linux_dsm_epyc7002/arch/x86/kernel/traps.c

1020 lines
29 KiB
C
Raw Normal View History

/*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
*
* Pentium III FXSR, SSE support
* Gareth Hughes <gareth@valinux.com>, May 2000
*/
/*
* Handle hardware traps and faults.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/context_tracking.h>
#include <linux/interrupt.h>
#include <linux/kallsyms.h>
#include <linux/spinlock.h>
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/kdebug.h>
#include <linux/kgdb.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/ptrace.h>
#include <linux/uprobes.h>
#include <linux/string.h>
#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/kexec.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/init.h>
#include <linux/bug.h>
#include <linux/nmi.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/io.h>
#ifdef CONFIG_EISA
#include <linux/ioport.h>
#include <linux/eisa.h>
#endif
#if defined(CONFIG_EDAC)
#include <linux/edac.h>
#endif
#include <asm/kmemcheck.h>
#include <asm/stacktrace.h>
#include <asm/processor.h>
#include <asm/debugreg.h>
#include <linux/atomic.h>
#include <asm/text-patching.h>
#include <asm/ftrace.h>
#include <asm/traps.h>
#include <asm/desc.h>
#include <asm/fpu/internal.h>
#include <asm/mce.h>
#include <asm/fixmap.h>
#include <asm/mach_traps.h>
kprobes/x86: Call out into INT3 handler directly instead of using notifier In fd4363fff3d96 ("x86: Introduce int3 (breakpoint)-based instruction patching"), the mechanism that was introduced for notifying alternatives code from int3 exception handler that and exception occured was die_notifier. This is however problematic, as early code might be using jump labels even before the notifier registration has been performed, which will then lead to an oops due to unhandled exception. One of such occurences has been encountered by Fengguang: int3: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.11.0-rc1-01429-g04bf576 #8 task: ffff88000da1b040 ti: ffff88000da1c000 task.ti: ffff88000da1c000 RIP: 0010:[<ffffffff811098cc>] [<ffffffff811098cc>] ttwu_do_wakeup+0x28/0x225 RSP: 0000:ffff88000dd03f10 EFLAGS: 00000006 RAX: 0000000000000000 RBX: ffff88000dd12940 RCX: ffffffff81769c40 RDX: 0000000000000002 RSI: 0000000000000000 RDI: 0000000000000001 RBP: ffff88000dd03f28 R08: ffffffff8176a8c0 R09: 0000000000000002 R10: ffffffff810ff484 R11: ffff88000dd129e8 R12: ffff88000dbc90c0 R13: ffff88000dbc90c0 R14: ffff88000da1dfd8 R15: ffff88000da1dfd8 FS: 0000000000000000(0000) GS:ffff88000dd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00000000ffffffff CR3: 0000000001c88000 CR4: 00000000000006e0 Stack: ffff88000dd12940 ffff88000dbc90c0 ffff88000da1dfd8 ffff88000dd03f48 ffffffff81109e2b ffff88000dd12940 0000000000000000 ffff88000dd03f68 ffffffff81109e9e 0000000000000000 0000000000012940 ffff88000dd03f98 Call Trace: <IRQ> [<ffffffff81109e2b>] ttwu_do_activate.constprop.56+0x6d/0x79 [<ffffffff81109e9e>] sched_ttwu_pending+0x67/0x84 [<ffffffff8110c845>] scheduler_ipi+0x15a/0x2b0 [<ffffffff8104dfb4>] smp_reschedule_interrupt+0x38/0x41 [<ffffffff8173bf5d>] reschedule_interrupt+0x6d/0x80 <EOI> [<ffffffff810ff484>] ? __atomic_notifier_call_chain+0x5/0xc1 [<ffffffff8105cc30>] ? native_safe_halt+0xd/0x16 [<ffffffff81015f10>] default_idle+0x147/0x282 [<ffffffff81017026>] arch_cpu_idle+0x3d/0x5d [<ffffffff81127d6a>] cpu_idle_loop+0x46d/0x5db [<ffffffff81127f5c>] cpu_startup_entry+0x84/0x84 [<ffffffff8104f4f8>] start_secondary+0x3c8/0x3d5 [...] Fix this by directly calling poke_int3_handler() from the int3 exception handler (analogically to what ftrace has been doing already), instead of relying on notifier, registration of which might not have yet been finalized by the time of the first trap. Reported-and-tested-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Jiri Kosina <jkosina@suse.cz> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: H. Peter Anvin <hpa@linux.intel.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/alpine.LNX.2.00.1307231007490.14024@pobox.suse.cz Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-23 15:09:28 +07:00
#include <asm/alternative.h>
#include <asm/fpu/xstate.h>
#include <asm/trace/mpx.h>
x86, mpx: On-demand kernel allocation of bounds tables This is really the meat of the MPX patch set. If there is one patch to review in the entire series, this is the one. There is a new ABI here and this kernel code also interacts with userspace memory in a relatively unusual manner. (small FAQ below). Long Description: This patch adds two prctl() commands to provide enable or disable the management of bounds tables in kernel, including on-demand kernel allocation (See the patch "on-demand kernel allocation of bounds tables") and cleanup (See the patch "cleanup unused bound tables"). Applications do not strictly need the kernel to manage bounds tables and we expect some applications to use MPX without taking advantage of this kernel support. This means the kernel can not simply infer whether an application needs bounds table management from the MPX registers. The prctl() is an explicit signal from userspace. PR_MPX_ENABLE_MANAGEMENT is meant to be a signal from userspace to require kernel's help in managing bounds tables. PR_MPX_DISABLE_MANAGEMENT is the opposite, meaning that userspace don't want kernel's help any more. With PR_MPX_DISABLE_MANAGEMENT, the kernel won't allocate and free bounds tables even if the CPU supports MPX. PR_MPX_ENABLE_MANAGEMENT will fetch the base address of the bounds directory out of a userspace register (bndcfgu) and then cache it into a new field (->bd_addr) in the 'mm_struct'. PR_MPX_DISABLE_MANAGEMENT will set "bd_addr" to an invalid address. Using this scheme, we can use "bd_addr" to determine whether the management of bounds tables in kernel is enabled. Also, the only way to access that bndcfgu register is via an xsaves, which can be expensive. Caching "bd_addr" like this also helps reduce the cost of those xsaves when doing table cleanup at munmap() time. Unfortunately, we can not apply this optimization to #BR fault time because we need an xsave to get the value of BNDSTATUS. ==== Why does the hardware even have these Bounds Tables? ==== MPX only has 4 hardware registers for storing bounds information. If MPX-enabled code needs more than these 4 registers, it needs to spill them somewhere. It has two special instructions for this which allow the bounds to be moved between the bounds registers and some new "bounds tables". They are similar conceptually to a page fault and will be raised by the MPX hardware during both bounds violations or when the tables are not present. This patch handles those #BR exceptions for not-present tables by carving the space out of the normal processes address space (essentially calling the new mmap() interface indroduced earlier in this patch set.) and then pointing the bounds-directory over to it. The tables *need* to be accessed and controlled by userspace because the instructions for moving bounds in and out of them are extremely frequent. They potentially happen every time a register pointing to memory is dereferenced. Any direct kernel involvement (like a syscall) to access the tables would obviously destroy performance. ==== Why not do this in userspace? ==== This patch is obviously doing this allocation in the kernel. However, MPX does not strictly *require* anything in the kernel. It can theoretically be done completely from userspace. Here are a few ways this *could* be done. I don't think any of them are practical in the real-world, but here they are. Q: Can virtual space simply be reserved for the bounds tables so that we never have to allocate them? A: As noted earlier, these tables are *HUGE*. An X-GB virtual area needs 4*X GB of virtual space, plus 2GB for the bounds directory. If we were to preallocate them for the 128TB of user virtual address space, we would need to reserve 512TB+2GB, which is larger than the entire virtual address space today. This means they can not be reserved ahead of time. Also, a single process's pre-popualated bounds directory consumes 2GB of virtual *AND* physical memory. IOW, it's completely infeasible to prepopulate bounds directories. Q: Can we preallocate bounds table space at the same time memory is allocated which might contain pointers that might eventually need bounds tables? A: This would work if we could hook the site of each and every memory allocation syscall. This can be done for small, constrained applications. But, it isn't practical at a larger scale since a given app has no way of controlling how all the parts of the app might allocate memory (think libraries). The kernel is really the only place to intercept these calls. Q: Could a bounds fault be handed to userspace and the tables allocated there in a signal handler instead of in the kernel? A: (thanks to tglx) mmap() is not on the list of safe async handler functions and even if mmap() would work it still requires locking or nasty tricks to keep track of the allocation state there. Having ruled out all of the userspace-only approaches for managing bounds tables that we could think of, we create them on demand in the kernel. Based-on-patch-by: Qiaowei Ren <qiaowei.ren@intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: linux-mm@kvack.org Cc: linux-mips@linux-mips.org Cc: Dave Hansen <dave@sr71.net> Link: http://lkml.kernel.org/r/20141114151829.AD4310DE@viggo.jf.intel.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2014-11-14 22:18:29 +07:00
#include <asm/mpx.h>
#include <asm/vm86.h>
#ifdef CONFIG_X86_64
#include <asm/x86_init.h>
#include <asm/pgalloc.h>
#include <asm/proto.h>
/* No need to be aligned, but done to keep all IDTs defined the same way. */
gate_desc debug_idt_table[NR_VECTORS] __page_aligned_bss;
#else
#include <asm/processor-flags.h>
#include <asm/setup.h>
#include <asm/proto.h>
#endif
/* Must be page-aligned because the real IDT is used in a fixmap. */
gate_desc idt_table[NR_VECTORS] __page_aligned_bss;
DECLARE_BITMAP(used_vectors, NR_VECTORS);
EXPORT_SYMBOL_GPL(used_vectors);
static inline void cond_local_irq_enable(struct pt_regs *regs)
{
if (regs->flags & X86_EFLAGS_IF)
local_irq_enable();
}
static inline void cond_local_irq_disable(struct pt_regs *regs)
{
if (regs->flags & X86_EFLAGS_IF)
local_irq_disable();
}
/*
* In IST context, we explicitly disable preemption. This serves two
* purposes: it makes it much less likely that we would accidentally
* schedule in IST context and it will force a warning if we somehow
* manage to schedule by accident.
*/
void ist_enter(struct pt_regs *regs)
{
if (user_mode(regs)) {
Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull x86 asm changes from Ingo Molnar: "The biggest changes in this cycle were: - Revamp, simplify (and in some cases fix) Time Stamp Counter (TSC) primitives. (Andy Lutomirski) - Add new, comprehensible entry and exit handlers written in C. (Andy Lutomirski) - vm86 mode cleanups and fixes. (Brian Gerst) - 32-bit compat code cleanups. (Brian Gerst) The amount of simplification in low level assembly code is already palpable: arch/x86/entry/entry_32.S | 130 +---- arch/x86/entry/entry_64.S | 197 ++----- but more simplifications are planned. There's also the usual laudry mix of low level changes - see the changelog for details" * 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (83 commits) x86/asm: Drop repeated macro of X86_EFLAGS_AC definition x86/asm/msr: Make wrmsrl() a function x86/asm/delay: Introduce an MWAITX-based delay with a configurable timer x86/asm: Add MONITORX/MWAITX instruction support x86/traps: Weaken context tracking entry assertions x86/asm/tsc: Add rdtscll() merge helper selftests/x86: Add syscall_nt selftest selftests/x86: Disable sigreturn_64 x86/vdso: Emit a GNU hash x86/entry: Remove do_notify_resume(), syscall_trace_leave(), and their TIF masks x86/entry/32: Migrate to C exit path x86/entry/32: Remove 32-bit syscall audit optimizations x86/vm86: Rename vm86->v86flags and v86mask x86/vm86: Rename vm86->vm86_info to user_vm86 x86/vm86: Clean up vm86.h includes x86/vm86: Move the vm86 IRQ definitions to vm86.h x86/vm86: Use the normal pt_regs area for vm86 x86/vm86: Eliminate 'struct kernel_vm86_struct' x86/vm86: Move fields from 'struct kernel_vm86_struct' to 'struct vm86' x86/vm86: Move vm86 fields out of 'thread_struct' ...
2015-09-01 22:40:25 +07:00
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
} else {
/*
* We might have interrupted pretty much anything. In
* fact, if we're a machine check, we can even interrupt
* NMI processing. We don't want in_nmi() to return true,
* but we need to notify RCU.
*/
rcu_nmi_enter();
}
preempt_disable();
/* This code is a bit fragile. Test it. */
RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work");
}
void ist_exit(struct pt_regs *regs)
{
preempt_enable_no_resched();
if (!user_mode(regs))
rcu_nmi_exit();
}
/**
* ist_begin_non_atomic() - begin a non-atomic section in an IST exception
* @regs: regs passed to the IST exception handler
*
* IST exception handlers normally cannot schedule. As a special
* exception, if the exception interrupted userspace code (i.e.
* user_mode(regs) would return true) and the exception was not
* a double fault, it can be safe to schedule. ist_begin_non_atomic()
* begins a non-atomic section within an ist_enter()/ist_exit() region.
* Callers are responsible for enabling interrupts themselves inside
* the non-atomic section, and callers must call ist_end_non_atomic()
* before ist_exit().
*/
void ist_begin_non_atomic(struct pt_regs *regs)
{
BUG_ON(!user_mode(regs));
/*
* Sanity check: we need to be on the normal thread stack. This
* will catch asm bugs and any attempt to use ist_preempt_enable
* from double_fault.
*/
BUG_ON((unsigned long)(current_top_of_stack() -
current_stack_pointer()) >= THREAD_SIZE);
preempt_enable_no_resched();
}
/**
* ist_end_non_atomic() - begin a non-atomic section in an IST exception
*
* Ends a non-atomic section started with ist_begin_non_atomic().
*/
void ist_end_non_atomic(void)
{
preempt_disable();
}
kprobes, x86: Use NOKPROBE_SYMBOL() instead of __kprobes annotation Use NOKPROBE_SYMBOL macro for protecting functions from kprobes instead of __kprobes annotation under arch/x86. This applies nokprobe_inline annotation for some cases, because NOKPROBE_SYMBOL() will inhibit inlining by referring the symbol address. This just folds a bunch of previous NOKPROBE_SYMBOL() cleanup patches for x86 to one patch. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Link: http://lkml.kernel.org/r/20140417081814.26341.51656.stgit@ltc230.yrl.intra.hitachi.co.jp Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Fernando Luis Vázquez Cao <fernando_b1@lab.ntt.co.jp> Cc: Gleb Natapov <gleb@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Lebon <jlebon@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Matt Fleming <matt.fleming@intel.com> Cc: Michel Lespinasse <walken@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Seiji Aguchi <seiji.aguchi@hds.com> Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vineet Gupta <vgupta@synopsys.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-04-17 15:18:14 +07:00
static nokprobe_inline int
do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
struct pt_regs *regs, long error_code)
{
if (v8086_mode(regs)) {
/*
* Traps 0, 1, 3, 4, and 5 should be forwarded to vm86.
* On nmi (interrupt 2), do_trap should not be called.
*/
if (trapnr < X86_TRAP_UD) {
if (!handle_vm86_trap((struct kernel_vm86_regs *) regs,
error_code, trapnr))
return 0;
}
return -1;
}
if (!user_mode(regs)) {
if (!fixup_exception(regs, trapnr)) {
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = trapnr;
die(str, regs, error_code);
}
return 0;
}
return -1;
}
static siginfo_t *fill_trap_info(struct pt_regs *regs, int signr, int trapnr,
siginfo_t *info)
{
unsigned long siaddr;
int sicode;
switch (trapnr) {
default:
return SEND_SIG_PRIV;
case X86_TRAP_DE:
sicode = FPE_INTDIV;
siaddr = uprobe_get_trap_addr(regs);
break;
case X86_TRAP_UD:
sicode = ILL_ILLOPN;
siaddr = uprobe_get_trap_addr(regs);
break;
case X86_TRAP_AC:
sicode = BUS_ADRALN;
siaddr = 0;
break;
}
info->si_signo = signr;
info->si_errno = 0;
info->si_code = sicode;
info->si_addr = (void __user *)siaddr;
return info;
}
kprobes, x86: Use NOKPROBE_SYMBOL() instead of __kprobes annotation Use NOKPROBE_SYMBOL macro for protecting functions from kprobes instead of __kprobes annotation under arch/x86. This applies nokprobe_inline annotation for some cases, because NOKPROBE_SYMBOL() will inhibit inlining by referring the symbol address. This just folds a bunch of previous NOKPROBE_SYMBOL() cleanup patches for x86 to one patch. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Link: http://lkml.kernel.org/r/20140417081814.26341.51656.stgit@ltc230.yrl.intra.hitachi.co.jp Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Fernando Luis Vázquez Cao <fernando_b1@lab.ntt.co.jp> Cc: Gleb Natapov <gleb@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Lebon <jlebon@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Matt Fleming <matt.fleming@intel.com> Cc: Michel Lespinasse <walken@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Seiji Aguchi <seiji.aguchi@hds.com> Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vineet Gupta <vgupta@synopsys.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-04-17 15:18:14 +07:00
static void
do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
long error_code, siginfo_t *info)
{
struct task_struct *tsk = current;
if (!do_trap_no_signal(tsk, trapnr, str, regs, error_code))
return;
/*
* We want error_code and trap_nr set for userspace faults and
* kernelspace faults which result in die(), but not
* kernelspace faults which are fixed up. die() gives the
* process no chance to handle the signal and notice the
* kernel fault information, so that won't result in polluting
* the information about previously queued, but not yet
* delivered, faults. See also do_general_protection below.
*/
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = trapnr;
if (show_unhandled_signals && unhandled_signal(tsk, signr) &&
printk_ratelimit()) {
pr_info("%s[%d] trap %s ip:%lx sp:%lx error:%lx",
tsk->comm, tsk->pid, str,
regs->ip, regs->sp, error_code);
print_vma_addr(" in ", regs->ip);
pr_cont("\n");
}
force_sig_info(signr, info ?: SEND_SIG_PRIV, tsk);
}
kprobes, x86: Use NOKPROBE_SYMBOL() instead of __kprobes annotation Use NOKPROBE_SYMBOL macro for protecting functions from kprobes instead of __kprobes annotation under arch/x86. This applies nokprobe_inline annotation for some cases, because NOKPROBE_SYMBOL() will inhibit inlining by referring the symbol address. This just folds a bunch of previous NOKPROBE_SYMBOL() cleanup patches for x86 to one patch. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Link: http://lkml.kernel.org/r/20140417081814.26341.51656.stgit@ltc230.yrl.intra.hitachi.co.jp Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Fernando Luis Vázquez Cao <fernando_b1@lab.ntt.co.jp> Cc: Gleb Natapov <gleb@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Lebon <jlebon@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Matt Fleming <matt.fleming@intel.com> Cc: Michel Lespinasse <walken@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Seiji Aguchi <seiji.aguchi@hds.com> Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vineet Gupta <vgupta@synopsys.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-04-17 15:18:14 +07:00
NOKPROBE_SYMBOL(do_trap);
static void do_error_trap(struct pt_regs *regs, long error_code, char *str,
unsigned long trapnr, int signr)
{
siginfo_t info;
Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull x86 asm changes from Ingo Molnar: "The biggest changes in this cycle were: - Revamp, simplify (and in some cases fix) Time Stamp Counter (TSC) primitives. (Andy Lutomirski) - Add new, comprehensible entry and exit handlers written in C. (Andy Lutomirski) - vm86 mode cleanups and fixes. (Brian Gerst) - 32-bit compat code cleanups. (Brian Gerst) The amount of simplification in low level assembly code is already palpable: arch/x86/entry/entry_32.S | 130 +---- arch/x86/entry/entry_64.S | 197 ++----- but more simplifications are planned. There's also the usual laudry mix of low level changes - see the changelog for details" * 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (83 commits) x86/asm: Drop repeated macro of X86_EFLAGS_AC definition x86/asm/msr: Make wrmsrl() a function x86/asm/delay: Introduce an MWAITX-based delay with a configurable timer x86/asm: Add MONITORX/MWAITX instruction support x86/traps: Weaken context tracking entry assertions x86/asm/tsc: Add rdtscll() merge helper selftests/x86: Add syscall_nt selftest selftests/x86: Disable sigreturn_64 x86/vdso: Emit a GNU hash x86/entry: Remove do_notify_resume(), syscall_trace_leave(), and their TIF masks x86/entry/32: Migrate to C exit path x86/entry/32: Remove 32-bit syscall audit optimizations x86/vm86: Rename vm86->v86flags and v86mask x86/vm86: Rename vm86->vm86_info to user_vm86 x86/vm86: Clean up vm86.h includes x86/vm86: Move the vm86 IRQ definitions to vm86.h x86/vm86: Use the normal pt_regs area for vm86 x86/vm86: Eliminate 'struct kernel_vm86_struct' x86/vm86: Move fields from 'struct kernel_vm86_struct' to 'struct vm86' x86/vm86: Move vm86 fields out of 'thread_struct' ...
2015-09-01 22:40:25 +07:00
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) !=
NOTIFY_STOP) {
cond_local_irq_enable(regs);
do_trap(trapnr, signr, str, regs, error_code,
fill_trap_info(regs, signr, trapnr, &info));
}
}
#define DO_ERROR(trapnr, signr, str, name) \
dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \
{ \
do_error_trap(regs, error_code, str, trapnr, signr); \
}
DO_ERROR(X86_TRAP_DE, SIGFPE, "divide error", divide_error)
DO_ERROR(X86_TRAP_OF, SIGSEGV, "overflow", overflow)
DO_ERROR(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op)
DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun",coprocessor_segment_overrun)
DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS)
DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present)
DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment)
DO_ERROR(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check)
x86/mm/64: Enable vmapped stacks (CONFIG_HAVE_ARCH_VMAP_STACK=y) This allows x86_64 kernels to enable vmapped stacks by setting HAVE_ARCH_VMAP_STACK=y - which enables the CONFIG_VMAP_STACK=y high level Kconfig option. There are a couple of interesting bits: First, x86 lazily faults in top-level paging entries for the vmalloc area. This won't work if we get a page fault while trying to access the stack: the CPU will promote it to a double-fault and we'll die. To avoid this problem, probe the new stack when switching stacks and forcibly populate the pgd entry for the stack when switching mms. Second, once we have guard pages around the stack, we'll want to detect and handle stack overflow. I didn't enable it on x86_32. We'd need to rework the double-fault code a bit and I'm concerned about running out of vmalloc virtual addresses under some workloads. This patch, by itself, will behave somewhat erratically when the stack overflows while RSP is still more than a few tens of bytes above the bottom of the stack. Specifically, we'll get #PF and make it to no_context and them oops without reliably triggering a double-fault, and no_context doesn't know about stack overflows. The next patch will improve that case. Thank you to Nadav and Brian for helping me pay enough attention to the SDM to hopefully get this right. Signed-off-by: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/c88f3e2920b18e6cc621d772a04a62c06869037e.1470907718.git.luto@kernel.org [ Minor edits. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-11 16:35:23 +07:00
#ifdef CONFIG_VMAP_STACK
__visible void __noreturn handle_stack_overflow(const char *message,
struct pt_regs *regs,
unsigned long fault_address)
x86/mm/64: Enable vmapped stacks (CONFIG_HAVE_ARCH_VMAP_STACK=y) This allows x86_64 kernels to enable vmapped stacks by setting HAVE_ARCH_VMAP_STACK=y - which enables the CONFIG_VMAP_STACK=y high level Kconfig option. There are a couple of interesting bits: First, x86 lazily faults in top-level paging entries for the vmalloc area. This won't work if we get a page fault while trying to access the stack: the CPU will promote it to a double-fault and we'll die. To avoid this problem, probe the new stack when switching stacks and forcibly populate the pgd entry for the stack when switching mms. Second, once we have guard pages around the stack, we'll want to detect and handle stack overflow. I didn't enable it on x86_32. We'd need to rework the double-fault code a bit and I'm concerned about running out of vmalloc virtual addresses under some workloads. This patch, by itself, will behave somewhat erratically when the stack overflows while RSP is still more than a few tens of bytes above the bottom of the stack. Specifically, we'll get #PF and make it to no_context and them oops without reliably triggering a double-fault, and no_context doesn't know about stack overflows. The next patch will improve that case. Thank you to Nadav and Brian for helping me pay enough attention to the SDM to hopefully get this right. Signed-off-by: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/c88f3e2920b18e6cc621d772a04a62c06869037e.1470907718.git.luto@kernel.org [ Minor edits. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-11 16:35:23 +07:00
{
printk(KERN_EMERG "BUG: stack guard page was hit at %p (stack is %p..%p)\n",
(void *)fault_address, current->stack,
(char *)current->stack + THREAD_SIZE - 1);
die(message, regs, 0);
/* Be absolutely certain we don't return. */
panic(message);
}
#endif
#ifdef CONFIG_X86_64
/* Runs on IST stack */
dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
{
static const char str[] = "double fault";
struct task_struct *tsk = current;
x86/mm/64: Enable vmapped stacks (CONFIG_HAVE_ARCH_VMAP_STACK=y) This allows x86_64 kernels to enable vmapped stacks by setting HAVE_ARCH_VMAP_STACK=y - which enables the CONFIG_VMAP_STACK=y high level Kconfig option. There are a couple of interesting bits: First, x86 lazily faults in top-level paging entries for the vmalloc area. This won't work if we get a page fault while trying to access the stack: the CPU will promote it to a double-fault and we'll die. To avoid this problem, probe the new stack when switching stacks and forcibly populate the pgd entry for the stack when switching mms. Second, once we have guard pages around the stack, we'll want to detect and handle stack overflow. I didn't enable it on x86_32. We'd need to rework the double-fault code a bit and I'm concerned about running out of vmalloc virtual addresses under some workloads. This patch, by itself, will behave somewhat erratically when the stack overflows while RSP is still more than a few tens of bytes above the bottom of the stack. Specifically, we'll get #PF and make it to no_context and them oops without reliably triggering a double-fault, and no_context doesn't know about stack overflows. The next patch will improve that case. Thank you to Nadav and Brian for helping me pay enough attention to the SDM to hopefully get this right. Signed-off-by: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/c88f3e2920b18e6cc621d772a04a62c06869037e.1470907718.git.luto@kernel.org [ Minor edits. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-11 16:35:23 +07:00
#ifdef CONFIG_VMAP_STACK
unsigned long cr2;
#endif
#ifdef CONFIG_X86_ESPFIX64
extern unsigned char native_irq_return_iret[];
/*
* If IRET takes a non-IST fault on the espfix64 stack, then we
* end up promoting it to a doublefault. In that case, modify
* the stack to make it look like we just entered the #GP
* handler from user space, similar to bad_iret.
*
* No need for ist_enter here because we don't use RCU.
*/
if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY &&
regs->cs == __KERNEL_CS &&
regs->ip == (unsigned long)native_irq_return_iret)
{
struct pt_regs *normal_regs = task_pt_regs(current);
/* Fake a #GP(0) from userspace. */
memmove(&normal_regs->ip, (void *)regs->sp, 5*8);
normal_regs->orig_ax = 0; /* Missing (lost) #GP error code */
regs->ip = (unsigned long)general_protection;
regs->sp = (unsigned long)&normal_regs->orig_ax;
return;
}
#endif
ist_enter(regs);
notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = X86_TRAP_DF;
x86/mm/64: Enable vmapped stacks (CONFIG_HAVE_ARCH_VMAP_STACK=y) This allows x86_64 kernels to enable vmapped stacks by setting HAVE_ARCH_VMAP_STACK=y - which enables the CONFIG_VMAP_STACK=y high level Kconfig option. There are a couple of interesting bits: First, x86 lazily faults in top-level paging entries for the vmalloc area. This won't work if we get a page fault while trying to access the stack: the CPU will promote it to a double-fault and we'll die. To avoid this problem, probe the new stack when switching stacks and forcibly populate the pgd entry for the stack when switching mms. Second, once we have guard pages around the stack, we'll want to detect and handle stack overflow. I didn't enable it on x86_32. We'd need to rework the double-fault code a bit and I'm concerned about running out of vmalloc virtual addresses under some workloads. This patch, by itself, will behave somewhat erratically when the stack overflows while RSP is still more than a few tens of bytes above the bottom of the stack. Specifically, we'll get #PF and make it to no_context and them oops without reliably triggering a double-fault, and no_context doesn't know about stack overflows. The next patch will improve that case. Thank you to Nadav and Brian for helping me pay enough attention to the SDM to hopefully get this right. Signed-off-by: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/c88f3e2920b18e6cc621d772a04a62c06869037e.1470907718.git.luto@kernel.org [ Minor edits. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-08-11 16:35:23 +07:00
#ifdef CONFIG_VMAP_STACK
/*
* If we overflow the stack into a guard page, the CPU will fail
* to deliver #PF and will send #DF instead. Similarly, if we
* take any non-IST exception while too close to the bottom of
* the stack, the processor will get a page fault while
* delivering the exception and will generate a double fault.
*
* According to the SDM (footnote in 6.15 under "Interrupt 14 -
* Page-Fault Exception (#PF):
*
* Processors update CR2 whenever a page fault is detected. If a
* second page fault occurs while an earlier page fault is being
* deliv- ered, the faulting linear address of the second fault will
* overwrite the contents of CR2 (replacing the previous
* address). These updates to CR2 occur even if the page fault
* results in a double fault or occurs during the delivery of a
* double fault.
*
* The logic below has a small possibility of incorrectly diagnosing
* some errors as stack overflows. For example, if the IDT or GDT
* gets corrupted such that #GP delivery fails due to a bad descriptor
* causing #GP and we hit this condition while CR2 coincidentally
* points to the stack guard page, we'll think we overflowed the
* stack. Given that we're going to panic one way or another
* if this happens, this isn't necessarily worth fixing.
*
* If necessary, we could improve the test by only diagnosing
* a stack overflow if the saved RSP points within 47 bytes of
* the bottom of the stack: if RSP == tsk_stack + 48 and we
* take an exception, the stack is already aligned and there
* will be enough room SS, RSP, RFLAGS, CS, RIP, and a
* possible error code, so a stack overflow would *not* double
* fault. With any less space left, exception delivery could
* fail, and, as a practical matter, we've overflowed the
* stack even if the actual trigger for the double fault was
* something else.
*/
cr2 = read_cr2();
if ((unsigned long)task_stack_page(tsk) - 1 - cr2 < PAGE_SIZE)
handle_stack_overflow("kernel stack overflow (double-fault)", regs, cr2);
#endif
#ifdef CONFIG_DOUBLEFAULT
df_debug(regs, error_code);
#endif
/*
* This is always a kernel trap and never fixable (and thus must
* never return).
*/
for (;;)
die(str, regs, error_code);
}
#endif
x86, mpx: On-demand kernel allocation of bounds tables This is really the meat of the MPX patch set. If there is one patch to review in the entire series, this is the one. There is a new ABI here and this kernel code also interacts with userspace memory in a relatively unusual manner. (small FAQ below). Long Description: This patch adds two prctl() commands to provide enable or disable the management of bounds tables in kernel, including on-demand kernel allocation (See the patch "on-demand kernel allocation of bounds tables") and cleanup (See the patch "cleanup unused bound tables"). Applications do not strictly need the kernel to manage bounds tables and we expect some applications to use MPX without taking advantage of this kernel support. This means the kernel can not simply infer whether an application needs bounds table management from the MPX registers. The prctl() is an explicit signal from userspace. PR_MPX_ENABLE_MANAGEMENT is meant to be a signal from userspace to require kernel's help in managing bounds tables. PR_MPX_DISABLE_MANAGEMENT is the opposite, meaning that userspace don't want kernel's help any more. With PR_MPX_DISABLE_MANAGEMENT, the kernel won't allocate and free bounds tables even if the CPU supports MPX. PR_MPX_ENABLE_MANAGEMENT will fetch the base address of the bounds directory out of a userspace register (bndcfgu) and then cache it into a new field (->bd_addr) in the 'mm_struct'. PR_MPX_DISABLE_MANAGEMENT will set "bd_addr" to an invalid address. Using this scheme, we can use "bd_addr" to determine whether the management of bounds tables in kernel is enabled. Also, the only way to access that bndcfgu register is via an xsaves, which can be expensive. Caching "bd_addr" like this also helps reduce the cost of those xsaves when doing table cleanup at munmap() time. Unfortunately, we can not apply this optimization to #BR fault time because we need an xsave to get the value of BNDSTATUS. ==== Why does the hardware even have these Bounds Tables? ==== MPX only has 4 hardware registers for storing bounds information. If MPX-enabled code needs more than these 4 registers, it needs to spill them somewhere. It has two special instructions for this which allow the bounds to be moved between the bounds registers and some new "bounds tables". They are similar conceptually to a page fault and will be raised by the MPX hardware during both bounds violations or when the tables are not present. This patch handles those #BR exceptions for not-present tables by carving the space out of the normal processes address space (essentially calling the new mmap() interface indroduced earlier in this patch set.) and then pointing the bounds-directory over to it. The tables *need* to be accessed and controlled by userspace because the instructions for moving bounds in and out of them are extremely frequent. They potentially happen every time a register pointing to memory is dereferenced. Any direct kernel involvement (like a syscall) to access the tables would obviously destroy performance. ==== Why not do this in userspace? ==== This patch is obviously doing this allocation in the kernel. However, MPX does not strictly *require* anything in the kernel. It can theoretically be done completely from userspace. Here are a few ways this *could* be done. I don't think any of them are practical in the real-world, but here they are. Q: Can virtual space simply be reserved for the bounds tables so that we never have to allocate them? A: As noted earlier, these tables are *HUGE*. An X-GB virtual area needs 4*X GB of virtual space, plus 2GB for the bounds directory. If we were to preallocate them for the 128TB of user virtual address space, we would need to reserve 512TB+2GB, which is larger than the entire virtual address space today. This means they can not be reserved ahead of time. Also, a single process's pre-popualated bounds directory consumes 2GB of virtual *AND* physical memory. IOW, it's completely infeasible to prepopulate bounds directories. Q: Can we preallocate bounds table space at the same time memory is allocated which might contain pointers that might eventually need bounds tables? A: This would work if we could hook the site of each and every memory allocation syscall. This can be done for small, constrained applications. But, it isn't practical at a larger scale since a given app has no way of controlling how all the parts of the app might allocate memory (think libraries). The kernel is really the only place to intercept these calls. Q: Could a bounds fault be handed to userspace and the tables allocated there in a signal handler instead of in the kernel? A: (thanks to tglx) mmap() is not on the list of safe async handler functions and even if mmap() would work it still requires locking or nasty tricks to keep track of the allocation state there. Having ruled out all of the userspace-only approaches for managing bounds tables that we could think of, we create them on demand in the kernel. Based-on-patch-by: Qiaowei Ren <qiaowei.ren@intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: linux-mm@kvack.org Cc: linux-mips@linux-mips.org Cc: Dave Hansen <dave@sr71.net> Link: http://lkml.kernel.org/r/20141114151829.AD4310DE@viggo.jf.intel.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2014-11-14 22:18:29 +07:00
dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
{
const struct mpx_bndcsr *bndcsr;
x86, mpx: On-demand kernel allocation of bounds tables This is really the meat of the MPX patch set. If there is one patch to review in the entire series, this is the one. There is a new ABI here and this kernel code also interacts with userspace memory in a relatively unusual manner. (small FAQ below). Long Description: This patch adds two prctl() commands to provide enable or disable the management of bounds tables in kernel, including on-demand kernel allocation (See the patch "on-demand kernel allocation of bounds tables") and cleanup (See the patch "cleanup unused bound tables"). Applications do not strictly need the kernel to manage bounds tables and we expect some applications to use MPX without taking advantage of this kernel support. This means the kernel can not simply infer whether an application needs bounds table management from the MPX registers. The prctl() is an explicit signal from userspace. PR_MPX_ENABLE_MANAGEMENT is meant to be a signal from userspace to require kernel's help in managing bounds tables. PR_MPX_DISABLE_MANAGEMENT is the opposite, meaning that userspace don't want kernel's help any more. With PR_MPX_DISABLE_MANAGEMENT, the kernel won't allocate and free bounds tables even if the CPU supports MPX. PR_MPX_ENABLE_MANAGEMENT will fetch the base address of the bounds directory out of a userspace register (bndcfgu) and then cache it into a new field (->bd_addr) in the 'mm_struct'. PR_MPX_DISABLE_MANAGEMENT will set "bd_addr" to an invalid address. Using this scheme, we can use "bd_addr" to determine whether the management of bounds tables in kernel is enabled. Also, the only way to access that bndcfgu register is via an xsaves, which can be expensive. Caching "bd_addr" like this also helps reduce the cost of those xsaves when doing table cleanup at munmap() time. Unfortunately, we can not apply this optimization to #BR fault time because we need an xsave to get the value of BNDSTATUS. ==== Why does the hardware even have these Bounds Tables? ==== MPX only has 4 hardware registers for storing bounds information. If MPX-enabled code needs more than these 4 registers, it needs to spill them somewhere. It has two special instructions for this which allow the bounds to be moved between the bounds registers and some new "bounds tables". They are similar conceptually to a page fault and will be raised by the MPX hardware during both bounds violations or when the tables are not present. This patch handles those #BR exceptions for not-present tables by carving the space out of the normal processes address space (essentially calling the new mmap() interface indroduced earlier in this patch set.) and then pointing the bounds-directory over to it. The tables *need* to be accessed and controlled by userspace because the instructions for moving bounds in and out of them are extremely frequent. They potentially happen every time a register pointing to memory is dereferenced. Any direct kernel involvement (like a syscall) to access the tables would obviously destroy performance. ==== Why not do this in userspace? ==== This patch is obviously doing this allocation in the kernel. However, MPX does not strictly *require* anything in the kernel. It can theoretically be done completely from userspace. Here are a few ways this *could* be done. I don't think any of them are practical in the real-world, but here they are. Q: Can virtual space simply be reserved for the bounds tables so that we never have to allocate them? A: As noted earlier, these tables are *HUGE*. An X-GB virtual area needs 4*X GB of virtual space, plus 2GB for the bounds directory. If we were to preallocate them for the 128TB of user virtual address space, we would need to reserve 512TB+2GB, which is larger than the entire virtual address space today. This means they can not be reserved ahead of time. Also, a single process's pre-popualated bounds directory consumes 2GB of virtual *AND* physical memory. IOW, it's completely infeasible to prepopulate bounds directories. Q: Can we preallocate bounds table space at the same time memory is allocated which might contain pointers that might eventually need bounds tables? A: This would work if we could hook the site of each and every memory allocation syscall. This can be done for small, constrained applications. But, it isn't practical at a larger scale since a given app has no way of controlling how all the parts of the app might allocate memory (think libraries). The kernel is really the only place to intercept these calls. Q: Could a bounds fault be handed to userspace and the tables allocated there in a signal handler instead of in the kernel? A: (thanks to tglx) mmap() is not on the list of safe async handler functions and even if mmap() would work it still requires locking or nasty tricks to keep track of the allocation state there. Having ruled out all of the userspace-only approaches for managing bounds tables that we could think of, we create them on demand in the kernel. Based-on-patch-by: Qiaowei Ren <qiaowei.ren@intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: linux-mm@kvack.org Cc: linux-mips@linux-mips.org Cc: Dave Hansen <dave@sr71.net> Link: http://lkml.kernel.org/r/20141114151829.AD4310DE@viggo.jf.intel.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2014-11-14 22:18:29 +07:00
siginfo_t *info;
Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull x86 asm changes from Ingo Molnar: "The biggest changes in this cycle were: - Revamp, simplify (and in some cases fix) Time Stamp Counter (TSC) primitives. (Andy Lutomirski) - Add new, comprehensible entry and exit handlers written in C. (Andy Lutomirski) - vm86 mode cleanups and fixes. (Brian Gerst) - 32-bit compat code cleanups. (Brian Gerst) The amount of simplification in low level assembly code is already palpable: arch/x86/entry/entry_32.S | 130 +---- arch/x86/entry/entry_64.S | 197 ++----- but more simplifications are planned. There's also the usual laudry mix of low level changes - see the changelog for details" * 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (83 commits) x86/asm: Drop repeated macro of X86_EFLAGS_AC definition x86/asm/msr: Make wrmsrl() a function x86/asm/delay: Introduce an MWAITX-based delay with a configurable timer x86/asm: Add MONITORX/MWAITX instruction support x86/traps: Weaken context tracking entry assertions x86/asm/tsc: Add rdtscll() merge helper selftests/x86: Add syscall_nt selftest selftests/x86: Disable sigreturn_64 x86/vdso: Emit a GNU hash x86/entry: Remove do_notify_resume(), syscall_trace_leave(), and their TIF masks x86/entry/32: Migrate to C exit path x86/entry/32: Remove 32-bit syscall audit optimizations x86/vm86: Rename vm86->v86flags and v86mask x86/vm86: Rename vm86->vm86_info to user_vm86 x86/vm86: Clean up vm86.h includes x86/vm86: Move the vm86 IRQ definitions to vm86.h x86/vm86: Use the normal pt_regs area for vm86 x86/vm86: Eliminate 'struct kernel_vm86_struct' x86/vm86: Move fields from 'struct kernel_vm86_struct' to 'struct vm86' x86/vm86: Move vm86 fields out of 'thread_struct' ...
2015-09-01 22:40:25 +07:00
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
x86, mpx: On-demand kernel allocation of bounds tables This is really the meat of the MPX patch set. If there is one patch to review in the entire series, this is the one. There is a new ABI here and this kernel code also interacts with userspace memory in a relatively unusual manner. (small FAQ below). Long Description: This patch adds two prctl() commands to provide enable or disable the management of bounds tables in kernel, including on-demand kernel allocation (See the patch "on-demand kernel allocation of bounds tables") and cleanup (See the patch "cleanup unused bound tables"). Applications do not strictly need the kernel to manage bounds tables and we expect some applications to use MPX without taking advantage of this kernel support. This means the kernel can not simply infer whether an application needs bounds table management from the MPX registers. The prctl() is an explicit signal from userspace. PR_MPX_ENABLE_MANAGEMENT is meant to be a signal from userspace to require kernel's help in managing bounds tables. PR_MPX_DISABLE_MANAGEMENT is the opposite, meaning that userspace don't want kernel's help any more. With PR_MPX_DISABLE_MANAGEMENT, the kernel won't allocate and free bounds tables even if the CPU supports MPX. PR_MPX_ENABLE_MANAGEMENT will fetch the base address of the bounds directory out of a userspace register (bndcfgu) and then cache it into a new field (->bd_addr) in the 'mm_struct'. PR_MPX_DISABLE_MANAGEMENT will set "bd_addr" to an invalid address. Using this scheme, we can use "bd_addr" to determine whether the management of bounds tables in kernel is enabled. Also, the only way to access that bndcfgu register is via an xsaves, which can be expensive. Caching "bd_addr" like this also helps reduce the cost of those xsaves when doing table cleanup at munmap() time. Unfortunately, we can not apply this optimization to #BR fault time because we need an xsave to get the value of BNDSTATUS. ==== Why does the hardware even have these Bounds Tables? ==== MPX only has 4 hardware registers for storing bounds information. If MPX-enabled code needs more than these 4 registers, it needs to spill them somewhere. It has two special instructions for this which allow the bounds to be moved between the bounds registers and some new "bounds tables". They are similar conceptually to a page fault and will be raised by the MPX hardware during both bounds violations or when the tables are not present. This patch handles those #BR exceptions for not-present tables by carving the space out of the normal processes address space (essentially calling the new mmap() interface indroduced earlier in this patch set.) and then pointing the bounds-directory over to it. The tables *need* to be accessed and controlled by userspace because the instructions for moving bounds in and out of them are extremely frequent. They potentially happen every time a register pointing to memory is dereferenced. Any direct kernel involvement (like a syscall) to access the tables would obviously destroy performance. ==== Why not do this in userspace? ==== This patch is obviously doing this allocation in the kernel. However, MPX does not strictly *require* anything in the kernel. It can theoretically be done completely from userspace. Here are a few ways this *could* be done. I don't think any of them are practical in the real-world, but here they are. Q: Can virtual space simply be reserved for the bounds tables so that we never have to allocate them? A: As noted earlier, these tables are *HUGE*. An X-GB virtual area needs 4*X GB of virtual space, plus 2GB for the bounds directory. If we were to preallocate them for the 128TB of user virtual address space, we would need to reserve 512TB+2GB, which is larger than the entire virtual address space today. This means they can not be reserved ahead of time. Also, a single process's pre-popualated bounds directory consumes 2GB of virtual *AND* physical memory. IOW, it's completely infeasible to prepopulate bounds directories. Q: Can we preallocate bounds table space at the same time memory is allocated which might contain pointers that might eventually need bounds tables? A: This would work if we could hook the site of each and every memory allocation syscall. This can be done for small, constrained applications. But, it isn't practical at a larger scale since a given app has no way of controlling how all the parts of the app might allocate memory (think libraries). The kernel is really the only place to intercept these calls. Q: Could a bounds fault be handed to userspace and the tables allocated there in a signal handler instead of in the kernel? A: (thanks to tglx) mmap() is not on the list of safe async handler functions and even if mmap() would work it still requires locking or nasty tricks to keep track of the allocation state there. Having ruled out all of the userspace-only approaches for managing bounds tables that we could think of, we create them on demand in the kernel. Based-on-patch-by: Qiaowei Ren <qiaowei.ren@intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: linux-mm@kvack.org Cc: linux-mips@linux-mips.org Cc: Dave Hansen <dave@sr71.net> Link: http://lkml.kernel.org/r/20141114151829.AD4310DE@viggo.jf.intel.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2014-11-14 22:18:29 +07:00
if (notify_die(DIE_TRAP, "bounds", regs, error_code,
X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP)
return;
cond_local_irq_enable(regs);
x86, mpx: On-demand kernel allocation of bounds tables This is really the meat of the MPX patch set. If there is one patch to review in the entire series, this is the one. There is a new ABI here and this kernel code also interacts with userspace memory in a relatively unusual manner. (small FAQ below). Long Description: This patch adds two prctl() commands to provide enable or disable the management of bounds tables in kernel, including on-demand kernel allocation (See the patch "on-demand kernel allocation of bounds tables") and cleanup (See the patch "cleanup unused bound tables"). Applications do not strictly need the kernel to manage bounds tables and we expect some applications to use MPX without taking advantage of this kernel support. This means the kernel can not simply infer whether an application needs bounds table management from the MPX registers. The prctl() is an explicit signal from userspace. PR_MPX_ENABLE_MANAGEMENT is meant to be a signal from userspace to require kernel's help in managing bounds tables. PR_MPX_DISABLE_MANAGEMENT is the opposite, meaning that userspace don't want kernel's help any more. With PR_MPX_DISABLE_MANAGEMENT, the kernel won't allocate and free bounds tables even if the CPU supports MPX. PR_MPX_ENABLE_MANAGEMENT will fetch the base address of the bounds directory out of a userspace register (bndcfgu) and then cache it into a new field (->bd_addr) in the 'mm_struct'. PR_MPX_DISABLE_MANAGEMENT will set "bd_addr" to an invalid address. Using this scheme, we can use "bd_addr" to determine whether the management of bounds tables in kernel is enabled. Also, the only way to access that bndcfgu register is via an xsaves, which can be expensive. Caching "bd_addr" like this also helps reduce the cost of those xsaves when doing table cleanup at munmap() time. Unfortunately, we can not apply this optimization to #BR fault time because we need an xsave to get the value of BNDSTATUS. ==== Why does the hardware even have these Bounds Tables? ==== MPX only has 4 hardware registers for storing bounds information. If MPX-enabled code needs more than these 4 registers, it needs to spill them somewhere. It has two special instructions for this which allow the bounds to be moved between the bounds registers and some new "bounds tables". They are similar conceptually to a page fault and will be raised by the MPX hardware during both bounds violations or when the tables are not present. This patch handles those #BR exceptions for not-present tables by carving the space out of the normal processes address space (essentially calling the new mmap() interface indroduced earlier in this patch set.) and then pointing the bounds-directory over to it. The tables *need* to be accessed and controlled by userspace because the instructions for moving bounds in and out of them are extremely frequent. They potentially happen every time a register pointing to memory is dereferenced. Any direct kernel involvement (like a syscall) to access the tables would obviously destroy performance. ==== Why not do this in userspace? ==== This patch is obviously doing this allocation in the kernel. However, MPX does not strictly *require* anything in the kernel. It can theoretically be done completely from userspace. Here are a few ways this *could* be done. I don't think any of them are practical in the real-world, but here they are. Q: Can virtual space simply be reserved for the bounds tables so that we never have to allocate them? A: As noted earlier, these tables are *HUGE*. An X-GB virtual area needs 4*X GB of virtual space, plus 2GB for the bounds directory. If we were to preallocate them for the 128TB of user virtual address space, we would need to reserve 512TB+2GB, which is larger than the entire virtual address space today. This means they can not be reserved ahead of time. Also, a single process's pre-popualated bounds directory consumes 2GB of virtual *AND* physical memory. IOW, it's completely infeasible to prepopulate bounds directories. Q: Can we preallocate bounds table space at the same time memory is allocated which might contain pointers that might eventually need bounds tables? A: This would work if we could hook the site of each and every memory allocation syscall. This can be done for small, constrained applications. But, it isn't practical at a larger scale since a given app has no way of controlling how all the parts of the app might allocate memory (think libraries). The kernel is really the only place to intercept these calls. Q: Could a bounds fault be handed to userspace and the tables allocated there in a signal handler instead of in the kernel? A: (thanks to tglx) mmap() is not on the list of safe async handler functions and even if mmap() would work it still requires locking or nasty tricks to keep track of the allocation state there. Having ruled out all of the userspace-only approaches for managing bounds tables that we could think of, we create them on demand in the kernel. Based-on-patch-by: Qiaowei Ren <qiaowei.ren@intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: linux-mm@kvack.org Cc: linux-mips@linux-mips.org Cc: Dave Hansen <dave@sr71.net> Link: http://lkml.kernel.org/r/20141114151829.AD4310DE@viggo.jf.intel.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2014-11-14 22:18:29 +07:00
if (!user_mode(regs))
x86, mpx: On-demand kernel allocation of bounds tables This is really the meat of the MPX patch set. If there is one patch to review in the entire series, this is the one. There is a new ABI here and this kernel code also interacts with userspace memory in a relatively unusual manner. (small FAQ below). Long Description: This patch adds two prctl() commands to provide enable or disable the management of bounds tables in kernel, including on-demand kernel allocation (See the patch "on-demand kernel allocation of bounds tables") and cleanup (See the patch "cleanup unused bound tables"). Applications do not strictly need the kernel to manage bounds tables and we expect some applications to use MPX without taking advantage of this kernel support. This means the kernel can not simply infer whether an application needs bounds table management from the MPX registers. The prctl() is an explicit signal from userspace. PR_MPX_ENABLE_MANAGEMENT is meant to be a signal from userspace to require kernel's help in managing bounds tables. PR_MPX_DISABLE_MANAGEMENT is the opposite, meaning that userspace don't want kernel's help any more. With PR_MPX_DISABLE_MANAGEMENT, the kernel won't allocate and free bounds tables even if the CPU supports MPX. PR_MPX_ENABLE_MANAGEMENT will fetch the base address of the bounds directory out of a userspace register (bndcfgu) and then cache it into a new field (->bd_addr) in the 'mm_struct'. PR_MPX_DISABLE_MANAGEMENT will set "bd_addr" to an invalid address. Using this scheme, we can use "bd_addr" to determine whether the management of bounds tables in kernel is enabled. Also, the only way to access that bndcfgu register is via an xsaves, which can be expensive. Caching "bd_addr" like this also helps reduce the cost of those xsaves when doing table cleanup at munmap() time. Unfortunately, we can not apply this optimization to #BR fault time because we need an xsave to get the value of BNDSTATUS. ==== Why does the hardware even have these Bounds Tables? ==== MPX only has 4 hardware registers for storing bounds information. If MPX-enabled code needs more than these 4 registers, it needs to spill them somewhere. It has two special instructions for this which allow the bounds to be moved between the bounds registers and some new "bounds tables". They are similar conceptually to a page fault and will be raised by the MPX hardware during both bounds violations or when the tables are not present. This patch handles those #BR exceptions for not-present tables by carving the space out of the normal processes address space (essentially calling the new mmap() interface indroduced earlier in this patch set.) and then pointing the bounds-directory over to it. The tables *need* to be accessed and controlled by userspace because the instructions for moving bounds in and out of them are extremely frequent. They potentially happen every time a register pointing to memory is dereferenced. Any direct kernel involvement (like a syscall) to access the tables would obviously destroy performance. ==== Why not do this in userspace? ==== This patch is obviously doing this allocation in the kernel. However, MPX does not strictly *require* anything in the kernel. It can theoretically be done completely from userspace. Here are a few ways this *could* be done. I don't think any of them are practical in the real-world, but here they are. Q: Can virtual space simply be reserved for the bounds tables so that we never have to allocate them? A: As noted earlier, these tables are *HUGE*. An X-GB virtual area needs 4*X GB of virtual space, plus 2GB for the bounds directory. If we were to preallocate them for the 128TB of user virtual address space, we would need to reserve 512TB+2GB, which is larger than the entire virtual address space today. This means they can not be reserved ahead of time. Also, a single process's pre-popualated bounds directory consumes 2GB of virtual *AND* physical memory. IOW, it's completely infeasible to prepopulate bounds directories. Q: Can we preallocate bounds table space at the same time memory is allocated which might contain pointers that might eventually need bounds tables? A: This would work if we could hook the site of each and every memory allocation syscall. This can be done for small, constrained applications. But, it isn't practical at a larger scale since a given app has no way of controlling how all the parts of the app might allocate memory (think libraries). The kernel is really the only place to intercept these calls. Q: Could a bounds fault be handed to userspace and the tables allocated there in a signal handler instead of in the kernel? A: (thanks to tglx) mmap() is not on the list of safe async handler functions and even if mmap() would work it still requires locking or nasty tricks to keep track of the allocation state there. Having ruled out all of the userspace-only approaches for managing bounds tables that we could think of, we create them on demand in the kernel. Based-on-patch-by: Qiaowei Ren <qiaowei.ren@intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: linux-mm@kvack.org Cc: linux-mips@linux-mips.org Cc: Dave Hansen <dave@sr71.net> Link: http://lkml.kernel.org/r/20141114151829.AD4310DE@viggo.jf.intel.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2014-11-14 22:18:29 +07:00
die("bounds", regs, error_code);
if (!cpu_feature_enabled(X86_FEATURE_MPX)) {
/* The exception is not from Intel MPX */
goto exit_trap;
}
/*
* We need to look at BNDSTATUS to resolve this exception.
* A NULL here might mean that it is in its 'init state',
* which is all zeros which indicates MPX was not
* responsible for the exception.
x86, mpx: On-demand kernel allocation of bounds tables This is really the meat of the MPX patch set. If there is one patch to review in the entire series, this is the one. There is a new ABI here and this kernel code also interacts with userspace memory in a relatively unusual manner. (small FAQ below). Long Description: This patch adds two prctl() commands to provide enable or disable the management of bounds tables in kernel, including on-demand kernel allocation (See the patch "on-demand kernel allocation of bounds tables") and cleanup (See the patch "cleanup unused bound tables"). Applications do not strictly need the kernel to manage bounds tables and we expect some applications to use MPX without taking advantage of this kernel support. This means the kernel can not simply infer whether an application needs bounds table management from the MPX registers. The prctl() is an explicit signal from userspace. PR_MPX_ENABLE_MANAGEMENT is meant to be a signal from userspace to require kernel's help in managing bounds tables. PR_MPX_DISABLE_MANAGEMENT is the opposite, meaning that userspace don't want kernel's help any more. With PR_MPX_DISABLE_MANAGEMENT, the kernel won't allocate and free bounds tables even if the CPU supports MPX. PR_MPX_ENABLE_MANAGEMENT will fetch the base address of the bounds directory out of a userspace register (bndcfgu) and then cache it into a new field (->bd_addr) in the 'mm_struct'. PR_MPX_DISABLE_MANAGEMENT will set "bd_addr" to an invalid address. Using this scheme, we can use "bd_addr" to determine whether the management of bounds tables in kernel is enabled. Also, the only way to access that bndcfgu register is via an xsaves, which can be expensive. Caching "bd_addr" like this also helps reduce the cost of those xsaves when doing table cleanup at munmap() time. Unfortunately, we can not apply this optimization to #BR fault time because we need an xsave to get the value of BNDSTATUS. ==== Why does the hardware even have these Bounds Tables? ==== MPX only has 4 hardware registers for storing bounds information. If MPX-enabled code needs more than these 4 registers, it needs to spill them somewhere. It has two special instructions for this which allow the bounds to be moved between the bounds registers and some new "bounds tables". They are similar conceptually to a page fault and will be raised by the MPX hardware during both bounds violations or when the tables are not present. This patch handles those #BR exceptions for not-present tables by carving the space out of the normal processes address space (essentially calling the new mmap() interface indroduced earlier in this patch set.) and then pointing the bounds-directory over to it. The tables *need* to be accessed and controlled by userspace because the instructions for moving bounds in and out of them are extremely frequent. They potentially happen every time a register pointing to memory is dereferenced. Any direct kernel involvement (like a syscall) to access the tables would obviously destroy performance. ==== Why not do this in userspace? ==== This patch is obviously doing this allocation in the kernel. However, MPX does not strictly *require* anything in the kernel. It can theoretically be done completely from userspace. Here are a few ways this *could* be done. I don't think any of them are practical in the real-world, but here they are. Q: Can virtual space simply be reserved for the bounds tables so that we never have to allocate them? A: As noted earlier, these tables are *HUGE*. An X-GB virtual area needs 4*X GB of virtual space, plus 2GB for the bounds directory. If we were to preallocate them for the 128TB of user virtual address space, we would need to reserve 512TB+2GB, which is larger than the entire virtual address space today. This means they can not be reserved ahead of time. Also, a single process's pre-popualated bounds directory consumes 2GB of virtual *AND* physical memory. IOW, it's completely infeasible to prepopulate bounds directories. Q: Can we preallocate bounds table space at the same time memory is allocated which might contain pointers that might eventually need bounds tables? A: This would work if we could hook the site of each and every memory allocation syscall. This can be done for small, constrained applications. But, it isn't practical at a larger scale since a given app has no way of controlling how all the parts of the app might allocate memory (think libraries). The kernel is really the only place to intercept these calls. Q: Could a bounds fault be handed to userspace and the tables allocated there in a signal handler instead of in the kernel? A: (thanks to tglx) mmap() is not on the list of safe async handler functions and even if mmap() would work it still requires locking or nasty tricks to keep track of the allocation state there. Having ruled out all of the userspace-only approaches for managing bounds tables that we could think of, we create them on demand in the kernel. Based-on-patch-by: Qiaowei Ren <qiaowei.ren@intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: linux-mm@kvack.org Cc: linux-mips@linux-mips.org Cc: Dave Hansen <dave@sr71.net> Link: http://lkml.kernel.org/r/20141114151829.AD4310DE@viggo.jf.intel.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2014-11-14 22:18:29 +07:00
*/
x86/fpu: Rename XSAVE macros There are two concepts that have some confusing naming: 1. Extended State Component numbers (currently called XFEATURE_BIT_*) 2. Extended State Component masks (currently called XSTATE_*) The numbers are (currently) from 0-9. State component 3 is the bounds registers for MPX, for instance. But when we want to enable "state component 3", we go set a bit in XCR0. The bit we set is 1<<3. We can check to see if a state component feature is enabled by looking at its bit. The current 'xfeature_bit's are at best xfeature bit _numbers_. Calling them bits is at best inconsistent with ending the enum list with 'XFEATURES_NR_MAX'. This patch renames the enum to be 'xfeature'. These also happen to be what the Intel documentation calls a "state component". We also want to differentiate these from the "XSTATE_*" macros. The "XSTATE_*" macros are a mask, and we rename them to match. These macros are reasonably widely used so this patch is a wee bit big, but this really is just a rename. The only non-mechanical part of this is the s/XSTATE_EXTEND_MASK/XFEATURE_MASK_EXTEND/ We need a better name for it, but that's another patch. Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: dave@sr71.net Cc: linux-kernel@vger.kernel.org Link: http://lkml.kernel.org/r/20150902233126.38653250@viggo.jf.intel.com [ Ported to v4.3-rc1. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-09-03 06:31:26 +07:00
bndcsr = get_xsave_field_ptr(XFEATURE_MASK_BNDCSR);
x86, mpx: On-demand kernel allocation of bounds tables This is really the meat of the MPX patch set. If there is one patch to review in the entire series, this is the one. There is a new ABI here and this kernel code also interacts with userspace memory in a relatively unusual manner. (small FAQ below). Long Description: This patch adds two prctl() commands to provide enable or disable the management of bounds tables in kernel, including on-demand kernel allocation (See the patch "on-demand kernel allocation of bounds tables") and cleanup (See the patch "cleanup unused bound tables"). Applications do not strictly need the kernel to manage bounds tables and we expect some applications to use MPX without taking advantage of this kernel support. This means the kernel can not simply infer whether an application needs bounds table management from the MPX registers. The prctl() is an explicit signal from userspace. PR_MPX_ENABLE_MANAGEMENT is meant to be a signal from userspace to require kernel's help in managing bounds tables. PR_MPX_DISABLE_MANAGEMENT is the opposite, meaning that userspace don't want kernel's help any more. With PR_MPX_DISABLE_MANAGEMENT, the kernel won't allocate and free bounds tables even if the CPU supports MPX. PR_MPX_ENABLE_MANAGEMENT will fetch the base address of the bounds directory out of a userspace register (bndcfgu) and then cache it into a new field (->bd_addr) in the 'mm_struct'. PR_MPX_DISABLE_MANAGEMENT will set "bd_addr" to an invalid address. Using this scheme, we can use "bd_addr" to determine whether the management of bounds tables in kernel is enabled. Also, the only way to access that bndcfgu register is via an xsaves, which can be expensive. Caching "bd_addr" like this also helps reduce the cost of those xsaves when doing table cleanup at munmap() time. Unfortunately, we can not apply this optimization to #BR fault time because we need an xsave to get the value of BNDSTATUS. ==== Why does the hardware even have these Bounds Tables? ==== MPX only has 4 hardware registers for storing bounds information. If MPX-enabled code needs more than these 4 registers, it needs to spill them somewhere. It has two special instructions for this which allow the bounds to be moved between the bounds registers and some new "bounds tables". They are similar conceptually to a page fault and will be raised by the MPX hardware during both bounds violations or when the tables are not present. This patch handles those #BR exceptions for not-present tables by carving the space out of the normal processes address space (essentially calling the new mmap() interface indroduced earlier in this patch set.) and then pointing the bounds-directory over to it. The tables *need* to be accessed and controlled by userspace because the instructions for moving bounds in and out of them are extremely frequent. They potentially happen every time a register pointing to memory is dereferenced. Any direct kernel involvement (like a syscall) to access the tables would obviously destroy performance. ==== Why not do this in userspace? ==== This patch is obviously doing this allocation in the kernel. However, MPX does not strictly *require* anything in the kernel. It can theoretically be done completely from userspace. Here are a few ways this *could* be done. I don't think any of them are practical in the real-world, but here they are. Q: Can virtual space simply be reserved for the bounds tables so that we never have to allocate them? A: As noted earlier, these tables are *HUGE*. An X-GB virtual area needs 4*X GB of virtual space, plus 2GB for the bounds directory. If we were to preallocate them for the 128TB of user virtual address space, we would need to reserve 512TB+2GB, which is larger than the entire virtual address space today. This means they can not be reserved ahead of time. Also, a single process's pre-popualated bounds directory consumes 2GB of virtual *AND* physical memory. IOW, it's completely infeasible to prepopulate bounds directories. Q: Can we preallocate bounds table space at the same time memory is allocated which might contain pointers that might eventually need bounds tables? A: This would work if we could hook the site of each and every memory allocation syscall. This can be done for small, constrained applications. But, it isn't practical at a larger scale since a given app has no way of controlling how all the parts of the app might allocate memory (think libraries). The kernel is really the only place to intercept these calls. Q: Could a bounds fault be handed to userspace and the tables allocated there in a signal handler instead of in the kernel? A: (thanks to tglx) mmap() is not on the list of safe async handler functions and even if mmap() would work it still requires locking or nasty tricks to keep track of the allocation state there. Having ruled out all of the userspace-only approaches for managing bounds tables that we could think of, we create them on demand in the kernel. Based-on-patch-by: Qiaowei Ren <qiaowei.ren@intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: linux-mm@kvack.org Cc: linux-mips@linux-mips.org Cc: Dave Hansen <dave@sr71.net> Link: http://lkml.kernel.org/r/20141114151829.AD4310DE@viggo.jf.intel.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2014-11-14 22:18:29 +07:00
if (!bndcsr)
goto exit_trap;
trace_bounds_exception_mpx(bndcsr);
x86, mpx: On-demand kernel allocation of bounds tables This is really the meat of the MPX patch set. If there is one patch to review in the entire series, this is the one. There is a new ABI here and this kernel code also interacts with userspace memory in a relatively unusual manner. (small FAQ below). Long Description: This patch adds two prctl() commands to provide enable or disable the management of bounds tables in kernel, including on-demand kernel allocation (See the patch "on-demand kernel allocation of bounds tables") and cleanup (See the patch "cleanup unused bound tables"). Applications do not strictly need the kernel to manage bounds tables and we expect some applications to use MPX without taking advantage of this kernel support. This means the kernel can not simply infer whether an application needs bounds table management from the MPX registers. The prctl() is an explicit signal from userspace. PR_MPX_ENABLE_MANAGEMENT is meant to be a signal from userspace to require kernel's help in managing bounds tables. PR_MPX_DISABLE_MANAGEMENT is the opposite, meaning that userspace don't want kernel's help any more. With PR_MPX_DISABLE_MANAGEMENT, the kernel won't allocate and free bounds tables even if the CPU supports MPX. PR_MPX_ENABLE_MANAGEMENT will fetch the base address of the bounds directory out of a userspace register (bndcfgu) and then cache it into a new field (->bd_addr) in the 'mm_struct'. PR_MPX_DISABLE_MANAGEMENT will set "bd_addr" to an invalid address. Using this scheme, we can use "bd_addr" to determine whether the management of bounds tables in kernel is enabled. Also, the only way to access that bndcfgu register is via an xsaves, which can be expensive. Caching "bd_addr" like this also helps reduce the cost of those xsaves when doing table cleanup at munmap() time. Unfortunately, we can not apply this optimization to #BR fault time because we need an xsave to get the value of BNDSTATUS. ==== Why does the hardware even have these Bounds Tables? ==== MPX only has 4 hardware registers for storing bounds information. If MPX-enabled code needs more than these 4 registers, it needs to spill them somewhere. It has two special instructions for this which allow the bounds to be moved between the bounds registers and some new "bounds tables". They are similar conceptually to a page fault and will be raised by the MPX hardware during both bounds violations or when the tables are not present. This patch handles those #BR exceptions for not-present tables by carving the space out of the normal processes address space (essentially calling the new mmap() interface indroduced earlier in this patch set.) and then pointing the bounds-directory over to it. The tables *need* to be accessed and controlled by userspace because the instructions for moving bounds in and out of them are extremely frequent. They potentially happen every time a register pointing to memory is dereferenced. Any direct kernel involvement (like a syscall) to access the tables would obviously destroy performance. ==== Why not do this in userspace? ==== This patch is obviously doing this allocation in the kernel. However, MPX does not strictly *require* anything in the kernel. It can theoretically be done completely from userspace. Here are a few ways this *could* be done. I don't think any of them are practical in the real-world, but here they are. Q: Can virtual space simply be reserved for the bounds tables so that we never have to allocate them? A: As noted earlier, these tables are *HUGE*. An X-GB virtual area needs 4*X GB of virtual space, plus 2GB for the bounds directory. If we were to preallocate them for the 128TB of user virtual address space, we would need to reserve 512TB+2GB, which is larger than the entire virtual address space today. This means they can not be reserved ahead of time. Also, a single process's pre-popualated bounds directory consumes 2GB of virtual *AND* physical memory. IOW, it's completely infeasible to prepopulate bounds directories. Q: Can we preallocate bounds table space at the same time memory is allocated which might contain pointers that might eventually need bounds tables? A: This would work if we could hook the site of each and every memory allocation syscall. This can be done for small, constrained applications. But, it isn't practical at a larger scale since a given app has no way of controlling how all the parts of the app might allocate memory (think libraries). The kernel is really the only place to intercept these calls. Q: Could a bounds fault be handed to userspace and the tables allocated there in a signal handler instead of in the kernel? A: (thanks to tglx) mmap() is not on the list of safe async handler functions and even if mmap() would work it still requires locking or nasty tricks to keep track of the allocation state there. Having ruled out all of the userspace-only approaches for managing bounds tables that we could think of, we create them on demand in the kernel. Based-on-patch-by: Qiaowei Ren <qiaowei.ren@intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: linux-mm@kvack.org Cc: linux-mips@linux-mips.org Cc: Dave Hansen <dave@sr71.net> Link: http://lkml.kernel.org/r/20141114151829.AD4310DE@viggo.jf.intel.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2014-11-14 22:18:29 +07:00
/*
* The error code field of the BNDSTATUS register communicates status
* information of a bound range exception #BR or operation involving
* bound directory.
*/
switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) {
case 2: /* Bound directory has invalid entry. */
if (mpx_handle_bd_fault())
x86, mpx: On-demand kernel allocation of bounds tables This is really the meat of the MPX patch set. If there is one patch to review in the entire series, this is the one. There is a new ABI here and this kernel code also interacts with userspace memory in a relatively unusual manner. (small FAQ below). Long Description: This patch adds two prctl() commands to provide enable or disable the management of bounds tables in kernel, including on-demand kernel allocation (See the patch "on-demand kernel allocation of bounds tables") and cleanup (See the patch "cleanup unused bound tables"). Applications do not strictly need the kernel to manage bounds tables and we expect some applications to use MPX without taking advantage of this kernel support. This means the kernel can not simply infer whether an application needs bounds table management from the MPX registers. The prctl() is an explicit signal from userspace. PR_MPX_ENABLE_MANAGEMENT is meant to be a signal from userspace to require kernel's help in managing bounds tables. PR_MPX_DISABLE_MANAGEMENT is the opposite, meaning that userspace don't want kernel's help any more. With PR_MPX_DISABLE_MANAGEMENT, the kernel won't allocate and free bounds tables even if the CPU supports MPX. PR_MPX_ENABLE_MANAGEMENT will fetch the base address of the bounds directory out of a userspace register (bndcfgu) and then cache it into a new field (->bd_addr) in the 'mm_struct'. PR_MPX_DISABLE_MANAGEMENT will set "bd_addr" to an invalid address. Using this scheme, we can use "bd_addr" to determine whether the management of bounds tables in kernel is enabled. Also, the only way to access that bndcfgu register is via an xsaves, which can be expensive. Caching "bd_addr" like this also helps reduce the cost of those xsaves when doing table cleanup at munmap() time. Unfortunately, we can not apply this optimization to #BR fault time because we need an xsave to get the value of BNDSTATUS. ==== Why does the hardware even have these Bounds Tables? ==== MPX only has 4 hardware registers for storing bounds information. If MPX-enabled code needs more than these 4 registers, it needs to spill them somewhere. It has two special instructions for this which allow the bounds to be moved between the bounds registers and some new "bounds tables". They are similar conceptually to a page fault and will be raised by the MPX hardware during both bounds violations or when the tables are not present. This patch handles those #BR exceptions for not-present tables by carving the space out of the normal processes address space (essentially calling the new mmap() interface indroduced earlier in this patch set.) and then pointing the bounds-directory over to it. The tables *need* to be accessed and controlled by userspace because the instructions for moving bounds in and out of them are extremely frequent. They potentially happen every time a register pointing to memory is dereferenced. Any direct kernel involvement (like a syscall) to access the tables would obviously destroy performance. ==== Why not do this in userspace? ==== This patch is obviously doing this allocation in the kernel. However, MPX does not strictly *require* anything in the kernel. It can theoretically be done completely from userspace. Here are a few ways this *could* be done. I don't think any of them are practical in the real-world, but here they are. Q: Can virtual space simply be reserved for the bounds tables so that we never have to allocate them? A: As noted earlier, these tables are *HUGE*. An X-GB virtual area needs 4*X GB of virtual space, plus 2GB for the bounds directory. If we were to preallocate them for the 128TB of user virtual address space, we would need to reserve 512TB+2GB, which is larger than the entire virtual address space today. This means they can not be reserved ahead of time. Also, a single process's pre-popualated bounds directory consumes 2GB of virtual *AND* physical memory. IOW, it's completely infeasible to prepopulate bounds directories. Q: Can we preallocate bounds table space at the same time memory is allocated which might contain pointers that might eventually need bounds tables? A: This would work if we could hook the site of each and every memory allocation syscall. This can be done for small, constrained applications. But, it isn't practical at a larger scale since a given app has no way of controlling how all the parts of the app might allocate memory (think libraries). The kernel is really the only place to intercept these calls. Q: Could a bounds fault be handed to userspace and the tables allocated there in a signal handler instead of in the kernel? A: (thanks to tglx) mmap() is not on the list of safe async handler functions and even if mmap() would work it still requires locking or nasty tricks to keep track of the allocation state there. Having ruled out all of the userspace-only approaches for managing bounds tables that we could think of, we create them on demand in the kernel. Based-on-patch-by: Qiaowei Ren <qiaowei.ren@intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: linux-mm@kvack.org Cc: linux-mips@linux-mips.org Cc: Dave Hansen <dave@sr71.net> Link: http://lkml.kernel.org/r/20141114151829.AD4310DE@viggo.jf.intel.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2014-11-14 22:18:29 +07:00
goto exit_trap;
break; /* Success, it was handled */
case 1: /* Bound violation. */
info = mpx_generate_siginfo(regs);
if (IS_ERR(info)) {
x86, mpx: On-demand kernel allocation of bounds tables This is really the meat of the MPX patch set. If there is one patch to review in the entire series, this is the one. There is a new ABI here and this kernel code also interacts with userspace memory in a relatively unusual manner. (small FAQ below). Long Description: This patch adds two prctl() commands to provide enable or disable the management of bounds tables in kernel, including on-demand kernel allocation (See the patch "on-demand kernel allocation of bounds tables") and cleanup (See the patch "cleanup unused bound tables"). Applications do not strictly need the kernel to manage bounds tables and we expect some applications to use MPX without taking advantage of this kernel support. This means the kernel can not simply infer whether an application needs bounds table management from the MPX registers. The prctl() is an explicit signal from userspace. PR_MPX_ENABLE_MANAGEMENT is meant to be a signal from userspace to require kernel's help in managing bounds tables. PR_MPX_DISABLE_MANAGEMENT is the opposite, meaning that userspace don't want kernel's help any more. With PR_MPX_DISABLE_MANAGEMENT, the kernel won't allocate and free bounds tables even if the CPU supports MPX. PR_MPX_ENABLE_MANAGEMENT will fetch the base address of the bounds directory out of a userspace register (bndcfgu) and then cache it into a new field (->bd_addr) in the 'mm_struct'. PR_MPX_DISABLE_MANAGEMENT will set "bd_addr" to an invalid address. Using this scheme, we can use "bd_addr" to determine whether the management of bounds tables in kernel is enabled. Also, the only way to access that bndcfgu register is via an xsaves, which can be expensive. Caching "bd_addr" like this also helps reduce the cost of those xsaves when doing table cleanup at munmap() time. Unfortunately, we can not apply this optimization to #BR fault time because we need an xsave to get the value of BNDSTATUS. ==== Why does the hardware even have these Bounds Tables? ==== MPX only has 4 hardware registers for storing bounds information. If MPX-enabled code needs more than these 4 registers, it needs to spill them somewhere. It has two special instructions for this which allow the bounds to be moved between the bounds registers and some new "bounds tables". They are similar conceptually to a page fault and will be raised by the MPX hardware during both bounds violations or when the tables are not present. This patch handles those #BR exceptions for not-present tables by carving the space out of the normal processes address space (essentially calling the new mmap() interface indroduced earlier in this patch set.) and then pointing the bounds-directory over to it. The tables *need* to be accessed and controlled by userspace because the instructions for moving bounds in and out of them are extremely frequent. They potentially happen every time a register pointing to memory is dereferenced. Any direct kernel involvement (like a syscall) to access the tables would obviously destroy performance. ==== Why not do this in userspace? ==== This patch is obviously doing this allocation in the kernel. However, MPX does not strictly *require* anything in the kernel. It can theoretically be done completely from userspace. Here are a few ways this *could* be done. I don't think any of them are practical in the real-world, but here they are. Q: Can virtual space simply be reserved for the bounds tables so that we never have to allocate them? A: As noted earlier, these tables are *HUGE*. An X-GB virtual area needs 4*X GB of virtual space, plus 2GB for the bounds directory. If we were to preallocate them for the 128TB of user virtual address space, we would need to reserve 512TB+2GB, which is larger than the entire virtual address space today. This means they can not be reserved ahead of time. Also, a single process's pre-popualated bounds directory consumes 2GB of virtual *AND* physical memory. IOW, it's completely infeasible to prepopulate bounds directories. Q: Can we preallocate bounds table space at the same time memory is allocated which might contain pointers that might eventually need bounds tables? A: This would work if we could hook the site of each and every memory allocation syscall. This can be done for small, constrained applications. But, it isn't practical at a larger scale since a given app has no way of controlling how all the parts of the app might allocate memory (think libraries). The kernel is really the only place to intercept these calls. Q: Could a bounds fault be handed to userspace and the tables allocated there in a signal handler instead of in the kernel? A: (thanks to tglx) mmap() is not on the list of safe async handler functions and even if mmap() would work it still requires locking or nasty tricks to keep track of the allocation state there. Having ruled out all of the userspace-only approaches for managing bounds tables that we could think of, we create them on demand in the kernel. Based-on-patch-by: Qiaowei Ren <qiaowei.ren@intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: linux-mm@kvack.org Cc: linux-mips@linux-mips.org Cc: Dave Hansen <dave@sr71.net> Link: http://lkml.kernel.org/r/20141114151829.AD4310DE@viggo.jf.intel.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2014-11-14 22:18:29 +07:00
/*
* We failed to decode the MPX instruction. Act as if
* the exception was not caused by MPX.
*/
goto exit_trap;
}
/*
* Success, we decoded the instruction and retrieved
* an 'info' containing the address being accessed
* which caused the exception. This information
* allows and application to possibly handle the
* #BR exception itself.
*/
do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, info);
kfree(info);
break;
case 0: /* No exception caused by Intel MPX operations. */
goto exit_trap;
default:
die("bounds", regs, error_code);
}
return;
x86, mpx: On-demand kernel allocation of bounds tables This is really the meat of the MPX patch set. If there is one patch to review in the entire series, this is the one. There is a new ABI here and this kernel code also interacts with userspace memory in a relatively unusual manner. (small FAQ below). Long Description: This patch adds two prctl() commands to provide enable or disable the management of bounds tables in kernel, including on-demand kernel allocation (See the patch "on-demand kernel allocation of bounds tables") and cleanup (See the patch "cleanup unused bound tables"). Applications do not strictly need the kernel to manage bounds tables and we expect some applications to use MPX without taking advantage of this kernel support. This means the kernel can not simply infer whether an application needs bounds table management from the MPX registers. The prctl() is an explicit signal from userspace. PR_MPX_ENABLE_MANAGEMENT is meant to be a signal from userspace to require kernel's help in managing bounds tables. PR_MPX_DISABLE_MANAGEMENT is the opposite, meaning that userspace don't want kernel's help any more. With PR_MPX_DISABLE_MANAGEMENT, the kernel won't allocate and free bounds tables even if the CPU supports MPX. PR_MPX_ENABLE_MANAGEMENT will fetch the base address of the bounds directory out of a userspace register (bndcfgu) and then cache it into a new field (->bd_addr) in the 'mm_struct'. PR_MPX_DISABLE_MANAGEMENT will set "bd_addr" to an invalid address. Using this scheme, we can use "bd_addr" to determine whether the management of bounds tables in kernel is enabled. Also, the only way to access that bndcfgu register is via an xsaves, which can be expensive. Caching "bd_addr" like this also helps reduce the cost of those xsaves when doing table cleanup at munmap() time. Unfortunately, we can not apply this optimization to #BR fault time because we need an xsave to get the value of BNDSTATUS. ==== Why does the hardware even have these Bounds Tables? ==== MPX only has 4 hardware registers for storing bounds information. If MPX-enabled code needs more than these 4 registers, it needs to spill them somewhere. It has two special instructions for this which allow the bounds to be moved between the bounds registers and some new "bounds tables". They are similar conceptually to a page fault and will be raised by the MPX hardware during both bounds violations or when the tables are not present. This patch handles those #BR exceptions for not-present tables by carving the space out of the normal processes address space (essentially calling the new mmap() interface indroduced earlier in this patch set.) and then pointing the bounds-directory over to it. The tables *need* to be accessed and controlled by userspace because the instructions for moving bounds in and out of them are extremely frequent. They potentially happen every time a register pointing to memory is dereferenced. Any direct kernel involvement (like a syscall) to access the tables would obviously destroy performance. ==== Why not do this in userspace? ==== This patch is obviously doing this allocation in the kernel. However, MPX does not strictly *require* anything in the kernel. It can theoretically be done completely from userspace. Here are a few ways this *could* be done. I don't think any of them are practical in the real-world, but here they are. Q: Can virtual space simply be reserved for the bounds tables so that we never have to allocate them? A: As noted earlier, these tables are *HUGE*. An X-GB virtual area needs 4*X GB of virtual space, plus 2GB for the bounds directory. If we were to preallocate them for the 128TB of user virtual address space, we would need to reserve 512TB+2GB, which is larger than the entire virtual address space today. This means they can not be reserved ahead of time. Also, a single process's pre-popualated bounds directory consumes 2GB of virtual *AND* physical memory. IOW, it's completely infeasible to prepopulate bounds directories. Q: Can we preallocate bounds table space at the same time memory is allocated which might contain pointers that might eventually need bounds tables? A: This would work if we could hook the site of each and every memory allocation syscall. This can be done for small, constrained applications. But, it isn't practical at a larger scale since a given app has no way of controlling how all the parts of the app might allocate memory (think libraries). The kernel is really the only place to intercept these calls. Q: Could a bounds fault be handed to userspace and the tables allocated there in a signal handler instead of in the kernel? A: (thanks to tglx) mmap() is not on the list of safe async handler functions and even if mmap() would work it still requires locking or nasty tricks to keep track of the allocation state there. Having ruled out all of the userspace-only approaches for managing bounds tables that we could think of, we create them on demand in the kernel. Based-on-patch-by: Qiaowei Ren <qiaowei.ren@intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: linux-mm@kvack.org Cc: linux-mips@linux-mips.org Cc: Dave Hansen <dave@sr71.net> Link: http://lkml.kernel.org/r/20141114151829.AD4310DE@viggo.jf.intel.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2014-11-14 22:18:29 +07:00
exit_trap:
/*
* This path out is for all the cases where we could not
* handle the exception in some way (like allocating a
* table or telling userspace about it. We will also end
* up here if the kernel has MPX turned off at compile
* time..
*/
do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, NULL);
}
kprobes, x86: Use NOKPROBE_SYMBOL() instead of __kprobes annotation Use NOKPROBE_SYMBOL macro for protecting functions from kprobes instead of __kprobes annotation under arch/x86. This applies nokprobe_inline annotation for some cases, because NOKPROBE_SYMBOL() will inhibit inlining by referring the symbol address. This just folds a bunch of previous NOKPROBE_SYMBOL() cleanup patches for x86 to one patch. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Link: http://lkml.kernel.org/r/20140417081814.26341.51656.stgit@ltc230.yrl.intra.hitachi.co.jp Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Fernando Luis Vázquez Cao <fernando_b1@lab.ntt.co.jp> Cc: Gleb Natapov <gleb@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Lebon <jlebon@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Matt Fleming <matt.fleming@intel.com> Cc: Michel Lespinasse <walken@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Seiji Aguchi <seiji.aguchi@hds.com> Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vineet Gupta <vgupta@synopsys.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-04-17 15:18:14 +07:00
dotraplinkage void
do_general_protection(struct pt_regs *regs, long error_code)
{
struct task_struct *tsk;
Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull x86 asm changes from Ingo Molnar: "The biggest changes in this cycle were: - Revamp, simplify (and in some cases fix) Time Stamp Counter (TSC) primitives. (Andy Lutomirski) - Add new, comprehensible entry and exit handlers written in C. (Andy Lutomirski) - vm86 mode cleanups and fixes. (Brian Gerst) - 32-bit compat code cleanups. (Brian Gerst) The amount of simplification in low level assembly code is already palpable: arch/x86/entry/entry_32.S | 130 +---- arch/x86/entry/entry_64.S | 197 ++----- but more simplifications are planned. There's also the usual laudry mix of low level changes - see the changelog for details" * 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (83 commits) x86/asm: Drop repeated macro of X86_EFLAGS_AC definition x86/asm/msr: Make wrmsrl() a function x86/asm/delay: Introduce an MWAITX-based delay with a configurable timer x86/asm: Add MONITORX/MWAITX instruction support x86/traps: Weaken context tracking entry assertions x86/asm/tsc: Add rdtscll() merge helper selftests/x86: Add syscall_nt selftest selftests/x86: Disable sigreturn_64 x86/vdso: Emit a GNU hash x86/entry: Remove do_notify_resume(), syscall_trace_leave(), and their TIF masks x86/entry/32: Migrate to C exit path x86/entry/32: Remove 32-bit syscall audit optimizations x86/vm86: Rename vm86->v86flags and v86mask x86/vm86: Rename vm86->vm86_info to user_vm86 x86/vm86: Clean up vm86.h includes x86/vm86: Move the vm86 IRQ definitions to vm86.h x86/vm86: Use the normal pt_regs area for vm86 x86/vm86: Eliminate 'struct kernel_vm86_struct' x86/vm86: Move fields from 'struct kernel_vm86_struct' to 'struct vm86' x86/vm86: Move vm86 fields out of 'thread_struct' ...
2015-09-01 22:40:25 +07:00
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
cond_local_irq_enable(regs);
if (v8086_mode(regs)) {
local_irq_enable();
handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
return;
}
tsk = current;
if (!user_mode(regs)) {
if (fixup_exception(regs, X86_TRAP_GP))
return;
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = X86_TRAP_GP;
if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP)
die("general protection fault", regs, error_code);
return;
}
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = X86_TRAP_GP;
if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
printk_ratelimit()) {
pr_info("%s[%d] general protection ip:%lx sp:%lx error:%lx",
tsk->comm, task_pid_nr(tsk),
regs->ip, regs->sp, error_code);
print_vma_addr(" in ", regs->ip);
pr_cont("\n");
}
force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
}
kprobes, x86: Use NOKPROBE_SYMBOL() instead of __kprobes annotation Use NOKPROBE_SYMBOL macro for protecting functions from kprobes instead of __kprobes annotation under arch/x86. This applies nokprobe_inline annotation for some cases, because NOKPROBE_SYMBOL() will inhibit inlining by referring the symbol address. This just folds a bunch of previous NOKPROBE_SYMBOL() cleanup patches for x86 to one patch. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Link: http://lkml.kernel.org/r/20140417081814.26341.51656.stgit@ltc230.yrl.intra.hitachi.co.jp Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Fernando Luis Vázquez Cao <fernando_b1@lab.ntt.co.jp> Cc: Gleb Natapov <gleb@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Lebon <jlebon@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Matt Fleming <matt.fleming@intel.com> Cc: Michel Lespinasse <walken@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Seiji Aguchi <seiji.aguchi@hds.com> Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vineet Gupta <vgupta@synopsys.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-04-17 15:18:14 +07:00
NOKPROBE_SYMBOL(do_general_protection);
/* May run on IST stack. */
kprobes, x86: Use NOKPROBE_SYMBOL() instead of __kprobes annotation Use NOKPROBE_SYMBOL macro for protecting functions from kprobes instead of __kprobes annotation under arch/x86. This applies nokprobe_inline annotation for some cases, because NOKPROBE_SYMBOL() will inhibit inlining by referring the symbol address. This just folds a bunch of previous NOKPROBE_SYMBOL() cleanup patches for x86 to one patch. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Link: http://lkml.kernel.org/r/20140417081814.26341.51656.stgit@ltc230.yrl.intra.hitachi.co.jp Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Fernando Luis Vázquez Cao <fernando_b1@lab.ntt.co.jp> Cc: Gleb Natapov <gleb@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Lebon <jlebon@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Matt Fleming <matt.fleming@intel.com> Cc: Michel Lespinasse <walken@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Seiji Aguchi <seiji.aguchi@hds.com> Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vineet Gupta <vgupta@synopsys.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-04-17 15:18:14 +07:00
dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
{
#ifdef CONFIG_DYNAMIC_FTRACE
/*
* ftrace must be first, everything else may cause a recursive crash.
* See note by declaration of modifying_ftrace_code in ftrace.c
*/
if (unlikely(atomic_read(&modifying_ftrace_code)) &&
ftrace_int3_handler(regs))
return;
#endif
kprobes/x86: Call out into INT3 handler directly instead of using notifier In fd4363fff3d96 ("x86: Introduce int3 (breakpoint)-based instruction patching"), the mechanism that was introduced for notifying alternatives code from int3 exception handler that and exception occured was die_notifier. This is however problematic, as early code might be using jump labels even before the notifier registration has been performed, which will then lead to an oops due to unhandled exception. One of such occurences has been encountered by Fengguang: int3: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.11.0-rc1-01429-g04bf576 #8 task: ffff88000da1b040 ti: ffff88000da1c000 task.ti: ffff88000da1c000 RIP: 0010:[<ffffffff811098cc>] [<ffffffff811098cc>] ttwu_do_wakeup+0x28/0x225 RSP: 0000:ffff88000dd03f10 EFLAGS: 00000006 RAX: 0000000000000000 RBX: ffff88000dd12940 RCX: ffffffff81769c40 RDX: 0000000000000002 RSI: 0000000000000000 RDI: 0000000000000001 RBP: ffff88000dd03f28 R08: ffffffff8176a8c0 R09: 0000000000000002 R10: ffffffff810ff484 R11: ffff88000dd129e8 R12: ffff88000dbc90c0 R13: ffff88000dbc90c0 R14: ffff88000da1dfd8 R15: ffff88000da1dfd8 FS: 0000000000000000(0000) GS:ffff88000dd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00000000ffffffff CR3: 0000000001c88000 CR4: 00000000000006e0 Stack: ffff88000dd12940 ffff88000dbc90c0 ffff88000da1dfd8 ffff88000dd03f48 ffffffff81109e2b ffff88000dd12940 0000000000000000 ffff88000dd03f68 ffffffff81109e9e 0000000000000000 0000000000012940 ffff88000dd03f98 Call Trace: <IRQ> [<ffffffff81109e2b>] ttwu_do_activate.constprop.56+0x6d/0x79 [<ffffffff81109e9e>] sched_ttwu_pending+0x67/0x84 [<ffffffff8110c845>] scheduler_ipi+0x15a/0x2b0 [<ffffffff8104dfb4>] smp_reschedule_interrupt+0x38/0x41 [<ffffffff8173bf5d>] reschedule_interrupt+0x6d/0x80 <EOI> [<ffffffff810ff484>] ? __atomic_notifier_call_chain+0x5/0xc1 [<ffffffff8105cc30>] ? native_safe_halt+0xd/0x16 [<ffffffff81015f10>] default_idle+0x147/0x282 [<ffffffff81017026>] arch_cpu_idle+0x3d/0x5d [<ffffffff81127d6a>] cpu_idle_loop+0x46d/0x5db [<ffffffff81127f5c>] cpu_startup_entry+0x84/0x84 [<ffffffff8104f4f8>] start_secondary+0x3c8/0x3d5 [...] Fix this by directly calling poke_int3_handler() from the int3 exception handler (analogically to what ftrace has been doing already), instead of relying on notifier, registration of which might not have yet been finalized by the time of the first trap. Reported-and-tested-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Jiri Kosina <jkosina@suse.cz> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: H. Peter Anvin <hpa@linux.intel.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/alpine.LNX.2.00.1307231007490.14024@pobox.suse.cz Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-23 15:09:28 +07:00
if (poke_int3_handler(regs))
return;
ist_enter(regs);
Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull x86 asm changes from Ingo Molnar: "The biggest changes in this cycle were: - Revamp, simplify (and in some cases fix) Time Stamp Counter (TSC) primitives. (Andy Lutomirski) - Add new, comprehensible entry and exit handlers written in C. (Andy Lutomirski) - vm86 mode cleanups and fixes. (Brian Gerst) - 32-bit compat code cleanups. (Brian Gerst) The amount of simplification in low level assembly code is already palpable: arch/x86/entry/entry_32.S | 130 +---- arch/x86/entry/entry_64.S | 197 ++----- but more simplifications are planned. There's also the usual laudry mix of low level changes - see the changelog for details" * 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (83 commits) x86/asm: Drop repeated macro of X86_EFLAGS_AC definition x86/asm/msr: Make wrmsrl() a function x86/asm/delay: Introduce an MWAITX-based delay with a configurable timer x86/asm: Add MONITORX/MWAITX instruction support x86/traps: Weaken context tracking entry assertions x86/asm/tsc: Add rdtscll() merge helper selftests/x86: Add syscall_nt selftest selftests/x86: Disable sigreturn_64 x86/vdso: Emit a GNU hash x86/entry: Remove do_notify_resume(), syscall_trace_leave(), and their TIF masks x86/entry/32: Migrate to C exit path x86/entry/32: Remove 32-bit syscall audit optimizations x86/vm86: Rename vm86->v86flags and v86mask x86/vm86: Rename vm86->vm86_info to user_vm86 x86/vm86: Clean up vm86.h includes x86/vm86: Move the vm86 IRQ definitions to vm86.h x86/vm86: Use the normal pt_regs area for vm86 x86/vm86: Eliminate 'struct kernel_vm86_struct' x86/vm86: Move fields from 'struct kernel_vm86_struct' to 'struct vm86' x86/vm86: Move vm86 fields out of 'thread_struct' ...
2015-09-01 22:40:25 +07:00
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
SIGTRAP) == NOTIFY_STOP)
goto exit;
#endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */
#ifdef CONFIG_KPROBES
if (kprobe_int3_handler(regs))
goto exit;
#endif
if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
SIGTRAP) == NOTIFY_STOP)
goto exit;
x86: Add counter when debug stack is used with interrupts enabled Mathieu Desnoyers pointed out a case that can cause issues with NMIs running on the debug stack: int3 -> interrupt -> NMI -> int3 Because the interrupt changes the stack, the NMI will not see that it preempted the debug stack. Looking deeper at this case, interrupts only happen when the int3 is from userspace or in an a location in the exception table (fixup). userspace -> int3 -> interurpt -> NMI -> int3 All other int3s that happen in the kernel should be processed without ever enabling interrupts, as the do_trap() call will panic the kernel if it is called to process any other location within the kernel. Adding a counter around the sections that enable interrupts while using the debug stack allows the NMI to also check that case. If the NMI sees that it either interrupted a task using the debug stack or the debug counter is non-zero, then it will have to change the IDT table to make the int3 not change stacks (which will corrupt the stack if it does). Note, I had to move the debug_usage functions out of processor.h and into debugreg.h because of the static inlined functions to inc and dec the debug_usage counter. __get_cpu_var() requires smp.h which includes processor.h, and would fail to build. Link: http://lkml.kernel.org/r/1323976535.23971.112.camel@gandalf.stny.rr.com Reported-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: H. Peter Anvin <hpa@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Paul Turner <pjt@google.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-12-16 23:43:02 +07:00
/*
* Let others (NMI) know that the debug stack is in use
* as we may switch to the interrupt stack.
*/
debug_stack_usage_inc();
preempt_disable();
cond_local_irq_enable(regs);
do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
cond_local_irq_disable(regs);
preempt_enable_no_resched();
x86: Add counter when debug stack is used with interrupts enabled Mathieu Desnoyers pointed out a case that can cause issues with NMIs running on the debug stack: int3 -> interrupt -> NMI -> int3 Because the interrupt changes the stack, the NMI will not see that it preempted the debug stack. Looking deeper at this case, interrupts only happen when the int3 is from userspace or in an a location in the exception table (fixup). userspace -> int3 -> interurpt -> NMI -> int3 All other int3s that happen in the kernel should be processed without ever enabling interrupts, as the do_trap() call will panic the kernel if it is called to process any other location within the kernel. Adding a counter around the sections that enable interrupts while using the debug stack allows the NMI to also check that case. If the NMI sees that it either interrupted a task using the debug stack or the debug counter is non-zero, then it will have to change the IDT table to make the int3 not change stacks (which will corrupt the stack if it does). Note, I had to move the debug_usage functions out of processor.h and into debugreg.h because of the static inlined functions to inc and dec the debug_usage counter. __get_cpu_var() requires smp.h which includes processor.h, and would fail to build. Link: http://lkml.kernel.org/r/1323976535.23971.112.camel@gandalf.stny.rr.com Reported-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: H. Peter Anvin <hpa@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Paul Turner <pjt@google.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-12-16 23:43:02 +07:00
debug_stack_usage_dec();
exit:
ist_exit(regs);
}
kprobes, x86: Use NOKPROBE_SYMBOL() instead of __kprobes annotation Use NOKPROBE_SYMBOL macro for protecting functions from kprobes instead of __kprobes annotation under arch/x86. This applies nokprobe_inline annotation for some cases, because NOKPROBE_SYMBOL() will inhibit inlining by referring the symbol address. This just folds a bunch of previous NOKPROBE_SYMBOL() cleanup patches for x86 to one patch. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Link: http://lkml.kernel.org/r/20140417081814.26341.51656.stgit@ltc230.yrl.intra.hitachi.co.jp Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Fernando Luis Vázquez Cao <fernando_b1@lab.ntt.co.jp> Cc: Gleb Natapov <gleb@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Lebon <jlebon@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Matt Fleming <matt.fleming@intel.com> Cc: Michel Lespinasse <walken@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Seiji Aguchi <seiji.aguchi@hds.com> Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vineet Gupta <vgupta@synopsys.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-04-17 15:18:14 +07:00
NOKPROBE_SYMBOL(do_int3);
#ifdef CONFIG_X86_64
/*
* Help handler running on IST stack to switch off the IST stack if the
* interrupted code was in user mode. The actual stack switch is done in
* entry_64.S
*/
asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs)
{
struct pt_regs *regs = task_pt_regs(current);
*regs = *eregs;
return regs;
}
kprobes, x86: Use NOKPROBE_SYMBOL() instead of __kprobes annotation Use NOKPROBE_SYMBOL macro for protecting functions from kprobes instead of __kprobes annotation under arch/x86. This applies nokprobe_inline annotation for some cases, because NOKPROBE_SYMBOL() will inhibit inlining by referring the symbol address. This just folds a bunch of previous NOKPROBE_SYMBOL() cleanup patches for x86 to one patch. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Link: http://lkml.kernel.org/r/20140417081814.26341.51656.stgit@ltc230.yrl.intra.hitachi.co.jp Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Fernando Luis Vázquez Cao <fernando_b1@lab.ntt.co.jp> Cc: Gleb Natapov <gleb@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Lebon <jlebon@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Matt Fleming <matt.fleming@intel.com> Cc: Michel Lespinasse <walken@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Seiji Aguchi <seiji.aguchi@hds.com> Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vineet Gupta <vgupta@synopsys.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-04-17 15:18:14 +07:00
NOKPROBE_SYMBOL(sync_regs);
struct bad_iret_stack {
void *error_entry_ret;
struct pt_regs regs;
};
asmlinkage __visible notrace
struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
{
/*
* This is called from entry_64.S early in handling a fault
* caused by a bad iret to user mode. To handle the fault
* correctly, we want move our stack frame to task_pt_regs
* and we want to pretend that the exception came from the
* iret target.
*/
struct bad_iret_stack *new_stack =
container_of(task_pt_regs(current),
struct bad_iret_stack, regs);
/* Copy the IRET target to the new stack. */
memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8);
/* Copy the remainder of the stack from the current stack. */
memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip));
BUG_ON(!user_mode(&new_stack->regs));
return new_stack;
}
NOKPROBE_SYMBOL(fixup_bad_iret);
#endif
x86/entry: Vastly simplify SYSENTER TF (single-step) handling Due to a blatant design error, SYSENTER doesn't clear TF (single-step). As a result, if a user does SYSENTER with TF set, we will single-step through the kernel until something clears TF. There is absolutely nothing we can do to prevent this short of turning off SYSENTER [1]. Simplify the handling considerably with two changes: 1. We already sanitize EFLAGS in SYSENTER to clear NT and AC. We can add TF to that list of flags to sanitize with no overhead whatsoever. 2. Teach do_debug() to ignore single-step traps in the SYSENTER prologue. That's all we need to do. Don't get too excited -- our handling is still buggy on 32-bit kernels. There's nothing wrong with the SYSENTER code itself, but the #DB prologue has a clever fixup for traps on the very first instruction of entry_SYSENTER_32, and the fixup doesn't work quite correctly. The next two patches will fix that. [1] We could probably prevent it by forcing BTF on at all times and making sure we clear TF before any branches in the SYSENTER code. Needless to say, this is a bad idea. Signed-off-by: Andy Lutomirski <luto@kernel.org> Cc: Andrew Cooper <andrew.cooper3@citrix.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/a30d2ea06fe4b621fe6a9ef911b02c0f38feb6f2.1457578375.git.luto@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-03-10 10:00:30 +07:00
static bool is_sysenter_singlestep(struct pt_regs *regs)
{
/*
* We don't try for precision here. If we're anywhere in the region of
* code that can be single-stepped in the SYSENTER entry path, then
* assume that this is a useless single-step trap due to SYSENTER
* being invoked with TF set. (We don't know in advance exactly
* which instructions will be hit because BTF could plausibly
* be set.)
*/
#ifdef CONFIG_X86_32
return (regs->ip - (unsigned long)__begin_SYSENTER_singlestep_region) <
(unsigned long)__end_SYSENTER_singlestep_region -
(unsigned long)__begin_SYSENTER_singlestep_region;
#elif defined(CONFIG_IA32_EMULATION)
return (regs->ip - (unsigned long)entry_SYSENTER_compat) <
(unsigned long)__end_entry_SYSENTER_compat -
(unsigned long)entry_SYSENTER_compat;
#else
return false;
#endif
}
/*
* Our handling of the processor debug registers is non-trivial.
* We do not clear them on entry and exit from the kernel. Therefore
* it is possible to get a watchpoint trap here from inside the kernel.
* However, the code in ./ptrace.c has ensured that the user can
* only set watchpoints on userspace addresses. Therefore the in-kernel
* watchpoint trap can only occur in code which is reading/writing
* from user space. Such code must not hold kernel locks (since it
* can equally take a page fault), therefore it is safe to call
* force_sig_info even though that claims and releases locks.
*
* Code in ./signal.c ensures that the debug control register
* is restored before we deliver any signal, and therefore that
* user code runs with the correct debug control register even though
* we clear it here.
*
* Being careful here means that we don't have to be as careful in a
* lot of more complicated places (task switching can be a bit lazy
* about restoring all the debug state, and ptrace doesn't have to
* find every occurrence of the TF bit that could be saved away even
* by user code)
*
* May run on IST stack.
*/
kprobes, x86: Use NOKPROBE_SYMBOL() instead of __kprobes annotation Use NOKPROBE_SYMBOL macro for protecting functions from kprobes instead of __kprobes annotation under arch/x86. This applies nokprobe_inline annotation for some cases, because NOKPROBE_SYMBOL() will inhibit inlining by referring the symbol address. This just folds a bunch of previous NOKPROBE_SYMBOL() cleanup patches for x86 to one patch. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Link: http://lkml.kernel.org/r/20140417081814.26341.51656.stgit@ltc230.yrl.intra.hitachi.co.jp Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Fernando Luis Vázquez Cao <fernando_b1@lab.ntt.co.jp> Cc: Gleb Natapov <gleb@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Lebon <jlebon@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Matt Fleming <matt.fleming@intel.com> Cc: Michel Lespinasse <walken@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Seiji Aguchi <seiji.aguchi@hds.com> Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vineet Gupta <vgupta@synopsys.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-04-17 15:18:14 +07:00
dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
{
struct task_struct *tsk = current;
int user_icebp = 0;
unsigned long dr6;
int si_code;
ist_enter(regs);
get_debugreg(dr6, 6);
/*
* The Intel SDM says:
*
* Certain debug exceptions may clear bits 0-3. The remaining
* contents of the DR6 register are never cleared by the
* processor. To avoid confusion in identifying debug
* exceptions, debug handlers should clear the register before
* returning to the interrupted task.
*
* Keep it simple: clear DR6 immediately.
*/
set_debugreg(0, 6);
/* Filter out all the reserved bits which are preset to 1 */
dr6 &= ~DR6_RESERVED;
/*
* The SDM says "The processor clears the BTF flag when it
* generates a debug exception." Clear TIF_BLOCKSTEP to keep
* TIF_BLOCKSTEP in sync with the hardware BTF flag.
*/
clear_tsk_thread_flag(tsk, TIF_BLOCKSTEP);
x86/entry: Vastly simplify SYSENTER TF (single-step) handling Due to a blatant design error, SYSENTER doesn't clear TF (single-step). As a result, if a user does SYSENTER with TF set, we will single-step through the kernel until something clears TF. There is absolutely nothing we can do to prevent this short of turning off SYSENTER [1]. Simplify the handling considerably with two changes: 1. We already sanitize EFLAGS in SYSENTER to clear NT and AC. We can add TF to that list of flags to sanitize with no overhead whatsoever. 2. Teach do_debug() to ignore single-step traps in the SYSENTER prologue. That's all we need to do. Don't get too excited -- our handling is still buggy on 32-bit kernels. There's nothing wrong with the SYSENTER code itself, but the #DB prologue has a clever fixup for traps on the very first instruction of entry_SYSENTER_32, and the fixup doesn't work quite correctly. The next two patches will fix that. [1] We could probably prevent it by forcing BTF on at all times and making sure we clear TF before any branches in the SYSENTER code. Needless to say, this is a bad idea. Signed-off-by: Andy Lutomirski <luto@kernel.org> Cc: Andrew Cooper <andrew.cooper3@citrix.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/a30d2ea06fe4b621fe6a9ef911b02c0f38feb6f2.1457578375.git.luto@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-03-10 10:00:30 +07:00
if (unlikely(!user_mode(regs) && (dr6 & DR_STEP) &&
is_sysenter_singlestep(regs))) {
dr6 &= ~DR_STEP;
if (!dr6)
goto exit;
/*
* else we might have gotten a single-step trap and hit a
* watchpoint at the same time, in which case we should fall
* through and handle the watchpoint.
*/
}
/*
* If dr6 has no reason to give us about the origin of this trap,
* then it's very likely the result of an icebp/int01 trap.
* User wants a sigtrap for that.
*/
if (!dr6 && user_mode(regs))
user_icebp = 1;
x86/entry: Vastly simplify SYSENTER TF (single-step) handling Due to a blatant design error, SYSENTER doesn't clear TF (single-step). As a result, if a user does SYSENTER with TF set, we will single-step through the kernel until something clears TF. There is absolutely nothing we can do to prevent this short of turning off SYSENTER [1]. Simplify the handling considerably with two changes: 1. We already sanitize EFLAGS in SYSENTER to clear NT and AC. We can add TF to that list of flags to sanitize with no overhead whatsoever. 2. Teach do_debug() to ignore single-step traps in the SYSENTER prologue. That's all we need to do. Don't get too excited -- our handling is still buggy on 32-bit kernels. There's nothing wrong with the SYSENTER code itself, but the #DB prologue has a clever fixup for traps on the very first instruction of entry_SYSENTER_32, and the fixup doesn't work quite correctly. The next two patches will fix that. [1] We could probably prevent it by forcing BTF on at all times and making sure we clear TF before any branches in the SYSENTER code. Needless to say, this is a bad idea. Signed-off-by: Andy Lutomirski <luto@kernel.org> Cc: Andrew Cooper <andrew.cooper3@citrix.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/a30d2ea06fe4b621fe6a9ef911b02c0f38feb6f2.1457578375.git.luto@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-03-10 10:00:30 +07:00
/* Catch kmemcheck conditions! */
if ((dr6 & DR_STEP) && kmemcheck_trap(regs))
goto exit;
/* Store the virtualized DR6 value */
tsk->thread.debugreg6 = dr6;
#ifdef CONFIG_KPROBES
if (kprobe_debug_handler(regs))
goto exit;
#endif
if (notify_die(DIE_DEBUG, "debug", regs, (long)&dr6, error_code,
SIGTRAP) == NOTIFY_STOP)
goto exit;
x86: Add counter when debug stack is used with interrupts enabled Mathieu Desnoyers pointed out a case that can cause issues with NMIs running on the debug stack: int3 -> interrupt -> NMI -> int3 Because the interrupt changes the stack, the NMI will not see that it preempted the debug stack. Looking deeper at this case, interrupts only happen when the int3 is from userspace or in an a location in the exception table (fixup). userspace -> int3 -> interurpt -> NMI -> int3 All other int3s that happen in the kernel should be processed without ever enabling interrupts, as the do_trap() call will panic the kernel if it is called to process any other location within the kernel. Adding a counter around the sections that enable interrupts while using the debug stack allows the NMI to also check that case. If the NMI sees that it either interrupted a task using the debug stack or the debug counter is non-zero, then it will have to change the IDT table to make the int3 not change stacks (which will corrupt the stack if it does). Note, I had to move the debug_usage functions out of processor.h and into debugreg.h because of the static inlined functions to inc and dec the debug_usage counter. __get_cpu_var() requires smp.h which includes processor.h, and would fail to build. Link: http://lkml.kernel.org/r/1323976535.23971.112.camel@gandalf.stny.rr.com Reported-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: H. Peter Anvin <hpa@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Paul Turner <pjt@google.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-12-16 23:43:02 +07:00
/*
* Let others (NMI) know that the debug stack is in use
* as we may switch to the interrupt stack.
*/
debug_stack_usage_inc();
/* It's safe to allow irq's after DR6 has been saved */
preempt_disable();
cond_local_irq_enable(regs);
if (v8086_mode(regs)) {
handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code,
X86_TRAP_DB);
cond_local_irq_disable(regs);
preempt_enable_no_resched();
x86: Add counter when debug stack is used with interrupts enabled Mathieu Desnoyers pointed out a case that can cause issues with NMIs running on the debug stack: int3 -> interrupt -> NMI -> int3 Because the interrupt changes the stack, the NMI will not see that it preempted the debug stack. Looking deeper at this case, interrupts only happen when the int3 is from userspace or in an a location in the exception table (fixup). userspace -> int3 -> interurpt -> NMI -> int3 All other int3s that happen in the kernel should be processed without ever enabling interrupts, as the do_trap() call will panic the kernel if it is called to process any other location within the kernel. Adding a counter around the sections that enable interrupts while using the debug stack allows the NMI to also check that case. If the NMI sees that it either interrupted a task using the debug stack or the debug counter is non-zero, then it will have to change the IDT table to make the int3 not change stacks (which will corrupt the stack if it does). Note, I had to move the debug_usage functions out of processor.h and into debugreg.h because of the static inlined functions to inc and dec the debug_usage counter. __get_cpu_var() requires smp.h which includes processor.h, and would fail to build. Link: http://lkml.kernel.org/r/1323976535.23971.112.camel@gandalf.stny.rr.com Reported-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: H. Peter Anvin <hpa@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Paul Turner <pjt@google.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-12-16 23:43:02 +07:00
debug_stack_usage_dec();
goto exit;
}
x86/entry: Vastly simplify SYSENTER TF (single-step) handling Due to a blatant design error, SYSENTER doesn't clear TF (single-step). As a result, if a user does SYSENTER with TF set, we will single-step through the kernel until something clears TF. There is absolutely nothing we can do to prevent this short of turning off SYSENTER [1]. Simplify the handling considerably with two changes: 1. We already sanitize EFLAGS in SYSENTER to clear NT and AC. We can add TF to that list of flags to sanitize with no overhead whatsoever. 2. Teach do_debug() to ignore single-step traps in the SYSENTER prologue. That's all we need to do. Don't get too excited -- our handling is still buggy on 32-bit kernels. There's nothing wrong with the SYSENTER code itself, but the #DB prologue has a clever fixup for traps on the very first instruction of entry_SYSENTER_32, and the fixup doesn't work quite correctly. The next two patches will fix that. [1] We could probably prevent it by forcing BTF on at all times and making sure we clear TF before any branches in the SYSENTER code. Needless to say, this is a bad idea. Signed-off-by: Andy Lutomirski <luto@kernel.org> Cc: Andrew Cooper <andrew.cooper3@citrix.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/a30d2ea06fe4b621fe6a9ef911b02c0f38feb6f2.1457578375.git.luto@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-03-10 10:00:30 +07:00
if (WARN_ON_ONCE((dr6 & DR_STEP) && !user_mode(regs))) {
/*
* Historical junk that used to handle SYSENTER single-stepping.
* This should be unreachable now. If we survive for a while
* without anyone hitting this warning, we'll turn this into
* an oops.
*/
tsk->thread.debugreg6 &= ~DR_STEP;
set_tsk_thread_flag(tsk, TIF_SINGLESTEP);
regs->flags &= ~X86_EFLAGS_TF;
}
si_code = get_si_code(tsk->thread.debugreg6);
if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp)
send_sigtrap(tsk, regs, error_code, si_code);
cond_local_irq_disable(regs);
preempt_enable_no_resched();
x86: Add counter when debug stack is used with interrupts enabled Mathieu Desnoyers pointed out a case that can cause issues with NMIs running on the debug stack: int3 -> interrupt -> NMI -> int3 Because the interrupt changes the stack, the NMI will not see that it preempted the debug stack. Looking deeper at this case, interrupts only happen when the int3 is from userspace or in an a location in the exception table (fixup). userspace -> int3 -> interurpt -> NMI -> int3 All other int3s that happen in the kernel should be processed without ever enabling interrupts, as the do_trap() call will panic the kernel if it is called to process any other location within the kernel. Adding a counter around the sections that enable interrupts while using the debug stack allows the NMI to also check that case. If the NMI sees that it either interrupted a task using the debug stack or the debug counter is non-zero, then it will have to change the IDT table to make the int3 not change stacks (which will corrupt the stack if it does). Note, I had to move the debug_usage functions out of processor.h and into debugreg.h because of the static inlined functions to inc and dec the debug_usage counter. __get_cpu_var() requires smp.h which includes processor.h, and would fail to build. Link: http://lkml.kernel.org/r/1323976535.23971.112.camel@gandalf.stny.rr.com Reported-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: H. Peter Anvin <hpa@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Paul Turner <pjt@google.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-12-16 23:43:02 +07:00
debug_stack_usage_dec();
exit:
#if defined(CONFIG_X86_32)
/*
* This is the most likely code path that involves non-trivial use
* of the SYSENTER stack. Check that we haven't overrun it.
*/
WARN(this_cpu_read(cpu_tss.SYSENTER_stack_canary) != STACK_END_MAGIC,
"Overran or corrupted SYSENTER stack\n");
#endif
ist_exit(regs);
}
kprobes, x86: Use NOKPROBE_SYMBOL() instead of __kprobes annotation Use NOKPROBE_SYMBOL macro for protecting functions from kprobes instead of __kprobes annotation under arch/x86. This applies nokprobe_inline annotation for some cases, because NOKPROBE_SYMBOL() will inhibit inlining by referring the symbol address. This just folds a bunch of previous NOKPROBE_SYMBOL() cleanup patches for x86 to one patch. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Link: http://lkml.kernel.org/r/20140417081814.26341.51656.stgit@ltc230.yrl.intra.hitachi.co.jp Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Fernando Luis Vázquez Cao <fernando_b1@lab.ntt.co.jp> Cc: Gleb Natapov <gleb@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Lebon <jlebon@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Matt Fleming <matt.fleming@intel.com> Cc: Michel Lespinasse <walken@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Seiji Aguchi <seiji.aguchi@hds.com> Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vineet Gupta <vgupta@synopsys.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-04-17 15:18:14 +07:00
NOKPROBE_SYMBOL(do_debug);
/*
* Note that we play around with the 'TS' bit in an attempt to get
* the correct behaviour even in the presence of the asynchronous
* IRQ13 behaviour
*/
static void math_error(struct pt_regs *regs, int error_code, int trapnr)
{
struct task_struct *task = current;
struct fpu *fpu = &task->thread.fpu;
siginfo_t info;
char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
"simd exception";
if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) == NOTIFY_STOP)
return;
cond_local_irq_enable(regs);
if (!user_mode(regs)) {
if (!fixup_exception(regs, trapnr)) {
task->thread.error_code = error_code;
task->thread.trap_nr = trapnr;
die(str, regs, error_code);
}
return;
}
/*
* Save the info for the exception handler and clear the error.
*/
fpu__save(fpu);
task->thread.trap_nr = trapnr;
task->thread.error_code = error_code;
info.si_signo = SIGFPE;
info.si_errno = 0;
info.si_addr = (void __user *)uprobe_get_trap_addr(regs);
info.si_code = fpu__exception_code(fpu, trapnr);
/* Retry when we get spurious exceptions: */
if (!info.si_code)
return;
force_sig_info(SIGFPE, &info, task);
}
dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
{
Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull x86 asm changes from Ingo Molnar: "The biggest changes in this cycle were: - Revamp, simplify (and in some cases fix) Time Stamp Counter (TSC) primitives. (Andy Lutomirski) - Add new, comprehensible entry and exit handlers written in C. (Andy Lutomirski) - vm86 mode cleanups and fixes. (Brian Gerst) - 32-bit compat code cleanups. (Brian Gerst) The amount of simplification in low level assembly code is already palpable: arch/x86/entry/entry_32.S | 130 +---- arch/x86/entry/entry_64.S | 197 ++----- but more simplifications are planned. There's also the usual laudry mix of low level changes - see the changelog for details" * 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (83 commits) x86/asm: Drop repeated macro of X86_EFLAGS_AC definition x86/asm/msr: Make wrmsrl() a function x86/asm/delay: Introduce an MWAITX-based delay with a configurable timer x86/asm: Add MONITORX/MWAITX instruction support x86/traps: Weaken context tracking entry assertions x86/asm/tsc: Add rdtscll() merge helper selftests/x86: Add syscall_nt selftest selftests/x86: Disable sigreturn_64 x86/vdso: Emit a GNU hash x86/entry: Remove do_notify_resume(), syscall_trace_leave(), and their TIF masks x86/entry/32: Migrate to C exit path x86/entry/32: Remove 32-bit syscall audit optimizations x86/vm86: Rename vm86->v86flags and v86mask x86/vm86: Rename vm86->vm86_info to user_vm86 x86/vm86: Clean up vm86.h includes x86/vm86: Move the vm86 IRQ definitions to vm86.h x86/vm86: Use the normal pt_regs area for vm86 x86/vm86: Eliminate 'struct kernel_vm86_struct' x86/vm86: Move fields from 'struct kernel_vm86_struct' to 'struct vm86' x86/vm86: Move vm86 fields out of 'thread_struct' ...
2015-09-01 22:40:25 +07:00
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
math_error(regs, error_code, X86_TRAP_MF);
}
dotraplinkage void
do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
{
Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull x86 asm changes from Ingo Molnar: "The biggest changes in this cycle were: - Revamp, simplify (and in some cases fix) Time Stamp Counter (TSC) primitives. (Andy Lutomirski) - Add new, comprehensible entry and exit handlers written in C. (Andy Lutomirski) - vm86 mode cleanups and fixes. (Brian Gerst) - 32-bit compat code cleanups. (Brian Gerst) The amount of simplification in low level assembly code is already palpable: arch/x86/entry/entry_32.S | 130 +---- arch/x86/entry/entry_64.S | 197 ++----- but more simplifications are planned. There's also the usual laudry mix of low level changes - see the changelog for details" * 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (83 commits) x86/asm: Drop repeated macro of X86_EFLAGS_AC definition x86/asm/msr: Make wrmsrl() a function x86/asm/delay: Introduce an MWAITX-based delay with a configurable timer x86/asm: Add MONITORX/MWAITX instruction support x86/traps: Weaken context tracking entry assertions x86/asm/tsc: Add rdtscll() merge helper selftests/x86: Add syscall_nt selftest selftests/x86: Disable sigreturn_64 x86/vdso: Emit a GNU hash x86/entry: Remove do_notify_resume(), syscall_trace_leave(), and their TIF masks x86/entry/32: Migrate to C exit path x86/entry/32: Remove 32-bit syscall audit optimizations x86/vm86: Rename vm86->v86flags and v86mask x86/vm86: Rename vm86->vm86_info to user_vm86 x86/vm86: Clean up vm86.h includes x86/vm86: Move the vm86 IRQ definitions to vm86.h x86/vm86: Use the normal pt_regs area for vm86 x86/vm86: Eliminate 'struct kernel_vm86_struct' x86/vm86: Move fields from 'struct kernel_vm86_struct' to 'struct vm86' x86/vm86: Move vm86 fields out of 'thread_struct' ...
2015-09-01 22:40:25 +07:00
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
math_error(regs, error_code, X86_TRAP_XF);
}
dotraplinkage void
do_spurious_interrupt_bug(struct pt_regs *regs, long error_code)
{
cond_local_irq_enable(regs);
}
kprobes, x86: Use NOKPROBE_SYMBOL() instead of __kprobes annotation Use NOKPROBE_SYMBOL macro for protecting functions from kprobes instead of __kprobes annotation under arch/x86. This applies nokprobe_inline annotation for some cases, because NOKPROBE_SYMBOL() will inhibit inlining by referring the symbol address. This just folds a bunch of previous NOKPROBE_SYMBOL() cleanup patches for x86 to one patch. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Link: http://lkml.kernel.org/r/20140417081814.26341.51656.stgit@ltc230.yrl.intra.hitachi.co.jp Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Fernando Luis Vázquez Cao <fernando_b1@lab.ntt.co.jp> Cc: Gleb Natapov <gleb@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Lebon <jlebon@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Matt Fleming <matt.fleming@intel.com> Cc: Michel Lespinasse <walken@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Seiji Aguchi <seiji.aguchi@hds.com> Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vineet Gupta <vgupta@synopsys.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-04-17 15:18:14 +07:00
dotraplinkage void
do_device_not_available(struct pt_regs *regs, long error_code)
{
unsigned long cr0;
Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull x86 asm changes from Ingo Molnar: "The biggest changes in this cycle were: - Revamp, simplify (and in some cases fix) Time Stamp Counter (TSC) primitives. (Andy Lutomirski) - Add new, comprehensible entry and exit handlers written in C. (Andy Lutomirski) - vm86 mode cleanups and fixes. (Brian Gerst) - 32-bit compat code cleanups. (Brian Gerst) The amount of simplification in low level assembly code is already palpable: arch/x86/entry/entry_32.S | 130 +---- arch/x86/entry/entry_64.S | 197 ++----- but more simplifications are planned. There's also the usual laudry mix of low level changes - see the changelog for details" * 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (83 commits) x86/asm: Drop repeated macro of X86_EFLAGS_AC definition x86/asm/msr: Make wrmsrl() a function x86/asm/delay: Introduce an MWAITX-based delay with a configurable timer x86/asm: Add MONITORX/MWAITX instruction support x86/traps: Weaken context tracking entry assertions x86/asm/tsc: Add rdtscll() merge helper selftests/x86: Add syscall_nt selftest selftests/x86: Disable sigreturn_64 x86/vdso: Emit a GNU hash x86/entry: Remove do_notify_resume(), syscall_trace_leave(), and their TIF masks x86/entry/32: Migrate to C exit path x86/entry/32: Remove 32-bit syscall audit optimizations x86/vm86: Rename vm86->v86flags and v86mask x86/vm86: Rename vm86->vm86_info to user_vm86 x86/vm86: Clean up vm86.h includes x86/vm86: Move the vm86 IRQ definitions to vm86.h x86/vm86: Use the normal pt_regs area for vm86 x86/vm86: Eliminate 'struct kernel_vm86_struct' x86/vm86: Move fields from 'struct kernel_vm86_struct' to 'struct vm86' x86/vm86: Move vm86 fields out of 'thread_struct' ...
2015-09-01 22:40:25 +07:00
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
x86, fpu: use non-lazy fpu restore for processors supporting xsave Fundamental model of the current Linux kernel is to lazily init and restore FPU instead of restoring the task state during context switch. This changes that fundamental lazy model to the non-lazy model for the processors supporting xsave feature. Reasons driving this model change are: i. Newer processors support optimized state save/restore using xsaveopt and xrstor by tracking the INIT state and MODIFIED state during context-switch. This is faster than modifying the cr0.TS bit which has serializing semantics. ii. Newer glibc versions use SSE for some of the optimized copy/clear routines. With certain workloads (like boot, kernel-compilation etc), application completes its work with in the first 5 task switches, thus taking upto 5 #DNA traps with the kernel not getting a chance to apply the above mentioned pre-load heuristic. iii. Some xstate features (like AMD's LWP feature) don't honor the cr0.TS bit and thus will not work correctly in the presence of lazy restore. Non-lazy state restore is needed for enabling such features. Some data on a two socket SNB system: * Saved 20K DNA exceptions during boot on a two socket SNB system. * Saved 50K DNA exceptions during kernel-compilation workload. * Improved throughput of the AVX based checksumming function inside the kernel by ~15% as xsave/xrstor is faster than the serializing clts/stts pair. Also now kernel_fpu_begin/end() relies on the patched alternative instructions. So move check_fpu() which uses the kernel_fpu_begin/end() after alternative_instructions(). Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Link: http://lkml.kernel.org/r/1345842782-24175-7-git-send-email-suresh.b.siddha@intel.com Merge 32-bit boot fix from, Link: http://lkml.kernel.org/r/1347300665-6209-4-git-send-email-suresh.b.siddha@intel.com Cc: Jim Kukunas <james.t.kukunas@linux.intel.com> Cc: NeilBrown <neilb@suse.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2012-08-25 04:13:02 +07:00
#ifdef CONFIG_MATH_EMULATION
if (!boot_cpu_has(X86_FEATURE_FPU) && (read_cr0() & X86_CR0_EM)) {
struct math_emu_info info = { };
cond_local_irq_enable(regs);
info.regs = regs;
math_emulate(&info);
return;
}
#endif
/* This should not happen. */
cr0 = read_cr0();
if (WARN(cr0 & X86_CR0_TS, "CR0.TS was set")) {
/* Try to fix it up and carry on. */
write_cr0(cr0 & ~X86_CR0_TS);
} else {
/*
* Something terrible happened, and we're better off trying
* to kill the task than getting stuck in a never-ending
* loop of #NM faults.
*/
die("unexpected #NM exception", regs, error_code);
}
}
kprobes, x86: Use NOKPROBE_SYMBOL() instead of __kprobes annotation Use NOKPROBE_SYMBOL macro for protecting functions from kprobes instead of __kprobes annotation under arch/x86. This applies nokprobe_inline annotation for some cases, because NOKPROBE_SYMBOL() will inhibit inlining by referring the symbol address. This just folds a bunch of previous NOKPROBE_SYMBOL() cleanup patches for x86 to one patch. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Link: http://lkml.kernel.org/r/20140417081814.26341.51656.stgit@ltc230.yrl.intra.hitachi.co.jp Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Fernando Luis Vázquez Cao <fernando_b1@lab.ntt.co.jp> Cc: Gleb Natapov <gleb@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Lebon <jlebon@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Matt Fleming <matt.fleming@intel.com> Cc: Michel Lespinasse <walken@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Seiji Aguchi <seiji.aguchi@hds.com> Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vineet Gupta <vgupta@synopsys.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-04-17 15:18:14 +07:00
NOKPROBE_SYMBOL(do_device_not_available);
#ifdef CONFIG_X86_32
dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
{
siginfo_t info;
Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull x86 asm changes from Ingo Molnar: "The biggest changes in this cycle were: - Revamp, simplify (and in some cases fix) Time Stamp Counter (TSC) primitives. (Andy Lutomirski) - Add new, comprehensible entry and exit handlers written in C. (Andy Lutomirski) - vm86 mode cleanups and fixes. (Brian Gerst) - 32-bit compat code cleanups. (Brian Gerst) The amount of simplification in low level assembly code is already palpable: arch/x86/entry/entry_32.S | 130 +---- arch/x86/entry/entry_64.S | 197 ++----- but more simplifications are planned. There's also the usual laudry mix of low level changes - see the changelog for details" * 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (83 commits) x86/asm: Drop repeated macro of X86_EFLAGS_AC definition x86/asm/msr: Make wrmsrl() a function x86/asm/delay: Introduce an MWAITX-based delay with a configurable timer x86/asm: Add MONITORX/MWAITX instruction support x86/traps: Weaken context tracking entry assertions x86/asm/tsc: Add rdtscll() merge helper selftests/x86: Add syscall_nt selftest selftests/x86: Disable sigreturn_64 x86/vdso: Emit a GNU hash x86/entry: Remove do_notify_resume(), syscall_trace_leave(), and their TIF masks x86/entry/32: Migrate to C exit path x86/entry/32: Remove 32-bit syscall audit optimizations x86/vm86: Rename vm86->v86flags and v86mask x86/vm86: Rename vm86->vm86_info to user_vm86 x86/vm86: Clean up vm86.h includes x86/vm86: Move the vm86 IRQ definitions to vm86.h x86/vm86: Use the normal pt_regs area for vm86 x86/vm86: Eliminate 'struct kernel_vm86_struct' x86/vm86: Move fields from 'struct kernel_vm86_struct' to 'struct vm86' x86/vm86: Move vm86 fields out of 'thread_struct' ...
2015-09-01 22:40:25 +07:00
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
local_irq_enable();
info.si_signo = SIGILL;
info.si_errno = 0;
info.si_code = ILL_BADSTK;
info.si_addr = NULL;
if (notify_die(DIE_TRAP, "iret exception", regs, error_code,
X86_TRAP_IRET, SIGILL) != NOTIFY_STOP) {
do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
&info);
}
}
#endif
/* Set of traps needed for early debugging. */
void __init early_trap_init(void)
{
/*
* Don't use IST to set DEBUG_STACK as it doesn't work until TSS
* is ready in cpu_init() <-- trap_init(). Before trap_init(),
* CPU runs at ring 0 so it is impossible to hit an invalid
* stack. Using the original stack works well enough at this
* early stage. DEBUG_STACK will be equipped after cpu_init() in
* trap_init().
*
* We don't need to set trace_idt_table like set_intr_gate(),
* since we don't have trace_debug and it will be reset to
* 'debug' in trap_init() by set_intr_gate_ist().
*/
set_intr_gate_notrace(X86_TRAP_DB, debug);
/* int3 can be called from all */
set_system_intr_gate(X86_TRAP_BP, &int3);
x86, 64bit: Use a #PF handler to materialize early mappings on demand Linear mode (CR0.PG = 0) is mutually exclusive with 64-bit mode; all 64-bit code has to use page tables. This makes it awkward before we have first set up properly all-covering page tables to access objects that are outside the static kernel range. So far we have dealt with that simply by mapping a fixed amount of low memory, but that fails in at least two upcoming use cases: 1. We will support load and run kernel, struct boot_params, ramdisk, command line, etc. above the 4 GiB mark. 2. need to access ramdisk early to get microcode to update that as early possible. We could use early_iomap to access them too, but it will make code to messy and hard to be unified with 32 bit. Hence, set up a #PF table and use a fixed number of buffers to set up page tables on demand. If the buffers fill up then we simply flush them and start over. These buffers are all in __initdata, so it does not increase RAM usage at runtime. Thus, with the help of the #PF handler, we can set the final kernel mapping from blank, and switch to init_level4_pgt later. During the switchover in head_64.S, before #PF handler is available, we use three pages to handle kernel crossing 1G, 512G boundaries with sharing page by playing games with page aliasing: the same page is mapped twice in the higher-level tables with appropriate wraparound. The kernel region itself will be properly mapped; other mappings may be spurious. early_make_pgtable is using kernel high mapping address to access pages to set page table. -v4: Add phys_base offset to make kexec happy, and add init_mapping_kernel() - Yinghai -v5: fix compiling with xen, and add back ident level3 and level2 for xen also move back init_level4_pgt from BSS to DATA again. because we have to clear it anyway. - Yinghai -v6: switch to init_level4_pgt in init_mem_mapping. - Yinghai -v7: remove not needed clear_page for init_level4_page it is with fill 512,8,0 already in head_64.S - Yinghai -v8: we need to keep that handler alive until init_mem_mapping and don't let early_trap_init to trash that early #PF handler. So split early_trap_pf_init out and move it down. - Yinghai -v9: switchover only cover kernel space instead of 1G so could avoid touch possible mem holes. - Yinghai -v11: change far jmp back to far return to initial_code, that is needed to fix failure that is reported by Konrad on AMD systems. - Yinghai Signed-off-by: Yinghai Lu <yinghai@kernel.org> Link: http://lkml.kernel.org/r/1359058816-7615-12-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2013-01-25 03:19:52 +07:00
#ifdef CONFIG_X86_32
set_intr_gate(X86_TRAP_PF, page_fault);
x86, 64bit: Use a #PF handler to materialize early mappings on demand Linear mode (CR0.PG = 0) is mutually exclusive with 64-bit mode; all 64-bit code has to use page tables. This makes it awkward before we have first set up properly all-covering page tables to access objects that are outside the static kernel range. So far we have dealt with that simply by mapping a fixed amount of low memory, but that fails in at least two upcoming use cases: 1. We will support load and run kernel, struct boot_params, ramdisk, command line, etc. above the 4 GiB mark. 2. need to access ramdisk early to get microcode to update that as early possible. We could use early_iomap to access them too, but it will make code to messy and hard to be unified with 32 bit. Hence, set up a #PF table and use a fixed number of buffers to set up page tables on demand. If the buffers fill up then we simply flush them and start over. These buffers are all in __initdata, so it does not increase RAM usage at runtime. Thus, with the help of the #PF handler, we can set the final kernel mapping from blank, and switch to init_level4_pgt later. During the switchover in head_64.S, before #PF handler is available, we use three pages to handle kernel crossing 1G, 512G boundaries with sharing page by playing games with page aliasing: the same page is mapped twice in the higher-level tables with appropriate wraparound. The kernel region itself will be properly mapped; other mappings may be spurious. early_make_pgtable is using kernel high mapping address to access pages to set page table. -v4: Add phys_base offset to make kexec happy, and add init_mapping_kernel() - Yinghai -v5: fix compiling with xen, and add back ident level3 and level2 for xen also move back init_level4_pgt from BSS to DATA again. because we have to clear it anyway. - Yinghai -v6: switch to init_level4_pgt in init_mem_mapping. - Yinghai -v7: remove not needed clear_page for init_level4_page it is with fill 512,8,0 already in head_64.S - Yinghai -v8: we need to keep that handler alive until init_mem_mapping and don't let early_trap_init to trash that early #PF handler. So split early_trap_pf_init out and move it down. - Yinghai -v9: switchover only cover kernel space instead of 1G so could avoid touch possible mem holes. - Yinghai -v11: change far jmp back to far return to initial_code, that is needed to fix failure that is reported by Konrad on AMD systems. - Yinghai Signed-off-by: Yinghai Lu <yinghai@kernel.org> Link: http://lkml.kernel.org/r/1359058816-7615-12-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2013-01-25 03:19:52 +07:00
#endif
load_idt(&idt_descr);
}
x86, 64bit: Use a #PF handler to materialize early mappings on demand Linear mode (CR0.PG = 0) is mutually exclusive with 64-bit mode; all 64-bit code has to use page tables. This makes it awkward before we have first set up properly all-covering page tables to access objects that are outside the static kernel range. So far we have dealt with that simply by mapping a fixed amount of low memory, but that fails in at least two upcoming use cases: 1. We will support load and run kernel, struct boot_params, ramdisk, command line, etc. above the 4 GiB mark. 2. need to access ramdisk early to get microcode to update that as early possible. We could use early_iomap to access them too, but it will make code to messy and hard to be unified with 32 bit. Hence, set up a #PF table and use a fixed number of buffers to set up page tables on demand. If the buffers fill up then we simply flush them and start over. These buffers are all in __initdata, so it does not increase RAM usage at runtime. Thus, with the help of the #PF handler, we can set the final kernel mapping from blank, and switch to init_level4_pgt later. During the switchover in head_64.S, before #PF handler is available, we use three pages to handle kernel crossing 1G, 512G boundaries with sharing page by playing games with page aliasing: the same page is mapped twice in the higher-level tables with appropriate wraparound. The kernel region itself will be properly mapped; other mappings may be spurious. early_make_pgtable is using kernel high mapping address to access pages to set page table. -v4: Add phys_base offset to make kexec happy, and add init_mapping_kernel() - Yinghai -v5: fix compiling with xen, and add back ident level3 and level2 for xen also move back init_level4_pgt from BSS to DATA again. because we have to clear it anyway. - Yinghai -v6: switch to init_level4_pgt in init_mem_mapping. - Yinghai -v7: remove not needed clear_page for init_level4_page it is with fill 512,8,0 already in head_64.S - Yinghai -v8: we need to keep that handler alive until init_mem_mapping and don't let early_trap_init to trash that early #PF handler. So split early_trap_pf_init out and move it down. - Yinghai -v9: switchover only cover kernel space instead of 1G so could avoid touch possible mem holes. - Yinghai -v11: change far jmp back to far return to initial_code, that is needed to fix failure that is reported by Konrad on AMD systems. - Yinghai Signed-off-by: Yinghai Lu <yinghai@kernel.org> Link: http://lkml.kernel.org/r/1359058816-7615-12-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2013-01-25 03:19:52 +07:00
void __init early_trap_pf_init(void)
{
#ifdef CONFIG_X86_64
set_intr_gate(X86_TRAP_PF, page_fault);
x86, 64bit: Use a #PF handler to materialize early mappings on demand Linear mode (CR0.PG = 0) is mutually exclusive with 64-bit mode; all 64-bit code has to use page tables. This makes it awkward before we have first set up properly all-covering page tables to access objects that are outside the static kernel range. So far we have dealt with that simply by mapping a fixed amount of low memory, but that fails in at least two upcoming use cases: 1. We will support load and run kernel, struct boot_params, ramdisk, command line, etc. above the 4 GiB mark. 2. need to access ramdisk early to get microcode to update that as early possible. We could use early_iomap to access them too, but it will make code to messy and hard to be unified with 32 bit. Hence, set up a #PF table and use a fixed number of buffers to set up page tables on demand. If the buffers fill up then we simply flush them and start over. These buffers are all in __initdata, so it does not increase RAM usage at runtime. Thus, with the help of the #PF handler, we can set the final kernel mapping from blank, and switch to init_level4_pgt later. During the switchover in head_64.S, before #PF handler is available, we use three pages to handle kernel crossing 1G, 512G boundaries with sharing page by playing games with page aliasing: the same page is mapped twice in the higher-level tables with appropriate wraparound. The kernel region itself will be properly mapped; other mappings may be spurious. early_make_pgtable is using kernel high mapping address to access pages to set page table. -v4: Add phys_base offset to make kexec happy, and add init_mapping_kernel() - Yinghai -v5: fix compiling with xen, and add back ident level3 and level2 for xen also move back init_level4_pgt from BSS to DATA again. because we have to clear it anyway. - Yinghai -v6: switch to init_level4_pgt in init_mem_mapping. - Yinghai -v7: remove not needed clear_page for init_level4_page it is with fill 512,8,0 already in head_64.S - Yinghai -v8: we need to keep that handler alive until init_mem_mapping and don't let early_trap_init to trash that early #PF handler. So split early_trap_pf_init out and move it down. - Yinghai -v9: switchover only cover kernel space instead of 1G so could avoid touch possible mem holes. - Yinghai -v11: change far jmp back to far return to initial_code, that is needed to fix failure that is reported by Konrad on AMD systems. - Yinghai Signed-off-by: Yinghai Lu <yinghai@kernel.org> Link: http://lkml.kernel.org/r/1359058816-7615-12-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2013-01-25 03:19:52 +07:00
#endif
}
void __init trap_init(void)
{
int i;
#ifdef CONFIG_EISA
void __iomem *p = early_ioremap(0x0FFFD9, 4);
if (readl(p) == 'E' + ('I'<<8) + ('S'<<16) + ('A'<<24))
EISA_bus = 1;
early_iounmap(p, 4);
#endif
set_intr_gate(X86_TRAP_DE, divide_error);
set_intr_gate_ist(X86_TRAP_NMI, &nmi, NMI_STACK);
/* int4 can be called from all */
set_system_intr_gate(X86_TRAP_OF, &overflow);
set_intr_gate(X86_TRAP_BR, bounds);
set_intr_gate(X86_TRAP_UD, invalid_op);
set_intr_gate(X86_TRAP_NM, device_not_available);
#ifdef CONFIG_X86_32
set_task_gate(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS);
#else
set_intr_gate_ist(X86_TRAP_DF, &double_fault, DOUBLEFAULT_STACK);
#endif
set_intr_gate(X86_TRAP_OLD_MF, coprocessor_segment_overrun);
set_intr_gate(X86_TRAP_TS, invalid_TSS);
set_intr_gate(X86_TRAP_NP, segment_not_present);
set_intr_gate(X86_TRAP_SS, stack_segment);
set_intr_gate(X86_TRAP_GP, general_protection);
set_intr_gate(X86_TRAP_SPURIOUS, spurious_interrupt_bug);
set_intr_gate(X86_TRAP_MF, coprocessor_error);
set_intr_gate(X86_TRAP_AC, alignment_check);
#ifdef CONFIG_X86_MCE
set_intr_gate_ist(X86_TRAP_MC, &machine_check, MCE_STACK);
#endif
set_intr_gate(X86_TRAP_XF, simd_coprocessor_error);
/* Reserve all the builtin and the syscall vector: */
for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++)
set_bit(i, used_vectors);
#ifdef CONFIG_IA32_EMULATION
set_system_intr_gate(IA32_SYSCALL_VECTOR, entry_INT80_compat);
set_bit(IA32_SYSCALL_VECTOR, used_vectors);
#endif
#ifdef CONFIG_X86_32
set_system_intr_gate(IA32_SYSCALL_VECTOR, entry_INT80_32);
set_bit(IA32_SYSCALL_VECTOR, used_vectors);
#endif
/*
* Set the IDT descriptor to a fixed read-only location, so that the
* "sidt" instruction will not leak the location of the kernel, and
* to defend the IDT against arbitrary memory write vulnerabilities.
* It will be reloaded in cpu_init() */
__set_fixmap(FIX_RO_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO);
idt_descr.address = fix_to_virt(FIX_RO_IDT);
/*
* Should be a barrier for any external CPU state:
*/
cpu_init();
/*
* X86_TRAP_DB and X86_TRAP_BP have been set
* in early_trap_init(). However, ITS works only after
* cpu_init() loads TSS. See comments in early_trap_init().
*/
set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK);
/* int3 can be called from all */
set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK);
x86_init.irqs.trap_init();
#ifdef CONFIG_X86_64
memcpy(&debug_idt_table, &idt_table, IDT_ENTRIES * 16);
set_nmi_gate(X86_TRAP_DB, &debug);
set_nmi_gate(X86_TRAP_BP, &int3);
#endif
}