From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Google-Smtp-Source: AH8x226ir+yztWMf2SSdZRE7FUaj0QS/w7mjriNjyBlS1N4uexrL2j/r5ii3FwjekNKb89GJlMvI ARC-Seal: i=1; a=rsa-sha256; t=1516644272; cv=none; d=google.com; s=arc-20160816; b=uHOmDU5m3SBoXbO7FTtmKTX+7L9sG8irwF1T4tQCOz3JmrAI6Hzj7vz/K6oLeWv9gQ Z259G6hfbrrd+5noqO9R1Iw+YDk4Ks3hY9eN0gNKMUgY/I9hUjflXqar5dyENV1NiFou NDpKBwrHCtKMfqXhfx992OELfZrRaBcx8yuCNWdXM3BEaGxpQBJ/wxJlb83F7Kj9pwNp bKGw4+b4xPpBJOB6KiD3kzhc8UefDZqkFOYUb5uwld9OGuwNwVeRVp+rnvfbxUIYsFKt yT6tP2y2yo8IVhbSzFYXvEbsvvlthHUIp5sHWG+Uxkrt0G1FOVSdSmdwxACPkRISAg0C B6sw== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=message-id:date:subject:cc:to:from:dmarc-filter :arc-authentication-results; bh=GaKq8/5CQYB3wlk9QNpdHo3deAJaJj5HYfWrfq9hvAU=; b=WWxgWMQjNGWk8/FU6kt+udwziKH0oTL8ybmXrVR7uyy0h62WJu14cIW/ZagqwcAP0R 5xn7V1vlNkoar9U5L8z7naWrYqfMVAmOg9A5oIa1nzK7oBLiLxP7OKeWzdSba4A3CsTw 1geXZUF8rHrFtFbg/a3jl/YWrbN7uLbgofqJF0zj7LgDVPjd6p3B98/acZy0ChyrRoHa GgcCsX5Fbzk0lRFcOw0H9LWGdLOaXgXaLTP3BUXoXgzCuVpl39Kau7YV1GumOvdXdcMd a6ggWM+JPj4C64u09m/sKXrsl8NPyPaCRPQ1cH3KGMAkXzJlQqrovhaisecC73C0+/99 qS9g== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: best guess record for domain of luto@kernel.org designates 198.145.29.99 as permitted sender) smtp.mailfrom=luto@kernel.org Authentication-Results: mx.google.com; spf=pass (google.com: best guess record for domain of luto@kernel.org designates 198.145.29.99 as permitted sender) smtp.mailfrom=luto@kernel.org DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 5F16521781 Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.org Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=luto@kernel.org From: Andy Lutomirski To: x86@kernel.org, LKML Cc: Linus Torvalds , Greg Kroah-Hartman , Alan Cox , Jann Horn , Samuel Neves , Dan Williams , Kernel Hardening , Borislav Petkov , Andy Lutomirski Subject: [PATCH] x86/retpoline/entry: Disable the entire SYSCALL64 fast path with retpolines on Date: Mon, 22 Jan 2018 10:04:29 -0800 Message-Id: <503224b776b9513885453756e44bab235221124e.1516644136.git.luto@kernel.org> X-Mailer: git-send-email 2.13.6 X-getmail-retrieved-from-mailbox: INBOX X-GMAIL-THRID: =?utf-8?q?1590316784671066673?= X-GMAIL-MSGID: =?utf-8?q?1590316784671066673?= X-Mailing-List: linux-kernel@vger.kernel.org List-ID: The existing retpoline code carefully and awkwardly retpolinifies the SYSCALL64 slow path. This stops the fast path from being particularly fast, and it's IMO rather messy. Instead, just bypass the fast path entirely if retpolines are on. This seems to be a speedup on a "minimal" retpoline kernel, mainly because do_syscall_64() ends up calling the syscall handler without using a slow retpoline thunk. As an added benefit, we won't need to apply further Spectre mitigations to the fast path. The current fast path spectre mitigations may have a hole: if the syscall nr is out of bounds, it is plausible that the CPU would mispredict the bounds check and, load a bogus function pointer, and speculatively execute it right though the retpoline. If this is indeed a problem, we need to fix it in the slow paths anyway, but with this patch applied, we can at least leave the fast path alone. Cleans-up: 2641f08bb7fc ("x86/retpoline/entry: Convert entry assembler indirect jumps") Signed-off-by: Andy Lutomirski --- arch/x86/entry/entry_64.S | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 4f8e1d35a97c..b915bad58754 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -245,6 +245,9 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) * If we need to do entry work or if we guess we'll need to do * exit work, go straight to the slow path. */ +#ifdef CONFIG_RETPOLINE + ALTERNATIVE "", "jmp entry_SYSCALL64_slow_path", X86_FEATURE_RETPOLINE +#endif movq PER_CPU_VAR(current_task), %r11 testl $_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) jnz entry_SYSCALL64_slow_path @@ -270,13 +273,11 @@ entry_SYSCALL_64_fastpath: * This call instruction is handled specially in stub_ptregs_64. * It might end up jumping to the slow path. If it jumps, RAX * and all argument registers are clobbered. + * + * NB: no retpoline needed -- we don't execute this code with + * retpolines enabled. */ -#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) @@ -431,6 +432,9 @@ ENTRY(stub_ptregs_64) * which we achieve by trying again on the slow path. If we are on * the slow path, the extra regs are already saved. * + * This code is unreachable (even via mispredicted conditional branches) + * if we're using retpolines. + * * RAX stores a pointer to the C function implementing the syscall. * IRQs are on. */ @@ -448,12 +452,19 @@ ENTRY(stub_ptregs_64) jmp entry_SYSCALL64_slow_path 1: - JMP_NOSPEC %rax /* Called from C */ + jmp *%rax /* Called from C */ END(stub_ptregs_64) .macro ptregs_stub func ENTRY(ptregs_\func) UNWIND_HINT_FUNC +#ifdef CONFIG_RETPOLINE + /* + * If retpolines are enabled, we don't use the syscall fast path, + * so just jump straight to the syscall body. + */ + ALTERNATIVE "", __stringify(jmp \func), X86_FEATURE_RETPOLINE +#endif leaq \func(%rip), %rax jmp stub_ptregs_64 END(ptregs_\func) -- 2.13.6