- Linux-stable-mirror - lists.linaro.org

[PATCH 4.4.y 070/101] x86/process: Allow runtime control of Speculative Store Bypass

by Srivatsa S. Bhat

From: Thomas Gleixner <tglx(a)linutronix.de> commit 885f82bfbc6fefb6664ea27965c3ab9ac4194b8c upstream The Speculative Store Bypass vulnerability can be mitigated with the Reduced Data Speculation (RDS) feature. To allow finer grained control of this eventually expensive mitigation a per task mitigation control is required. Add a new TIF_RDS flag and put it into the group of TIF flags which are evaluated for mismatch in switch_to(). If these bits differ in the previous and the next task, then the slow path function __switch_to_xtra() is invoked. Implement the TIF_RDS dependent mitigation control in the slow path. If the prctl for controlling Speculative Store Bypass is disabled or no task uses the prctl then there is no overhead in the switch_to() fast path. Update the KVM related speculation control functions to take TID_RDS into account as well. Based on a patch from Tim Chen. Completely rewritten. Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Ingo Molnar <mingo(a)kernel.org> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/msr-index.h | 3 ++- arch/x86/include/asm/spec-ctrl.h | 17 +++++++++++++++++ arch/x86/include/asm/thread_info.h | 6 ++++-- arch/x86/kernel/cpu/bugs.c | 26 +++++++++++++++++++++----- arch/x86/kernel/process.c | 22 ++++++++++++++++++++++ 5 files changed, 66 insertions(+), 8 deletions(-) diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 71a2c84..883cf0d 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -35,7 +35,8 @@ #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_RDS (1 << 2) /* Reduced Data Speculation */ +#define SPEC_CTRL_RDS_SHIFT 2 /* Reduced Data Speculation bit */ +#define SPEC_CTRL_RDS (1 << SPEC_CTRL_RDS_SHIFT) /* Reduced Data Speculation */ #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */ diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h index 3ad6442..45ef00a 100644 --- a/arch/x86/include/asm/spec-ctrl.h +++ b/arch/x86/include/asm/spec-ctrl.h @@ -2,6 +2,7 @@ #ifndef _ASM_X86_SPECCTRL_H_ #define _ASM_X86_SPECCTRL_H_ +#include <linux/thread_info.h> #include <asm/nospec-branch.h> /* @@ -18,4 +19,20 @@ extern void x86_spec_ctrl_restore_host(u64); extern u64 x86_amd_ls_cfg_base; extern u64 x86_amd_ls_cfg_rds_mask; +/* The Intel SPEC CTRL MSR base value cache */ +extern u64 x86_spec_ctrl_base; + +static inline u64 rds_tif_to_spec_ctrl(u64 tifn) +{ + BUILD_BUG_ON(TIF_RDS < SPEC_CTRL_RDS_SHIFT); + return (tifn & _TIF_RDS) >> (TIF_RDS - SPEC_CTRL_RDS_SHIFT); +} + +static inline u64 rds_tif_to_amd_ls_cfg(u64 tifn) +{ + return (tifn & _TIF_RDS) ? x86_amd_ls_cfg_rds_mask : 0ULL; +} + +extern void speculative_store_bypass_update(void); + #endif diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 18c9aaa..36a49b4 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -92,6 +92,7 @@ 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_RDS 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 */ @@ -114,8 +115,9 @@ struct thread_info { #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) -#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) +#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) +#define _TIF_RDS (1 << TIF_RDS) #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) @@ -147,7 +149,7 @@ struct thread_info { /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ - (_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP) + (_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP|_TIF_RDS) #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/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 47a3cc0..0f8303e 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -32,7 +32,7 @@ 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. */ -static u64 x86_spec_ctrl_base; +u64 x86_spec_ctrl_base; /* * The vendor and possibly platform specific bits which can be modified in @@ -139,25 +139,41 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_set); u64 x86_spec_ctrl_get_default(void) { - return x86_spec_ctrl_base; + u64 msrval = x86_spec_ctrl_base; + + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + msrval |= rds_tif_to_spec_ctrl(current_thread_info()->flags); + return msrval; } EXPORT_SYMBOL_GPL(x86_spec_ctrl_get_default); void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl) { + u64 host = x86_spec_ctrl_base; + if (!boot_cpu_has(X86_FEATURE_IBRS)) return; - if (x86_spec_ctrl_base != guest_spec_ctrl) + + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + host |= rds_tif_to_spec_ctrl(current_thread_info()->flags); + + if (host != guest_spec_ctrl) wrmsrl(MSR_IA32_SPEC_CTRL, guest_spec_ctrl); } EXPORT_SYMBOL_GPL(x86_spec_ctrl_set_guest); void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl) { + u64 host = x86_spec_ctrl_base; + if (!boot_cpu_has(X86_FEATURE_IBRS)) return; - if (x86_spec_ctrl_base != guest_spec_ctrl) - wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + host |= rds_tif_to_spec_ctrl(current_thread_info()->flags); + + if (host != guest_spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, host); } EXPORT_SYMBOL_GPL(x86_spec_ctrl_restore_host); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index d112963..9689e92 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -31,6 +31,7 @@ #include <asm/tlbflush.h> #include <asm/mce.h> #include <asm/vm86.h> +#include <asm/spec-ctrl.h> /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -198,6 +199,24 @@ static inline void switch_to_bitmap(struct tss_struct *tss, } } +static __always_inline void __speculative_store_bypass_update(unsigned long tifn) +{ + u64 msr; + + if (static_cpu_has(X86_FEATURE_AMD_RDS)) { + msr = x86_amd_ls_cfg_base | rds_tif_to_amd_ls_cfg(tifn); + wrmsrl(MSR_AMD64_LS_CFG, msr); + } else { + msr = x86_spec_ctrl_base | rds_tif_to_spec_ctrl(tifn); + wrmsrl(MSR_IA32_SPEC_CTRL, msr); + } +} + +void speculative_store_bypass_update(void) +{ + __speculative_store_bypass_update(current_thread_info()->flags); +} + void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, struct tss_struct *tss) { @@ -226,6 +245,9 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, if ((tifp ^ tifn) & _TIF_NOTSC) cr4_toggle_bits(X86_CR4_TSD); + + if ((tifp ^ tifn) & _TIF_RDS) + __speculative_store_bypass_update(tifn); } /*

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 069/101] x86/process: Optimize TIF_NOTSC switch

by Srivatsa S. Bhat

From: Thomas Gleixner <tglx(a)linutronix.de> commit 5a920155e388ec22a22e0532fb695b9215c9b34d upstream Provide and use a toggle helper instead of doing it with a branch. x86_64: arch/x86/kernel/process.o text data bss dec hex 3008 8577 16 11601 2d51 Before 2976 8577 16 11569 2d31 After i386: arch/x86/kernel/process.o text data bss dec hex 2925 8673 8 11606 2d56 Before 2893 8673 8 11574 2d36 After Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Andy Lutomirski <luto(a)kernel.org> Link: http://lkml.kernel.org/r/20170214081104.9244-4-khuey@kylehuey.com Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/tlbflush.h | 10 ++++++++++ arch/x86/kernel/process.c | 22 ++++------------------ 2 files changed, 14 insertions(+), 18 deletions(-) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 8ce07db..72cfe3e 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -111,6 +111,16 @@ static inline void cr4_clear_bits(unsigned long mask) } } +static inline void cr4_toggle_bits(unsigned long mask) +{ + unsigned long cr4; + + cr4 = this_cpu_read(cpu_tlbstate.cr4); + cr4 ^= mask; + this_cpu_write(cpu_tlbstate.cr4, cr4); + __write_cr4(cr4); +} + /* Read the CR4 shadow. */ static inline unsigned long cr4_read_shadow(void) { diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 166aef3..d112963 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -130,11 +130,6 @@ void flush_thread(void) fpu__clear(&tsk->thread.fpu); } -static void hard_disable_TSC(void) -{ - cr4_set_bits(X86_CR4_TSD); -} - void disable_TSC(void) { preempt_disable(); @@ -143,15 +138,10 @@ void disable_TSC(void) * Must flip the CPU state synchronously with * TIF_NOTSC in the current running context. */ - hard_disable_TSC(); + cr4_set_bits(X86_CR4_TSD); preempt_enable(); } -static void hard_enable_TSC(void) -{ - cr4_clear_bits(X86_CR4_TSD); -} - static void enable_TSC(void) { preempt_disable(); @@ -160,7 +150,7 @@ static void enable_TSC(void) * Must flip the CPU state synchronously with * TIF_NOTSC in the current running context. */ - hard_enable_TSC(); + cr4_clear_bits(X86_CR4_TSD); preempt_enable(); } @@ -234,12 +224,8 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); } - if ((tifp ^ tifn) & _TIF_NOTSC) { - if (tifn & _TIF_NOTSC) - hard_disable_TSC(); - else - hard_enable_TSC(); - } + if ((tifp ^ tifn) & _TIF_NOTSC) + cr4_toggle_bits(X86_CR4_TSD); } /*

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 068/101] x86/process: Correct and optimize TIF_BLOCKSTEP switch

by Srivatsa S. Bhat

From: Kyle Huey <me(a)kylehuey.com> commit b9894a2f5bd18b1691cb6872c9afe32b148d0132 upstream The debug control MSR is "highly magical" as the blockstep bit can be cleared by hardware under not well documented circumstances. So a task switch relying on the bit set by the previous task (according to the previous tasks thread flags) can trip over this and not update the flag for the next task. To fix this its required to handle DEBUGCTLMSR_BTF when either the previous or the next or both tasks have the TIF_BLOCKSTEP flag set. While at it avoid branching within the TIF_BLOCKSTEP case and evaluating boot_cpu_data twice in kernels without CONFIG_X86_DEBUGCTLMSR. x86_64: arch/x86/kernel/process.o text data bss dec hex 3024 8577 16 11617 2d61 Before 3008 8577 16 11601 2d51 After i386: No change [ tglx: Made the shift value explicit, use a local variable to make the code readable and massaged changelog] Originally-by: Thomas Gleixner <tglx(a)linutronix.de> Signed-off-by: Kyle Huey <khuey(a)kylehuey.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Andy Lutomirski <luto(a)kernel.org> Link: http://lkml.kernel.org/r/20170214081104.9244-3-khuey@kylehuey.com Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/msr-index.h | 1 + arch/x86/kernel/process.c | 12 +++++++----- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index a29edb7..71a2c84 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -150,6 +150,7 @@ /* DEBUGCTLMSR bits (others vary by model): */ #define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */ +#define DEBUGCTLMSR_BTF_SHIFT 1 #define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */ #define DEBUGCTLMSR_TR (1UL << 6) #define DEBUGCTLMSR_BTS (1UL << 7) diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index cc0f288..166aef3 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -223,13 +223,15 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, propagate_user_return_notify(prev_p, next_p); - if ((tifp ^ tifn) & _TIF_BLOCKSTEP) { - unsigned long debugctl = get_debugctlmsr(); + if ((tifp & _TIF_BLOCKSTEP || tifn & _TIF_BLOCKSTEP) && + arch_has_block_step()) { + unsigned long debugctl, msk; + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); debugctl &= ~DEBUGCTLMSR_BTF; - if (tifn & _TIF_BLOCKSTEP) - debugctl |= DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); + msk = tifn & _TIF_BLOCKSTEP; + debugctl |= (msk >> TIF_BLOCKSTEP) << DEBUGCTLMSR_BTF_SHIFT; + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); } if ((tifp ^ tifn) & _TIF_NOTSC) {

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 067/101] x86/process: Optimize TIF checks in __switch_to_xtra()

by Srivatsa S. Bhat

From: Kyle Huey <me(a)kylehuey.com> commit af8b3cd3934ec60f4c2a420d19a9d416554f140b upstream Help the compiler to avoid reevaluating the thread flags for each checked bit by reordering the bit checks and providing an explicit xor for evaluation. With default defconfigs for each arch, x86_64: arch/x86/kernel/process.o text data bss dec hex 3056 8577 16 11649 2d81 Before 3024 8577 16 11617 2d61 After i386: arch/x86/kernel/process.o text data bss dec hex 2957 8673 8 11638 2d76 Before 2925 8673 8 11606 2d56 After Originally-by: Thomas Gleixner <tglx(a)linutronix.de> Signed-off-by: Kyle Huey <khuey(a)kylehuey.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Andy Lutomirski <luto(a)kernel.org> Link: http://lkml.kernel.org/r/20170214081104.9244-2-khuey@kylehuey.com Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> [dwmw2: backported to make TIF_RDS handling simpler. No deferred TR reload.] Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/kernel/process.c | 54 ++++++++++++++++++++++++++------------------- 1 file changed, 31 insertions(+), 23 deletions(-) diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 7c5c5dc..cc0f288 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -188,48 +188,56 @@ int set_tsc_mode(unsigned int val) return 0; } +static inline void switch_to_bitmap(struct tss_struct *tss, + struct thread_struct *prev, + struct thread_struct *next, + unsigned long tifp, unsigned long tifn) +{ + if (tifn & _TIF_IO_BITMAP) { + /* + * Copy the relevant range of the IO bitmap. + * Normally this is 128 bytes or less: + */ + memcpy(tss->io_bitmap, next->io_bitmap_ptr, + max(prev->io_bitmap_max, next->io_bitmap_max)); + } else if (tifp & _TIF_IO_BITMAP) { + /* + * Clear any possible leftover bits: + */ + memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); + } +} + void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, struct tss_struct *tss) { struct thread_struct *prev, *next; + unsigned long tifp, tifn; prev = &prev_p->thread; next = &next_p->thread; - if (test_tsk_thread_flag(prev_p, TIF_BLOCKSTEP) ^ - test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) { + tifn = READ_ONCE(task_thread_info(next_p)->flags); + tifp = READ_ONCE(task_thread_info(prev_p)->flags); + switch_to_bitmap(tss, prev, next, tifp, tifn); + + propagate_user_return_notify(prev_p, next_p); + + if ((tifp ^ tifn) & _TIF_BLOCKSTEP) { unsigned long debugctl = get_debugctlmsr(); debugctl &= ~DEBUGCTLMSR_BTF; - if (test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) + if (tifn & _TIF_BLOCKSTEP) debugctl |= DEBUGCTLMSR_BTF; - update_debugctlmsr(debugctl); } - if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ - test_tsk_thread_flag(next_p, TIF_NOTSC)) { - /* prev and next are different */ - if (test_tsk_thread_flag(next_p, TIF_NOTSC)) + if ((tifp ^ tifn) & _TIF_NOTSC) { + if (tifn & _TIF_NOTSC) hard_disable_TSC(); else hard_enable_TSC(); } - - if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { - /* - * Copy the relevant range of the IO bitmap. - * Normally this is 128 bytes or less: - */ - memcpy(tss->io_bitmap, next->io_bitmap_ptr, - max(prev->io_bitmap_max, next->io_bitmap_max)); - } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) { - /* - * Clear any possible leftover bits: - */ - memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); - } - propagate_user_return_notify(prev_p, next_p); } /*

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 066/101] prctl: Add speculation control prctls

by Srivatsa S. Bhat

From: Thomas Gleixner <tglx(a)linutronix.de> commit b617cfc858161140d69cc0b5cc211996b557a1c7 upstream Add two new prctls to control aspects of speculation related vulnerabilites and their mitigations to provide finer grained control over performance impacting mitigations. PR_GET_SPECULATION_CTRL returns the state of the speculation misfeature which is selected with arg2 of prctl(2). The return value uses bit 0-2 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 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 allows to control the speculation misfeature, which is selected by arg2 of prctl(2) per task. arg3 is used to hand in the control value, i.e. either PR_SPEC_ENABLE or PR_SPEC_DISABLE. The common return values are: EINVAL prctl is not implemented by the architecture or the unused prctl() arguments are not 0 ENODEV arg2 is selecting a not supported speculation misfeature PR_SET_SPECULATION_CTRL has these additional return values: ERANGE arg3 is incorrect, i.e. it's not either PR_SPEC_ENABLE or PR_SPEC_DISABLE ENXIO prctl control of the selected speculation misfeature is disabled The first supported controlable speculation misfeature is PR_SPEC_STORE_BYPASS. Add the define so this can be shared between architectures. Based on an initial patch from Tim Chen and mostly rewritten. Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Ingo Molnar <mingo(a)kernel.org> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- Documentation/spec_ctrl.txt | 86 +++++++++++++++++++++++++++++++++++++++++++ include/linux/nospec.h | 5 +++ include/uapi/linux/prctl.h | 11 ++++++ kernel/sys.c | 20 ++++++++++ 4 files changed, 122 insertions(+) create mode 100644 Documentation/spec_ctrl.txt diff --git a/Documentation/spec_ctrl.txt b/Documentation/spec_ctrl.txt new file mode 100644 index 0000000..ddbebcd --- /dev/null +++ b/Documentation/spec_ctrl.txt @@ -0,0 +1,86 @@ +=================== +Speculation Control +=================== + +Quite some CPUs have speculation related misfeatures which are in fact +vulnerabilites causing data leaks in various forms even accross privilege +domains. + +The kernel provides mitigation for such vulnerabilities in various +forms. Some of these mitigations are compile time configurable and some 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 0-2 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 +==== ================ =================================================== + +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. + +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 + +ENXIO Control of the selected speculation misfeature is not possible. + See PR_GET_SPECULATION_CTRL. +======= ================================================================= + +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); diff --git a/include/linux/nospec.h b/include/linux/nospec.h index e791ebc..700bb8a 100644 --- a/include/linux/nospec.h +++ b/include/linux/nospec.h @@ -55,4 +55,9 @@ static inline unsigned long array_index_mask_nospec(unsigned long index, \ (typeof(_i)) (_i & _mask); \ }) + +/* Speculation control prctl */ +int arch_prctl_spec_ctrl_get(unsigned long which); +int arch_prctl_spec_ctrl_set(unsigned long which, unsigned long ctrl); + #endif /* _LINUX_NOSPEC_H */ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index a8d0759..3b316be 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -197,4 +197,15 @@ struct prctl_mm_map { # define PR_CAP_AMBIENT_LOWER 3 # define PR_CAP_AMBIENT_CLEAR_ALL 4 +/* Per task speculation control */ +#define PR_GET_SPECULATION_CTRL 52 +#define PR_SET_SPECULATION_CTRL 53 +/* Speculation control variants */ +# define PR_SPEC_STORE_BYPASS 0 +/* Return and control values for PR_SET/GET_SPECULATION_CTRL */ +# define PR_SPEC_NOT_AFFECTED 0 +# define PR_SPEC_PRCTL (1UL << 0) +# define PR_SPEC_ENABLE (1UL << 1) +# define PR_SPEC_DISABLE (1UL << 2) + #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/sys.c b/kernel/sys.c index 6624919..d80c33f 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2075,6 +2075,16 @@ static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr) } #endif +int __weak arch_prctl_spec_ctrl_get(unsigned long which) +{ + return -EINVAL; +} + +int __weak arch_prctl_spec_ctrl_set(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) { @@ -2269,6 +2279,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_GET_FP_MODE: error = GET_FP_MODE(me); break; + case PR_GET_SPECULATION_CTRL: + if (arg3 || arg4 || arg5) + return -EINVAL; + error = arch_prctl_spec_ctrl_get(arg2); + break; + case PR_SET_SPECULATION_CTRL: + if (arg4 || arg5) + return -EINVAL; + error = arch_prctl_spec_ctrl_set(arg2, arg3); + break; default: error = -EINVAL; break;

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 065/101] x86/speculation: Create spec-ctrl.h to avoid include hell

by Srivatsa S. Bhat

From: Thomas Gleixner <tglx(a)linutronix.de> commit 28a2775217b17208811fa43a9e96bd1fdf417b86 upstream Having everything in nospec-branch.h creates a hell of dependencies when adding the prctl based switching mechanism. Move everything which is not required in nospec-branch.h to spec-ctrl.h and fix up the includes in the relevant files. Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Reviewed-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/nospec-branch.h | 14 -------------- arch/x86/include/asm/spec-ctrl.h | 21 +++++++++++++++++++++ arch/x86/kernel/cpu/amd.c | 2 +- arch/x86/kernel/cpu/bugs.c | 2 +- arch/x86/kvm/svm.c | 2 +- arch/x86/kvm/vmx.c | 2 +- 6 files changed, 25 insertions(+), 18 deletions(-) create mode 100644 arch/x86/include/asm/spec-ctrl.h diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index ac2fdc96..47c454c 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -183,26 +183,12 @@ enum spectre_v2_mitigation { extern void x86_spec_ctrl_set(u64); extern u64 x86_spec_ctrl_get_default(void); -/* - * 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. - */ -extern void x86_spec_ctrl_set_guest(u64); -extern void x86_spec_ctrl_restore_host(u64); - /* The Speculative Store Bypass disable variants */ enum ssb_mitigation { SPEC_STORE_BYPASS_NONE, SPEC_STORE_BYPASS_DISABLE, }; -/* AMD specific Speculative Store Bypass MSR data */ -extern u64 x86_amd_ls_cfg_base; -extern u64 x86_amd_ls_cfg_rds_mask; - extern char __indirect_thunk_start[]; extern char __indirect_thunk_end[]; diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h new file mode 100644 index 0000000..3ad6442 --- /dev/null +++ b/arch/x86/include/asm/spec-ctrl.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SPECCTRL_H_ +#define _ASM_X86_SPECCTRL_H_ + +#include <asm/nospec-branch.h> + +/* + * On VMENTER we must preserve whatever view of the SPEC_CTRL MSR + * the guest has, while on VMEXIT we restore the host view. This + * would be easier if SPEC_CTRL were architecturally maskable or + * shadowable for guests but this is not (currently) the case. + * Takes the guest view of SPEC_CTRL MSR as a parameter. + */ +extern void x86_spec_ctrl_set_guest(u64); +extern void x86_spec_ctrl_restore_host(u64); + +/* AMD specific Speculative Store Bypass MSR data */ +extern u64 x86_amd_ls_cfg_base; +extern u64 x86_amd_ls_cfg_rds_mask; + +#endif diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 4452f38..14e9849 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -9,7 +9,7 @@ #include <asm/processor.h> #include <asm/apic.h> #include <asm/cpu.h> -#include <asm/nospec-branch.h> +#include <asm/spec-ctrl.h> #include <asm/smp.h> #include <asm/pci-direct.h> #include <asm/delay.h> diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index b8911af..47a3cc0 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -12,7 +12,7 @@ #include <linux/cpu.h> #include <linux/module.h> -#include <asm/nospec-branch.h> +#include <asm/spec-ctrl.h> #include <asm/cmdline.h> #include <asm/bugs.h> #include <asm/processor.h> diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 4265437..df7827a 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -37,7 +37,7 @@ #include <asm/desc.h> #include <asm/debugreg.h> #include <asm/kvm_para.h> -#include <asm/nospec-branch.h> +#include <asm/spec-ctrl.h> #include <asm/virtext.h> #include "trace.h" diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 63c44a9..1814388 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -48,7 +48,7 @@ #include <asm/kexec.h> #include <asm/apic.h> #include <asm/irq_remapping.h> -#include <asm/nospec-branch.h> +#include <asm/spec-ctrl.h> #include "trace.h" #include "pmu.h"

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 064/101] x86/bugs/AMD: Add support to disable RDS on Fam[15, 16, 17]h if requested

by Srivatsa S. Bhat

From: David Woodhouse <dwmw(a)amazon.co.uk> commit 764f3c21588a059cd783c6ba0734d4db2d72822d upstream AMD does not need the Speculative Store Bypass mitigation to be enabled. The parameters for this are already available and can be done via MSR C001_1020. Each family uses a different bit in that MSR for this. [ tglx: Expose the bit mask via a variable and move the actual MSR fiddling into the bugs code as that's the right thing to do and also required to prepare for dynamic enable/disable ] [ Srivatsa: Removed __ro_after_init for 4.4.y ] Suggested-by: Borislav Petkov <bp(a)suse.de> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/nospec-branch.h | 4 ++++ arch/x86/kernel/cpu/amd.c | 26 ++++++++++++++++++++++++++ arch/x86/kernel/cpu/bugs.c | 27 ++++++++++++++++++++++++++- arch/x86/kernel/cpu/common.c | 4 ++++ 5 files changed, 61 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 9510f5f..b7cdd1c 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -204,6 +204,7 @@ #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_AMD_RDS (7*32+24) /* "" AMD RDS implementation */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index c786d01..ac2fdc96 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -199,6 +199,10 @@ enum ssb_mitigation { SPEC_STORE_BYPASS_DISABLE, }; +/* AMD specific Speculative Store Bypass MSR data */ +extern u64 x86_amd_ls_cfg_base; +extern u64 x86_amd_ls_cfg_rds_mask; + extern char __indirect_thunk_start[]; extern char __indirect_thunk_end[]; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 9b29414..4452f38 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -9,6 +9,7 @@ #include <asm/processor.h> #include <asm/apic.h> #include <asm/cpu.h> +#include <asm/nospec-branch.h> #include <asm/smp.h> #include <asm/pci-direct.h> #include <asm/delay.h> @@ -519,6 +520,26 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_MWAITX)) use_mwaitx_delay(); + + 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 RDS. + */ + if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) { + setup_force_cpu_cap(X86_FEATURE_RDS); + setup_force_cpu_cap(X86_FEATURE_AMD_RDS); + x86_amd_ls_cfg_rds_mask = 1ULL << bit; + } + } } static void early_init_amd(struct cpuinfo_x86 *c) @@ -794,6 +815,11 @@ static void init_amd(struct cpuinfo_x86 *c) /* AMD CPUs don't reset SS attributes on SYSRET, Xen does. */ if (!cpu_has(c, X86_FEATURE_XENPV)) set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); + + if (boot_cpu_has(X86_FEATURE_AMD_RDS)) { + set_cpu_cap(c, X86_FEATURE_RDS); + set_cpu_cap(c, X86_FEATURE_AMD_RDS); + } } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index c37e211..b8911af 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -40,6 +40,13 @@ static u64 x86_spec_ctrl_base; */ static u64 x86_spec_ctrl_mask = ~SPEC_CTRL_IBRS; +/* + * AMD specific MSR info for Speculative Store Bypass control. + * x86_amd_ls_cfg_rds_mask is initialized in identify_boot_cpu(). + */ +u64 x86_amd_ls_cfg_base; +u64 x86_amd_ls_cfg_rds_mask; + void __init check_bugs(void) { identify_boot_cpu(); @@ -51,7 +58,8 @@ void __init check_bugs(void) /* * Read the SPEC_CTRL MSR to account for reserved bits which may - * have unknown values. + * 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_IBRS)) rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); @@ -153,6 +161,14 @@ void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl) } EXPORT_SYMBOL_GPL(x86_spec_ctrl_restore_host); +static void x86_amd_rds_enable(void) +{ + u64 msrval = x86_amd_ls_cfg_base | x86_amd_ls_cfg_rds_mask; + + if (boot_cpu_has(X86_FEATURE_AMD_RDS)) + wrmsrl(MSR_AMD64_LS_CFG, msrval); +} + #ifdef RETPOLINE static bool spectre_v2_bad_module; @@ -442,6 +458,11 @@ static enum ssb_mitigation_cmd __init __ssb_select_mitigation(void) switch (cmd) { case SPEC_STORE_BYPASS_CMD_AUTO: + /* + * AMD platforms by default don't need SSB mitigation. + */ + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + break; case SPEC_STORE_BYPASS_CMD_ON: mode = SPEC_STORE_BYPASS_DISABLE; break; @@ -468,6 +489,7 @@ static enum ssb_mitigation_cmd __init __ssb_select_mitigation(void) x86_spec_ctrl_set(SPEC_CTRL_RDS); break; case X86_VENDOR_AMD: + x86_amd_rds_enable(); break; } } @@ -489,6 +511,9 @@ void x86_spec_ctrl_setup_ap(void) { if (boot_cpu_has(X86_FEATURE_IBRS)) x86_spec_ctrl_set(x86_spec_ctrl_base & ~x86_spec_ctrl_mask); + + if (ssb_mode == SPEC_STORE_BYPASS_DISABLE) + x86_amd_rds_enable(); } #ifdef CONFIG_SYSFS diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 2f1d403..7405c86 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -851,6 +851,10 @@ static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = { { 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, }, {} };

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 063/101] x86/bugs: Whitelist allowed SPEC_CTRL MSR values

by Srivatsa S. Bhat

From: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> commit 1115a859f33276fe8afb31c60cf9d8e657872558 upstream Intel and AMD SPEC_CTRL (0x48) MSR semantics may differ in the future (or in fact use different MSRs for the same functionality). As such a run-time mechanism is required to whitelist the appropriate MSR values. [ tglx: Made the variable __ro_after_init ] [ Srivatsa: Removed __ro_after_init for 4.4.y ] Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/kernel/cpu/bugs.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 56b84a5..c37e211 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -34,6 +34,12 @@ static void __init ssb_select_mitigation(void); */ static u64 x86_spec_ctrl_base; +/* + * The vendor and possibly platform specific bits which can be modified in + * x86_spec_ctrl_base. + */ +static u64 x86_spec_ctrl_mask = ~SPEC_CTRL_IBRS; + void __init check_bugs(void) { identify_boot_cpu(); @@ -116,7 +122,7 @@ static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; void x86_spec_ctrl_set(u64 val) { - if (val & ~(SPEC_CTRL_IBRS | SPEC_CTRL_RDS)) + if (val & x86_spec_ctrl_mask) WARN_ONCE(1, "SPEC_CTRL MSR value 0x%16llx is unknown.\n", val); else wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base | val); @@ -458,6 +464,7 @@ static enum ssb_mitigation_cmd __init __ssb_select_mitigation(void) switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_INTEL: x86_spec_ctrl_base |= SPEC_CTRL_RDS; + x86_spec_ctrl_mask &= ~SPEC_CTRL_RDS; x86_spec_ctrl_set(SPEC_CTRL_RDS); break; case X86_VENDOR_AMD: @@ -481,7 +488,7 @@ static void ssb_select_mitigation() void x86_spec_ctrl_setup_ap(void) { if (boot_cpu_has(X86_FEATURE_IBRS)) - x86_spec_ctrl_set(x86_spec_ctrl_base & (SPEC_CTRL_IBRS | SPEC_CTRL_RDS)); + x86_spec_ctrl_set(x86_spec_ctrl_base & ~x86_spec_ctrl_mask); } #ifdef CONFIG_SYSFS

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 062/101] x86/bugs/intel: Set proper CPU features and setup RDS

by Srivatsa S. Bhat

From: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> commit 772439717dbf703b39990be58d8d4e3e4ad0598a upstream Intel CPUs expose methods to: - Detect whether RDS capability is available via CPUID.7.0.EDX[31], - The SPEC_CTRL MSR(0x48), bit 2 set to enable RDS. - MSR_IA32_ARCH_CAPABILITIES, Bit(4) no need to enable RRS. With that in mind if spec_store_bypass_disable=[auto,on] is selected set at boot-time the SPEC_CTRL MSR to enable RDS if the platform requires it. Note that this does not fix the KVM case where the SPEC_CTRL is exposed to guests which can muck with it, see patch titled : KVM/SVM/VMX/x86/spectre_v2: Support the combination of guest and host IBRS. And for the firmware (IBRS to be set), see patch titled: x86/spectre_v2: Read SPEC_CTRL MSR during boot and re-use reserved bits [ tglx: Distangled it from the intel implementation and kept the call order ] Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Borislav Petkov <bp(a)suse.de> Reviewed-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/msr-index.h | 6 ++++++ arch/x86/kernel/cpu/bugs.c | 30 ++++++++++++++++++++++++++++-- arch/x86/kernel/cpu/common.c | 10 ++++++---- arch/x86/kernel/cpu/cpu.h | 3 +++ arch/x86/kernel/cpu/intel.c | 1 + 5 files changed, 44 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index f4701f0..a29edb7 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -35,6 +35,7 @@ #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_RDS (1 << 2) /* Reduced Data Speculation */ #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */ @@ -56,6 +57,11 @@ #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_RDS_NO (1 << 4) /* + * Not susceptible to Speculative Store Bypass + * attack, so no Reduced Data Speculation control + * required. + */ #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 826aa81..56b84a5 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -116,7 +116,7 @@ static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; void x86_spec_ctrl_set(u64 val) { - if (val & ~SPEC_CTRL_IBRS) + if (val & ~(SPEC_CTRL_IBRS | SPEC_CTRL_RDS)) WARN_ONCE(1, "SPEC_CTRL MSR value 0x%16llx is unknown.\n", val); else wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base | val); @@ -443,8 +443,28 @@ static enum ssb_mitigation_cmd __init __ssb_select_mitigation(void) break; } - if (mode != SPEC_STORE_BYPASS_NONE) + /* + * We have three CPU feature flags that are in play here: + * - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible. + * - X86_FEATURE_RDS - CPU is able to turn off speculative store bypass + * - X86_FEATURE_SPEC_STORE_BYPASS_DISABLE - engage the mitigation + */ + if (mode != SPEC_STORE_BYPASS_NONE) { 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_RDS; + x86_spec_ctrl_set(SPEC_CTRL_RDS); + break; + case X86_VENDOR_AMD: + break; + } + } + return mode; } @@ -458,6 +478,12 @@ static void ssb_select_mitigation() #undef pr_fmt +void x86_spec_ctrl_setup_ap(void) +{ + if (boot_cpu_has(X86_FEATURE_IBRS)) + x86_spec_ctrl_set(x86_spec_ctrl_base & (SPEC_CTRL_IBRS | SPEC_CTRL_RDS)); +} + #ifdef CONFIG_SYSFS ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index eb78ddf..2f1d403 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -859,7 +859,11 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = 0; - if (!x86_match_cpu(cpu_no_spec_store_bypass)) + 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_RDS_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); if (x86_match_cpu(cpu_no_speculation)) @@ -871,9 +875,6 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (x86_match_cpu(cpu_no_meltdown)) return; - if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); - /* Rogue Data Cache Load? No! */ if (ia32_cap & ARCH_CAP_RDCL_NO) return; @@ -1216,6 +1217,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) enable_sep_cpu(); #endif mtrr_ap_init(); + x86_spec_ctrl_setup_ap(); } struct msr_range { diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 2584265..3b19d82 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -46,4 +46,7 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[], extern void get_cpu_cap(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); + +extern void x86_spec_ctrl_setup_ap(void); + #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 77d9f68..ac25d1e5 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -119,6 +119,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_STIBP); setup_clear_cpu_cap(X86_FEATURE_SPEC_CTRL); setup_clear_cpu_cap(X86_FEATURE_INTEL_STIBP); + setup_clear_cpu_cap(X86_FEATURE_RDS); } /*

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 061/101] x86/bugs: Provide boot parameters for the spec_store_bypass_disable mitigation

by Srivatsa S. Bhat

From: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> commit 24f7fc83b9204d20f878c57cb77d261ae825e033 upstream Contemporary high performance processors use a common industry-wide optimization known as "Speculative Store Bypass" in which loads from addresses to which a recent store has occurred may (speculatively) see an older value. Intel refers to this feature as "Memory Disambiguation" which is part of their "Smart Memory Access" capability. Memory Disambiguation can expose a cache side-channel attack against such speculatively read values. An attacker can create exploit code that allows them to read memory outside of a sandbox environment (for example, malicious JavaScript in a web page), or to perform more complex attacks against code running within the same privilege level, e.g. via the stack. As a first step to mitigate against such attacks, provide two boot command line control knobs: nospec_store_bypass_disable spec_store_bypass_disable=[off,auto,on] By default affected x86 processors will power on with Speculative Store Bypass enabled. Hence the provided kernel parameters are written from the point of view of whether to enable a mitigation or not. The parameters are as follows: - auto - Kernel detects whether your CPU model contains an implementation of Speculative Store Bypass and picks the most appropriate mitigation. - on - disable Speculative Store Bypass - off - enable Speculative Store Bypass [ tglx: Reordered the checks so that the whole evaluation is not done when the CPU does not support RDS ] Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Borislav Petkov <bp(a)suse.de> Reviewed-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- Documentation/kernel-parameters.txt | 33 +++++++++++ arch/x86/include/asm/cpufeatures.h | 1 arch/x86/include/asm/nospec-branch.h | 6 ++ arch/x86/kernel/cpu/bugs.c | 103 ++++++++++++++++++++++++++++++++++ 4 files changed, 143 insertions(+) diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index e60d0b5..dc138b8 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2460,6 +2460,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted. allow data leaks with this option, which is equivalent to spectre_v2=off. + nospec_store_bypass_disable + [HW] Disable all mitigations for the Speculative Store Bypass vulnerability + noxsave [BUGS=X86] Disables x86 extended register state save and restore using xsave. The kernel will fallback to enabling legacy floating-point and sse state. @@ -3623,6 +3626,36 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Not specifying this option is equivalent to spectre_v2=auto. + spec_store_bypass_disable= + [HW] Control Speculative Store Bypass (SSB) Disable mitigation + (Speculative Store Bypass vulnerability) + + Certain CPUs are vulnerable to an exploit against a + a common industry wide performance optimization known + as "Speculative Store Bypass" in which recent stores + to the same memory location may not be observed by + later loads during speculative execution. The idea + is that such stores are unlikely and that they can + be detected prior to instruction retirement at the + end of a particular speculation execution window. + + In vulnerable processors, the speculatively forwarded + store can be used in a cache side channel attack, for + example to read memory to which the attacker does not + directly have access (e.g. inside sandboxed code). + + This parameter controls whether the Speculative Store + Bypass optimization is used. + + on - Unconditionally disable Speculative Store Bypass + off - Unconditionally enable Speculative Store Bypass + auto - Kernel detects whether the CPU model contains an + implementation of Speculative Store Bypass and + picks the most appropriate mitigation + + Not specifying this option is equivalent to + spec_store_bypass_disable=auto. + spia_io_base= [HW,MTD] spia_fio_base= spia_pedr= diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 3fce65d..9510f5f 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -203,6 +203,7 @@ #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. */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 11db69a..c786d01 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -193,6 +193,12 @@ extern u64 x86_spec_ctrl_get_default(void); extern void x86_spec_ctrl_set_guest(u64); extern void x86_spec_ctrl_restore_host(u64); +/* The Speculative Store Bypass disable variants */ +enum ssb_mitigation { + SPEC_STORE_BYPASS_NONE, + SPEC_STORE_BYPASS_DISABLE, +}; + extern char __indirect_thunk_start[]; extern char __indirect_thunk_end[]; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 0ad13b1..826aa81 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -26,6 +26,7 @@ #include <asm/intel-family.h> static void __init spectre_v2_select_mitigation(void); +static void __init ssb_select_mitigation(void); /* * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any @@ -52,6 +53,12 @@ void __init check_bugs(void) /* 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. @@ -357,6 +364,99 @@ retpoline_auto: } #undef pr_fmt +#define pr_fmt(fmt) "Speculative Store Bypass: " fmt + +static enum ssb_mitigation ssb_mode = 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, +}; + +static const char *ssb_strings[] = { + [SPEC_STORE_BYPASS_NONE] = "Vulnerable", + [SPEC_STORE_BYPASS_DISABLE] = "Mitigation: Speculative Store Bypass disabled" +}; + +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 */ +}; + +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_cmd __init __ssb_select_mitigation(void) +{ + enum ssb_mitigation mode = SPEC_STORE_BYPASS_NONE; + enum ssb_mitigation_cmd cmd; + + if (!boot_cpu_has(X86_FEATURE_RDS)) + 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_ON: + mode = SPEC_STORE_BYPASS_DISABLE; + break; + case SPEC_STORE_BYPASS_CMD_NONE: + break; + } + + if (mode != SPEC_STORE_BYPASS_NONE) + setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE); + return mode; +} + +static void ssb_select_mitigation() +{ + 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 #ifdef CONFIG_SYSFS @@ -382,6 +482,9 @@ ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, 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; }

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 060/101] x86/cpufeatures: Add X86_FEATURE_RDS

by Srivatsa S. Bhat

From: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> commit 0cc5fa00b0a88dad140b4e5c2cead9951ad36822 upstream Add the CPU feature bit CPUID.7.0.EDX[31] which indicates whether the CPU supports Reduced Data Speculation. [ tglx: Split it out from a later patch ] Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/cpufeatures.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 08cf4f7..3fce65d 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -297,6 +297,7 @@ #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_RDS (18*32+31) /* Reduced Data Speculation */ /* * BUG word(s)

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 059/101] x86/bugs: Expose /sys/../spec_store_bypass

by Srivatsa S. Bhat

From: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> commit c456442cd3a59eeb1d60293c26cbe2ff2c4e42cf upstream Add the sysfs file for the new vulerability. It does not do much except show the words 'Vulnerable' for recent x86 cores. Intel cores prior to family 6 are known not to be vulnerable, and so are some Atoms and some Xeon Phi. It assumes that older Cyrix, Centaur, etc. cores are immune. Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Borislav Petkov <bp(a)suse.de> Reviewed-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- Documentation/ABI/testing/sysfs-devices-system-cpu | 1 + arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/kernel/cpu/bugs.c | 5 ++++ arch/x86/kernel/cpu/common.c | 23 ++++++++++++++++++++ drivers/base/cpu.c | 8 +++++++ include/linux/cpu.h | 2 ++ 6 files changed, 40 insertions(+) diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index ea6a043..50f9568 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -276,6 +276,7 @@ What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/meltdown /sys/devices/system/cpu/vulnerabilities/spectre_v1 /sys/devices/system/cpu/vulnerabilities/spectre_v2 + /sys/devices/system/cpu/vulnerabilities/spec_store_bypass Date: January 2018 Contact: Linux kernel mailing list <linux-kernel(a)vger.kernel.org> Description: Information about CPU vulnerabilities diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index bc76bf3..08cf4f7 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -315,5 +315,6 @@ #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/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index e71e281..0ad13b1 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -403,4 +403,9 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c { return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V2); } + +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 97558d1..eb78ddf 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -835,10 +835,33 @@ static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { {} }; +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_ANY, 4, }, + {} +}; + static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = 0; + if (!x86_match_cpu(cpu_no_spec_store_bypass)) + setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); + if (x86_match_cpu(cpu_no_speculation)) return; diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 3db71af..143edea 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -518,14 +518,22 @@ 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/include/linux/cpu.h b/include/linux/cpu.h index 7e04bcd..2f9d120 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -46,6 +46,8 @@ 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,

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 058/101] x86/cpu/intel: Add Knights Mill to Intel family

by Srivatsa S. Bhat

From: Piotr Luc <piotr.luc(a)intel.com> commit 0047f59834e5947d45f34f5f12eb330d158f700b upstream Add CPUID of Knights Mill (KNM) processor to Intel family list. Signed-off-by: Piotr Luc <piotr.luc(a)intel.com> Reviewed-by: Dave Hansen <dave.hansen(a)intel.com> Cc: Andy Lutomirski <luto(a)kernel.org> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Brian Gerst <brgerst(a)gmail.com> Cc: Denys Vlasenko <dvlasenk(a)redhat.com> Cc: H. Peter Anvin <hpa(a)zytor.com> Cc: Josh Poimboeuf <jpoimboe(a)redhat.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Link: http://lkml.kernel.org/r/20161012180520.30976-1-piotr.luc@intel.com Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/intel-family.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 0b27c1e..e13ff5a 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -67,5 +67,6 @@ /* Xeon Phi */ #define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */ +#define INTEL_FAM6_XEON_PHI_KNM 0x85 /* Knights Mill */ #endif /* _ASM_X86_INTEL_FAMILY_H */

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 057/101] x86/cpu: Rename Merrifield2 to Moorefield

by Srivatsa S. Bhat

From: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com> commit f5fbf848303c8704d0e1a1e7cabd08fd0a49552f upstream Merrifield2 is actually Moorefield. Rename it accordingly and drop tail digit from Merrifield1. Signed-off-by: Andy Shevchenko <andriy.shevchenko(a)linux.intel.com> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Link: http://lkml.kernel.org/r/20160906184254.94440-1-andriy.shevchenko@linux.int… Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/intel-family.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 12fa187..0b27c1e 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -58,8 +58,8 @@ #define INTEL_FAM6_ATOM_SILVERMONT1 0x37 /* BayTrail/BYT / Valleyview */ #define INTEL_FAM6_ATOM_SILVERMONT2 0x4D /* Avaton/Rangely */ #define INTEL_FAM6_ATOM_AIRMONT 0x4C /* CherryTrail / Braswell */ -#define INTEL_FAM6_ATOM_MERRIFIELD1 0x4A /* Tangier */ -#define INTEL_FAM6_ATOM_MERRIFIELD2 0x5A /* Annidale */ +#define INTEL_FAM6_ATOM_MERRIFIELD 0x4A /* Tangier */ +#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Annidale */ #define INTEL_FAM6_ATOM_GOLDMONT 0x5C #define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */ #define INTEL_FAM6_ATOM_GEMINI_LAKE 0x7A

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 056/101] x86/bugs, KVM: Support the combination of guest and host IBRS

by Srivatsa S. Bhat

From: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> commit 5cf687548705412da47c9cec342fd952d71ed3d5 upstream A guest may modify the SPEC_CTRL MSR from the value used by the kernel. Since the kernel doesn't use IBRS, this means a value of zero is what is needed in the host. But the 336996-Speculative-Execution-Side-Channel-Mitigations.pdf refers to the other bits as reserved so the kernel should respect the boot time SPEC_CTRL value and use that. This allows to deal with future extensions to the SPEC_CTRL interface if any at all. Note: This uses wrmsrl() instead of native_wrmsl(). I does not make any difference as paravirt will over-write the callq *0xfff.. with the wrmsrl assembler code. Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Borislav Petkov <bp(a)suse.de> Reviewed-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> [ Srivatsa: Backported to 4.4.y, skipping the KVM changes in this patch. ] Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/nospec-branch.h | 10 ++++++++++ arch/x86/kernel/cpu/bugs.c | 18 ++++++++++++++++++ 2 files changed, 28 insertions(+) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index daec318..11db69a 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -183,6 +183,16 @@ enum spectre_v2_mitigation { extern void x86_spec_ctrl_set(u64); extern u64 x86_spec_ctrl_get_default(void); +/* + * 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. + */ +extern void x86_spec_ctrl_set_guest(u64); +extern void x86_spec_ctrl_restore_host(u64); + extern char __indirect_thunk_start[]; extern char __indirect_thunk_end[]; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 42c2204..e71e281 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -122,6 +122,24 @@ u64 x86_spec_ctrl_get_default(void) } EXPORT_SYMBOL_GPL(x86_spec_ctrl_get_default); +void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl) +{ + if (!boot_cpu_has(X86_FEATURE_IBRS)) + return; + if (x86_spec_ctrl_base != guest_spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, guest_spec_ctrl); +} +EXPORT_SYMBOL_GPL(x86_spec_ctrl_set_guest); + +void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl) +{ + if (!boot_cpu_has(X86_FEATURE_IBRS)) + return; + if (x86_spec_ctrl_base != guest_spec_ctrl) + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); +} +EXPORT_SYMBOL_GPL(x86_spec_ctrl_restore_host); + #ifdef RETPOLINE static bool spectre_v2_bad_module;

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 055/101] x86/bugs: Read SPEC_CTRL MSR during boot and re-use reserved bits

by Srivatsa S. Bhat

From: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> commit 1b86883ccb8d5d9506529d42dbe1a5257cb30b18 upstream The 336996-Speculative-Execution-Side-Channel-Mitigations.pdf refers to all the other bits as reserved. The Intel SDM glossary defines reserved as implementation specific - aka unknown. As such at bootup this must be taken it into account and proper masking for the bits in use applied. A copy of this document is available at https://bugzilla.kernel.org/show_bug.cgi?id=199511 [ tglx: Made x86_spec_ctrl_base __ro_after_init ] [ Srivatsa: Removed __ro_after_init for 4.4.y ] Suggested-by: Jon Masters <jcm(a)redhat.com> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Borislav Petkov <bp(a)suse.de> Reviewed-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/nospec-branch.h | 24 ++++++++++++++++++++---- arch/x86/kernel/cpu/bugs.c | 27 +++++++++++++++++++++++++++ 2 files changed, 47 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 6403016..daec318 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -172,6 +172,17 @@ enum spectre_v2_mitigation { SPECTRE_V2_IBRS, }; +/* + * The Intel specification for the SPEC_CTRL MSR requires that we + * preserve any already set reserved bits at boot time (e.g. for + * future additions that this kernel is not currently aware of). + * We then set any additional mitigation bits that we want + * ourselves and always use this as the base for SPEC_CTRL. + * We also use this when handling guest entry/exit as below. + */ +extern void x86_spec_ctrl_set(u64); +extern u64 x86_spec_ctrl_get_default(void); + extern char __indirect_thunk_start[]; extern char __indirect_thunk_end[]; @@ -208,8 +219,9 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) 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); } /* @@ -220,14 +232,18 @@ static inline void indirect_branch_prediction_barrier(void) */ #define firmware_restrict_branch_speculation_start() \ do { \ + u64 val = x86_spec_ctrl_get_default() | 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_get_default(); \ + \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, val, \ X86_FEATURE_USE_IBRS_FW); \ preempt_enable(); \ } while (0) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 75f3d49..42c2204 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -27,6 +27,12 @@ static void __init spectre_v2_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. + */ +static u64 x86_spec_ctrl_base; + void __init check_bugs(void) { identify_boot_cpu(); @@ -36,6 +42,13 @@ 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. + */ + if (boot_cpu_has(X86_FEATURE_IBRS)) + rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + /* Select the proper spectre mitigation before patching alternatives */ spectre_v2_select_mitigation(); @@ -94,6 +107,20 @@ static const char *spectre_v2_strings[] = { static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; +void x86_spec_ctrl_set(u64 val) +{ + if (val & ~SPEC_CTRL_IBRS) + WARN_ONCE(1, "SPEC_CTRL MSR value 0x%16llx is unknown.\n", val); + else + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base | val); +} +EXPORT_SYMBOL_GPL(x86_spec_ctrl_set); + +u64 x86_spec_ctrl_get_default(void) +{ + return x86_spec_ctrl_base; +} +EXPORT_SYMBOL_GPL(x86_spec_ctrl_get_default); #ifdef RETPOLINE static bool spectre_v2_bad_module;

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 054/101] x86/bugs: Concentrate bug reporting into a separate function

by Srivatsa S. Bhat

From: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> commit d1059518b4789cabe34bb4b714d07e6089c82ca1 upstream Those SysFS functions have a similar preamble, as such make common code to handle them. Suggested-by: Borislav Petkov <bp(a)suse.de> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Borislav Petkov <bp(a)suse.de> Reviewed-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/kernel/cpu/bugs.c | 46 +++++++++++++++++++++++++++++++------------- 1 file changed, 32 insertions(+), 14 deletions(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index b294fdc..75f3d49 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -314,30 +314,48 @@ retpoline_auto: #undef pr_fmt #ifdef CONFIG_SYSFS -ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) + +ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, + char *buf, unsigned int bug) { - if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + if (!boot_cpu_has_bug(bug)) return sprintf(buf, "Not affected\n"); - if (boot_cpu_has(X86_FEATURE_KAISER)) - return sprintf(buf, "Mitigation: PTI\n"); + + switch (bug) { + case X86_BUG_CPU_MELTDOWN: + if (boot_cpu_has(X86_FEATURE_KAISER)) + return sprintf(buf, "Mitigation: PTI\n"); + + break; + + case X86_BUG_SPECTRE_V1: + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); + + case X86_BUG_SPECTRE_V2: + return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", + spectre_v2_module_string()); + + 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 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()); + return cpu_show_common(dev, attr, buf, X86_BUG_SPECTRE_V2); } #endif

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 053/101] x86/bugs: Concentrate bug detection into a separate function

by Srivatsa S. Bhat

From: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> commit 4a28bfe3267b68e22c663ac26185aa16c9b879ef upstream Combine the various logic which goes through all those x86_cpu_id matching structures in one function. Suggested-by: Borislav Petkov <bp(a)suse.de> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk(a)oracle.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Borislav Petkov <bp(a)suse.de> Reviewed-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/kernel/cpu/common.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 48499b4..97558d1 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -835,21 +835,27 @@ static const __initconst struct x86_cpu_id cpu_no_meltdown[] = { {} }; -static bool __init cpu_vulnerable_to_meltdown(struct cpuinfo_x86 *c) +static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = 0; + 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 false; + return; if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES)) rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); /* 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); } /* @@ -898,12 +904,7 @@ 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);

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 052/101] x86/nospec: Simplify alternative_msr_write()

by Srivatsa S. Bhat

From: Linus Torvalds <torvalds(a)linux-foundation.org> commit 1aa7a5735a41418d8e01fa7c9565eb2657e2ea3f upstream The macro is not type safe and I did look for why that "g" constraint for the asm doesn't work: it's because the asm is more fundamentally wrong. It does movl %[val], %%eax but "val" isn't a 32-bit value, so then gcc will pass it in a register, and generate code like movl %rsi, %eax and gas will complain about a nonsensical 'mov' instruction (it's moving a 64-bit register to a 32-bit one). Passing it through memory will just hide the real bug - gcc still thinks the memory location is 64-bit, but the "movl" will only load the first 32 bits and it all happens to work because x86 is little-endian. Convert it to a type safe inline function with a little trick which hands the feature into the ALTERNATIVE macro. Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Reviewed-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/nospec-branch.h | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index b9dd1d9..6403016 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -195,15 +195,16 @@ 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" (val), + "d" (val >> 32), + [feature] "i" (feature) + : "memory"); +} static inline void indirect_branch_prediction_barrier(void) {

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 050/101] xen: set cpu capabilities from xen_start_kernel()

by Srivatsa S. Bhat

From: Juergen Gross <jgross(a)suse.com> Upstream commit: 0808e80cb760de2733c0527d2090ed2205a1eef8 ("xen: set cpu capabilities from xen_start_kernel()") There is no need to set the same capabilities for each cpu individually. This can easily be done for all cpus when starting the kernel. Signed-off-by: Juergen Gross <jgross(a)suse.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky(a)oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/xen/enlighten.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index cbef64b..2d7ab4e 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -460,6 +460,14 @@ static void __init xen_init_cpuid_mask(void) cpuid_leaf1_ecx_set_mask = (1 << (X86_FEATURE_MWAIT % 32)); } +static void __init xen_init_capabilities(void) +{ + if (xen_pv_domain()) { + setup_clear_cpu_cap(X86_BUG_SYSRET_SS_ATTRS); + setup_force_cpu_cap(X86_FEATURE_XENPV); + } +} + static void xen_set_debugreg(int reg, unsigned long val) { HYPERVISOR_set_debugreg(reg, val); @@ -1587,6 +1595,7 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_init_irq_ops(); xen_init_cpuid_mask(); + xen_init_capabilities(); #ifdef CONFIG_X86_LOCAL_APIC /* @@ -1883,14 +1892,6 @@ bool xen_hvm_need_lapic(void) } EXPORT_SYMBOL_GPL(xen_hvm_need_lapic); -static void xen_set_cpu_features(struct cpuinfo_x86 *c) -{ - if (xen_pv_domain()) { - clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); - set_cpu_cap(c, X86_FEATURE_XENPV); - } -} - const struct hypervisor_x86 x86_hyper_xen = { .name = "Xen", .detect = xen_platform, @@ -1898,7 +1899,6 @@ const struct hypervisor_x86 x86_hyper_xen = { .init_platform = xen_hvm_guest_init, #endif .x2apic_available = xen_x2apic_para_available, - .set_cpu_features = xen_set_cpu_features, }; EXPORT_SYMBOL(x86_hyper_xen);

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 049/101] selftest/seccomp: Fix the seccomp(2) signature

by Srivatsa S. Bhat

From: Mickaël Salaün <mic(a)digikod.net> commit 505ce68c6da3432454c62e43c24a22ea5b1d754b upstream Signed-off-by: Mickaël Salaün <mic(a)digikod.net> Cc: Andy Lutomirski <luto(a)amacapital.net> Cc: Kees Cook <keescook(a)chromium.org> Cc: Shuah Khan <shuahkh(a)osg.samsung.com> Cc: Will Drewry <wad(a)chromium.org> Acked-by: Kees Cook <keescook(a)chromium.org> Signed-off-by: Shuah Khan <shuahkh(a)osg.samsung.com> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- tools/testing/selftests/seccomp/seccomp_bpf.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index d446346..29487e0 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -1481,10 +1481,10 @@ TEST_F(TRACE_syscall, syscall_dropped) #endif #ifndef seccomp -int seccomp(unsigned int op, unsigned int flags, struct sock_fprog *filter) +int seccomp(unsigned int op, unsigned int flags, void *args) { errno = 0; - return syscall(__NR_seccomp, op, flags, filter); + return syscall(__NR_seccomp, op, flags, args); } #endif

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 048/101] selftest/seccomp: Fix the flag name SECCOMP_FILTER_FLAG_TSYNC

by Srivatsa S. Bhat

From: Mickaël Salaün <mic(a)digikod.net> commit 6c045d07bb305c527140bdec4cf8ab50f7c980d8 upstream Rename SECCOMP_FLAG_FILTER_TSYNC to SECCOMP_FILTER_FLAG_TSYNC to match the UAPI. Signed-off-by: Mickaël Salaün <mic(a)digikod.net> Cc: Andy Lutomirski <luto(a)amacapital.net> Cc: Kees Cook <keescook(a)chromium.org> Cc: Shuah Khan <shuahkh(a)osg.samsung.com> Cc: Will Drewry <wad(a)chromium.org> Acked-by: Kees Cook <keescook(a)chromium.org> Signed-off-by: Shuah Khan <shuahkh(a)osg.samsung.com> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- tools/testing/selftests/seccomp/seccomp_bpf.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 882fe83..d446346 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -1476,8 +1476,8 @@ TEST_F(TRACE_syscall, syscall_dropped) #define SECCOMP_SET_MODE_FILTER 1 #endif -#ifndef SECCOMP_FLAG_FILTER_TSYNC -#define SECCOMP_FLAG_FILTER_TSYNC 1 +#ifndef SECCOMP_FILTER_FLAG_TSYNC +#define SECCOMP_FILTER_FLAG_TSYNC 1 #endif #ifndef seccomp @@ -1592,7 +1592,7 @@ TEST(TSYNC_first) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } - ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC, + ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC, &prog); ASSERT_NE(ENOSYS, errno) { TH_LOG("Kernel does not support seccomp syscall!"); @@ -1810,7 +1810,7 @@ TEST_F(TSYNC, two_siblings_with_ancestor) self->sibling_count++; } - ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC, + ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC, &self->apply_prog); ASSERT_EQ(0, ret) { TH_LOG("Could install filter on all threads!"); @@ -1871,7 +1871,7 @@ TEST_F(TSYNC, two_siblings_with_no_filter) TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!"); } - ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC, + ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC, &self->apply_prog); ASSERT_NE(ENOSYS, errno) { TH_LOG("Kernel does not support seccomp syscall!"); @@ -1919,7 +1919,7 @@ TEST_F(TSYNC, two_siblings_with_one_divergence) self->sibling_count++; } - ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC, + ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC, &self->apply_prog); ASSERT_EQ(self->sibling[0].system_tid, ret) { TH_LOG("Did not fail on diverged sibling."); @@ -1971,7 +1971,7 @@ TEST_F(TSYNC, two_siblings_not_under_filter) TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER!"); } - ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC, + ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC, &self->apply_prog); ASSERT_EQ(ret, self->sibling[0].system_tid) { TH_LOG("Did not fail on diverged sibling."); @@ -2000,7 +2000,7 @@ TEST_F(TSYNC, two_siblings_not_under_filter) /* Switch to the remaining sibling */ sib = !sib; - ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC, + ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC, &self->apply_prog); ASSERT_EQ(0, ret) { TH_LOG("Expected the remaining sibling to sync"); @@ -2023,7 +2023,7 @@ TEST_F(TSYNC, two_siblings_not_under_filter) while (!kill(self->sibling[sib].system_tid, 0)) sleep(0.1); - ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC, + ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC, &self->apply_prog); ASSERT_EQ(0, ret); /* just us chickens */ }

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 047/101] x86/speculation: Remove Skylake C2 from Speculation Control microcode blacklist

by Srivatsa S. Bhat

From: Alexander Sergeyev <sergeev917(a)gmail.com> commit e3b3121fa8da94cb20f9e0c64ab7981ae47fd085 upstream. In accordance with Intel's microcode revision guidance from March 6 MCU rev 0xc2 is cleared on both Skylake H/S and Skylake Xeon E3 processors that share CPUID 506E3. Signed-off-by: Alexander Sergeyev <sergeev917(a)gmail.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: Jia Zhang <qianyue.zj(a)alibaba-inc.com> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Kyle Huey <me(a)kylehuey.com> Cc: David Woodhouse <dwmw(a)amazon.co.uk> Link: https://lkml.kernel.org/r/20180313193856.GA8580@localhost.localdomain Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/kernel/cpu/intel.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index dcc0349..77d9f68 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -29,7 +29,7 @@ /* * Early microcode releases for the Spectre v2 mitigation were broken. * Information taken from; - * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/01/microcode-up… + * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/03/microcode-up… * - https://kb.vmware.com/s/article/52345 * - Microcode revisions observed in the wild * - Release note from 20180108 microcode release @@ -47,7 +47,6 @@ static const struct sku_microcode spectre_bad_microcodes[] = { { INTEL_FAM6_KABYLAKE_MOBILE, 0x09, 0x80 }, { INTEL_FAM6_SKYLAKE_X, 0x03, 0x0100013e }, { INTEL_FAM6_SKYLAKE_X, 0x04, 0x0200003c }, - { INTEL_FAM6_SKYLAKE_DESKTOP, 0x03, 0xc2 }, { INTEL_FAM6_BROADWELL_CORE, 0x04, 0x28 }, { INTEL_FAM6_BROADWELL_GT3E, 0x01, 0x1b }, { INTEL_FAM6_BROADWELL_XEON_D, 0x02, 0x14 },

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 046/101] x86/speculation: Move firmware_restrict_branch_speculation_*() from C to CPP

by Srivatsa S. Bhat

From: Ingo Molnar <mingo(a)kernel.org> commit d72f4e29e6d84b7ec02ae93088aa459ac70e733b upstream. firmware_restrict_branch_speculation_*() recently started using preempt_enable()/disable(), but those are relatively high level primitives and cause build failures on some 32-bit builds. Since we want to keep <asm/nospec-branch.h> low level, convert them to macros to avoid header hell... Cc: David Woodhouse <dwmw(a)amazon.co.uk> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: arjan.van.de.ven(a)intel.com Cc: bp(a)alien8.de Cc: dave.hansen(a)intel.com Cc: jmattson(a)google.com Cc: karahmed(a)amazon.de Cc: kvm(a)vger.kernel.org Cc: pbonzini(a)redhat.com Cc: rkrcmar(a)redhat.com Cc: linux-kernel(a)vger.kernel.org Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/nospec-branch.h | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 36ded24..b9dd1d9 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -214,20 +214,22 @@ static inline void indirect_branch_prediction_barrier(void) /* * With retpoline, we must use IBRS to restrict branch prediction * before calling into firmware. + * + * (Implemented as CPP macros due to header hell.) */ -static inline void firmware_restrict_branch_speculation_start(void) -{ - preempt_disable(); - alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS, - X86_FEATURE_USE_IBRS_FW); -} +#define firmware_restrict_branch_speculation_start() \ +do { \ + preempt_disable(); \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS, \ + X86_FEATURE_USE_IBRS_FW); \ +} while (0) -static inline void firmware_restrict_branch_speculation_end(void) -{ - alternative_msr_write(MSR_IA32_SPEC_CTRL, 0, - X86_FEATURE_USE_IBRS_FW); - preempt_enable(); -} +#define firmware_restrict_branch_speculation_end() \ +do { \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, 0, \ + X86_FEATURE_USE_IBRS_FW); \ + preempt_enable(); \ +} while (0) #endif /* __ASSEMBLY__ */

7 years, 1 month

1
0
0 0

[PATCH 4.4.y 045/101] x86/speculation: Use IBRS if available before calling into firmware

by Srivatsa S. Bhat

From: David Woodhouse <dwmw(a)amazon.co.uk> commit dd84441a797150dcc49298ec95c459a8891d8bb1 upstream. Retpoline means the kernel is safe because it has no indirect branches. But firmware isn't, so use IBRS for firmware calls if it's available. Block preemption while IBRS is set, although in practice the call sites already had to be doing that. Ignore hpwdt.c for now. It's taking spinlocks and calling into firmware code, from an NMI handler. I don't want to touch that with a bargepole. Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Reviewed-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: arjan.van.de.ven(a)intel.com Cc: bp(a)alien8.de Cc: dave.hansen(a)intel.com Cc: jmattson(a)google.com Cc: karahmed(a)amazon.de Cc: kvm(a)vger.kernel.org Cc: pbonzini(a)redhat.com Cc: rkrcmar(a)redhat.com Link: http://lkml.kernel.org/r/1519037457-7643-2-git-send-email-dwmw@amazon.co.uk Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> [ Srivatsa: Backported to 4.4.y, patching the efi_call_virt() family of functions, which are the 4.4.y-equivalents of arch_efi_call_virt_setup()/teardown() ] Signed-off-by: Srivatsa S. Bhat <srivatsa(a)csail.mit.edu> Reviewed-by: Matt Helsley (VMware) <matt.helsley(a)gmail.com> Reviewed-by: Alexey Makhalov <amakhalov(a)vmware.com> Reviewed-by: Bo Gan <ganb(a)vmware.com> --- arch/x86/include/asm/apm.h | 6 +++++ arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/efi.h | 7 ++++++ arch/x86/include/asm/nospec-branch.h | 39 ++++++++++++++++++++++++++-------- arch/x86/kernel/cpu/bugs.c | 12 ++++++++++ arch/x86/platform/efi/efi_64.c | 3 +++ 6 files changed, 58 insertions(+), 10 deletions(-) diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h index 20370c6..3d1ec41 100644 --- a/arch/x86/include/asm/apm.h +++ b/arch/x86/include/asm/apm.h @@ -6,6 +6,8 @@ #ifndef _ASM_X86_MACH_DEFAULT_APM_H #define _ASM_X86_MACH_DEFAULT_APM_H +#include <asm/nospec-branch.h> + #ifdef APM_ZERO_SEGS # define APM_DO_ZERO_SEGS \ "pushl %%ds\n\t" \ @@ -31,6 +33,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ + firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -43,6 +46,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, "=S" (*esi) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); + firmware_restrict_branch_speculation_end(); } static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in, @@ -55,6 +59,7 @@ static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in, * N.B. We do NOT need a cld after the BIOS call * because we always save and restore the flags. */ + firmware_restrict_branch_speculation_start(); __asm__ __volatile__(APM_DO_ZERO_SEGS "pushl %%edi\n\t" "pushl %%ebp\n\t" @@ -67,6 +72,7 @@ static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in, "=S" (si) : "a" (func), "b" (ebx_in), "c" (ecx_in) : "memory", "cc"); + firmware_restrict_branch_speculation_end(); return error; } diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 782005d..bc76bf3 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -202,6 +202,7 @@ #define X86_FEATURE_KAISER ( 7*32+31) /* CONFIG_PAGE_TABLE_ISOLATION w/o nokaiser */ #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 */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 0010c78..7e5a2ff 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -3,6 +3,7 @@ #include <asm/fpu/api.h> #include <asm/pgtable.h> +#include <asm/nospec-branch.h> /* * We map the EFI regions needed for runtime services non-contiguously, @@ -39,8 +40,10 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...); ({ \ efi_status_t __s; \ kernel_fpu_begin(); \ + firmware_restrict_branch_speculation_start(); \ __s = ((efi_##f##_t __attribute__((regparm(0)))*) \ efi.systab->runtime->f)(args); \ + firmware_restrict_branch_speculation_end(); \ kernel_fpu_end(); \ __s; \ }) @@ -49,8 +52,10 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...); #define __efi_call_virt(f, args...) \ ({ \ kernel_fpu_begin(); \ + firmware_restrict_branch_speculation_start(); \ ((efi_##f##_t __attribute__((regparm(0)))*) \ efi.systab->runtime->f)(args); \ + firmware_restrict_branch_speculation_end(); \ kernel_fpu_end(); \ }) @@ -71,7 +76,9 @@ extern u64 asmlinkage efi_call(void *fp, ...); efi_sync_low_kernel_mappings(); \ preempt_disable(); \ __kernel_fpu_begin(); \ + firmware_restrict_branch_speculation_start(); \ __s = efi_call((void *)efi.systab->runtime->f, __VA_ARGS__); \ + firmware_restrict_branch_speculation_end(); \ __kernel_fpu_end(); \ preempt_enable(); \ __s; \ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index bca2860..36ded24 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -195,17 +195,38 @@ 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 inline void indirect_branch_prediction_barrier(void) { - asm volatile(ALTERNATIVE("", - "movl %[msr], %%ecx\n\t" - "movl %[val], %%eax\n\t" - "movl $0, %%edx\n\t" - "wrmsr", - X86_FEATURE_USE_IBPB) - : : [msr] "i" (MSR_IA32_PRED_CMD), - [val] "i" (PRED_CMD_IBPB) - : "eax", "ecx", "edx", "memory"); + alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, + X86_FEATURE_USE_IBPB); +} + +/* + * With retpoline, we must use IBRS to restrict branch prediction + * before calling into firmware. + */ +static inline void firmware_restrict_branch_speculation_start(void) +{ + preempt_disable(); + alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS, + X86_FEATURE_USE_IBRS_FW); +} + +static inline void firmware_restrict_branch_speculation_end(void) +{ + alternative_msr_write(MSR_IA32_SPEC_CTRL, 0, + X86_FEATURE_USE_IBRS_FW); + preempt_enable(); } #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index fea368d..b294fdc 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -300,6 +300,15 @@ retpoline_auto: setup_force_cpu_cap(X86_FEATURE_USE_IBPB); pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n"); } + + /* + * Retpoline means the kernel is safe because it has no indirect + * branches. But firmware isn't, so use IBRS to protect that. + */ + if (boot_cpu_has(X86_FEATURE_IBRS)) { + setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); + pr_info("Enabling Restricted Speculation for firmware calls\n"); + } } #undef pr_fmt @@ -326,8 +335,9 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return sprintf(buf, "Not affected\n"); - return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + 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()); } #endif diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index a0ac0f9..f5a8cd9 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -40,6 +40,7 @@ #include <asm/fixmap.h> #include <asm/realmode.h> #include <asm/time.h> +#include <asm/nospec-branch.h> /* * We allocate runtime services regions bottom-up, starting from -4G, i.e. @@ -347,6 +348,7 @@ extern efi_status_t efi64_thunk(u32, ...); \ efi_sync_low_kernel_mappings(); \ local_irq_save(flags); \ + firmware_restrict_branch_speculation_start(); \ \ efi_scratch.prev_cr3 = read_cr3(); \ write_cr3((unsigned long)efi_scratch.efi_pgt); \ @@ -357,6 +359,7 @@ extern efi_status_t efi64_thunk(u32, ...); \ write_cr3(efi_scratch.prev_cr3); \ __flush_tlb_all(); \ + firmware_restrict_branch_speculation_end(); \ local_irq_restore(flags); \ \ __s; \

7 years, 1 month

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror