From 484cea4f362e1eeb5c869abbfb5f90eae6421b38 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 8 Jun 2021 16:36:18 +0200 Subject: x86/fpu: Prevent state corruption in __fpu__restore_sig() The non-compacted slowpath uses __copy_from_user() and copies the entire user buffer into the kernel buffer, verbatim. This means that the kernel buffer may now contain entirely invalid state on which XRSTOR will #GP. validate_user_xstate_header() can detect some of that corruption, but that leaves the onus on callers to clear the buffer. Prior to XSAVES support, it was possible just to reinitialize the buffer, completely, but with supervisor states that is not longer possible as the buffer clearing code split got it backwards. Fixing that is possible but not corrupting the state in the first place is more robust. Avoid corruption of the kernel XSAVE buffer by using copy_user_to_xstate() which validates the XSAVE header contents before copying the actual states to the kernel. copy_user_to_xstate() was previously only called for compacted-format kernel buffers, but it works for both compacted and non-compacted forms. Using it for the non-compacted form is slower because of multiple __copy_from_user() operations, but that cost is less important than robust code in an already slow path. [ Changelog polished by Dave Hansen ] Fixes: b860eb8dce59 ("x86/fpu/xstate: Define new functions for clearing fpregs and xstates") Reported-by: syzbot+2067e764dbcd10721e2e@syzkaller.appspotmail.com Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Reviewed-by: Borislav Petkov Acked-by: Dave Hansen Acked-by: Rik van Riel Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20210608144345.611833074@linutronix.de --- arch/x86/kernel/fpu/signal.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'arch/x86/kernel/fpu/signal.c') diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index a4ec65317a7f..d5bc96a536c2 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -405,14 +405,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) if (use_xsave() && !fx_only) { u64 init_bv = xfeatures_mask_user() & ~user_xfeatures; - if (using_compacted_format()) { - ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx); - } else { - ret = __copy_from_user(&fpu->state.xsave, buf_fx, state_size); - - if (!ret && state_size > offsetof(struct xregs_state, header)) - ret = validate_user_xstate_header(&fpu->state.xsave.header); - } + ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx); if (ret) goto err_out; -- cgit v1.2.3 From d8778e393afa421f1f117471144f8ce6deb6953a Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 8 Jun 2021 16:36:19 +0200 Subject: x86/fpu: Invalidate FPU state after a failed XRSTOR from a user buffer Both Intel and AMD consider it to be architecturally valid for XRSTOR to fail with #PF but nonetheless change the register state. The actual conditions under which this might occur are unclear [1], but it seems plausible that this might be triggered if one sibling thread unmaps a page and invalidates the shared TLB while another sibling thread is executing XRSTOR on the page in question. __fpu__restore_sig() can execute XRSTOR while the hardware registers are preserved on behalf of a different victim task (using the fpu_fpregs_owner_ctx mechanism), and, in theory, XRSTOR could fail but modify the registers. If this happens, then there is a window in which __fpu__restore_sig() could schedule out and the victim task could schedule back in without reloading its own FPU registers. This would result in part of the FPU state that __fpu__restore_sig() was attempting to load leaking into the victim task's user-visible state. Invalidate preserved FPU registers on XRSTOR failure to prevent this situation from corrupting any state. [1] Frequent readers of the errata lists might imagine "complex microarchitectural conditions". Fixes: 1d731e731c4c ("x86/fpu: Add a fastpath to __fpu__restore_sig()") Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Acked-by: Dave Hansen Acked-by: Rik van Riel Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20210608144345.758116583@linutronix.de --- arch/x86/kernel/fpu/signal.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'arch/x86/kernel/fpu/signal.c') diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index d5bc96a536c2..4ab9aeb9a963 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -369,6 +369,25 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) fpregs_unlock(); return 0; } + + /* + * The above did an FPU restore operation, restricted to + * the user portion of the registers, and failed, but the + * microcode might have modified the FPU registers + * nevertheless. + * + * If the FPU registers do not belong to current, then + * invalidate the FPU register state otherwise the task might + * preempt current and return to user space with corrupted + * FPU registers. + * + * In case current owns the FPU registers then no further + * action is required. The fixup below will handle it + * correctly. + */ + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + __cpu_invalidate_fpregs_state(); + fpregs_unlock(); } else { /* -- cgit v1.2.3 From efa165504943f2128d50f63de0c02faf6dcceb0d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 9 Jun 2021 21:18:00 +0200 Subject: x86/fpu: Reset state for all signal restore failures If access_ok() or fpregs_soft_set() fails in __fpu__restore_sig() then the function just returns but does not clear the FPU state as it does for all other fatal failures. Clear the FPU state for these failures as well. Fixes: 72a671ced66d ("x86, fpu: Unify signal handling code paths for x86 and x86_64 kernels") Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/87mtryyhhz.ffs@nanos.tec.linutronix.de --- arch/x86/kernel/fpu/signal.c | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) (limited to 'arch/x86/kernel/fpu/signal.c') diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 4ab9aeb9a963..ec3ae3054792 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -307,13 +307,17 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) return 0; } - if (!access_ok(buf, size)) - return -EACCES; + if (!access_ok(buf, size)) { + ret = -EACCES; + goto out; + } - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_set(current, NULL, - 0, sizeof(struct user_i387_ia32_struct), - NULL, buf) != 0; + if (!static_cpu_has(X86_FEATURE_FPU)) { + ret = fpregs_soft_set(current, NULL, 0, + sizeof(struct user_i387_ia32_struct), + NULL, buf); + goto out; + } if (use_xsave()) { struct _fpx_sw_bytes fx_sw_user; @@ -396,7 +400,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) */ ret = __copy_from_user(&env, buf, sizeof(env)); if (ret) - goto err_out; + goto out; envp = &env; } @@ -426,7 +430,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx); if (ret) - goto err_out; + goto out; sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures, fx_only); @@ -446,7 +450,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) ret = __copy_from_user(&fpu->state.fxsave, buf_fx, state_size); if (ret) { ret = -EFAULT; - goto err_out; + goto out; } sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures, @@ -464,7 +468,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) } else { ret = __copy_from_user(&fpu->state.fsave, buf_fx, state_size); if (ret) - goto err_out; + goto out; fpregs_lock(); ret = copy_kernel_to_fregs_err(&fpu->state.fsave); @@ -475,7 +479,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) fpregs_deactivate(fpu); fpregs_unlock(); -err_out: +out: if (ret) fpu__clear_user_states(fpu); return ret; -- cgit v1.2.3