_list_lock); - - if (!virtqueue_enable_cb(vq) && ret == -ENOSPC) - continue; /* retry now that we have more space */ break; } diff --git a/net/wireless/chan.c b/net/wireless/chan.c index b0e11b6dc994..0f506220a3bd 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -513,6 +513,7 @@ static bool cfg80211_chandef_dfs_available(struct wiphy *wiphy, r = cfg80211_get_chans_dfs_available(wiphy, chandef->center_freq2, width); + break; default: WARN_ON(chandef->center_freq2); break; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 46417f9cce68..f02653a08993 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5380,6 +5380,7 @@ static int nl80211_parse_mesh_config(struct genl_info *info, { struct nlattr *tb[NL80211_MESHCONF_ATTR_MAX + 1]; u32 mask = 0; + u16 ht_opmode; #define FILL_IN_MESH_PARAM_IF_SET(tb, cfg, param, min, max, mask, attr, fn) \ do { \ @@ -5471,9 +5472,36 @@ do { \ FILL_IN_MESH_PARAM_IF_SET(tb, cfg, rssi_threshold, -255, 0, mask, NL80211_MESHCONF_RSSI_THRESHOLD, nl80211_check_s32); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, ht_opmode, 0, 16, - mask, NL80211_MESHCONF_HT_OPMODE, - nl80211_check_u16); + /* + * Check HT operation mode based on + * IEEE 802.11 2012 8.4.2.59 HT Operation element. + */ + if (tb[NL80211_MESHCONF_HT_OPMODE]) { + ht_opmode = nla_get_u16(tb[NL80211_MESHCONF_HT_OPMODE]); + + if (ht_opmode & ~(IEEE80211_HT_OP_MODE_PROTECTION | + IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT | + IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)) + return -EINVAL; + + if ((ht_opmode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT) && + (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)) + return -EINVAL; + + switch (ht_opmode & IEEE80211_HT_OP_MODE_PROTECTION) { + case IEEE80211_HT_OP_MODE_PROTECTION_NONE: + case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ: + if (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT) + return -EINVAL; + break; + case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER: + case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED: + if (!(ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)) + return -EINVAL; + break; + } + cfg->ht_opmode = ht_opmode; + } FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPactivePathToRootTimeout, 1, 65535, mask, NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT, diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h index 217c8d507f2e..7927a090fa0d 100644 --- a/samples/bpf/bpf_helpers.h +++ b/samples/bpf/bpf_helpers.h @@ -72,8 +72,8 @@ static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flag (void *) BPF_FUNC_l3_csum_replace; static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) = (void *) BPF_FUNC_l4_csum_replace; -static int (*bpf_skb_in_cgroup)(void *ctx, void *map, int index) = - (void *) BPF_FUNC_skb_in_cgroup; +static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) = + (void *) BPF_FUNC_skb_under_cgroup; #if defined(__x86_64__) diff --git a/samples/bpf/test_cgrp2_tc_kern.c b/samples/bpf/test_cgrp2_tc_kern.c index 2732c37c8d5b..10ff73404e3a 100644 --- a/samples/bpf/test_cgrp2_tc_kern.c +++ b/samples/bpf/test_cgrp2_tc_kern.c @@ -57,7 +57,7 @@ int handle_egress(struct __sk_buff *skb) bpf_trace_printk(dont_care_msg, sizeof(dont_care_msg), eth->h_proto, ip6h->nexthdr); return TC_ACT_OK; - } else if (bpf_skb_in_cgroup(skb, &test_cgrp2_array_pin, 0) != 1) { + } else if (bpf_skb_under_cgroup(skb, &test_cgrp2_array_pin, 0) != 1) { bpf_trace_printk(pass_msg, sizeof(pass_msg)); return TC_ACT_OK; } else { diff --git a/samples/bpf/test_maps.c b/samples/bpf/test_maps.c index 47bf0858f9e4..cce2b59751eb 100644 --- a/samples/bpf/test_maps.c +++ b/samples/bpf/test_maps.c @@ -68,7 +68,16 @@ static void test_hashmap_sanity(int i, void *data) assert(bpf_update_elem(map_fd, &key, &value, BPF_NOEXIST) == -1 && errno == E2BIG); + /* update existing element, thought the map is full */ + key = 1; + assert(bpf_update_elem(map_fd, &key, &value, BPF_EXIST) == 0); + key = 2; + assert(bpf_update_elem(map_fd, &key, &value, BPF_ANY) == 0); + key = 1; + assert(bpf_update_elem(map_fd, &key, &value, BPF_ANY) == 0); + /* check that key = 0 doesn't exist */ + key = 0; assert(bpf_delete_elem(map_fd, &key) == -1 && errno == ENOENT); /* iterate over two elements */ @@ -413,10 +422,12 @@ static void do_work(int fn, void *data) for (i = fn; i < MAP_SIZE; i += TASKS) { key = value = i; - if (do_update) + if (do_update) { assert(bpf_update_elem(map_fd, &key, &value, BPF_NOEXIST) == 0); - else + assert(bpf_update_elem(map_fd, &key, &value, BPF_EXIST) == 0); + } else { assert(bpf_delete_elem(map_fd, &key) == 0); + } } } diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 89dacf9b4e6c..160c7f713722 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -906,20 +906,23 @@ static int azx_resume(struct device *dev) struct snd_card *card = dev_get_drvdata(dev); struct azx *chip; struct hda_intel *hda; + struct hdac_bus *bus; if (!card) return 0; chip = card->private_data; hda = container_of(chip, struct hda_intel, chip); + bus = azx_bus(chip); if (chip->disabled || hda->init_failed || !chip->running) return 0; - if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL - && hda->need_i915_power) { - snd_hdac_display_power(azx_bus(chip), true); - snd_hdac_i915_set_bclk(azx_bus(chip)); + if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) { + snd_hdac_display_power(bus, true); + if (hda->need_i915_power) + snd_hdac_i915_set_bclk(bus); } + if (chip->msi) if (pci_enable_msi(pci) < 0) chip->msi = 0; @@ -929,6 +932,11 @@ static int azx_resume(struct device *dev) hda_intel_init_chip(chip, true); + /* power down again for link-controlled chips */ + if ((chip->driver_caps & AZX_DCAPS_I915_POWERWELL) && + !hda->need_i915_power) + snd_hdac_display_power(bus, false); + snd_power_change_state(card, SNDRV_CTL_POWER_D0); trace_azx_resume(chip); @@ -1008,6 +1016,7 @@ static int azx_runtime_resume(struct device *dev) chip = card->private_data; hda = container_of(chip, struct hda_intel, chip); + bus = azx_bus(chip); if (chip->disabled || hda->init_failed) return 0; @@ -1015,15 +1024,9 @@ static int azx_runtime_resume(struct device *dev) return 0; if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) { - bus = azx_bus(chip); - if (hda->need_i915_power) { - snd_hdac_display_power(bus, true); + snd_hdac_display_power(bus, true); + if (hda->need_i915_power) snd_hdac_i915_set_bclk(bus); - } else { - /* toggle codec wakeup bit for STATESTS read */ - snd_hdac_set_codec_wakeup(bus, true); - snd_hdac_set_codec_wakeup(bus, false); - } } /* Read STATESTS before controller reset */ @@ -1043,6 +1046,11 @@ static int azx_runtime_resume(struct device *dev) azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) & ~STATESTS_INT_MASK); + /* power down again for link-controlled chips */ + if ((chip->driver_caps & AZX_DCAPS_I915_POWERWELL) && + !hda->need_i915_power) + snd_hdac_display_power(bus, false); + trace_azx_runtime_resume(chip); return 0; } diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 6adde457b602..6cf1f3597455 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1128,6 +1128,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) { /* devices which do not support reading the sample rate. */ switch (chip->usb_id) { + case USB_ID(0x041E, 0x4080): /* Creative Live Cam VF0610 */ case USB_ID(0x045E, 0x075D): /* MS Lifecam Cinema */ case USB_ID(0x045E, 0x076D): /* MS Lifecam HD-5000 */ case USB_ID(0x045E, 0x076E): /* MS Lifecam HD-5001 */ @@ -1138,6 +1139,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */ case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ case USB_ID(0x0556, 0x0014): /* Phoenix Audio TMX320VC */ + case USB_ID(0x05A3, 0x9420): /* ELP HD USB Camera */ case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */ case USB_ID(0x1de7, 0x0013): /* Phoenix Audio MT202exe */ case USB_ID(0x1de7, 0x0014): /* Phoenix Audio TMX320 */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 4a413485f9eb..92a8308b96f6 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -225,7 +225,6 @@ #define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */ #define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */ #define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ -#define X86_FEATURE_PCOMMIT ( 9*32+22) /* PCOMMIT instruction */ #define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ #define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ #define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ @@ -301,10 +300,6 @@ #define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ #define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ #define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ -#define X86_BUG_NULL_SEG X86_BUG(9) /* Nulling a selector preserves the base */ -#define X86_BUG_SWAPGS_FENCE X86_BUG(10) /* SWAPGS without input dep on GS */ - - #ifdef CONFIG_X86_32 /* * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional @@ -312,5 +307,7 @@ */ #define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ #endif - +#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ +#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 911e9358ceb1..85599ad4d024 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -56,5 +56,7 @@ #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 #define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE) +#define DISABLED_MASK17 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h index 4916144e3c42..fac9a5c0abe9 100644 --- a/tools/arch/x86/include/asm/required-features.h +++ b/tools/arch/x86/include/asm/required-features.h @@ -99,5 +99,7 @@ #define REQUIRED_MASK14 0 #define REQUIRED_MASK15 0 #define REQUIRED_MASK16 0 +#define REQUIRED_MASK17 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index 5b15d94a33f8..37fee272618f 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -78,7 +78,6 @@ #define EXIT_REASON_PML_FULL 62 #define EXIT_REASON_XSAVES 63 #define EXIT_REASON_XRSTORS 64 -#define EXIT_REASON_PCOMMIT 65 #define VMX_EXIT_REASONS \ { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ @@ -127,8 +126,7 @@ { EXIT_REASON_INVVPID, "INVVPID" }, \ { EXIT_REASON_INVPCID, "INVPCID" }, \ { EXIT_REASON_XSAVES, "XSAVES" }, \ - { EXIT_REASON_XRSTORS, "XRSTORS" }, \ - { EXIT_REASON_PCOMMIT, "PCOMMIT" } + { EXIT_REASON_XRSTORS, "XRSTORS" } #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 #define VMX_ABORT_LOAD_HOST_MSR_FAIL 4 diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 406459b935a2..da218fec6056 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -84,6 +84,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PERCPU_HASH, BPF_MAP_TYPE_PERCPU_ARRAY, BPF_MAP_TYPE_STACK_TRACE, + BPF_MAP_TYPE_CGROUP_ARRAY, }; enum bpf_prog_type { @@ -93,6 +94,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SCHED_CLS, BPF_PROG_TYPE_SCHED_ACT, BPF_PROG_TYPE_TRACEPOINT, + BPF_PROG_TYPE_XDP, }; #define BPF_PSEUDO_MAP_FD 1 @@ -313,6 +315,66 @@ enum bpf_func_id { */ BPF_FUNC_skb_get_tunnel_opt, BPF_FUNC_skb_set_tunnel_opt, + + /** + * bpf_skb_change_proto(skb, proto, flags) + * Change protocol of the skb. Currently supported is + * v4 -> v6, v6 -> v4 transitions. The helper will also + * resize the skb. eBPF program is expected to fill the + * new headers via skb_store_bytes and lX_csum_replace. + * @skb: pointer to skb + * @proto: new skb->protocol type + * @flags: reserved + * Return: 0 on success or negative error + */ + BPF_FUNC_skb_change_proto, + + /** + * bpf_skb_change_type(skb, type) + * Change packet type of skb. + * @skb: pointer to skb + * @type: new skb->pkt_type type + * Return: 0 on success or negative error + */ + BPF_FUNC_skb_change_type, + + /** + * bpf_skb_in_cgroup(skb, map, index) - Check cgroup2 membership of skb + * @skb: pointer to skb + * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type + * @index: index of the cgroup in the bpf_map + * Return: + * == 0 skb failed the cgroup2 descendant test + * == 1 skb succeeded the cgroup2 descendant test + * < 0 error + */ + BPF_FUNC_skb_in_cgroup, + + /** + * bpf_get_hash_recalc(skb) + * Retrieve and possibly recalculate skb->hash. + * @skb: pointer to skb + * Return: hash + */ + BPF_FUNC_get_hash_recalc, + + /** + * u64 bpf_get_current_task(void) + * Returns current task_struct + * Return: current + */ + BPF_FUNC_get_current_task, + + /** + * bpf_probe_write_user(void *dst, void *src, int len) + * safely attempt to write to a location + * @dst: destination address in userspace + * @src: source address on stack + * @len: number of bytes to copy + * Return: 0 on success or negative error + */ + BPF_FUNC_probe_write_user, + __BPF_FUNC_MAX_ID, }; @@ -347,9 +409,11 @@ enum bpf_func_id { #define BPF_F_ZERO_CSUM_TX (1ULL << 1) #define BPF_F_DONT_FRAGMENT (1ULL << 2) -/* BPF_FUNC_perf_event_output flags. */ +/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */ #define BPF_F_INDEX_MASK 0xffffffffULL #define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK +/* BPF_FUNC_perf_event_output for sk_buff input context. */ +#define BPF_F_CTXLEN_MASK (0xfffffULL << 32) /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure @@ -386,4 +450,24 @@ struct bpf_tunnel_key { __u32 tunnel_label; }; +/* User return codes for XDP prog type. + * A valid XDP program must return one of these defined values. All other + * return codes are reserved for future use. Unknown return codes will result + * in packet drop. + */ +enum xdp_action { + XDP_ABORTED = 0, + XDP_DROP, + XDP_PASS, + XDP_TX, +}; + +/* user accessible metadata for XDP packet hook + * new fields must be added to the end of this structure + */ +struct xdp_md { + __u32 data; + __u32 data_end; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index 736da44596e4..b303bcdd8ed1 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -176,10 +176,18 @@ Each probe argument follows below syntax. 'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.) '$vars' and '$params' special arguments are also available for NAME, '$vars' is expanded to the local variables (including function parameters) which can access at given probe point. '$params' is expanded to only the function parameters. -'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type. +'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. Currently, basic types (u8/u16/u32/u64/s8/s16/s32/s64), signedness casting (u/s), "string" and bitfield are supported. (see TYPES for detail) On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid. +TYPES +----- +Basic types (u8/u16/u32/u64/s8/s16/s32/s64) are integer types. Prefix 's' and 'u' means those types are signed and unsigned respectively. Traced arguments are shown in decimal (signed) or hex (unsigned). You can also use 's' or 'u' to specify only signedness and leave its size auto-detected by perf probe. +String type is a special type, which fetches a "null-terminated" string from kernel space. This means it will fail and store NULL if the string container has been paged out. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type. +Bitfield is another special type, which takes 3 parameters, bit-width, bit-offset, and container-size (usually 32). The syntax is; + + b<bit-width>@<bit-offset>/<container-size> + LINE SYNTAX ----------- Line range is described by following syntax. diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 1f6c70594f0f..053bbbd84ece 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -116,8 +116,8 @@ OPTIONS --fields:: Comma separated list of fields to print. Options are: comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, - srcline, period, iregs, brstack, brstacksym, flags. - Field list can be prepended with the type, trace, sw or hw, + srcline, period, iregs, brstack, brstacksym, flags, bpf-output, + callindent. Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index c6d0f91731a1..8d4dc97d80ba 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -54,10 +54,6 @@ int arch__compare_symbol_names(const char *namea, const char *nameb) #endif #if defined(_CALL_ELF) && _CALL_ELF == 2 -bool arch__prefers_symtab(void) -{ - return true; -} #ifdef HAVE_LIBELF_SUPPORT void arch__sym_update(struct symbol *s, GElf_Sym *sym) @@ -100,4 +96,27 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev, tev->point.offset += lep_offset; } } + +void arch__post_process_probe_trace_events(struct perf_probe_event *pev, + int ntevs) +{ + struct probe_trace_event *tev; + struct map *map; + struct symbol *sym = NULL; + struct rb_node *tmp; + int i = 0; + + map = get_target_map(pev->target, pev->uprobes); + if (!map || map__load(map, NULL) < 0) + return; + + for (i = 0; i < ntevs; i++) { + tev = &pev->tevs[i]; + map__for_each_symbol(map, sym, tmp) { + if (map->unmap_ip(map, sym->start) == tev->point.address) + arch__fix_tev_from_maps(pev, tev, map, sym); + } + } +} + #endif diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 971ff91b16cb..9c640a8081c7 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2116,7 +2116,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "Valid types: hw,sw,trace,raw. " "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," "addr,symoff,period,iregs,brstack,brstacksym,flags," - "callindent", parse_output_fields), + "bpf-output,callindent", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 0c16d20d7e32..3c7452b39f57 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -331,7 +331,7 @@ static int read_counter(struct perf_evsel *counter) return 0; } -static void read_counters(bool close_counters) +static void read_counters(void) { struct perf_evsel *counter; @@ -341,11 +341,6 @@ static void read_counters(bool close_counters) if (perf_stat_process_counter(&stat_config, counter)) pr_warning("failed to process counter %s\n", counter->name); - - if (close_counters) { - perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), - thread_map__nr(evsel_list->threads)); - } } } @@ -353,7 +348,7 @@ static void process_interval(void) { struct timespec ts, rs; - read_counters(false); + read_counters(); clock_gettime(CLOCK_MONOTONIC, &ts); diff_timespec(&rs, &ts, &ref_time); @@ -380,6 +375,17 @@ static void enable_counters(void) perf_evlist__enable(evsel_list); } +static void disable_counters(void) +{ + /* + * If we don't have tracee (attaching to task or cpu), counters may + * still be running. To get accurate group ratios, we must stop groups + * from counting before reading their constituent counters. + */ + if (!target__none(&target)) + perf_evlist__disable(evsel_list); +} + static volatile int workload_exec_errno; /* @@ -657,11 +663,20 @@ try_again: } } + disable_counters(); + t1 = rdclock(); update_stats(&walltime_nsecs_stats, t1 - t0); - read_counters(true); + /* + * Closing a group leader splits the group, and as we only disable + * group leaders, results in remaining events becoming enabled. To + * avoid arbitrary skew, we must read all counters before closing any + * group leaders. + */ + read_counters(); + perf_evlist__close(evsel_list); return WEXITSTATUS(status); } diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 953dc1ab2ed7..28733962cd80 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -170,15 +170,17 @@ static struct map *kernel_get_module_map(const char *module) module = "kernel"; for (pos = maps__first(maps); pos; pos = map__next(pos)) { + /* short_name is "[module]" */ if (strncmp(pos->dso->short_name + 1, module, - pos->dso->short_name_len - 2) == 0) { + pos->dso->short_name_len - 2) == 0 && + module[pos->dso->short_name_len - 2] == '\0') { return pos; } } return NULL; } -static struct map *get_target_map(const char *target, bool user) +struct map *get_target_map(const char *target, bool user) { /* Init maps of given executable or kernel */ if (user) @@ -385,7 +387,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, if (uprobes) address = sym->start; else - address = map->unmap_ip(map, sym->start); + address = map->unmap_ip(map, sym->start) - map->reloc; break; } if (!address) { @@ -664,22 +666,14 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs, return ret; } -/* Post processing the probe events */ -static int post_process_probe_trace_events(struct probe_trace_event *tevs, - int ntevs, const char *module, - bool uprobe) +static int +post_process_kernel_probe_trace_events(struct probe_trace_event *tevs, + int ntevs) { struct ref_reloc_sym *reloc_sym; char *tmp; int i, skipped = 0; - if (uprobe) - return add_exec_to_probe_trace_events(tevs, ntevs, module); - - /* Note that currently ref_reloc_sym based probe is not for drivers */ - if (module) - return add_module_to_probe_trace_events(tevs, ntevs, module); - reloc_sym = kernel_get_ref_reloc_sym(); if (!reloc_sym) { pr_warning("Relocated base symbol is not found!\n"); @@ -711,6 +705,34 @@ static int post_process_probe_trace_events(struct probe_trace_event *tevs, return skipped; } +void __weak +arch__post_process_probe_trace_events(struct perf_probe_event *pev __maybe_unused, + int ntevs __maybe_unused) +{ +} + +/* Post processing the probe events */ +static int post_process_probe_trace_events(struct perf_probe_event *pev, + struct probe_trace_event *tevs, + int ntevs, const char *module, + bool uprobe) +{ + int ret; + + if (uprobe) + ret = add_exec_to_probe_trace_events(tevs, ntevs, module); + else if (module) + /* Currently ref_reloc_sym based probe is not for drivers */ + ret = add_module_to_probe_trace_events(tevs, ntevs, module); + else + ret = post_process_kernel_probe_trace_events(tevs, ntevs); + + if (ret >= 0) + arch__post_process_probe_trace_events(pev, ntevs); + + return ret; +} + /* Try to find perf_probe_event with debuginfo */ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, struct probe_trace_event **tevs) @@ -749,7 +771,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, if (ntevs > 0) { /* Succeeded to find trace events */ pr_debug("Found %d probe_trace_events.\n", ntevs); - ret = post_process_probe_trace_events(*tevs, ntevs, + ret = post_process_probe_trace_events(pev, *tevs, ntevs, pev->target, pev->uprobes); if (ret < 0 || ret == ntevs) { clear_probe_trace_events(*tevs, ntevs); @@ -2936,8 +2958,6 @@ errout: return err; } -bool __weak arch__prefers_symtab(void) { return false; } - /* Concatinate two arrays */ static void *memcat(void *a, size_t sz_a, void *b, size_t sz_b) { @@ -3158,12 +3178,6 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev, if (ret > 0 || pev->sdt) /* SDT can be found only in the cache */ return ret == 0 ? -ENOENT : ret; /* Found in probe cache */ - if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) { - ret = find_probe_trace_events_from_map(pev, tevs); - if (ret > 0) - return ret; /* Found in symbol table */ - } - /* Convert perf_probe_event with debuginfo */ ret = try_to_find_probe_trace_events(pev, tevs); if (ret != 0) diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index e18ea9fe6385..f4f45db77c1c 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -158,7 +158,6 @@ int show_line_range(struct line_range *lr, const char *module, bool user); int show_available_vars(struct perf_probe_event *pevs, int npevs, struct strfilter *filter); int show_available_funcs(const char *module, struct strfilter *filter, bool user); -bool arch__prefers_symtab(void); void arch__fix_tev_from_maps(struct perf_probe_event *pev, struct probe_trace_event *tev, struct map *map, struct symbol *sym); @@ -173,4 +172,9 @@ int e_snprintf(char *str, size_t size, const char *format, ...) int copy_to_probe_trace_arg(struct probe_trace_arg *tvar, struct perf_probe_arg *pvar); +struct map *get_target_map(const char *target, bool user); + +void arch__post_process_probe_trace_events(struct perf_probe_event *pev, + int ntevs); + #endif /*_PROBE_EVENT_H */ diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index f2d9ff064e2d..5c290c682afe 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -297,10 +297,13 @@ static int convert_variable_type(Dwarf_Die *vr_die, char sbuf[STRERR_BUFSIZE]; int bsize, boffs, total; int ret; + char sign; /* TODO: check all types */ - if (cast && strcmp(cast, "string") != 0) { + if (cast && strcmp(cast, "string") != 0 && + strcmp(cast, "s") != 0 && strcmp(cast, "u") != 0) { /* Non string type is OK */ + /* and respect signedness cast */ tvar->type = strdup(cast); return (tvar->type == NULL) ? -ENOMEM : 0; } @@ -361,6 +364,13 @@ static int convert_variable_type(Dwarf_Die *vr_die, return (tvar->type == NULL) ? -ENOMEM : 0; } + if (cast && (strcmp(cast, "u") == 0)) + sign = 'u'; + else if (cast && (strcmp(cast, "s") == 0)) + sign = 's'; + else + sign = die_is_signed_type(&type) ? 's' : 'u'; + ret = dwarf_bytesize(&type); if (ret <= 0) /* No size ... try to use default type */ @@ -373,8 +383,7 @@ static int convert_variable_type(Dwarf_Die *vr_die, dwarf_diename(&type), MAX_BASIC_TYPE_BITS); ret = MAX_BASIC_TYPE_BITS; } - ret = snprintf(buf, 16, "%c%d", - die_is_signed_type(&type) ? 's' : 'u', ret); + ret = snprintf(buf, 16, "%c%d", sign, ret); formatted: if (ret < 0 || ret >= 16) { diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 947d21f38398..3d3cb8392c86 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -588,7 +588,11 @@ static char *get_trace_output(struct hist_entry *he) } else { pevent_event_info(&seq, evsel->tp_format, &rec); } - return seq.buffer; + /* + * Trim the buffer, it starts at 4KB and we're not going to + * add anything more to this buffer. + */ + return realloc(seq.buffer, seq.len + 1); } static int64_t diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 5404efa578a3..dd48f421844c 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -13,6 +13,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/platform_device.h> #include <linux/dma-mapping.h> +#include <linux/workqueue.h> #include <linux/libnvdimm.h> #include <linux/vmalloc.h> #include <linux/device.h> @@ -1474,6 +1475,7 @@ static int nfit_test_probe(struct platform_device *pdev) if (nfit_test->setup != nfit_test0_setup) return 0; + flush_work(&acpi_desc->work); nfit_test->setup_hotplug = 1; nfit_test->setup(nfit_test); diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index 3c40c9d0e6c7..1cc6d64c39b7 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -8,7 +8,7 @@ ifeq ($(ARCH),powerpc) GIT_VERSION = $(shell git describe --always --long --dirty || echo "unknown") -CFLAGS := -Wall -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $(CFLAGS) +CFLAGS := -std=gnu99 -Wall -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $(CFLAGS) export CFLAGS diff --git a/tools/virtio/linux/dma-mapping.h b/tools/virtio/linux/dma-mapping.h index 4f93af89ae16..18601f6689b9 100644 --- a/tools/virtio/linux/dma-mapping.h +++ b/tools/virtio/linux/dma-mapping.h @@ -14,4 +14,20 @@ enum dma_data_direction { DMA_NONE = 3, }; +#define dma_alloc_coherent(d, s, hp, f) ({ \ + void *__dma_alloc_coherent_p = kmalloc((s), (f)); \ + *(hp) = (unsigned long)__dma_alloc_coherent_p; \ + __dma_alloc_coherent_p; \ +}) + +#define dma_free_coherent(d, s, p, h) kfree(p) + +#define dma_map_page(d, p, o, s, dir) (page_to_phys(p) + (o)) + +#define dma_map_single(d, p, s, dir) (virt_to_phys(p)) +#define dma_mapping_error(...) (0) + +#define dma_unmap_single(...) do { } while (0) +#define dma_unmap_page(...) do { } while (0) + #endif diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index 033849948215..d9554fc3f340 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -20,7 +20,9 @@ #define PAGE_SIZE getpagesize() #define PAGE_MASK (~(PAGE_SIZE-1)) +#define PAGE_ALIGN(x) ((x + PAGE_SIZE - 1) & PAGE_MASK) +typedef unsigned long long phys_addr_t; typedef unsigned long long dma_addr_t; typedef size_t __kernel_size_t; typedef unsigned int __wsum; @@ -57,6 +59,11 @@ static inline void *kzalloc(size_t s, gfp_t gfp) return p; } +static inline void *alloc_pages_exact(size_t s, gfp_t gfp) +{ + return kmalloc(s, gfp); +} + static inline void kfree(void *p) { if (p >= __kfree_ignore_start && p < __kfree_ignore_end) @@ -64,6 +71,11 @@ static inline void kfree(void *p) free(p); } +static inline void free_pages_exact(void *p, size_t s) +{ + kfree(p); +} + static inline void *krealloc(void *p, size_t s, gfp_t gfp) { return realloc(p, s); @@ -105,6 +117,8 @@ static inline void free_page(unsigned long addr) #define dev_err(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__) #define dev_warn(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__) +#define WARN_ON_ONCE(cond) ((cond) && fprintf (stderr, "WARNING\n")) + #define min(x, y) ({ \ typeof(x) _min1 = (x); \ typeof(y) _min2 = (y); \ diff --git a/tools/virtio/linux/slab.h b/tools/virtio/linux/slab.h index 81baeac8ae40..7e1c1197d439 100644 --- a/tools/virtio/linux/slab.h +++ b/tools/virtio/linux/slab.h @@ -1,2 +1,6 @@ #ifndef LINUX_SLAB_H +#define GFP_KERNEL 0 +#define GFP_ATOMIC 0 +#define __GFP_NOWARN 0 +#define __GFP_ZERO 0 #endif diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h index ee125e714053..9377c8b4ac16 100644 --- a/tools/virtio/linux/virtio.h +++ b/tools/virtio/linux/virtio.h @@ -3,8 +3,12 @@ #include <linux/scatterlist.h> #include <linux/kernel.h> +struct device { + void *parent; +}; + struct virtio_device { - void *dev; + struct device dev; u64 features; }; diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h index 57a6964a1e35..9ba11815e0a1 100644 --- a/tools/virtio/linux/virtio_config.h +++ b/tools/virtio/linux/virtio_config.h @@ -40,6 +40,19 @@ static inline void __virtio_clear_bit(struct virtio_device *vdev, #define virtio_has_feature(dev, feature) \ (__virtio_test_bit((dev), feature)) +/** + * virtio_has_iommu_quirk - determine whether this device has the iommu quirk + * @vdev: the device + */ +static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev) +{ + /* + * Note the reverse polarity of the quirk feature (compared to most + * other features), this is for compatibility with legacy systems. + */ + return !virtio_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM); +} + static inline bool virtio_is_little_endian(struct virtio_device *vdev) { return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) || diff --git a/tools/virtio/ringtest/ptr_ring.c b/tools/virtio/ringtest/ptr_ring.c index 68e4f9f0da3a..bd2ad1d3b7a9 100644 --- a/tools/virtio/ringtest/ptr_ring.c +++ b/tools/virtio/ringtest/ptr_ring.c @@ -13,6 +13,7 @@ #define cache_line_size() SMP_CACHE_BYTES #define ____cacheline_aligned_in_smp __attribute__ ((aligned (SMP_CACHE_BYTES))) #define unlikely(x) (__builtin_expect(!!(x), 0)) +#define likely(x) (__builtin_expect(!!(x), 1)) #define ALIGN(x, a) (((x) + (a) - 1) / (a) * (a)) typedef pthread_spinlock_t spinlock_t; diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index fb4b0a79a950..83777c1cbae0 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -73,12 +73,8 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) int i, vcpu_lock_idx = -1, ret; struct kvm_vcpu *vcpu; - mutex_lock(&kvm->lock); - - if (irqchip_in_kernel(kvm)) { - ret = -EEXIST; - goto out; - } + if (irqchip_in_kernel(kvm)) + return -EEXIST; /* * This function is also called by the KVM_CREATE_IRQCHIP handler, @@ -87,10 +83,8 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) * the proper checks already. */ if (type == KVM_DEV_TYPE_ARM_VGIC_V2 && - !kvm_vgic_global_state.can_emulate_gicv2) { - ret = -ENODEV; - goto out; - } + !kvm_vgic_global_state.can_emulate_gicv2) + return -ENODEV; /* * Any time a vcpu is run, vcpu_load is called which tries to grab the @@ -138,9 +132,6 @@ out_unlock: vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx); mutex_unlock(&vcpu->mutex); } - -out: - mutex_unlock(&kvm->lock); return ret; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index cc081ccfcaa3..195078225aa5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -696,6 +696,11 @@ static void kvm_destroy_devices(struct kvm *kvm) { struct kvm_device *dev, *tmp; + /* + * We do not need to take the kvm->lock here, because nobody else + * has a reference to the struct kvm at this point and therefore + * cannot access the devices list anyhow. + */ list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) { list_del(&dev->vm_node); dev->ops->destroy(dev); @@ -2832,19 +2837,28 @@ static int kvm_ioctl_create_device(struct kvm *kvm, dev->ops = ops; dev->kvm = kvm; + mutex_lock(&kvm->lock); ret = ops->create(dev, cd->type); if (ret < 0) { + mutex_unlock(&kvm->lock); kfree(dev); return ret; } + list_add(&dev->vm_node, &kvm->devices); + mutex_unlock(&kvm->lock); + + if (ops->init) + ops->init(dev); ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); if (ret < 0) { ops->destroy(dev); + mutex_lock(&kvm->lock); + list_del(&dev->vm_node); + mutex_unlock(&kvm->lock); return ret; } - list_add(&dev->vm_node, &kvm->devices); kvm_get_kvm(kvm); cd->fd = ret; return 0; |