From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Peter Zijlstra <peterz@infradead.org>,
Andrew Cooper <Andrew.Cooper3@citrix.com>,
Borislav Petkov <bp@suse.de>,
Josh Poimboeuf <jpoimboe@kernel.org>,
Sasha Levin <sashal@kernel.org>,
tglx@linutronix.de, mingo@redhat.com, bp@alien8.de,
dave.hansen@linux.intel.com, x86@kernel.org, puwen@hygon.cn,
pawan.kumar.gupta@linux.intel.com, adrian.hunter@intel.com,
alexander.shishkin@linux.intel.com,
ricardo.neri-calderon@linux.intel.com, brijesh.singh@amd.com,
ray.huang@amd.com, tony.luck@intel.com, kim.phillips@amd.com,
thomas.lendacky@amd.com, mario.limonciello@amd.com,
andrew.cooper3@citrix.com, jane.malalane@citrix.com
Subject: [PATCH AUTOSEL 5.18 23/54] x86/cpu/amd: Add Spectral Chicken
Date: Tue, 19 Jul 2022 21:10:00 -0400 [thread overview]
Message-ID: <20220720011031.1023305-23-sashal@kernel.org> (raw)
In-Reply-To: <20220720011031.1023305-1-sashal@kernel.org>
From: Peter Zijlstra <peterz@infradead.org>
[ Upstream commit d7caac991feeef1b871ee6988fd2c9725df09039 ]
Zen2 uarchs have an undocumented, unnamed, MSR that contains a chicken
bit for some speculation behaviour. It needs setting.
Note: very belatedly AMD released naming; it's now officially called
MSR_AMD64_DE_CFG2 and MSR_AMD64_DE_CFG2_SUPPRESS_NOBR_PRED_BIT
but shall remain the SPECTRAL CHICKEN.
Suggested-by: Andrew Cooper <Andrew.Cooper3@citrix.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
arch/x86/include/asm/msr-index.h | 3 +++
arch/x86/kernel/cpu/amd.c | 23 ++++++++++++++++++++++-
arch/x86/kernel/cpu/cpu.h | 2 ++
arch/x86/kernel/cpu/hygon.c | 6 ++++++
4 files changed, 33 insertions(+), 1 deletion(-)
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index bd283cdd963a..0ff05c7882b2 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -553,6 +553,9 @@
/* Fam 17h MSRs */
#define MSR_F17H_IRPERF 0xc00000e9
+#define MSR_ZEN2_SPECTRAL_CHICKEN 0xc00110e3
+#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT BIT_ULL(1)
+
/* Fam 16h MSRs */
#define MSR_F16H_L2I_PERF_CTL 0xc0010230
#define MSR_F16H_L2I_PERF_CTR 0xc0010231
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 0c0b09796ced..8cf0659c0521 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -862,6 +862,26 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
clear_rdrand_cpuid_bit(c);
}
+void init_spectral_chicken(struct cpuinfo_x86 *c)
+{
+ u64 value;
+
+ /*
+ * On Zen2 we offer this chicken (bit) on the altar of Speculation.
+ *
+ * This suppresses speculation from the middle of a basic block, i.e. it
+ * suppresses non-branch predictions.
+ *
+ * We use STIBP as a heuristic to filter out Zen2 from the rest of F17H
+ */
+ if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_AMD_STIBP)) {
+ if (!rdmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, &value)) {
+ value |= MSR_ZEN2_SPECTRAL_CHICKEN_BIT;
+ wrmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, value);
+ }
+ }
+}
+
static void init_amd_zn(struct cpuinfo_x86 *c)
{
set_cpu_cap(c, X86_FEATURE_ZEN);
@@ -907,7 +927,8 @@ static void init_amd(struct cpuinfo_x86 *c)
case 0x12: init_amd_ln(c); break;
case 0x15: init_amd_bd(c); break;
case 0x16: init_amd_jg(c); break;
- case 0x17: fallthrough;
+ case 0x17: init_spectral_chicken(c);
+ fallthrough;
case 0x19: init_amd_zn(c); break;
}
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 2a8e584fc991..7c9b5893c30a 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -61,6 +61,8 @@ static inline void tsx_init(void) { }
static inline void tsx_ap_init(void) { }
#endif /* CONFIG_CPU_SUP_INTEL */
+extern void init_spectral_chicken(struct cpuinfo_x86 *c);
+
extern void get_cpu_cap(struct cpuinfo_x86 *c);
extern void get_cpu_address_sizes(struct cpuinfo_x86 *c);
extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index 3fcdda4c1e11..21fd425088fe 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -302,6 +302,12 @@ static void init_hygon(struct cpuinfo_x86 *c)
/* get apicid instead of initial apic id from cpuid */
c->apicid = hard_smp_processor_id();
+ /*
+ * XXX someone from Hygon needs to confirm this DTRT
+ *
+ init_spectral_chicken(c);
+ */
+
set_cpu_cap(c, X86_FEATURE_ZEN);
set_cpu_cap(c, X86_FEATURE_CPB);
--
2.35.1
next prev parent reply other threads:[~2022-07-20 1:13 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-07-20 1:09 [PATCH AUTOSEL 5.18 01/54] Revert "evm: Fix memleak in init_desc" Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 02/54] ARM: rockchip: Add missing of_node_put() in rockchip_suspend_init() Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 03/54] x86/kvm/vmx: Make noinstr clean Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 04/54] x86/cpufeatures: Move RETPOLINE flags to word 11 Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 05/54] x86/retpoline: Cleanup some #ifdefery Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 06/54] x86/retpoline: Swizzle retpoline thunk Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 07/54] x86/retpoline: Use -mfunction-return Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 08/54] x86,objtool: Create .return_sites Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 09/54] x86/kvm: Fix SETcc emulation for return thunks Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 10/54] x86/vsyscall_emu/64: Don't use RET in vsyscall emulation Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 11/54] x86/sev: Avoid using __x86_return_thunk Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 12/54] objtool: Treat .text.__x86.* as noinstr Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 13/54] x86/bugs: Report AMD retbleed vulnerability Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 14/54] x86/bugs: Add AMD retbleed= boot parameter Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 15/54] x86/bugs: Enable STIBP for JMP2RET Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 16/54] x86/bugs: Keep a per-CPU IA32_SPEC_CTRL value Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 17/54] x86/bugs: Optimize SPEC_CTRL MSR writes Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 18/54] x86/bugs: Split spectre_v2_select_mitigation() and spectre_v2_user_select_mitigation() Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 19/54] x86/bugs: Report Intel retbleed vulnerability Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 20/54] objtool: Update Retpoline validation Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 21/54] x86/xen: Rename SYS* entry points Sasha Levin
2022-07-20 1:09 ` [PATCH AUTOSEL 5.18 22/54] x86/bugs: Do IBPB fallback check only once Sasha Levin
2022-07-20 1:10 ` Sasha Levin [this message]
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 24/54] x86/speculation: Fix RSB filling with CONFIG_RETPOLINE=n Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 25/54] KVM: VMX: Flatten __vmx_vcpu_run() Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 26/54] KVM: VMX: Convert launched argument to flags Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 27/54] KVM: VMX: Prevent guest RSB poisoning attacks with eIBRS Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 28/54] tty: Add N_CAN327 line discipline ID for ELM327 based CAN driver Sasha Levin
2022-07-25 5:35 ` Jiri Slaby
2022-07-25 7:00 ` Greg Kroah-Hartman
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 29/54] wifi: mac80211: check skb_shared in ieee80211_8023_xmit() Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 30/54] wifi: mac80211: do not wake queues on a vif that is being stopped Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 31/54] wifi: cfg80211: Allow P2P client interface to indicate port authorization Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 32/54] drm: panel-orientation-quirks: Add quirk for the Lenovo Yoga Tablet 2 830 Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 33/54] nilfs2: fix incorrect masking of permission flags for symlinks Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 34/54] xdp: Fix spurious packet loss in generic XDP TX path Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 35/54] drm/ssd130x: Fix pre-charge period setting Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 36/54] ASoC: ti: omap-mcbsp: duplicate sysfs error Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 37/54] ASoC: tlv320adcx140: Fix tx_mask check Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 38/54] ASoC: wcd9335: Use int array instead of bitmask for TX mixers Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 39/54] ASoC: wm5102: Fix event generation for output compensation Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 40/54] ASoC: wm8998: Fix event generation for input mux Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 41/54] ASoC: cs47l92: Fix event generation for OUT1 demux Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 42/54] ASoC: arizona: Update arizona_aif_cfg_changed to use RX_BCLK_RATE Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 43/54] ASoC: qdsp6: fix potential memory leak in q6apm_get_audioreach_graph() Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 44/54] ASoC: rt5640: Fix the wrong state of JD1 and JD2 Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 45/54] scsi: target: Fix WRITE_SAME No Data Buffer crash Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 46/54] x86/kexec: Disable RET on kexec Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 47/54] platform/x86: gigabyte-wmi: add support for B660I AORUS PRO DDR4 Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 48/54] platform/x86: asus-wmi: Add key mappings Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 49/54] platform/x86: intel_atomisp2_led: Also turn off the always-on camera LED on the Asus T100TAF Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 50/54] scsi: ufs: core: Fix missing clk change notification on host reset Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 51/54] scsi: pm80xx: Fix 'Unknown' max/min linkrate Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 52/54] scsi: pm80xx: Set stopped phy's linkrate to Disabled Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 53/54] KVM: nVMX: Always enable TSC scaling for L2 when it was enabled for L1 Sasha Levin
2022-07-20 1:10 ` [PATCH AUTOSEL 5.18 54/54] ubsan: disable UBSAN_DIV_ZERO for clang Sasha Levin
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=20220720011031.1023305-23-sashal@kernel.org \
--to=sashal@kernel.org \
--cc=Andrew.Cooper3@citrix.com \
--cc=adrian.hunter@intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=bp@alien8.de \
--cc=bp@suse.de \
--cc=brijesh.singh@amd.com \
--cc=dave.hansen@linux.intel.com \
--cc=jane.malalane@citrix.com \
--cc=jpoimboe@kernel.org \
--cc=kim.phillips@amd.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mario.limonciello@amd.com \
--cc=mingo@redhat.com \
--cc=pawan.kumar.gupta@linux.intel.com \
--cc=peterz@infradead.org \
--cc=puwen@hygon.cn \
--cc=ray.huang@amd.com \
--cc=ricardo.neri-calderon@linux.intel.com \
--cc=stable@vger.kernel.org \
--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