linux_dsm_epyc7002/arch/x86/kernel/fpu/signal.c
Eric Biggers 814fb7bb7d x86/fpu: Don't let userspace set bogus xcomp_bv
On x86, userspace can use the ptrace() or rt_sigreturn() system calls to
set a task's extended state (xstate) or "FPU" registers.  ptrace() can
set them for another task using the PTRACE_SETREGSET request with
NT_X86_XSTATE, while rt_sigreturn() can set them for the current task.
In either case, registers can be set to any value, but the kernel
assumes that the XSAVE area itself remains valid in the sense that the
CPU can restore it.

However, in the case where the kernel is using the uncompacted xstate
format (which it does whenever the XSAVES instruction is unavailable),
it was possible for userspace to set the xcomp_bv field in the
xstate_header to an arbitrary value.  However, all bits in that field
are reserved in the uncompacted case, so when switching to a task with
nonzero xcomp_bv, the XRSTOR instruction failed with a #GP fault.  This
caused the WARN_ON_FPU(err) in copy_kernel_to_xregs() to be hit.  In
addition, since the error is otherwise ignored, the FPU registers from
the task previously executing on the CPU were leaked.

Fix the bug by checking that the user-supplied value of xcomp_bv is 0 in
the uncompacted case, and returning an error otherwise.

The reason for validating xcomp_bv rather than simply overwriting it
with 0 is that we want userspace to see an error if it (incorrectly)
provides an XSAVE area in compacted format rather than in uncompacted
format.

Note that as before, in case of error we clear the task's FPU state.
This is perhaps non-ideal, especially for PTRACE_SETREGSET; it might be
better to return an error before changing anything.  But it seems the
"clear on error" behavior is fine for now, and it's a little tricky to
do otherwise because it would mean we couldn't simply copy the full
userspace state into kernel memory in one __copy_from_user().

This bug was found by syzkaller, which hit the above-mentioned
WARN_ON_FPU():

    WARNING: CPU: 1 PID: 0 at ./arch/x86/include/asm/fpu/internal.h:373 __switch_to+0x5b5/0x5d0
    CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.13.0 #453
    Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
    task: ffff9ba2bc8e42c0 task.stack: ffffa78cc036c000
    RIP: 0010:__switch_to+0x5b5/0x5d0
    RSP: 0000:ffffa78cc08bbb88 EFLAGS: 00010082
    RAX: 00000000fffffffe RBX: ffff9ba2b8bf2180 RCX: 00000000c0000100
    RDX: 00000000ffffffff RSI: 000000005cb10700 RDI: ffff9ba2b8bf36c0
    RBP: ffffa78cc08bbbd0 R08: 00000000929fdf46 R09: 0000000000000001
    R10: 0000000000000000 R11: 0000000000000000 R12: ffff9ba2bc8e42c0
    R13: 0000000000000000 R14: ffff9ba2b8bf3680 R15: ffff9ba2bf5d7b40
    FS:  00007f7e5cb10700(0000) GS:ffff9ba2bf400000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    CR2: 00000000004005cc CR3: 0000000079fd5000 CR4: 00000000001406e0
    Call Trace:
    Code: 84 00 00 00 00 00 e9 11 fd ff ff 0f ff 66 0f 1f 84 00 00 00 00 00 e9 e7 fa ff ff 0f ff 66 0f 1f 84 00 00 00 00 00 e9 c2 fa ff ff <0f> ff 66 0f 1f 84 00 00 00 00 00 e9 d4 fc ff ff 66 66 2e 0f 1f

Here is a C reproducer.  The expected behavior is that the program spin
forever with no output.  However, on a buggy kernel running on a
processor with the "xsave" feature but without the "xsaves" feature
(e.g. Sandy Bridge through Broadwell for Intel), within a second or two
the program reports that the xmm registers were corrupted, i.e. were not
restored correctly.  With CONFIG_X86_DEBUG_FPU=y it also hits the above
kernel warning.

    #define _GNU_SOURCE
    #include <stdbool.h>
    #include <inttypes.h>
    #include <linux/elf.h>
    #include <stdio.h>
    #include <sys/ptrace.h>
    #include <sys/uio.h>
    #include <sys/wait.h>
    #include <unistd.h>

    int main(void)
    {
        int pid = fork();
        uint64_t xstate[512];
        struct iovec iov = { .iov_base = xstate, .iov_len = sizeof(xstate) };

        if (pid == 0) {
            bool tracee = true;
            for (int i = 0; i < sysconf(_SC_NPROCESSORS_ONLN) && tracee; i++)
                tracee = (fork() != 0);
            uint32_t xmm0[4] = { [0 ... 3] = tracee ? 0x00000000 : 0xDEADBEEF };
            asm volatile("   movdqu %0, %%xmm0\n"
                         "   mov %0, %%rbx\n"
                         "1: movdqu %%xmm0, %0\n"
                         "   mov %0, %%rax\n"
                         "   cmp %%rax, %%rbx\n"
                         "   je 1b\n"
                         : "+m" (xmm0) : : "rax", "rbx", "xmm0");
            printf("BUG: xmm registers corrupted!  tracee=%d, xmm0=%08X%08X%08X%08X\n",
                   tracee, xmm0[0], xmm0[1], xmm0[2], xmm0[3]);
        } else {
            usleep(100000);
            ptrace(PTRACE_ATTACH, pid, 0, 0);
            wait(NULL);
            ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov);
            xstate[65] = -1;
            ptrace(PTRACE_SETREGSET, pid, NT_X86_XSTATE, &iov);
            ptrace(PTRACE_CONT, pid, 0, 0);
            wait(NULL);
        }
        return 1;
    }

Note: the program only tests for the bug using the ptrace() system call.
The bug can also be reproduced using the rt_sigreturn() system call, but
only when called from a 32-bit program, since for 64-bit programs the
kernel restores the FPU state from the signal frame by doing XRSTOR
directly from userspace memory (with proper error checking).

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Eric Biggers <ebiggers@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: <stable@vger.kernel.org> [v3.17+]
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Eric Biggers <ebiggers3@gmail.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Kevin Hao <haokexin@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michael Halcrow <mhalcrow@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
Cc: Yu-cheng Yu <yu-cheng.yu@intel.com>
Cc: kernel-hardening@lists.openwall.com
Fixes: 0b29643a58 ("x86/xsaves: Change compacted format xsave area header")
Link: http://lkml.kernel.org/r/20170922174156.16780-2-ebiggers3@gmail.com
Link: http://lkml.kernel.org/r/20170923130016.21448-25-mingo@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-09-25 09:26:32 +02:00

429 lines
12 KiB
C

/*
* FPU signal frame handling routines.
*/
#include <linux/compat.h>
#include <linux/cpu.h>
#include <asm/fpu/internal.h>
#include <asm/fpu/signal.h>
#include <asm/fpu/regset.h>
#include <asm/fpu/xstate.h>
#include <asm/sigframe.h>
#include <asm/trace/fpu.h>
static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
/*
* Check for the presence of extended state information in the
* user fpstate pointer in the sigcontext.
*/
static inline int check_for_xstate(struct fxregs_state __user *buf,
void __user *fpstate,
struct _fpx_sw_bytes *fx_sw)
{
int min_xstate_size = sizeof(struct fxregs_state) +
sizeof(struct xstate_header);
unsigned int magic2;
if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw)))
return -1;
/* Check for the first magic field and other error scenarios. */
if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
fx_sw->xstate_size < min_xstate_size ||
fx_sw->xstate_size > fpu_user_xstate_size ||
fx_sw->xstate_size > fx_sw->extended_size)
return -1;
/*
* Check for the presence of second magic word at the end of memory
* layout. This detects the case where the user just copied the legacy
* fpstate layout with out copying the extended state information
* in the memory layout.
*/
if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))
|| magic2 != FP_XSTATE_MAGIC2)
return -1;
return 0;
}
/*
* Signal frame handlers.
*/
static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
{
if (use_fxsr()) {
struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
struct user_i387_ia32_struct env;
struct _fpstate_32 __user *fp = buf;
convert_from_fxsr(&env, tsk);
if (__copy_to_user(buf, &env, sizeof(env)) ||
__put_user(xsave->i387.swd, &fp->status) ||
__put_user(X86_FXSR_MAGIC, &fp->magic))
return -1;
} else {
struct fregs_state __user *fp = buf;
u32 swd;
if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status))
return -1;
}
return 0;
}
static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
{
struct xregs_state __user *x = buf;
struct _fpx_sw_bytes *sw_bytes;
u32 xfeatures;
int err;
/* Setup the bytes not touched by the [f]xsave and reserved for SW. */
sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved;
err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes));
if (!use_xsave())
return err;
err |= __put_user(FP_XSTATE_MAGIC2,
(__u32 *)(buf + fpu_user_xstate_size));
/*
* Read the xfeatures which we copied (directly from the cpu or
* from the state in task struct) to the user buffers.
*/
err |= __get_user(xfeatures, (__u32 *)&x->header.xfeatures);
/*
* For legacy compatible, we always set FP/SSE bits in the bit
* vector while saving the state to the user context. This will
* enable us capturing any changes(during sigreturn) to
* the FP/SSE bits by the legacy applications which don't touch
* xfeatures in the xsave header.
*
* xsave aware apps can change the xfeatures in the xsave
* header as well as change any contents in the memory layout.
* xrestore as part of sigreturn will capture all the changes.
*/
xfeatures |= XFEATURE_MASK_FPSSE;
err |= __put_user(xfeatures, (__u32 *)&x->header.xfeatures);
return err;
}
static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
{
int err;
if (use_xsave())
err = copy_xregs_to_user(buf);
else if (use_fxsr())
err = copy_fxregs_to_user((struct fxregs_state __user *) buf);
else
err = copy_fregs_to_user((struct fregs_state __user *) buf);
if (unlikely(err) && __clear_user(buf, fpu_user_xstate_size))
err = -EFAULT;
return err;
}
/*
* Save the fpu, extended register state to the user signal frame.
*
* 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save
* state is copied.
* 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'.
*
* buf == buf_fx for 64-bit frames and 32-bit fsave frame.
* buf != buf_fx for 32-bit frames with fxstate.
*
* If the fpu, extended register state is live, save the state directly
* to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise,
* copy the thread's fpu state to the user frame starting at 'buf_fx'.
*
* If this is a 32-bit frame with fxstate, put a fsave header before
* the aligned state at 'buf_fx'.
*
* For [f]xsave state, update the SW reserved fields in the [f]xsave frame
* indicating the absence/presence of the extended state to the user.
*/
int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
{
struct fpu *fpu = &current->thread.fpu;
struct xregs_state *xsave = &fpu->state.xsave;
struct task_struct *tsk = current;
int ia32_fxstate = (buf != buf_fx);
ia32_fxstate &= (IS_ENABLED(CONFIG_X86_32) ||
IS_ENABLED(CONFIG_IA32_EMULATION));
if (!access_ok(VERIFY_WRITE, buf, size))
return -EACCES;
if (!static_cpu_has(X86_FEATURE_FPU))
return fpregs_soft_get(current, NULL, 0,
sizeof(struct user_i387_ia32_struct), NULL,
(struct _fpstate_32 __user *) buf) ? -1 : 1;
if (fpu->fpstate_active || using_compacted_format()) {
/* Save the live register state to the user directly. */
if (copy_fpregs_to_sigframe(buf_fx))
return -1;
/* Update the thread's fxstate to save the fsave header. */
if (ia32_fxstate)
copy_fxregs_to_kernel(fpu);
} else {
/*
* It is a *bug* if kernel uses compacted-format for xsave
* area and we copy it out directly to a signal frame. It
* should have been handled above by saving the registers
* directly.
*/
if (boot_cpu_has(X86_FEATURE_XSAVES)) {
WARN_ONCE(1, "x86/fpu: saving compacted-format xsave area to a signal frame!\n");
return -1;
}
fpstate_sanitize_xstate(fpu);
if (__copy_to_user(buf_fx, xsave, fpu_user_xstate_size))
return -1;
}
/* Save the fsave header for the 32-bit frames. */
if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf))
return -1;
if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
return -1;
return 0;
}
static inline void
sanitize_restored_xstate(struct task_struct *tsk,
struct user_i387_ia32_struct *ia32_env,
u64 xfeatures, int fx_only)
{
struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
struct xstate_header *header = &xsave->header;
if (use_xsave()) {
/* These bits must be zero. */
memset(header->reserved, 0, 48);
/*
* Init the state that is not present in the memory
* layout and not enabled by the OS.
*/
if (fx_only)
header->xfeatures = XFEATURE_MASK_FPSSE;
else
header->xfeatures &= (xfeatures_mask & xfeatures);
}
if (use_fxsr()) {
/*
* mscsr reserved bits must be masked to zero for security
* reasons.
*/
xsave->i387.mxcsr &= mxcsr_feature_mask;
convert_to_fxsr(tsk, ia32_env);
}
}
/*
* Restore the extended state if present. Otherwise, restore the FP/SSE state.
*/
static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only)
{
if (use_xsave()) {
if ((unsigned long)buf % 64 || fx_only) {
u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE;
copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
return copy_user_to_fxregs(buf);
} else {
u64 init_bv = xfeatures_mask & ~xbv;
if (unlikely(init_bv))
copy_kernel_to_xregs(&init_fpstate.xsave, init_bv);
return copy_user_to_xregs(buf, xbv);
}
} else if (use_fxsr()) {
return copy_user_to_fxregs(buf);
} else
return copy_user_to_fregs(buf);
}
static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
{
int ia32_fxstate = (buf != buf_fx);
struct task_struct *tsk = current;
struct fpu *fpu = &tsk->thread.fpu;
int state_size = fpu_kernel_xstate_size;
u64 xfeatures = 0;
int fx_only = 0;
ia32_fxstate &= (IS_ENABLED(CONFIG_X86_32) ||
IS_ENABLED(CONFIG_IA32_EMULATION));
if (!buf) {
fpu__clear(fpu);
return 0;
}
if (!access_ok(VERIFY_READ, buf, size))
return -EACCES;
fpu__activate_curr(fpu);
if (!static_cpu_has(X86_FEATURE_FPU))
return fpregs_soft_set(current, NULL,
0, sizeof(struct user_i387_ia32_struct),
NULL, buf) != 0;
if (use_xsave()) {
struct _fpx_sw_bytes fx_sw_user;
if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) {
/*
* Couldn't find the extended state information in the
* memory layout. Restore just the FP/SSE and init all
* the other extended state.
*/
state_size = sizeof(struct fxregs_state);
fx_only = 1;
trace_x86_fpu_xstate_check_failed(fpu);
} else {
state_size = fx_sw_user.xstate_size;
xfeatures = fx_sw_user.xfeatures;
}
}
if (ia32_fxstate) {
/*
* For 32-bit frames with fxstate, copy the user state to the
* thread's fpu state, reconstruct fxstate from the fsave
* header. Sanitize the copied state etc.
*/
struct fpu *fpu = &tsk->thread.fpu;
struct user_i387_ia32_struct env;
int err = 0;
/*
* Drop the current fpu which clears fpu->fpstate_active. This ensures
* that any context-switch during the copy of the new state,
* avoids the intermediate state from getting restored/saved.
* Thus avoiding the new restored state from getting corrupted.
* We will be ready to restore/save the state only after
* fpu->fpstate_active is again set.
*/
fpu__drop(fpu);
if (using_compacted_format()) {
err = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
} else {
err = __copy_from_user(&fpu->state.xsave, buf_fx, state_size);
/* xcomp_bv must be 0 when using uncompacted format */
if (!err && state_size > offsetof(struct xregs_state, header) && fpu->state.xsave.header.xcomp_bv)
err = -EINVAL;
}
if (err || __copy_from_user(&env, buf, sizeof(env))) {
fpstate_init(&fpu->state);
trace_x86_fpu_init_state(fpu);
err = -1;
} else {
sanitize_restored_xstate(tsk, &env, xfeatures, fx_only);
}
fpu->fpstate_active = 1;
preempt_disable();
fpu__restore(fpu);
preempt_enable();
return err;
} else {
/*
* For 64-bit frames and 32-bit fsave frames, restore the user
* state to the registers directly (with exceptions handled).
*/
user_fpu_begin();
if (copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only)) {
fpu__clear(fpu);
return -1;
}
}
return 0;
}
static inline int xstate_sigframe_size(void)
{
return use_xsave() ? fpu_user_xstate_size + FP_XSTATE_MAGIC2_SIZE :
fpu_user_xstate_size;
}
/*
* Restore FPU state from a sigframe:
*/
int fpu__restore_sig(void __user *buf, int ia32_frame)
{
void __user *buf_fx = buf;
int size = xstate_sigframe_size();
if (ia32_frame && use_fxsr()) {
buf_fx = buf + sizeof(struct fregs_state);
size += sizeof(struct fregs_state);
}
return __fpu__restore_sig(buf, buf_fx, size);
}
unsigned long
fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
unsigned long *buf_fx, unsigned long *size)
{
unsigned long frame_size = xstate_sigframe_size();
*buf_fx = sp = round_down(sp - frame_size, 64);
if (ia32_frame && use_fxsr()) {
frame_size += sizeof(struct fregs_state);
sp -= sizeof(struct fregs_state);
}
*size = frame_size;
return sp;
}
/*
* Prepare the SW reserved portion of the fxsave memory layout, indicating
* the presence of the extended state information in the memory layout
* pointed by the fpstate pointer in the sigcontext.
* This will be saved when ever the FP and extended state context is
* saved on the user stack during the signal handler delivery to the user.
*/
void fpu__init_prepare_fx_sw_frame(void)
{
int size = fpu_user_xstate_size + FP_XSTATE_MAGIC2_SIZE;
fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
fx_sw_reserved.extended_size = size;
fx_sw_reserved.xfeatures = xfeatures_mask;
fx_sw_reserved.xstate_size = fpu_user_xstate_size;
if (IS_ENABLED(CONFIG_IA32_EMULATION) ||
IS_ENABLED(CONFIG_X86_32)) {
int fsave_header_size = sizeof(struct fregs_state);
fx_sw_reserved_ia32 = fx_sw_reserved;
fx_sw_reserved_ia32.extended_size = size + fsave_header_size;
}
}