From mboxrd@z Thu Jan 1 00:00:00 1970 From: Greg Kroah-Hartman Subject: [PATCH 4.4 11/36] x86/syscall: Sanitize syscall table de-references under speculation fix Date: Fri, 9 Mar 2018 16:18:27 -0800 Message-ID: <20180310001807.821338686@linuxfoundation.org> References: <20180310001807.213987241@linuxfoundation.org> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Return-path: List-Post: List-Help: List-Unsubscribe: List-Subscribe: In-Reply-To: <20180310001807.213987241@linuxfoundation.org> To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Jan Beulich , Linus Torvalds , Dan Williams , Thomas Gleixner , linux-arch@vger.kernel.org, kernel-hardening@lists.openwall.com, Andy Lutomirski , alan@linux.intel.com, Jinpu Wang , Jiri Slaby List-Id: linux-arch.vger.kernel.org 4.4-stable review patch. If anyone has any objections, please let me know. ------------------ From: Jiri Slaby In 4.4.118, we have commit c8961332d6da (x86/syscall: Sanitize syscall table de-references under speculation), which is a backport of upstream commit 2fbd7af5af86. But it fixed only the C part of the upstream patch -- the IA32 sysentry. So it ommitted completely the assembly part -- the 64bit sysentry. Fix that in this patch by explicit array_index_mask_nospec written in assembly. The same was used in lib/getuser.S. However, to have "sbb" working properly, we have to switch from "cmp" against (NR_syscalls-1) to (NR_syscalls), otherwise the last syscall number would be "and"ed by 0. It is because the original "ja" relies on "CF" or "ZF", but we rely only on "CF" in "sbb". That means: switch to "jae" conditional jump too. Final note: use rcx for mask as this is exactly what is overwritten by the 4th syscall argument (r10) right after. Reported-by: Jan Beulich Cc: Linus Torvalds Cc: Dan Williams Cc: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: kernel-hardening@lists.openwall.com Cc: gregkh@linuxfoundation.org Cc: Andy Lutomirski Cc: alan@linux.intel.com Cc: Jinpu Wang Signed-off-by: Jiri Slaby Signed-off-by: Greg Kroah-Hartman --- arch/x86/entry/entry_64.S | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -178,12 +178,14 @@ GLOBAL(entry_SYSCALL_64_after_swapgs) jnz tracesys entry_SYSCALL_64_fastpath: #if __SYSCALL_MASK == ~0 - cmpq $__NR_syscall_max, %rax + cmpq $NR_syscalls, %rax #else andl $__SYSCALL_MASK, %eax - cmpl $__NR_syscall_max, %eax + cmpl $NR_syscalls, %eax #endif - ja 1f /* return -ENOSYS (already in pt_regs->ax) */ + jae 1f /* return -ENOSYS (already in pt_regs->ax) */ + sbb %rcx, %rcx /* array_index_mask_nospec() */ + and %rcx, %rax movq %r10, %rcx #ifdef CONFIG_RETPOLINE movq sys_call_table(, %rax, 8), %rax @@ -276,12 +278,14 @@ tracesys_phase2: RESTORE_C_REGS_EXCEPT_RAX RESTORE_EXTRA_REGS #if __SYSCALL_MASK == ~0 - cmpq $__NR_syscall_max, %rax + cmpq $NR_syscalls, %rax #else andl $__SYSCALL_MASK, %eax - cmpl $__NR_syscall_max, %eax + cmpl $NR_syscalls, %eax #endif - ja 1f /* return -ENOSYS (already in pt_regs->ax) */ + jae 1f /* return -ENOSYS (already in pt_regs->ax) */ + sbb %rcx, %rcx /* array_index_mask_nospec() */ + and %rcx, %rax movq %r10, %rcx /* fixup for C */ #ifdef CONFIG_RETPOLINE movq sys_call_table(, %rax, 8), %rax From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.linuxfoundation.org ([140.211.169.12]:38778 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932727AbeCJATl (ORCPT ); Fri, 9 Mar 2018 19:19:41 -0500 From: Greg Kroah-Hartman Subject: [PATCH 4.4 11/36] x86/syscall: Sanitize syscall table de-references under speculation fix Date: Fri, 9 Mar 2018 16:18:27 -0800 Message-ID: <20180310001807.821338686@linuxfoundation.org> In-Reply-To: <20180310001807.213987241@linuxfoundation.org> References: <20180310001807.213987241@linuxfoundation.org> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Sender: linux-arch-owner@vger.kernel.org List-ID: To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Jan Beulich , Linus Torvalds , Dan Williams , Thomas Gleixner , linux-arch@vger.kernel.org, kernel-hardening@lists.openwall.com, Andy Lutomirski , alan@linux.intel.com, Jinpu Wang , Jiri Slaby Message-ID: <20180310001827.FtjMTYSN-M0VykVPisddaPsP-ZsLkPYnYZkspBCT3rA@z> 4.4-stable review patch. If anyone has any objections, please let me know. ------------------ From: Jiri Slaby In 4.4.118, we have commit c8961332d6da (x86/syscall: Sanitize syscall table de-references under speculation), which is a backport of upstream commit 2fbd7af5af86. But it fixed only the C part of the upstream patch -- the IA32 sysentry. So it ommitted completely the assembly part -- the 64bit sysentry. Fix that in this patch by explicit array_index_mask_nospec written in assembly. The same was used in lib/getuser.S. However, to have "sbb" working properly, we have to switch from "cmp" against (NR_syscalls-1) to (NR_syscalls), otherwise the last syscall number would be "and"ed by 0. It is because the original "ja" relies on "CF" or "ZF", but we rely only on "CF" in "sbb". That means: switch to "jae" conditional jump too. Final note: use rcx for mask as this is exactly what is overwritten by the 4th syscall argument (r10) right after. Reported-by: Jan Beulich Cc: Linus Torvalds Cc: Dan Williams Cc: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: kernel-hardening@lists.openwall.com Cc: gregkh@linuxfoundation.org Cc: Andy Lutomirski Cc: alan@linux.intel.com Cc: Jinpu Wang Signed-off-by: Jiri Slaby Signed-off-by: Greg Kroah-Hartman --- arch/x86/entry/entry_64.S | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -178,12 +178,14 @@ GLOBAL(entry_SYSCALL_64_after_swapgs) jnz tracesys entry_SYSCALL_64_fastpath: #if __SYSCALL_MASK == ~0 - cmpq $__NR_syscall_max, %rax + cmpq $NR_syscalls, %rax #else andl $__SYSCALL_MASK, %eax - cmpl $__NR_syscall_max, %eax + cmpl $NR_syscalls, %eax #endif - ja 1f /* return -ENOSYS (already in pt_regs->ax) */ + jae 1f /* return -ENOSYS (already in pt_regs->ax) */ + sbb %rcx, %rcx /* array_index_mask_nospec() */ + and %rcx, %rax movq %r10, %rcx #ifdef CONFIG_RETPOLINE movq sys_call_table(, %rax, 8), %rax @@ -276,12 +278,14 @@ tracesys_phase2: RESTORE_C_REGS_EXCEPT_RAX RESTORE_EXTRA_REGS #if __SYSCALL_MASK == ~0 - cmpq $__NR_syscall_max, %rax + cmpq $NR_syscalls, %rax #else andl $__SYSCALL_MASK, %eax - cmpl $__NR_syscall_max, %eax + cmpl $NR_syscalls, %eax #endif - ja 1f /* return -ENOSYS (already in pt_regs->ax) */ + jae 1f /* return -ENOSYS (already in pt_regs->ax) */ + sbb %rcx, %rcx /* array_index_mask_nospec() */ + and %rcx, %rax movq %r10, %rcx /* fixup for C */ #ifdef CONFIG_RETPOLINE movq sys_call_table(, %rax, 8), %rax