Re: Linux 4.9.102

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index dfd56ec7a850..6d75a9c00e8a 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -355,6 +355,7 @@ 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 + /sys/devices/system/cpu/vulnerabilities/spec_store_bypass Date: January 2018 Contact: Linux kernel mailing list linux-kernel@vger.kernel.org Description: Information about CPU vulnerabilities diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 5f9e51436a99..52240a63132e 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2699,6 +2699,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted. allow data leaks with this option, which is equivalent to spectre_v2=off.

+ nospec_store_bypass_disable + [HW] Disable all mitigations for the Speculative Store Bypass vulnerability + 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. @@ -3973,6 +3976,48 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Not specifying this option is equivalent to spectre_v2=auto.

+ spec_store_bypass_disable= + [HW] Control Speculative Store Bypass (SSB) Disable mitigation + (Speculative Store Bypass vulnerability) + + Certain CPUs are vulnerable to an exploit against a + a common industry wide performance optimization known + as "Speculative Store Bypass" in which recent stores + to the same memory location may not be observed by + later loads during speculative execution. The idea + is that such stores are unlikely and that they can + be detected prior to instruction retirement at the + end of a particular speculation execution window. + + In vulnerable processors, the speculatively forwarded + store can be used in a cache side channel attack, for + example to read memory to which the attacker does not + directly have access (e.g. inside sandboxed code). + + This parameter controls whether the Speculative Store + Bypass optimization is used. + + on - Unconditionally disable Speculative Store Bypass + off - Unconditionally enable Speculative Store Bypass + auto - Kernel detects whether the CPU model contains an + implementation of Speculative Store Bypass and + picks the most appropriate mitigation. If the + CPU is not vulnerable, "off" is selected. If the + CPU is vulnerable the default mitigation is + architecture and Kconfig dependent. See below. + prctl - Control Speculative Store Bypass per thread + via prctl. Speculative Store Bypass is enabled + for a process by default. The state of the control + is inherited on fork. + seccomp - Same as "prctl" above, but all seccomp threads + will disable SSB unless they explicitly opt out. + + Not specifying this option is equivalent to + spec_store_bypass_disable=auto. + + Default mitigations: + X86: If CONFIG_SECCOMP=y "seccomp", otherwise "prctl" + spia_io_base= [HW,MTD] spia_fio_base= spia_pedr= diff --git a/Documentation/spec_ctrl.txt b/Documentation/spec_ctrl.txt new file mode 100644 index 000000000000..32f3d55c54b7 --- /dev/null +++ b/Documentation/spec_ctrl.txt @@ -0,0 +1,94 @@ +=================== +Speculation Control +=================== + +Quite some CPUs have speculation-related misfeatures which are in +fact vulnerabilities causing data leaks in various forms even across +privilege domains. + +The kernel provides mitigation for such vulnerabilities in various +forms. Some of these mitigations are compile-time configurable and some +can be supplied on the kernel command line. + +There is also a class of mitigations which are very expensive, but they can +be restricted to a certain set of processes or tasks in controlled +environments. The mechanism to control these mitigations is via +:manpage:`prctl(2)`. + +There are two prctl options which are related to this: + + * PR_GET_SPECULATION_CTRL + + * PR_SET_SPECULATION_CTRL + +PR_GET_SPECULATION_CTRL +----------------------- + +PR_GET_SPECULATION_CTRL returns the state of the speculation misfeature +which is selected with arg2 of prctl(2). The return value uses bits 0-3 with +the following meaning: + +==== ===================== =================================================== +Bit Define Description +==== ===================== =================================================== +0 PR_SPEC_PRCTL Mitigation can be controlled per task by + PR_SET_SPECULATION_CTRL. +1 PR_SPEC_ENABLE The speculation feature is enabled, mitigation is + disabled. +2 PR_SPEC_DISABLE The speculation feature is disabled, mitigation is + enabled. +3 PR_SPEC_FORCE_DISABLE Same as PR_SPEC_DISABLE, but cannot be undone. A + subsequent prctl(..., PR_SPEC_ENABLE) will fail. +==== ===================== =================================================== + +If all bits are 0 the CPU is not affected by the speculation misfeature. + +If PR_SPEC_PRCTL is set, then the per-task control of the mitigation is +available. If not set, prctl(PR_SET_SPECULATION_CTRL) for the speculation +misfeature will fail. + +PR_SET_SPECULATION_CTRL +----------------------- + +PR_SET_SPECULATION_CTRL allows to control the speculation misfeature, which +is selected by arg2 of :manpage:`prctl(2)` per task. arg3 is used to hand +in the control value, i.e. either PR_SPEC_ENABLE or PR_SPEC_DISABLE or +PR_SPEC_FORCE_DISABLE. + +Common error codes +------------------ +======= ================================================================= +Value Meaning +======= ================================================================= +EINVAL The prctl is not implemented by the architecture or unused + prctl(2) arguments are not 0. + +ENODEV arg2 is selecting a not supported speculation misfeature. +======= ================================================================= + +PR_SET_SPECULATION_CTRL error codes +----------------------------------- +======= ================================================================= +Value Meaning +======= ================================================================= +0 Success + +ERANGE arg3 is incorrect, i.e. it's neither PR_SPEC_ENABLE nor + PR_SPEC_DISABLE nor PR_SPEC_FORCE_DISABLE. + +ENXIO Control of the selected speculation misfeature is not possible. + See PR_GET_SPECULATION_CTRL. + +EPERM Speculation was disabled with PR_SPEC_FORCE_DISABLE and caller + tried to enable it again. +======= ================================================================= + +Speculation misfeature controls +------------------------------- +- PR_SPEC_STORE_BYPASS: Speculative Store Bypass + + Invocations: + * prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, 0, 0, 0); + * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_ENABLE, 0, 0); + * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE, 0, 0); + * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_FORCE_DISABLE, 0, 0); diff --git a/Makefile b/Makefile index 7d7bda23db8f..d84c39c290f7 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 9 -SUBLEVEL = 101 +SUBLEVEL = 102 EXTRAVERSION = NAME = Roaring Lionus

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 12f99fd2e3b2..3aed4492c9a7 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -534,4 +534,14 @@ THUMB( orr \reg , \reg , #PSR_T_BIT ) #endif .endm

+#ifdef CONFIG_KPROBES +#define _ASM_NOKPROBE(entry) \ + .pushsection "_kprobe_blacklist", "aw" ; \ + .balign 4 ; \ + .long entry; \ + .popsection +#else +#define _ASM_NOKPROBE(entry) +#endif + #endif /* __ASM_ASSEMBLER_H__ */ diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index d10e36235438..7f66b1b3aca1 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -223,6 +223,22 @@ static inline unsigned int kvm_get_vmid_bits(void) return 8; }

+/* + * We are not in the kvm->srcu critical section most of the time, so we take + * the SRCU read lock here. Since we copy the data from the user page, we + * can immediately drop the lock again. + */ +static inline int kvm_read_guest_lock(struct kvm *kvm, + gpa_t gpa, void *data, unsigned long len) +{ + int srcu_idx = srcu_read_lock(&kvm->srcu); + int ret = kvm_read_guest(kvm, gpa, data, len); + + srcu_read_unlock(&kvm->srcu, srcu_idx); + + return ret; +} + static inline void *kvm_get_hyp_vector(void) { return kvm_ksym_ref(__kvm_hyp_vector); diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 1b304897aa12..aa316a7562b1 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -19,6 +19,7 @@ #include <linux/uaccess.h> #include <linux/hardirq.h> #include <linux/kdebug.h> +#include <linux/kprobes.h> #include <linux/module.h> #include <linux/kexec.h> #include <linux/bug.h> @@ -415,7 +416,8 @@ void unregister_undef_hook(struct undef_hook *hook) raw_spin_unlock_irqrestore(&undef_lock, flags); }

-static int call_undef_hook(struct pt_regs *regs, unsigned int instr) +static nokprobe_inline +int call_undef_hook(struct pt_regs *regs, unsigned int instr) { struct undef_hook *hook; unsigned long flags; @@ -488,6 +490,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)

arm_notify_die("Oops - undefined instruction", regs, &info, 0, 6); } +NOKPROBE_SYMBOL(do_undefinstr)

/* * Handle FIQ similarly to NMI on x86 systems. diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S index df73914e81c8..746e7801dcdf 100644 --- a/arch/arm/lib/getuser.S +++ b/arch/arm/lib/getuser.S @@ -38,6 +38,7 @@ ENTRY(__get_user_1) mov r0, #0 ret lr ENDPROC(__get_user_1) +_ASM_NOKPROBE(__get_user_1)

ENTRY(__get_user_2) check_uaccess r0, 2, r1, r2, __get_user_bad @@ -58,6 +59,7 @@ rb .req r0 mov r0, #0 ret lr ENDPROC(__get_user_2) +_ASM_NOKPROBE(__get_user_2)

ENTRY(__get_user_4) check_uaccess r0, 4, r1, r2, __get_user_bad @@ -65,6 +67,7 @@ ENTRY(__get_user_4) mov r0, #0 ret lr ENDPROC(__get_user_4) +_ASM_NOKPROBE(__get_user_4)

ENTRY(__get_user_8) check_uaccess r0, 8, r1, r2, __get_user_bad8 @@ -78,6 +81,7 @@ ENTRY(__get_user_8) mov r0, #0 ret lr ENDPROC(__get_user_8) +_ASM_NOKPROBE(__get_user_8)

#ifdef __ARMEB__ ENTRY(__get_user_32t_8) @@ -91,6 +95,7 @@ ENTRY(__get_user_32t_8) mov r0, #0 ret lr ENDPROC(__get_user_32t_8) +_ASM_NOKPROBE(__get_user_32t_8)

ENTRY(__get_user_64t_1) check_uaccess r0, 1, r1, r2, __get_user_bad8 @@ -98,6 +103,7 @@ ENTRY(__get_user_64t_1) mov r0, #0 ret lr ENDPROC(__get_user_64t_1) +_ASM_NOKPROBE(__get_user_64t_1)

ENTRY(__get_user_64t_2) check_uaccess r0, 2, r1, r2, __get_user_bad8 @@ -114,6 +120,7 @@ rb .req r0 mov r0, #0 ret lr ENDPROC(__get_user_64t_2) +_ASM_NOKPROBE(__get_user_64t_2)

ENTRY(__get_user_64t_4) check_uaccess r0, 4, r1, r2, __get_user_bad8 @@ -121,6 +128,7 @@ ENTRY(__get_user_64t_4) mov r0, #0 ret lr ENDPROC(__get_user_64t_4) +_ASM_NOKPROBE(__get_user_64t_4) #endif

__get_user_bad8: @@ -131,6 +139,8 @@ __get_user_bad: ret lr ENDPROC(__get_user_bad) ENDPROC(__get_user_bad8) +_ASM_NOKPROBE(__get_user_bad) +_ASM_NOKPROBE(__get_user_bad8)

.pushsection __ex_table, "a" .long 1b, __get_user_bad diff --git a/arch/arm/probes/kprobes/opt-arm.c b/arch/arm/probes/kprobes/opt-arm.c index bcdecc25461b..b2aa9b32bff2 100644 --- a/arch/arm/probes/kprobes/opt-arm.c +++ b/arch/arm/probes/kprobes/opt-arm.c @@ -165,13 +165,14 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) { unsigned long flags; struct kprobe *p = &op->kp; - struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + struct kprobe_ctlblk *kcb;

/* Save skipped registers */ regs->ARM_pc = (unsigned long)op->kp.addr; regs->ARM_ORIG_r0 = ~0UL;

local_irq_save(flags); + kcb = get_kprobe_ctlblk();

if (kprobe_running()) { kprobes_inc_nmissed_count(&op->kp); @@ -191,6 +192,7 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs)

local_irq_restore(flags); } +NOKPROBE_SYMBOL(optimized_callback)

int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *orig) { diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 80bf33715ecb..eac73a640ea7 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -313,6 +313,22 @@ static inline unsigned int kvm_get_vmid_bits(void) return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8; }

+/* + * We are not in the kvm->srcu critical section most of the time, so we take + * the SRCU read lock here. Since we copy the data from the user page, we + * can immediately drop the lock again. + */ +static inline int kvm_read_guest_lock(struct kvm *kvm, + gpa_t gpa, void *data, unsigned long len) +{ + int srcu_idx = srcu_read_lock(&kvm->srcu); + int ret = kvm_read_guest(kvm, gpa, data, len); + + srcu_read_unlock(&kvm->srcu, srcu_idx); + + return ret; +} + #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR #include <asm/mmu.h>

diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index f516ac508ae3..bf0f712ac0e0 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -228,14 +228,6 @@ static int show_cpuinfo(struct seq_file *m, void *v) unsigned short maj; unsigned short min;

- /* We only show online cpus: disable preempt (overzealous, I - * knew) to prevent cpu going down. */ - preempt_disable(); - if (!cpu_online(cpu_id)) { - preempt_enable(); - return 0; - } - #ifdef CONFIG_SMP pvr = per_cpu(cpu_pvr, cpu_id); #else @@ -340,9 +332,6 @@ static int show_cpuinfo(struct seq_file *m, void *v) #ifdef CONFIG_SMP seq_printf(m, "\n"); #endif - - preempt_enable(); - /* If this is the last cpu, print the summary */ if (cpumask_next(cpu_id, cpu_online_mask) >= nr_cpu_ids) show_cpuinfo_summary(m); diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c index 1bceb95f422d..5584247f5029 100644 --- a/arch/powerpc/platforms/powernv/opal-nvram.c +++ b/arch/powerpc/platforms/powernv/opal-nvram.c @@ -44,6 +44,10 @@ static ssize_t opal_nvram_read(char *buf, size_t count, loff_t *index) return count; }

+/* + * This can be called in the panic path with interrupts off, so use + * mdelay in that case. + */ static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index) { s64 rc = OPAL_BUSY; @@ -58,10 +62,16 @@ static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index) while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { rc = opal_write_nvram(__pa(buf), count, off); if (rc == OPAL_BUSY_EVENT) { - msleep(OPAL_BUSY_DELAY_MS); + if (in_interrupt() || irqs_disabled()) + mdelay(OPAL_BUSY_DELAY_MS); + else + msleep(OPAL_BUSY_DELAY_MS); opal_poll_events(NULL); } else if (rc == OPAL_BUSY) { - msleep(OPAL_BUSY_DELAY_MS); + if (in_interrupt() || irqs_disabled()) + mdelay(OPAL_BUSY_DELAY_MS); + else + msleep(OPAL_BUSY_DELAY_MS); } }

diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index 285d6561076d..7ff976737bb1 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -173,10 +173,9 @@ void do_softirq_own_stack(void) new -= STACK_FRAME_OVERHEAD; ((struct stack_frame *) new)->back_chain = old; asm volatile(" la 15,0(%0)\n" - " basr 14,%2\n" + " brasl 14,__do_softirq\n" " la 15,0(%1)\n" - : : "a" (new), "a" (old), - "a" (__do_softirq) + : : "a" (new), "a" (old) : "0", "1", "2", "3", "4", "5", "14", "cc", "memory" ); } else { diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index fcc634c1479a..96e4fcad57bf 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -739,6 +739,10 @@ static int __hw_perf_event_init(struct perf_event *event) */ rate = 0; if (attr->freq) { + if (!attr->sample_freq) { + err = -EINVAL; + goto out; + } rate = freq_to_sample_rate(&si, attr->sample_freq); rate = hw_limit_rate(&si, rate); attr->freq = 0; diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index cc69e37548db..c0ad1bb27fa2 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -330,7 +330,8 @@ __setup_efi_pci32(efi_pci_io_protocol_32 *pci, struct pci_setup_rom **__rom) if (status != EFI_SUCCESS) goto free_struct;

- memcpy(rom->romdata, pci->romimage, pci->romsize); + memcpy(rom->romdata, (void *)(unsigned long)pci->romimage, + pci->romsize); return status;

free_struct: @@ -436,7 +437,8 @@ __setup_efi_pci64(efi_pci_io_protocol_64 *pci, struct pci_setup_rom **__rom) if (status != EFI_SUCCESS) goto free_struct;

- memcpy(rom->romdata, pci->romimage, pci->romsize); + memcpy(rom->romdata, (void *)(unsigned long)pci->romimage, + pci->romsize); return status;

free_struct: diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index a2485311164b..c278f276c9b3 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -197,6 +197,9 @@ #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_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ +#define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */ + #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */

/* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */ @@ -204,6 +207,13 @@

#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ #define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ +#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ +#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* "" AMD SSBD implementation */ +#define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */ +#define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ +#define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_ZEN ( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */ +

/* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -261,9 +271,10 @@ /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */ #define X86_FEATURE_CLZERO (13*32+0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+1) /* Instructions Retired Count */ -#define X86_FEATURE_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */ -#define X86_FEATURE_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */ -#define X86_FEATURE_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_AMD_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */ +#define X86_FEATURE_AMD_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */ +#define X86_FEATURE_AMD_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */

/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ @@ -299,6 +310,7 @@ #define X86_FEATURE_SUCCOR (17*32+1) /* Uncorrectable error containment and recovery */ #define X86_FEATURE_SMCA (17*32+3) /* Scalable MCA */

+ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ @@ -306,6 +318,7 @@ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */ +#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */

/* * BUG word(s) @@ -335,5 +348,6 @@ #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 */ +#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */

#endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 20cfeeb681c6..7598a6c26f76 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -864,7 +864,7 @@ struct kvm_x86_ops { int (*hardware_setup)(void); /* __init */ void (*hardware_unsetup)(void); /* __exit */ bool (*cpu_has_accelerated_tpr)(void); - bool (*cpu_has_high_real_mode_segbase)(void); + bool (*has_emulated_msr)(int index); void (*cpuid_update)(struct kvm_vcpu *vcpu);

int (*vm_init)(struct kvm *kvm); diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 5a295bb97103..733650874b30 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -113,7 +113,7 @@ static inline int init_new_context(struct task_struct *tsk,

#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { - /* pkey 0 is the default and always allocated */ + /* pkey 0 is the default and allocated implicitly */ mm->context.pkey_allocation_map = 0x1; /* -1 means unallocated or invalid */ mm->context.execute_only_pkey = -1; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index c768bc1550a1..1ec13e253174 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -40,6 +40,8 @@ #define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */ #define SPEC_CTRL_IBRS (1 << 0) /* Indirect Branch Restricted Speculation */ #define SPEC_CTRL_STIBP (1 << 1) /* Single Thread Indirect Branch Predictors */ +#define SPEC_CTRL_SSBD_SHIFT 2 /* Speculative Store Bypass Disable bit */ +#define SPEC_CTRL_SSBD (1 << SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */

#define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */ @@ -61,6 +63,11 @@ #define MSR_IA32_ARCH_CAPABILITIES 0x0000010a #define ARCH_CAP_RDCL_NO (1 << 0) /* Not susceptible to Meltdown */ #define ARCH_CAP_IBRS_ALL (1 << 1) /* Enhanced IBRS support */ +#define ARCH_CAP_SSB_NO (1 << 4) /* + * Not susceptible to Speculative Store Bypass + * attack, so no Speculative Store Bypass + * control required. + */

#define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e @@ -135,6 +142,7 @@

/* DEBUGCTLMSR bits (others vary by model): */ #define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */ +#define DEBUGCTLMSR_BTF_SHIFT 1 #define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */ #define DEBUGCTLMSR_TR (1UL << 6) #define DEBUGCTLMSR_BTS (1UL << 7) @@ -315,6 +323,8 @@ #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */

+#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f + /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index f928ad9b143f..8b38df98548e 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -217,6 +217,14 @@ enum spectre_v2_mitigation { SPECTRE_V2_IBRS, };

+/* The Speculative Store Bypass disable variants */ +enum ssb_mitigation { + SPEC_STORE_BYPASS_NONE, + SPEC_STORE_BYPASS_DISABLE, + SPEC_STORE_BYPASS_PRCTL, + SPEC_STORE_BYPASS_SECCOMP, +}; + extern char __indirect_thunk_start[]; extern char __indirect_thunk_end[];

@@ -241,22 +249,27 @@ static inline void vmexit_fill_RSB(void) #endif }

-#define alternative_msr_write(_msr, _val, _feature) \ - asm volatile(ALTERNATIVE("", \ - "movl %[msr], %%ecx\n\t" \ - "movl %[val], %%eax\n\t" \ - "movl $0, %%edx\n\t" \ - "wrmsr", \ - _feature) \ - : : [msr] "i" (_msr), [val] "i" (_val) \ - : "eax", "ecx", "edx", "memory") +static __always_inline +void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) +{ + asm volatile(ALTERNATIVE("", "wrmsr", %c[feature]) + : : "c" (msr), + "a" ((u32)val), + "d" ((u32)(val >> 32)), + [feature] "i" (feature) + : "memory"); +}

static inline void indirect_branch_prediction_barrier(void) { - alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, - X86_FEATURE_USE_IBPB); + u64 val = PRED_CMD_IBPB; + + alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB); }

+/* The Intel SPEC CTRL MSR base value cache */ +extern u64 x86_spec_ctrl_base; + /* * With retpoline, we must use IBRS to restrict branch prediction * before calling into firmware. @@ -265,14 +278,18 @@ static inline void indirect_branch_prediction_barrier(void) */ #define firmware_restrict_branch_speculation_start() \ do { \ + u64 val = x86_spec_ctrl_base | SPEC_CTRL_IBRS; \ + \ preempt_disable(); \ - alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS, \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, val, \ X86_FEATURE_USE_IBRS_FW); \ } while (0)

#define firmware_restrict_branch_speculation_end() \ do { \ - alternative_msr_write(MSR_IA32_SPEC_CTRL, 0, \ + u64 val = x86_spec_ctrl_base; \ + \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, val, \ X86_FEATURE_USE_IBRS_FW); \ preempt_enable(); \ } while (0) diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index b3b09b98896d..c50d6dcf4a22 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_PKEYS_H #define _ASM_X86_PKEYS_H

+#define ARCH_DEFAULT_PKEY 0 + #define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1)

extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, @@ -14,7 +16,7 @@ extern int __execute_only_pkey(struct mm_struct *mm); static inline int execute_only_pkey(struct mm_struct *mm) { if (!boot_cpu_has(X86_FEATURE_OSPKE)) - return 0; + return ARCH_DEFAULT_PKEY;

return __execute_only_pkey(mm); } @@ -48,13 +50,21 @@ bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) { /* * "Allocated" pkeys are those that have been returned - * from pkey_alloc(). pkey 0 is special, and never - * returned from pkey_alloc(). + * from pkey_alloc() or pkey 0 which is allocated + * implicitly when the mm is created. */ - if (pkey <= 0) + if (pkey < 0) return false; if (pkey >= arch_max_pkey()) return false; + /* + * The exec-only pkey is set in the allocation map, but + * is not available to any of the user interfaces like + * mprotect_pkey(). + */ + if (pkey == mm->context.execute_only_pkey) + return false; + return mm_pkey_allocation_map(mm) & (1U << pkey); }

diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h new file mode 100644 index 000000000000..ae7c2c5cd7f0 --- /dev/null +++ b/arch/x86/include/asm/spec-ctrl.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SPECCTRL_H_ +#define _ASM_X86_SPECCTRL_H_ + +#include <linux/thread_info.h> +#include <asm/nospec-branch.h> + +/* + * On VMENTER we must preserve whatever view of the SPEC_CTRL MSR + * the guest has, while on VMEXIT we restore the host view. This + * would be easier if SPEC_CTRL were architecturally maskable or + * shadowable for guests but this is not (currently) the case. + * Takes the guest view of SPEC_CTRL MSR as a parameter and also + * the guest's version of VIRT_SPEC_CTRL, if emulated. + */ +extern void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool guest); + +/** + * x86_spec_ctrl_set_guest - Set speculation control registers for the guest + * @guest_spec_ctrl: The guest content of MSR_SPEC_CTRL + * @guest_virt_spec_ctrl: The guest controlled bits of MSR_VIRT_SPEC_CTRL + * (may get translated to MSR_AMD64_LS_CFG bits) + * + * Avoids writing to the MSR if the content/bits are the same + */ +static inline +void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl) +{ + x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, true); +} + +/** + * x86_spec_ctrl_restore_host - Restore host speculation control registers + * @guest_spec_ctrl: The guest content of MSR_SPEC_CTRL + * @guest_virt_spec_ctrl: The guest controlled bits of MSR_VIRT_SPEC_CTRL + * (may get translated to MSR_AMD64_LS_CFG bits) + * + * Avoids writing to the MSR if the content/bits are the same + */ +static inline +void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl) +{ + x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, false); +} + +/* AMD specific Speculative Store Bypass MSR data */ +extern u64 x86_amd_ls_cfg_base; +extern u64 x86_amd_ls_cfg_ssbd_mask; + +static inline u64 ssbd_tif_to_spec_ctrl(u64 tifn) +{ + BUILD_BUG_ON(TIF_SSBD < SPEC_CTRL_SSBD_SHIFT); + return (tifn & _TIF_SSBD) >> (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT); +} + +static inline unsigned long ssbd_spec_ctrl_to_tif(u64 spec_ctrl) +{ + BUILD_BUG_ON(TIF_SSBD < SPEC_CTRL_SSBD_SHIFT); + return (spec_ctrl & SPEC_CTRL_SSBD) << (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT); +} + +static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn) +{ + return (tifn & _TIF_SSBD) ? x86_amd_ls_cfg_ssbd_mask : 0ULL; +} + +#ifdef CONFIG_SMP +extern void speculative_store_bypass_ht_init(void); +#else +static inline void speculative_store_bypass_ht_init(void) { } +#endif + +extern void speculative_store_bypass_update(unsigned long tif); + +static inline void speculative_store_bypass_update_current(void) +{ + speculative_store_bypass_update(current_thread_info()->flags); +} + +#endif diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 89978b9c667a..2d8788a59b4d 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -83,6 +83,7 @@ struct thread_info { #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_SINGLESTEP 4 /* reenable singlestep on user return*/ +#define TIF_SSBD 5 /* Reduced data speculation */ #define TIF_SYSCALL_EMU 6 /* syscall emulation active */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SECCOMP 8 /* secure computing */ @@ -104,8 +105,9 @@ struct thread_info { #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) -#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) +#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) +#define _TIF_SSBD (1 << TIF_SSBD) #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) @@ -139,7 +141,7 @@ struct thread_info {

/* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ - (_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP) + (_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP|_TIF_SSBD)

#define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 99185a064978..686a58d793e5 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -111,6 +111,16 @@ static inline void cr4_clear_bits(unsigned long mask) } }

+static inline void cr4_toggle_bits(unsigned long mask) +{ + unsigned long cr4; + + cr4 = this_cpu_read(cpu_tlbstate.cr4); + cr4 ^= mask; + this_cpu_write(cpu_tlbstate.cr4, cr4); + __write_cr4(cr4); +} + /* Read the CR4 shadow. */ static inline unsigned long cr4_read_shadow(void) { diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index c375bc672f82..4c2be99fa0fb 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -9,6 +9,7 @@ #include <asm/processor.h> #include <asm/apic.h> #include <asm/cpu.h> +#include <asm/spec-ctrl.h> #include <asm/smp.h> #include <asm/pci-direct.h> #include <asm/delay.h> @@ -542,6 +543,26 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) rdmsrl(MSR_FAM10H_NODE_ID, value); nodes_per_socket = ((value >> 3) & 7) + 1; } + + if (c->x86 >= 0x15 && c->x86 <= 0x17) { + unsigned int bit; + + switch (c->x86) { + case 0x15: bit = 54; break; + case 0x16: bit = 33; break; + case 0x17: bit = 10; break; + default: return; + } + /* + * Try to cache the base value so further operations can + * avoid RMW. If that faults, do not enable SSBD. + */ + if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) { + setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD); + setup_force_cpu_cap(X86_FEATURE_SSBD); + x86_amd_ls_cfg_ssbd_mask = 1ULL << bit; + } + } }

static void early_init_amd(struct cpuinfo_x86 *c) @@ -728,6 +749,17 @@ static void init_amd_bd(struct cpuinfo_x86 *c) } }

+static void init_amd_zn(struct cpuinfo_x86 *c) +{ + set_cpu_cap(c, X86_FEATURE_ZEN); + /* + * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects + * all up to and including B1. + */ + if (c->x86_model <= 1 && c->x86_stepping <= 1) + set_cpu_cap(c, X86_FEATURE_CPB); +} + static void init_amd(struct cpuinfo_x86 *c) { u32 dummy; @@ -758,6 +790,7 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x10: init_amd_gh(c); break; case 0x12: init_amd_ln(c); break; case 0x15: init_amd_bd(c); break; + case 0x17: init_amd_zn(c); break; }

/* Enable workaround for FXSAVE leak */ @@ -824,8 +857,9 @@ static void init_amd(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_3DNOW) || cpu_has(c, X86_FEATURE_LM)) set_cpu_cap(c, X86_FEATURE_3DNOWPREFETCH);

- /* AMD CPUs don't reset SS attributes on SYSRET */ - set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); + /* AMD CPUs don't reset SS attributes on SYSRET, Xen does. */ + if (!cpu_has(c, X86_FEATURE_XENPV)) + set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); }

#ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index b8b0b6e78371..86af9b1b049d 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -11,8 +11,10 @@ #include <linux/utsname.h> #include <linux/cpu.h> #include <linux/module.h> +#include <linux/nospec.h> +#include <linux/prctl.h>

-#include <asm/nospec-branch.h> +#include <asm/spec-ctrl.h> #include <asm/cmdline.h> #include <asm/bugs.h> #include <asm/processor.h> @@ -26,6 +28,27 @@ #include <asm/intel-family.h>

static void __init spectre_v2_select_mitigation(void); +static void __init ssb_select_mitigation(void); + +/* + * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any + * writes to SPEC_CTRL contain whatever reserved bits have been set. + */ +u64 __ro_after_init x86_spec_ctrl_base; +EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); + +/* + * The vendor and possibly platform specific bits which can be modified in + * x86_spec_ctrl_base. + */ +static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS; + +/* + * AMD specific MSR info for Speculative Store Bypass control. + * x86_amd_ls_cfg_ssbd_mask is initialized in identify_boot_cpu(). + */ +u64 __ro_after_init x86_amd_ls_cfg_base; +u64 __ro_after_init x86_amd_ls_cfg_ssbd_mask;

void __init check_bugs(void) { @@ -36,9 +59,27 @@ void __init check_bugs(void) print_cpu_info(&boot_cpu_data); }

+ /* + * Read the SPEC_CTRL MSR to account for reserved bits which may + * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD + * init code as it is not enumerated and depends on the family. + */ + if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) + rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + + /* Allow STIBP in MSR_SPEC_CTRL if supported */ + if (boot_cpu_has(X86_FEATURE_STIBP)) + x86_spec_ctrl_mask |= SPEC_CTRL_STIBP; + /* Select the proper spectre mitigation before patching alternatives */ spectre_v2_select_mitigation();

+ /* + * Select proper mitigation for any exposure to the Speculative Store + * Bypass vulnerability. + */ + ssb_select_mitigation(); + #ifdef CONFIG_X86_32 /* * Check whether we are able to run this kernel safely on SMP. @@ -92,7 +133,76 @@ static const char *spectre_v2_strings[] = { #undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt

-static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; +static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = + SPECTRE_V2_NONE; + +void +x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) +{ + u64 msrval, guestval, hostval = x86_spec_ctrl_base; + struct thread_info *ti = current_thread_info(); + + /* Is MSR_SPEC_CTRL implemented ? */ + if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) { + /* + * Restrict guest_spec_ctrl to supported values. Clear the + * modifiable bits in the host base value and or the + * modifiable bits from the guest value. + */ + guestval = hostval & ~x86_spec_ctrl_mask; + guestval |= guest_spec_ctrl & x86_spec_ctrl_mask; + + /* SSBD controlled in MSR_SPEC_CTRL */ + if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD)) + hostval |= ssbd_tif_to_spec_ctrl(ti->flags); + + if (hostval != guestval) { + msrval = setguest ? guestval : hostval; + wrmsrl(MSR_IA32_SPEC_CTRL, msrval); + } + } + + /* + * If SSBD is not handled in MSR_SPEC_CTRL on AMD, update + * MSR_AMD64_L2_CFG or MSR_VIRT_SPEC_CTRL if supported. + */ + if (!static_cpu_has(X86_FEATURE_LS_CFG_SSBD) && + !static_cpu_has(X86_FEATURE_VIRT_SSBD)) + return; + + /* + * If the host has SSBD mitigation enabled, force it in the host's + * virtual MSR value. If its not permanently enabled, evaluate + * current's TIF_SSBD thread flag. + */ + if (static_cpu_has(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE)) + hostval = SPEC_CTRL_SSBD; + else + hostval = ssbd_tif_to_spec_ctrl(ti->flags); + + /* Sanitize the guest value */ + guestval = guest_virt_spec_ctrl & SPEC_CTRL_SSBD; + + if (hostval != guestval) { + unsigned long tif; + + tif = setguest ? ssbd_spec_ctrl_to_tif(guestval) : + ssbd_spec_ctrl_to_tif(hostval); + + speculative_store_bypass_update(tif); + } +} +EXPORT_SYMBOL_GPL(x86_virt_spec_ctrl); + +static void x86_amd_ssb_disable(void) +{ + u64 msrval = x86_amd_ls_cfg_base | x86_amd_ls_cfg_ssbd_mask; + + if (boot_cpu_has(X86_FEATURE_VIRT_SSBD)) + wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, SPEC_CTRL_SSBD); + else if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD)) + wrmsrl(MSR_AMD64_LS_CFG, msrval); +}

#ifdef RETPOLINE static bool spectre_v2_bad_module; @@ -311,32 +421,289 @@ static void __init spectre_v2_select_mitigation(void) }

#undef pr_fmt +#define pr_fmt(fmt) "Speculative Store Bypass: " fmt + +static enum ssb_mitigation ssb_mode __ro_after_init = SPEC_STORE_BYPASS_NONE; + +/* The kernel command line selection */ +enum ssb_mitigation_cmd { + SPEC_STORE_BYPASS_CMD_NONE, + SPEC_STORE_BYPASS_CMD_AUTO, + SPEC_STORE_BYPASS_CMD_ON, + SPEC_STORE_BYPASS_CMD_PRCTL, + SPEC_STORE_BYPASS_CMD_SECCOMP, +}; + +static const char *ssb_strings[] = { + [SPEC_STORE_BYPASS_NONE] = "Vulnerable", + [SPEC_STORE_BYPASS_DISABLE] = "Mitigation: Speculative Store Bypass disabled", + [SPEC_STORE_BYPASS_PRCTL] = "Mitigation: Speculative Store Bypass disabled via prctl", + [SPEC_STORE_BYPASS_SECCOMP] = "Mitigation: Speculative Store Bypass disabled via prctl and seccomp", +}; + +static const struct { + const char *option; + enum ssb_mitigation_cmd cmd; +} ssb_mitigation_options[] = { + { "auto", SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */ + { "on", SPEC_STORE_BYPASS_CMD_ON }, /* Disable Speculative Store Bypass */ + { "off", SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */ + { "prctl", SPEC_STORE_BYPASS_CMD_PRCTL }, /* Disable Speculative Store Bypass via prctl */ + { "seccomp", SPEC_STORE_BYPASS_CMD_SECCOMP }, /* Disable Speculative Store Bypass via prctl and seccomp */ +}; + +static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void) +{ + enum ssb_mitigation_cmd cmd = SPEC_STORE_BYPASS_CMD_AUTO; + char arg[20]; + int ret, i; + + if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) { + return SPEC_STORE_BYPASS_CMD_NONE; + } else { + ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable", + arg, sizeof(arg)); + if (ret < 0) + return SPEC_STORE_BYPASS_CMD_AUTO; + + for (i = 0; i < ARRAY_SIZE(ssb_mitigation_options); i++) { + if (!match_option(arg, ret, ssb_mitigation_options[i].option)) + continue; + + cmd = ssb_mitigation_options[i].cmd; + break; + } + + if (i >= ARRAY_SIZE(ssb_mitigation_options)) { + pr_err("unknown option (%s). Switching to AUTO select\n", arg); + return SPEC_STORE_BYPASS_CMD_AUTO; + } + } + + return cmd; +} + +static enum ssb_mitigation __init __ssb_select_mitigation(void) +{ + enum ssb_mitigation mode = SPEC_STORE_BYPASS_NONE; + enum ssb_mitigation_cmd cmd; + + if (!boot_cpu_has(X86_FEATURE_SSBD)) + return mode; + + cmd = ssb_parse_cmdline(); + if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS) && + (cmd == SPEC_STORE_BYPASS_CMD_NONE || + cmd == SPEC_STORE_BYPASS_CMD_AUTO)) + return mode; + + switch (cmd) { + case SPEC_STORE_BYPASS_CMD_AUTO: + case SPEC_STORE_BYPASS_CMD_SECCOMP: + /* + * Choose prctl+seccomp as the default mode if seccomp is + * enabled. + */ + if (IS_ENABLED(CONFIG_SECCOMP)) + mode = SPEC_STORE_BYPASS_SECCOMP; + else + mode = SPEC_STORE_BYPASS_PRCTL; + break; + case SPEC_STORE_BYPASS_CMD_ON: + mode = SPEC_STORE_BYPASS_DISABLE; + break; + case SPEC_STORE_BYPASS_CMD_PRCTL: + mode = SPEC_STORE_BYPASS_PRCTL; + break; + case SPEC_STORE_BYPASS_CMD_NONE: + break; + } + + /* + * We have three CPU feature flags that are in play here: + * - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible. + * - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass + * - X86_FEATURE_SPEC_STORE_BYPASS_DISABLE - engage the mitigation + */ + if (mode == SPEC_STORE_BYPASS_DISABLE) { + setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE); + /* + * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD uses + * a completely different MSR and bit dependent on family. + */ + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_INTEL: + x86_spec_ctrl_base |= SPEC_CTRL_SSBD; + x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + break; + case X86_VENDOR_AMD: + x86_amd_ssb_disable(); + break; + } + } + + return mode; +} + +static void ssb_select_mitigation(void) +{ + ssb_mode = __ssb_select_mitigation(); + + if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + pr_info("%s\n", ssb_strings[ssb_mode]); +} + +#undef pr_fmt +#define pr_fmt(fmt) "Speculation prctl: " fmt + +static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) +{ + bool update; + + if (ssb_mode != SPEC_STORE_BYPASS_PRCTL && + ssb_mode != SPEC_STORE_BYPASS_SECCOMP) + return -ENXIO; + + switch (ctrl) { + case PR_SPEC_ENABLE: + /* If speculation is force disabled, enable is not allowed */ + if (task_spec_ssb_force_disable(task)) + return -EPERM; + task_clear_spec_ssb_disable(task); + update = test_and_clear_tsk_thread_flag(task, TIF_SSBD); + break; + case PR_SPEC_DISABLE: + task_set_spec_ssb_disable(task); + update = !test_and_set_tsk_thread_flag(task, TIF_SSBD); + break; + case PR_SPEC_FORCE_DISABLE: + task_set_spec_ssb_disable(task); + task_set_spec_ssb_force_disable(task); + update = !test_and_set_tsk_thread_flag(task, TIF_SSBD); + break; + default: + return -ERANGE; + } + + /* + * If being set on non-current task, delay setting the CPU + * mitigation until it is next scheduled. + */ + if (task == current && update) + speculative_store_bypass_update_current(); + + return 0; +} + +int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, + unsigned long ctrl) +{ + switch (which) { + case PR_SPEC_STORE_BYPASS: + return ssb_prctl_set(task, ctrl); + default: + return -ENODEV; + } +} + +#ifdef CONFIG_SECCOMP +void arch_seccomp_spec_mitigate(struct task_struct *task) +{ + if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP) + ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE); +} +#endif + +static int ssb_prctl_get(struct task_struct *task) +{ + switch (ssb_mode) { + case SPEC_STORE_BYPASS_DISABLE: + return PR_SPEC_DISABLE; + case SPEC_STORE_BYPASS_SECCOMP: + case SPEC_STORE_BYPASS_PRCTL: + if (task_spec_ssb_force_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; + if (task_spec_ssb_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_DISABLE; + return PR_SPEC_PRCTL | PR_SPEC_ENABLE; + default: + if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + return PR_SPEC_ENABLE; + return PR_SPEC_NOT_AFFECTED; + } +} + +int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) +{ + switch (which) { + case PR_SPEC_STORE_BYPASS: + return ssb_prctl_get(task); + default: + return -ENODEV; + } +} + +void x86_spec_ctrl_setup_ap(void) +{ + if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + + if (ssb_mode == SPEC_STORE_BYPASS_DISABLE) + x86_amd_ssb_disable(); +}

#ifdef CONFIG_SYSFS -ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) + +static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, + char *buf, unsigned int bug) { - if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + if (!boot_cpu_has_bug(bug)) return sprintf(buf, "Not affected\n"); - if (boot_cpu_has(X86_FEATURE_KAISER)) - return sprintf(buf, "Mitigation: PTI\n"); + + switch (bug) { + case X86_BUG_CPU_MELTDOWN: + if (boot_cpu_has(X86_FEATURE_KAISER)) + return sprintf(buf, "Mitigation: PTI\n"); + + break; + + case X86_BUG_SPECTRE_V1: + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); + + case X86_BUG_SPECTRE_V2: + return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", + spectre_v2_module_string()); + + case X86_BUG_SPEC_STORE_BYPASS: + return sprintf(buf, "%s\n", ssb_strings[ssb_mode]); + + default: + break; + } + return sprintf(buf, "Vulnerable\n"); }

+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_CPU_MELTDOWN); +} + 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, "Mitigation: __user pointer sanitization\n"); + return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V1); }

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 cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V2); +}

- return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], - boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", - boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", - spectre_v2_module_string()); +ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS); } #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 301bbd1f2373..b0fd028b2eee 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -725,17 +725,32 @@ static void init_speculation_control(struct cpuinfo_x86 *c) * and they also have a different bit for STIBP support. Also, * a hypervisor might have set the individual AMD bits even on * Intel CPUs, for finer-grained selection of what's available. - * - * We use the AMD bits in 0x8000_0008 EBX as the generic hardware - * features, which are visible in /proc/cpuinfo and used by the - * kernel. So set those accordingly from the Intel bits. */ if (cpu_has(c, X86_FEATURE_SPEC_CTRL)) { set_cpu_cap(c, X86_FEATURE_IBRS); set_cpu_cap(c, X86_FEATURE_IBPB); + set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL); } + if (cpu_has(c, X86_FEATURE_INTEL_STIBP)) set_cpu_cap(c, X86_FEATURE_STIBP); + + if (cpu_has(c, X86_FEATURE_SPEC_CTRL_SSBD) || + cpu_has(c, X86_FEATURE_VIRT_SSBD)) + set_cpu_cap(c, X86_FEATURE_SSBD); + + if (cpu_has(c, X86_FEATURE_AMD_IBRS)) { + set_cpu_cap(c, X86_FEATURE_IBRS); + set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL); + } + + if (cpu_has(c, X86_FEATURE_AMD_IBPB)) + set_cpu_cap(c, X86_FEATURE_IBPB); + + if (cpu_has(c, X86_FEATURE_AMD_STIBP)) { + set_cpu_cap(c, X86_FEATURE_STIBP); + set_cpu_cap(c, X86_FEATURE_MSR_SPEC_CTRL); + } }

void get_cpu_cap(struct cpuinfo_x86 *c) @@ -879,21 +894,55 @@ static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { {} };

-static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c) +static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = { + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_CORE_YONAH }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL }, + { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM }, + { X86_VENDOR_CENTAUR, 5, }, + { X86_VENDOR_INTEL, 5, }, + { X86_VENDOR_NSC, 5, }, + { X86_VENDOR_AMD, 0x12, }, + { X86_VENDOR_AMD, 0x11, }, + { X86_VENDOR_AMD, 0x10, }, + { X86_VENDOR_AMD, 0xf, }, + { X86_VENDOR_ANY, 4, }, + {} +}; + +static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = 0;

- if (x86_match_cpu(cpu_no_meltdown)) - return false; - if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);

+ if (!x86_match_cpu(cpu_no_spec_store_bypass) && + !(ia32_cap & ARCH_CAP_SSB_NO)) + setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); + + if (x86_match_cpu(cpu_no_speculation)) + return; + + setup_force_cpu_bug(X86_BUG_SPECTRE_V1); + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + + if (x86_match_cpu(cpu_no_meltdown)) + return; + /* Rogue Data Cache Load? No! */ if (ia32_cap & ARCH_CAP_RDCL_NO) - return false; + return;

- return true; + setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); }

/* @@ -942,12 +991,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)

setup_force_cpu_cap(X86_FEATURE_ALWAYS);

- if (!x86_match_cpu(cpu_no_speculation)) { - if (cpu_vulnerable_to_meltdown(c)) - setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); - setup_force_cpu_bug(X86_BUG_SPECTRE_V1); - setup_force_cpu_bug(X86_BUG_SPECTRE_V2); - } + cpu_set_bug_bits(c);

fpu__init_system(c);

@@ -1315,6 +1359,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) #endif mtrr_ap_init(); validate_apic_and_package_id(c); + x86_spec_ctrl_setup_ap(); }

struct msr_range { diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 2584265d4745..3b19d82f7932 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -46,4 +46,7 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[],

extern void get_cpu_cap(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); + +extern void x86_spec_ctrl_setup_ap(void); + #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 8fb1d6522f8e..93781e3f05b2 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -153,7 +153,10 @@ static void early_init_intel(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_IBPB); setup_clear_cpu_cap(X86_FEATURE_STIBP); setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL); + setup_clear_cpu_cap(X86_FEATURE_MSR_SPEC_CTRL); setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP); + setup_clear_cpu_cap(X86_FEATURE_SSBD); + setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL_SSBD); }

/* diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index a55b32007785..00a9047539d7 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -33,6 +33,7 @@ #include <asm/mce.h> #include <asm/vm86.h> #include <asm/switch_to.h> +#include <asm/spec-ctrl.h>

/* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -134,11 +135,6 @@ void flush_thread(void) fpu__clear(&tsk->thread.fpu); }

-static void hard_disable_TSC(void) -{ - cr4_set_bits(X86_CR4_TSD); -} - void disable_TSC(void) { preempt_disable(); @@ -147,15 +143,10 @@ void disable_TSC(void) * Must flip the CPU state synchronously with * TIF_NOTSC in the current running context. */ - hard_disable_TSC(); + cr4_set_bits(X86_CR4_TSD); preempt_enable(); }

-static void hard_enable_TSC(void) -{ - cr4_clear_bits(X86_CR4_TSD); -} - static void enable_TSC(void) { preempt_disable(); @@ -164,7 +155,7 @@ static void enable_TSC(void) * Must flip the CPU state synchronously with * TIF_NOTSC in the current running context. */ - hard_enable_TSC(); + cr4_clear_bits(X86_CR4_TSD); preempt_enable(); }

@@ -192,48 +183,199 @@ int set_tsc_mode(unsigned int val) return 0; }

-void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, - struct tss_struct *tss) +static inline void switch_to_bitmap(struct tss_struct *tss, + struct thread_struct *prev, + struct thread_struct *next, + unsigned long tifp, unsigned long tifn) { - struct thread_struct *prev, *next; - - prev = &prev_p->thread; - next = &next_p->thread; - - if (test_tsk_thread_flag(prev_p, TIF_BLOCKSTEP) ^ - test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) { - unsigned long debugctl = get_debugctlmsr(); - - debugctl &= ~DEBUGCTLMSR_BTF; - if (test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) - debugctl |= DEBUGCTLMSR_BTF; - - update_debugctlmsr(debugctl); - } - - if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ - test_tsk_thread_flag(next_p, TIF_NOTSC)) { - /* prev and next are different */ - if (test_tsk_thread_flag(next_p, TIF_NOTSC)) - hard_disable_TSC(); - else - hard_enable_TSC(); - } - - if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { + if (tifn & _TIF_IO_BITMAP) { /* * Copy the relevant range of the IO bitmap. * Normally this is 128 bytes or less: */ memcpy(tss->io_bitmap, next->io_bitmap_ptr, max(prev->io_bitmap_max, next->io_bitmap_max)); - } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) { + } else if (tifp & _TIF_IO_BITMAP) { /* * Clear any possible leftover bits: */ memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); } +} + +#ifdef CONFIG_SMP + +struct ssb_state { + struct ssb_state *shared_state; + raw_spinlock_t lock; + unsigned int disable_state; + unsigned long local_state; +}; + +#define LSTATE_SSB 0 + +static DEFINE_PER_CPU(struct ssb_state, ssb_state); + +void speculative_store_bypass_ht_init(void) +{ + struct ssb_state *st = this_cpu_ptr(&ssb_state); + unsigned int this_cpu = smp_processor_id(); + unsigned int cpu; + + st->local_state = 0; + + /* + * Shared state setup happens once on the first bringup + * of the CPU. It's not destroyed on CPU hotunplug. + */ + if (st->shared_state) + return; + + raw_spin_lock_init(&st->lock); + + /* + * Go over HT siblings and check whether one of them has set up the + * shared state pointer already. + */ + for_each_cpu(cpu, topology_sibling_cpumask(this_cpu)) { + if (cpu == this_cpu) + continue; + + if (!per_cpu(ssb_state, cpu).shared_state) + continue; + + /* Link it to the state of the sibling: */ + st->shared_state = per_cpu(ssb_state, cpu).shared_state; + return; + } + + /* + * First HT sibling to come up on the core. Link shared state of + * the first HT sibling to itself. The siblings on the same core + * which come up later will see the shared state pointer and link + * themself to the state of this CPU. + */ + st->shared_state = st; +} + +/* + * Logic is: First HT sibling enables SSBD for both siblings in the core + * and last sibling to disable it, disables it for the whole core. This how + * MSR_SPEC_CTRL works in "hardware": + * + * CORE_SPEC_CTRL = THREAD0_SPEC_CTRL | THREAD1_SPEC_CTRL + */ +static __always_inline void amd_set_core_ssb_state(unsigned long tifn) +{ + struct ssb_state *st = this_cpu_ptr(&ssb_state); + u64 msr = x86_amd_ls_cfg_base; + + if (!static_cpu_has(X86_FEATURE_ZEN)) { + msr |= ssbd_tif_to_amd_ls_cfg(tifn); + wrmsrl(MSR_AMD64_LS_CFG, msr); + return; + } + + if (tifn & _TIF_SSBD) { + /* + * Since this can race with prctl(), block reentry on the + * same CPU. + */ + if (__test_and_set_bit(LSTATE_SSB, &st->local_state)) + return; + + msr |= x86_amd_ls_cfg_ssbd_mask; + + raw_spin_lock(&st->shared_state->lock); + /* First sibling enables SSBD: */ + if (!st->shared_state->disable_state) + wrmsrl(MSR_AMD64_LS_CFG, msr); + st->shared_state->disable_state++; + raw_spin_unlock(&st->shared_state->lock); + } else { + if (!__test_and_clear_bit(LSTATE_SSB, &st->local_state)) + return; + + raw_spin_lock(&st->shared_state->lock); + st->shared_state->disable_state--; + if (!st->shared_state->disable_state) + wrmsrl(MSR_AMD64_LS_CFG, msr); + raw_spin_unlock(&st->shared_state->lock); + } +} +#else +static __always_inline void amd_set_core_ssb_state(unsigned long tifn) +{ + u64 msr = x86_amd_ls_cfg_base | ssbd_tif_to_amd_ls_cfg(tifn); + + wrmsrl(MSR_AMD64_LS_CFG, msr); +} +#endif + +static __always_inline void amd_set_ssb_virt_state(unsigned long tifn) +{ + /* + * SSBD has the same definition in SPEC_CTRL and VIRT_SPEC_CTRL, + * so ssbd_tif_to_spec_ctrl() just works. + */ + wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, ssbd_tif_to_spec_ctrl(tifn)); +} + +static __always_inline void intel_set_ssb_state(unsigned long tifn) +{ + u64 msr = x86_spec_ctrl_base | ssbd_tif_to_spec_ctrl(tifn); + + wrmsrl(MSR_IA32_SPEC_CTRL, msr); +} + +static __always_inline void __speculative_store_bypass_update(unsigned long tifn) +{ + if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) + amd_set_ssb_virt_state(tifn); + else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) + amd_set_core_ssb_state(tifn); + else + intel_set_ssb_state(tifn); +} + +void speculative_store_bypass_update(unsigned long tif) +{ + preempt_disable(); + __speculative_store_bypass_update(tif); + preempt_enable(); +} + +void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, + struct tss_struct *tss) +{ + struct thread_struct *prev, *next; + unsigned long tifp, tifn; + + prev = &prev_p->thread; + next = &next_p->thread; + + tifn = READ_ONCE(task_thread_info(next_p)->flags); + tifp = READ_ONCE(task_thread_info(prev_p)->flags); + switch_to_bitmap(tss, prev, next, tifp, tifn); + propagate_user_return_notify(prev_p, next_p); + + if ((tifp & _TIF_BLOCKSTEP || tifn & _TIF_BLOCKSTEP) && + arch_has_block_step()) { + unsigned long debugctl, msk; + + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + debugctl &= ~DEBUGCTLMSR_BTF; + msk = tifn & _TIF_BLOCKSTEP; + debugctl |= (msk >> TIF_BLOCKSTEP) << DEBUGCTLMSR_BTF_SHIFT; + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + } + + if ((tifp ^ tifn) & _TIF_NOTSC) + cr4_toggle_bits(X86_CR4_TSD); + + if ((tifp ^ tifn) & _TIF_SSBD) + __speculative_store_bypass_update(tifn); }

/* diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 83929cc47a4b..cb945146b7c8 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -75,6 +75,7 @@ #include <asm/i8259.h> #include <asm/realmode.h> #include <asm/misc.h> +#include <asm/spec-ctrl.h>

/* Number of siblings per CPU package */ int smp_num_siblings = 1; @@ -229,6 +230,8 @@ static void notrace start_secondary(void *unused) */ check_tsc_sync_target();

+ speculative_store_bypass_ht_init(); + /* * Lock vector_lock and initialize the vectors on this cpu * before setting the cpu online. We must set it online with @@ -1325,6 +1328,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) set_mtrr_aps_delayed_init();

smp_quirk_init_udelay(); + + speculative_store_bypass_ht_init(); }

void arch_enable_nonboot_cpus_begin(void) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 93f924de06cf..a69f18d4676c 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -357,7 +357,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,

/* cpuid 0x80000008.ebx */ const u32 kvm_cpuid_8000_0008_ebx_x86_features = - F(IBPB) | F(IBRS); + F(AMD_IBPB) | F(AMD_IBRS) | F(VIRT_SSBD);

/* cpuid 0xC0000001.edx */ const u32 kvm_cpuid_C000_0001_edx_x86_features = @@ -382,7 +382,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,

/* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = - F(SPEC_CTRL) | F(ARCH_CAPABILITIES); + F(SPEC_CTRL) | F(SSBD) | F(ARCH_CAPABILITIES);

/* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); @@ -618,13 +618,20 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); entry->edx = 0; - /* IBRS and IBPB aren't necessarily present in hardware cpuid */ - if (boot_cpu_has(X86_FEATURE_IBPB)) - entry->ebx |= F(IBPB); - if (boot_cpu_has(X86_FEATURE_IBRS)) - entry->ebx |= F(IBRS); + /* + * IBRS, IBPB and VIRT_SSBD aren't necessarily present in + * hardware cpuid + */ + if (boot_cpu_has(X86_FEATURE_AMD_IBPB)) + entry->ebx |= F(AMD_IBPB); + if (boot_cpu_has(X86_FEATURE_AMD_IBRS)) + entry->ebx |= F(AMD_IBRS); + if (boot_cpu_has(X86_FEATURE_VIRT_SSBD)) + entry->ebx |= F(VIRT_SSBD); entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features; cpuid_mask(&entry->ebx, CPUID_8000_0008_EBX); + if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD)) + entry->ebx |= F(VIRT_SSBD); break; } case 0x80000019: diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index d1beb7156704..c38369781239 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -165,21 +165,21 @@ static inline bool guest_cpuid_has_ibpb(struct kvm_vcpu *vcpu) struct kvm_cpuid_entry2 *best;

best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); - if (best && (best->ebx & bit(X86_FEATURE_IBPB))) + if (best && (best->ebx & bit(X86_FEATURE_AMD_IBPB))) return true; best = kvm_find_cpuid_entry(vcpu, 7, 0); return best && (best->edx & bit(X86_FEATURE_SPEC_CTRL)); }

-static inline bool guest_cpuid_has_ibrs(struct kvm_vcpu *vcpu) +static inline bool guest_cpuid_has_spec_ctrl(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best;

best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); - if (best && (best->ebx & bit(X86_FEATURE_IBRS))) + if (best && (best->ebx & bit(X86_FEATURE_AMD_IBRS))) return true; best = kvm_find_cpuid_entry(vcpu, 7, 0); - return best && (best->edx & bit(X86_FEATURE_SPEC_CTRL)); + return best && (best->edx & (bit(X86_FEATURE_SPEC_CTRL) | bit(X86_FEATURE_SSBD))); }

static inline bool guest_cpuid_has_arch_capabilities(struct kvm_vcpu *vcpu) @@ -190,6 +190,15 @@ static inline bool guest_cpuid_has_arch_capabilities(struct kvm_vcpu *vcpu) return best && (best->edx & bit(X86_FEATURE_ARCH_CAPABILITIES)); }

+static inline bool guest_cpuid_has_virt_ssbd(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); + return best && (best->ebx & bit(X86_FEATURE_VIRT_SSBD)); +} + +

/* * NRIPS is provided through cpuidfn 0x8000000a.edx bit 3 diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index aaa93b4b0380..a27f9e442ffc 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -45,7 +45,7 @@ #include <asm/kvm_para.h> #include <asm/irq_remapping.h> #include <asm/microcode.h> -#include <asm/nospec-branch.h> +#include <asm/spec-ctrl.h>

#include <asm/virtext.h> #include "trace.h" @@ -185,6 +185,12 @@ struct vcpu_svm { } host;

u64 spec_ctrl; + /* + * Contains guest-controlled bits of VIRT_SPEC_CTRL, which will be + * translated into the appropriate L2_CFG bits on the host to + * perform speculative control. + */ + u64 virt_spec_ctrl;

u32 *msrpm;

@@ -1561,6 +1567,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) u32 eax = 1;

svm->spec_ctrl = 0; + svm->virt_spec_ctrl = 0;

if (!init_event) { svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | @@ -3545,11 +3552,18 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has_ibrs(vcpu)) + !guest_cpuid_has_spec_ctrl(vcpu)) return 1;

msr_info->data = svm->spec_ctrl; break; + case MSR_AMD64_VIRT_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has_virt_ssbd(vcpu)) + return 1; + + msr_info->data = svm->virt_spec_ctrl; + break; case MSR_IA32_UCODE_REV: msr_info->data = 0x01000065; break; @@ -3643,7 +3657,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_IA32_SPEC_CTRL: if (!msr->host_initiated && - !guest_cpuid_has_ibrs(vcpu)) + !guest_cpuid_has_spec_ctrl(vcpu)) return 1;

/* The STIBP bit doesn't fault even if it's not advertised */ @@ -3684,6 +3698,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); break; + case MSR_AMD64_VIRT_SPEC_CTRL: + if (!msr->host_initiated && + !guest_cpuid_has_virt_ssbd(vcpu)) + return 1; + + if (data & ~SPEC_CTRL_SSBD) + return 1; + + svm->virt_spec_ctrl = data; + break; case MSR_STAR: svm->vmcb->save.star = data; break; @@ -4917,8 +4941,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) * is no need to worry about the conditional branch over the wrmsr * being speculatively taken. */ - if (svm->spec_ctrl) - native_wrmsrl(MSR_IA32_SPEC_CTRL, svm->spec_ctrl); + x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl);

asm volatile ( "push %%" _ASM_BP "; \n\t" @@ -5012,6 +5035,18 @@ 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 + loadsegment(fs, svm->host.fs); +#ifndef CONFIG_X86_32_LAZY_GS + loadsegment(gs, svm->host.gs); +#endif +#endif + /* * We do not use IBRS in the kernel. If this vCPU has used the * SPEC_CTRL MSR it may have left it on; save the value and @@ -5030,20 +5065,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);

- if (svm->spec_ctrl) - native_wrmsrl(MSR_IA32_SPEC_CTRL, 0); - - /* Eliminate branch target predictions from guest mode */ - vmexit_fill_RSB(); - -#ifdef CONFIG_X86_64 - wrmsrl(MSR_GS_BASE, svm->host.gs_base); -#else - loadsegment(fs, svm->host.fs); -#ifndef CONFIG_X86_32_LAZY_GS - loadsegment(gs, svm->host.gs); -#endif -#endif + x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl);

reload_tss(vcpu);

@@ -5145,7 +5167,7 @@ static bool svm_cpu_has_accelerated_tpr(void) return false; }

-static bool svm_has_high_real_mode_segbase(void) +static bool svm_has_emulated_msr(int index) { return true; } @@ -5462,7 +5484,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .hardware_enable = svm_hardware_enable, .hardware_disable = svm_hardware_disable, .cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr, - .cpu_has_high_real_mode_segbase = svm_has_high_real_mode_segbase, + .has_emulated_msr = svm_has_emulated_msr,

.vcpu_create = svm_create_vcpu, .vcpu_free = svm_free_vcpu, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index b978aeccda78..d92523afb425 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -50,7 +50,7 @@ #include <asm/apic.h> #include <asm/irq_remapping.h> #include <asm/microcode.h> -#include <asm/nospec-branch.h> +#include <asm/spec-ctrl.h>

#include "trace.h" #include "pmu.h" @@ -3020,7 +3020,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has_ibrs(vcpu)) + !guest_cpuid_has_spec_ctrl(vcpu)) return 1;

msr_info->data = to_vmx(vcpu)->spec_ctrl; @@ -3137,11 +3137,11 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has_ibrs(vcpu)) + !guest_cpuid_has_spec_ctrl(vcpu)) return 1;

/* The STIBP bit doesn't fault even if it's not advertised */ - if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP)) + if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD)) return 1;

vmx->spec_ctrl = data; @@ -8691,9 +8691,21 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) } }

-static bool vmx_has_high_real_mode_segbase(void) +static bool vmx_has_emulated_msr(int index) { - return enable_unrestricted_guest || emulate_invalid_guest_state; + switch (index) { + case MSR_IA32_SMBASE: + /* + * We cannot do SMM unless we can run the guest in big + * real mode. + */ + return enable_unrestricted_guest || emulate_invalid_guest_state; + case MSR_AMD64_VIRT_SPEC_CTRL: + /* This is AMD only. */ + return false; + default: + return true; + } }

static bool vmx_mpx_supported(void) @@ -8916,10 +8928,10 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * is no need to worry about the conditional branch over the wrmsr * being speculatively taken. */ - if (vmx->spec_ctrl) - native_wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl); + x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);

vmx->__launched = vmx->loaded_vmcs->launched; + asm( /* Store host registers */ "push %%" _ASM_DX "; push %%" _ASM_BP ";" @@ -9055,8 +9067,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);

- if (vmx->spec_ctrl) - native_wrmsrl(MSR_IA32_SPEC_CTRL, 0); + x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);

/* Eliminate branch target predictions from guest mode */ vmexit_fill_RSB(); @@ -11347,7 +11358,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .hardware_enable = hardware_enable, .hardware_disable = hardware_disable, .cpu_has_accelerated_tpr = report_flexpriority, - .cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase, + .has_emulated_msr = vmx_has_emulated_msr,

.vcpu_create = vmx_create_vcpu, .vcpu_free = vmx_free_vcpu, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3aaaf305420d..a0cb85f30c94 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1002,6 +1002,7 @@ static u32 emulated_msrs[] = { MSR_IA32_MCG_CTL, MSR_IA32_MCG_EXT_CTL, MSR_IA32_SMBASE, + MSR_AMD64_VIRT_SPEC_CTRL, };

static unsigned num_emulated_msrs; @@ -2664,7 +2665,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) * fringe case that is not enabled except via specific settings * of the module parameters. */ - r = kvm_x86_ops->cpu_has_high_real_mode_segbase(); + r = kvm_x86_ops->has_emulated_msr(MSR_IA32_SMBASE); break; case KVM_CAP_COALESCED_MMIO: r = KVM_COALESCED_MMIO_PAGE_OFFSET; @@ -4226,14 +4227,8 @@ static void kvm_init_msr_list(void) num_msrs_to_save = j;

for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) { - switch (emulated_msrs[i]) { - case MSR_IA32_SMBASE: - if (!kvm_x86_ops->cpu_has_high_real_mode_segbase()) - continue; - break; - default: - break; - } + if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i])) + continue;

if (j < i) emulated_msrs[j] = emulated_msrs[i]; diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index f88ce0e5efd9..0bbec041c003 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -95,26 +95,27 @@ int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey */ if (pkey != -1) return pkey; - /* - * Look for a protection-key-drive execute-only mapping - * which is now being given permissions that are not - * execute-only. Move it back to the default pkey. - */ - if (vma_is_pkey_exec_only(vma) && - (prot & (PROT_READ|PROT_WRITE))) { - return 0; - } + /* * The mapping is execute-only. Go try to get the * execute-only protection key. If we fail to do that, * fall through as if we do not have execute-only - * support. + * support in this mm. */ if (prot == PROT_EXEC) { pkey = execute_only_pkey(vma->vm_mm); if (pkey > 0) return pkey; + } else if (vma_is_pkey_exec_only(vma)) { + /* + * Protections are *not* PROT_EXEC, but the mapping + * is using the exec-only pkey. This mapping was + * PROT_EXEC and will no longer be. Move back to + * the default pkey. + */ + return ARCH_DEFAULT_PKEY; } + /* * This is a vanilla, non-pkey mprotect (or we failed to * setup execute-only), inherit the pkey from the VMA we diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 2bea87cc0ff2..081437b5f381 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1977,10 +1977,8 @@ EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);

static void xen_set_cpu_features(struct cpuinfo_x86 *c) { - if (xen_pv_domain()) { - clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); + if (xen_pv_domain()) set_cpu_cap(c, X86_FEATURE_XENPV); - } }

static void xen_pin_vcpu(int cpu) diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 418f1b8576cf..c92f75f7ae33 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1317,8 +1317,6 @@ void xen_flush_tlb_all(void) struct mmuext_op *op; struct multicall_space mcs;

- trace_xen_mmu_flush_tlb_all(0); - preempt_disable();

mcs = xen_mc_entry(sizeof(*op)); @@ -1336,8 +1334,6 @@ static void xen_flush_tlb(void) struct mmuext_op *op; struct multicall_space mcs;

- trace_xen_mmu_flush_tlb(0); - preempt_disable();

mcs = xen_mc_entry(sizeof(*op)); diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 56b6c8508a89..cbb1cc6bbdb4 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -519,14 +519,22 @@ ssize_t __weak cpu_show_spectre_v2(struct device *dev, return sprintf(buf, "Not affected\n"); }

+ssize_t __weak cpu_show_spec_store_bypass(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 DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL);

static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, &dev_attr_spectre_v1.attr, &dev_attr_spectre_v2.attr, + &dev_attr_spec_store_bypass.attr, NULL };

diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c index 340e037b3224..884c1ec61ac9 100644 --- a/drivers/i2c/busses/i2c-designware-core.c +++ b/drivers/i2c/busses/i2c-designware-core.c @@ -507,7 +507,10 @@ static void i2c_dw_xfer_init(struct dw_i2c_dev *dev) i2c_dw_disable_int(dev);

/* Enable the adapter */ - __i2c_dw_enable_and_wait(dev, true); + __i2c_dw_enable(dev, true); + + /* Dummy read to avoid the register getting stuck on Bay Trail */ + dw_readl(dev, DW_IC_ENABLE_STATUS);

/* Clear and enable interrupts */ dw_readl(dev, DW_IC_CLR_INTR); diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c index 48b3866a9ded..35286907c636 100644 --- a/drivers/s390/cio/qdio_setup.c +++ b/drivers/s390/cio/qdio_setup.c @@ -140,7 +140,7 @@ static int __qdio_allocate_qs(struct qdio_q **irq_ptr_qs, int nr_queues) int i;

for (i = 0; i < nr_queues; i++) { - q = kmem_cache_alloc(qdio_q_cache, GFP_KERNEL); + q = kmem_cache_zalloc(qdio_q_cache, GFP_KERNEL); if (!q) return -ENOMEM;

@@ -456,7 +456,6 @@ int qdio_setup_irq(struct qdio_initialize *init_data) { struct ciw *ciw; struct qdio_irq *irq_ptr = init_data->cdev->private->qdio_data; - int rc;

memset(&irq_ptr->qib, 0, sizeof(irq_ptr->qib)); memset(&irq_ptr->siga_flag, 0, sizeof(irq_ptr->siga_flag)); @@ -493,16 +492,14 @@ int qdio_setup_irq(struct qdio_initialize *init_data) ciw = ccw_device_get_ciw(init_data->cdev, CIW_TYPE_EQUEUE); if (!ciw) { DBF_ERROR("%4x NO EQ", irq_ptr->schid.sch_no); - rc = -EINVAL; - goto out_err; + return -EINVAL; } irq_ptr->equeue = *ciw;

ciw = ccw_device_get_ciw(init_data->cdev, CIW_TYPE_AQUEUE); if (!ciw) { DBF_ERROR("%4x NO AQ", irq_ptr->schid.sch_no); - rc = -EINVAL; - goto out_err; + return -EINVAL; } irq_ptr->aqueue = *ciw;

@@ -510,9 +507,6 @@ int qdio_setup_irq(struct qdio_initialize *init_data) irq_ptr->orig_handler = init_data->cdev->handler; init_data->cdev->handler = qdio_int_handler; return 0; -out_err: - qdio_release_memory(irq_ptr); - return rc; }

void qdio_print_subchannel_info(struct qdio_irq *irq_ptr, diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index 7d629b4e1ecc..adc3f56d4773 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -514,7 +514,7 @@ static int bcm_qspi_bspi_set_mode(struct bcm_qspi *qspi,

static void bcm_qspi_enable_bspi(struct bcm_qspi *qspi) { - if (!has_bspi(qspi) || (qspi->bspi_enabled)) + if (!has_bspi(qspi)) return;

qspi->bspi_enabled = 1; @@ -529,7 +529,7 @@ static void bcm_qspi_enable_bspi(struct bcm_qspi *qspi)

static void bcm_qspi_disable_bspi(struct bcm_qspi *qspi) { - if (!has_bspi(qspi) || (!qspi->bspi_enabled)) + if (!has_bspi(qspi)) return;

qspi->bspi_enabled = 0; @@ -543,16 +543,19 @@ static void bcm_qspi_disable_bspi(struct bcm_qspi *qspi)

static void bcm_qspi_chip_select(struct bcm_qspi *qspi, int cs) { - u32 data = 0; + u32 rd = 0; + u32 wr = 0;

- if (qspi->curr_cs == cs) - return; if (qspi->base[CHIP_SELECT]) { - data = bcm_qspi_read(qspi, CHIP_SELECT, 0); - data = (data & ~0xff) | (1 << cs); - bcm_qspi_write(qspi, CHIP_SELECT, 0, data); + rd = bcm_qspi_read(qspi, CHIP_SELECT, 0); + wr = (rd & ~0xff) | (1 << cs); + if (rd == wr) + return; + bcm_qspi_write(qspi, CHIP_SELECT, 0, wr); usleep_range(10, 20); } + + dev_dbg(&qspi->pdev->dev, "using cs:%d\n", cs); qspi->curr_cs = cs; }

@@ -770,8 +773,13 @@ static int write_to_hw(struct bcm_qspi *qspi, struct spi_device *spi) dev_dbg(&qspi->pdev->dev, "WR %04x\n", val); } mspi_cdram = MSPI_CDRAM_CONT_BIT; - mspi_cdram |= (~(1 << spi->chip_select) & - MSPI_CDRAM_PCS); + + if (has_bspi(qspi)) + mspi_cdram &= ~1; + else + mspi_cdram |= (~(1 << spi->chip_select) & + MSPI_CDRAM_PCS); + mspi_cdram |= ((tp.trans->bits_per_word <= 8) ? 0 : MSPI_CDRAM_BITSE_BIT);

diff --git a/drivers/spi/spi-pxa2xx.h b/drivers/spi/spi-pxa2xx.h index ce31b8199bb3..b8e004d1467b 100644 --- a/drivers/spi/spi-pxa2xx.h +++ b/drivers/spi/spi-pxa2xx.h @@ -38,7 +38,7 @@ struct driver_data {

/* SSP register addresses */ void __iomem *ioaddr; - u32 ssdr_physical; + phys_addr_t ssdr_physical;

/* SSP masks*/ u32 dma_cr1; diff --git a/drivers/usb/usbip/stub.h b/drivers/usb/usbip/stub.h index 910f027773aa..84c0599b45b7 100644 --- a/drivers/usb/usbip/stub.h +++ b/drivers/usb/usbip/stub.h @@ -87,6 +87,7 @@ struct bus_id_priv { struct stub_device *sdev; struct usb_device *udev; char shutdown_busid; + spinlock_t busid_lock; };

/* stub_priv is allocated from stub_priv_cache */ @@ -97,6 +98,7 @@ extern struct usb_device_driver stub_driver;

/* stub_main.c */ struct bus_id_priv *get_busid_priv(const char *busid); +void put_busid_priv(struct bus_id_priv *bid); int del_match_busid(char *busid); void stub_device_cleanup_urbs(struct stub_device *sdev);

diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c index 3550224f4d69..8e629b6a6f3f 100644 --- a/drivers/usb/usbip/stub_dev.c +++ b/drivers/usb/usbip/stub_dev.c @@ -314,9 +314,9 @@ static int stub_probe(struct usb_device *udev) struct stub_device *sdev = NULL; const char *udev_busid = dev_name(&udev->dev); struct bus_id_priv *busid_priv; - int rc; + int rc = 0;

- dev_dbg(&udev->dev, "Enter\n"); + dev_dbg(&udev->dev, "Enter probe\n");

/* check we should claim or not by busid_table */ busid_priv = get_busid_priv(udev_busid); @@ -331,13 +331,15 @@ static int stub_probe(struct usb_device *udev) * other matched drivers by the driver core. * See driver_probe_device() in driver/base/dd.c */ - return -ENODEV; + rc = -ENODEV; + goto call_put_busid_priv; }

if (udev->descriptor.bDeviceClass == USB_CLASS_HUB) { dev_dbg(&udev->dev, "%s is a usb hub device... skip!\n", udev_busid); - return -ENODEV; + rc = -ENODEV; + goto call_put_busid_priv; }

if (!strcmp(udev->bus->bus_name, "vhci_hcd")) { @@ -345,13 +347,16 @@ static int stub_probe(struct usb_device *udev) "%s is attached on vhci_hcd... skip!\n", udev_busid);

- return -ENODEV; + rc = -ENODEV; + goto call_put_busid_priv; }

/* ok, this is my device */ sdev = stub_device_alloc(udev); - if (!sdev) - return -ENOMEM; + if (!sdev) { + rc = -ENOMEM; + goto call_put_busid_priv; + }

dev_info(&udev->dev, "usbip-host: register new device (bus %u dev %u)\n", @@ -383,7 +388,9 @@ static int stub_probe(struct usb_device *udev) } busid_priv->status = STUB_BUSID_ALLOC;

- return 0; + rc = 0; + goto call_put_busid_priv; + err_files: usb_hub_release_port(udev->parent, udev->portnum, (struct usb_dev_state *) udev); @@ -393,6 +400,9 @@ static int stub_probe(struct usb_device *udev)

busid_priv->sdev = NULL; stub_device_free(sdev); + +call_put_busid_priv: + put_busid_priv(busid_priv); return rc; }

@@ -418,7 +428,7 @@ static void stub_disconnect(struct usb_device *udev) struct bus_id_priv *busid_priv; int rc;

- dev_dbg(&udev->dev, "Enter\n"); + dev_dbg(&udev->dev, "Enter disconnect\n");

busid_priv = get_busid_priv(udev_busid); if (!busid_priv) { @@ -431,7 +441,7 @@ static void stub_disconnect(struct usb_device *udev) /* get stub_device */ if (!sdev) { dev_err(&udev->dev, "could not get device"); - return; + goto call_put_busid_priv; }

dev_set_drvdata(&udev->dev, NULL); @@ -446,12 +456,12 @@ static void stub_disconnect(struct usb_device *udev) (struct usb_dev_state *) udev); if (rc) { dev_dbg(&udev->dev, "unable to release port\n"); - return; + goto call_put_busid_priv; }

/* If usb reset is called from event handler */ if (usbip_in_eh(current)) - return; + goto call_put_busid_priv;

/* shutdown the current connection */ shutdown_busid(busid_priv); @@ -462,12 +472,11 @@ static void stub_disconnect(struct usb_device *udev) busid_priv->sdev = NULL; stub_device_free(sdev);

- if (busid_priv->status == STUB_BUSID_ALLOC) { + if (busid_priv->status == STUB_BUSID_ALLOC) busid_priv->status = STUB_BUSID_ADDED; - } else { - busid_priv->status = STUB_BUSID_OTHER; - del_match_busid((char *)udev_busid); - } + +call_put_busid_priv: + put_busid_priv(busid_priv); }

#ifdef CONFIG_PM diff --git a/drivers/usb/usbip/stub_main.c b/drivers/usb/usbip/stub_main.c index f761e02e75c9..fa90496ca7a8 100644 --- a/drivers/usb/usbip/stub_main.c +++ b/drivers/usb/usbip/stub_main.c @@ -28,6 +28,7 @@ #define DRIVER_DESC "USB/IP Host Driver"

struct kmem_cache *stub_priv_cache; + /* * busid_tables defines matching busids that usbip can grab. A user can change * dynamically what device is locally used and what device is exported to a @@ -39,6 +40,8 @@ static spinlock_t busid_table_lock;

static void init_busid_table(void) { + int i; + /* * This also sets the bus_table[i].status to * STUB_BUSID_OTHER, which is 0. @@ -46,6 +49,9 @@ static void init_busid_table(void) memset(busid_table, 0, sizeof(busid_table));

spin_lock_init(&busid_table_lock); + + for (i = 0; i < MAX_BUSID; i++) + spin_lock_init(&busid_table[i].busid_lock); }

/* @@ -57,15 +63,20 @@ static int get_busid_idx(const char *busid) int i; int idx = -1;

- for (i = 0; i < MAX_BUSID; i++) + for (i = 0; i < MAX_BUSID; i++) { + spin_lock(&busid_table[i].busid_lock); if (busid_table[i].name[0]) if (!strncmp(busid_table[i].name, busid, BUSID_SIZE)) { idx = i; + spin_unlock(&busid_table[i].busid_lock); break; } + spin_unlock(&busid_table[i].busid_lock); + } return idx; }

+/* Returns holding busid_lock. Should call put_busid_priv() to unlock */ struct bus_id_priv *get_busid_priv(const char *busid) { int idx; @@ -73,13 +84,22 @@ struct bus_id_priv *get_busid_priv(const char *busid)

spin_lock(&busid_table_lock); idx = get_busid_idx(busid); - if (idx >= 0) + if (idx >= 0) { bid = &(busid_table[idx]); + /* get busid_lock before returning */ + spin_lock(&bid->busid_lock); + } spin_unlock(&busid_table_lock);

return bid; }

+void put_busid_priv(struct bus_id_priv *bid) +{ + if (bid) + spin_unlock(&bid->busid_lock); +} + static int add_match_busid(char *busid) { int i; @@ -92,15 +112,19 @@ static int add_match_busid(char *busid) goto out; }

- for (i = 0; i < MAX_BUSID; i++) + for (i = 0; i < MAX_BUSID; i++) { + spin_lock(&busid_table[i].busid_lock); if (!busid_table[i].name[0]) { strlcpy(busid_table[i].name, busid, BUSID_SIZE); if ((busid_table[i].status != STUB_BUSID_ALLOC) && (busid_table[i].status != STUB_BUSID_REMOV)) busid_table[i].status = STUB_BUSID_ADDED; ret = 0; + spin_unlock(&busid_table[i].busid_lock); break; } + spin_unlock(&busid_table[i].busid_lock); + }

out: spin_unlock(&busid_table_lock); @@ -121,6 +145,8 @@ int del_match_busid(char *busid) /* found */ ret = 0;

+ spin_lock(&busid_table[idx].busid_lock); + if (busid_table[idx].status == STUB_BUSID_OTHER) memset(busid_table[idx].name, 0, BUSID_SIZE);

@@ -128,6 +154,7 @@ int del_match_busid(char *busid) (busid_table[idx].status != STUB_BUSID_ADDED)) busid_table[idx].status = STUB_BUSID_REMOV;

+ spin_unlock(&busid_table[idx].busid_lock); out: spin_unlock(&busid_table_lock);

@@ -140,9 +167,12 @@ static ssize_t show_match_busid(struct device_driver *drv, char *buf) char *out = buf;

spin_lock(&busid_table_lock); - for (i = 0; i < MAX_BUSID; i++) + for (i = 0; i < MAX_BUSID; i++) { + spin_lock(&busid_table[i].busid_lock); if (busid_table[i].name[0]) out += sprintf(out, "%s ", busid_table[i].name); + spin_unlock(&busid_table[i].busid_lock); + } spin_unlock(&busid_table_lock); out += sprintf(out, "\n");

@@ -184,6 +214,51 @@ static ssize_t store_match_busid(struct device_driver *dev, const char *buf, static DRIVER_ATTR(match_busid, S_IRUSR | S_IWUSR, show_match_busid, store_match_busid);

+static int do_rebind(char *busid, struct bus_id_priv *busid_priv) +{ + int ret; + + /* device_attach() callers should hold parent lock for USB */ + if (busid_priv->udev->dev.parent) + device_lock(busid_priv->udev->dev.parent); + ret = device_attach(&busid_priv->udev->dev); + if (busid_priv->udev->dev.parent) + device_unlock(busid_priv->udev->dev.parent); + if (ret < 0) { + dev_err(&busid_priv->udev->dev, "rebind failed\n"); + return ret; + } + return 0; +} + +static void stub_device_rebind(void) +{ +#if IS_MODULE(CONFIG_USBIP_HOST) + struct bus_id_priv *busid_priv; + int i; + + /* update status to STUB_BUSID_OTHER so probe ignores the device */ + spin_lock(&busid_table_lock); + for (i = 0; i < MAX_BUSID; i++) { + if (busid_table[i].name[0] && + busid_table[i].shutdown_busid) { + busid_priv = &(busid_table[i]); + busid_priv->status = STUB_BUSID_OTHER; + } + } + spin_unlock(&busid_table_lock); + + /* now run rebind - no need to hold locks. driver files are removed */ + for (i = 0; i < MAX_BUSID; i++) { + if (busid_table[i].name[0] && + busid_table[i].shutdown_busid) { + busid_priv = &(busid_table[i]); + do_rebind(busid_table[i].name, busid_priv); + } + } +#endif +} + static ssize_t rebind_store(struct device_driver *dev, const char *buf, size_t count) { @@ -201,16 +276,17 @@ static ssize_t rebind_store(struct device_driver *dev, const char *buf, if (!bid) return -ENODEV;

- /* device_attach() callers should hold parent lock for USB */ - if (bid->udev->dev.parent) - device_lock(bid->udev->dev.parent); - ret = device_attach(&bid->udev->dev); - if (bid->udev->dev.parent) - device_unlock(bid->udev->dev.parent); - if (ret < 0) { - dev_err(&bid->udev->dev, "rebind failed\n"); + /* mark the device for deletion so probe ignores it during rescan */ + bid->status = STUB_BUSID_OTHER; + /* release the busid lock */ + put_busid_priv(bid); + + ret = do_rebind((char *) buf, bid); + if (ret < 0) return ret; - } + + /* delete device from busid_table */ + del_match_busid((char *) buf);

return count; } @@ -333,6 +409,9 @@ static void __exit usbip_host_exit(void) */ usb_deregister_device_driver(&stub_driver);

+ /* initiate scan to attach devices */ + stub_device_rebind(); + kmem_cache_destroy(stub_priv_cache); }

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index f6ba165d3f81..409b12392474 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2486,10 +2486,8 @@ read_block_for_search(struct btrfs_trans_handle *trans, if (p->reada != READA_NONE) reada_for_search(root, p, level, slot, key->objectid);

- btrfs_release_path(p); - ret = -EAGAIN; - tmp = read_tree_block(root, blocknr, 0); + tmp = read_tree_block(root, blocknr, gen); if (!IS_ERR(tmp)) { /* * If the read above didn't mark this buffer up to date, @@ -2503,6 +2501,8 @@ read_block_for_search(struct btrfs_trans_handle *trans, } else { ret = PTR_ERR(tmp); } + + btrfs_release_path(p); return ret; }

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 52401732cddc..c65350e5119c 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4614,6 +4614,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; u64 logged_isize = 0; bool need_log_inode_item = true; + bool xattrs_logged = false;

path = btrfs_alloc_path(); if (!path) @@ -4918,6 +4919,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, err = btrfs_log_all_xattrs(trans, root, inode, path, dst_path); if (err) goto out_unlock; + xattrs_logged = true; if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) { btrfs_release_path(path); btrfs_release_path(dst_path); @@ -4930,6 +4932,11 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, btrfs_release_path(dst_path); if (need_log_inode_item) { err = log_inode_item(trans, log, dst_path, inode); + if (!err && !xattrs_logged) { + err = btrfs_log_all_xattrs(trans, root, inode, path, + dst_path); + btrfs_release_path(path); + } if (err) goto out_unlock; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 4730ba2cc049..c2495cde26f6 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3966,6 +3966,15 @@ int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info) return 0; }

+ /* + * A ro->rw remount sequence should continue with the paused balance + * regardless of who pauses it, system or the user as of now, so set + * the resume flag. + */ + spin_lock(&fs_info->balance_lock); + fs_info->balance_ctl->flags |= BTRFS_BALANCE_RESUME; + spin_unlock(&fs_info->balance_lock); + tsk = kthread_run(balance_kthread, fs_info, "btrfs-balance"); return PTR_ERR_OR_ZERO(tsk); } diff --git a/fs/proc/array.c b/fs/proc/array.c index 794b52a6c20d..94f83e74db24 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -80,6 +80,7 @@ #include <linux/delayacct.h> #include <linux/seq_file.h> #include <linux/pid_namespace.h> +#include <linux/prctl.h> #include <linux/ptrace.h> #include <linux/tracehook.h> #include <linux/string_helpers.h> @@ -345,8 +346,32 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p) { #ifdef CONFIG_SECCOMP seq_put_decimal_ull(m, "Seccomp:\t", p->seccomp.mode); - seq_putc(m, '\n'); #endif + seq_printf(m, "\nSpeculation_Store_Bypass:\t"); + switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) { + case -EINVAL: + seq_printf(m, "unknown"); + break; + case PR_SPEC_NOT_AFFECTED: + seq_printf(m, "not vulnerable"); + break; + case PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE: + seq_printf(m, "thread force mitigated"); + break; + case PR_SPEC_PRCTL | PR_SPEC_DISABLE: + seq_printf(m, "thread mitigated"); + break; + case PR_SPEC_PRCTL | PR_SPEC_ENABLE: + seq_printf(m, "thread vulnerable"); + break; + case PR_SPEC_DISABLE: + seq_printf(m, "globally mitigated"); + break; + default: + seq_printf(m, "vulnerable"); + break; + } + seq_putc(m, '\n'); }

static inline void task_context_switch_counts(struct seq_file *m, diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 2f475ad89a0d..917829b27350 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -50,6 +50,8 @@ 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 ssize_t cpu_show_spec_store_bypass(struct device *dev, + struct device_attribute *attr, char *buf);

extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/include/linux/efi.h b/include/linux/efi.h index cba7177cbec7..80b1b8faf503 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -380,8 +380,8 @@ typedef struct { u32 attributes; u32 get_bar_attributes; u32 set_bar_attributes; - uint64_t romsize; - void *romimage; + u64 romsize; + u32 romimage; } efi_pci_io_protocol_32;

typedef struct { @@ -400,8 +400,8 @@ typedef struct { u64 attributes; u64 get_bar_attributes; u64 set_bar_attributes; - uint64_t romsize; - void *romimage; + u64 romsize; + u64 romimage; } efi_pci_io_protocol_64;

typedef struct { diff --git a/include/linux/nospec.h b/include/linux/nospec.h index e791ebc65c9c..0c5ef54fd416 100644 --- a/include/linux/nospec.h +++ b/include/linux/nospec.h @@ -7,6 +7,8 @@ #define _LINUX_NOSPEC_H #include <asm/barrier.h>

+struct task_struct; + /** * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise * @index: array element index @@ -55,4 +57,12 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, \ (typeof(_i)) (_i & _mask); \ }) + +/* Speculation control prctl */ +int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which); +int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, + unsigned long ctrl); +/* Speculation control for seccomp enforced mitigation */ +void arch_seccomp_spec_mitigate(struct task_struct *task); + #endif /* _LINUX_NOSPEC_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index c549c8c9245c..5ebef8c86c26 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2354,6 +2354,8 @@ static inline void memalloc_noio_restore(unsigned int flags) #define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ #define PFA_LMK_WAITING 3 /* Lowmemorykiller is waiting */ +#define PFA_SPEC_SSB_DISABLE 4 /* Speculative Store Bypass disabled */ +#define PFA_SPEC_SSB_FORCE_DISABLE 5 /* Speculative Store Bypass force disabled*/

#define TASK_PFA_TEST(name, func) \ @@ -2380,6 +2382,13 @@ TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab) TASK_PFA_TEST(LMK_WAITING, lmk_waiting) TASK_PFA_SET(LMK_WAITING, lmk_waiting)

+TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable) +TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable) +TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) + +TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) +TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) + /* * task->jobctl flags */ diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index ecc296c137cd..50c460a956f1 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -3,7 +3,8 @@

#include <uapi/linux/seccomp.h>

-#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC) +#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \ + SECCOMP_FILTER_FLAG_SPEC_ALLOW)

#ifdef CONFIG_SECCOMP

diff --git a/include/linux/signal.h b/include/linux/signal.h index b63f63eaa39c..5308304993be 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -97,6 +97,23 @@ static inline int sigisemptyset(sigset_t *set) } }

+static inline int sigequalsets(const sigset_t *set1, const sigset_t *set2) +{ + switch (_NSIG_WORDS) { + case 4: + return (set1->sig[3] == set2->sig[3]) && + (set1->sig[2] == set2->sig[2]) && + (set1->sig[1] == set2->sig[1]) && + (set1->sig[0] == set2->sig[0]); + case 2: + return (set1->sig[1] == set2->sig[1]) && + (set1->sig[0] == set2->sig[0]); + case 1: + return set1->sig[0] == set2->sig[0]; + } + return 0; +} + #define sigmask(sig) (1UL << ((sig) - 1))

#ifndef __HAVE_ARCH_SIG_SETOPS diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h index bce990f5a35d..d6be935caa50 100644 --- a/include/trace/events/xen.h +++ b/include/trace/events/xen.h @@ -377,22 +377,6 @@ DECLARE_EVENT_CLASS(xen_mmu_pgd, DEFINE_XEN_MMU_PGD_EVENT(xen_mmu_pgd_pin); DEFINE_XEN_MMU_PGD_EVENT(xen_mmu_pgd_unpin);

-TRACE_EVENT(xen_mmu_flush_tlb_all, - TP_PROTO(int x), - TP_ARGS(x), - TP_STRUCT__entry(__array(char, x, 0)), - TP_fast_assign((void)x), - TP_printk("%s", "") - ); - -TRACE_EVENT(xen_mmu_flush_tlb, - TP_PROTO(int x), - TP_ARGS(x), - TP_STRUCT__entry(__array(char, x, 0)), - TP_fast_assign((void)x), - TP_printk("%s", "") - ); - TRACE_EVENT(xen_mmu_flush_tlb_single, TP_PROTO(unsigned long addr), TP_ARGS(addr), diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index a8d0759a9e40..64776b72e1eb 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -197,4 +197,16 @@ struct prctl_mm_map { # define PR_CAP_AMBIENT_LOWER 3 # define PR_CAP_AMBIENT_CLEAR_ALL 4

+/* Per task speculation control */ +#define PR_GET_SPECULATION_CTRL 52 +#define PR_SET_SPECULATION_CTRL 53 +/* Speculation control variants */ +# define PR_SPEC_STORE_BYPASS 0 +/* Return and control values for PR_SET/GET_SPECULATION_CTRL */ +# define PR_SPEC_NOT_AFFECTED 0 +# define PR_SPEC_PRCTL (1UL << 0) +# define PR_SPEC_ENABLE (1UL << 1) +# define PR_SPEC_DISABLE (1UL << 2) +# define PR_SPEC_FORCE_DISABLE (1UL << 3) + #endif /* _LINUX_PRCTL_H */ diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index 0f238a43ff1e..e4acb615792b 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -15,7 +15,9 @@ #define SECCOMP_SET_MODE_FILTER 1

/* Valid flags for SECCOMP_SET_MODE_FILTER */ -#define SECCOMP_FILTER_FLAG_TSYNC 1 +#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0) +/* In v4.14+ SECCOMP_FILTER_FLAG_LOG is (1UL << 1) */ +#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2)

/* * All BPF programs must return a 32-bit value. diff --git a/kernel/seccomp.c b/kernel/seccomp.c index af182a6df25b..3975856d476c 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -16,6 +16,8 @@ #include <linux/atomic.h> #include <linux/audit.h> #include <linux/compat.h> +#include <linux/nospec.h> +#include <linux/prctl.h> #include <linux/sched.h> #include <linux/seccomp.h> #include <linux/slab.h> @@ -214,8 +216,11 @@ static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode) return true; }

+void __weak arch_seccomp_spec_mitigate(struct task_struct *task) { } + static inline void seccomp_assign_mode(struct task_struct *task, - unsigned long seccomp_mode) + unsigned long seccomp_mode, + unsigned long flags) { assert_spin_locked(&task->sighand->siglock);

@@ -225,6 +230,9 @@ static inline void seccomp_assign_mode(struct task_struct *task, * filter) is set. */ smp_mb__before_atomic(); + /* Assume default seccomp processes want spec flaw mitigation. */ + if ((flags & SECCOMP_FILTER_FLAG_SPEC_ALLOW) == 0) + arch_seccomp_spec_mitigate(task); set_tsk_thread_flag(task, TIF_SECCOMP); }

@@ -292,7 +300,7 @@ static inline pid_t seccomp_can_sync_threads(void) * without dropping the locks. * */ -static inline void seccomp_sync_threads(void) +static inline void seccomp_sync_threads(unsigned long flags) { struct task_struct *thread, *caller;

@@ -333,7 +341,8 @@ static inline void seccomp_sync_threads(void) * allow one thread to transition the other. */ if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) - seccomp_assign_mode(thread, SECCOMP_MODE_FILTER); + seccomp_assign_mode(thread, SECCOMP_MODE_FILTER, + flags); } }

@@ -452,7 +461,7 @@ static long seccomp_attach_filter(unsigned int flags,

/* Now that the new filter is in place, synchronize to all threads. */ if (flags & SECCOMP_FILTER_FLAG_TSYNC) - seccomp_sync_threads(); + seccomp_sync_threads(flags);

return 0; } @@ -712,7 +721,7 @@ static long seccomp_set_mode_strict(void) #ifdef TIF_NOTSC disable_TSC(); #endif - seccomp_assign_mode(current, seccomp_mode); + seccomp_assign_mode(current, seccomp_mode, 0); ret = 0;

out: @@ -770,7 +779,7 @@ static long seccomp_set_mode_filter(unsigned int flags, /* Do not free the successfully attached filter. */ prepared = NULL;

- seccomp_assign_mode(current, seccomp_mode); + seccomp_assign_mode(current, seccomp_mode, flags); out: spin_unlock_irq(&current->sighand->siglock); if (flags & SECCOMP_FILTER_FLAG_TSYNC) diff --git a/kernel/signal.c b/kernel/signal.c index 7ebe236a5364..17428fec19b0 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2495,6 +2495,13 @@ void __set_current_blocked(const sigset_t *newset) { struct task_struct *tsk = current;

+ /* + * In case the signal mask hasn't changed, there is nothing we need + * to do. The current->blocked shouldn't be modified by other task. + */ + if (sigequalsets(&tsk->blocked, newset)) + return; + spin_lock_irq(&tsk->sighand->siglock); __set_task_blocked(tsk, newset); spin_unlock_irq(&tsk->sighand->siglock); diff --git a/kernel/sys.c b/kernel/sys.c index 89d5be418157..143cd63f1d47 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -53,6 +53,8 @@ #include <linux/uidgid.h> #include <linux/cred.h>

+#include <linux/nospec.h> + #include <linux/kmsg_dump.h> /* Move somewhere else to avoid recompiling? */ #include <generated/utsrelease.h> @@ -2072,6 +2074,17 @@ static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr) } #endif

+int __weak arch_prctl_spec_ctrl_get(struct task_struct *t, unsigned long which) +{ + return -EINVAL; +} + +int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which, + unsigned long ctrl) +{ + return -EINVAL; +} + SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { @@ -2270,6 +2283,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_GET_FP_MODE: error = GET_FP_MODE(me); break; + case PR_GET_SPECULATION_CTRL: + if (arg3 || arg4 || arg5) + return -EINVAL; + error = arch_prctl_spec_ctrl_get(me, arg2); + break; + case PR_SET_SPECULATION_CTRL: + if (arg4 || arg5) + return -EINVAL; + error = arch_prctl_spec_ctrl_set(me, arg2, arg3); + break; default: error = -EINVAL; break; diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index d2a20e83ebae..22d7454b387b 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -610,6 +610,14 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev) now = ktime_get(); /* Find all expired events */ for_each_cpu(cpu, tick_broadcast_oneshot_mask) { + /* + * Required for !SMP because for_each_cpu() reports + * unconditionally CPU0 as set on UP kernels. + */ + if (!IS_ENABLED(CONFIG_SMP) && + cpumask_empty(tick_broadcast_oneshot_mask)) + break; + td = &per_cpu(tick_cpu_device, cpu); if (td->evtdev->next_event.tv64 <= now.tv64) { cpumask_set_cpu(cpu, tmpmask); diff --git a/mm/Kconfig b/mm/Kconfig index 86e3e0e74d20..ea074a9d4958 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -666,6 +666,7 @@ config DEFERRED_STRUCT_PAGE_INIT depends on ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT depends on NO_BOOTMEM && MEMORY_HOTPLUG depends on !FLATMEM + depends on !NEED_PER_CPU_KM help Ordinarily all struct pages are initialised during early boot in a single thread. On very large machines this can take a considerable diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fa3ef25441e5..762f31fb5b67 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2200,41 +2200,46 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, }

if (nlh->nlmsg_flags & NLM_F_REPLACE) { - if (nft_is_active_next(net, old_rule)) { - trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE, - old_rule); - if (trans == NULL) { - err = -ENOMEM; - goto err2; - } - nft_deactivate_next(net, old_rule); - chain->use--; - list_add_tail_rcu(&rule->list, &old_rule->list); - } else { + if (!nft_is_active_next(net, old_rule)) { err = -ENOENT; goto err2; } - } else if (nlh->nlmsg_flags & NLM_F_APPEND) - if (old_rule) - list_add_rcu(&rule->list, &old_rule->list); - else - list_add_tail_rcu(&rule->list, &chain->rules); - else { - if (old_rule) - list_add_tail_rcu(&rule->list, &old_rule->list); - else - list_add_rcu(&rule->list, &chain->rules); - } + trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE, + old_rule); + if (trans == NULL) { + err = -ENOMEM; + goto err2; + } + nft_deactivate_next(net, old_rule); + chain->use--;

- if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) { - err = -ENOMEM; - goto err3; + if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) { + err = -ENOMEM; + goto err2; + } + + list_add_tail_rcu(&rule->list, &old_rule->list); + } else { + if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) { + err = -ENOMEM; + goto err2; + } + + if (nlh->nlmsg_flags & NLM_F_APPEND) { + if (old_rule) + list_add_rcu(&rule->list, &old_rule->list); + else + list_add_tail_rcu(&rule->list, &chain->rules); + } else { + if (old_rule) + list_add_tail_rcu(&rule->list, &old_rule->list); + else + list_add_rcu(&rule->list, &chain->rules); + } } chain->use++; return 0;

-err3: - list_del_rcu(&rule->list); err2: nf_tables_rule_destroy(&ctx, rule); err1: diff --git a/sound/core/control_compat.c b/sound/core/control_compat.c index 1fa70766ffab..84ee29c3b1a0 100644 --- a/sound/core/control_compat.c +++ b/sound/core/control_compat.c @@ -400,8 +400,7 @@ static int snd_ctl_elem_add_compat(struct snd_ctl_file *file, if (copy_from_user(&data->id, &data32->id, sizeof(data->id)) || copy_from_user(&data->type, &data32->type, 3 * sizeof(u32))) goto error; - if (get_user(data->owner, &data32->owner) || - get_user(data->type, &data32->type)) + if (get_user(data->owner, &data32->owner)) goto error; switch (data->type) { case SNDRV_CTL_ELEM_TYPE_BOOLEAN: diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 7d3f88d90eec..4e9112001306 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2061,6 +2061,8 @@ static struct snd_pci_quirk power_save_blacklist[] = { SND_PCI_QUIRK(0x1849, 0x0c0c, "Asrock B85M-ITX", 0), /* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */ SND_PCI_QUIRK(0x1043, 0x8733, "Asus Prime X370-Pro", 0), + /* https://bugzilla.redhat.com/show_bug.cgi?id=1572975 */ + SND_PCI_QUIRK(0x17aa, 0x36a7, "Lenovo C50 All in one", 0), /* https://bugzilla.kernel.org/show_bug.cgi?id=198611 */ SND_PCI_QUIRK(0x17aa, 0x2227, "Lenovo X1 Carbon 3rd Gen", 0), {} diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index dedf8eb4570e..db8404e31fae 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -905,6 +905,14 @@ static void volume_control_quirks(struct usb_mixer_elem_info *cval, } break;

+ case USB_ID(0x0d8c, 0x0103): + if (!strcmp(kctl->id.name, "PCM Playback Volume")) { + usb_audio_info(chip, + "set volume quirk for CM102-A+/102S+\n"); + cval->min = -256; + } + break; + case USB_ID(0x0471, 0x0101): case USB_ID(0x0471, 0x0104): case USB_ID(0x0471, 0x0105): diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index f68998149351..d5be7b5ff899 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -1692,7 +1692,11 @@ TEST_F_SIGNAL(TRACE_syscall, kill_after_ptrace, SIGSYS) #endif

#ifndef SECCOMP_FILTER_FLAG_TSYNC -#define SECCOMP_FILTER_FLAG_TSYNC 1 +#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0) +#endif + +#ifndef SECCOMP_FILTER_FLAG_SPEC_ALLOW +#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2) #endif

#ifndef seccomp @@ -1791,6 +1795,78 @@ TEST(seccomp_syscall_mode_lock) } }

+/* + * Test detection of known and unknown filter flags. Userspace needs to be able + * to check if a filter flag is supported by the current kernel and a good way + * of doing that is by attempting to enter filter mode, with the flag bit in + * question set, and a NULL pointer for the _args_ parameter. EFAULT indicates + * that the flag is valid and EINVAL indicates that the flag is invalid. + */ +TEST(detect_seccomp_filter_flags) +{ + unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC, + SECCOMP_FILTER_FLAG_SPEC_ALLOW }; + unsigned int flag, all_flags; + int i; + long ret; + + /* Test detection of known-good filter flags */ + for (i = 0, all_flags = 0; i < ARRAY_SIZE(flags); i++) { + int bits = 0; + + flag = flags[i]; + /* Make sure the flag is a single bit! */ + while (flag) { + if (flag & 0x1) + bits ++; + flag >>= 1; + } + ASSERT_EQ(1, bits); + flag = flags[i]; + + ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL); + ASSERT_NE(ENOSYS, errno) { + TH_LOG("Kernel does not support seccomp syscall!"); + } + EXPECT_EQ(-1, ret); + EXPECT_EQ(EFAULT, errno) { + TH_LOG("Failed to detect that a known-good filter flag (0x%X) is supported!", + flag); + } + + all_flags |= flag; + } + + /* Test detection of all known-good filter flags */ + ret = seccomp(SECCOMP_SET_MODE_FILTER, all_flags, NULL); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EFAULT, errno) { + TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!", + all_flags); + } + + /* Test detection of an unknown filter flag */ + flag = -1; + ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno) { + TH_LOG("Failed to detect that an unknown filter flag (0x%X) is unsupported!", + flag); + } + + /* + * Test detection of an unknown filter flag that may simply need to be + * added to this test + */ + flag = flags[ARRAY_SIZE(flags) - 1] << 1; + ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno) { + TH_LOG("Failed to detect that an unknown filter flag (0x%X) is unsupported! Does a new flag need to be added to this test?", + flag); + } +} + TEST(TSYNC_first) { struct sock_filter filter[] = { diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 31f562507915..1ebbf233de9a 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -208,8 +208,8 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq, u8 prop; int ret;

- ret = kvm_read_guest(kvm, propbase + irq->intid - GIC_LPI_OFFSET, - &prop, 1); + ret = kvm_read_guest_lock(kvm, propbase + irq->intid - GIC_LPI_OFFSET, + &prop, 1);

if (ret) return ret; @@ -339,8 +339,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) * this very same byte in the last iteration. Reuse that. */ if (byte_offset != last_byte_offset) { - ret = kvm_read_guest(vcpu->kvm, pendbase + byte_offset, - &pendmask, 1); + ret = kvm_read_guest_lock(vcpu->kvm, + pendbase + byte_offset, + &pendmask, 1); if (ret) { kfree(intids); return ret; @@ -628,7 +629,7 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, int id) return false;

/* Each 1st level entry is represented by a 64-bit value. */ - if (kvm_read_guest(its->dev->kvm, + if (kvm_read_guest_lock(its->dev->kvm, BASER_ADDRESS(baser) + index * sizeof(indirect_ptr), &indirect_ptr, sizeof(indirect_ptr))) return false; @@ -1152,8 +1153,8 @@ static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its) cbaser = CBASER_ADDRESS(its->cbaser);

while (its->cwriter != its->creadr) { - int ret = kvm_read_guest(kvm, cbaser + its->creadr, - cmd_buf, ITS_CMD_SIZE); + int ret = kvm_read_guest_lock(kvm, cbaser + its->creadr, + cmd_buf, ITS_CMD_SIZE); /* * If kvm_read_guest() fails, this could be due to the guest * programming a bogus value in CBASER or something else going