From: Kim Phillips <kim.phillips@amd.com>
To: Peter Zijlstra <peterz@infradead.org>, Borislav Petkov <bp@alien8.de>
Cc: x86@kernel.org, Boris Ostrovsky <boris.ostrovsky@oracle.com>,
Dave Hansen <dave.hansen@linux.intel.com>,
"H. Peter Anvin" <hpa@zytor.com>, Ingo Molnar <mingo@redhat.com>,
Joao Martins <joao.m.martins@oracle.com>,
Jonathan Corbet <corbet@lwn.net>,
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Sean Christopherson <seanjc@google.com>,
Thomas Gleixner <tglx@linutronix.de>,
David Woodhouse <dwmw@amazon.co.uk>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Juergen Gross <jgross@suse.com>, Tony Luck <tony.luck@intel.com>,
Babu Moger <Babu.Moger@amd.com>,
Tom Lendacky <thomas.lendacky@amd.com>,
kvm@vger.kernel.org, linux-doc@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH 2/3] x86/speculation: Support Automatic IBRS
Date: Mon, 7 Nov 2022 16:39:02 -0600 [thread overview]
Message-ID: <d413c064-ee9b-5853-9cf1-544adde22c8a@amd.com> (raw)
In-Reply-To: <Y2ZEinL+wlIX+1Sn@hirez.programming.kicks-ass.net>
On 11/5/22 6:10 AM, Peter Zijlstra wrote:
> On Fri, Nov 04, 2022 at 10:52:13PM +0100, Borislav Petkov wrote:
>> On Fri, Nov 04, 2022 at 04:36:50PM -0500, Kim Phillips wrote:
>>> - Allow for spectre_v2=autoibrs in the kernel command line,
>>> reverting to auto-selection if the feature isn't available.
>>
>> Why?
>>
>> What the whole logic here should do is enable autoibrs when detected
>> automatically, without the need for the user to even select it as it is
>> the superior mitigation.
>
> Well; perhaps the whole autoibrs thing should be mapped to the existing
> eIBRS options. AFAICT this is the same thing under a new name, no need
> to invent yet more options. bugs.c is quite insane enough already.
I've started a version that has AUTOIBRS reuse SPECTRE_V2_EIBRS
spectre_v2_mitigation enum, but, so far, it's change to bugs.c
looks bigger: 58 lines changed vs. 34 (see below).
Let me know if you want me to send it as a part of a v2 submission
after I take care of the kvm CPUID review.
Thanks,
Kim
Autoibrs-as-eibrs diff:
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 2e9dd8823244..3ab90f23e7f7 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -442,7 +442,6 @@ enum spectre_v2_mitigation {
SPECTRE_V2_EIBRS_RETPOLINE,
SPECTRE_V2_EIBRS_LFENCE,
SPECTRE_V2_IBRS,
- SPECTRE_V2_AUTO_IBRS,
};
/* The indirect branch speculation control variants */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 31e5af78baa0..ccfd8fb12095 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1005,6 +1005,7 @@ static inline const char *spectre_v2_module_string(void) { return ""; }
#endif
#define SPECTRE_V2_LFENCE_MSG "WARNING: LFENCE mitigation is not recommended for this CPU, data leaks possible!\n"
+#define SPECTRE_V2_EIBRS_AMD_MSG "WARNING: AutoIBRS does not need additional RETPOLINE/LFENCE mitigations, not doing them\n"
#define SPECTRE_V2_EIBRS_EBPF_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS on, data leaks possible via Spectre v2 BHB attacks!\n"
#define SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS+LFENCE mitigation and SMT, data leaks possible via Spectre v2 BHB attacks!\n"
#define SPECTRE_V2_IBRS_PERF_MSG "WARNING: IBRS mitigation selected on Enhanced IBRS CPU, this may cause unnecessary performance loss\n"
@@ -1125,7 +1126,7 @@ spectre_v2_parse_user_cmdline(void)
return SPECTRE_V2_USER_CMD_AUTO;
}
-/* Checks for Intel IBRS versions */
+/* Checks for IBRS versions */
static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode)
{
return mode == SPECTRE_V2_IBRS ||
@@ -1201,7 +1202,8 @@ spectre_v2_user_select_mitigation(void)
*/
if (!boot_cpu_has(X86_FEATURE_STIBP) ||
!smt_possible ||
- spectre_v2_in_ibrs_mode(spectre_v2_enabled))
+ (spectre_v2_in_ibrs_mode(spectre_v2_enabled) &&
+ !boot_cpu_has(X86_FEATURE_AUTOIBRS)))
return;
/*
@@ -1231,11 +1233,10 @@ static const char * const spectre_v2_strings[] = {
[SPECTRE_V2_NONE] = "Vulnerable",
[SPECTRE_V2_RETPOLINE] = "Mitigation: Retpolines",
[SPECTRE_V2_LFENCE] = "Mitigation: LFENCE",
- [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced IBRS",
+ [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced / Automatic IBRS",
[SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced IBRS + LFENCE",
[SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced IBRS + Retpolines",
[SPECTRE_V2_IBRS] = "Mitigation: IBRS",
- [SPECTRE_V2_AUTO_IBRS] = "Mitigation: Automatic IBRS",
};
static const struct {
@@ -1250,9 +1251,9 @@ static const struct {
{ "retpoline,lfence", SPECTRE_V2_CMD_RETPOLINE_LFENCE, false },
{ "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false },
{ "eibrs", SPECTRE_V2_CMD_EIBRS, false },
+ { "autoibrs", SPECTRE_V2_CMD_EIBRS, false },
{ "eibrs,lfence", SPECTRE_V2_CMD_EIBRS_LFENCE, false },
{ "eibrs,retpoline", SPECTRE_V2_CMD_EIBRS_RETPOLINE, false },
- { "autoibrs", SPECTRE_V2_CMD_AUTOIBRS, false },
{ "auto", SPECTRE_V2_CMD_AUTO, false },
{ "ibrs", SPECTRE_V2_CMD_IBRS, false },
};
@@ -1303,15 +1304,17 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
if ((cmd == SPECTRE_V2_CMD_EIBRS ||
cmd == SPECTRE_V2_CMD_EIBRS_LFENCE ||
cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) &&
- !boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) {
- pr_err("%s selected but CPU doesn't have eIBRS. Switching to AUTO select\n",
+ (!boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) ||
+ !boot_cpu_has(X86_FEATURE_AUTOIBRS))) {
+ pr_err("%s selected but CPU doesn't have Enhanced or Automatic IBRS. Switching to AUTO select\n",
mitigation_options[i].option);
return SPECTRE_V2_CMD_AUTO;
}
- if (cmd == SPECTRE_V2_CMD_AUTOIBRS &&
- !boot_cpu_has(X86_FEATURE_AUTOIBRS)) {
- pr_err("%s selected but CPU doesn't have AMD Automatic IBRS. Switching to AUTO select\n",
+ if ((cmd == SPECTRE_V2_CMD_EIBRS_LFENCE ||
+ cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) &&
+ boot_cpu_has(X86_FEATURE_AUTOIBRS)) {
+ pr_err("%s selected but AMD Automatic IBRS doesn't need extra retpoline mitigations. Switching to AUTO select\n",
mitigation_options[i].option);
return SPECTRE_V2_CMD_AUTO;
}
@@ -1403,7 +1406,6 @@ static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_
*/
switch (mode) {
case SPECTRE_V2_NONE:
- case SPECTRE_V2_AUTO_IBRS:
return;
case SPECTRE_V2_EIBRS_LFENCE:
@@ -1447,12 +1449,8 @@ static void __init spectre_v2_select_mitigation(void)
case SPECTRE_V2_CMD_FORCE:
case SPECTRE_V2_CMD_AUTO:
- if (boot_cpu_has(X86_FEATURE_AUTOIBRS)) {
- mode = SPECTRE_V2_AUTO_IBRS;
- break;
- }
-
- if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) {
+ if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) ||
+ boot_cpu_has(X86_FEATURE_AUTOIBRS)) {
mode = SPECTRE_V2_EIBRS;
break;
}
@@ -1488,19 +1486,24 @@ static void __init spectre_v2_select_mitigation(void)
break;
case SPECTRE_V2_CMD_EIBRS:
+ case SPECTRE_V2_CMD_AUTOIBRS:
mode = SPECTRE_V2_EIBRS;
break;
case SPECTRE_V2_CMD_EIBRS_LFENCE:
- mode = SPECTRE_V2_EIBRS_LFENCE;
+ if (boot_cpu_has(X86_FEATURE_AUTOIBRS)) {
+ pr_err(SPECTRE_V2_EIBRS_AMD_MSG);
+ mode = SPECTRE_V2_EIBRS;
+ } else
+ mode = SPECTRE_V2_EIBRS_LFENCE;
break;
case SPECTRE_V2_CMD_EIBRS_RETPOLINE:
- mode = SPECTRE_V2_EIBRS_RETPOLINE;
- break;
-
- case SPECTRE_V2_CMD_AUTOIBRS:
- mode = SPECTRE_V2_AUTO_IBRS;
+ if (boot_cpu_has(X86_FEATURE_AUTOIBRS)) {
+ pr_err(SPECTRE_V2_EIBRS_AMD_MSG);
+ mode = SPECTRE_V2_EIBRS;
+ } else
+ mode = SPECTRE_V2_EIBRS_RETPOLINE;
break;
}
@@ -1508,8 +1511,13 @@ static void __init spectre_v2_select_mitigation(void)
pr_err(SPECTRE_V2_EIBRS_EBPF_MSG);
if (spectre_v2_in_ibrs_mode(mode)) {
- x86_spec_ctrl_base |= SPEC_CTRL_IBRS;
- write_spec_ctrl_current(x86_spec_ctrl_base, true);
+ if (boot_cpu_has(X86_FEATURE_AUTOIBRS)) {
+ rdmsrl(MSR_EFER, efer);
+ wrmsrl(MSR_EFER, efer | EFER_AUTOIBRS);
+ } else {
+ x86_spec_ctrl_base |= SPEC_CTRL_IBRS;
+ write_spec_ctrl_current(x86_spec_ctrl_base, true);
+ }
}
switch (mode) {
@@ -1517,11 +1525,6 @@ static void __init spectre_v2_select_mitigation(void)
case SPECTRE_V2_EIBRS:
break;
- case SPECTRE_V2_AUTO_IBRS:
- rdmsrl(MSR_EFER, efer);
- wrmsrl(MSR_EFER, efer | EFER_AUTOIBRS);
- break;
-
case SPECTRE_V2_IBRS:
setup_force_cpu_cap(X86_FEATURE_KERNEL_IBRS);
if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED))
@@ -1616,8 +1619,8 @@ static void __init spectre_v2_select_mitigation(void)
pr_info("Enabling Speculation Barrier for firmware calls\n");
}
- } else if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_ibrs_mode(mode) &&
- mode != SPECTRE_V2_AUTO_IBRS) {
+ } else if ((boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_ibrs_mode(mode)) ||
+ (boot_cpu_has(X86_FEATURE_AUTOIBRS) && !spectre_v2_in_ibrs_mode(mode))) {
setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
pr_info("Enabling Restricted Speculation for firmware calls\n");
}
@@ -2353,7 +2356,8 @@ static ssize_t mmio_stale_data_show_state(char *buf)
static char *stibp_state(void)
{
- if (spectre_v2_in_ibrs_mode(spectre_v2_enabled))
+ if (spectre_v2_in_ibrs_mode(spectre_v2_enabled) &&
+ !boot_cpu_has(X86_FEATURE_AUTOIBRS))
return "";
switch (spectre_v2_user_stibp) {
next prev parent reply other threads:[~2022-11-07 22:39 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-11-04 21:36 [PATCH 0/3] x86/speculation: Support Automatic IBRS Kim Phillips
2022-11-04 21:36 ` [PATCH 1/3] x86/cpufeatures: Add support for cpuid leaf 80000021/EAX (FeatureExt2Eax) Kim Phillips
2022-11-04 21:48 ` Borislav Petkov
2022-11-15 23:10 ` Kim Phillips
2022-11-16 11:59 ` Borislav Petkov
2022-11-16 20:22 ` Sean Christopherson
2022-11-16 21:01 ` Borislav Petkov
2022-11-04 21:36 ` [PATCH 2/3] x86/speculation: Support Automatic IBRS Kim Phillips
2022-11-04 21:52 ` Borislav Petkov
2022-11-05 11:10 ` Peter Zijlstra
2022-11-07 22:39 ` Kim Phillips [this message]
2022-11-07 23:41 ` Dave Hansen
2022-11-08 8:06 ` Peter Zijlstra
2022-11-11 12:09 ` Borislav Petkov
2022-11-11 12:40 ` Thadeu Lima de Souza Cascardo
2022-11-12 0:46 ` Kim Phillips
2022-11-12 0:54 ` Jim Mattson
2022-11-05 11:39 ` David Laight
2022-11-07 22:40 ` Kim Phillips
2022-11-04 21:36 ` [PATCH 3/3] x86/speculation: Support Automatic IBRS under virtualization Kim Phillips
2022-11-04 22:00 ` Jim Mattson
2022-11-07 22:29 ` Kim Phillips
2022-11-07 22:42 ` Jim Mattson
2022-11-08 22:48 ` Kim Phillips
2022-11-08 22:59 ` Jim Mattson
2022-11-06 8:38 ` Paolo Bonzini
2022-11-04 22:06 ` [PATCH 0/3] x86/speculation: Support Automatic IBRS Dave Hansen
2022-11-07 22:43 ` Kim Phillips
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=d413c064-ee9b-5853-9cf1-544adde22c8a@amd.com \
--to=kim.phillips@amd.com \
--cc=Babu.Moger@amd.com \
--cc=boris.ostrovsky@oracle.com \
--cc=bp@alien8.de \
--cc=corbet@lwn.net \
--cc=dave.hansen@linux.intel.com \
--cc=dwmw@amazon.co.uk \
--cc=gregkh@linuxfoundation.org \
--cc=hpa@zytor.com \
--cc=jgross@suse.com \
--cc=joao.m.martins@oracle.com \
--cc=konrad.wilk@oracle.com \
--cc=kvm@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=seanjc@google.com \
--cc=tglx@linutronix.de \
--cc=thomas.lendacky@amd.com \
--cc=tony.luck@intel.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox