diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 4ed63b6cfb15..2e5e0232b8fa 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -453,6 +453,7 @@ 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 Description: Information about CPU vulnerabilities diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 1d1d53f85ddd..9824d049367e 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2647,6 +2647,9 @@ 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. @@ -3997,6 +4000,48 @@ 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/devicetree/bindings/net/marvell-pp2.txt b/Documentation/devicetree/bindings/net/marvell-pp2.txt index 1814fa13f6ab..fc019df0d863 100644 --- a/Documentation/devicetree/bindings/net/marvell-pp2.txt +++ b/Documentation/devicetree/bindings/net/marvell-pp2.txt @@ -21,9 +21,10 @@ Required properties: - main controller clock (for both armada-375-pp2 and armada-7k-pp2) - GOP clock (for both armada-375-pp2 and armada-7k-pp2) - MG clock (only for armada-7k-pp2) + - MG Core clock (only for armada-7k-pp2) - AXI clock (only for armada-7k-pp2) -- clock-names: names of used clocks, must be "pp_clk", "gop_clk", "mg_clk" - and "axi_clk" (the 2 latter only for armada-7k-pp2). +- clock-names: names of used clocks, must be "pp_clk", "gop_clk", "mg_clk", + "mg_core_clk" and "axi_clk" (the 3 latter only for armada-7k-pp2). The ethernet ports are represented by subnodes. At least one port is required. @@ -80,8 +81,8 @@ cpm_ethernet: ethernet@0 { compatible = "marvell,armada-7k-pp22"; reg = <0x0 0x100000>, <0x129000 0xb000>; clocks = <&cpm_syscon0 1 3>, <&cpm_syscon0 1 9>, - <&cpm_syscon0 1 5>, <&cpm_syscon0 1 18>; - clock-names = "pp_clk", "gop_clk", "gp_clk", "axi_clk"; + <&cpm_syscon0 1 5>, <&cpm_syscon0 1 6>, <&cpm_syscon0 1 18>; + clock-names = "pp_clk", "gop_clk", "mg_clk", "mg_core_clk", "axi_clk"; eth0: eth0 { interrupts = , diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst index 7b2eb1b7d4ca..a3233da7fa88 100644 --- a/Documentation/userspace-api/index.rst +++ b/Documentation/userspace-api/index.rst @@ -19,6 +19,7 @@ place where this information is gathered. no_new_privs seccomp_filter unshare + spec_ctrl .. only:: subproject and html diff --git a/Documentation/userspace-api/spec_ctrl.rst b/Documentation/userspace-api/spec_ctrl.rst new file mode 100644 index 000000000000..32f3d55c54b7 --- /dev/null +++ b/Documentation/userspace-api/spec_ctrl.rst @@ -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 33f3c94f02ca..79c191442771 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 16 -SUBLEVEL = 10 +SUBLEVEL = 11 EXTRAVERSION = NAME = Fearless Coyote diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index bc8d4bbd82e2..9342904cccca 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -536,4 +536,14 @@ 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 de1b919404e4..1f0b07aef85b 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -295,6 +295,22 @@ 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 5e3633c24e63..2fe87109ae46 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -417,7 +418,8 @@ 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; @@ -490,6 +492,7 @@ asmlinkage void 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/boot/dts/marvell/armada-cp110.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi index a8af4136dbe7..a97d9245e883 100644 --- a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi @@ -40,9 +40,10 @@ compatible = "marvell,armada-7k-pp22"; reg = <0x0 0x100000>, <0x129000 0xb000>; clocks = <&CP110_LABEL(clk) 1 3>, <&CP110_LABEL(clk) 1 9>, - <&CP110_LABEL(clk) 1 5>, <&CP110_LABEL(clk) 1 18>; + <&CP110_LABEL(clk) 1 5>, <&CP110_LABEL(clk) 1 6>, + <&CP110_LABEL(clk) 1 18>; clock-names = "pp_clk", "gop_clk", - "mg_clk", "axi_clk"; + "mg_clk", "mg_core_clk", "axi_clk"; marvell,system-controller = <&CP110_LABEL(syscon0)>; status = "disabled"; dma-coherent; @@ -143,6 +144,8 @@ #size-cells = <0>; compatible = "marvell,xmdio"; reg = <0x12a600 0x10>; + clocks = <&CP110_LABEL(clk) 1 5>, + <&CP110_LABEL(clk) 1 6>, <&CP110_LABEL(clk) 1 18>; status = "disabled"; }; diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 7faed6e48b46..c2b7a77702e7 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -348,6 +348,22 @@ 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 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 94f2099bceb0..3d17c41074ca 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -176,10 +176,9 @@ 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 1c9ddd7aa5ec..0292d68e7dde 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -753,6 +753,10 @@ 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 886a9115af62..48db9732b684 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -163,7 +163,8 @@ __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: @@ -269,7 +270,8 @@ __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 d554c11e01ff..2464ad88287c 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -198,7 +198,6 @@ #define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ #define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ #define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */ - #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ @@ -207,13 +206,19 @@ #define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ - +#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_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ #define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */ - #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 via LS_CFG MSR */ +#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 */ @@ -274,9 +279,10 @@ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ #define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ -#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 */ @@ -333,6 +339,7 @@ #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) @@ -362,5 +369,6 @@ #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 b605a5b6a30c..4b0539a52c4c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -933,7 +933,7 @@ 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 1de72ce514cd..ed97ef3b48a7 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -192,7 +192,7 @@ 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 c9084dedfcfa..1fce70c0f799 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -42,6 +42,8 @@ #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 */ @@ -68,6 +70,11 @@ #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 @@ -340,6 +347,8 @@ #define MSR_AMD64_SEV_ENABLED_BIT 0 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) +#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 a0ba1ffda0df..851c04b7a092 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -2,6 +2,8 @@ #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, @@ -15,7 +17,7 @@ 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); } @@ -49,13 +51,21 @@ 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 +#include + +/* + * 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 a5d9521bb2cb..2ff2a30a264f 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -79,6 +79,7 @@ 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 */ @@ -105,6 +106,7 @@ struct thread_info { #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #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) @@ -144,7 +146,7 @@ struct thread_info { /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ - (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP) + (_TIF_IO_BITMAP|_TIF_NOCPUID|_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/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index c88e0b127810..b481b95bd8f6 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -14,8 +14,11 @@ #include #define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450 +#define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0 #define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463 #define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 +#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb +#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec /* Protect the PCI config register pairs used for SMN and DF indirect access. */ static DEFINE_MUTEX(smn_mutex); @@ -24,6 +27,7 @@ static u32 *flush_words; static const struct pci_device_id amd_root_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) }, {} }; @@ -39,6 +43,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, {} }; @@ -51,6 +56,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, {} }; diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 8b04234e010b..7685444a106b 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -116,6 +116,7 @@ static void init_x2apic_ldr(void) goto update; } cmsk = cluster_hotplug_mask; + cmsk->clusterid = cluster; cluster_hotplug_mask = NULL; update: this_cpu_write(cluster_masks, cmsk); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f0e6456ca7d3..718fae428124 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -554,6 +555,26 @@ 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_detect_mem_encrypt(struct cpuinfo_x86 *c) @@ -791,6 +812,7 @@ 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. diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index bfca937bdcc3..7416fc206b4a 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -12,8 +12,10 @@ #include #include #include +#include +#include -#include +#include #include #include #include @@ -27,6 +29,27 @@ #include 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) { @@ -37,9 +60,27 @@ 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. @@ -93,7 +134,76 @@ 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; @@ -312,32 +422,289 @@ 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_PTI)) - return sprintf(buf, "Mitigation: PTI\n"); + + switch (bug) { + case X86_BUG_CPU_MELTDOWN: + if (boot_cpu_has(X86_FEATURE_PTI)) + 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 348cf4821240..5f74f94244e1 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -757,17 +757,32 @@ 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) @@ -918,21 +933,55 @@ 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); } /* @@ -982,12 +1031,7 @@ 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); @@ -1347,6 +1391,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) #endif mtrr_ap_init(); validate_apic_and_package_id(c); + x86_spec_ctrl_setup_ap(); } static __init int setup_noclflush(char *arg) diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index e806b11a99af..37672d299e35 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -50,4 +50,6 @@ extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); +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 c3af167d0a70..c895f38a7a5e 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -188,7 +188,10 @@ 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 03408b942adb..30ca2d1a9231 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -38,6 +38,7 @@ #include #include #include +#include /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -278,6 +279,148 @@ static inline void switch_to_bitmap(struct tss_struct *tss, } } +#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) { @@ -309,6 +452,9 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, if ((tifp ^ tifn) & _TIF_NOCPUID) set_cpuid_faulting(!!(tifn & _TIF_NOCPUID)); + + if ((tifp ^ tifn) & _TIF_SSBD) + __speculative_store_bypass_update(tifn); } /* diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 9eb448c7859d..fa093b77689f 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -528,6 +528,7 @@ void set_personality_64bit(void) clear_thread_flag(TIF_X32); /* Pretend that this comes from a 64bit execve */ task_pt_regs(current)->orig_ax = __NR_execve; + current_thread_info()->status &= ~TS_COMPAT; /* Ensure the corresponding mm is not marked. */ if (current->mm) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 12599e55e040..d50bc80f5172 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -77,6 +77,7 @@ #include #include #include +#include /* Number of siblings per CPU package */ int smp_num_siblings = 1; @@ -242,6 +243,8 @@ static void notrace start_secondary(void *unused) */ check_tsc_sync_target(); + speculative_store_bypass_ht_init(); + /* * Lock vector_lock, set CPU online and bring the vector * allocator online. Online must be set with vector_lock held @@ -1257,6 +1260,8 @@ 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 b671fc2d0422..3f400004f602 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -374,7 +374,7 @@ 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 = @@ -402,7 +402,7 @@ 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(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | + F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | F(SSBD) | F(ARCH_CAPABILITIES); /* all calls to cpuid_count() should be made on the same cpu */ @@ -642,13 +642,20 @@ 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/svm.c b/arch/x86/kvm/svm.c index be9c839e2c89..dbbd762359a9 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -50,7 +50,7 @@ #include #include #include -#include +#include #include #include "trace.h" @@ -192,6 +192,12 @@ 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; @@ -1910,6 +1916,7 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.microcode_version = 0x01000065; svm->spec_ctrl = 0; + svm->virt_spec_ctrl = 0; if (!init_event) { svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | @@ -3959,11 +3966,18 @@ 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(vcpu, X86_FEATURE_IBRS)) + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS)) return 1; msr_info->data = svm->spec_ctrl; break; + case MSR_AMD64_VIRT_SPEC_CTRL: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD)) + return 1; + + msr_info->data = svm->virt_spec_ctrl; + break; case MSR_F15H_IC_CFG: { int family, model; @@ -4057,7 +4071,7 @@ 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(vcpu, X86_FEATURE_IBRS)) + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS)) return 1; /* The STIBP bit doesn't fault even if it's not advertised */ @@ -4084,7 +4098,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_IA32_PRED_CMD: if (!msr->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_IBPB)) + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB)) return 1; if (data & ~PRED_CMD_IBPB) @@ -4098,6 +4112,16 @@ 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(vcpu, X86_FEATURE_VIRT_SSBD)) + return 1; + + if (data & ~SPEC_CTRL_SSBD) + return 1; + + svm->virt_spec_ctrl = data; + break; case MSR_STAR: svm->vmcb->save.star = data; break; @@ -5401,8 +5425,7 @@ 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" @@ -5496,6 +5519,18 @@ 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 @@ -5514,20 +5549,7 @@ 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); @@ -5630,7 +5652,7 @@ 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; } @@ -6854,7 +6876,7 @@ 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 657c93409042..3deb153bf9d9 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -52,7 +52,7 @@ #include #include #include -#include +#include #include "trace.h" #include "pmu.h" @@ -1314,6 +1314,12 @@ static inline bool cpu_has_vmx_vmfunc(void) SECONDARY_EXEC_ENABLE_VMFUNC; } +static bool vmx_umip_emulated(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_DESC; +} + static inline bool report_flexpriority(void) { return flexpriority_enabled; @@ -3269,7 +3275,6 @@ 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(vcpu, X86_FEATURE_IBRS) && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) return 1; @@ -3390,12 +3395,11 @@ 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(vcpu, X86_FEATURE_IBRS) && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) 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; @@ -3421,7 +3425,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_PRED_CMD: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_IBPB) && !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) return 1; @@ -4494,14 +4497,16 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) (to_vmx(vcpu)->rmode.vm86_active ? KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON); - if ((cr4 & X86_CR4_UMIP) && !boot_cpu_has(X86_FEATURE_UMIP)) { - vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, - SECONDARY_EXEC_DESC); - hw_cr4 &= ~X86_CR4_UMIP; - } else if (!is_guest_mode(vcpu) || - !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC)) - vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, + if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) { + if (cr4 & X86_CR4_UMIP) { + vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_DESC); + hw_cr4 &= ~X86_CR4_UMIP; + } else if (!is_guest_mode(vcpu) || + !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC)) + vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_DESC); + } if (cr4 & X86_CR4_VMXE) { /* @@ -9226,9 +9231,21 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) } STACK_FRAME_NON_STANDARD(vmx_handle_external_intr); -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) @@ -9243,12 +9260,6 @@ static bool vmx_xsaves_supported(void) SECONDARY_EXEC_XSAVES; } -static bool vmx_umip_emulated(void) -{ - return vmcs_config.cpu_based_2nd_exec_ctrl & - SECONDARY_EXEC_DESC; -} - static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) { u32 exit_intr_info; @@ -9466,10 +9477,10 @@ 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 ";" @@ -9605,8 +9616,7 @@ 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(); @@ -12299,7 +12309,7 @@ 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 18b5ca7a3197..f3df3a934733 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1045,6 +1045,7 @@ static u32 emulated_msrs[] = { MSR_SMI_COUNT, MSR_PLATFORM_INFO, MSR_MISC_FEATURES_ENABLES, + MSR_AMD64_VIRT_SPEC_CTRL, }; static unsigned num_emulated_msrs; @@ -2843,7 +2844,7 @@ 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_VAPIC: r = !kvm_x86_ops->cpu_has_accelerated_tpr(); @@ -4522,14 +4523,8 @@ 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 d7bc0eea20a5..6e98e0a7c923 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -94,26 +94,27 @@ 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/mmu.c b/arch/x86/xen/mmu.c index d33e7dbe3129..2d76106788a3 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -42,13 +42,11 @@ xmaddr_t arbitrary_virt_to_machine(void *vaddr) } EXPORT_SYMBOL_GPL(arbitrary_virt_to_machine); -static void xen_flush_tlb_all(void) +static noinline 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)); diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index aae88fec9941..ac17c206afd1 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1280,13 +1280,11 @@ unsigned long xen_read_cr2_direct(void) return this_cpu_read(xen_vcpu_info.arch.cr2); } -static void xen_flush_tlb(void) +static noinline 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 d21a2d913107..827905794b48 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -532,14 +532,22 @@ 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/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index fb586e09682d..a8bec064d14a 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -20,7 +20,7 @@ config ACPI_CPPC_CPUFREQ config ARM_ARMADA_37XX_CPUFREQ tristate "Armada 37xx CPUFreq support" - depends on ARCH_MVEBU + depends on ARCH_MVEBU && CPUFREQ_DT help This adds the CPUFreq driver support for Marvell Armada 37xx SoCs. The Armada 37xx PMU supports 4 frequency and VDD levels. diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index 9acc1e157813..6d3e01b2bde9 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -716,7 +716,7 @@ static void remove_compat_control_link(struct drm_device *dev) if (!minor) return; - name = kasprintf(GFP_KERNEL, "controlD%d", minor->index); + name = kasprintf(GFP_KERNEL, "controlD%d", minor->index + 64); if (!name) return; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 175d552c8bae..a2917dfd45cd 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -7139,6 +7139,9 @@ enum { #define SLICE_ECO_CHICKEN0 _MMIO(0x7308) #define PIXEL_MASK_CAMMING_DISABLE (1 << 14) +#define GEN9_WM_CHICKEN3 _MMIO(0x5588) +#define GEN9_FACTOR_IN_CLR_VAL_HIZ (1 << 9) + /* WaCatErrorRejectionIssue */ #define GEN7_SQ_CHICKEN_MBCUNIT_CONFIG _MMIO(0x9030) #define GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB (1<<11) diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index fa960cfd2764..02ec078b0979 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -1098,6 +1098,10 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_GPGPU_LEVEL_MASK, GEN9_PREEMPT_GPGPU_COMMAND_LEVEL); + /* WaClearHIZ_WM_CHICKEN3:bxt,glk */ + if (IS_GEN9_LP(dev_priv)) + WA_SET_BIT_MASKED(GEN9_WM_CHICKEN3, GEN9_FACTOR_IN_CLR_VAL_HIZ); + /* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt,glk,cfl */ ret = wa_ring_whitelist_reg(engine, GEN9_CTX_PREEMPT_REG); if (ret) diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index ef23553ff5cb..001a80dfad31 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -272,7 +272,7 @@ config SENSORS_K8TEMP config SENSORS_K10TEMP tristate "AMD Family 10h+ temperature sensor" - depends on X86 && PCI + depends on X86 && PCI && AMD_NB help If you say yes here you get support for the temperature sensor(s) inside your CPU. Supported are later revisions of diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index d2cc55e21374..3b73dee6fdc6 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -23,6 +23,7 @@ #include #include #include +#include #include MODULE_DESCRIPTION("AMD Family 10h+ CPU core temperature monitor"); @@ -40,8 +41,8 @@ static DEFINE_MUTEX(nb_smu_ind_mutex); #define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463 #endif -#ifndef PCI_DEVICE_ID_AMD_17H_RR_NB -#define PCI_DEVICE_ID_AMD_17H_RR_NB 0x15d0 +#ifndef PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 +#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb #endif /* CPUID function 0x80000001, ebx */ @@ -63,10 +64,12 @@ static DEFINE_MUTEX(nb_smu_ind_mutex); #define NB_CAP_HTC 0x00000400 /* - * For F15h M60h, functionality of REG_REPORTED_TEMPERATURE - * has been moved to D0F0xBC_xD820_0CA4 [Reported Temperature - * Control] + * For F15h M60h and M70h, REG_HARDWARE_THERMAL_CONTROL + * and REG_REPORTED_TEMPERATURE have been moved to + * D0F0xBC_xD820_0C64 [Hardware Temperature Control] + * D0F0xBC_xD820_0CA4 [Reported Temperature Control] */ +#define F15H_M60H_HARDWARE_TEMP_CTRL_OFFSET 0xd8200c64 #define F15H_M60H_REPORTED_TEMP_CTRL_OFFSET 0xd8200ca4 /* F17h M01h Access througn SMN */ @@ -74,6 +77,7 @@ static DEFINE_MUTEX(nb_smu_ind_mutex); struct k10temp_data { struct pci_dev *pdev; + void (*read_htcreg)(struct pci_dev *pdev, u32 *regval); void (*read_tempreg)(struct pci_dev *pdev, u32 *regval); int temp_offset; u32 temp_adjust_mask; @@ -98,6 +102,11 @@ static const struct tctl_offset tctl_offset_table[] = { { 0x17, "AMD Ryzen Threadripper 1910", 10000 }, }; +static void read_htcreg_pci(struct pci_dev *pdev, u32 *regval) +{ + pci_read_config_dword(pdev, REG_HARDWARE_THERMAL_CONTROL, regval); +} + static void read_tempreg_pci(struct pci_dev *pdev, u32 *regval) { pci_read_config_dword(pdev, REG_REPORTED_TEMPERATURE, regval); @@ -114,6 +123,12 @@ static void amd_nb_index_read(struct pci_dev *pdev, unsigned int devfn, mutex_unlock(&nb_smu_ind_mutex); } +static void read_htcreg_nb_f15(struct pci_dev *pdev, u32 *regval) +{ + amd_nb_index_read(pdev, PCI_DEVFN(0, 0), 0xb8, + F15H_M60H_HARDWARE_TEMP_CTRL_OFFSET, regval); +} + static void read_tempreg_nb_f15(struct pci_dev *pdev, u32 *regval) { amd_nb_index_read(pdev, PCI_DEVFN(0, 0), 0xb8, @@ -122,8 +137,8 @@ static void read_tempreg_nb_f15(struct pci_dev *pdev, u32 *regval) static void read_tempreg_nb_f17(struct pci_dev *pdev, u32 *regval) { - amd_nb_index_read(pdev, PCI_DEVFN(0, 0), 0x60, - F17H_M01H_REPORTED_TEMP_CTRL_OFFSET, regval); + amd_smn_read(amd_pci_dev_to_node_id(pdev), + F17H_M01H_REPORTED_TEMP_CTRL_OFFSET, regval); } static ssize_t temp1_input_show(struct device *dev, @@ -160,8 +175,7 @@ static ssize_t show_temp_crit(struct device *dev, u32 regval; int value; - pci_read_config_dword(data->pdev, - REG_HARDWARE_THERMAL_CONTROL, ®val); + data->read_htcreg(data->pdev, ®val); value = ((regval >> 16) & 0x7f) * 500 + 52000; if (show_hyst) value -= ((regval >> 24) & 0xf) * 500; @@ -181,13 +195,18 @@ static umode_t k10temp_is_visible(struct kobject *kobj, struct pci_dev *pdev = data->pdev; if (index >= 2) { - u32 reg_caps, reg_htc; + u32 reg; + + if (!data->read_htcreg) + return 0; pci_read_config_dword(pdev, REG_NORTHBRIDGE_CAPABILITIES, - ®_caps); - pci_read_config_dword(pdev, REG_HARDWARE_THERMAL_CONTROL, - ®_htc); - if (!(reg_caps & NB_CAP_HTC) || !(reg_htc & HTC_ENABLE)) + ®); + if (!(reg & NB_CAP_HTC)) + return 0; + + data->read_htcreg(data->pdev, ®); + if (!(reg & HTC_ENABLE)) return 0; } return attr->mode; @@ -268,11 +287,13 @@ static int k10temp_probe(struct pci_dev *pdev, if (boot_cpu_data.x86 == 0x15 && (boot_cpu_data.x86_model == 0x60 || boot_cpu_data.x86_model == 0x70)) { + data->read_htcreg = read_htcreg_nb_f15; data->read_tempreg = read_tempreg_nb_f15; } else if (boot_cpu_data.x86 == 0x17) { data->temp_adjust_mask = 0x80000; data->read_tempreg = read_tempreg_nb_f17; } else { + data->read_htcreg = read_htcreg_pci; data->read_tempreg = read_tempreg_pci; } @@ -302,7 +323,7 @@ static const struct pci_device_id k10temp_id_table[] = { { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, - { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_RR_NB) }, + { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) }, {} }; MODULE_DEVICE_TABLE(pci, k10temp_id_table); diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index 05732531829f..d64d6ee1de01 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -209,7 +209,10 @@ 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/md/bcache/debug.c b/drivers/md/bcache/debug.c index af89408befe8..b218426a6493 100644 --- a/drivers/md/bcache/debug.c +++ b/drivers/md/bcache/debug.c @@ -251,6 +251,9 @@ void bch_debug_exit(void) int __init bch_debug_init(struct kobject *kobj) { + if (!IS_ENABLED(CONFIG_DEBUG_FS)) + return 0; + debug = debugfs_create_dir("bcache", NULL); return IS_ERR_OR_NULL(debug); diff --git a/drivers/mtd/nand/marvell_nand.c b/drivers/mtd/nand/marvell_nand.c index f978c06fbd7d..e81ad33ab849 100644 --- a/drivers/mtd/nand/marvell_nand.c +++ b/drivers/mtd/nand/marvell_nand.c @@ -1190,11 +1190,13 @@ static void marvell_nfc_hw_ecc_bch_read_chunk(struct nand_chip *chip, int chunk, NDCB0_CMD2(NAND_CMD_READSTART); /* - * Trigger the naked read operation only on the last chunk. - * Otherwise, use monolithic read. + * Trigger the monolithic read on the first chunk, then naked read on + * intermediate chunks and finally a last naked read on the last chunk. */ - if (lt->nchunks == 1 || (chunk < lt->nchunks - 1)) + if (chunk == 0) nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_MONOLITHIC_RW); + else if (chunk < lt->nchunks - 1) + nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_NAKED_RW); else nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_LAST_NAKED_RW); diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c index 98f3cfdc0d02..5a116db5a65f 100644 --- a/drivers/s390/cio/qdio_setup.c +++ b/drivers/s390/cio/qdio_setup.c @@ -141,7 +141,7 @@ 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/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index 2c7550797ec2..dce92b2a895d 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -715,6 +715,10 @@ void cp_free(struct channel_program *cp) * and stores the result to ccwchain list. @cp must have been * initialized by a previous call with cp_init(). Otherwise, undefined * behavior occurs. + * For each chain composing the channel program: + * - On entry ch_len holds the count of CCWs to be translated. + * - On exit ch_len is adjusted to the count of successfully translated CCWs. + * This allows cp_free to find in ch_len the count of CCWs to free in a chain. * * The S/390 CCW Translation APIS (prefixed by 'cp_') are introduced * as helpers to do ccw chain translation inside the kernel. Basically @@ -749,11 +753,18 @@ int cp_prefetch(struct channel_program *cp) for (idx = 0; idx < len; idx++) { ret = ccwchain_fetch_one(chain, idx, cp); if (ret) - return ret; + goto out_err; } } return 0; +out_err: + /* Only cleanup the chain elements that were actually translated. */ + chain->ch_len = idx; + list_for_each_entry_continue(chain, &cp->ccwchain_list, next) { + chain->ch_len = 0; + } + return ret; } /** diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index a172ab299e80..ff01f865a173 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -490,7 +490,7 @@ 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; @@ -505,7 +505,7 @@ 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; @@ -519,16 +519,19 @@ 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; } @@ -755,8 +758,13 @@ 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 94f7b0713281..02a8012a318a 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/tee/tee_shm.c b/drivers/tee/tee_shm.c index 556960a1bab3..07d3be6f0780 100644 --- a/drivers/tee/tee_shm.c +++ b/drivers/tee/tee_shm.c @@ -360,9 +360,10 @@ int tee_shm_get_fd(struct tee_shm *shm) if (!(shm->flags & TEE_SHM_DMA_BUF)) return -EINVAL; + get_dma_buf(shm->dmabuf); fd = dma_buf_fd(shm->dmabuf, O_CLOEXEC); - if (fd >= 0) - get_dma_buf(shm->dmabuf); + if (fd < 0) + dma_buf_put(shm->dmabuf); return fd; } diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 72ebbc908e19..32cd52ca8318 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -354,7 +354,7 @@ int xhci_find_slot_id_by_port(struct usb_hcd *hcd, struct xhci_hcd *xhci, slot_id = 0; for (i = 0; i < MAX_HC_SLOTS; i++) { - if (!xhci->devs[i]) + if (!xhci->devs[i] || !xhci->devs[i]->udev) continue; speed = xhci->devs[i]->udev->speed; if (((speed >= USB_SPEED_SUPER) == (hcd->speed >= HCD_USB3)) diff --git a/drivers/usb/usbip/stub.h b/drivers/usb/usbip/stub.h index 14a72357800a..35618ceb2791 100644 --- a/drivers/usb/usbip/stub.h +++ b/drivers/usb/usbip/stub.h @@ -73,6 +73,7 @@ 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 */ @@ -83,6 +84,7 @@ 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 dd8ef36ab10e..c0d6ff1baa72 100644 --- a/drivers/usb/usbip/stub_dev.c +++ b/drivers/usb/usbip/stub_dev.c @@ -300,9 +300,9 @@ 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); @@ -317,13 +317,15 @@ 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")) { @@ -331,13 +333,16 @@ 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", @@ -369,7 +374,9 @@ 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); @@ -379,6 +386,9 @@ 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; } @@ -404,7 +414,7 @@ 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) { @@ -417,7 +427,7 @@ 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); @@ -432,12 +442,12 @@ 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); @@ -448,12 +458,11 @@ 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 d41d0cdeec0f..bf8a5feb0ee9 100644 --- a/drivers/usb/usbip/stub_main.c +++ b/drivers/usb/usbip/stub_main.c @@ -14,6 +14,7 @@ #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 @@ -25,6 +26,8 @@ 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. @@ -32,6 +35,9 @@ 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); } /* @@ -43,15 +49,20 @@ 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; @@ -59,13 +70,22 @@ 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; @@ -78,15 +98,19 @@ 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); @@ -107,6 +131,8 @@ 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); @@ -114,6 +140,7 @@ 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); @@ -126,9 +153,12 @@ static ssize_t match_busid_show(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"); @@ -169,6 +199,51 @@ static ssize_t match_busid_store(struct device_driver *dev, const char *buf, } static DRIVER_ATTR_RW(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) { @@ -186,16 +261,17 @@ 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; } @@ -317,6 +393,9 @@ 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 b88a79e69ddf..d3b59f14f9c2 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2491,10 +2491,8 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p, if (p->reada != READA_NONE) reada_for_search(fs_info, p, level, slot, key->objectid); - btrfs_release_path(p); - ret = -EAGAIN; - tmp = read_tree_block(fs_info, blocknr, 0); + tmp = read_tree_block(fs_info, blocknr, gen); if (!IS_ERR(tmp)) { /* * If the read above didn't mark this buffer up to date, @@ -2508,6 +2506,8 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p, } else { ret = PTR_ERR(tmp); } + + btrfs_release_path(p); return ret; } @@ -5460,12 +5460,24 @@ int btrfs_compare_trees(struct btrfs_root *left_root, down_read(&fs_info->commit_root_sem); left_level = btrfs_header_level(left_root->commit_root); left_root_level = left_level; - left_path->nodes[left_level] = left_root->commit_root; + left_path->nodes[left_level] = + btrfs_clone_extent_buffer(left_root->commit_root); + if (!left_path->nodes[left_level]) { + up_read(&fs_info->commit_root_sem); + ret = -ENOMEM; + goto out; + } extent_buffer_get(left_path->nodes[left_level]); right_level = btrfs_header_level(right_root->commit_root); right_root_level = right_level; - right_path->nodes[right_level] = right_root->commit_root; + right_path->nodes[right_level] = + btrfs_clone_extent_buffer(right_root->commit_root); + if (!right_path->nodes[right_level]) { + up_read(&fs_info->commit_root_sem); + ret = -ENOMEM; + goto out; + } extent_buffer_get(right_path->nodes[right_level]); up_read(&fs_info->commit_root_sem); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index da308774b8a4..13b66ff1719c 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3153,6 +3153,8 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, u64 *orig_start, u64 *orig_block_len, u64 *ram_bytes); +void __btrfs_del_delalloc_inode(struct btrfs_root *root, + struct btrfs_inode *inode); struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry); int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index); int btrfs_unlink_inode(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 21f34ad0d411..fea78d138073 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3744,6 +3744,7 @@ void close_ctree(struct btrfs_fs_info *fs_info) set_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags); btrfs_free_qgroup_config(fs_info); + ASSERT(list_empty(&fs_info->delalloc_roots)); if (percpu_counter_sum(&fs_info->delalloc_bytes)) { btrfs_info(fs_info, "at unmount delalloc count %lld", @@ -4049,15 +4050,15 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info) static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info) { + /* cleanup FS via transaction */ + btrfs_cleanup_transaction(fs_info); + mutex_lock(&fs_info->cleaner_mutex); btrfs_run_delayed_iputs(fs_info); mutex_unlock(&fs_info->cleaner_mutex); down_write(&fs_info->cleanup_work_sem); up_write(&fs_info->cleanup_work_sem); - - /* cleanup FS via transaction */ - btrfs_cleanup_transaction(fs_info); } static void btrfs_destroy_ordered_extents(struct btrfs_root *root) @@ -4182,19 +4183,23 @@ static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root) list_splice_init(&root->delalloc_inodes, &splice); while (!list_empty(&splice)) { + struct inode *inode = NULL; btrfs_inode = list_first_entry(&splice, struct btrfs_inode, delalloc_inodes); - - list_del_init(&btrfs_inode->delalloc_inodes); - clear_bit(BTRFS_INODE_IN_DELALLOC_LIST, - &btrfs_inode->runtime_flags); + __btrfs_del_delalloc_inode(root, btrfs_inode); spin_unlock(&root->delalloc_lock); - btrfs_invalidate_inodes(btrfs_inode->root); - + /* + * Make sure we get a live inode and that it'll not disappear + * meanwhile. + */ + inode = igrab(&btrfs_inode->vfs_inode); + if (inode) { + invalidate_inode_pages2(inode->i_mapping); + iput(inode); + } spin_lock(&root->delalloc_lock); } - spin_unlock(&root->delalloc_lock); } @@ -4210,7 +4215,6 @@ static void btrfs_destroy_all_delalloc_inodes(struct btrfs_fs_info *fs_info) while (!list_empty(&splice)) { root = list_first_entry(&splice, struct btrfs_root, delalloc_root); - list_del_init(&root->delalloc_root); root = btrfs_grab_fs_root(root); BUG_ON(!root); spin_unlock(&fs_info->delalloc_root_lock); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index ef1cf323832a..f370bdc126b8 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1762,12 +1762,12 @@ static void btrfs_add_delalloc_inodes(struct btrfs_root *root, spin_unlock(&root->delalloc_lock); } -static void btrfs_del_delalloc_inode(struct btrfs_root *root, - struct btrfs_inode *inode) + +void __btrfs_del_delalloc_inode(struct btrfs_root *root, + struct btrfs_inode *inode) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); - spin_lock(&root->delalloc_lock); if (!list_empty(&inode->delalloc_inodes)) { list_del_init(&inode->delalloc_inodes); clear_bit(BTRFS_INODE_IN_DELALLOC_LIST, @@ -1780,6 +1780,13 @@ static void btrfs_del_delalloc_inode(struct btrfs_root *root, spin_unlock(&fs_info->delalloc_root_lock); } } +} + +static void btrfs_del_delalloc_inode(struct btrfs_root *root, + struct btrfs_inode *inode) +{ + spin_lock(&root->delalloc_lock); + __btrfs_del_delalloc_inode(root, inode); spin_unlock(&root->delalloc_lock); } diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index b30a056963ab..29619496e358 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -393,6 +393,7 @@ static int prop_compression_apply(struct inode *inode, const char *value, size_t len) { + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); int type; if (len == 0) { @@ -403,14 +404,17 @@ static int prop_compression_apply(struct inode *inode, return 0; } - if (!strncmp("lzo", value, 3)) + if (!strncmp("lzo", value, 3)) { type = BTRFS_COMPRESS_LZO; - else if (!strncmp("zlib", value, 4)) + btrfs_set_fs_incompat(fs_info, COMPRESS_LZO); + } else if (!strncmp("zlib", value, 4)) { type = BTRFS_COMPRESS_ZLIB; - else if (!strncmp("zstd", value, len)) + } else if (!strncmp("zstd", value, len)) { type = BTRFS_COMPRESS_ZSTD; - else + btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD); + } else { return -EINVAL; + } BTRFS_I(inode)->flags &= ~BTRFS_INODE_NOCOMPRESS; BTRFS_I(inode)->flags |= BTRFS_INODE_COMPRESS; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 434457794c27..ac6ea1503cd6 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4749,6 +4749,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, struct extent_map_tree *em_tree = &inode->extent_tree; u64 logged_isize = 0; bool need_log_inode_item = true; + bool xattrs_logged = false; path = btrfs_alloc_path(); if (!path) @@ -5050,6 +5051,7 @@ 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); @@ -5062,6 +5064,11 @@ 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 b2d05c6b1c56..854cb4533f88 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4046,6 +4046,15 @@ 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 598803576e4c..9a517c03ac78 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -85,6 +85,7 @@ #include #include #include +#include #include #include #include @@ -347,6 +348,30 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p) #ifdef CONFIG_SECCOMP seq_put_decimal_ull(m, "\nSeccomp:\t", p->seccomp.mode); #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'); } diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 6b66cd1aa0b9..660a7d5e4702 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -146,6 +146,7 @@ struct bpf_insn_aux_data { s32 call_imm; /* saved imm field of call insn */ }; int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ + int sanitize_stack_off; /* stack slot to be cleared */ bool seen; /* this insn was processed by the verifier */ }; diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 7b01bc11c692..a97a63eef59f 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -53,6 +53,8 @@ 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 f5083aa72eae..c2520ca123aa 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -395,8 +395,8 @@ 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 { @@ -415,8 +415,8 @@ 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 +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 b161ef8a902e..710508af02c8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1365,7 +1365,8 @@ static inline bool is_percpu_thread(void) #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ #define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ - +#define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */ +#define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ @@ -1390,6 +1391,13 @@ TASK_PFA_TEST(SPREAD_SLAB, spread_slab) TASK_PFA_SET(SPREAD_SLAB, spread_slab) TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab) +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) + static inline void current_restore_flags(unsigned long orig_flags, unsigned long flags) { diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index c723a5c4e3ff..e5320f6c8654 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -4,8 +4,9 @@ #include -#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \ - SECCOMP_FILTER_FLAG_LOG) +#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \ + SECCOMP_FILTER_FLAG_LOG | \ + SECCOMP_FILTER_FLAG_SPEC_ALLOW) #ifdef CONFIG_SECCOMP diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h index 7dd8f34c37df..fdcf88bcf0ea 100644 --- a/include/trace/events/xen.h +++ b/include/trace/events/xen.h @@ -352,22 +352,6 @@ 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_one_user, TP_PROTO(unsigned long addr), TP_ARGS(addr), diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index af5f8c2df87a..db9f15f5db04 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -207,4 +207,16 @@ struct prctl_mm_map { # define PR_SVE_VL_LEN_MASK 0xffff # define PR_SVE_VL_INHERIT (1 << 17) /* inherit across exec */ +/* 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 2a0bd9dd104d..9efc0e73d50b 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -17,8 +17,9 @@ #define SECCOMP_GET_ACTION_AVAIL 2 /* Valid flags for SECCOMP_SET_MODE_FILTER */ -#define SECCOMP_FILTER_FLAG_TSYNC 1 -#define SECCOMP_FILTER_FLAG_LOG 2 +#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0) +#define SECCOMP_FILTER_FLAG_LOG (1UL << 1) +#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2) /* * All BPF programs must return a 32-bit value. diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c6eff108aa99..1a17e0d84347 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -970,7 +970,7 @@ static bool register_is_null(struct bpf_reg_state *reg) */ static int check_stack_write(struct bpf_verifier_env *env, struct bpf_func_state *state, /* func where register points to */ - int off, int size, int value_regno) + int off, int size, int value_regno, int insn_idx) { struct bpf_func_state *cur; /* state of the current function */ int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err; @@ -1009,8 +1009,33 @@ static int check_stack_write(struct bpf_verifier_env *env, state->stack[spi].spilled_ptr = cur->regs[value_regno]; state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; - for (i = 0; i < BPF_REG_SIZE; i++) + for (i = 0; i < BPF_REG_SIZE; i++) { + if (state->stack[spi].slot_type[i] == STACK_MISC && + !env->allow_ptr_leaks) { + int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off; + int soff = (-spi - 1) * BPF_REG_SIZE; + + /* detected reuse of integer stack slot with a pointer + * which means either llvm is reusing stack slot or + * an attacker is trying to exploit CVE-2018-3639 + * (speculative store bypass) + * Have to sanitize that slot with preemptive + * store of zero. + */ + if (*poff && *poff != soff) { + /* disallow programs where single insn stores + * into two different stack slots, since verifier + * cannot sanitize them + */ + verbose(env, + "insn %d cannot access two stack slots fp%d and fp%d", + insn_idx, *poff, soff); + return -EINVAL; + } + *poff = soff; + } state->stack[spi].slot_type[i] = STACK_SPILL; + } } else { u8 type = STACK_MISC; @@ -1685,7 +1710,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (t == BPF_WRITE) err = check_stack_write(env, state, off, size, - value_regno); + value_regno, insn_idx); else err = check_stack_read(env, state, off, size, value_regno); @@ -5156,6 +5181,34 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) else continue; + if (type == BPF_WRITE && + env->insn_aux_data[i + delta].sanitize_stack_off) { + struct bpf_insn patch[] = { + /* Sanitize suspicious stack slot with zero. + * There are no memory dependencies for this store, + * since it's only using frame pointer and immediate + * constant of zero + */ + BPF_ST_MEM(BPF_DW, BPF_REG_FP, + env->insn_aux_data[i + delta].sanitize_stack_off, + 0), + /* the original STX instruction will immediately + * overwrite the same stack slot with appropriate value + */ + *insn, + }; + + cnt = ARRAY_SIZE(patch); + new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX) continue; diff --git a/kernel/seccomp.c b/kernel/seccomp.c index dc77548167ef..e691d9a6c58d 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -19,6 +19,8 @@ #include #include #include +#include +#include #include #include #include @@ -227,8 +229,11 @@ 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); @@ -238,6 +243,9 @@ 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); } @@ -305,7 +313,7 @@ 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; @@ -346,7 +354,8 @@ 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); } } @@ -469,7 +478,7 @@ 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; } @@ -818,7 +827,7 @@ 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: @@ -876,7 +885,7 @@ 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(¤t->sighand->siglock); if (flags & SECCOMP_FILTER_FLAG_TSYNC) diff --git a/kernel/sys.c b/kernel/sys.c index f2289de20e19..9afc4cb5acf5 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -61,6 +61,8 @@ #include #include +#include + #include /* Move somewhere else to avoid recompiling? */ #include @@ -2190,6 +2192,17 @@ static int propagate_has_child_subreaper(struct task_struct *p, void *data) return 1; } +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) { @@ -2398,6 +2411,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_SVE_GET_VL: error = SVE_GET_VL(); 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 b398c2ea69b2..aa2094d5dd27 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -612,6 +612,14 @@ 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 <= now) { cpumask_set_cpu(cpu, tmpmask); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 8e00138d593f..a7705b0f139c 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1612,11 +1612,9 @@ static void set_iter_tags(struct radix_tree_iter *iter, static void __rcu **skip_siblings(struct radix_tree_node **nodep, void __rcu **slot, struct radix_tree_iter *iter) { - void *sib = node_to_entry(slot - 1); - while (iter->index < iter->next_index) { *nodep = rcu_dereference_raw(*slot); - if (*nodep && *nodep != sib) + if (*nodep && !is_sibling_entry(iter->node, *nodep)) return slot; slot++; iter->index = __radix_tree_iter_add(iter, 1); @@ -1631,7 +1629,7 @@ void __rcu **__radix_tree_next_slot(void __rcu **slot, struct radix_tree_iter *iter, unsigned flags) { unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; - struct radix_tree_node *node = rcu_dereference_raw(*slot); + struct radix_tree_node *node; slot = skip_siblings(&node, slot, iter); diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 413367cf569e..d47a802220f5 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -329,23 +329,32 @@ static void noinline __init test_mem_optimisations(void) unsigned int start, nbits; for (start = 0; start < 1024; start += 8) { - memset(bmap1, 0x5a, sizeof(bmap1)); - memset(bmap2, 0x5a, sizeof(bmap2)); for (nbits = 0; nbits < 1024 - start; nbits += 8) { + memset(bmap1, 0x5a, sizeof(bmap1)); + memset(bmap2, 0x5a, sizeof(bmap2)); + bitmap_set(bmap1, start, nbits); __bitmap_set(bmap2, start, nbits); - if (!bitmap_equal(bmap1, bmap2, 1024)) + if (!bitmap_equal(bmap1, bmap2, 1024)) { printk("set not equal %d %d\n", start, nbits); - if (!__bitmap_equal(bmap1, bmap2, 1024)) + failed_tests++; + } + if (!__bitmap_equal(bmap1, bmap2, 1024)) { printk("set not __equal %d %d\n", start, nbits); + failed_tests++; + } bitmap_clear(bmap1, start, nbits); __bitmap_clear(bmap2, start, nbits); - if (!bitmap_equal(bmap1, bmap2, 1024)) + if (!bitmap_equal(bmap1, bmap2, 1024)) { printk("clear not equal %d %d\n", start, nbits); - if (!__bitmap_equal(bmap1, bmap2, 1024)) + failed_tests++; + } + if (!__bitmap_equal(bmap1, bmap2, 1024)) { printk("clear not __equal %d %d\n", start, nbits); + failed_tests++; + } } } } diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 89f8a4a4b770..38b509cc6b46 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -1659,19 +1659,22 @@ char *pointer_string(char *buf, char *end, const void *ptr, return number(buf, end, (unsigned long int)ptr, spec); } -static bool have_filled_random_ptr_key __read_mostly; +static DEFINE_STATIC_KEY_TRUE(not_filled_random_ptr_key); static siphash_key_t ptr_key __read_mostly; -static void fill_random_ptr_key(struct random_ready_callback *unused) +static void enable_ptr_key_workfn(struct work_struct *work) { get_random_bytes(&ptr_key, sizeof(ptr_key)); - /* - * have_filled_random_ptr_key==true is dependent on get_random_bytes(). - * ptr_to_id() needs to see have_filled_random_ptr_key==true - * after get_random_bytes() returns. - */ - smp_mb(); - WRITE_ONCE(have_filled_random_ptr_key, true); + /* Needs to run from preemptible context */ + static_branch_disable(¬_filled_random_ptr_key); +} + +static DECLARE_WORK(enable_ptr_key_work, enable_ptr_key_workfn); + +static void fill_random_ptr_key(struct random_ready_callback *unused) +{ + /* This may be in an interrupt handler. */ + queue_work(system_unbound_wq, &enable_ptr_key_work); } static struct random_ready_callback random_ready = { @@ -1685,7 +1688,8 @@ static int __init initialize_ptr_random(void) if (!ret) { return 0; } else if (ret == -EALREADY) { - fill_random_ptr_key(&random_ready); + /* This is in preemptible context */ + enable_ptr_key_workfn(&enable_ptr_key_work); return 0; } @@ -1699,7 +1703,7 @@ static char *ptr_to_id(char *buf, char *end, void *ptr, struct printf_spec spec) unsigned long hashval; const int default_width = 2 * sizeof(ptr); - if (unlikely(!have_filled_random_ptr_key)) { + if (static_branch_unlikely(¬_filled_random_ptr_key)) { spec.field_width = default_width; /* string length must be less than default_width */ return string(buf, end, "(ptrval)", spec); diff --git a/mm/Kconfig b/mm/Kconfig index c782e8fb7235..e07608f64d47 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -644,6 +644,7 @@ config DEFERRED_STRUCT_PAGE_INIT default n depends on NO_BOOTMEM 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 530e12ae52d7..c853386b86ff 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2357,41 +2357,46 @@ 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: @@ -3203,18 +3208,20 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, err = ops->init(set, &desc, nla); if (err < 0) - goto err2; + goto err3; err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); if (err < 0) - goto err3; + goto err4; list_add_tail_rcu(&set->list, &table->sets); table->use++; return 0; -err3: +err4: ops->destroy(set); +err3: + kfree(set->name); err2: kvfree(set); err1: @@ -4392,9 +4399,9 @@ struct nft_object *nf_tables_obj_lookup(const struct nft_table *table, } EXPORT_SYMBOL_GPL(nf_tables_obj_lookup); -struct nft_object *nf_tables_obj_lookup_byhandle(const struct nft_table *table, - const struct nlattr *nla, - u32 objtype, u8 genmask) +static struct nft_object *nf_tables_obj_lookup_byhandle(const struct nft_table *table, + const struct nlattr *nla, + u32 objtype, u8 genmask) { struct nft_object *obj; @@ -4914,7 +4921,7 @@ struct nft_flowtable *nf_tables_flowtable_lookup(const struct nft_table *table, } EXPORT_SYMBOL_GPL(nf_tables_flowtable_lookup); -struct nft_flowtable * +static struct nft_flowtable * nf_tables_flowtable_lookup_byhandle(const struct nft_table *table, const struct nlattr *nla, u8 genmask) { diff --git a/sound/core/control_compat.c b/sound/core/control_compat.c index a848836a5de0..507fd5210c1c 100644 --- a/sound/core/control_compat.c +++ b/sound/core/control_compat.c @@ -396,8 +396,7 @@ 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 738e1fe90312..62fbdbe74b93 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2208,6 +2208,8 @@ 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/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 2dd34dd77447..01a6643fc7d4 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2363,6 +2363,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3), SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX), SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD), SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD), SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Y530", ALC882_FIXUP_LENOVO_Y530), diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 06b22624ab7a..1a4c107b1940 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -915,6 +915,14 @@ 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 5df609950a66..e350cf3d4f90 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -134,11 +134,15 @@ struct seccomp_data { #endif #ifndef SECCOMP_FILTER_FLAG_TSYNC -#define SECCOMP_FILTER_FLAG_TSYNC 1 +#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0) #endif #ifndef SECCOMP_FILTER_FLAG_LOG -#define SECCOMP_FILTER_FLAG_LOG 2 +#define SECCOMP_FILTER_FLAG_LOG (1UL << 1) +#endif + +#ifndef SECCOMP_FILTER_FLAG_SPEC_ALLOW +#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2) #endif #ifndef PTRACE_SECCOMP_GET_METADATA @@ -2072,14 +2076,26 @@ TEST(seccomp_syscall_mode_lock) TEST(detect_seccomp_filter_flags) { unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC, - SECCOMP_FILTER_FLAG_LOG }; + SECCOMP_FILTER_FLAG_LOG, + 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!"); diff --git a/virt/kvm/arm/vgic/vgic-debug.c b/virt/kvm/arm/vgic/vgic-debug.c index 10b38178cff2..4ffc0b5e6105 100644 --- a/virt/kvm/arm/vgic/vgic-debug.c +++ b/virt/kvm/arm/vgic/vgic-debug.c @@ -211,6 +211,7 @@ static int vgic_debug_show(struct seq_file *s, void *v) struct vgic_state_iter *iter = (struct vgic_state_iter *)v; struct vgic_irq *irq; struct kvm_vcpu *vcpu = NULL; + unsigned long flags; if (iter->dist_id == 0) { print_dist_state(s, &kvm->arch.vgic); @@ -227,9 +228,9 @@ static int vgic_debug_show(struct seq_file *s, void *v) irq = &kvm->arch.vgic.spis[iter->intid - VGIC_NR_PRIVATE_IRQS]; } - spin_lock(&irq->irq_lock); + spin_lock_irqsave(&irq->irq_lock, flags); print_irq_state(s, irq, vcpu); - spin_unlock(&irq->irq_lock); + spin_unlock_irqrestore(&irq->irq_lock, flags); return 0; } diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index a8f07243aa9f..4ed79c939fb4 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -52,6 +52,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intid), *oldirq; + unsigned long flags; int ret; /* In this case there is no put, since we keep the reference. */ @@ -71,7 +72,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, irq->intid = intid; irq->target_vcpu = vcpu; - spin_lock(&dist->lpi_list_lock); + spin_lock_irqsave(&dist->lpi_list_lock, flags); /* * There could be a race with another vgic_add_lpi(), so we need to @@ -99,7 +100,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, dist->lpi_list_count++; out_unlock: - spin_unlock(&dist->lpi_list_lock); + spin_unlock_irqrestore(&dist->lpi_list_lock, flags); /* * We "cache" the configuration table entries in our struct vgic_irq's. @@ -280,8 +281,8 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq, int ret; unsigned long flags; - 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; @@ -315,6 +316,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr) { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; struct vgic_irq *irq; + unsigned long flags; u32 *intids; int irq_count, i = 0; @@ -330,7 +332,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr) if (!intids) return -ENOMEM; - spin_lock(&dist->lpi_list_lock); + spin_lock_irqsave(&dist->lpi_list_lock, flags); list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) { if (i == irq_count) break; @@ -339,7 +341,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr) continue; intids[i++] = irq->intid; } - spin_unlock(&dist->lpi_list_lock); + spin_unlock_irqrestore(&dist->lpi_list_lock, flags); *intid_ptr = intids; return i; @@ -348,10 +350,11 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr) static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu) { int ret = 0; + unsigned long flags; - spin_lock(&irq->irq_lock); + spin_lock_irqsave(&irq->irq_lock, flags); irq->target_vcpu = vcpu; - spin_unlock(&irq->irq_lock); + spin_unlock_irqrestore(&irq->irq_lock, flags); if (irq->hw) { struct its_vlpi_map map; @@ -441,8 +444,9 @@ 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; @@ -786,7 +790,7 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 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; @@ -1367,8 +1371,8 @@ 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 @@ -1893,7 +1897,7 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, int esz, int next_offset; size_t byte_offset; - ret = kvm_read_guest(kvm, gpa, entry, esz); + ret = kvm_read_guest_lock(kvm, gpa, entry, esz); if (ret) return ret; @@ -2263,7 +2267,7 @@ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz) int ret; BUG_ON(esz > sizeof(val)); - ret = kvm_read_guest(kvm, gpa, &val, esz); + ret = kvm_read_guest_lock(kvm, gpa, &val, esz); if (ret) return ret; val = le64_to_cpu(val); diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 0ff2006f3781..cf2f716532ac 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -329,7 +329,7 @@ int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq) bit_nr = irq->intid % BITS_PER_BYTE; ptr = pendbase + byte_offset; - ret = kvm_read_guest(kvm, ptr, &val, 1); + ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; @@ -382,7 +382,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) ptr = pendbase + byte_offset; if (byte_offset != last_byte_offset) { - ret = kvm_read_guest(kvm, ptr, &val, 1); + ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; last_byte_offset = byte_offset; diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index 8201899126f6..4232c40b34f8 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -40,9 +40,13 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = { * kvm->lock (mutex) * its->cmd_lock (mutex) * its->its_lock (mutex) - * vgic_cpu->ap_list_lock - * kvm->lpi_list_lock - * vgic_irq->irq_lock + * vgic_cpu->ap_list_lock must be taken with IRQs disabled + * kvm->lpi_list_lock must be taken with IRQs disabled + * vgic_irq->irq_lock must be taken with IRQs disabled + * + * As the ap_list_lock might be taken from the timer interrupt handler, + * we have to disable IRQs before taking this lock and everything lower + * than it. * * If you need to take multiple locks, always take the upper lock first, * then the lower ones, e.g. first take the its_lock, then the irq_lock. @@ -69,8 +73,9 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq = NULL; + unsigned long flags; - spin_lock(&dist->lpi_list_lock); + spin_lock_irqsave(&dist->lpi_list_lock, flags); list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) { if (irq->intid != intid) @@ -86,7 +91,7 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid) irq = NULL; out_unlock: - spin_unlock(&dist->lpi_list_lock); + spin_unlock_irqrestore(&dist->lpi_list_lock, flags); return irq; } @@ -127,19 +132,20 @@ static void vgic_irq_release(struct kref *ref) void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) { struct vgic_dist *dist = &kvm->arch.vgic; + unsigned long flags; if (irq->intid < VGIC_MIN_LPI) return; - spin_lock(&dist->lpi_list_lock); + spin_lock_irqsave(&dist->lpi_list_lock, flags); if (!kref_put(&irq->refcount, vgic_irq_release)) { - spin_unlock(&dist->lpi_list_lock); + spin_unlock_irqrestore(&dist->lpi_list_lock, flags); return; }; list_del(&irq->lpi_list); dist->lpi_list_count--; - spin_unlock(&dist->lpi_list_lock); + spin_unlock_irqrestore(&dist->lpi_list_lock, flags); kfree(irq); }