diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 498741737055..dfd56ec7a850 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -350,3 +350,19 @@ Contact: Linux ARM Kernel Mailing list linux-arm-kernel@lists.infradead.org Description: AArch64 CPU registers 'identification' directory exposes the CPU ID registers for identifying model and revision of the CPU. + +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 linux-kernel@vger.kernel.org +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 5d2676d043de..4c2667aa4634 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2691,6 +2691,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. nosmt [KNL,S390] Disable symmetric multithreading (SMT). Equivalent to smt=1.

+ nospectre_v2 [X86] Disable all mitigations for the Spectre variant 2 + (indirect branch prediction) vulnerability. System may + allow data leaks with this option, which is equivalent + to spectre_v2=off. + noxsave [BUGS=X86] Disables x86 extended register state save and restore using xsave. The kernel will fallback to enabling legacy floating-point and sse state. @@ -2763,8 +2768,6 @@ 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 @@ -3327,11 +3330,20 @@ 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 @@ -3937,6 +3949,29 @@ bytes respectively. Such letter suffixes can also be entirely omitted. sonypi.*= [HW] Sony Programmable I/O Control Device driver See Documentation/laptops/sonypi.txt

+ spectre_v2= [X86] Control mitigation of Spectre variant 2 + (indirect branch speculation) vulnerability. + + on - unconditionally enable + off - unconditionally disable + auto - kernel detects whether your CPU model is + vulnerable + + Selecting 'on' will, and 'auto' may, choose a + mitigation method at run time according to the + CPU, the available microcode, the setting of the + CONFIG_RETPOLINE configuration option, and the + compiler with which the kernel was built. + + Specific mitigations can also be selected manually: + + retpoline - replace indirect branches + retpoline,generic - google's original retpoline + retpoline,amd - AMD-specific minimal thunk + + Not specifying this option is equivalent to + spectre_v2=auto. + spia_io_base= [HW,MTD] spia_fio_base= spia_pedr= 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 2637f0ed0a07..aba553531d6a 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 9 -SUBLEVEL = 76 +SUBLEVEL = 77 EXTRAVERSION = NAME = Roaring Lionus

diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index b6e715fd3c90..dac7ceb1a677 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -112,7 +112,7 @@ 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); } @@ -182,14 +182,14 @@ 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); kvm_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 c558bce989cd..6e716a5f1173 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -683,6 +683,18 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value) struct task_struct *t; int max_users;

+ /* 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 11890e6e4093..0c8ae2cc6380 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 da8156fd3d58..0ca4d12ce95c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -64,6 +64,7 @@ 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 @@ -407,6 +408,19 @@ config GOLDFISH def_bool y depends on X86_GOLDFISH

+config RETPOLINE + bool "Avoid speculative indirect branches in kernel" + default y + ---help--- + Compile kernel with the retpoline compiler options to guard against + kernel-to-user data leaks by avoiding speculative indirect + branches. Requires a compiler with -mindirect-branch=thunk-extern + support for full protection. The kernel may run slower. + + Without compiler support, at least indirect branches in assembler + code are eliminated. Since this includes the syscall entry path, + it is not entirely pointless. + if X86_32 config X86_EXTENDED_PLATFORM bool "Support for extended (non-PC) x86 platforms" diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 2d449337a360..cd22cb8ebd42 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -182,6 +182,14 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables KBUILD_CFLAGS += $(mflags-y) KBUILD_AFLAGS += $(mflags-y)

+# Avoid indirect branches in kernel to deal with Spectre +ifdef CONFIG_RETPOLINE + RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register) + ifneq ($(RETPOLINE_CFLAGS),) + KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE + endif +endif + archscripts: scripts_basic $(Q)$(MAKE) $(build)=arch/x86/tools relocs

diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 383a6f84a060..fa8801b35e51 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -32,6 +32,7 @@ #include <linux/linkage.h> #include <asm/inst.h> #include <asm/frame.h> +#include <asm/nospec-branch.h>

/* * The following macros are used to move an (un)aligned 16 byte value to/from @@ -2734,7 +2735,7 @@ ENTRY(aesni_xts_crypt8) pxor INC, STATE4 movdqu IV, 0x30(OUTP)

- call *%r11 + CALL_NOSPEC %r11

movdqu 0x00(OUTP), INC pxor INC, STATE1 @@ -2779,7 +2780,7 @@ ENTRY(aesni_xts_crypt8) _aesni_gf128mul_x_ble() movups IV, (IVP)

- call *%r11 + CALL_NOSPEC %r11

movdqu 0x40(OUTP), INC pxor INC, STATE1 diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S index aa9e8bd163f6..77ff4de2224d 100644 --- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S @@ -17,6 +17,7 @@

#include <linux/linkage.h> #include <asm/frame.h> +#include <asm/nospec-branch.h>

#define CAMELLIA_TABLE_BYTE_LEN 272

@@ -1224,7 +1225,7 @@ camellia_xts_crypt_16way: vpxor 14 * 16(%rax), %xmm15, %xmm14; vpxor 15 * 16(%rax), %xmm15, %xmm15;

- call *%r9; + CALL_NOSPEC %r9;

addq $(16 * 16), %rsp;

diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S index 16186c18656d..7384342fbb41 100644 --- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S @@ -12,6 +12,7 @@

#include <linux/linkage.h> #include <asm/frame.h> +#include <asm/nospec-branch.h>

#define CAMELLIA_TABLE_BYTE_LEN 272

@@ -1337,7 +1338,7 @@ camellia_xts_crypt_32way: vpxor 14 * 32(%rax), %ymm15, %ymm14; vpxor 15 * 32(%rax), %ymm15, %ymm15;

- call *%r9; + CALL_NOSPEC %r9;

addq $(16 * 32), %rsp;

diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S index dc05f010ca9b..174fd4146043 100644 --- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S +++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S @@ -45,6 +45,7 @@

#include <asm/inst.h> #include <linux/linkage.h> +#include <asm/nospec-branch.h>

## ISCSI CRC 32 Implementation with crc32 and pclmulqdq Instruction

@@ -172,7 +173,7 @@ continue_block: movzxw (bufp, %rax, 2), len lea crc_array(%rip), bufp lea (bufp, len, 1), bufp - jmp *bufp + JMP_NOSPEC bufp

################################################################ ## 2a) PROCESS FULL BLOCKS: diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index edba8606b99a..bdc9aeaf2e45 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -45,6 +45,7 @@ #include <asm/asm.h> #include <asm/smap.h> #include <asm/export.h> +#include <asm/nospec-branch.h>

.section .entry.text, "ax"

@@ -260,7 +261,7 @@ ENTRY(ret_from_fork)

/* kernel thread */ 1: movl %edi, %eax - call *%ebx + CALL_NOSPEC %ebx /* * A kernel thread is allowed to return here after successfully * calling do_execve(). Exit to userspace to complete the execve() @@ -984,7 +985,8 @@ trace: movl 0x4(%ebp), %edx subl $MCOUNT_INSN_SIZE, %eax

- call *ftrace_trace_function + movl ftrace_trace_function, %ecx + CALL_NOSPEC %ecx

popl %edx popl %ecx @@ -1020,7 +1022,7 @@ return_to_handler: movl %eax, %ecx popl %edx popl %eax - jmp *%ecx + JMP_NOSPEC %ecx #endif

#ifdef CONFIG_TRACING @@ -1062,7 +1064,7 @@ error_code: movl %ecx, %es TRACE_IRQS_OFF movl %esp, %eax # pt_regs pointer - call *%edi + CALL_NOSPEC %edi jmp ret_from_exception END(page_fault)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index af4e58132d91..b9c901ce6582 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -37,6 +37,7 @@ #include <asm/pgtable_types.h> #include <asm/export.h> #include <asm/kaiser.h> +#include <asm/nospec-branch.h> #include <linux/err.h>

/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ @@ -208,7 +209,12 @@ entry_SYSCALL_64_fastpath: * It might end up jumping to the slow path. If it jumps, RAX * and all argument registers are clobbered. */ +#ifdef CONFIG_RETPOLINE + movq sys_call_table(, %rax, 8), %rax + call __x86_indirect_thunk_rax +#else call *sys_call_table(, %rax, 8) +#endif .Lentry_SYSCALL_64_after_fastpath_call:

movq %rax, RAX(%rsp) @@ -380,7 +386,7 @@ ENTRY(stub_ptregs_64) jmp entry_SYSCALL64_slow_path

1: - jmp *%rax /* Called from C */ + JMP_NOSPEC %rax /* Called from C */ END(stub_ptregs_64)

.macro ptregs_stub func @@ -457,7 +463,7 @@ ENTRY(ret_from_fork) 1: /* kernel thread */ movq %r12, %rdi - call *%rbx + CALL_NOSPEC %rbx /* * A kernel thread is allowed to return here after successfully * calling do_execve(). Exit to userspace to complete the execve() diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index d4aea31eec03..deca9b9c7923 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -139,7 +139,7 @@ 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) \ @@ -150,7 +150,7 @@ 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"

/* * Alternative instructions for different CPU types or capabilities. diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 44b8762fa0c7..b15aa4083dfd 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -10,7 +10,32 @@ #include <asm/pgtable.h> #include <asm/special_insns.h> #include <asm/preempt.h> +#include <asm/asm.h>

#ifndef CONFIG_X86_CMPXCHG64 extern void cmpxchg8b_emu(void); #endif + +#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_X86_32 +#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_e ## reg(void); +#else +#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_r ## reg(void); +INDIRECT_THUNK(8) +INDIRECT_THUNK(9) +INDIRECT_THUNK(10) +INDIRECT_THUNK(11) +INDIRECT_THUNK(12) +INDIRECT_THUNK(13) +INDIRECT_THUNK(14) +INDIRECT_THUNK(15) +#endif +INDIRECT_THUNK(ax) +INDIRECT_THUNK(bx) +INDIRECT_THUNK(cx) +INDIRECT_THUNK(dx) +INDIRECT_THUNK(si) +INDIRECT_THUNK(di) +INDIRECT_THUNK(bp) +INDIRECT_THUNK(sp) +#endif /* CONFIG_RETPOLINE */ diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 7acb51c49fec..00523524edbf 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -125,4 +125,15 @@ /* For C file, we already have NOKPROBE_SYMBOL macro */ #endif

+#ifndef __ASSEMBLY__ +/* + * This output constraint should be used for any inline asm which has a "call" + * instruction. Otherwise the asm may be inserted before the frame pointer + * gets set up by the containing function. If you forget to do this, objtool + * may print a "call without frame pointer save/setup" warning. + */ +register unsigned long current_stack_pointer asm(_ASM_SP); +#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer) +#endif + #endif /* _ASM_X86_ASM_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 1d2b69fc0ceb..9ea67a04ff4f 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -135,6 +135,8 @@ 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) + #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS) /* * Static testing of CPU features. Used the same as boot_cpu_has(). diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 454a37adb823..4467568a531b 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -194,6 +194,9 @@ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */

+#define X86_FEATURE_RETPOLINE ( 7*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* AMD Retpoline mitigation for Spectre variant 2 */ + #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ #define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */ @@ -316,5 +319,8 @@ #define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ #define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ #define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ +#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 */

#endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index b601ddac5719..b11c4c072df8 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -330,6 +330,9 @@ #define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL #define FAM10H_MMIO_CONF_BASE_SHIFT 20 #define MSR_FAM10H_NODE_ID 0xc001100c +#define MSR_F10H_DECFG 0xc0011029 +#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT 1 +#define MSR_F10H_DECFG_LFENCE_SERIALIZE BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT)

/* K8 MSRs */ #define MSR_K8_TOP_MEM1 0xc001001a diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h new file mode 100644 index 000000000000..402a11c803c3 --- /dev/null +++ b/arch/x86/include/asm/nospec-branch.h @@ -0,0 +1,214 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __NOSPEC_BRANCH_H__ +#define __NOSPEC_BRANCH_H__ + +#include <asm/alternative.h> +#include <asm/alternative-asm.h> +#include <asm/cpufeatures.h> + +/* + * Fill the CPU return stack buffer. + * + * Each entry in the RSB, if used for a speculative 'ret', contains an + * infinite 'pause; jmp' loop to capture speculative execution. + * + * This is required in various cases for retpoline and IBRS-based + * mitigations for the Spectre variant 2 vulnerability. Sometimes to + * eliminate potentially bogus entries from the RSB, and sometimes + * purely to ensure that it doesn't get empty, which on some CPUs would + * allow predictions from other (unwanted!) sources to be used. + * + * We define a CPP macro such that it can be used from both .S files and + * inline assembly. It's possible to do a .macro and then include that + * from C via asm(".include <asm/nospec-branch.h>") but let's not go there. + */ + +#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ +#define RSB_FILL_LOOPS 16 /* To avoid underflow */ + +/* + * Google experimented with loop-unrolling and this turned out to be + * the optimal version — two calls, each with their own speculation + * trap should their return address end up getting used, in a loop. + */ +#define __FILL_RETURN_BUFFER(reg, nr, sp) \ + mov $(nr/2), reg; \ +771: \ + call 772f; \ +773: /* speculation trap */ \ + pause; \ + jmp 773b; \ +772: \ + call 774f; \ +775: /* speculation trap */ \ + pause; \ + jmp 775b; \ +774: \ + dec reg; \ + jnz 771b; \ + add $(BITS_PER_LONG/8) * nr, sp; + +#ifdef __ASSEMBLY__ + +/* + * This should be used immediately before a retpoline alternative. It tells + * objtool where the retpolines are so that it can make sense of the control + * flow by just reading the original instruction(s) and ignoring the + * alternatives. + */ +.macro ANNOTATE_NOSPEC_ALTERNATIVE + .Lannotate_@: + .pushsection .discard.nospec + .long .Lannotate_@ - . + .popsection +.endm + +/* + * These are the bare retpoline primitives for indirect jmp and call. + * Do not use these directly; they only exist to make the ALTERNATIVE + * invocation below less ugly. + */ +.macro RETPOLINE_JMP reg:req + call .Ldo_rop_@ +.Lspec_trap_@: + pause + jmp .Lspec_trap_@ +.Ldo_rop_@: + mov \reg, (%_ASM_SP) + ret +.endm + +/* + * This is a wrapper around RETPOLINE_JMP so the called function in reg + * returns to the instruction after the macro. + */ +.macro RETPOLINE_CALL reg:req + jmp .Ldo_call_@ +.Ldo_retpoline_jmp_@: + RETPOLINE_JMP \reg +.Ldo_call_@: + call .Ldo_retpoline_jmp_@ +.endm + +/* + * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple + * indirect jmp/call which may be susceptible to the Spectre variant 2 + * attack. + */ +.macro JMP_NOSPEC reg:req +#ifdef CONFIG_RETPOLINE + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE_2 __stringify(jmp *\reg), \ + __stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE, \ + __stringify(lfence; jmp *\reg), X86_FEATURE_RETPOLINE_AMD +#else + jmp *\reg +#endif +.endm + +.macro CALL_NOSPEC reg:req +#ifdef CONFIG_RETPOLINE + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE_2 __stringify(call *\reg), \ + __stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\ + __stringify(lfence; call *\reg), X86_FEATURE_RETPOLINE_AMD +#else + call *\reg +#endif +.endm + + /* + * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP + * monstrosity above, manually. + */ +.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req +#ifdef CONFIG_RETPOLINE + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE "jmp .Lskip_rsb_@", \ + __stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)) \ + \ftr +.Lskip_rsb_@: +#endif +.endm + +#else /* __ASSEMBLY__ */ + +#define ANNOTATE_NOSPEC_ALTERNATIVE \ + "999:\n\t" \ + ".pushsection .discard.nospec\n\t" \ + ".long 999b - .\n\t" \ + ".popsection\n\t" + +#if defined(CONFIG_X86_64) && defined(RETPOLINE) + +/* + * Since the inline asm uses the %V modifier which is only in newer GCC, + * the 64-bit one is dependent on RETPOLINE not CONFIG_RETPOLINE. + */ +# define CALL_NOSPEC \ + ANNOTATE_NOSPEC_ALTERNATIVE \ + ALTERNATIVE( \ + "call *%[thunk_target]\n", \ + "call __x86_indirect_thunk_%V[thunk_target]\n", \ + X86_FEATURE_RETPOLINE) +# define THUNK_TARGET(addr) [thunk_target] "r" (addr) + +#elif defined(CONFIG_X86_32) && defined(CONFIG_RETPOLINE) +/* + * For i386 we use the original ret-equivalent retpoline, because + * otherwise we'll run out of registers. We don't care about CET + * here, anyway. + */ +# define CALL_NOSPEC ALTERNATIVE("call *%[thunk_target]\n", \ + " jmp 904f;\n" \ + " .align 16\n" \ + "901: call 903f;\n" \ + "902: pause;\n" \ + " jmp 902b;\n" \ + " .align 16\n" \ + "903: addl $4, %%esp;\n" \ + " pushl %[thunk_target];\n" \ + " ret;\n" \ + " .align 16\n" \ + "904: call 901b;\n", \ + X86_FEATURE_RETPOLINE) + +# define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#else /* No retpoline for C / inline asm */ +# define CALL_NOSPEC "call *%[thunk_target]\n" +# define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#endif + +/* The Spectre V2 mitigation variants */ +enum spectre_v2_mitigation { + SPECTRE_V2_NONE, + SPECTRE_V2_RETPOLINE_MINIMAL, + SPECTRE_V2_RETPOLINE_MINIMAL_AMD, + SPECTRE_V2_RETPOLINE_GENERIC, + SPECTRE_V2_RETPOLINE_AMD, + SPECTRE_V2_IBRS, +}; + +/* + * On VMEXIT we must ensure that no RSB predictions learned in the guest + * can be followed in the host, by overwriting the RSB completely. Both + * retpoline and IBRS mitigations for Spectre v2 need this; only on future + * CPUs with IBRS_ATT *might* it be avoided. + */ +static inline void vmexit_fill_RSB(void) +{ +#ifdef CONFIG_RETPOLINE + unsigned long loops = RSB_CLEAR_LOOPS / 2; + + asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE("jmp 910f", + __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)), + X86_FEATURE_RETPOLINE) + "910:" + : "=&r" (loops), ASM_CALL_CONSTRAINT + : "r" (loops) : "memory" ); +#endif +} +#endif /* __ASSEMBLY__ */ +#endif /* __NOSPEC_BRANCH_H__ */ diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index b6d425999f99..1178a51b77f3 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -27,6 +27,17 @@ static inline void paravirt_release_pud(unsigned long pfn) {} */ extern gfp_t __userpte_alloc_gfp;

+#ifdef CONFIG_PAGE_TABLE_ISOLATION +/* + * Instead of one PGD, we acquire two PGDs. Being order-1, it is + * both 8k in size and 8k-aligned. That lets us just flip bit 12 + * in a pointer to swap between the two 4k halves. + */ +#define PGD_ALLOCATION_ORDER 1 +#else +#define PGD_ALLOCATION_ORDER 0 +#endif + /* * Allocate and free page tables. */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 8cb52ee3ade6..e40b19ca486e 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/thread_info.h b/arch/x86/include/asm/thread_info.h index ad6f5eb07a95..bdf9c4c91572 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -152,17 +152,6 @@ struct thread_info { */ #ifndef __ASSEMBLY__

-static inline unsigned long current_stack_pointer(void) -{ - unsigned long sp; -#ifdef CONFIG_X86_64 - asm("mov %%rsp,%0" : "=g" (sp)); -#else - asm("mov %%esp,%0" : "=g" (sp)); -#endif - return sp; -} - /* * Walks up the stack frames to make sure that the specified object is * entirely contained by a single stack frame. diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 8b678af866f7..ccdc23d89b60 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -44,6 +44,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/smap.h> +#include <asm/nospec-branch.h>

#include <xen/interface/xen.h> #include <xen/interface/sched.h> @@ -216,9 +217,9 @@ privcmd_call(unsigned call, __HYPERCALL_5ARG(a1, a2, a3, a4, a5);

stac(); - asm volatile("call *%[call]" + asm volatile(CALL_NOSPEC : __HYPERCALL_5PARAM - : [call] "a" (&hypercall_page[call]) + : [thunk_target] "a" (&hypercall_page[call]) : __HYPERCALL_CLOBBER5); clac();

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 11cc600f4df0..0a1e8a67cc99 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -335,13 +335,12 @@ 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. */ @@ -350,14 +349,6 @@ 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 @@ -366,16 +357,8 @@ 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 @@ -422,6 +405,34 @@ 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) { @@ -466,7 +477,11 @@ 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 5cb272a7a5a3..10d5a3d6affc 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -340,9 +340,12 @@ recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insnbuf) 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 4a8697f7d4ef..33b63670bf09 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -20,13 +20,11 @@ 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/amd.c b/arch/x86/kernel/cpu/amd.c index 2b4cf04239b6..1b89f0c4251e 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -782,8 +782,32 @@ static void init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_K8);

if (cpu_has(c, X86_FEATURE_XMM2)) { - /* MFENCE stops RDTSC speculation */ - set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); + unsigned long long val; + int ret; + + /* + * A serializing LFENCE has less overhead than MFENCE, so + * use it for execution serialization. On families which + * don't have that MSR, LFENCE is already serializing. + * msr_set_bit() uses the safe accessors, too, even if the MSR + * is not present. + */ + msr_set_bit(MSR_F10H_DECFG, + MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT); + + /* + * Verify that the MSR write was successful (could be running + * under a hypervisor) and only then assume that LFENCE is + * serializing. + */ + ret = rdmsrl_safe(MSR_F10H_DECFG, &val); + if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) { + /* A serializing LFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); + } else { + /* MFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); + } }

/* diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 0b6124315441..49d25ddf0e9f 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -9,6 +9,10 @@ */ #include <linux/init.h> #include <linux/utsname.h> +#include <linux/cpu.h> + +#include <asm/nospec-branch.h> +#include <asm/cmdline.h> #include <asm/bugs.h> #include <asm/processor.h> #include <asm/processor-flags.h> @@ -16,23 +20,24 @@ #include <asm/msr.h> #include <asm/paravirt.h> #include <asm/alternative.h> +#include <asm/pgtable.h> +#include <asm/cacheflush.h> + +static void __init spectre_v2_select_mitigation(void);

void __init check_bugs(void) { -#ifdef CONFIG_X86_32 - /* - * Regardless of whether PCID is enumerated, the SDM says - * that it can't be enabled in 32-bit mode. - */ - setup_clear_cpu_cap(X86_FEATURE_PCID); -#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); + } + + /* Select the proper spectre mitigation before patching alternatives */ + spectre_v2_select_mitigation(); + +#ifdef CONFIG_X86_32 /* * Check whether we are able to run this kernel safely on SMP. * @@ -48,4 +53,194 @@ 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 +} + +/* The kernel command line selection */ +enum spectre_v2_mitigation_cmd { + SPECTRE_V2_CMD_NONE, + SPECTRE_V2_CMD_AUTO, + SPECTRE_V2_CMD_FORCE, + SPECTRE_V2_CMD_RETPOLINE, + SPECTRE_V2_CMD_RETPOLINE_GENERIC, + SPECTRE_V2_CMD_RETPOLINE_AMD, +}; + +static const char *spectre_v2_strings[] = { + [SPECTRE_V2_NONE] = "Vulnerable", + [SPECTRE_V2_RETPOLINE_MINIMAL] = "Vulnerable: Minimal generic ASM retpoline", + [SPECTRE_V2_RETPOLINE_MINIMAL_AMD] = "Vulnerable: Minimal AMD ASM retpoline", + [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline", + [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline", +}; + +#undef pr_fmt +#define pr_fmt(fmt) "Spectre V2 mitigation: " fmt + +static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; + +static void __init spec2_print_if_insecure(const char *reason) +{ + if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + pr_info("%s\n", reason); +} + +static void __init spec2_print_if_secure(const char *reason) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + pr_info("%s\n", reason); +} + +static inline bool retp_compiler(void) +{ + return __is_defined(RETPOLINE); +} + +static inline bool match_option(const char *arg, int arglen, const char *opt) +{ + int len = strlen(opt); + + return len == arglen && !strncmp(arg, opt, len); +} + +static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) +{ + char arg[20]; + int ret; + + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, + sizeof(arg)); + if (ret > 0) { + if (match_option(arg, ret, "off")) { + goto disable; + } else if (match_option(arg, ret, "on")) { + spec2_print_if_secure("force enabled on command line."); + return SPECTRE_V2_CMD_FORCE; + } else if (match_option(arg, ret, "retpoline")) { + spec2_print_if_insecure("retpoline selected on command line."); + return SPECTRE_V2_CMD_RETPOLINE; + } else if (match_option(arg, ret, "retpoline,amd")) { + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { + pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); + return SPECTRE_V2_CMD_AUTO; + } + spec2_print_if_insecure("AMD retpoline selected on command line."); + return SPECTRE_V2_CMD_RETPOLINE_AMD; + } else if (match_option(arg, ret, "retpoline,generic")) { + spec2_print_if_insecure("generic retpoline selected on command line."); + return SPECTRE_V2_CMD_RETPOLINE_GENERIC; + } else if (match_option(arg, ret, "auto")) { + return SPECTRE_V2_CMD_AUTO; + } + } + + if (!cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + return SPECTRE_V2_CMD_AUTO; +disable: + spec2_print_if_insecure("disabled on command line."); + return SPECTRE_V2_CMD_NONE; } + +static void __init spectre_v2_select_mitigation(void) +{ + enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); + enum spectre_v2_mitigation mode = SPECTRE_V2_NONE; + + /* + * If the CPU is not affected and the command line mode is NONE or AUTO + * then nothing to do. + */ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) && + (cmd == SPECTRE_V2_CMD_NONE || cmd == SPECTRE_V2_CMD_AUTO)) + return; + + switch (cmd) { + case SPECTRE_V2_CMD_NONE: + return; + + case SPECTRE_V2_CMD_FORCE: + /* FALLTRHU */ + case SPECTRE_V2_CMD_AUTO: + goto retpoline_auto; + + case SPECTRE_V2_CMD_RETPOLINE_AMD: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_amd; + break; + case SPECTRE_V2_CMD_RETPOLINE_GENERIC: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_generic; + break; + case SPECTRE_V2_CMD_RETPOLINE: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_auto; + break; + } + pr_err("kernel not compiled with retpoline; no mitigation available!"); + return; + +retpoline_auto: + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + retpoline_amd: + if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { + pr_err("LFENCE not serializing. Switching to generic retpoline\n"); + goto retpoline_generic; + } + mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD : + SPECTRE_V2_RETPOLINE_MINIMAL_AMD; + setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD); + setup_force_cpu_cap(X86_FEATURE_RETPOLINE); + } else { + retpoline_generic: + mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_GENERIC : + SPECTRE_V2_RETPOLINE_MINIMAL; + setup_force_cpu_cap(X86_FEATURE_RETPOLINE); + } + + spectre_v2_enabled = mode; + pr_info("%s\n", spectre_v2_strings[mode]); +} + +#undef pr_fmt + +#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, "%s\n", spectre_v2_strings[spectre_v2_enabled]); +} +#endif diff --git a/arch/x86/kernel/cpu/bugs_64.c b/arch/x86/kernel/cpu/bugs_64.c deleted file mode 100644 index a972ac4c7e7d..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 <linux/kernel.h> -#include <linux/init.h> -#include <asm/alternative.h> -#include <asm/bugs.h> -#include <asm/processor.h> -#include <asm/mtrr.h> -#include <asm/cacheflush.h> - -void __init check_bugs(void) -{ - identify_boot_cpu(); -#if !defined(CONFIG_SMP) - pr_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 918e44772b04..7b9ae04ddf5d 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -480,8 +480,8 @@ 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) { @@ -706,6 +706,16 @@ 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 eax, ebx, ecx, edx; @@ -872,7 +882,22 @@ 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); + +#ifdef CONFIG_X86_32 + /* + * Regardless of whether PCID is enumerated, the SDM says + * that it can't be enabled in 32-bit mode. + */ + setup_clear_cpu_cap(X86_FEATURE_PCID); +#endif }

void __init early_cpu_init(void) @@ -1086,10 +1111,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) this_cpu->c_identify(c);

/* Clear/Set all flags overridden 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]; - } + apply_forced_caps(c);

#ifdef CONFIG_X86_64 c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); @@ -1151,10 +1173,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) * Clear/Set all flags overridden 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 13dbcc0f9d03..ac3e636ad586 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -1051,8 +1051,17 @@ static bool is_blacklisted(unsigned int cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu);

- if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X) { - pr_err_once("late loading on model 79 is disabled.\n"); + /* + * 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 == INTEL_FAM6_BROADWELL_X && + 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 true; }

diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 1f38d9a4d9de..2763573ee1d2 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -19,6 +19,7 @@ #include <linux/mm.h>

#include <asm/apic.h> +#include <asm/nospec-branch.h>

#ifdef CONFIG_DEBUG_STACKOVERFLOW

@@ -54,17 +55,17 @@ DEFINE_PER_CPU(struct irq_stack *, softirq_stack); static void call_on_stack(void *func, void *stack) { asm volatile("xchgl %%ebx,%%esp \n" - "call *%%edi \n" + CALL_NOSPEC "movl %%ebx,%%esp \n" : "=b" (stack) : "0" (stack), - "D"(func) + [thunk_target] "D"(func) : "memory", "cc", "edx", "ecx", "eax"); }

static inline void *current_stack(void) { - return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1)); + return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1)); }

static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) @@ -88,17 +89,17 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)

/* Save the next esp at the bottom of the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer(); + *prev_esp = current_stack_pointer;

if (unlikely(overflow)) call_on_stack(print_stack_overflow, isp);

asm volatile("xchgl %%ebx,%%esp \n" - "call *%%edi \n" + CALL_NOSPEC "movl %%ebx,%%esp \n" : "=a" (arg1), "=b" (isp) : "0" (desc), "1" (isp), - "D" (desc->handle_irq) + [thunk_target] "D" (desc->handle_irq) : "memory", "cc", "ecx"); return 1; } @@ -139,7 +140,7 @@ void do_softirq_own_stack(void)

/* Push the previous esp onto the stack */ prev_esp = (u32 *)irqstk; - *prev_esp = current_stack_pointer(); + *prev_esp = current_stack_pointer;

call_on_stack(__do_softirq, isp); } diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S index 7b0d3da52fb4..287ec3bc141f 100644 --- a/arch/x86/kernel/mcount_64.S +++ b/arch/x86/kernel/mcount_64.S @@ -8,7 +8,7 @@ #include <asm/ptrace.h> #include <asm/ftrace.h> #include <asm/export.h> - +#include <asm/nospec-branch.h>

.code64 .section .entry.text, "ax" @@ -290,8 +290,9 @@ trace: * ip and parent ip are used and the list function is called when * function tracing is enabled. */ - call *ftrace_trace_function

+ movq ftrace_trace_function, %r8 + CALL_NOSPEC %r8 restore_mcount_regs

jmp fgraph_trace @@ -334,5 +335,5 @@ GLOBAL(return_to_handler) movq 8(%rsp), %rdx movq (%rsp), %rax addq $24, %rsp - jmp *%rdi + JMP_NOSPEC %rdi #endif diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index bd4e3d4d3625..322f433fbc76 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -153,7 +153,7 @@ void ist_begin_non_atomic(struct pt_regs *regs) * from double_fault. */ BUG_ON((unsigned long)(current_top_of_stack() - - current_stack_pointer()) >= THREAD_SIZE); + current_stack_pointer) >= THREAD_SIZE);

preempt_enable_no_resched(); } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 8148d8ca7930..24af898fb3a6 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -44,6 +44,7 @@ #include <asm/debugreg.h> #include <asm/kvm_para.h> #include <asm/irq_remapping.h> +#include <asm/nospec-branch.h>

#include <asm/virtext.h> #include "trace.h" @@ -4868,6 +4869,25 @@ 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 : @@ -4898,6 +4918,9 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) #endif );

+ /* Eliminate branch target predictions from guest mode */ + vmexit_fill_RSB(); + #ifdef CONFIG_X86_64 wrmsrl(MSR_GS_BASE, svm->host.gs_base); #else diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 263e56059fd5..3ca6d15994e4 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -48,6 +48,7 @@ #include <asm/kexec.h> #include <asm/apic.h> #include <asm/irq_remapping.h> +#include <asm/nospec-branch.h>

#include "trace.h" #include "pmu.h" @@ -857,8 +858,16 @@ 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]; @@ -8948,6 +8957,7 @@ 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" @@ -8964,12 +8974,23 @@ 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" @@ -9006,6 +9027,9 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) #endif );

+ /* Eliminate branch target predictions from guest mode */ + vmexit_fill_RSB(); + /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ if (debugctlmsr) update_debugctlmsr(debugctlmsr); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 73304b1a03cc..d3f80cccb9aa 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4264,7 +4264,7 @@ 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; @@ -4517,7 +4517,7 @@ 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; } @@ -4539,14 +4539,14 @@ 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/lib/Makefile b/arch/x86/lib/Makefile index 34a74131a12c..6bf1898ddf49 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -25,6 +25,7 @@ lib-y += memcpy_$(BITS).o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o +lib-$(CONFIG_RETPOLINE) += retpoline.o

obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o

diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S index 4d34bb548b41..46e71a74e612 100644 --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -29,7 +29,8 @@ #include <asm/errno.h> #include <asm/asm.h> #include <asm/export.h> - +#include <asm/nospec-branch.h> + /* * computes a partial checksum, e.g. for TCP/UDP fragments */ @@ -156,7 +157,7 @@ ENTRY(csum_partial) negl %ebx lea 45f(%ebx,%ebx,2), %ebx testl %esi, %esi - jmp *%ebx + JMP_NOSPEC %ebx

# Handle 2-byte-aligned regions 20: addw (%esi), %ax @@ -439,7 +440,7 @@ ENTRY(csum_partial_copy_generic) andl $-32,%edx lea 3f(%ebx,%ebx), %ebx testl %esi, %esi - jmp *%ebx + JMP_NOSPEC %ebx 1: addl $64,%esi addl $64,%edi SRC(movb -32(%edx),%bl) ; SRC(movb (%edx),%bl) diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S new file mode 100644 index 000000000000..cb45c6cb465f --- /dev/null +++ b/arch/x86/lib/retpoline.S @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <linux/stringify.h> +#include <linux/linkage.h> +#include <asm/dwarf2.h> +#include <asm/cpufeatures.h> +#include <asm/alternative-asm.h> +#include <asm/export.h> +#include <asm/nospec-branch.h> + +.macro THUNK reg + .section .text.__x86.indirect_thunk.\reg + +ENTRY(__x86_indirect_thunk_\reg) + CFI_STARTPROC + JMP_NOSPEC %\reg + CFI_ENDPROC +ENDPROC(__x86_indirect_thunk_\reg) +.endm + +/* + * Despite being an assembler file we can't just use .irp here + * because __KSYM_DEPS__ only uses the C preprocessor and would + * only see one instance of "__x86_indirect_thunk_\reg" rather + * than one per register with the correct names. So we do it + * the simple and nasty way... + */ +#define EXPORT_THUNK(reg) EXPORT_SYMBOL(__x86_indirect_thunk_ ## reg) +#define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg) + +GENERATE_THUNK(_ASM_AX) +GENERATE_THUNK(_ASM_BX) +GENERATE_THUNK(_ASM_CX) +GENERATE_THUNK(_ASM_DX) +GENERATE_THUNK(_ASM_SI) +GENERATE_THUNK(_ASM_DI) +GENERATE_THUNK(_ASM_BP) +GENERATE_THUNK(_ASM_SP) +#ifdef CONFIG_64BIT +GENERATE_THUNK(r8) +GENERATE_THUNK(r9) +GENERATE_THUNK(r10) +GENERATE_THUNK(r11) +GENERATE_THUNK(r12) +GENERATE_THUNK(r13) +GENERATE_THUNK(r14) +GENERATE_THUNK(r15) +#endif diff --git a/arch/x86/mm/kaiser.c b/arch/x86/mm/kaiser.c index 8f8e5e03d083..a8ade08a9bf5 100644 --- a/arch/x86/mm/kaiser.c +++ b/arch/x86/mm/kaiser.c @@ -197,6 +197,8 @@ 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/pgtable.c b/arch/x86/mm/pgtable.c index 5aaec8effc5f..209b9465e97a 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -345,13 +345,6 @@ static inline void _pgd_free(pgd_t *pgd) } #else

-/* - * Instead of one pgd, Kaiser acquires two pgds. Being order-1, it is - * both 8k in size and 8k-aligned. That lets us just flip bit 12 - * in a pointer to swap between the two 4k halves. - */ -#define PGD_ALLOCATION_ORDER kaiser_enabled - static inline pgd_t *_pgd_alloc(void) { return (pgd_t *)__get_free_pages(PGALLOC_GFP, PGD_ALLOCATION_ORDER); diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 41205de487e7..578973ade71b 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -110,7 +110,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * mapped in the new pgd, we'll double-fault. Forcibly * map it. */ - unsigned int stack_pgd_index = pgd_index(current_stack_pointer()); + unsigned int stack_pgd_index = pgd_index(current_stack_pointer);

pgd_t *pgd = next->pgd + stack_pgd_index;

diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 2f25a363068c..dcb2d9d185a2 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -142,7 +142,7 @@ int __init efi_alloc_page_tables(void) return 0;

gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO; - efi_pgd = (pgd_t *)__get_free_page(gfp_mask); + efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER); if (!efi_pgd) return -ENOMEM;

diff --git a/crypto/algapi.c b/crypto/algapi.c index 1fad2a6b3bbb..5c098ffa7d3d 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -167,6 +167,18 @@ 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 d02e7c0f5bfd..0651010bba21 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -235,6 +235,9 @@ 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 4c28e1a09786..56b6c8508a89 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -499,10 +499,58 @@ 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 24f4b544d270..e32badd26c8a 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4511,7 +4511,7 @@ 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/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index fefb9d995d2c..81f5a552e32f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -2729,6 +2729,8 @@ 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/hv/hv.c b/drivers/hv/hv.c index e0a8216ecf2b..13c32eb40738 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -31,6 +31,7 @@ #include <linux/clockchips.h> #include <asm/hyperv.h> #include <asm/mshyperv.h> +#include <asm/nospec-branch.h> #include "hyperv_vmbus.h"

/* The one and only */ @@ -103,9 +104,10 @@ u64 hv_do_hypercall(u64 control, void *input, void *output) return (u64)ULLONG_MAX;

__asm__ __volatile__("mov %0, %%r8" : : "r" (output_address) : "r8"); - __asm__ __volatile__("call *%3" : "=a" (hv_status) : + __asm__ __volatile__(CALL_NOSPEC : + "=a" (hv_status) : "c" (control), "d" (input_address), - "m" (hypercall_page)); + THUNK_TARGET(hypercall_page));

return hv_status;

@@ -123,11 +125,12 @@ u64 hv_do_hypercall(u64 control, void *input, void *output) if (!hypercall_page) return (u64)ULLONG_MAX;

- __asm__ __volatile__ ("call *%8" : "=d"(hv_status_hi), + __asm__ __volatile__ (CALL_NOSPEC : "=d"(hv_status_hi), "=a"(hv_status_lo) : "d" (control_hi), "a" (control_lo), "b" (input_address_hi), "c" (input_address_lo), "D"(output_address_hi), - "S"(output_address_lo), "m" (hypercall_page)); + "S"(output_address_lo), + THUNK_TARGET(hypercall_page));

return hv_status_lo | ((u64)hv_status_hi << 32); #endif /* !x86_64 */ diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index b9748970df4a..29ab814693fc 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -992,8 +992,7 @@ 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/md/dm-bufio.c b/drivers/md/dm-bufio.c index 7643f72adb1c..3ec647e8b9c6 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1554,7 +1554,8 @@ 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++) { @@ -1591,6 +1592,7 @@ 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) @@ -1599,8 +1601,9 @@ 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/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index eea9aea14b00..5d5012337d9e 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -449,7 +449,7 @@ 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 f3aaca743ea3..8a48656a376b 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1364,6 +1364,9 @@ static s32 e1000_disable_ulp_lpt_lp(struct e1000_hw *hw, bool force) * 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) { @@ -1379,7 +1382,7 @@ 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 @@ -1611,10 +1614,12 @@ 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/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 9e31a3390154..8aa91ddff287 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1328,9 +1328,9 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, static void __mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp_nexthop *nh, bool removing) { - if (!removing && !nh->should_offload) + if (!removing) nh->should_offload = 1; - else if (removing && nh->offloaded) + else nh->should_offload = 0; nh->update = 1; } diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 2140dedab712..b6816ae00b7a 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -3087,18 +3087,37 @@ 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 adf61a7b1b01..98bbb91336e4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -280,8 +280,14 @@ static void stmmac_eee_ctrl_timer(unsigned long arg) bool stmmac_eee_init(struct stmmac_priv *priv) { 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 f33460cec79f..9c257ffedb15 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -2419,14 +2419,9 @@ 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/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 9af9799935db..4cb9b11a545a 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -2205,13 +2205,9 @@ 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/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c index 0b4c1562420f..ba1fe61e6ea6 100644 --- a/drivers/net/wireless/ath/ath10k/htt_rx.c +++ b/drivers/net/wireless/ath/ath10k/htt_rx.c @@ -548,6 +548,11 @@ static int ath10k_htt_rx_crypto_param_len(struct ath10k *ar, return IEEE80211_TKIP_IV_LEN; case HTT_RX_MPDU_ENCRYPT_AES_CCM_WPA2: return IEEE80211_CCMP_HDR_LEN; + case HTT_RX_MPDU_ENCRYPT_AES_CCM256_WPA2: + return IEEE80211_CCMP_256_HDR_LEN; + case HTT_RX_MPDU_ENCRYPT_AES_GCMP_WPA2: + case HTT_RX_MPDU_ENCRYPT_AES_GCMP256_WPA2: + return IEEE80211_GCMP_HDR_LEN; case HTT_RX_MPDU_ENCRYPT_WEP128: case HTT_RX_MPDU_ENCRYPT_WAPI: break; @@ -573,6 +578,11 @@ static int ath10k_htt_rx_crypto_tail_len(struct ath10k *ar, return IEEE80211_TKIP_ICV_LEN; case HTT_RX_MPDU_ENCRYPT_AES_CCM_WPA2: return IEEE80211_CCMP_MIC_LEN; + case HTT_RX_MPDU_ENCRYPT_AES_CCM256_WPA2: + return IEEE80211_CCMP_256_MIC_LEN; + case HTT_RX_MPDU_ENCRYPT_AES_GCMP_WPA2: + case HTT_RX_MPDU_ENCRYPT_AES_GCMP256_WPA2: + return IEEE80211_GCMP_MIC_LEN; case HTT_RX_MPDU_ENCRYPT_WEP128: case HTT_RX_MPDU_ENCRYPT_WAPI: break; @@ -1024,9 +1034,21 @@ static void ath10k_htt_rx_h_undecap_raw(struct ath10k *ar, hdr = (void *)msdu->data;

/* Tail */ - if (status->flag & RX_FLAG_IV_STRIPPED) + if (status->flag & RX_FLAG_IV_STRIPPED) { skb_trim(msdu, msdu->len - ath10k_htt_rx_crypto_tail_len(ar, enctype)); + } else { + /* MIC */ + if ((status->flag & RX_FLAG_MIC_STRIPPED) && + enctype == HTT_RX_MPDU_ENCRYPT_AES_CCM_WPA2) + skb_trim(msdu, msdu->len - 8); + + /* ICV */ + if (status->flag & RX_FLAG_ICV_STRIPPED && + enctype != HTT_RX_MPDU_ENCRYPT_AES_CCM_WPA2) + skb_trim(msdu, msdu->len - + ath10k_htt_rx_crypto_tail_len(ar, enctype)); + }

/* MMIC */ if ((status->flag & RX_FLAG_MMIC_STRIPPED) && @@ -1048,7 +1070,8 @@ static void ath10k_htt_rx_h_undecap_raw(struct ath10k *ar, static void ath10k_htt_rx_h_undecap_nwifi(struct ath10k *ar, struct sk_buff *msdu, struct ieee80211_rx_status *status, - const u8 first_hdr[64]) + const u8 first_hdr[64], + enum htt_rx_mpdu_encrypt_type enctype) { struct ieee80211_hdr *hdr; struct htt_rx_desc *rxd; @@ -1056,6 +1079,7 @@ static void ath10k_htt_rx_h_undecap_nwifi(struct ath10k *ar, u8 da[ETH_ALEN]; u8 sa[ETH_ALEN]; int l3_pad_bytes; + int bytes_aligned = ar->hw_params.decap_align_bytes;

/* Delivered decapped frame: * [nwifi 802.11 header] <-- replaced with 802.11 hdr @@ -1084,6 +1108,14 @@ static void ath10k_htt_rx_h_undecap_nwifi(struct ath10k *ar, /* push original 802.11 header */ hdr = (struct ieee80211_hdr *)first_hdr; hdr_len = ieee80211_hdrlen(hdr->frame_control); + + if (!(status->flag & RX_FLAG_IV_STRIPPED)) { + memcpy(skb_push(msdu, + ath10k_htt_rx_crypto_param_len(ar, enctype)), + (void *)hdr + round_up(hdr_len, bytes_aligned), + ath10k_htt_rx_crypto_param_len(ar, enctype)); + } + memcpy(skb_push(msdu, hdr_len), hdr, hdr_len);

/* original 802.11 header has a different DA and in @@ -1144,6 +1176,7 @@ static void ath10k_htt_rx_h_undecap_eth(struct ath10k *ar, u8 sa[ETH_ALEN]; int l3_pad_bytes; struct htt_rx_desc *rxd; + int bytes_aligned = ar->hw_params.decap_align_bytes;

/* Delivered decapped frame: * [eth header] <-- replaced with 802.11 hdr & rfc1042/llc @@ -1172,6 +1205,14 @@ static void ath10k_htt_rx_h_undecap_eth(struct ath10k *ar, /* push original 802.11 header */ hdr = (struct ieee80211_hdr *)first_hdr; hdr_len = ieee80211_hdrlen(hdr->frame_control); + + if (!(status->flag & RX_FLAG_IV_STRIPPED)) { + memcpy(skb_push(msdu, + ath10k_htt_rx_crypto_param_len(ar, enctype)), + (void *)hdr + round_up(hdr_len, bytes_aligned), + ath10k_htt_rx_crypto_param_len(ar, enctype)); + } + memcpy(skb_push(msdu, hdr_len), hdr, hdr_len);

/* original 802.11 header has a different DA and in @@ -1185,12 +1226,14 @@ static void ath10k_htt_rx_h_undecap_eth(struct ath10k *ar, static void ath10k_htt_rx_h_undecap_snap(struct ath10k *ar, struct sk_buff *msdu, struct ieee80211_rx_status *status, - const u8 first_hdr[64]) + const u8 first_hdr[64], + enum htt_rx_mpdu_encrypt_type enctype) { struct ieee80211_hdr *hdr; size_t hdr_len; int l3_pad_bytes; struct htt_rx_desc *rxd; + int bytes_aligned = ar->hw_params.decap_align_bytes;

/* Delivered decapped frame: * [amsdu header] <-- replaced with 802.11 hdr @@ -1206,6 +1249,14 @@ static void ath10k_htt_rx_h_undecap_snap(struct ath10k *ar,

hdr = (struct ieee80211_hdr *)first_hdr; hdr_len = ieee80211_hdrlen(hdr->frame_control); + + if (!(status->flag & RX_FLAG_IV_STRIPPED)) { + memcpy(skb_push(msdu, + ath10k_htt_rx_crypto_param_len(ar, enctype)), + (void *)hdr + round_up(hdr_len, bytes_aligned), + ath10k_htt_rx_crypto_param_len(ar, enctype)); + } + memcpy(skb_push(msdu, hdr_len), hdr, hdr_len); }

@@ -1240,13 +1291,15 @@ static void ath10k_htt_rx_h_undecap(struct ath10k *ar, is_decrypted); break; case RX_MSDU_DECAP_NATIVE_WIFI: - ath10k_htt_rx_h_undecap_nwifi(ar, msdu, status, first_hdr); + ath10k_htt_rx_h_undecap_nwifi(ar, msdu, status, first_hdr, + enctype); break; case RX_MSDU_DECAP_ETHERNET2_DIX: ath10k_htt_rx_h_undecap_eth(ar, msdu, status, first_hdr, enctype); break; case RX_MSDU_DECAP_8023_SNAP_LLC: - ath10k_htt_rx_h_undecap_snap(ar, msdu, status, first_hdr); + ath10k_htt_rx_h_undecap_snap(ar, msdu, status, first_hdr, + enctype); break; } } @@ -1289,7 +1342,8 @@ static void ath10k_htt_rx_h_csum_offload(struct sk_buff *msdu)

static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, struct sk_buff_head *amsdu, - struct ieee80211_rx_status *status) + struct ieee80211_rx_status *status, + bool fill_crypt_header) { struct sk_buff *first; struct sk_buff *last; @@ -1299,7 +1353,6 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, enum htt_rx_mpdu_encrypt_type enctype; u8 first_hdr[64]; u8 *qos; - size_t hdr_len; bool has_fcs_err; bool has_crypto_err; bool has_tkip_err; @@ -1324,15 +1377,17 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, * decapped header. It'll be used for undecapping of each MSDU. */ hdr = (void *)rxd->rx_hdr_status; - hdr_len = ieee80211_hdrlen(hdr->frame_control); - memcpy(first_hdr, hdr, hdr_len); + memcpy(first_hdr, hdr, RX_HTT_HDR_STATUS_LEN);

/* Each A-MSDU subframe will use the original header as the base and be * reported as a separate MSDU so strip the A-MSDU bit from QoS Ctl. */ hdr = (void *)first_hdr; - qos = ieee80211_get_qos_ctl(hdr); - qos[0] &= ~IEEE80211_QOS_CTL_A_MSDU_PRESENT; + + if (ieee80211_is_data_qos(hdr->frame_control)) { + qos = ieee80211_get_qos_ctl(hdr); + qos[0] &= ~IEEE80211_QOS_CTL_A_MSDU_PRESENT; + }

/* Some attention flags are valid only in the last MSDU. */ last = skb_peek_tail(amsdu); @@ -1379,9 +1434,14 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, status->flag |= RX_FLAG_DECRYPTED;

if (likely(!is_mgmt)) - status->flag |= RX_FLAG_IV_STRIPPED | - RX_FLAG_MMIC_STRIPPED; -} + status->flag |= RX_FLAG_MMIC_STRIPPED; + + if (fill_crypt_header) + status->flag |= RX_FLAG_MIC_STRIPPED | + RX_FLAG_ICV_STRIPPED; + else + status->flag |= RX_FLAG_IV_STRIPPED; + }

skb_queue_walk(amsdu, msdu) { ath10k_htt_rx_h_csum_offload(msdu); @@ -1397,6 +1457,9 @@ static void ath10k_htt_rx_h_mpdu(struct ath10k *ar, if (is_mgmt) continue;

+ if (fill_crypt_header) + continue; + hdr = (void *)msdu->data; hdr->frame_control &= ~__cpu_to_le16(IEEE80211_FCTL_PROTECTED); } @@ -1407,6 +1470,9 @@ static void ath10k_htt_rx_h_deliver(struct ath10k *ar, struct ieee80211_rx_status *status) { struct sk_buff *msdu; + struct sk_buff *first_subframe; + + first_subframe = skb_peek(amsdu);

while ((msdu = __skb_dequeue(amsdu))) { /* Setup per-MSDU flags */ @@ -1415,6 +1481,13 @@ static void ath10k_htt_rx_h_deliver(struct ath10k *ar, else status->flag |= RX_FLAG_AMSDU_MORE;

+ if (msdu == first_subframe) { + first_subframe = NULL; + status->flag &= ~RX_FLAG_ALLOW_SAME_PN; + } else { + status->flag |= RX_FLAG_ALLOW_SAME_PN; + } + ath10k_process_rx(ar, status, msdu); } } @@ -1557,7 +1630,7 @@ static int ath10k_htt_rx_handle_amsdu(struct ath10k_htt *htt) ath10k_htt_rx_h_ppdu(ar, &amsdu, rx_status, 0xffff); ath10k_htt_rx_h_unchain(ar, &amsdu, ret > 0); ath10k_htt_rx_h_filter(ar, &amsdu, rx_status); - ath10k_htt_rx_h_mpdu(ar, &amsdu, rx_status); + ath10k_htt_rx_h_mpdu(ar, &amsdu, rx_status, true); ath10k_htt_rx_h_deliver(ar, &amsdu, rx_status);

return num_msdus; @@ -1892,7 +1965,7 @@ static int ath10k_htt_rx_in_ord_ind(struct ath10k *ar, struct sk_buff *skb) num_msdus += skb_queue_len(&amsdu); ath10k_htt_rx_h_ppdu(ar, &amsdu, status, vdev_id); ath10k_htt_rx_h_filter(ar, &amsdu, status); - ath10k_htt_rx_h_mpdu(ar, &amsdu, status); + ath10k_htt_rx_h_mpdu(ar, &amsdu, status, false); ath10k_htt_rx_h_deliver(ar, &amsdu, status); break; case -EAGAIN: diff --git a/drivers/net/wireless/ath/ath10k/rx_desc.h b/drivers/net/wireless/ath/ath10k/rx_desc.h index 034e7a54c5b2..e4878d0044bf 100644 --- a/drivers/net/wireless/ath/ath10k/rx_desc.h +++ b/drivers/net/wireless/ath/ath10k/rx_desc.h @@ -239,6 +239,9 @@ enum htt_rx_mpdu_encrypt_type { HTT_RX_MPDU_ENCRYPT_WAPI = 5, HTT_RX_MPDU_ENCRYPT_AES_CCM_WPA2 = 6, HTT_RX_MPDU_ENCRYPT_NONE = 7, + HTT_RX_MPDU_ENCRYPT_AES_CCM256_WPA2 = 8, + HTT_RX_MPDU_ENCRYPT_AES_GCMP_WPA2 = 9, + HTT_RX_MPDU_ENCRYPT_AES_GCMP256_WPA2 = 10, };

#define RX_MPDU_START_INFO0_PEER_IDX_MASK 0x000007ff diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index ceeb8c188ef3..00d82e8443bd 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -848,5 +848,5 @@ static void __exit acpi_wmi_exit(void) pr_info("Mapper unloaded\n"); }

-subsys_initcall(acpi_wmi_init); +subsys_initcall_sync(acpi_wmi_init); module_exit(acpi_wmi_exit); diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index 2b770cb0c488..558a66b459fa 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -774,10 +774,12 @@ 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 72e926d9868f..04d2b6e25503 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1940,7 +1940,6 @@ 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; @@ -1982,18 +1981,17 @@ 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; @@ -2132,12 +2130,8 @@ iscsit_handle_task_mgt_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, * 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 27dd1e12f246..14bb2db5273c 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 4c0782cb1e94..6f3eccf986c7 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1939,6 +1939,7 @@ 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);

@@ -2592,6 +2593,7 @@ 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/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 82eea55a7b5c..3b7d69ca83be 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1086,7 +1086,8 @@ 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 8e7737d7ac0a..03be5d574f23 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 1a874a1f3890..80b37d214beb 100644 --- a/drivers/usb/mon/mon_bin.c +++ b/drivers/usb/mon/mon_bin.c @@ -1002,7 +1002,9 @@ 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: @@ -1229,12 +1231,16 @@ 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/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 11ee55e080e5..3178d8afb3e6 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -121,6 +121,7 @@ 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 */ @@ -171,6 +172,7 @@ 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 9f356f7cf7d5..719ec68ae309 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -156,6 +156,13 @@ UNUSUAL_DEV(0x2109, 0x0711, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NO_ATA_1X),

+/* Reported-by: Icenowy Zheng icenowy@aosc.io */ +UNUSUAL_DEV(0x2537, 0x1068, 0x0000, 0x9999, + "Norelsys", + "NS1068X", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_IGNORE_UAS), + /* Reported-by: Takeo Nakayama javhera@gmx.com */ UNUSUAL_DEV(0x357d, 0x7788, 0x0000, 0x9999, "JMicron", diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c index e24b24fa0f16..2a5d3180777d 100644 --- a/drivers/usb/usbip/usbip_common.c +++ b/drivers/usb/usbip/usbip_common.c @@ -105,7 +105,7 @@ 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++) @@ -138,12 +138,8 @@ 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); @@ -251,9 +247,6 @@ 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); @@ -262,11 +255,9 @@ 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( @@ -276,8 +267,6 @@ 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/drivers/usb/usbip/vudc_rx.c b/drivers/usb/usbip/vudc_rx.c index e429b59f6f8a..d020e72b3122 100644 --- a/drivers/usb/usbip/vudc_rx.c +++ b/drivers/usb/usbip/vudc_rx.c @@ -132,6 +132,25 @@ static int v_recv_cmd_submit(struct vudc *udc, urb_p->new = 1; urb_p->seqnum = pdu->base.seqnum;

+ if (urb_p->ep->type == USB_ENDPOINT_XFER_ISOC) { + /* validate packet size and number of packets */ + unsigned int maxp, packets, bytes; + + maxp = usb_endpoint_maxp(urb_p->ep->desc); + maxp *= usb_endpoint_maxp_mult(urb_p->ep->desc); + bytes = pdu->u.cmd_submit.transfer_buffer_length; + packets = DIV_ROUND_UP(bytes, maxp); + + if (pdu->u.cmd_submit.number_of_packets < 0 || + pdu->u.cmd_submit.number_of_packets > packets) { + dev_err(&udc->gadget.dev, + "CMD_SUBMIT: isoc invalid num packets %d\n", + pdu->u.cmd_submit.number_of_packets); + ret = -EMSGSIZE; + goto free_urbp; + } + } + ret = alloc_urb_from_cmd(&urb_p->urb, pdu, urb_p->ep->type); if (ret) { usbip_event_add(&udc->ud, VUDC_EVENT_ERROR_MALLOC); diff --git a/drivers/usb/usbip/vudc_tx.c b/drivers/usb/usbip/vudc_tx.c index 234661782fa0..3ab4c86486a7 100644 --- a/drivers/usb/usbip/vudc_tx.c +++ b/drivers/usb/usbip/vudc_tx.c @@ -97,6 +97,13 @@ static int v_send_ret_submit(struct vudc *udc, struct urbp *urb_p) memset(&pdu_header, 0, sizeof(pdu_header)); memset(&msg, 0, sizeof(msg));

+ if (urb->actual_length > 0 && !urb->transfer_buffer) { + dev_err(&udc->gadget.dev, + "urb: actual_length %d transfer_buffer null\n", + urb->actual_length); + return -1; + } + if (urb_p->type == USB_ENDPOINT_XFER_ISOC) iovnum = 2 + urb->number_of_packets; else @@ -112,8 +119,8 @@ static int v_send_ret_submit(struct vudc *udc, struct urbp *urb_p)

/* 1. setup usbip_header */ setup_ret_submit_pdu(&pdu_header, urb_p); - usbip_dbg_stub_tx("setup txdata seqnum: %d urb: %p\n", - pdu_header.base.seqnum, urb); + usbip_dbg_stub_tx("setup txdata seqnum: %d\n", + pdu_header.base.seqnum); usbip_header_correct_endian(&pdu_header, 1);

iov[iovnum].iov_base = &pdu_header; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 97498be2ca2e..75ffd3b2149e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -43,6 +43,7 @@ struct bpf_map { u32 max_entries; u32 map_flags; u32 pages; + bool unpriv_array; struct user_struct *user; const struct bpf_map_ops *ops; struct work_struct work; @@ -189,6 +190,7 @@ 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/bpf_verifier.h b/include/linux/bpf_verifier.h index 4c4e9358c146..070fc49e39e2 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -67,7 +67,10 @@ struct bpf_verifier_state_list { };

struct bpf_insn_aux_data { - enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ + 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 */ + }; bool seen; /* this insn was processed by the verifier */ };

diff --git a/include/linux/cpu.h b/include/linux/cpu.h index e571128ad99a..2f475ad89a0d 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -44,6 +44,13 @@ 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/frame.h b/include/linux/frame.h index e6baaba3f1ae..d772c61c31da 100644 --- a/include/linux/frame.h +++ b/include/linux/frame.h @@ -11,7 +11,7 @@ * For more information, see tools/objtool/Documentation/stack-validation.txt. */ #define STACK_FRAME_NON_STANDARD(func) \ - static void __used __section(__func_stack_frame_non_standard) \ + static void __used __section(.discard.func_stack_frame_non_standard) \ *__func_stack_frame_non_standard_##func = func

#else /* !CONFIG_STACK_VALIDATION */ diff --git a/include/linux/phy.h b/include/linux/phy.h index a04d69ab7c34..867110c9d707 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -683,6 +683,17 @@ 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 f2e27e078362..01b3778ba6da 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/net/mac80211.h b/include/net/mac80211.h index 2c7d876e2a1a..8fd61bc50383 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1007,7 +1007,7 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * @RX_FLAG_DECRYPTED: This frame was decrypted in hardware. * @RX_FLAG_MMIC_STRIPPED: the Michael MIC is stripped off this frame, * verification has been done by the hardware. - * @RX_FLAG_IV_STRIPPED: The IV/ICV are stripped from this frame. + * @RX_FLAG_IV_STRIPPED: The IV and ICV are stripped from this frame. * If this flag is set, the stack cannot do any replay detection * hence the driver or hardware will have to do that. * @RX_FLAG_PN_VALIDATED: Currently only valid for CCMP/GCMP frames, this @@ -1078,6 +1078,8 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * @RX_FLAG_ALLOW_SAME_PN: Allow the same PN as same packet before. * This is used for AMSDU subframes which can have the same PN as * the first subframe. + * @RX_FLAG_ICV_STRIPPED: The ICV is stripped from this frame. CRC checking must + * be done in the hardware. */ enum mac80211_rx_flags { RX_FLAG_MMIC_ERROR = BIT(0), @@ -1113,6 +1115,7 @@ enum mac80211_rx_flags { RX_FLAG_RADIOTAP_VENDOR_DATA = BIT(31), RX_FLAG_MIC_STRIPPED = BIT_ULL(32), RX_FLAG_ALLOW_SAME_PN = BIT_ULL(33), + RX_FLAG_ICV_STRIPPED = BIT_ULL(34), };

#define RX_FLAG_STBC_SHIFT 26 diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index eb3b23b6ec54..30f99ce4c6ce 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -493,6 +493,7 @@ 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 8ade3eb6c640..90fce4d6956a 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -208,7 +208,7 @@ 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( @@ -222,7 +222,10 @@ 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 f3721e150d94..9a1e6ed7babc 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -46,9 +46,10 @@ static int bpf_array_alloc_percpu(struct bpf_array *array) static struct bpf_map *array_map_alloc(union bpf_attr *attr) { bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; + u32 elem_size, index_mask, max_entries; + bool unpriv = !capable(CAP_SYS_ADMIN); struct bpf_array *array; - u64 array_size; - u32 elem_size; + u64 array_size, mask64;

/* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || @@ -63,11 +64,32 @@ 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); + } + array_size = sizeof(*array); if (percpu) - array_size += (u64) attr->max_entries * sizeof(void *); + array_size += (u64) max_entries * sizeof(void *); else - array_size += (u64) attr->max_entries * elem_size; + array_size += (u64) max_entries * elem_size;

/* make sure there is no u32 overflow later in round_up() */ if (array_size >= U32_MAX - PAGE_SIZE) @@ -77,6 +99,8 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) array = bpf_map_area_alloc(array_size); if (!array) return ERR_PTR(-ENOMEM); + array->index_mask = index_mask; + array->map.unpriv_array = unpriv;

/* copy mandatory map attributes */ array->map.map_type = attr->map_type; @@ -110,7 +134,7 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key) if (unlikely(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 eBPF program */ @@ -122,7 +146,7 @@ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key) if (unlikely(index >= array->map.max_entries)) return NULL;

- return this_cpu_ptr(array->pptrs[index]); + return this_cpu_ptr(array->pptrs[index & array->index_mask]); }

int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value) @@ -142,7 +166,7 @@ int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value) */ size = round_up(map->value_size, 8); rcu_read_lock(); - pptr = array->pptrs[index]; + pptr = array->pptrs[index & array->index_mask]; for_each_possible_cpu(cpu) { bpf_long_memcpy(value + off, per_cpu_ptr(pptr, cpu), size); off += size; @@ -190,10 +214,11 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, return -EEXIST;

if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) - memcpy(this_cpu_ptr(array->pptrs[index]), + memcpy(this_cpu_ptr(array->pptrs[index & array->index_mask]), value, map->value_size); else - memcpy(array->value + array->elem_size * index, + memcpy(array->value + + array->elem_size * (index & array->index_mask), value, map->value_size); return 0; } @@ -227,7 +252,7 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, */ size = round_up(map->value_size, 8); rcu_read_lock(); - pptr = array->pptrs[index]; + pptr = array->pptrs[index & array->index_mask]; for_each_possible_cpu(cpu) { bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value + off, size); off += size; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 72ea91df71c9..91a2d3752007 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -565,57 +565,6 @@ 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) { @@ -808,9 +757,6 @@ 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 */ prog = bpf_prog_select_runtime(prog, &err); if (err < 0) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d7eeebfafe8d..19c44cf59bb2 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1187,7 +1187,7 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) } }

-static int check_call(struct bpf_verifier_env *env, int func_id) +static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) { struct bpf_verifier_state *state = &env->cur_state; const struct bpf_func_proto *fn = NULL; @@ -1238,6 +1238,13 @@ static int check_call(struct bpf_verifier_env *env, int func_id) err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta); if (err) return err; + if (func_id == BPF_FUNC_tail_call) { + if (meta.map_ptr == NULL) { + verbose("verifier bug\n"); + return -EINVAL; + } + env->insn_aux_data[insn_idx].map_ptr = meta.map_ptr; + } err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta); if (err) return err; @@ -3019,7 +3026,7 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; }

- err = check_call(env, insn->imm); + err = check_call(env, insn->imm, insn_idx); if (err) return err;

@@ -3362,6 +3369,81 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) return 0; }

+/* fixup insn->imm field of bpf_call instructions + * + * this function is called after eBPF program passed verification + */ +static int fixup_bpf_calls(struct bpf_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; + + + for (i = 0; i < insn_cnt; i++, insn++) { + if (insn->code != (BPF_JMP | BPF_CALL)) + continue; + + 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; +} + static void free_states(struct bpf_verifier_env *env) { struct bpf_verifier_state_list *sl, *sln; @@ -3463,6 +3545,9 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) /* 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 */ diff --git a/mm/zswap.c b/mm/zswap.c index dbef27822a98..ded051e3433d 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -752,18 +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 4a47074d1d7f..c8ea3cf9db85 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 ffd09c1675d4..2bbca23a9d05 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -3353,9 +3353,10 @@ 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: @@ -3574,16 +3575,17 @@ 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/ethtool.c b/net/core/ethtool.c index e9989b835a66..7913771ec474 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -742,15 +742,6 @@ static int ethtool_set_link_ksettings(struct net_device *dev, return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings); }

-static void -warn_incomplete_ethtool_legacy_settings_conversion(const char *details) -{ - char name[sizeof(current->comm)]; - - pr_info_once("warning: `%s' uses legacy ethtool link settings API, %s\n", - get_task_comm(name, current), details); -} - /* Query device for its ethtool_cmd settings. * * Backward compatibility note: for compatibility with legacy ethtool, @@ -777,10 +768,8 @@ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) &link_ksettings); if (err < 0) return err; - if (!convert_link_ksettings_to_legacy_settings(&cmd, - &link_ksettings)) - warn_incomplete_ethtool_legacy_settings_conversion( - "link modes are only partially reported"); + convert_link_ksettings_to_legacy_settings(&cmd, + &link_ksettings);

/* send a sensible cmd tag back to user */ cmd.cmd = ETHTOOL_GSET; diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 6b10573cc9fa..d1d9faf3046b 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -295,7 +295,7 @@ 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 506efba33a89..388584b8ff31 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1800,9 +1800,10 @@ 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, ipc6, rt, fl6); - if (err) + if (err) { + ip6_cork_release(&cork, &v6_cork); return ERR_PTR(err); - + } if (ipc6->dontfrag < 0) ipc6->dontfrag = inet6_sk(sk)->dontfrag;

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 11d22d642488..131e6aa954bc 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1080,10 +1080,11 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, 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/wep.c b/net/mac80211/wep.c index efa3f48f1ec5..73e8f347802e 100644 --- a/net/mac80211/wep.c +++ b/net/mac80211/wep.c @@ -293,7 +293,8 @@ ieee80211_crypto_wep_decrypt(struct ieee80211_rx_data *rx) return RX_DROP_UNUSABLE; ieee80211_wep_remove_iv(rx->local, rx->skb, rx->key); /* remove ICV */ - if (pskb_trim(rx->skb, rx->skb->len - IEEE80211_WEP_ICV_LEN)) + if (!(status->flag & RX_FLAG_ICV_STRIPPED) && + pskb_trim(rx->skb, rx->skb->len - IEEE80211_WEP_ICV_LEN)) return RX_DROP_UNUSABLE; }

diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 5c71d60f3a64..caa5986cb2e4 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -295,7 +295,8 @@ ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx) return RX_DROP_UNUSABLE;

/* Trim ICV */ - skb_trim(skb, skb->len - IEEE80211_TKIP_ICV_LEN); + if (!(status->flag & RX_FLAG_ICV_STRIPPED)) + skb_trim(skb, skb->len - IEEE80211_TKIP_ICV_LEN);

/* Remove IV */ memmove(skb->data + IEEE80211_TKIP_IV_LEN, skb->data, hdrlen); diff --git a/net/rds/rdma.c b/net/rds/rdma.c index de8496e60735..f6027f41cd34 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -524,6 +524,9 @@ 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], @@ -873,6 +876,7 @@ 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/net/sched/act_gact.c b/net/sched/act_gact.c index e0aa30f83c6c..9617b42aaf20 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -161,7 +161,7 @@ static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets, if (action == TC_ACT_SHOT) this_cpu_ptr(gact->common.cpu_qstats)->drops += packets;

- tm->lastuse = lastuse; + tm->lastuse = max_t(u64, tm->lastuse, lastuse); }

static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 6b07fba5770b..fc3650b06192 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -211,7 +211,7 @@ static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets, struct tcf_t *tm = &m->tcf_tm;

_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); - tm->lastuse = lastuse; + tm->lastuse = max_t(u64, tm->lastuse, lastuse); }

static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index bd8349759095..845eb9b800f3 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -838,6 +838,7 @@ static const char *const section_white_list[] = ".cmem*", /* EZchip */ ".fmt_slot*", /* EZchip */ ".gnu.lto*", + ".discard.*", NULL };

diff --git a/scripts/module-common.lds b/scripts/module-common.lds index 53234e85192a..9b6e246a45d0 100644 --- a/scripts/module-common.lds +++ b/scripts/module-common.lds @@ -4,7 +4,10 @@ * combine them automatically. */ SECTIONS { - /DISCARD/ : { *(.discard) } + /DISCARD/ : { + *(.discard) + *(.discard.*) + }

__ksymtab 0 : { *(SORT(___ksymtab+*)) } __ksymtab_gpl 0 : { *(SORT(___ksymtab_gpl+*)) } diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index ebc9fdfe64df..3321348fd86b 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -466,7 +466,6 @@ 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 c80d80e312e3..e685e779a4b8 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 <sound/core.h> #include <sound/control.h> #include <sound/pcm.h> +#include <sound/pcm_params.h> #include <sound/info.h> #include <sound/initval.h>

@@ -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/objtool/builtin-check.c b/tools/objtool/builtin-check.c index b8dadb050d2b..a688a857a7ae 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -51,7 +51,7 @@ struct instruction { unsigned int len, state; unsigned char type; unsigned long immediate; - bool alt_group, visited; + bool alt_group, visited, ignore_alts; struct symbol *call_dest; struct instruction *jump_dest; struct list_head alts; @@ -352,6 +352,40 @@ static void add_ignores(struct objtool_file *file) } }

+/* + * FIXME: For now, just ignore any alternatives which add retpolines. This is + * a temporary hack, as it doesn't allow ORC to unwind from inside a retpoline. + * But it at least allows objtool to understand the control flow *around* the + * retpoline. + */ +static int add_nospec_ignores(struct objtool_file *file) +{ + struct section *sec; + struct rela *rela; + struct instruction *insn; + + sec = find_section_by_name(file->elf, ".rela.discard.nospec"); + if (!sec) + return 0; + + list_for_each_entry(rela, &sec->rela_list, list) { + if (rela->sym->type != STT_SECTION) { + WARN("unexpected relocation symbol type in %s", sec->name); + return -1; + } + + insn = find_insn(file, rela->sym->sec, rela->addend); + if (!insn) { + WARN("bad .discard.nospec entry"); + return -1; + } + + insn->ignore_alts = true; + } + + return 0; +} + /* * Find the destination instructions for all jumps. */ @@ -382,6 +416,13 @@ static int add_jump_destinations(struct objtool_file *file) } else if (rela->sym->sec->idx) { dest_sec = rela->sym->sec; dest_off = rela->sym->sym.st_value + rela->addend + 4; + } else if (strstr(rela->sym->name, "_indirect_thunk_")) { + /* + * Retpoline jumps are really dynamic jumps in + * disguise, so convert them accordingly. + */ + insn->type = INSN_JUMP_DYNAMIC; + continue; } else { /* sibling call */ insn->jump_dest = 0; @@ -428,11 +469,18 @@ static int add_call_destinations(struct objtool_file *file) dest_off = insn->offset + insn->len + insn->immediate; insn->call_dest = find_symbol_by_offset(insn->sec, dest_off); + /* + * FIXME: Thanks to retpolines, it's now considered + * normal for a function to call within itself. So + * disable this warning for now. + */ +#if 0 if (!insn->call_dest) { WARN_FUNC("can't find call dest symbol at offset 0x%lx", insn->sec, insn->offset, dest_off); return -1; } +#endif } else if (rela->sym->type == STT_SECTION) { insn->call_dest = find_symbol_by_offset(rela->sym->sec, rela->addend+4); @@ -594,12 +642,6 @@ static int add_special_section_alts(struct objtool_file *file) return ret;

list_for_each_entry_safe(special_alt, tmp, &special_alts, list) { - alt = malloc(sizeof(*alt)); - if (!alt) { - WARN("malloc failed"); - ret = -1; - goto out; - }

orig_insn = find_insn(file, special_alt->orig_sec, special_alt->orig_off); @@ -610,6 +652,10 @@ static int add_special_section_alts(struct objtool_file *file) goto out; }

+ /* Ignore retpoline alternatives. */ + if (orig_insn->ignore_alts) + continue; + new_insn = NULL; if (!special_alt->group || special_alt->new_len) { new_insn = find_insn(file, special_alt->new_sec, @@ -635,6 +681,13 @@ static int add_special_section_alts(struct objtool_file *file) goto out; }

+ alt = malloc(sizeof(*alt)); + if (!alt) { + WARN("malloc failed"); + ret = -1; + goto out; + } + alt->insn = new_insn; list_add_tail(&alt->list, &orig_insn->alts);

@@ -854,6 +907,10 @@ static int decode_sections(struct objtool_file *file)

add_ignores(file);

+ ret = add_nospec_ignores(file); + if (ret) + return ret; + ret = add_jump_destinations(file); if (ret) return ret; @@ -1173,6 +1230,14 @@ static int validate_uncallable_instructions(struct objtool_file *file)

for_each_insn(file, insn) { if (!insn->visited && insn->type == INSN_RETURN) { + + /* + * Don't warn about call instructions in unvisited + * retpoline alternatives. + */ + if (!strcmp(insn->sec->name, ".altinstr_replacement")) + continue; + WARN_FUNC("return instruction outside of a callable function", insn->sec, insn->offset); warnings++; @@ -1229,7 +1294,7 @@ int cmd_check(int argc, const char **argv)

INIT_LIST_HEAD(&file.insn_list); hash_init(file.insn_hash); - file.whitelist = find_section_by_name(file.elf, "__func_stack_frame_non_standard"); + file.whitelist = find_section_by_name(file.elf, ".discard.func_stack_frame_non_standard"); file.rodata = find_section_by_name(file.elf, ".rodata"); file.ignore_unreachables = false; file.c_file = find_section_by_name(file.elf, ".comment"); diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 6300c1a41ff6..4af37bfe4aea 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -6,7 +6,7 @@ include ../lib.mk

TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall test_mremap_vdso \ check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test \ - protection_keys + protection_keys test_vsyscall TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer 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 <stdio.h> +#include <sys/time.h> +#include <time.h> +#include <stdlib.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <dlfcn.h> +#include <string.h> +#include <inttypes.h> +#include <signal.h> +#include <sys/ucontext.h> +#include <errno.h> +#include <err.h> +#include <sched.h> +#include <stdbool.h> +#include <setjmp.h> + +#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; +}