From 2641f08bb7fc63a636a2b18173221d7040a3512e Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 11 Jan 2018 21:46:28 +0000 Subject: x86/retpoline/entry: Convert entry assembler indirect jumps Convert indirect jumps in core 32/64bit entry assembler code to use non-speculative sequences when CONFIG_RETPOLINE is enabled. Don't use CALL_NOSPEC in entry_SYSCALL_64_fastpath because the return address after the 'call' instruction must be *precisely* at the .Lentry_SYSCALL_64_after_fastpath label for stub_ptregs_64 to work, and the use of alternatives will mess that up unless we play horrid games to prepend with NOPs and make the variants the same length. It's not worth it; in the case where we ALTERNATIVE out the retpoline, the first instruction at __x86.indirect_thunk.rax is going to be a bare jmp *%rax anyway. Signed-off-by: David Woodhouse Signed-off-by: Thomas Gleixner Acked-by: Ingo Molnar Acked-by: Arjan van de Ven Cc: gnomes@lxorguk.ukuu.org.uk Cc: Rik van Riel Cc: Andi Kleen Cc: Josh Poimboeuf Cc: thomas.lendacky@amd.com Cc: Peter Zijlstra Cc: Linus Torvalds Cc: Jiri Kosina Cc: Andy Lutomirski Cc: Dave Hansen Cc: Kees Cook Cc: Tim Chen Cc: Greg Kroah-Hartman Cc: Paul Turner Link: https://lkml.kernel.org/r/1515707194-20531-7-git-send-email-dwmw@amazon.co.uk --- arch/x86/entry/entry_32.S | 5 +++-- arch/x86/entry/entry_64.S | 12 +++++++++--- 2 files changed, 12 insertions(+), 5 deletions(-) (limited to 'arch/x86/entry') diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index ace8f321a5a1..a1f28a54f23a 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -44,6 +44,7 @@ #include #include #include +#include .section .entry.text, "ax" @@ -290,7 +291,7 @@ ENTRY(ret_from_fork) /* kernel thread */ 1: movl %edi, %eax - call *%ebx + CALL_NOSPEC %ebx /* * A kernel thread is allowed to return here after successfully * calling do_execve(). Exit to userspace to complete the execve() @@ -919,7 +920,7 @@ common_exception: movl %ecx, %es TRACE_IRQS_OFF movl %esp, %eax # pt_regs pointer - call *%edi + CALL_NOSPEC %edi jmp ret_from_exception END(common_exception) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index ed31d00dc5ee..59874bc1aed2 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -37,6 +37,7 @@ #include #include #include +#include #include #include "calling.h" @@ -187,7 +188,7 @@ ENTRY(entry_SYSCALL_64_trampoline) */ pushq %rdi movq $entry_SYSCALL_64_stage2, %rdi - jmp *%rdi + JMP_NOSPEC %rdi END(entry_SYSCALL_64_trampoline) .popsection @@ -266,7 +267,12 @@ entry_SYSCALL_64_fastpath: * It might end up jumping to the slow path. If it jumps, RAX * and all argument registers are clobbered. */ +#ifdef CONFIG_RETPOLINE + movq sys_call_table(, %rax, 8), %rax + call __x86_indirect_thunk_rax +#else call *sys_call_table(, %rax, 8) +#endif .Lentry_SYSCALL_64_after_fastpath_call: movq %rax, RAX(%rsp) @@ -438,7 +444,7 @@ ENTRY(stub_ptregs_64) jmp entry_SYSCALL64_slow_path 1: - jmp *%rax /* Called from C */ + JMP_NOSPEC %rax /* Called from C */ END(stub_ptregs_64) .macro ptregs_stub func @@ -517,7 +523,7 @@ ENTRY(ret_from_fork) 1: /* kernel thread */ movq %r12, %rdi - call *%rbx + CALL_NOSPEC %rbx /* * A kernel thread is allowed to return here after successfully * calling do_execve(). Exit to userspace to complete the execve() -- cgit v1.2.3 From f10ee3dcc9f0aba92a5c4c064628be5200765dc2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 14 Jan 2018 00:23:57 +0100 Subject: x86/pti: Fix !PCID and sanitize defines The switch to the user space page tables in the low level ASM code sets unconditionally bit 12 and bit 11 of CR3. Bit 12 is switching the base address of the page directory to the user part, bit 11 is switching the PCID to the PCID associated with the user page tables. This fails on a machine which lacks PCID support because bit 11 is set in CR3. Bit 11 is reserved when PCID is inactive. While the Intel SDM claims that the reserved bits are ignored when PCID is disabled, the AMD APM states that they should be cleared. This went unnoticed as the AMD APM was not checked when the code was developed and reviewed and test systems with Intel CPUs never failed to boot. The report is against a Centos 6 host where the guest fails to boot, so it's not yet clear whether this is a virt issue or can happen on real hardware too, but thats irrelevant as the AMD APM clearly ask for clearing the reserved bits. Make sure that on non PCID machines bit 11 is not set by the page table switching code. Andy suggested to rename the related bits and masks so they are clearly describing what they should be used for, which is done as well for clarity. That split could have been done with alternatives but the macro hell is horrible and ugly. This can be done on top if someone cares to remove the extra orq. For now it's a straight forward fix. Fixes: 6fd166aae78c ("x86/mm: Use/Fix PCID to optimize user/kernel switches") Reported-by: Laura Abbott Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: stable Cc: Borislav Petkov Cc: Andy Lutomirski Cc: Willy Tarreau Cc: David Woodhouse Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1801140009150.2371@nanos --- arch/x86/entry/calling.h | 36 ++++++++++++++++++---------------- arch/x86/include/asm/processor-flags.h | 2 +- arch/x86/include/asm/tlbflush.h | 6 +++--- 3 files changed, 23 insertions(+), 21 deletions(-) (limited to 'arch/x86/entry') diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 45a63e00a6af..3f48f695d5e6 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -198,8 +198,11 @@ For 32-bit we have the following conventions - kernel is built with * PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two * halves: */ -#define PTI_SWITCH_PGTABLES_MASK (1<= (1 << X86_CR3_PTI_SWITCH_BIT)); + BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_PCID_USER_BIT)); /* * The ASID being passed in here should have respected the * MAX_ASID_AVAILABLE and thus never have the switch bit set. */ - VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_SWITCH_BIT)); + VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_PCID_USER_BIT)); #endif /* * The dynamically-assigned ASIDs that get passed in are small @@ -112,7 +112,7 @@ static inline u16 user_pcid(u16 asid) { u16 ret = kern_pcid(asid); #ifdef CONFIG_PAGE_TABLE_ISOLATION - ret |= 1 << X86_CR3_PTI_SWITCH_BIT; + ret |= 1 << X86_CR3_PTI_PCID_USER_BIT; #endif return ret; } -- cgit v1.2.3