| Message ID | 20200312171755.177743-1-pcc@google.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | arm64: Expose original FAR_EL1 value in sigcontext | expand |
Hi Peter, On Thu, Mar 12, 2020 at 10:17:55AM -0700, Peter Collingbourne wrote: > diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c > index fde59981445ca..290ea59c68b85 100644 > --- a/arch/arm64/kernel/entry-common.c > +++ b/arch/arm64/kernel/entry-common.c > @@ -22,7 +22,6 @@ static void notrace el1_abort(struct pt_regs *regs, unsigned long esr) > unsigned long far = read_sysreg(far_el1); > > local_daif_inherit(regs); > - far = untagged_addr(far); > do_mem_abort(far, esr, regs); > } > NOKPROBE_SYMBOL(el1_abort); Would we get a signal on faults triggered by the kernel? Anyway, I'm fine with this change for consistency and may help with the fault information printed by the kernel with khwasan or (later) MTE. > @@ -104,7 +103,6 @@ static void notrace el0_da(struct pt_regs *regs, unsigned long esr) > > user_exit_irqoff(); > local_daif_restore(DAIF_PROCCTX); > - far = untagged_addr(far); > do_mem_abort(far, esr, regs); > } > NOKPROBE_SYMBOL(el0_da); > diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c > index 0b727edf41046..985cd44decf62 100644 > --- a/arch/arm64/kernel/hw_breakpoint.c > +++ b/arch/arm64/kernel/hw_breakpoint.c > @@ -730,7 +730,7 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val, > return 0; > } > > -static int watchpoint_handler(unsigned long addr, unsigned int esr, > +static int watchpoint_handler(unsigned long far, unsigned int esr, > struct pt_regs *regs) > { > int i, step = 0, *kernel_step, access, closest_match = 0; > @@ -741,6 +741,7 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, > struct debug_info *debug_info; > struct arch_hw_breakpoint *info; > struct arch_hw_breakpoint_ctrl ctrl; > + unsigned long addr = untagged_addr(far); > > slots = this_cpu_ptr(wp_on_reg); > debug_info = ¤t->thread.debug; Why do we need to untag this here? Have you hit any bug? This function gets the original FAR_EL1 value, untagged (via elX_dbg()), and we clear the tag further down in get_distance_from_watchpoint(). > diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c > index 339882db5a915..48e8b6c7b5369 100644 > --- a/arch/arm64/kernel/signal.c > +++ b/arch/arm64/kernel/signal.c > @@ -55,6 +55,7 @@ struct rt_sigframe_user_layout { > > unsigned long fpsimd_offset; > unsigned long esr_offset; > + unsigned long far_offset; > unsigned long sve_offset; > unsigned long extra_offset; > unsigned long end_offset; > @@ -383,6 +384,7 @@ static int parse_user_sigframe(struct user_ctxs *user, > break; > > case ESR_MAGIC: > + case FAR_MAGIC: > /* ignore */ > break; > > @@ -581,6 +583,11 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, > sizeof(struct esr_context)); > if (err) > return err; > + > + err = sigframe_alloc(user, &user->far_offset, > + sizeof(struct far_context)); > + if (err) > + return err; It looks fine, I think it makes sense to only expose the raw FAR_EL1 when we also expose the ESR_EL1 (via set_thread_esr()). > diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c > index 85566d32958f5..2ca2de1ff43be 100644 > --- a/arch/arm64/mm/fault.c > +++ b/arch/arm64/mm/fault.c > @@ -41,7 +41,7 @@ > #include <asm/traps.h> > > struct fault_info { > - int (*fn)(unsigned long addr, unsigned int esr, > + int (*fn)(unsigned long far, unsigned int esr, > struct pt_regs *regs); > int sig; > int code; > @@ -320,9 +320,11 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr, > die_kernel_fault(msg, addr, esr, regs); > } > > -static void set_thread_esr(unsigned long address, unsigned int esr) > +static void set_thread_esr(unsigned long far, unsigned int esr) We might as well rename this to set_thread_far_esr(). Thanks.
On Wed, Mar 25, 2020 at 6:10 AM Catalin Marinas <catalin.marinas@arm.com> wrote: > > Hi Peter, > > On Thu, Mar 12, 2020 at 10:17:55AM -0700, Peter Collingbourne wrote: > > diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c > > index fde59981445ca..290ea59c68b85 100644 > > --- a/arch/arm64/kernel/entry-common.c > > +++ b/arch/arm64/kernel/entry-common.c > > @@ -22,7 +22,6 @@ static void notrace el1_abort(struct pt_regs *regs, unsigned long esr) > > unsigned long far = read_sysreg(far_el1); > > > > local_daif_inherit(regs); > > - far = untagged_addr(far); > > do_mem_abort(far, esr, regs); > > } > > NOKPROBE_SYMBOL(el1_abort); > > Would we get a signal on faults triggered by the kernel? Anyway, I'm > fine with this change for consistency and may help with the fault > information printed by the kernel with khwasan or (later) MTE. It doesn't look like we would. As far as I can tell all of the signal injection paths are guarded with if (user_mode(regs)) and such. Agreed with the consistency argument. > > @@ -104,7 +103,6 @@ static void notrace el0_da(struct pt_regs *regs, unsigned long esr) > > > > user_exit_irqoff(); > > local_daif_restore(DAIF_PROCCTX); > > - far = untagged_addr(far); > > do_mem_abort(far, esr, regs); > > } > > NOKPROBE_SYMBOL(el0_da); > > diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c > > index 0b727edf41046..985cd44decf62 100644 > > --- a/arch/arm64/kernel/hw_breakpoint.c > > +++ b/arch/arm64/kernel/hw_breakpoint.c > > @@ -730,7 +730,7 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val, > > return 0; > > } > > > > -static int watchpoint_handler(unsigned long addr, unsigned int esr, > > +static int watchpoint_handler(unsigned long far, unsigned int esr, > > struct pt_regs *regs) > > { > > int i, step = 0, *kernel_step, access, closest_match = 0; > > @@ -741,6 +741,7 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, > > struct debug_info *debug_info; > > struct arch_hw_breakpoint *info; > > struct arch_hw_breakpoint_ctrl ctrl; > > + unsigned long addr = untagged_addr(far); > > > > slots = this_cpu_ptr(wp_on_reg); > > debug_info = ¤t->thread.debug; > > Why do we need to untag this here? Have you hit any bug? This function > gets the original FAR_EL1 value, untagged (via elX_dbg()), and we clear > the tag further down in get_distance_from_watchpoint(). You're right, I missed that this was going via elX_dbg() rather than an abort handler. In fact, this would seem to be a potential userspace break because the now-untagged address is also stored in counter_arch_bp(wp)->trigger, which is exposed to userspace via ptrace_hbptriggered in arch/arm64/kernel/ptrace.c. I've reverted this part in v2. > > diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c > > index 339882db5a915..48e8b6c7b5369 100644 > > --- a/arch/arm64/kernel/signal.c > > +++ b/arch/arm64/kernel/signal.c > > @@ -55,6 +55,7 @@ struct rt_sigframe_user_layout { > > > > unsigned long fpsimd_offset; > > unsigned long esr_offset; > > + unsigned long far_offset; > > unsigned long sve_offset; > > unsigned long extra_offset; > > unsigned long end_offset; > > @@ -383,6 +384,7 @@ static int parse_user_sigframe(struct user_ctxs *user, > > break; > > > > case ESR_MAGIC: > > + case FAR_MAGIC: > > /* ignore */ > > break; > > > > @@ -581,6 +583,11 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, > > sizeof(struct esr_context)); > > if (err) > > return err; > > + > > + err = sigframe_alloc(user, &user->far_offset, > > + sizeof(struct far_context)); > > + if (err) > > + return err; > > It looks fine, I think it makes sense to only expose the raw FAR_EL1 > when we also expose the ESR_EL1 (via set_thread_esr()). > > > diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c > > index 85566d32958f5..2ca2de1ff43be 100644 > > --- a/arch/arm64/mm/fault.c > > +++ b/arch/arm64/mm/fault.c > > @@ -41,7 +41,7 @@ > > #include <asm/traps.h> > > > > struct fault_info { > > - int (*fn)(unsigned long addr, unsigned int esr, > > + int (*fn)(unsigned long far, unsigned int esr, > > struct pt_regs *regs); > > int sig; > > int code; > > @@ -320,9 +320,11 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr, > > die_kernel_fault(msg, addr, esr, regs); > > } > > > > -static void set_thread_esr(unsigned long address, unsigned int esr) > > +static void set_thread_esr(unsigned long far, unsigned int esr) > > We might as well rename this to set_thread_far_esr(). Done in v2. Peter
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index 7a6e81ca23a8e..90e772d9b2cd8 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -32,7 +32,7 @@ static inline u32 disr_to_esr(u64 disr) } asmlinkage void enter_from_user_mode(void); -void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); +void do_mem_abort(unsigned long far, unsigned int esr, struct pt_regs *regs); void do_undefinstr(struct pt_regs *regs); asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr); void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 5ba63204d078a..77d916c075319 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -142,7 +142,7 @@ struct thread_struct { void *sve_state; /* SVE registers, if any */ unsigned int sve_vl; /* SVE vector length */ unsigned int sve_vl_onexec; /* SVE vl after next exec */ - unsigned long fault_address; /* fault info */ + unsigned long fault_address; /* FAR_EL1 value */ unsigned long fault_code; /* ESR_EL1 value */ struct debug_info debug; /* debugging */ #ifdef CONFIG_ARM64_PTR_AUTH diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index 8b0ebce92427b..f532a2505d5e8 100644 --- a/arch/arm64/include/uapi/asm/sigcontext.h +++ b/arch/arm64/include/uapi/asm/sigcontext.h @@ -44,6 +44,7 @@ struct sigcontext { * * 0x210 fpsimd_context * 0x10 esr_context + * 0x10 far_context * 0x8a0 sve_context (vl <= 64) (optional) * 0x20 extra_context (optional) * 0x10 terminator (null _aarch64_ctx) @@ -94,6 +95,14 @@ struct esr_context { __u64 esr; }; +/* FAR_EL1 context */ +#define FAR_MAGIC 0x46415201 + +struct far_context { + struct _aarch64_ctx head; + __u64 far; +}; + /* * extra_context: describes extra space in the signal frame for * additional structures that don't fit in sigcontext.__reserved[]. diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index fde59981445ca..290ea59c68b85 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -22,7 +22,6 @@ static void notrace el1_abort(struct pt_regs *regs, unsigned long esr) unsigned long far = read_sysreg(far_el1); local_daif_inherit(regs); - far = untagged_addr(far); do_mem_abort(far, esr, regs); } NOKPROBE_SYMBOL(el1_abort); @@ -104,7 +103,6 @@ static void notrace el0_da(struct pt_regs *regs, unsigned long esr) user_exit_irqoff(); local_daif_restore(DAIF_PROCCTX); - far = untagged_addr(far); do_mem_abort(far, esr, regs); } NOKPROBE_SYMBOL(el0_da); diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 0b727edf41046..985cd44decf62 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -730,7 +730,7 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val, return 0; } -static int watchpoint_handler(unsigned long addr, unsigned int esr, +static int watchpoint_handler(unsigned long far, unsigned int esr, struct pt_regs *regs) { int i, step = 0, *kernel_step, access, closest_match = 0; @@ -741,6 +741,7 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, struct debug_info *debug_info; struct arch_hw_breakpoint *info; struct arch_hw_breakpoint_ctrl ctrl; + unsigned long addr = untagged_addr(far); slots = this_cpu_ptr(wp_on_reg); debug_info = ¤t->thread.debug; diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 339882db5a915..48e8b6c7b5369 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -55,6 +55,7 @@ struct rt_sigframe_user_layout { unsigned long fpsimd_offset; unsigned long esr_offset; + unsigned long far_offset; unsigned long sve_offset; unsigned long extra_offset; unsigned long end_offset; @@ -383,6 +384,7 @@ static int parse_user_sigframe(struct user_ctxs *user, break; case ESR_MAGIC: + case FAR_MAGIC: /* ignore */ break; @@ -581,6 +583,11 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, sizeof(struct esr_context)); if (err) return err; + + err = sigframe_alloc(user, &user->far_offset, + sizeof(struct far_context)); + if (err) + return err; } if (system_supports_sve()) { @@ -621,7 +628,8 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, __put_user_error(regs->pc, &sf->uc.uc_mcontext.pc, err); __put_user_error(regs->pstate, &sf->uc.uc_mcontext.pstate, err); - __put_user_error(current->thread.fault_address, &sf->uc.uc_mcontext.fault_address, err); + __put_user_error(untagged_addr(current->thread.fault_address), + &sf->uc.uc_mcontext.fault_address, err); err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set)); @@ -641,6 +649,16 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, __put_user_error(current->thread.fault_code, &esr_ctx->esr, err); } + if (err == 0 && user->far_offset) { + struct far_context __user *far_ctx = + apply_user_offset(user, user->far_offset); + + __put_user_error(FAR_MAGIC, &far_ctx->head.magic, err); + __put_user_error(sizeof(*far_ctx), &far_ctx->head.size, err); + __put_user_error(current->thread.fault_address, &far_ctx->far, + err); + } + /* Scalable Vector Extension state, if present */ if (system_supports_sve() && err == 0 && user->sve_offset) { struct sve_context __user *sve_ctx = diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 85566d32958f5..2ca2de1ff43be 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -41,7 +41,7 @@ #include <asm/traps.h> struct fault_info { - int (*fn)(unsigned long addr, unsigned int esr, + int (*fn)(unsigned long far, unsigned int esr, struct pt_regs *regs); int sig; int code; @@ -320,9 +320,11 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr, die_kernel_fault(msg, addr, esr, regs); } -static void set_thread_esr(unsigned long address, unsigned int esr) +static void set_thread_esr(unsigned long far, unsigned int esr) { - current->thread.fault_address = address; + unsigned long addr = untagged_addr(far); + + current->thread.fault_address = far; /* * If the faulting address is in the kernel, we must sanitize the ESR. @@ -336,7 +338,7 @@ static void set_thread_esr(unsigned long address, unsigned int esr) * type", so we ignore this wrinkle and just return the translation * fault.) */ - if (!is_ttbr0_addr(current->thread.fault_address)) { + if (!is_ttbr0_addr(addr)) { switch (ESR_ELx_EC(esr)) { case ESR_ELx_EC_DABT_LOW: /* @@ -377,8 +379,11 @@ static void set_thread_esr(unsigned long address, unsigned int esr) current->thread.fault_code = esr; } -static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs) +static void do_bad_area(unsigned long far, unsigned int esr, + struct pt_regs *regs) { + unsigned long addr = untagged_addr(far); + /* * If we are in kernel mode at this point, we have no context to * handle this fault with. @@ -386,7 +391,7 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re if (user_mode(regs)) { const struct fault_info *inf = esr_to_fault_info(esr); - set_thread_esr(addr, esr); + set_thread_esr(far, esr); arm64_force_sig_fault(inf->sig, inf->code, (void __user *)addr, inf->name); } else { @@ -439,7 +444,7 @@ static bool is_write_abort(unsigned int esr) return (esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM); } -static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, +static int __kprobes do_page_fault(unsigned long far, unsigned int esr, struct pt_regs *regs) { const struct fault_info *inf; @@ -447,6 +452,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, vm_fault_t fault, major = 0; unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC; unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + unsigned long addr = untagged_addr(far); if (kprobe_page_fault(regs, esr)) return 0; @@ -580,7 +586,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, } inf = esr_to_fault_info(esr); - set_thread_esr(addr, esr); + set_thread_esr(far, esr); if (fault & VM_FAULT_SIGBUS) { /* * We had some memory, but were unable to successfully fix up @@ -615,30 +621,32 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, return 0; } -static int __kprobes do_translation_fault(unsigned long addr, +static int __kprobes do_translation_fault(unsigned long far, unsigned int esr, struct pt_regs *regs) { + unsigned long addr = untagged_addr(far); + if (is_ttbr0_addr(addr)) - return do_page_fault(addr, esr, regs); + return do_page_fault(far, esr, regs); - do_bad_area(addr, esr, regs); + do_bad_area(far, esr, regs); return 0; } -static int do_alignment_fault(unsigned long addr, unsigned int esr, +static int do_alignment_fault(unsigned long far, unsigned int esr, struct pt_regs *regs) { - do_bad_area(addr, esr, regs); + do_bad_area(far, esr, regs); return 0; } -static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs) +static int do_bad(unsigned long far, unsigned int esr, struct pt_regs *regs) { return 1; /* "fault" */ } -static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs) +static int do_sea(unsigned long far, unsigned int esr, struct pt_regs *regs) { const struct fault_info *inf; void __user *siaddr; @@ -654,7 +662,7 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs) if (esr & ESR_ELx_FnV) siaddr = NULL; else - siaddr = (void __user *)addr; + siaddr = (void __user *)untagged_addr(far); arm64_notify_die(inf->name, regs, inf->sig, inf->code, siaddr, esr); return 0; @@ -727,11 +735,12 @@ static const struct fault_info fault_info[] = { { do_bad, SIGKILL, SI_KERNEL, "unknown 63" }, }; -void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs) +void do_mem_abort(unsigned long far, unsigned int esr, struct pt_regs *regs) { const struct fault_info *inf = esr_to_fault_info(esr); + unsigned long addr = untagged_addr(far); - if (!inf->fn(addr, esr, regs)) + if (!inf->fn(far, esr, regs)) return; if (!user_mode(regs)) {
The kernel currently clears the tag bits (i.e. bits 56-63) in the fault address exposed via siginfo.si_addr and sigcontext.fault_address. However, the tag bits may be needed by tools in order to accurately diagnose memory errors, such as HWASan [1] or future tools based on the Memory Tagging Extension (MTE). We should not stop clearing these bits in the existing fault address fields, because there may be existing userspace applications that are expecting the tag bits to be cleared. Instead, create a far_context in sigcontext (similar to the existing esr_context), and store the original value of FAR_EL1 (including the tag bits) there. [1] http://clang.llvm.org/docs/HardwareAssistedAddressSanitizerDesign.html Signed-off-by: Peter Collingbourne <pcc@google.com> --- arch/arm64/include/asm/exception.h | 2 +- arch/arm64/include/asm/processor.h | 2 +- arch/arm64/include/uapi/asm/sigcontext.h | 9 +++++ arch/arm64/kernel/entry-common.c | 2 -- arch/arm64/kernel/hw_breakpoint.c | 3 +- arch/arm64/kernel/signal.c | 20 ++++++++++- arch/arm64/mm/fault.c | 45 ++++++++++++++---------- 7 files changed, 59 insertions(+), 24 deletions(-)