diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index b683e8ee69ec..ea6a043f5beb 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -271,3 +271,19 @@ Description: Parameters for the CPU cache attributes - WriteBack: data is written only to the cache line and the modified cache line is written to main memory only when it is replaced + +What: /sys/devices/system/cpu/vulnerabilities + /sys/devices/system/cpu/vulnerabilities/meltdown + /sys/devices/system/cpu/vulnerabilities/spectre_v1 + /sys/devices/system/cpu/vulnerabilities/spectre_v2 +Date: January 2018 +Contact: Linux kernel mailing list +Description: Information about CPU vulnerabilities + + The files are named after the code names of CPU + vulnerabilities. The output of those files reflects the + state of the CPUs in the system. Possible output values: + + "Not affected" CPU is not affected by the vulnerability + "Vulnerable" CPU is affected and no mitigation in effect + "Mitigation: $M" CPU is affected and mitigation $M is in effect diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 5977c4d71356..39280b72f27a 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2523,8 +2523,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted. nojitter [IA-64] Disables jitter checking for ITC timers. - nopti [X86-64] Disable KAISER isolation of kernel from user. - no-kvmclock [X86,KVM] Disable paravirtualized KVM clock driver no-kvmapf [X86,KVM] Disable paravirtualized asynchronous page @@ -3056,11 +3054,20 @@ bytes respectively. Such letter suffixes can also be entirely omitted. pt. [PARIDE] See Documentation/blockdev/paride.txt. - pti= [X86_64] - Control KAISER user/kernel address space isolation: - on - enable - off - disable - auto - default setting + pti= [X86_64] Control Page Table Isolation of user and + kernel address spaces. Disabling this feature + removes hardening, but improves performance of + system calls and interrupts. + + on - unconditionally enable + off - unconditionally disable + auto - kernel detects whether your CPU model is + vulnerable to issues that PTI mitigates + + Not specifying this option is equivalent to pti=auto. + + nopti [X86_64] + Equivalent to pti=off pty.legacy_count= [KNL] Number of legacy pty's. Overwrites compiled-in diff --git a/Documentation/x86/pti.txt b/Documentation/x86/pti.txt new file mode 100644 index 000000000000..d11eff61fc9a --- /dev/null +++ b/Documentation/x86/pti.txt @@ -0,0 +1,186 @@ +Overview +======== + +Page Table Isolation (pti, previously known as KAISER[1]) is a +countermeasure against attacks on the shared user/kernel address +space such as the "Meltdown" approach[2]. + +To mitigate this class of attacks, we create an independent set of +page tables for use only when running userspace applications. When +the kernel is entered via syscalls, interrupts or exceptions, the +page tables are switched to the full "kernel" copy. When the system +switches back to user mode, the user copy is used again. + +The userspace page tables contain only a minimal amount of kernel +data: only what is needed to enter/exit the kernel such as the +entry/exit functions themselves and the interrupt descriptor table +(IDT). There are a few strictly unnecessary things that get mapped +such as the first C function when entering an interrupt (see +comments in pti.c). + +This approach helps to ensure that side-channel attacks leveraging +the paging structures do not function when PTI is enabled. It can be +enabled by setting CONFIG_PAGE_TABLE_ISOLATION=y at compile time. +Once enabled at compile-time, it can be disabled at boot with the +'nopti' or 'pti=' kernel parameters (see kernel-parameters.txt). + +Page Table Management +===================== + +When PTI is enabled, the kernel manages two sets of page tables. +The first set is very similar to the single set which is present in +kernels without PTI. This includes a complete mapping of userspace +that the kernel can use for things like copy_to_user(). + +Although _complete_, the user portion of the kernel page tables is +crippled by setting the NX bit in the top level. This ensures +that any missed kernel->user CR3 switch will immediately crash +userspace upon executing its first instruction. + +The userspace page tables map only the kernel data needed to enter +and exit the kernel. This data is entirely contained in the 'struct +cpu_entry_area' structure which is placed in the fixmap which gives +each CPU's copy of the area a compile-time-fixed virtual address. + +For new userspace mappings, the kernel makes the entries in its +page tables like normal. The only difference is when the kernel +makes entries in the top (PGD) level. In addition to setting the +entry in the main kernel PGD, a copy of the entry is made in the +userspace page tables' PGD. + +This sharing at the PGD level also inherently shares all the lower +layers of the page tables. This leaves a single, shared set of +userspace page tables to manage. One PTE to lock, one set of +accessed bits, dirty bits, etc... + +Overhead +======== + +Protection against side-channel attacks is important. But, +this protection comes at a cost: + +1. Increased Memory Use + a. Each process now needs an order-1 PGD instead of order-0. + (Consumes an additional 4k per process). + b. The 'cpu_entry_area' structure must be 2MB in size and 2MB + aligned so that it can be mapped by setting a single PMD + entry. This consumes nearly 2MB of RAM once the kernel + is decompressed, but no space in the kernel image itself. + +2. Runtime Cost + a. CR3 manipulation to switch between the page table copies + must be done at interrupt, syscall, and exception entry + and exit (it can be skipped when the kernel is interrupted, + though.) Moves to CR3 are on the order of a hundred + cycles, and are required at every entry and exit. + b. A "trampoline" must be used for SYSCALL entry. This + trampoline depends on a smaller set of resources than the + non-PTI SYSCALL entry code, so requires mapping fewer + things into the userspace page tables. The downside is + that stacks must be switched at entry time. + d. Global pages are disabled for all kernel structures not + mapped into both kernel and userspace page tables. This + feature of the MMU allows different processes to share TLB + entries mapping the kernel. Losing the feature means more + TLB misses after a context switch. The actual loss of + performance is very small, however, never exceeding 1%. + d. Process Context IDentifiers (PCID) is a CPU feature that + allows us to skip flushing the entire TLB when switching page + tables by setting a special bit in CR3 when the page tables + are changed. This makes switching the page tables (at context + switch, or kernel entry/exit) cheaper. But, on systems with + PCID support, the context switch code must flush both the user + and kernel entries out of the TLB. The user PCID TLB flush is + deferred until the exit to userspace, minimizing the cost. + See intel.com/sdm for the gory PCID/INVPCID details. + e. The userspace page tables must be populated for each new + process. Even without PTI, the shared kernel mappings + are created by copying top-level (PGD) entries into each + new process. But, with PTI, there are now *two* kernel + mappings: one in the kernel page tables that maps everything + and one for the entry/exit structures. At fork(), we need to + copy both. + f. In addition to the fork()-time copying, there must also + be an update to the userspace PGD any time a set_pgd() is done + on a PGD used to map userspace. This ensures that the kernel + and userspace copies always map the same userspace + memory. + g. On systems without PCID support, each CR3 write flushes + the entire TLB. That means that each syscall, interrupt + or exception flushes the TLB. + h. INVPCID is a TLB-flushing instruction which allows flushing + of TLB entries for non-current PCIDs. Some systems support + PCIDs, but do not support INVPCID. On these systems, addresses + can only be flushed from the TLB for the current PCID. When + flushing a kernel address, we need to flush all PCIDs, so a + single kernel address flush will require a TLB-flushing CR3 + write upon the next use of every PCID. + +Possible Future Work +==================== +1. We can be more careful about not actually writing to CR3 + unless its value is actually changed. +2. Allow PTI to be enabled/disabled at runtime in addition to the + boot-time switching. + +Testing +======== + +To test stability of PTI, the following test procedure is recommended, +ideally doing all of these in parallel: + +1. Set CONFIG_DEBUG_ENTRY=y +2. Run several copies of all of the tools/testing/selftests/x86/ tests + (excluding MPX and protection_keys) in a loop on multiple CPUs for + several minutes. These tests frequently uncover corner cases in the + kernel entry code. In general, old kernels might cause these tests + themselves to crash, but they should never crash the kernel. +3. Run the 'perf' tool in a mode (top or record) that generates many + frequent performance monitoring non-maskable interrupts (see "NMI" + in /proc/interrupts). This exercises the NMI entry/exit code which + is known to trigger bugs in code paths that did not expect to be + interrupted, including nested NMIs. Using "-c" boosts the rate of + NMIs, and using two -c with separate counters encourages nested NMIs + and less deterministic behavior. + + while true; do perf record -c 10000 -e instructions,cycles -a sleep 10; done + +4. Launch a KVM virtual machine. +5. Run 32-bit binaries on systems supporting the SYSCALL instruction. + This has been a lightly-tested code path and needs extra scrutiny. + +Debugging +========= + +Bugs in PTI cause a few different signatures of crashes +that are worth noting here. + + * Failures of the selftests/x86 code. Usually a bug in one of the + more obscure corners of entry_64.S + * Crashes in early boot, especially around CPU bringup. Bugs + in the trampoline code or mappings cause these. + * Crashes at the first interrupt. Caused by bugs in entry_64.S, + like screwing up a page table switch. Also caused by + incorrectly mapping the IRQ handler entry code. + * Crashes at the first NMI. The NMI code is separate from main + interrupt handlers and can have bugs that do not affect + normal interrupts. Also caused by incorrectly mapping NMI + code. NMIs that interrupt the entry code must be very + careful and can be the cause of crashes that show up when + running perf. + * Kernel crashes at the first exit to userspace. entry_64.S + bugs, or failing to map some of the exit code. + * Crashes at first interrupt that interrupts userspace. The paths + in entry_64.S that return to userspace are sometimes separate + from the ones that return to the kernel. + * Double faults: overflowing the kernel stack because of page + faults upon page faults. Caused by touching non-pti-mapped + data in the entry code, or forgetting to switch to kernel + CR3 before calling into C functions which are not pti-mapped. + * Userspace segfaults early in boot, sometimes manifesting + as mount(8) failing to mount the rootfs. These have + tended to be TLB invalidation issues. Usually invalidating + the wrong PCID, or otherwise missing an invalidation. + +1. https://gruss.cc/files/kaiser.pdf +2. https://meltdownattack.com/meltdown.pdf diff --git a/Makefile b/Makefile index 4779517d9bf0..07070a1e6292 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 111 +SUBLEVEL = 112 EXTRAVERSION = NAME = Blurry Fish Butt diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index 3a10c9f1d0a4..387ee2a11e36 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -113,7 +113,7 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) } trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr, - data); + &data); data = vcpu_data_host_to_guest(vcpu, data, len); vcpu_set_reg(vcpu, vcpu->arch.mmio_decode.rt, data); } @@ -189,14 +189,14 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, data = vcpu_data_guest_to_host(vcpu, vcpu_get_reg(vcpu, rt), len); - trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data); + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, &data); mmio_write_buf(data_buf, len, data); ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, fault_ipa, len, data_buf); } else { trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, len, - fault_ipa, 0); + fault_ipa, NULL); ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, fault_ipa, len, data_buf); diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 163b3449a8de..fcbc4e57d765 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -664,6 +664,18 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value) unsigned long switch_count; struct task_struct *t; + /* If nothing to change, return right away, successfully. */ + if (value == mips_get_process_fp_mode(task)) + return 0; + + /* Only accept a mode change if 64-bit FP enabled for o32. */ + if (!IS_ENABLED(CONFIG_MIPS_O32_FP64_SUPPORT)) + return -EOPNOTSUPP; + + /* And only for o32 tasks. */ + if (IS_ENABLED(CONFIG_64BIT) && !test_thread_flag(TIF_32BIT_REGS)) + return -EOPNOTSUPP; + /* Check the value is valid */ if (value & ~known_bits) return -EOPNOTSUPP; diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index a3f38e6b7ea1..c3d2d2c05fdb 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -439,63 +439,160 @@ static int gpr64_set(struct task_struct *target, #endif /* CONFIG_64BIT */ +/* + * Copy the floating-point context to the supplied NT_PRFPREG buffer, + * !CONFIG_CPU_HAS_MSA variant. FP context's general register slots + * correspond 1:1 to buffer slots. Only general registers are copied. + */ +static int fpr_get_fpa(struct task_struct *target, + unsigned int *pos, unsigned int *count, + void **kbuf, void __user **ubuf) +{ + return user_regset_copyout(pos, count, kbuf, ubuf, + &target->thread.fpu, + 0, NUM_FPU_REGS * sizeof(elf_fpreg_t)); +} + +/* + * Copy the floating-point context to the supplied NT_PRFPREG buffer, + * CONFIG_CPU_HAS_MSA variant. Only lower 64 bits of FP context's + * general register slots are copied to buffer slots. Only general + * registers are copied. + */ +static int fpr_get_msa(struct task_struct *target, + unsigned int *pos, unsigned int *count, + void **kbuf, void __user **ubuf) +{ + unsigned int i; + u64 fpr_val; + int err; + + BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t)); + for (i = 0; i < NUM_FPU_REGS; i++) { + fpr_val = get_fpr64(&target->thread.fpu.fpr[i], 0); + err = user_regset_copyout(pos, count, kbuf, ubuf, + &fpr_val, i * sizeof(elf_fpreg_t), + (i + 1) * sizeof(elf_fpreg_t)); + if (err) + return err; + } + + return 0; +} + +/* + * Copy the floating-point context to the supplied NT_PRFPREG buffer. + * Choose the appropriate helper for general registers, and then copy + * the FCSR register separately. + */ static int fpr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - unsigned i; + const int fcr31_pos = NUM_FPU_REGS * sizeof(elf_fpreg_t); int err; - u64 fpr_val; - /* XXX fcr31 */ + if (sizeof(target->thread.fpu.fpr[0]) == sizeof(elf_fpreg_t)) + err = fpr_get_fpa(target, &pos, &count, &kbuf, &ubuf); + else + err = fpr_get_msa(target, &pos, &count, &kbuf, &ubuf); + if (err) + return err; - if (sizeof(target->thread.fpu.fpr[i]) == sizeof(elf_fpreg_t)) - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu, - 0, sizeof(elf_fpregset_t)); + err = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.fpu.fcr31, + fcr31_pos, fcr31_pos + sizeof(u32)); - for (i = 0; i < NUM_FPU_REGS; i++) { - fpr_val = get_fpr64(&target->thread.fpu.fpr[i], 0); - err = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &fpr_val, i * sizeof(elf_fpreg_t), - (i + 1) * sizeof(elf_fpreg_t)); + return err; +} + +/* + * Copy the supplied NT_PRFPREG buffer to the floating-point context, + * !CONFIG_CPU_HAS_MSA variant. Buffer slots correspond 1:1 to FP + * context's general register slots. Only general registers are copied. + */ +static int fpr_set_fpa(struct task_struct *target, + unsigned int *pos, unsigned int *count, + const void **kbuf, const void __user **ubuf) +{ + return user_regset_copyin(pos, count, kbuf, ubuf, + &target->thread.fpu, + 0, NUM_FPU_REGS * sizeof(elf_fpreg_t)); +} + +/* + * Copy the supplied NT_PRFPREG buffer to the floating-point context, + * CONFIG_CPU_HAS_MSA variant. Buffer slots are copied to lower 64 + * bits only of FP context's general register slots. Only general + * registers are copied. + */ +static int fpr_set_msa(struct task_struct *target, + unsigned int *pos, unsigned int *count, + const void **kbuf, const void __user **ubuf) +{ + unsigned int i; + u64 fpr_val; + int err; + + BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t)); + for (i = 0; i < NUM_FPU_REGS && *count > 0; i++) { + err = user_regset_copyin(pos, count, kbuf, ubuf, + &fpr_val, i * sizeof(elf_fpreg_t), + (i + 1) * sizeof(elf_fpreg_t)); if (err) return err; + set_fpr64(&target->thread.fpu.fpr[i], 0, fpr_val); } return 0; } +/* + * Copy the supplied NT_PRFPREG buffer to the floating-point context. + * Choose the appropriate helper for general registers, and then copy + * the FCSR register separately. + * + * We optimize for the case where `count % sizeof(elf_fpreg_t) == 0', + * which is supposed to have been guaranteed by the kernel before + * calling us, e.g. in `ptrace_regset'. We enforce that requirement, + * so that we can safely avoid preinitializing temporaries for + * partial register writes. + */ static int fpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - unsigned i; + const int fcr31_pos = NUM_FPU_REGS * sizeof(elf_fpreg_t); + u32 fcr31; int err; - u64 fpr_val; - /* XXX fcr31 */ + BUG_ON(count % sizeof(elf_fpreg_t)); + + if (pos + count > sizeof(elf_fpregset_t)) + return -EIO; init_fp_ctx(target); - if (sizeof(target->thread.fpu.fpr[i]) == sizeof(elf_fpreg_t)) - return user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu, - 0, sizeof(elf_fpregset_t)); + if (sizeof(target->thread.fpu.fpr[0]) == sizeof(elf_fpreg_t)) + err = fpr_set_fpa(target, &pos, &count, &kbuf, &ubuf); + else + err = fpr_set_msa(target, &pos, &count, &kbuf, &ubuf); + if (err) + return err; - BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t)); - for (i = 0; i < NUM_FPU_REGS && count >= sizeof(elf_fpreg_t); i++) { + if (count > 0) { err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &fpr_val, i * sizeof(elf_fpreg_t), - (i + 1) * sizeof(elf_fpreg_t)); + &fcr31, + fcr31_pos, fcr31_pos + sizeof(u32)); if (err) return err; - set_fpr64(&target->thread.fpu.fpr[i], 0, fpr_val); + + ptrace_setfcr31(target, fcr31); } - return 0; + return err; } enum mips_regset { diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 39d2dc66faa5..0ef2cdd11616 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -62,6 +62,7 @@ config X86 select GENERIC_CLOCKEVENTS_MIN_ADJUST select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE + select GENERIC_CPU_VULNERABILITIES select GENERIC_EARLY_IOREMAP select GENERIC_FIND_FIRST_BIT select GENERIC_IOMAP diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 09936e9c8154..d1cf17173b1b 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -138,7 +138,7 @@ static inline int alternatives_text_reserved(void *start, void *end) ".popsection\n" \ ".pushsection .altinstr_replacement, \"ax\"\n" \ ALTINSTR_REPLACEMENT(newinstr, feature, 1) \ - ".popsection" + ".popsection\n" #define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\ OLDINSTR_2(oldinstr, 1, 2) \ @@ -149,7 +149,7 @@ static inline int alternatives_text_reserved(void *start, void *end) ".pushsection .altinstr_replacement, \"ax\"\n" \ ALTINSTR_REPLACEMENT(newinstr1, feature1, 1) \ ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \ - ".popsection" + ".popsection\n" /* * This must be included *after* the definition of ALTERNATIVE due to diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index f6605712ca90..142028afd049 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -277,6 +277,9 @@ #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_CPU_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */ +#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */ +#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ #if defined(__KERNEL__) && !defined(__ASSEMBLY__) @@ -359,6 +362,8 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; set_bit(bit, (unsigned long *)cpu_caps_set); \ } while (0) +#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) + #define cpu_has_fpu boot_cpu_has(X86_FEATURE_FPU) #define cpu_has_de boot_cpu_has(X86_FEATURE_DE) #define cpu_has_pse boot_cpu_has(X86_FEATURE_PSE) diff --git a/arch/x86/include/asm/kaiser.h b/arch/x86/include/asm/kaiser.h index 802bbbdfe143..48c791a411ab 100644 --- a/arch/x86/include/asm/kaiser.h +++ b/arch/x86/include/asm/kaiser.h @@ -19,6 +19,16 @@ #define KAISER_SHADOW_PGD_OFFSET 0x1000 +#ifdef CONFIG_PAGE_TABLE_ISOLATION +/* + * A page table address must have this alignment to stay the same when + * KAISER_SHADOW_PGD_OFFSET mask is applied + */ +#define KAISER_KERNEL_PGD_ALIGNMENT (KAISER_SHADOW_PGD_OFFSET << 1) +#else +#define KAISER_KERNEL_PGD_ALIGNMENT PAGE_SIZE +#endif + #ifdef __ASSEMBLY__ #ifdef CONFIG_PAGE_TABLE_ISOLATION diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index f3bdaed0188f..c124d6ab4bf9 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -156,8 +156,8 @@ extern struct cpuinfo_x86 boot_cpu_data; extern struct cpuinfo_x86 new_cpu_data; extern struct tss_struct doublefault_tss; -extern __u32 cpu_caps_cleared[NCAPINTS]; -extern __u32 cpu_caps_set[NCAPINTS]; +extern __u32 cpu_caps_cleared[NCAPINTS + NBUGINTS]; +extern __u32 cpu_caps_set[NCAPINTS + NBUGINTS]; #ifdef CONFIG_SMP DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 6045cef376c2..c926255745e1 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -4,7 +4,7 @@ #include #include -#ifdef CONFIG_PARAVIRT_CLOCK +#ifdef CONFIG_KVM_GUEST extern struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void); #else static inline struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void) diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 1e5eb9f2ff5f..a1e4a6c3f394 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -321,13 +321,12 @@ acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long e #ifdef CONFIG_X86_IO_APIC #define MP_ISA_BUS 0 +static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity, + u8 trigger, u32 gsi); + static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, u32 gsi) { - int ioapic; - int pin; - struct mpc_intsrc mp_irq; - /* * Check bus_irq boundary. */ @@ -336,14 +335,6 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, return; } - /* - * Convert 'gsi' to 'ioapic.pin'. - */ - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) - return; - pin = mp_find_ioapic_pin(ioapic, gsi); - /* * TBD: This check is for faulty timer entries, where the override * erroneously sets the trigger to level, resulting in a HUGE @@ -352,16 +343,8 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger, if ((bus_irq == 0) && (trigger == 3)) trigger = 1; - mp_irq.type = MP_INTSRC; - mp_irq.irqtype = mp_INT; - mp_irq.irqflag = (trigger << 2) | polarity; - mp_irq.srcbus = MP_ISA_BUS; - mp_irq.srcbusirq = bus_irq; /* IRQ */ - mp_irq.dstapic = mpc_ioapic_id(ioapic); /* APIC ID */ - mp_irq.dstirq = pin; /* INTIN# */ - - mp_save_irq(&mp_irq); - + if (mp_register_ioapic_irq(bus_irq, polarity, trigger, gsi) < 0) + return; /* * Reset default identity mapping if gsi is also an legacy IRQ, * otherwise there will be more than one entry with the same GSI @@ -408,6 +391,34 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, return 0; } +static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity, + u8 trigger, u32 gsi) +{ + struct mpc_intsrc mp_irq; + int ioapic, pin; + + /* Convert 'gsi' to 'ioapic.pin'(INTIN#) */ + ioapic = mp_find_ioapic(gsi); + if (ioapic < 0) { + pr_warn("Failed to find ioapic for gsi : %u\n", gsi); + return ioapic; + } + + pin = mp_find_ioapic_pin(ioapic, gsi); + + mp_irq.type = MP_INTSRC; + mp_irq.irqtype = mp_INT; + mp_irq.irqflag = (trigger << 2) | polarity; + mp_irq.srcbus = MP_ISA_BUS; + mp_irq.srcbusirq = bus_irq; + mp_irq.dstapic = mpc_ioapic_id(ioapic); + mp_irq.dstirq = pin; + + mp_save_irq(&mp_irq); + + return 0; +} + static int __init acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end) { @@ -452,7 +463,11 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger, if (acpi_sci_flags & ACPI_MADT_POLARITY_MASK) polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK; - mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); + if (bus_irq < NR_IRQS_LEGACY) + mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); + else + mp_register_ioapic_irq(bus_irq, polarity, trigger, gsi); + acpi_penalize_sci_irq(bus_irq, trigger, polarity); /* diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 25f909362b7a..d6f375f1b928 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -339,9 +339,12 @@ done: static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr) { unsigned long flags; + int i; - if (instr[0] != 0x90) - return; + for (i = 0; i < a->padlen; i++) { + if (instr[i] != 0x90) + return; + } local_irq_save(flags); add_nops(instr + (a->instrlen - a->padlen), a->padlen); diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 58031303e304..8f184615053b 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -16,13 +16,11 @@ obj-y := intel_cacheinfo.o scattered.o topology.o obj-y += common.o obj-y += rdrand.o obj-y += match.o +obj-y += bugs.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o -obj-$(CONFIG_X86_32) += bugs.o -obj-$(CONFIG_X86_64) += bugs_64.o - obj-$(CONFIG_CPU_SUP_INTEL) += intel.o obj-$(CONFIG_CPU_SUP_AMD) += amd.o obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 0b6124315441..cd46f9039119 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -9,6 +9,7 @@ */ #include #include +#include #include #include #include @@ -16,6 +17,8 @@ #include #include #include +#include +#include void __init check_bugs(void) { @@ -28,11 +31,13 @@ void __init check_bugs(void) #endif identify_boot_cpu(); -#ifndef CONFIG_SMP - pr_info("CPU: "); - print_cpu_info(&boot_cpu_data); -#endif + if (!IS_ENABLED(CONFIG_SMP)) { + pr_info("CPU: "); + print_cpu_info(&boot_cpu_data); + } + +#ifdef CONFIG_X86_32 /* * Check whether we are able to run this kernel safely on SMP. * @@ -48,4 +53,46 @@ void __init check_bugs(void) alternative_instructions(); fpu__init_check_bugs(); +#else /* CONFIG_X86_64 */ + alternative_instructions(); + + /* + * Make sure the first 2MB area is not mapped by huge pages + * There are typically fixed size MTRRs in there and overlapping + * MTRRs into large pages causes slow downs. + * + * Right now we don't do that with gbpages because there seems + * very little benefit for that case. + */ + if (!direct_gbpages) + set_memory_4k((unsigned long)__va(0), 1); +#endif } + +#ifdef CONFIG_SYSFS +ssize_t cpu_show_meltdown(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + return sprintf(buf, "Not affected\n"); + if (boot_cpu_has(X86_FEATURE_KAISER)) + return sprintf(buf, "Mitigation: PTI\n"); + return sprintf(buf, "Vulnerable\n"); +} + +ssize_t cpu_show_spectre_v1(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) + return sprintf(buf, "Not affected\n"); + return sprintf(buf, "Vulnerable\n"); +} + +ssize_t cpu_show_spectre_v2(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + return sprintf(buf, "Not affected\n"); + return sprintf(buf, "Vulnerable\n"); +} +#endif diff --git a/arch/x86/kernel/cpu/bugs_64.c b/arch/x86/kernel/cpu/bugs_64.c deleted file mode 100644 index 04f0fe5af83e..000000000000 --- a/arch/x86/kernel/cpu/bugs_64.c +++ /dev/null @@ -1,33 +0,0 @@ -/* - * Copyright (C) 1994 Linus Torvalds - * Copyright (C) 2000 SuSE - */ - -#include -#include -#include -#include -#include -#include -#include - -void __init check_bugs(void) -{ - identify_boot_cpu(); -#if !defined(CONFIG_SMP) - printk(KERN_INFO "CPU: "); - print_cpu_info(&boot_cpu_data); -#endif - alternative_instructions(); - - /* - * Make sure the first 2MB area is not mapped by huge pages - * There are typically fixed size MTRRs in there and overlapping - * MTRRs into large pages causes slow downs. - * - * Right now we don't do that with gbpages because there seems - * very little benefit for that case. - */ - if (!direct_gbpages) - set_memory_4k((unsigned long)__va(0), 1); -} diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index cc154ac64f00..dc4dfad66a70 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -432,8 +432,8 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c) return NULL; /* Not found */ } -__u32 cpu_caps_cleared[NCAPINTS]; -__u32 cpu_caps_set[NCAPINTS]; +__u32 cpu_caps_cleared[NCAPINTS + NBUGINTS]; +__u32 cpu_caps_set[NCAPINTS + NBUGINTS]; void load_percpu_segment(int cpu) { @@ -664,6 +664,16 @@ void cpu_detect(struct cpuinfo_x86 *c) } } +static void apply_forced_caps(struct cpuinfo_x86 *c) +{ + int i; + + for (i = 0; i < NCAPINTS + NBUGINTS; i++) { + c->x86_capability[i] &= ~cpu_caps_cleared[i]; + c->x86_capability[i] |= cpu_caps_set[i]; + } +} + void get_cpu_cap(struct cpuinfo_x86 *c) { u32 tfms, xlvl; @@ -820,6 +830,13 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) } setup_force_cpu_cap(X86_FEATURE_ALWAYS); + + /* Assume for now that ALL x86 CPUs are insecure */ + setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); + + setup_force_cpu_bug(X86_BUG_SPECTRE_V1); + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + fpu__init_system(c); } @@ -955,11 +972,8 @@ static void identify_cpu(struct cpuinfo_x86 *c) if (this_cpu->c_identify) this_cpu->c_identify(c); - /* Clear/Set all flags overriden by options, after probe */ - for (i = 0; i < NCAPINTS; i++) { - c->x86_capability[i] &= ~cpu_caps_cleared[i]; - c->x86_capability[i] |= cpu_caps_set[i]; - } + /* Clear/Set all flags overridden by options, after probe */ + apply_forced_caps(c); #ifdef CONFIG_X86_64 c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); @@ -1020,10 +1034,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) * Clear/Set all flags overriden by options, need do it * before following smp all cpus cap AND. */ - for (i = 0; i < NCAPINTS; i++) { - c->x86_capability[i] &= ~cpu_caps_cleared[i]; - c->x86_capability[i] |= cpu_caps_set[i]; - } + apply_forced_caps(c); /* * On SMP, boot_cpu_data holds the common feature set between diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index abf581ade8d2..b428a8174be1 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -994,9 +994,17 @@ static bool is_blacklisted(unsigned int cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); - if (c->x86 == 6 && c->x86_model == 79) { - pr_err_once("late loading on model 79 is disabled.\n"); - return true; + /* + * Late loading on model 79 with microcode revision less than 0x0b000021 + * may result in a system hang. This behavior is documented in item + * BDF90, #334165 (Intel Xeon Processor E7-8800/4800 v4 Product Family). + */ + if (c->x86 == 6 && + c->x86_model == 79 && + c->x86_mask == 0x01 && + c->microcode < 0x0b000021) { + pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode); + pr_err_once("Please consider either early loading through initrd/built-in or a potential BIOS update.\n"); } return false; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 4b1152e57340..900ffb6c28b5 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3855,6 +3855,25 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) "mov %%r13, %c[r13](%[svm]) \n\t" "mov %%r14, %c[r14](%[svm]) \n\t" "mov %%r15, %c[r15](%[svm]) \n\t" +#endif + /* + * Clear host registers marked as clobbered to prevent + * speculative use. + */ + "xor %%" _ASM_BX ", %%" _ASM_BX " \n\t" + "xor %%" _ASM_CX ", %%" _ASM_CX " \n\t" + "xor %%" _ASM_DX ", %%" _ASM_DX " \n\t" + "xor %%" _ASM_SI ", %%" _ASM_SI " \n\t" + "xor %%" _ASM_DI ", %%" _ASM_DI " \n\t" +#ifdef CONFIG_X86_64 + "xor %%r8, %%r8 \n\t" + "xor %%r9, %%r9 \n\t" + "xor %%r10, %%r10 \n\t" + "xor %%r11, %%r11 \n\t" + "xor %%r12, %%r12 \n\t" + "xor %%r13, %%r13 \n\t" + "xor %%r14, %%r14 \n\t" + "xor %%r15, %%r15 \n\t" #endif "pop %%" _ASM_BP : diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index d915185ada05..c26255f19603 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -828,8 +828,16 @@ static inline short vmcs_field_to_offset(unsigned long field) { BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX); - if (field >= ARRAY_SIZE(vmcs_field_to_offset_table) || - vmcs_field_to_offset_table[field] == 0) + if (field >= ARRAY_SIZE(vmcs_field_to_offset_table)) + return -ENOENT; + + /* + * FIXME: Mitigation for CVE-2017-5753. To be replaced with a + * generic mechanism. + */ + asm("lfence"); + + if (vmcs_field_to_offset_table[field] == 0) return -ENOENT; return vmcs_field_to_offset_table[field]; @@ -8623,6 +8631,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) /* Save guest registers, load host registers, keep flags */ "mov %0, %c[wordsize](%%" _ASM_SP ") \n\t" "pop %0 \n\t" + "setbe %c[fail](%0)\n\t" "mov %%" _ASM_AX ", %c[rax](%0) \n\t" "mov %%" _ASM_BX ", %c[rbx](%0) \n\t" __ASM_SIZE(pop) " %c[rcx](%0) \n\t" @@ -8639,12 +8648,23 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) "mov %%r13, %c[r13](%0) \n\t" "mov %%r14, %c[r14](%0) \n\t" "mov %%r15, %c[r15](%0) \n\t" + "xor %%r8d, %%r8d \n\t" + "xor %%r9d, %%r9d \n\t" + "xor %%r10d, %%r10d \n\t" + "xor %%r11d, %%r11d \n\t" + "xor %%r12d, %%r12d \n\t" + "xor %%r13d, %%r13d \n\t" + "xor %%r14d, %%r14d \n\t" + "xor %%r15d, %%r15d \n\t" #endif "mov %%cr2, %%" _ASM_AX " \n\t" "mov %%" _ASM_AX ", %c[cr2](%0) \n\t" + "xor %%eax, %%eax \n\t" + "xor %%ebx, %%ebx \n\t" + "xor %%esi, %%esi \n\t" + "xor %%edi, %%edi \n\t" "pop %%" _ASM_BP "; pop %%" _ASM_DX " \n\t" - "setbe %c[fail](%0) \n\t" ".pushsection .rodata \n\t" ".global vmx_return \n\t" "vmx_return: " _ASM_PTR " 2b \n\t" diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ccf17dbfea09..f973cfa8ff4f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4114,7 +4114,7 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) addr, n, v)) && kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v)) break; - trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, *(u64 *)v); + trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, v); handled += n; addr += n; len -= n; @@ -4362,7 +4362,7 @@ static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes) { if (vcpu->mmio_read_completed) { trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes, - vcpu->mmio_fragments[0].gpa, *(u64 *)val); + vcpu->mmio_fragments[0].gpa, val); vcpu->mmio_read_completed = 0; return 1; } @@ -4384,14 +4384,14 @@ static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, static int write_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes, void *val) { - trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val); + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, val); return vcpu_mmio_write(vcpu, gpa, bytes, val); } static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, void *val, int bytes) { - trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0); + trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, NULL); return X86EMUL_IO_NEEDED; } diff --git a/arch/x86/mm/kaiser.c b/arch/x86/mm/kaiser.c index 6a7a77929a8c..8af98513d36c 100644 --- a/arch/x86/mm/kaiser.c +++ b/arch/x86/mm/kaiser.c @@ -198,6 +198,8 @@ static int kaiser_add_user_map(const void *__start_addr, unsigned long size, * requires that not to be #defined to 0): so mask it off here. */ flags &= ~_PAGE_GLOBAL; + if (!(__supported_pte_mask & _PAGE_NX)) + flags &= ~_PAGE_NX; for (; address < end_addr; address += PAGE_SIZE) { target_address = get_pa_from_mapping(address); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 3f1bb4f93a5a..3146b1da6d72 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -750,11 +750,8 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size) return 1; while (cursor < to) { - if (!devmem_is_allowed(pfn)) { - pr_info("x86/PAT: Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n", - current->comm, from, to - 1); + if (!devmem_is_allowed(pfn)) return 0; - } cursor += PAGE_SIZE; pfn++; } diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 0b7a63d98440..805a3271a137 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -4,6 +4,7 @@ #include #include #include +#include struct real_mode_header *real_mode_header; u32 *trampoline_cr4_features; @@ -15,7 +16,8 @@ void __init reserve_real_mode(void) size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob); /* Has to be under 1M so we can execute real-mode AP code. */ - mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE); + mem = memblock_find_in_range(0, 1 << 20, size, + KAISER_KERNEL_PGD_ALIGNMENT); if (!mem) panic("Cannot allocate trampoline\n"); diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index dac7b20d2f9d..781cca63f795 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -30,6 +30,7 @@ #include #include #include +#include #include "realmode.h" .text @@ -139,7 +140,7 @@ tr_gdt: tr_gdt_end: .bss - .balign PAGE_SIZE + .balign KAISER_KERNEL_PGD_ALIGNMENT GLOBAL(trampoline_pgd) .space PAGE_SIZE .balign 8 diff --git a/crypto/algapi.c b/crypto/algapi.c index 43f5bdb6b570..eb58b73ca925 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -168,6 +168,18 @@ void crypto_remove_spawns(struct crypto_alg *alg, struct list_head *list, spawn->alg = NULL; spawns = &inst->alg.cra_users; + + /* + * We may encounter an unregistered instance here, since + * an instance's spawns are set up prior to the instance + * being registered. An unregistered instance will have + * NULL ->cra_users.next, since ->cra_users isn't + * properly initialized until registration. But an + * unregistered instance cannot have any users, so treat + * it the same as ->cra_users being empty. + */ + if (spawns->next == NULL) + break; } } while ((spawns = crypto_more_spawns(alg, &stack, &top, &secondary_spawns))); diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index 98504ec99c7d..59992788966c 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -223,6 +223,9 @@ config GENERIC_CPU_DEVICES config GENERIC_CPU_AUTOPROBE bool +config GENERIC_CPU_VULNERABILITIES + bool + config SOC_BUS bool diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 91bbb1959d8d..3db71afbba93 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -498,10 +498,58 @@ static void __init cpu_dev_register_generic(void) #endif } +#ifdef CONFIG_GENERIC_CPU_VULNERABILITIES + +ssize_t __weak cpu_show_meltdown(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + +ssize_t __weak cpu_show_spectre_v1(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + +ssize_t __weak cpu_show_spectre_v2(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + +static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); +static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); +static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); + +static struct attribute *cpu_root_vulnerabilities_attrs[] = { + &dev_attr_meltdown.attr, + &dev_attr_spectre_v1.attr, + &dev_attr_spectre_v2.attr, + NULL +}; + +static const struct attribute_group cpu_root_vulnerabilities_group = { + .name = "vulnerabilities", + .attrs = cpu_root_vulnerabilities_attrs, +}; + +static void __init cpu_register_vulnerabilities(void) +{ + if (sysfs_create_group(&cpu_subsys.dev_root->kobj, + &cpu_root_vulnerabilities_group)) + pr_err("Unable to register CPU vulnerabilities\n"); +} + +#else +static inline void cpu_register_vulnerabilities(void) { } +#endif + void __init cpu_dev_init(void) { if (subsys_system_register(&cpu_subsys, cpu_root_attr_groups)) panic("Failed to register CPU subsystem"); cpu_dev_register_generic(); + cpu_register_vulnerabilities(); } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index ca3bcc81b623..e0699a20859f 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3767,7 +3767,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) segment_size = rbd_obj_bytes(&rbd_dev->header); blk_queue_max_hw_sectors(q, segment_size / SECTOR_SIZE); q->limits.max_sectors = queue_max_hw_sectors(q); - blk_queue_max_segments(q, segment_size / SECTOR_SIZE); + blk_queue_max_segments(q, USHRT_MAX); blk_queue_max_segment_size(q, segment_size); blk_queue_io_min(q, segment_size); blk_queue_io_opt(q, segment_size); diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index cf25020576fa..340f96e44642 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -238,7 +238,10 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf, goto out; } - mutex_lock(&reading_mutex); + if (mutex_lock_interruptible(&reading_mutex)) { + err = -ERESTARTSYS; + goto out_put; + } if (!data_avail) { bytes_read = rng_get_data(rng, rng_buffer, rng_buffer_size(), @@ -288,6 +291,7 @@ out: out_unlock_reading: mutex_unlock(&reading_mutex); +out_put: put_rng(rng); goto out; } diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 2898d19fadf5..23f52a897283 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -70,12 +70,8 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size) u64 cursor = from; while (cursor < to) { - if (!devmem_is_allowed(pfn)) { - printk(KERN_INFO - "Program %s tried to access /dev/mem between %Lx->%Lx.\n", - current->comm, from, to); + if (!devmem_is_allowed(pfn)) return 0; - } cursor += PAGE_SIZE; pfn++; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 04fd0f2b6af0..fda8e85dd5a2 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -2678,6 +2678,8 @@ static int vmw_cmd_dx_view_define(struct vmw_private *dev_priv, } view_type = vmw_view_cmd_to_type(header->id); + if (view_type == vmw_view_max) + return -EINVAL; cmd = container_of(header, typeof(*cmd), header); ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface, user_surface_converter, diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index c52131233ba7..a73874508c3a 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -957,8 +957,7 @@ static int srpt_init_ch_qp(struct srpt_rdma_ch *ch, struct ib_qp *qp) return -ENOMEM; attr->qp_state = IB_QPS_INIT; - attr->qp_access_flags = IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_READ | - IB_ACCESS_REMOTE_WRITE; + attr->qp_access_flags = IB_ACCESS_LOCAL_WRITE; attr->port_num = ch->sport->port; attr->pkey_index = 0; diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 64f1eb8fdcbc..347aaaa5a7ea 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -1541,13 +1541,15 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain) return -ENOMEM; arm_smmu_ops.pgsize_bitmap = pgtbl_cfg.pgsize_bitmap; - smmu_domain->pgtbl_ops = pgtbl_ops; ret = finalise_stage_fn(smmu_domain, &pgtbl_cfg); - if (IS_ERR_VALUE(ret)) + if (IS_ERR_VALUE(ret)) { free_io_pgtable_ops(pgtbl_ops); + return ret; + } - return ret; + smmu_domain->pgtbl_ops = pgtbl_ops; + return 0; } static struct arm_smmu_group *arm_smmu_group_get(struct device *dev) diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 2ec7f90e3455..969c815c90b6 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1527,7 +1527,8 @@ static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan, int l; struct dm_buffer *b, *tmp; unsigned long freed = 0; - unsigned long count = nr_to_scan; + unsigned long count = c->n_buffers[LIST_CLEAN] + + c->n_buffers[LIST_DIRTY]; unsigned long retain_target = get_retain_buffers(c); for (l = 0; l < LIST_SIZE; l++) { @@ -1564,6 +1565,7 @@ dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { struct dm_bufio_client *c; unsigned long count; + unsigned long retain_target; c = container_of(shrink, struct dm_bufio_client, shrinker); if (sc->gfp_mask & __GFP_FS) @@ -1572,8 +1574,9 @@ dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc) return 0; count = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY]; + retain_target = get_retain_buffers(c); dm_bufio_unlock(c); - return count; + return (count < retain_target) ? 0 : (count - retain_target); } /* diff --git a/drivers/media/usb/usbvision/usbvision-video.c b/drivers/media/usb/usbvision/usbvision-video.c index 91d709efef7a..cafc34938a79 100644 --- a/drivers/media/usb/usbvision/usbvision-video.c +++ b/drivers/media/usb/usbvision/usbvision-video.c @@ -1461,6 +1461,13 @@ static int usbvision_probe(struct usb_interface *intf, printk(KERN_INFO "%s: %s found\n", __func__, usbvision_device_data[model].model_string); + /* + * this is a security check. + * an exploit using an incorrect bInterfaceNumber is known + */ + if (ifnum >= USB_MAXINTERFACES || !dev->actconfig->interface[ifnum]) + return -ENODEV; + if (usbvision_device_data[model].interface >= 0) interface = &dev->actconfig->interface[usbvision_device_data[model].interface]->altsetting[0]; else if (ifnum < dev->actconfig->desc.bNumInterfaces) diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 27e2352fcc42..b227f81e4a7e 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -430,7 +430,7 @@ static int gs_usb_set_bittiming(struct net_device *netdev) dev_err(netdev->dev.parent, "Couldn't set bittimings (err=%d)", rc); - return rc; + return (rc > 0) ? 0 : rc; } static void gs_usb_xmit_callback(struct urb *urb) diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 91a5a0ae9cd7..1908a38e7f31 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1362,6 +1362,9 @@ out: * Checks to see of the link status of the hardware has changed. If a * change in link status has been detected, then we read the PHY registers * to get the current speed/duplex if link exists. + * + * Returns a negative error code (-E1000_ERR_*) or 0 (link down) or 1 (link + * up). **/ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) { @@ -1377,7 +1380,7 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) * Change or Rx Sequence Error interrupt. */ if (!mac->get_link_status) - return 0; + return 1; /* First we want to see if the MII Status Register reports * link. If so, then we want to get the current speed/duplex @@ -1585,10 +1588,12 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) * different link partner. */ ret_val = e1000e_config_fc_after_link_up(hw); - if (ret_val) + if (ret_val) { e_dbg("Error configuring flow control\n"); + return ret_val; + } - return ret_val; + return 1; } static s32 e1000_get_variants_ich8lan(struct e1000_adapter *adapter) diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 479af106aaeb..424d1dee55c9 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -3176,18 +3176,37 @@ static int sh_eth_drv_probe(struct platform_device *pdev) /* ioremap the TSU registers */ if (mdp->cd->tsu) { struct resource *rtsu; + rtsu = platform_get_resource(pdev, IORESOURCE_MEM, 1); - mdp->tsu_addr = devm_ioremap_resource(&pdev->dev, rtsu); - if (IS_ERR(mdp->tsu_addr)) { - ret = PTR_ERR(mdp->tsu_addr); + if (!rtsu) { + dev_err(&pdev->dev, "no TSU resource\n"); + ret = -ENODEV; + goto out_release; + } + /* We can only request the TSU region for the first port + * of the two sharing this TSU for the probe to succeed... + */ + if (devno % 2 == 0 && + !devm_request_mem_region(&pdev->dev, rtsu->start, + resource_size(rtsu), + dev_name(&pdev->dev))) { + dev_err(&pdev->dev, "can't request TSU resource.\n"); + ret = -EBUSY; + goto out_release; + } + mdp->tsu_addr = devm_ioremap(&pdev->dev, rtsu->start, + resource_size(rtsu)); + if (!mdp->tsu_addr) { + dev_err(&pdev->dev, "TSU region ioremap() failed.\n"); + ret = -ENOMEM; goto out_release; } mdp->port = devno % 2; ndev->features = NETIF_F_HW_VLAN_CTAG_FILTER; } - /* initialize first or needed device */ - if (!devno || pd->needs_init) { + /* Need to init only the first port of the two sharing a TSU */ + if (devno % 2 == 0) { if (mdp->cd->chip_reset) mdp->cd->chip_reset(ndev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 4b100ef4af9f..5adaf537513b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -272,8 +272,14 @@ bool stmmac_eee_init(struct stmmac_priv *priv) { char *phy_bus_name = priv->plat->phy_bus_name; unsigned long flags; + int interface = priv->plat->interface; bool ret = false; + if ((interface != PHY_INTERFACE_MODE_MII) && + (interface != PHY_INTERFACE_MODE_GMII) && + !phy_interface_mode_is_rgmii(interface)) + goto out; + /* Using PCS we cannot dial with the phy registers at this stage * so we do not support extra feature like EEE. */ diff --git a/drivers/net/usb/cx82310_eth.c b/drivers/net/usb/cx82310_eth.c index e221bfcee76b..947bea81d924 100644 --- a/drivers/net/usb/cx82310_eth.c +++ b/drivers/net/usb/cx82310_eth.c @@ -293,12 +293,9 @@ static struct sk_buff *cx82310_tx_fixup(struct usbnet *dev, struct sk_buff *skb, { int len = skb->len; - if (skb_headroom(skb) < 2) { - struct sk_buff *skb2 = skb_copy_expand(skb, 2, 0, flags); + if (skb_cow_head(skb, 2)) { dev_kfree_skb_any(skb); - skb = skb2; - if (!skb) - return NULL; + return NULL; } skb_push(skb, 2); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 226668ead0d8..41e9ebd7d0a6 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -2050,14 +2050,9 @@ static struct sk_buff *lan78xx_tx_prep(struct lan78xx_net *dev, { u32 tx_cmd_a, tx_cmd_b; - if (skb_headroom(skb) < TX_OVERHEAD) { - struct sk_buff *skb2; - - skb2 = skb_copy_expand(skb, TX_OVERHEAD, 0, flags); + if (skb_cow_head(skb, TX_OVERHEAD)) { dev_kfree_skb_any(skb); - skb = skb2; - if (!skb) - return NULL; + return NULL; } if (lan78xx_linearize(skb) < 0) diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 304ec25eaf95..89950f5cea71 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -25,12 +25,13 @@ #include #include #include +#include /* Information for net-next */ #define NETNEXT_VERSION "08" /* Information for net */ -#define NET_VERSION "2" +#define NET_VERSION "3" #define DRIVER_VERSION "v1." NETNEXT_VERSION "." NET_VERSION #define DRIVER_AUTHOR "Realtek linux nic maintainers " @@ -604,6 +605,9 @@ struct r8152 { struct delayed_work schedule; struct mii_if_info mii; struct mutex control; /* use for hw setting */ +#ifdef CONFIG_PM_SLEEP + struct notifier_block pm_notifier; +#endif struct rtl_ops { void (*init)(struct r8152 *); @@ -1943,7 +1947,6 @@ static void _rtl8152_set_rx_mode(struct net_device *netdev) __le32 tmp[2]; u32 ocp_data; - clear_bit(RTL8152_SET_RX_MODE, &tp->flags); netif_stop_queue(netdev); ocp_data = ocp_read_dword(tp, MCU_TYPE_PLA, PLA_RCR); ocp_data &= ~RCR_ACPT_ALL; @@ -2429,8 +2432,6 @@ static void rtl_phy_reset(struct r8152 *tp) u16 data; int i; - clear_bit(PHY_RESET, &tp->flags); - data = r8152_mdio_read(tp, MII_BMCR); /* don't reset again before the previous one complete */ @@ -2460,23 +2461,23 @@ static void r8153_teredo_off(struct r8152 *tp) ocp_write_dword(tp, MCU_TYPE_PLA, PLA_TEREDO_TIMER, 0); } -static void r8152b_disable_aldps(struct r8152 *tp) +static void r8152_aldps_en(struct r8152 *tp, bool enable) { - ocp_reg_write(tp, OCP_ALDPS_CONFIG, ENPDNPS | LINKENA | DIS_SDSAVE); - msleep(20); -} - -static inline void r8152b_enable_aldps(struct r8152 *tp) -{ - ocp_reg_write(tp, OCP_ALDPS_CONFIG, ENPWRSAVE | ENPDNPS | - LINKENA | DIS_SDSAVE); + if (enable) { + ocp_reg_write(tp, OCP_ALDPS_CONFIG, ENPWRSAVE | ENPDNPS | + LINKENA | DIS_SDSAVE); + } else { + ocp_reg_write(tp, OCP_ALDPS_CONFIG, ENPDNPS | LINKENA | + DIS_SDSAVE); + msleep(20); + } } static void rtl8152_disable(struct r8152 *tp) { - r8152b_disable_aldps(tp); + r8152_aldps_en(tp, false); rtl_disable(tp); - r8152b_enable_aldps(tp); + r8152_aldps_en(tp, true); } static void r8152b_hw_phy_cfg(struct r8152 *tp) @@ -2788,30 +2789,26 @@ static void r8153_enter_oob(struct r8152 *tp) ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, ocp_data); } -static void r8153_disable_aldps(struct r8152 *tp) -{ - u16 data; - - data = ocp_reg_read(tp, OCP_POWER_CFG); - data &= ~EN_ALDPS; - ocp_reg_write(tp, OCP_POWER_CFG, data); - msleep(20); -} - -static void r8153_enable_aldps(struct r8152 *tp) +static void r8153_aldps_en(struct r8152 *tp, bool enable) { u16 data; data = ocp_reg_read(tp, OCP_POWER_CFG); - data |= EN_ALDPS; - ocp_reg_write(tp, OCP_POWER_CFG, data); + if (enable) { + data |= EN_ALDPS; + ocp_reg_write(tp, OCP_POWER_CFG, data); + } else { + data &= ~EN_ALDPS; + ocp_reg_write(tp, OCP_POWER_CFG, data); + msleep(20); + } } static void rtl8153_disable(struct r8152 *tp) { - r8153_disable_aldps(tp); + r8153_aldps_en(tp, false); rtl_disable(tp); - r8153_enable_aldps(tp); + r8153_aldps_en(tp, true); usb_enable_lpm(tp->udev); } @@ -2889,10 +2886,9 @@ static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u16 speed, u8 duplex) r8152_mdio_write(tp, MII_ADVERTISE, anar); r8152_mdio_write(tp, MII_BMCR, bmcr); - if (test_bit(PHY_RESET, &tp->flags)) { + if (test_and_clear_bit(PHY_RESET, &tp->flags)) { int i; - clear_bit(PHY_RESET, &tp->flags); for (i = 0; i < 50; i++) { msleep(20); if ((r8152_mdio_read(tp, MII_BMCR) & BMCR_RESET) == 0) @@ -2901,7 +2897,6 @@ static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u16 speed, u8 duplex) } out: - return ret; } @@ -2910,9 +2905,9 @@ static void rtl8152_up(struct r8152 *tp) if (test_bit(RTL8152_UNPLUG, &tp->flags)) return; - r8152b_disable_aldps(tp); + r8152_aldps_en(tp, false); r8152b_exit_oob(tp); - r8152b_enable_aldps(tp); + r8152_aldps_en(tp, true); } static void rtl8152_down(struct r8152 *tp) @@ -2923,9 +2918,9 @@ static void rtl8152_down(struct r8152 *tp) } r8152_power_cut_en(tp, false); - r8152b_disable_aldps(tp); + r8152_aldps_en(tp, false); r8152b_enter_oob(tp); - r8152b_enable_aldps(tp); + r8152_aldps_en(tp, true); } static void rtl8153_up(struct r8152 *tp) @@ -2934,9 +2929,9 @@ static void rtl8153_up(struct r8152 *tp) return; r8153_u1u2en(tp, false); - r8153_disable_aldps(tp); + r8153_aldps_en(tp, false); r8153_first_init(tp); - r8153_enable_aldps(tp); + r8153_aldps_en(tp, true); r8153_u2p3en(tp, true); r8153_u1u2en(tp, true); usb_enable_lpm(tp->udev); @@ -2952,9 +2947,9 @@ static void rtl8153_down(struct r8152 *tp) r8153_u1u2en(tp, false); r8153_u2p3en(tp, false); r8153_power_cut_en(tp, false); - r8153_disable_aldps(tp); + r8153_aldps_en(tp, false); r8153_enter_oob(tp); - r8153_enable_aldps(tp); + r8153_aldps_en(tp, true); } static bool rtl8152_in_nway(struct r8152 *tp) @@ -2988,7 +2983,6 @@ static void set_carrier(struct r8152 *tp) struct net_device *netdev = tp->netdev; u8 speed; - clear_bit(RTL8152_LINK_CHG, &tp->flags); speed = rtl8152_get_speed(tp); if (speed & LINK_STATUS) { @@ -3038,20 +3032,18 @@ static void rtl_work_func_t(struct work_struct *work) goto out1; } - if (test_bit(RTL8152_LINK_CHG, &tp->flags)) + if (test_and_clear_bit(RTL8152_LINK_CHG, &tp->flags)) set_carrier(tp); - if (test_bit(RTL8152_SET_RX_MODE, &tp->flags)) + if (test_and_clear_bit(RTL8152_SET_RX_MODE, &tp->flags)) _rtl8152_set_rx_mode(tp->netdev); /* don't schedule napi before linking */ - if (test_bit(SCHEDULE_NAPI, &tp->flags) && - netif_carrier_ok(tp->netdev)) { - clear_bit(SCHEDULE_NAPI, &tp->flags); + if (test_and_clear_bit(SCHEDULE_NAPI, &tp->flags) && + netif_carrier_ok(tp->netdev)) napi_schedule(&tp->napi); - } - if (test_bit(PHY_RESET, &tp->flags)) + if (test_and_clear_bit(PHY_RESET, &tp->flags)) rtl_phy_reset(tp); mutex_unlock(&tp->control); @@ -3060,6 +3052,33 @@ out1: usb_autopm_put_interface(tp->intf); } +#ifdef CONFIG_PM_SLEEP +static int rtl_notifier(struct notifier_block *nb, unsigned long action, + void *data) +{ + struct r8152 *tp = container_of(nb, struct r8152, pm_notifier); + + switch (action) { + case PM_HIBERNATION_PREPARE: + case PM_SUSPEND_PREPARE: + usb_autopm_get_interface(tp->intf); + break; + + case PM_POST_HIBERNATION: + case PM_POST_SUSPEND: + usb_autopm_put_interface(tp->intf); + break; + + case PM_POST_RESTORE: + case PM_RESTORE_PREPARE: + default: + break; + } + + return NOTIFY_DONE; +} +#endif + static int rtl8152_open(struct net_device *netdev) { struct r8152 *tp = netdev_priv(netdev); @@ -3102,6 +3121,10 @@ static int rtl8152_open(struct net_device *netdev) mutex_unlock(&tp->control); usb_autopm_put_interface(tp->intf); +#ifdef CONFIG_PM_SLEEP + tp->pm_notifier.notifier_call = rtl_notifier; + register_pm_notifier(&tp->pm_notifier); +#endif out: return res; @@ -3112,6 +3135,9 @@ static int rtl8152_close(struct net_device *netdev) struct r8152 *tp = netdev_priv(netdev); int res = 0; +#ifdef CONFIG_PM_SLEEP + unregister_pm_notifier(&tp->pm_notifier); +#endif napi_disable(&tp->napi); clear_bit(WORK_ENABLE, &tp->flags); usb_kill_urb(tp->intr_urb); @@ -3250,7 +3276,7 @@ static void r8152b_init(struct r8152 *tp) if (test_bit(RTL8152_UNPLUG, &tp->flags)) return; - r8152b_disable_aldps(tp); + r8152_aldps_en(tp, false); if (tp->version == RTL_VER_01) { ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_LED_FEATURE); @@ -3272,7 +3298,7 @@ static void r8152b_init(struct r8152 *tp) ocp_write_word(tp, MCU_TYPE_PLA, PLA_GPHY_INTR_IMR, ocp_data); r8152b_enable_eee(tp); - r8152b_enable_aldps(tp); + r8152_aldps_en(tp, true); r8152b_enable_fc(tp); rtl_tally_reset(tp); @@ -3290,7 +3316,7 @@ static void r8153_init(struct r8152 *tp) if (test_bit(RTL8152_UNPLUG, &tp->flags)) return; - r8153_disable_aldps(tp); + r8153_aldps_en(tp, false); r8153_u1u2en(tp, false); for (i = 0; i < 500; i++) { @@ -3379,7 +3405,7 @@ static void r8153_init(struct r8152 *tp) EEE_SPDWN_EN); r8153_enable_eee(tp); - r8153_enable_aldps(tp); + r8153_aldps_en(tp, true); r8152b_enable_fc(tp); rtl_tally_reset(tp); r8153_u2p3en(tp, true); diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 30033dbe6662..c5f375befd2f 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -2193,13 +2193,9 @@ static struct sk_buff *smsc75xx_tx_fixup(struct usbnet *dev, { u32 tx_cmd_a, tx_cmd_b; - if (skb_headroom(skb) < SMSC75XX_TX_OVERHEAD) { - struct sk_buff *skb2 = - skb_copy_expand(skb, SMSC75XX_TX_OVERHEAD, 0, flags); + if (skb_cow_head(skb, SMSC75XX_TX_OVERHEAD)) { dev_kfree_skb_any(skb); - skb = skb2; - if (!skb) - return NULL; + return NULL; } tx_cmd_a = (u32)(skb->len & TX_CMD_A_LEN) | TX_CMD_A_FCS; diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index 4a1e9c489f1f..aadfe1d1c37e 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -456,14 +456,9 @@ static struct sk_buff *sr9700_tx_fixup(struct usbnet *dev, struct sk_buff *skb, len = skb->len; - if (skb_headroom(skb) < SR_TX_OVERHEAD) { - struct sk_buff *skb2; - - skb2 = skb_copy_expand(skb, SR_TX_OVERHEAD, 0, flags); + if (skb_cow_head(skb, SR_TX_OVERHEAD)) { dev_kfree_skb_any(skb); - skb = skb2; - if (!skb) - return NULL; + return NULL; } __skb_push(skb, SR_TX_OVERHEAD); diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index 9c6357c03905..b64327722660 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -759,10 +759,12 @@ static long ashmem_ioctl(struct file *file, unsigned int cmd, unsigned long arg) break; case ASHMEM_SET_SIZE: ret = -EINVAL; + mutex_lock(&ashmem_mutex); if (!asma->file) { ret = 0; asma->size = (size_t)arg; } + mutex_unlock(&ashmem_mutex); break; case ASHMEM_GET_SIZE: ret = asma->size; diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 8a4092cd97ee..58fe27705b96 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1759,7 +1759,6 @@ iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, struct iscsi_tmr_req *tmr_req; struct iscsi_tm *hdr; int out_of_order_cmdsn = 0, ret; - bool sess_ref = false; u8 function, tcm_function = TMR_UNKNOWN; hdr = (struct iscsi_tm *) buf; @@ -1801,18 +1800,17 @@ iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, buf); } + transport_init_se_cmd(&cmd->se_cmd, &iscsi_ops, + conn->sess->se_sess, 0, DMA_NONE, + TCM_SIMPLE_TAG, cmd->sense_buffer + 2); + + target_get_sess_cmd(&cmd->se_cmd, true); + /* * TASK_REASSIGN for ERL=2 / connection stays inside of * LIO-Target $FABRIC_MOD */ if (function != ISCSI_TM_FUNC_TASK_REASSIGN) { - transport_init_se_cmd(&cmd->se_cmd, &iscsi_ops, - conn->sess->se_sess, 0, DMA_NONE, - TCM_SIMPLE_TAG, cmd->sense_buffer + 2); - - target_get_sess_cmd(&cmd->se_cmd, true); - sess_ref = true; - switch (function) { case ISCSI_TM_FUNC_ABORT_TASK: tcm_function = TMR_ABORT_TASK; @@ -1951,12 +1949,8 @@ attach: * For connection recovery, this is also the default action for * TMR TASK_REASSIGN. */ - if (sess_ref) { - pr_debug("Handle TMR, using sess_ref=true check\n"); - target_put_sess_cmd(&cmd->se_cmd); - } - iscsit_add_cmd_to_response_queue(cmd, conn, cmd->i_state); + target_put_sess_cmd(&cmd->se_cmd); return 0; } EXPORT_SYMBOL(iscsit_handle_task_mgt_cmd); diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index c9be953496ec..e926dd52b6b5 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -133,6 +133,15 @@ static bool __target_check_io_state(struct se_cmd *se_cmd, spin_unlock(&se_cmd->t_state_lock); return false; } + if (se_cmd->transport_state & CMD_T_PRE_EXECUTE) { + if (se_cmd->scsi_status) { + pr_debug("Attempted to abort io tag: %llu early failure" + " status: 0x%02x\n", se_cmd->tag, + se_cmd->scsi_status); + spin_unlock(&se_cmd->t_state_lock); + return false; + } + } if (sess->sess_tearing_down || se_cmd->cmd_wait_set) { pr_debug("Attempted to abort io tag: %llu already shutdown," " skipping\n", se_cmd->tag); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 37abf881ca75..21f888ac550e 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1933,6 +1933,7 @@ void target_execute_cmd(struct se_cmd *cmd) } cmd->t_state = TRANSPORT_PROCESSING; + cmd->transport_state &= ~CMD_T_PRE_EXECUTE; cmd->transport_state |= CMD_T_ACTIVE|CMD_T_BUSY|CMD_T_SENT; spin_unlock_irq(&cmd->t_state_lock); @@ -2572,6 +2573,7 @@ int target_get_sess_cmd(struct se_cmd *se_cmd, bool ack_kref) ret = -ESHUTDOWN; goto out; } + se_cmd->transport_state |= CMD_T_PRE_EXECUTE; list_add_tail(&se_cmd->se_cmd_list, &se_sess->sess_cmd_list); out: spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags); diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index b07f864f68e8..ed27fda13387 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -133,6 +133,12 @@ static void sysrq_handle_crash(int key) { char *killer = NULL; + /* we need to release the RCU read lock here, + * otherwise we get an annoying + * 'BUG: sleeping function called from invalid context' + * complaint from the kernel before the panic. + */ + rcu_read_unlock(); panic_on_oops = 1; /* force panic */ wmb(); *killer = 1; diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index f7481c4e2bc9..d9363713b7f1 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1071,7 +1071,8 @@ int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id, return 1; fail: - + if (dev->eps[0].ring) + xhci_ring_free(xhci, dev->eps[0].ring); if (dev->in_ctx) xhci_free_container_ctx(xhci, dev->in_ctx); if (dev->out_ctx) diff --git a/drivers/usb/misc/usb3503.c b/drivers/usb/misc/usb3503.c index b45cb77c0744..9e8789877763 100644 --- a/drivers/usb/misc/usb3503.c +++ b/drivers/usb/misc/usb3503.c @@ -292,6 +292,8 @@ static int usb3503_probe(struct usb3503 *hub) if (gpio_is_valid(hub->gpio_reset)) { err = devm_gpio_request_one(dev, hub->gpio_reset, GPIOF_OUT_INIT_LOW, "usb3503 reset"); + /* Datasheet defines a hardware reset to be at least 100us */ + usleep_range(100, 10000); if (err) { dev_err(dev, "unable to request GPIO %d as reset pin (%d)\n", diff --git a/drivers/usb/mon/mon_bin.c b/drivers/usb/mon/mon_bin.c index 3598f1a62673..251d123d9046 100644 --- a/drivers/usb/mon/mon_bin.c +++ b/drivers/usb/mon/mon_bin.c @@ -1001,7 +1001,9 @@ static long mon_bin_ioctl(struct file *file, unsigned int cmd, unsigned long arg break; case MON_IOCQ_RING_SIZE: + mutex_lock(&rp->fetch_lock); ret = rp->b_size; + mutex_unlock(&rp->fetch_lock); break; case MON_IOCT_RING_SIZE: @@ -1228,12 +1230,16 @@ static int mon_bin_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf) unsigned long offset, chunk_idx; struct page *pageptr; + mutex_lock(&rp->fetch_lock); offset = vmf->pgoff << PAGE_SHIFT; - if (offset >= rp->b_size) + if (offset >= rp->b_size) { + mutex_unlock(&rp->fetch_lock); return VM_FAULT_SIGBUS; + } chunk_idx = offset / CHUNK_SIZE; pageptr = rp->b_vec[chunk_idx].pg; get_page(pageptr); + mutex_unlock(&rp->fetch_lock); vmf->page = pageptr; return 0; } diff --git a/drivers/usb/musb/ux500.c b/drivers/usb/musb/ux500.c index b2685e75a683..3eaa4ba6867d 100644 --- a/drivers/usb/musb/ux500.c +++ b/drivers/usb/musb/ux500.c @@ -348,7 +348,9 @@ static int ux500_suspend(struct device *dev) struct ux500_glue *glue = dev_get_drvdata(dev); struct musb *musb = glue_to_musb(glue); - usb_phy_set_suspend(musb->xceiv, 1); + if (musb) + usb_phy_set_suspend(musb->xceiv, 1); + clk_disable_unprepare(glue->clk); return 0; @@ -366,7 +368,8 @@ static int ux500_resume(struct device *dev) return ret; } - usb_phy_set_suspend(musb->xceiv, 0); + if (musb) + usb_phy_set_suspend(musb->xceiv, 0); return 0; } diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 1f5ecf905b7d..a4ab4fdf5ba3 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -120,6 +120,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x8470) }, /* Juniper Networks BX Series System Console */ { USB_DEVICE(0x10C4, 0x8477) }, /* Balluff RFID */ { USB_DEVICE(0x10C4, 0x84B6) }, /* Starizona Hyperion */ + { USB_DEVICE(0x10C4, 0x85A7) }, /* LifeScan OneTouch Verio IQ */ { USB_DEVICE(0x10C4, 0x85EA) }, /* AC-Services IBUS-IF */ { USB_DEVICE(0x10C4, 0x85EB) }, /* AC-Services CIS-IBUS */ { USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */ @@ -170,6 +171,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */ { USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */ { USB_DEVICE(0x18EF, 0xE025) }, /* ELV Marble Sound Board 1 */ + { USB_DEVICE(0x18EF, 0xE030) }, /* ELV ALC 8xxx Battery Charger */ { USB_DEVICE(0x18EF, 0xE032) }, /* ELV TFD500 Data Logger */ { USB_DEVICE(0x1901, 0x0190) }, /* GE B850 CP2105 Recorder interface */ { USB_DEVICE(0x1901, 0x0193) }, /* GE B650 CP2104 PMC interface */ diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index 2f80163ffb94..8ed80f28416f 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -155,6 +155,13 @@ UNUSUAL_DEV(0x2109, 0x0711, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NO_ATA_1X), +/* Reported-by: Icenowy Zheng */ +UNUSUAL_DEV(0x2537, 0x1068, 0x0000, 0x9999, + "Norelsys", + "NS1068X", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_IGNORE_UAS), + /* Reported-by: Takeo Nakayama */ UNUSUAL_DEV(0x357d, 0x7788, 0x0000, 0x9999, "JMicron", diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c index e40da7759a0e..9752b93f754e 100644 --- a/drivers/usb/usbip/usbip_common.c +++ b/drivers/usb/usbip/usbip_common.c @@ -103,7 +103,7 @@ static void usbip_dump_usb_device(struct usb_device *udev) dev_dbg(dev, " devnum(%d) devpath(%s) usb speed(%s)", udev->devnum, udev->devpath, usb_speed_string(udev->speed)); - pr_debug("tt %p, ttport %d\n", udev->tt, udev->ttport); + pr_debug("tt hub ttport %d\n", udev->ttport); dev_dbg(dev, " "); for (i = 0; i < 16; i++) @@ -136,12 +136,8 @@ static void usbip_dump_usb_device(struct usb_device *udev) } pr_debug("\n"); - dev_dbg(dev, "parent %p, bus %p\n", udev->parent, udev->bus); - - dev_dbg(dev, - "descriptor %p, config %p, actconfig %p, rawdescriptors %p\n", - &udev->descriptor, udev->config, - udev->actconfig, udev->rawdescriptors); + dev_dbg(dev, "parent %s, bus %s\n", dev_name(&udev->parent->dev), + udev->bus->bus_name); dev_dbg(dev, "have_langid %d, string_langid %d\n", udev->have_langid, udev->string_langid); @@ -249,9 +245,6 @@ void usbip_dump_urb(struct urb *urb) dev = &urb->dev->dev; - dev_dbg(dev, " urb :%p\n", urb); - dev_dbg(dev, " dev :%p\n", urb->dev); - usbip_dump_usb_device(urb->dev); dev_dbg(dev, " pipe :%08x ", urb->pipe); @@ -260,11 +253,9 @@ void usbip_dump_urb(struct urb *urb) dev_dbg(dev, " status :%d\n", urb->status); dev_dbg(dev, " transfer_flags :%08X\n", urb->transfer_flags); - dev_dbg(dev, " transfer_buffer :%p\n", urb->transfer_buffer); dev_dbg(dev, " transfer_buffer_length:%d\n", urb->transfer_buffer_length); dev_dbg(dev, " actual_length :%d\n", urb->actual_length); - dev_dbg(dev, " setup_packet :%p\n", urb->setup_packet); if (urb->setup_packet && usb_pipetype(urb->pipe) == PIPE_CONTROL) usbip_dump_usb_ctrlrequest( @@ -274,8 +265,6 @@ void usbip_dump_urb(struct urb *urb) dev_dbg(dev, " number_of_packets :%d\n", urb->number_of_packets); dev_dbg(dev, " interval :%d\n", urb->interval); dev_dbg(dev, " error_count :%d\n", urb->error_count); - dev_dbg(dev, " context :%p\n", urb->context); - dev_dbg(dev, " complete :%p\n", urb->complete); } EXPORT_SYMBOL_GPL(usbip_dump_urb); diff --git a/fs/locks.c b/fs/locks.c index 8eddae23e10b..b515e65f1376 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2220,10 +2220,12 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, error = do_lock_file_wait(filp, cmd, file_lock); /* - * Attempt to detect a close/fcntl race and recover by - * releasing the lock that was just acquired. + * Attempt to detect a close/fcntl race and recover by releasing the + * lock that was just acquired. There is no need to do that when we're + * unlocking though, or for OFD locks. */ - if (!error && file_lock->fl_type != F_UNLCK) { + if (!error && file_lock->fl_type != F_UNLCK && + !(file_lock->fl_flags & FL_OFDLCK)) { /* * We need that spin_lock here - it prevents reordering between * update of i_flctx->flc_posix and check for it done in @@ -2362,10 +2364,12 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, error = do_lock_file_wait(filp, cmd, file_lock); /* - * Attempt to detect a close/fcntl race and recover by - * releasing the lock that was just acquired. + * Attempt to detect a close/fcntl race and recover by releasing the + * lock that was just acquired. There is no need to do that when we're + * unlocking though, or for OFD locks. */ - if (!error && file_lock->fl_type != F_UNLCK) { + if (!error && file_lock->fl_type != F_UNLCK && + !(file_lock->fl_flags & FL_OFDLCK)) { /* * We need that spin_lock here - it prevents reordering between * update of i_flctx->flc_posix and check for it done in diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4f6d29c8e3d8..f2157159b26f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -37,6 +37,7 @@ struct bpf_map { u32 value_size; u32 max_entries; u32 pages; + bool unpriv_array; struct user_struct *user; const struct bpf_map_ops *ops; struct work_struct work; @@ -141,6 +142,7 @@ struct bpf_prog_aux { struct bpf_array { struct bpf_map map; u32 elem_size; + u32 index_mask; /* 'ownership' of prog_array is claimed by the first program that * is going to use this map or by the first program which FD is stored * in the map to make sure that all callers and callees have the same diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 3ea9aae2387d..7e04bcd9af8e 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -40,6 +40,13 @@ extern void cpu_remove_dev_attr(struct device_attribute *attr); extern int cpu_add_dev_attr_group(struct attribute_group *attrs); extern void cpu_remove_dev_attr_group(struct attribute_group *attrs); +extern ssize_t cpu_show_meltdown(struct device *dev, + struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_spectre_v1(struct device *dev, + struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_spectre_v2(struct device *dev, + struct device_attribute *attr, char *buf); + extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, const struct attribute_group **groups, diff --git a/include/linux/filter.h b/include/linux/filter.h index ccb98b459c59..677fa3b42194 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -466,6 +466,9 @@ u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); void bpf_int_jit_compile(struct bpf_prog *fp); bool bpf_helper_changes_skb_data(void *func); +struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, + const struct bpf_insn *patch, u32 len); + #ifdef CONFIG_BPF_JIT typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); diff --git a/include/linux/phy.h b/include/linux/phy.h index 5bc4b9d563a9..dbfd5ce9350f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -682,6 +682,17 @@ static inline bool phy_is_internal(struct phy_device *phydev) return phydev->is_internal; } +/** + * phy_interface_mode_is_rgmii - Convenience function for testing if a + * PHY interface mode is RGMII (all variants) + * @mode: the phy_interface_t enum + */ +static inline bool phy_interface_mode_is_rgmii(phy_interface_t mode) +{ + return mode >= PHY_INTERFACE_MODE_RGMII && + mode <= PHY_INTERFACE_MODE_RGMII_TXID; +}; + /** * phy_interface_is_rgmii - Convenience function for testing if a PHY interface * is RGMII (all variants) diff --git a/include/linux/sh_eth.h b/include/linux/sh_eth.h index 8c9131db2b25..b050ef51e27e 100644 --- a/include/linux/sh_eth.h +++ b/include/linux/sh_eth.h @@ -16,7 +16,6 @@ struct sh_eth_plat_data { unsigned char mac_addr[ETH_ALEN]; unsigned no_ether_link:1; unsigned ether_link_active_low:1; - unsigned needs_init:1; }; #endif diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index 9982a2bcb880..0eed9fd79ea5 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -496,6 +496,7 @@ struct se_cmd { #define CMD_T_BUSY (1 << 9) #define CMD_T_TAS (1 << 10) #define CMD_T_FABRIC_STOP (1 << 11) +#define CMD_T_PRE_EXECUTE (1 << 12) spinlock_t t_state_lock; struct kref cmd_kref; struct completion t_transport_stop_comp; diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index d6f83222a6a1..67ff6555967f 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -204,7 +204,7 @@ TRACE_EVENT(kvm_ack_irq, { KVM_TRACE_MMIO_WRITE, "write" } TRACE_EVENT(kvm_mmio, - TP_PROTO(int type, int len, u64 gpa, u64 val), + TP_PROTO(int type, int len, u64 gpa, void *val), TP_ARGS(type, len, gpa, val), TP_STRUCT__entry( @@ -218,7 +218,10 @@ TRACE_EVENT(kvm_mmio, __entry->type = type; __entry->len = len; __entry->gpa = gpa; - __entry->val = val; + __entry->val = 0; + if (val) + memcpy(&__entry->val, val, + min_t(u32, sizeof(__entry->val), len)); ), TP_printk("mmio %s len %u gpa 0x%llx val 0x%llx", diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index b0799bced518..3608fa1aec8a 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -20,8 +20,10 @@ /* Called from syscall */ static struct bpf_map *array_map_alloc(union bpf_attr *attr) { + u32 elem_size, array_size, index_mask, max_entries; + bool unpriv = !capable(CAP_SYS_ADMIN); struct bpf_array *array; - u32 elem_size, array_size; + u64 mask64; /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || @@ -36,12 +38,33 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) elem_size = round_up(attr->value_size, 8); + max_entries = attr->max_entries; + + /* On 32 bit archs roundup_pow_of_two() with max_entries that has + * upper most bit set in u32 space is undefined behavior due to + * resulting 1U << 32, so do it manually here in u64 space. + */ + mask64 = fls_long(max_entries - 1); + mask64 = 1ULL << mask64; + mask64 -= 1; + + index_mask = mask64; + if (unpriv) { + /* round up array size to nearest power of 2, + * since cpu will speculate within index_mask limits + */ + max_entries = index_mask + 1; + /* Check for overflows. */ + if (max_entries < attr->max_entries) + return ERR_PTR(-E2BIG); + } + /* check round_up into zero and u32 overflow */ if (elem_size == 0 || - attr->max_entries > (U32_MAX - PAGE_SIZE - sizeof(*array)) / elem_size) + max_entries > (U32_MAX - PAGE_SIZE - sizeof(*array)) / elem_size) return ERR_PTR(-ENOMEM); - array_size = sizeof(*array) + attr->max_entries * elem_size; + array_size = sizeof(*array) + max_entries * elem_size; /* allocate all map elements and zero-initialize them */ array = kzalloc(array_size, GFP_USER | __GFP_NOWARN); @@ -50,6 +73,8 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) if (!array) return ERR_PTR(-ENOMEM); } + array->index_mask = index_mask; + array->map.unpriv_array = unpriv; /* copy mandatory map attributes */ array->map.key_size = attr->key_size; @@ -70,7 +95,7 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key) if (index >= array->map.max_entries) return NULL; - return array->value + array->elem_size * index; + return array->value + array->elem_size * (index & array->index_mask); } /* Called from syscall */ @@ -111,7 +136,9 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, /* all elements already exist */ return -EEXIST; - memcpy(array->value + array->elem_size * index, value, map->value_size); + memcpy(array->value + + array->elem_size * (index & array->index_mask), + value, map->value_size); return 0; } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 334b1bdd572c..3fd76cf0c21e 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -137,6 +137,77 @@ void __bpf_prog_free(struct bpf_prog *fp) } EXPORT_SYMBOL_GPL(__bpf_prog_free); +static bool bpf_is_jmp_and_has_target(const struct bpf_insn *insn) +{ + return BPF_CLASS(insn->code) == BPF_JMP && + /* Call and Exit are both special jumps with no + * target inside the BPF instruction image. + */ + BPF_OP(insn->code) != BPF_CALL && + BPF_OP(insn->code) != BPF_EXIT; +} + +static void bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta) +{ + struct bpf_insn *insn = prog->insnsi; + u32 i, insn_cnt = prog->len; + + for (i = 0; i < insn_cnt; i++, insn++) { + if (!bpf_is_jmp_and_has_target(insn)) + continue; + + /* Adjust offset of jmps if we cross boundaries. */ + if (i < pos && i + insn->off + 1 > pos) + insn->off += delta; + else if (i > pos + delta && i + insn->off + 1 <= pos + delta) + insn->off -= delta; + } +} + +struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, + const struct bpf_insn *patch, u32 len) +{ + u32 insn_adj_cnt, insn_rest, insn_delta = len - 1; + struct bpf_prog *prog_adj; + + /* Since our patchlet doesn't expand the image, we're done. */ + if (insn_delta == 0) { + memcpy(prog->insnsi + off, patch, sizeof(*patch)); + return prog; + } + + insn_adj_cnt = prog->len + insn_delta; + + /* Several new instructions need to be inserted. Make room + * for them. Likely, there's no need for a new allocation as + * last page could have large enough tailroom. + */ + prog_adj = bpf_prog_realloc(prog, bpf_prog_size(insn_adj_cnt), + GFP_USER); + if (!prog_adj) + return NULL; + + prog_adj->len = insn_adj_cnt; + + /* Patching happens in 3 steps: + * + * 1) Move over tail of insnsi from next instruction onwards, + * so we can patch the single target insn with one or more + * new ones (patching is always from 1 to n insns, n > 0). + * 2) Inject new instructions at the target location. + * 3) Adjust branch offsets if necessary. + */ + insn_rest = insn_adj_cnt - off - len; + + memmove(prog_adj->insnsi + off + len, prog_adj->insnsi + off + 1, + sizeof(*patch) * insn_rest); + memcpy(prog_adj->insnsi + off, patch, sizeof(*patch) * len); + + bpf_adj_branches(prog_adj, off, insn_delta); + + return prog_adj; +} + #ifdef CONFIG_BPF_JIT struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4e32cc94edd9..424accd20c2d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -447,57 +447,6 @@ void bpf_register_prog_type(struct bpf_prog_type_list *tl) list_add(&tl->list_node, &bpf_prog_types); } -/* fixup insn->imm field of bpf_call instructions: - * if (insn->imm == BPF_FUNC_map_lookup_elem) - * insn->imm = bpf_map_lookup_elem - __bpf_call_base; - * else if (insn->imm == BPF_FUNC_map_update_elem) - * insn->imm = bpf_map_update_elem - __bpf_call_base; - * else ... - * - * this function is called after eBPF program passed verification - */ -static void fixup_bpf_calls(struct bpf_prog *prog) -{ - const struct bpf_func_proto *fn; - int i; - - for (i = 0; i < prog->len; i++) { - struct bpf_insn *insn = &prog->insnsi[i]; - - if (insn->code == (BPF_JMP | BPF_CALL)) { - /* we reach here when program has bpf_call instructions - * and it passed bpf_check(), means that - * ops->get_func_proto must have been supplied, check it - */ - BUG_ON(!prog->aux->ops->get_func_proto); - - if (insn->imm == BPF_FUNC_get_route_realm) - prog->dst_needed = 1; - if (insn->imm == BPF_FUNC_get_prandom_u32) - bpf_user_rnd_init_once(); - if (insn->imm == BPF_FUNC_tail_call) { - /* mark bpf_tail_call as different opcode - * to avoid conditional branch in - * interpeter for every normal call - * and to prevent accidental JITing by - * JIT compiler that doesn't support - * bpf_tail_call yet - */ - insn->imm = 0; - insn->code |= BPF_X; - continue; - } - - fn = prog->aux->ops->get_func_proto(insn->imm); - /* all functions that have prototype and verifier allowed - * programs to call them, must be real in-kernel functions - */ - BUG_ON(!fn->func); - insn->imm = fn->func - __bpf_call_base; - } - } -} - /* drop refcnt on maps used by eBPF program and free auxilary data */ static void free_used_maps(struct bpf_prog_aux *aux) { @@ -680,9 +629,6 @@ static int bpf_prog_load(union bpf_attr *attr) if (err < 0) goto free_used_maps; - /* fixup BPF_CALL->imm field */ - fixup_bpf_calls(prog); - /* eBPF program is ready to be JITed */ err = bpf_prog_select_runtime(prog); if (err < 0) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index eb759f5008b8..014c2d759916 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -186,6 +186,13 @@ struct verifier_stack_elem { struct verifier_stack_elem *next; }; +struct bpf_insn_aux_data { + union { + enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ + struct bpf_map *map_ptr; /* pointer for call insn into lookup_elem */ + }; +}; + #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ /* single container for all structs @@ -200,6 +207,7 @@ struct verifier_env { struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ u32 used_map_cnt; /* number of used maps */ bool allow_ptr_leaks; + struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ }; /* verbose verifier prints what it's seeing @@ -945,7 +953,7 @@ error: return -EINVAL; } -static int check_call(struct verifier_env *env, int func_id) +static int check_call(struct verifier_env *env, int func_id, int insn_idx) { struct verifier_state *state = &env->cur_state; const struct bpf_func_proto *fn = NULL; @@ -981,6 +989,13 @@ static int check_call(struct verifier_env *env, int func_id) err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &map); if (err) return err; + if (func_id == BPF_FUNC_tail_call) { + if (map == NULL) { + verbose("verifier bug\n"); + return -EINVAL; + } + env->insn_aux_data[insn_idx].map_ptr = map; + } err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &map); if (err) return err; @@ -1784,7 +1799,7 @@ static int do_check(struct verifier_env *env) return err; } else if (class == BPF_LDX) { - enum bpf_reg_type src_reg_type; + enum bpf_reg_type *prev_src_type, src_reg_type; /* check for reserved fields is already done */ @@ -1813,16 +1828,18 @@ static int do_check(struct verifier_env *env) continue; } - if (insn->imm == 0) { + prev_src_type = &env->insn_aux_data[insn_idx].ptr_type; + + if (*prev_src_type == NOT_INIT) { /* saw a valid insn * dst_reg = *(u32 *)(src_reg + off) - * use reserved 'imm' field to mark this insn + * save type to validate intersecting paths */ - insn->imm = src_reg_type; + *prev_src_type = src_reg_type; - } else if (src_reg_type != insn->imm && + } else if (src_reg_type != *prev_src_type && (src_reg_type == PTR_TO_CTX || - insn->imm == PTR_TO_CTX)) { + *prev_src_type == PTR_TO_CTX)) { /* ABuser program is trying to use the same insn * dst_reg = *(u32*) (src_reg + off) * with different pointer types: @@ -1835,7 +1852,7 @@ static int do_check(struct verifier_env *env) } } else if (class == BPF_STX) { - enum bpf_reg_type dst_reg_type; + enum bpf_reg_type *prev_dst_type, dst_reg_type; if (BPF_MODE(insn->code) == BPF_XADD) { err = check_xadd(env, insn); @@ -1863,11 +1880,13 @@ static int do_check(struct verifier_env *env) if (err) return err; - if (insn->imm == 0) { - insn->imm = dst_reg_type; - } else if (dst_reg_type != insn->imm && + prev_dst_type = &env->insn_aux_data[insn_idx].ptr_type; + + if (*prev_dst_type == NOT_INIT) { + *prev_dst_type = dst_reg_type; + } else if (dst_reg_type != *prev_dst_type && (dst_reg_type == PTR_TO_CTX || - insn->imm == PTR_TO_CTX)) { + *prev_dst_type == PTR_TO_CTX)) { verbose("same insn cannot be used with different pointers\n"); return -EINVAL; } @@ -1902,7 +1921,7 @@ static int do_check(struct verifier_env *env) return -EINVAL; } - err = check_call(env, insn->imm); + err = check_call(env, insn->imm, insn_idx); if (err) return err; @@ -2098,24 +2117,39 @@ static void convert_pseudo_ld_imm64(struct verifier_env *env) insn->src_reg = 0; } -static void adjust_branches(struct bpf_prog *prog, int pos, int delta) +/* single env->prog->insni[off] instruction was replaced with the range + * insni[off, off + cnt). Adjust corresponding insn_aux_data by copying + * [0, off) and [off, end) to new locations, so the patched range stays zero + */ +static int adjust_insn_aux_data(struct verifier_env *env, u32 prog_len, + u32 off, u32 cnt) { - struct bpf_insn *insn = prog->insnsi; - int insn_cnt = prog->len; - int i; + struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data; - for (i = 0; i < insn_cnt; i++, insn++) { - if (BPF_CLASS(insn->code) != BPF_JMP || - BPF_OP(insn->code) == BPF_CALL || - BPF_OP(insn->code) == BPF_EXIT) - continue; + if (cnt == 1) + return 0; + new_data = vzalloc(sizeof(struct bpf_insn_aux_data) * prog_len); + if (!new_data) + return -ENOMEM; + memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off); + memcpy(new_data + off + cnt - 1, old_data + off, + sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1)); + env->insn_aux_data = new_data; + vfree(old_data); + return 0; +} - /* adjust offset of jmps if necessary */ - if (i < pos && i + insn->off + 1 > pos) - insn->off += delta; - else if (i > pos + delta && i + insn->off + 1 <= pos + delta) - insn->off -= delta; - } +static struct bpf_prog *bpf_patch_insn_data(struct verifier_env *env, u32 off, + const struct bpf_insn *patch, u32 len) +{ + struct bpf_prog *new_prog; + + new_prog = bpf_patch_insn_single(env->prog, off, patch, len); + if (!new_prog) + return NULL; + if (adjust_insn_aux_data(env, new_prog->len, off, len)) + return NULL; + return new_prog; } /* convert load instructions that access fields of 'struct __sk_buff' @@ -2124,17 +2158,18 @@ static void adjust_branches(struct bpf_prog *prog, int pos, int delta) static int convert_ctx_accesses(struct verifier_env *env) { struct bpf_insn *insn = env->prog->insnsi; - int insn_cnt = env->prog->len; + const int insn_cnt = env->prog->len; struct bpf_insn insn_buf[16]; struct bpf_prog *new_prog; - u32 cnt; - int i; enum bpf_access_type type; + int i, delta = 0; if (!env->prog->aux->ops->convert_ctx_access) return 0; for (i = 0; i < insn_cnt; i++, insn++) { + u32 cnt; + if (insn->code == (BPF_LDX | BPF_MEM | BPF_W)) type = BPF_READ; else if (insn->code == (BPF_STX | BPF_MEM | BPF_W)) @@ -2142,11 +2177,8 @@ static int convert_ctx_accesses(struct verifier_env *env) else continue; - if (insn->imm != PTR_TO_CTX) { - /* clear internal mark */ - insn->imm = 0; + if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX) continue; - } cnt = env->prog->aux->ops-> convert_ctx_access(type, insn->dst_reg, insn->src_reg, @@ -2156,34 +2188,89 @@ static int convert_ctx_accesses(struct verifier_env *env) return -EINVAL; } - if (cnt == 1) { - memcpy(insn, insn_buf, sizeof(*insn)); - continue; - } - - /* several new insns need to be inserted. Make room for them */ - insn_cnt += cnt - 1; - new_prog = bpf_prog_realloc(env->prog, - bpf_prog_size(insn_cnt), - GFP_USER); + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; - new_prog->len = insn_cnt; + delta += cnt - 1; + + /* keep walking new program and skip insns we just inserted */ + env->prog = new_prog; + insn = new_prog->insnsi + i + delta; + } - memmove(new_prog->insnsi + i + cnt, new_prog->insns + i + 1, - sizeof(*insn) * (insn_cnt - i - cnt)); + return 0; +} - /* copy substitute insns in place of load instruction */ - memcpy(new_prog->insnsi + i, insn_buf, sizeof(*insn) * cnt); +/* fixup insn->imm field of bpf_call instructions + * + * this function is called after eBPF program passed verification + */ +static int fixup_bpf_calls(struct verifier_env *env) +{ + struct bpf_prog *prog = env->prog; + struct bpf_insn *insn = prog->insnsi; + const struct bpf_func_proto *fn; + const int insn_cnt = prog->len; + struct bpf_insn insn_buf[16]; + struct bpf_prog *new_prog; + struct bpf_map *map_ptr; + int i, cnt, delta = 0; - /* adjust branches in the whole program */ - adjust_branches(new_prog, i, cnt - 1); + for (i = 0; i < insn_cnt; i++, insn++) { + if (insn->code != (BPF_JMP | BPF_CALL)) + continue; - /* keep walking new program and skip insns we just inserted */ - env->prog = new_prog; - insn = new_prog->insnsi + i + cnt - 1; - i += cnt - 1; + if (insn->imm == BPF_FUNC_get_route_realm) + prog->dst_needed = 1; + if (insn->imm == BPF_FUNC_get_prandom_u32) + bpf_user_rnd_init_once(); + if (insn->imm == BPF_FUNC_tail_call) { + /* mark bpf_tail_call as different opcode to avoid + * conditional branch in the interpeter for every normal + * call and to prevent accidental JITing by JIT compiler + * that doesn't support bpf_tail_call yet + */ + insn->imm = 0; + insn->code |= BPF_X; + + /* instead of changing every JIT dealing with tail_call + * emit two extra insns: + * if (index >= max_entries) goto out; + * index &= array->index_mask; + * to avoid out-of-bounds cpu speculation + */ + map_ptr = env->insn_aux_data[i + delta].map_ptr; + if (!map_ptr->unpriv_array) + continue; + insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3, + map_ptr->max_entries, 2); + insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3, + container_of(map_ptr, + struct bpf_array, + map)->index_mask); + insn_buf[2] = *insn; + cnt = 3; + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + + fn = prog->aux->ops->get_func_proto(insn->imm); + /* all functions that have prototype and verifier allowed + * programs to call them, must be real in-kernel functions + */ + if (!fn->func) { + verbose("kernel subsystem misconfigured func %d\n", + insn->imm); + return -EFAULT; + } + insn->imm = fn->func - __bpf_call_base; } return 0; @@ -2227,6 +2314,11 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (!env) return -ENOMEM; + env->insn_aux_data = vzalloc(sizeof(struct bpf_insn_aux_data) * + (*prog)->len); + ret = -ENOMEM; + if (!env->insn_aux_data) + goto err_free_env; env->prog = *prog; /* grab the mutex to protect few globals used by verifier */ @@ -2245,12 +2337,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) /* log_* values have to be sane */ if (log_size < 128 || log_size > UINT_MAX >> 8 || log_level == 0 || log_ubuf == NULL) - goto free_env; + goto err_unlock; ret = -ENOMEM; log_buf = vmalloc(log_size); if (!log_buf) - goto free_env; + goto err_unlock; } else { log_level = 0; } @@ -2282,6 +2374,9 @@ skip_full_check: /* program is valid, convert *(u32*)(ctx + off) accesses */ ret = convert_ctx_accesses(env); + if (ret == 0) + ret = fixup_bpf_calls(env); + if (log_level && log_len >= log_size - 1) { BUG_ON(log_len >= log_size); /* verifier log exceeded user supplied buffer */ @@ -2319,14 +2414,16 @@ skip_full_check: free_log_buf: if (log_level) vfree(log_buf); -free_env: if (!env->prog->aux->used_maps) /* if we didn't copy map pointers into bpf_prog_info, release * them now. Otherwise free_bpf_prog_info() will release them. */ release_maps(env); *prog = env->prog; - kfree(env); +err_unlock: mutex_unlock(&bpf_verifier_lock); + vfree(env->insn_aux_data); +err_free_env: + kfree(env); return ret; } diff --git a/kernel/futex.c b/kernel/futex.c index 3057dabf726f..fc68462801de 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1939,8 +1939,12 @@ static int unqueue_me(struct futex_q *q) /* In the common case we don't take the spinlock, which is nice. */ retry: - lock_ptr = q->lock_ptr; - barrier(); + /* + * q->lock_ptr can change between this read and the following spin_lock. + * Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and + * optimizing lock_ptr out of the logic below. + */ + lock_ptr = READ_ONCE(q->lock_ptr); if (lock_ptr != NULL) { spin_lock(lock_ptr); /* diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 89350f924c85..79d2d765a75f 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -719,6 +719,7 @@ static inline void __mutex_unlock_common_slowpath(struct mutex *lock, int nested) { unsigned long flags; + WAKE_Q(wake_q); /* * As a performance measurement, release the lock before doing other @@ -746,11 +747,11 @@ __mutex_unlock_common_slowpath(struct mutex *lock, int nested) struct mutex_waiter, list); debug_mutex_wake_waiter(lock, waiter); - - wake_up_process(waiter->task); + wake_q_add(&wake_q, waiter->task); } spin_unlock_mutex(&lock->wait_lock, flags); + wake_up_q(&wake_q); } /* diff --git a/mm/compaction.c b/mm/compaction.c index dba02dec7195..b6f145ed7ae1 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -200,7 +200,8 @@ static void reset_cached_positions(struct zone *zone) { zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn; zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn; - zone->compact_cached_free_pfn = zone_end_pfn(zone); + zone->compact_cached_free_pfn = + round_down(zone_end_pfn(zone) - 1, pageblock_nr_pages); } /* @@ -552,13 +553,17 @@ unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn) { - unsigned long isolated, pfn, block_end_pfn; + unsigned long isolated, pfn, block_start_pfn, block_end_pfn; LIST_HEAD(freelist); pfn = start_pfn; + block_start_pfn = pfn & ~(pageblock_nr_pages - 1); + if (block_start_pfn < cc->zone->zone_start_pfn) + block_start_pfn = cc->zone->zone_start_pfn; block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); for (; pfn < end_pfn; pfn += isolated, + block_start_pfn = block_end_pfn, block_end_pfn += pageblock_nr_pages) { /* Protect pfn from changing by isolate_freepages_block */ unsigned long isolate_start_pfn = pfn; @@ -571,11 +576,13 @@ isolate_freepages_range(struct compact_control *cc, * scanning range to right one. */ if (pfn >= block_end_pfn) { + block_start_pfn = pfn & ~(pageblock_nr_pages - 1); block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); block_end_pfn = min(block_end_pfn, end_pfn); } - if (!pageblock_pfn_to_page(pfn, block_end_pfn, cc->zone)) + if (!pageblock_pfn_to_page(block_start_pfn, + block_end_pfn, cc->zone)) break; isolated = isolate_freepages_block(cc, &isolate_start_pfn, @@ -861,18 +868,23 @@ unsigned long isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn) { - unsigned long pfn, block_end_pfn; + unsigned long pfn, block_start_pfn, block_end_pfn; /* Scan block by block. First and last block may be incomplete */ pfn = start_pfn; + block_start_pfn = pfn & ~(pageblock_nr_pages - 1); + if (block_start_pfn < cc->zone->zone_start_pfn) + block_start_pfn = cc->zone->zone_start_pfn; block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); for (; pfn < end_pfn; pfn = block_end_pfn, + block_start_pfn = block_end_pfn, block_end_pfn += pageblock_nr_pages) { block_end_pfn = min(block_end_pfn, end_pfn); - if (!pageblock_pfn_to_page(pfn, block_end_pfn, cc->zone)) + if (!pageblock_pfn_to_page(block_start_pfn, + block_end_pfn, cc->zone)) continue; pfn = isolate_migratepages_block(cc, pfn, block_end_pfn, @@ -1090,7 +1102,9 @@ int sysctl_compact_unevictable_allowed __read_mostly = 1; static isolate_migrate_t isolate_migratepages(struct zone *zone, struct compact_control *cc) { - unsigned long low_pfn, end_pfn; + unsigned long block_start_pfn; + unsigned long block_end_pfn; + unsigned long low_pfn; unsigned long isolate_start_pfn; struct page *page; const isolate_mode_t isolate_mode = @@ -1102,16 +1116,21 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, * initialized by compact_zone() */ low_pfn = cc->migrate_pfn; + block_start_pfn = cc->migrate_pfn & ~(pageblock_nr_pages - 1); + if (block_start_pfn < zone->zone_start_pfn) + block_start_pfn = zone->zone_start_pfn; /* Only scan within a pageblock boundary */ - end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages); + block_end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages); /* * Iterate over whole pageblocks until we find the first suitable. * Do not cross the free scanner. */ - for (; end_pfn <= cc->free_pfn; - low_pfn = end_pfn, end_pfn += pageblock_nr_pages) { + for (; block_end_pfn <= cc->free_pfn; + low_pfn = block_end_pfn, + block_start_pfn = block_end_pfn, + block_end_pfn += pageblock_nr_pages) { /* * This can potentially iterate a massively long zone with @@ -1122,7 +1141,8 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, && compact_should_abort(cc)) break; - page = pageblock_pfn_to_page(low_pfn, end_pfn, zone); + page = pageblock_pfn_to_page(block_start_pfn, block_end_pfn, + zone); if (!page) continue; @@ -1141,8 +1161,8 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, /* Perform the isolation */ isolate_start_pfn = low_pfn; - low_pfn = isolate_migratepages_block(cc, low_pfn, end_pfn, - isolate_mode); + low_pfn = isolate_migratepages_block(cc, low_pfn, + block_end_pfn, isolate_mode); if (!low_pfn || cc->contended) { acct_isolated(zone, cc); @@ -1358,11 +1378,11 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) */ cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync]; cc->free_pfn = zone->compact_cached_free_pfn; - if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) { - cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1); + if (cc->free_pfn < start_pfn || cc->free_pfn >= end_pfn) { + cc->free_pfn = round_down(end_pfn - 1, pageblock_nr_pages); zone->compact_cached_free_pfn = cc->free_pfn; } - if (cc->migrate_pfn < start_pfn || cc->migrate_pfn > end_pfn) { + if (cc->migrate_pfn < start_pfn || cc->migrate_pfn >= end_pfn) { cc->migrate_pfn = start_pfn; zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn; zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index fd51ebfc423f..6d0dbde4503b 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1162,6 +1162,7 @@ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc, unsigned long balanced_dirty_ratelimit; unsigned long step; unsigned long x; + unsigned long shift; /* * The dirty rate will match the writeout rate in long term, except @@ -1286,11 +1287,11 @@ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc, * rate itself is constantly fluctuating. So decrease the track speed * when it gets close to the target. Helps eliminate pointless tremors. */ - step >>= dirty_ratelimit / (2 * step + 1); - /* - * Limit the tracking speed to avoid overshooting. - */ - step = (step + 7) / 8; + shift = dirty_ratelimit / (2 * step + 1); + if (shift < BITS_PER_LONG) + step = DIV_ROUND_UP(step >> shift, 8); + else + step = 0; if (dirty_ratelimit < balanced_dirty_ratelimit) dirty_ratelimit += step; diff --git a/mm/zswap.c b/mm/zswap.c index 45476f429789..568015e2fe7a 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -123,7 +123,7 @@ struct zswap_pool { struct crypto_comp * __percpu *tfm; struct kref kref; struct list_head list; - struct rcu_head rcu_head; + struct work_struct work; struct notifier_block notifier; char tfm_name[CRYPTO_MAX_ALG_NAME]; }; @@ -667,9 +667,11 @@ static int __must_check zswap_pool_get(struct zswap_pool *pool) return kref_get_unless_zero(&pool->kref); } -static void __zswap_pool_release(struct rcu_head *head) +static void __zswap_pool_release(struct work_struct *work) { - struct zswap_pool *pool = container_of(head, typeof(*pool), rcu_head); + struct zswap_pool *pool = container_of(work, typeof(*pool), work); + + synchronize_rcu(); /* nobody should have been able to get a kref... */ WARN_ON(kref_get_unless_zero(&pool->kref)); @@ -689,7 +691,9 @@ static void __zswap_pool_empty(struct kref *kref) WARN_ON(pool == zswap_pool_current()); list_del_rcu(&pool->list); - call_rcu(&pool->rcu_head, __zswap_pool_release); + + INIT_WORK(&pool->work, __zswap_pool_release); + schedule_work(&pool->work); spin_unlock(&zswap_pools_lock); } @@ -748,18 +752,22 @@ static int __zswap_param_set(const char *val, const struct kernel_param *kp, pool = zswap_pool_find_get(type, compressor); if (pool) { zswap_pool_debug("using existing", pool); + WARN_ON(pool == zswap_pool_current()); list_del_rcu(&pool->list); - } else { - spin_unlock(&zswap_pools_lock); - pool = zswap_pool_create(type, compressor); - spin_lock(&zswap_pools_lock); } + spin_unlock(&zswap_pools_lock); + + if (!pool) + pool = zswap_pool_create(type, compressor); + if (pool) ret = param_set_charp(s, kp); else ret = -EINVAL; + spin_lock(&zswap_pools_lock); + if (!ret) { put_pool = zswap_pool_current(); list_add_rcu(&pool->list, &zswap_pools); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 01abb6431fd9..e2713b0794ae 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -111,12 +111,7 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) vlan_gvrp_uninit_applicant(real_dev); } - /* Take it out of our own structures, but be sure to interlock with - * HW accelerating devices or SW vlan input packet processing if - * VLAN is not 0 (leave it there for 802.1p). - */ - if (vlan_id) - vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id); + vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id); /* Get rid of the vlan's reference to real_dev */ dev_put(real_dev); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 357bcd34cf1f..af68674690af 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -3342,9 +3342,10 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data, size_t data break; case L2CAP_CONF_EFS: - remote_efs = 1; - if (olen == sizeof(efs)) + if (olen == sizeof(efs)) { + remote_efs = 1; memcpy(&efs, (void *) val, olen); + } break; case L2CAP_CONF_EWS: @@ -3563,16 +3564,17 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, break; case L2CAP_CONF_EFS: - if (olen == sizeof(efs)) + if (olen == sizeof(efs)) { memcpy(&efs, (void *)val, olen); - if (chan->local_stype != L2CAP_SERV_NOTRAFIC && - efs.stype != L2CAP_SERV_NOTRAFIC && - efs.stype != chan->local_stype) - return -ECONNREFUSED; + if (chan->local_stype != L2CAP_SERV_NOTRAFIC && + efs.stype != L2CAP_SERV_NOTRAFIC && + efs.stype != chan->local_stype) + return -ECONNREFUSED; - l2cap_add_conf_opt(&ptr, L2CAP_CONF_EFS, sizeof(efs), - (unsigned long) &efs, endptr - ptr); + l2cap_add_conf_opt(&ptr, L2CAP_CONF_EFS, sizeof(efs), + (unsigned long) &efs, endptr - ptr); + } break; case L2CAP_CONF_FCS: diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 0c1d58d43f67..a47f693f9f14 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -289,7 +289,7 @@ static int sock_diag_bind(struct net *net, int group) case SKNLGRP_INET6_UDP_DESTROY: if (!sock_diag_handlers[AF_INET6]) request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, AF_INET); + NETLINK_SOCK_DIAG, AF_INET6); break; } return 0; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 1b4f5f2d2929..b809958f7388 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1785,8 +1785,10 @@ struct sk_buff *ip6_make_skb(struct sock *sk, cork.base.opt = NULL; v6_cork.opt = NULL; err = ip6_setup_cork(sk, &cork, &v6_cork, hlimit, tclass, opt, rt, fl6); - if (err) + if (err) { + ip6_cork_release(&cork, &v6_cork); return ERR_PTR(err); + } if (dontfrag < 0) dontfrag = inet6_sk(sk)->dontfrag; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 97cb02dc5f02..a7170a23ab0b 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1083,10 +1083,11 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); neigh_release(neigh); } - } else if (!(t->parms.flags & - (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) { - /* enable the cache only only if the routing decision does - * not depend on the current inner header value + } else if (t->parms.proto != 0 && !(t->parms.flags & + (IP6_TNL_F_USE_ORIG_TCLASS | + IP6_TNL_F_USE_ORIG_FWMARK))) { + /* enable the cache only if neither the outer protocol nor the + * routing decision depends on the current inner header value */ use_cache = true; } diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 4d2aaebd4f97..e546a987a9d3 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -91,7 +91,7 @@ static const struct file_operations reset_ops = { }; #endif -static const char *hw_flag_names[NUM_IEEE80211_HW_FLAGS + 1] = { +static const char *hw_flag_names[] = { #define FLAG(F) [IEEE80211_HW_##F] = #F FLAG(HAS_RATE_CONTROL), FLAG(RX_INCLUDES_FCS), @@ -125,9 +125,6 @@ static const char *hw_flag_names[NUM_IEEE80211_HW_FLAGS + 1] = { FLAG(TDLS_WIDER_BW), FLAG(SUPPORTS_AMSDU_IN_AMPDU), FLAG(BEACON_TX_STATUS), - - /* keep last for the build bug below */ - (void *)0x1 #undef FLAG }; @@ -147,7 +144,7 @@ static ssize_t hwflags_read(struct file *file, char __user *user_buf, /* fail compilation if somebody adds or removes * a flag without updating the name array above */ - BUILD_BUG_ON(hw_flag_names[NUM_IEEE80211_HW_FLAGS] != (void *)0x1); + BUILD_BUG_ON(ARRAY_SIZE(hw_flag_names) != NUM_IEEE80211_HW_FLAGS); for (i = 0; i < NUM_IEEE80211_HW_FLAGS; i++) { if (test_bit(i, local->hw.flags)) diff --git a/net/rds/rdma.c b/net/rds/rdma.c index bdf151c6307d..bdfc395d1be2 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -517,6 +517,9 @@ int rds_rdma_extra_size(struct rds_rdma_args *args) local_vec = (struct rds_iovec __user *)(unsigned long) args->local_vec_addr; + if (args->nr_local == 0) + return -EINVAL; + /* figure out the number of pages in the vector */ for (i = 0; i < args->nr_local; i++) { if (copy_from_user(&vec, &local_vec[i], @@ -866,6 +869,7 @@ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, err: if (page) put_page(page); + rm->atomic.op_active = 0; kfree(rm->atomic.op_notifier); return ret; diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index 33e72c809e50..494b7b533366 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -465,7 +465,6 @@ static int snd_pcm_hw_param_near(struct snd_pcm_substream *pcm, v = snd_pcm_hw_param_last(pcm, params, var, dir); else v = snd_pcm_hw_param_first(pcm, params, var, dir); - snd_BUG_ON(v < 0); return v; } @@ -1370,8 +1369,11 @@ static ssize_t snd_pcm_oss_write1(struct snd_pcm_substream *substream, const cha if ((tmp = snd_pcm_oss_make_ready(substream)) < 0) return tmp; - mutex_lock(&runtime->oss.params_lock); while (bytes > 0) { + if (mutex_lock_interruptible(&runtime->oss.params_lock)) { + tmp = -ERESTARTSYS; + break; + } if (bytes < runtime->oss.period_bytes || runtime->oss.buffer_used > 0) { tmp = bytes; if (tmp + runtime->oss.buffer_used > runtime->oss.period_bytes) @@ -1415,14 +1417,18 @@ static ssize_t snd_pcm_oss_write1(struct snd_pcm_substream *substream, const cha xfer += tmp; if ((substream->f_flags & O_NONBLOCK) != 0 && tmp != runtime->oss.period_bytes) - break; + tmp = -EAGAIN; } - } - mutex_unlock(&runtime->oss.params_lock); - return xfer; - err: - mutex_unlock(&runtime->oss.params_lock); + mutex_unlock(&runtime->oss.params_lock); + if (tmp < 0) + break; + if (signal_pending(current)) { + tmp = -ERESTARTSYS; + break; + } + tmp = 0; + } return xfer > 0 ? (snd_pcm_sframes_t)xfer : tmp; } @@ -1470,8 +1476,11 @@ static ssize_t snd_pcm_oss_read1(struct snd_pcm_substream *substream, char __use if ((tmp = snd_pcm_oss_make_ready(substream)) < 0) return tmp; - mutex_lock(&runtime->oss.params_lock); while (bytes > 0) { + if (mutex_lock_interruptible(&runtime->oss.params_lock)) { + tmp = -ERESTARTSYS; + break; + } if (bytes < runtime->oss.period_bytes || runtime->oss.buffer_used > 0) { if (runtime->oss.buffer_used == 0) { tmp = snd_pcm_oss_read2(substream, runtime->oss.buffer, runtime->oss.period_bytes, 1); @@ -1502,12 +1511,16 @@ static ssize_t snd_pcm_oss_read1(struct snd_pcm_substream *substream, char __use bytes -= tmp; xfer += tmp; } - } - mutex_unlock(&runtime->oss.params_lock); - return xfer; - err: - mutex_unlock(&runtime->oss.params_lock); + mutex_unlock(&runtime->oss.params_lock); + if (tmp < 0) + break; + if (signal_pending(current)) { + tmp = -ERESTARTSYS; + break; + } + tmp = 0; + } return xfer > 0 ? (snd_pcm_sframes_t)xfer : tmp; } diff --git a/sound/core/oss/pcm_plugin.c b/sound/core/oss/pcm_plugin.c index 727ac44d39f4..a84a1d3d23e5 100644 --- a/sound/core/oss/pcm_plugin.c +++ b/sound/core/oss/pcm_plugin.c @@ -591,18 +591,26 @@ snd_pcm_sframes_t snd_pcm_plug_write_transfer(struct snd_pcm_substream *plug, st snd_pcm_sframes_t frames = size; plugin = snd_pcm_plug_first(plug); - while (plugin && frames > 0) { + while (plugin) { + if (frames <= 0) + return frames; if ((next = plugin->next) != NULL) { snd_pcm_sframes_t frames1 = frames; - if (plugin->dst_frames) + if (plugin->dst_frames) { frames1 = plugin->dst_frames(plugin, frames); + if (frames1 <= 0) + return frames1; + } if ((err = next->client_channels(next, frames1, &dst_channels)) < 0) { return err; } if (err != frames1) { frames = err; - if (plugin->src_frames) + if (plugin->src_frames) { frames = plugin->src_frames(plugin, frames1); + if (frames <= 0) + return frames; + } } } else dst_channels = NULL; diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index cd20f91326fe..7b805766306e 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -1664,7 +1664,7 @@ int snd_pcm_hw_param_first(struct snd_pcm_substream *pcm, return changed; if (params->rmask) { int err = snd_pcm_hw_refine(pcm, params); - if (snd_BUG_ON(err < 0)) + if (err < 0) return err; } return snd_pcm_hw_param_value(params, var, dir); @@ -1711,7 +1711,7 @@ int snd_pcm_hw_param_last(struct snd_pcm_substream *pcm, return changed; if (params->rmask) { int err = snd_pcm_hw_refine(pcm, params); - if (snd_BUG_ON(err < 0)) + if (err < 0) return err; } return snd_pcm_hw_param_value(params, var, dir); diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c index 54f348a4fb78..cbd20cb8ca11 100644 --- a/sound/drivers/aloop.c +++ b/sound/drivers/aloop.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include @@ -305,19 +306,6 @@ static int loopback_trigger(struct snd_pcm_substream *substream, int cmd) return 0; } -static void params_change_substream(struct loopback_pcm *dpcm, - struct snd_pcm_runtime *runtime) -{ - struct snd_pcm_runtime *dst_runtime; - - if (dpcm == NULL || dpcm->substream == NULL) - return; - dst_runtime = dpcm->substream->runtime; - if (dst_runtime == NULL) - return; - dst_runtime->hw = dpcm->cable->hw; -} - static void params_change(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; @@ -329,10 +317,6 @@ static void params_change(struct snd_pcm_substream *substream) cable->hw.rate_max = runtime->rate; cable->hw.channels_min = runtime->channels; cable->hw.channels_max = runtime->channels; - params_change_substream(cable->streams[SNDRV_PCM_STREAM_PLAYBACK], - runtime); - params_change_substream(cable->streams[SNDRV_PCM_STREAM_CAPTURE], - runtime); } static int loopback_prepare(struct snd_pcm_substream *substream) @@ -620,26 +604,29 @@ static unsigned int get_cable_index(struct snd_pcm_substream *substream) static int rule_format(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { + struct loopback_pcm *dpcm = rule->private; + struct loopback_cable *cable = dpcm->cable; + struct snd_mask m; - struct snd_pcm_hardware *hw = rule->private; - struct snd_mask *maskp = hw_param_mask(params, rule->var); - - maskp->bits[0] &= (u_int32_t)hw->formats; - maskp->bits[1] &= (u_int32_t)(hw->formats >> 32); - memset(maskp->bits + 2, 0, (SNDRV_MASK_MAX-64) / 8); /* clear rest */ - if (! maskp->bits[0] && ! maskp->bits[1]) - return -EINVAL; - return 0; + snd_mask_none(&m); + mutex_lock(&dpcm->loopback->cable_lock); + m.bits[0] = (u_int32_t)cable->hw.formats; + m.bits[1] = (u_int32_t)(cable->hw.formats >> 32); + mutex_unlock(&dpcm->loopback->cable_lock); + return snd_mask_refine(hw_param_mask(params, rule->var), &m); } static int rule_rate(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { - struct snd_pcm_hardware *hw = rule->private; + struct loopback_pcm *dpcm = rule->private; + struct loopback_cable *cable = dpcm->cable; struct snd_interval t; - t.min = hw->rate_min; - t.max = hw->rate_max; + mutex_lock(&dpcm->loopback->cable_lock); + t.min = cable->hw.rate_min; + t.max = cable->hw.rate_max; + mutex_unlock(&dpcm->loopback->cable_lock); t.openmin = t.openmax = 0; t.integer = 0; return snd_interval_refine(hw_param_interval(params, rule->var), &t); @@ -648,22 +635,44 @@ static int rule_rate(struct snd_pcm_hw_params *params, static int rule_channels(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { - struct snd_pcm_hardware *hw = rule->private; + struct loopback_pcm *dpcm = rule->private; + struct loopback_cable *cable = dpcm->cable; struct snd_interval t; - t.min = hw->channels_min; - t.max = hw->channels_max; + mutex_lock(&dpcm->loopback->cable_lock); + t.min = cable->hw.channels_min; + t.max = cable->hw.channels_max; + mutex_unlock(&dpcm->loopback->cable_lock); t.openmin = t.openmax = 0; t.integer = 0; return snd_interval_refine(hw_param_interval(params, rule->var), &t); } +static void free_cable(struct snd_pcm_substream *substream) +{ + struct loopback *loopback = substream->private_data; + int dev = get_cable_index(substream); + struct loopback_cable *cable; + + cable = loopback->cables[substream->number][dev]; + if (!cable) + return; + if (cable->streams[!substream->stream]) { + /* other stream is still alive */ + cable->streams[substream->stream] = NULL; + } else { + /* free the cable */ + loopback->cables[substream->number][dev] = NULL; + kfree(cable); + } +} + static int loopback_open(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; struct loopback *loopback = substream->private_data; struct loopback_pcm *dpcm; - struct loopback_cable *cable; + struct loopback_cable *cable = NULL; int err = 0; int dev = get_cable_index(substream); @@ -682,7 +691,6 @@ static int loopback_open(struct snd_pcm_substream *substream) if (!cable) { cable = kzalloc(sizeof(*cable), GFP_KERNEL); if (!cable) { - kfree(dpcm); err = -ENOMEM; goto unlock; } @@ -700,19 +708,19 @@ static int loopback_open(struct snd_pcm_substream *substream) /* are cached -> they do not reflect the actual state */ err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_FORMAT, - rule_format, &runtime->hw, + rule_format, dpcm, SNDRV_PCM_HW_PARAM_FORMAT, -1); if (err < 0) goto unlock; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_RATE, - rule_rate, &runtime->hw, + rule_rate, dpcm, SNDRV_PCM_HW_PARAM_RATE, -1); if (err < 0) goto unlock; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS, - rule_channels, &runtime->hw, + rule_channels, dpcm, SNDRV_PCM_HW_PARAM_CHANNELS, -1); if (err < 0) goto unlock; @@ -724,6 +732,10 @@ static int loopback_open(struct snd_pcm_substream *substream) else runtime->hw = cable->hw; unlock: + if (err < 0) { + free_cable(substream); + kfree(dpcm); + } mutex_unlock(&loopback->cable_lock); return err; } @@ -732,20 +744,10 @@ static int loopback_close(struct snd_pcm_substream *substream) { struct loopback *loopback = substream->private_data; struct loopback_pcm *dpcm = substream->runtime->private_data; - struct loopback_cable *cable; - int dev = get_cable_index(substream); loopback_timer_stop(dpcm); mutex_lock(&loopback->cable_lock); - cable = loopback->cables[substream->number][dev]; - if (cable->streams[!substream->stream]) { - /* other stream is still alive */ - cable->streams[substream->stream] = NULL; - } else { - /* free the cable */ - loopback->cables[substream->number][dev] = NULL; - kfree(cable); - } + free_cable(substream); mutex_unlock(&loopback->cable_lock); return 0; } diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index b5f08e8cab33..e4bb1de1d526 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -1,9 +1,5 @@ # Makefile for vm selftests -ifndef OUTPUT - OUTPUT := $(shell pwd) -endif - CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS) BINARIES = compaction_test BINARIES += hugepage-mmap diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index eabcff411984..92d7eff2827a 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -4,7 +4,8 @@ include ../lib.mk .PHONY: all all_32 all_64 warn_32bit_failure clean -TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs ldt_gdt syscall_nt ptrace_syscall +TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs ldt_gdt syscall_nt ptrace_syscall \ + test_vsyscall TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault sigreturn test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c new file mode 100644 index 000000000000..6e0bd52ad53d --- /dev/null +++ b/tools/testing/selftests/x86/test_vsyscall.c @@ -0,0 +1,500 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#define _GNU_SOURCE + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef __x86_64__ +# define VSYS(x) (x) +#else +# define VSYS(x) 0 +#endif + +#ifndef SYS_getcpu +# ifdef __x86_64__ +# define SYS_getcpu 309 +# else +# define SYS_getcpu 318 +# endif +#endif + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +/* vsyscalls and vDSO */ +bool should_read_vsyscall = false; + +typedef long (*gtod_t)(struct timeval *tv, struct timezone *tz); +gtod_t vgtod = (gtod_t)VSYS(0xffffffffff600000); +gtod_t vdso_gtod; + +typedef int (*vgettime_t)(clockid_t, struct timespec *); +vgettime_t vdso_gettime; + +typedef long (*time_func_t)(time_t *t); +time_func_t vtime = (time_func_t)VSYS(0xffffffffff600400); +time_func_t vdso_time; + +typedef long (*getcpu_t)(unsigned *, unsigned *, void *); +getcpu_t vgetcpu = (getcpu_t)VSYS(0xffffffffff600800); +getcpu_t vdso_getcpu; + +static void init_vdso(void) +{ + void *vdso = dlopen("linux-vdso.so.1", RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); + if (!vdso) + vdso = dlopen("linux-gate.so.1", RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); + if (!vdso) { + printf("[WARN]\tfailed to find vDSO\n"); + return; + } + + vdso_gtod = (gtod_t)dlsym(vdso, "__vdso_gettimeofday"); + if (!vdso_gtod) + printf("[WARN]\tfailed to find gettimeofday in vDSO\n"); + + vdso_gettime = (vgettime_t)dlsym(vdso, "__vdso_clock_gettime"); + if (!vdso_gettime) + printf("[WARN]\tfailed to find clock_gettime in vDSO\n"); + + vdso_time = (time_func_t)dlsym(vdso, "__vdso_time"); + if (!vdso_time) + printf("[WARN]\tfailed to find time in vDSO\n"); + + vdso_getcpu = (getcpu_t)dlsym(vdso, "__vdso_getcpu"); + if (!vdso_getcpu) { + /* getcpu() was never wired up in the 32-bit vDSO. */ + printf("[%s]\tfailed to find getcpu in vDSO\n", + sizeof(long) == 8 ? "WARN" : "NOTE"); + } +} + +static int init_vsys(void) +{ +#ifdef __x86_64__ + int nerrs = 0; + FILE *maps; + char line[128]; + bool found = false; + + maps = fopen("/proc/self/maps", "r"); + if (!maps) { + printf("[WARN]\tCould not open /proc/self/maps -- assuming vsyscall is r-x\n"); + should_read_vsyscall = true; + return 0; + } + + while (fgets(line, sizeof(line), maps)) { + char r, x; + void *start, *end; + char name[128]; + if (sscanf(line, "%p-%p %c-%cp %*x %*x:%*x %*u %s", + &start, &end, &r, &x, name) != 5) + continue; + + if (strcmp(name, "[vsyscall]")) + continue; + + printf("\tvsyscall map: %s", line); + + if (start != (void *)0xffffffffff600000 || + end != (void *)0xffffffffff601000) { + printf("[FAIL]\taddress range is nonsense\n"); + nerrs++; + } + + printf("\tvsyscall permissions are %c-%c\n", r, x); + should_read_vsyscall = (r == 'r'); + if (x != 'x') { + vgtod = NULL; + vtime = NULL; + vgetcpu = NULL; + } + + found = true; + break; + } + + fclose(maps); + + if (!found) { + printf("\tno vsyscall map in /proc/self/maps\n"); + should_read_vsyscall = false; + vgtod = NULL; + vtime = NULL; + vgetcpu = NULL; + } + + return nerrs; +#else + return 0; +#endif +} + +/* syscalls */ +static inline long sys_gtod(struct timeval *tv, struct timezone *tz) +{ + return syscall(SYS_gettimeofday, tv, tz); +} + +static inline int sys_clock_gettime(clockid_t id, struct timespec *ts) +{ + return syscall(SYS_clock_gettime, id, ts); +} + +static inline long sys_time(time_t *t) +{ + return syscall(SYS_time, t); +} + +static inline long sys_getcpu(unsigned * cpu, unsigned * node, + void* cache) +{ + return syscall(SYS_getcpu, cpu, node, cache); +} + +static jmp_buf jmpbuf; + +static void sigsegv(int sig, siginfo_t *info, void *ctx_void) +{ + siglongjmp(jmpbuf, 1); +} + +static double tv_diff(const struct timeval *a, const struct timeval *b) +{ + return (double)(a->tv_sec - b->tv_sec) + + (double)((int)a->tv_usec - (int)b->tv_usec) * 1e-6; +} + +static int check_gtod(const struct timeval *tv_sys1, + const struct timeval *tv_sys2, + const struct timezone *tz_sys, + const char *which, + const struct timeval *tv_other, + const struct timezone *tz_other) +{ + int nerrs = 0; + double d1, d2; + + if (tz_other && (tz_sys->tz_minuteswest != tz_other->tz_minuteswest || tz_sys->tz_dsttime != tz_other->tz_dsttime)) { + printf("[FAIL] %s tz mismatch\n", which); + nerrs++; + } + + d1 = tv_diff(tv_other, tv_sys1); + d2 = tv_diff(tv_sys2, tv_other); + printf("\t%s time offsets: %lf %lf\n", which, d1, d2); + + if (d1 < 0 || d2 < 0) { + printf("[FAIL]\t%s time was inconsistent with the syscall\n", which); + nerrs++; + } else { + printf("[OK]\t%s gettimeofday()'s timeval was okay\n", which); + } + + return nerrs; +} + +static int test_gtod(void) +{ + struct timeval tv_sys1, tv_sys2, tv_vdso, tv_vsys; + struct timezone tz_sys, tz_vdso, tz_vsys; + long ret_vdso = -1; + long ret_vsys = -1; + int nerrs = 0; + + printf("[RUN]\ttest gettimeofday()\n"); + + if (sys_gtod(&tv_sys1, &tz_sys) != 0) + err(1, "syscall gettimeofday"); + if (vdso_gtod) + ret_vdso = vdso_gtod(&tv_vdso, &tz_vdso); + if (vgtod) + ret_vsys = vgtod(&tv_vsys, &tz_vsys); + if (sys_gtod(&tv_sys2, &tz_sys) != 0) + err(1, "syscall gettimeofday"); + + if (vdso_gtod) { + if (ret_vdso == 0) { + nerrs += check_gtod(&tv_sys1, &tv_sys2, &tz_sys, "vDSO", &tv_vdso, &tz_vdso); + } else { + printf("[FAIL]\tvDSO gettimeofday() failed: %ld\n", ret_vdso); + nerrs++; + } + } + + if (vgtod) { + if (ret_vsys == 0) { + nerrs += check_gtod(&tv_sys1, &tv_sys2, &tz_sys, "vsyscall", &tv_vsys, &tz_vsys); + } else { + printf("[FAIL]\tvsys gettimeofday() failed: %ld\n", ret_vsys); + nerrs++; + } + } + + return nerrs; +} + +static int test_time(void) { + int nerrs = 0; + + printf("[RUN]\ttest time()\n"); + long t_sys1, t_sys2, t_vdso = 0, t_vsys = 0; + long t2_sys1 = -1, t2_sys2 = -1, t2_vdso = -1, t2_vsys = -1; + t_sys1 = sys_time(&t2_sys1); + if (vdso_time) + t_vdso = vdso_time(&t2_vdso); + if (vtime) + t_vsys = vtime(&t2_vsys); + t_sys2 = sys_time(&t2_sys2); + if (t_sys1 < 0 || t_sys1 != t2_sys1 || t_sys2 < 0 || t_sys2 != t2_sys2) { + printf("[FAIL]\tsyscall failed (ret1:%ld output1:%ld ret2:%ld output2:%ld)\n", t_sys1, t2_sys1, t_sys2, t2_sys2); + nerrs++; + return nerrs; + } + + if (vdso_time) { + if (t_vdso < 0 || t_vdso != t2_vdso) { + printf("[FAIL]\tvDSO failed (ret:%ld output:%ld)\n", t_vdso, t2_vdso); + nerrs++; + } else if (t_vdso < t_sys1 || t_vdso > t_sys2) { + printf("[FAIL]\tvDSO returned the wrong time (%ld %ld %ld)\n", t_sys1, t_vdso, t_sys2); + nerrs++; + } else { + printf("[OK]\tvDSO time() is okay\n"); + } + } + + if (vtime) { + if (t_vsys < 0 || t_vsys != t2_vsys) { + printf("[FAIL]\tvsyscall failed (ret:%ld output:%ld)\n", t_vsys, t2_vsys); + nerrs++; + } else if (t_vsys < t_sys1 || t_vsys > t_sys2) { + printf("[FAIL]\tvsyscall returned the wrong time (%ld %ld %ld)\n", t_sys1, t_vsys, t_sys2); + nerrs++; + } else { + printf("[OK]\tvsyscall time() is okay\n"); + } + } + + return nerrs; +} + +static int test_getcpu(int cpu) +{ + int nerrs = 0; + long ret_sys, ret_vdso = -1, ret_vsys = -1; + + printf("[RUN]\tgetcpu() on CPU %d\n", cpu); + + cpu_set_t cpuset; + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); + if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) { + printf("[SKIP]\tfailed to force CPU %d\n", cpu); + return nerrs; + } + + unsigned cpu_sys, cpu_vdso, cpu_vsys, node_sys, node_vdso, node_vsys; + unsigned node = 0; + bool have_node = false; + ret_sys = sys_getcpu(&cpu_sys, &node_sys, 0); + if (vdso_getcpu) + ret_vdso = vdso_getcpu(&cpu_vdso, &node_vdso, 0); + if (vgetcpu) + ret_vsys = vgetcpu(&cpu_vsys, &node_vsys, 0); + + if (ret_sys == 0) { + if (cpu_sys != cpu) { + printf("[FAIL]\tsyscall reported CPU %hu but should be %d\n", cpu_sys, cpu); + nerrs++; + } + + have_node = true; + node = node_sys; + } + + if (vdso_getcpu) { + if (ret_vdso) { + printf("[FAIL]\tvDSO getcpu() failed\n"); + nerrs++; + } else { + if (!have_node) { + have_node = true; + node = node_vdso; + } + + if (cpu_vdso != cpu) { + printf("[FAIL]\tvDSO reported CPU %hu but should be %d\n", cpu_vdso, cpu); + nerrs++; + } else { + printf("[OK]\tvDSO reported correct CPU\n"); + } + + if (node_vdso != node) { + printf("[FAIL]\tvDSO reported node %hu but should be %hu\n", node_vdso, node); + nerrs++; + } else { + printf("[OK]\tvDSO reported correct node\n"); + } + } + } + + if (vgetcpu) { + if (ret_vsys) { + printf("[FAIL]\tvsyscall getcpu() failed\n"); + nerrs++; + } else { + if (!have_node) { + have_node = true; + node = node_vsys; + } + + if (cpu_vsys != cpu) { + printf("[FAIL]\tvsyscall reported CPU %hu but should be %d\n", cpu_vsys, cpu); + nerrs++; + } else { + printf("[OK]\tvsyscall reported correct CPU\n"); + } + + if (node_vsys != node) { + printf("[FAIL]\tvsyscall reported node %hu but should be %hu\n", node_vsys, node); + nerrs++; + } else { + printf("[OK]\tvsyscall reported correct node\n"); + } + } + } + + return nerrs; +} + +static int test_vsys_r(void) +{ +#ifdef __x86_64__ + printf("[RUN]\tChecking read access to the vsyscall page\n"); + bool can_read; + if (sigsetjmp(jmpbuf, 1) == 0) { + *(volatile int *)0xffffffffff600000; + can_read = true; + } else { + can_read = false; + } + + if (can_read && !should_read_vsyscall) { + printf("[FAIL]\tWe have read access, but we shouldn't\n"); + return 1; + } else if (!can_read && should_read_vsyscall) { + printf("[FAIL]\tWe don't have read access, but we should\n"); + return 1; + } else { + printf("[OK]\tgot expected result\n"); + } +#endif + + return 0; +} + + +#ifdef __x86_64__ +#define X86_EFLAGS_TF (1UL << 8) +static volatile sig_atomic_t num_vsyscall_traps; + +static unsigned long get_eflags(void) +{ + unsigned long eflags; + asm volatile ("pushfq\n\tpopq %0" : "=rm" (eflags)); + return eflags; +} + +static void set_eflags(unsigned long eflags) +{ + asm volatile ("pushq %0\n\tpopfq" : : "rm" (eflags) : "flags"); +} + +static void sigtrap(int sig, siginfo_t *info, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t *)ctx_void; + unsigned long ip = ctx->uc_mcontext.gregs[REG_RIP]; + + if (((ip ^ 0xffffffffff600000UL) & ~0xfffUL) == 0) + num_vsyscall_traps++; +} + +static int test_native_vsyscall(void) +{ + time_t tmp; + bool is_native; + + if (!vtime) + return 0; + + printf("[RUN]\tchecking for native vsyscall\n"); + sethandler(SIGTRAP, sigtrap, 0); + set_eflags(get_eflags() | X86_EFLAGS_TF); + vtime(&tmp); + set_eflags(get_eflags() & ~X86_EFLAGS_TF); + + /* + * If vsyscalls are emulated, we expect a single trap in the + * vsyscall page -- the call instruction will trap with RIP + * pointing to the entry point before emulation takes over. + * In native mode, we expect two traps, since whatever code + * the vsyscall page contains will be more than just a ret + * instruction. + */ + is_native = (num_vsyscall_traps > 1); + + printf("\tvsyscalls are %s (%d instructions in vsyscall page)\n", + (is_native ? "native" : "emulated"), + (int)num_vsyscall_traps); + + return 0; +} +#endif + +int main(int argc, char **argv) +{ + int nerrs = 0; + + init_vdso(); + nerrs += init_vsys(); + + nerrs += test_gtod(); + nerrs += test_time(); + nerrs += test_getcpu(0); + nerrs += test_getcpu(1); + + sethandler(SIGSEGV, sigsegv, 0); + nerrs += test_vsys_r(); + +#ifdef __x86_64__ + nerrs += test_native_vsyscall(); +#endif + + return nerrs ? 1 : 0; +}