From:   Usama Arif <usama.arif@bytedance.com>
To:     dwmw2@infradead.org, tglx@linutronix.de, arjan@linux.intel.com
Cc:     mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com,
        hpa@zytor.com, x86@kernel.org, pbonzini@redhat.com,
        paulmck@kernel.org, linux-kernel@vger.kernel.org,
        kvm@vger.kernel.org, rcu@vger.kernel.org, mimoja@mimoja.de,
        hewenliang4@huawei.com, thomas.lendacky@amd.com, seanjc@google.com,
        pmenzel@molgen.mpg.de, fam.zheng@bytedance.com,
        punit.agrawal@bytedance.com, simon.evans@bytedance.com,
        liangma@liangbit.com, David Woodhouse <dwmw@amazon.co.uk>
Subject: [PATCH v6 07/11] x86/smpboot: Disable parallel boot for AMD CPUs
Date:   Thu,  2 Feb 2023 21:56:21 +0000
Message-Id: <20230202215625.3248306-8-usama.arif@bytedance.com>
In-Reply-To: <20230202215625.3248306-1-usama.arif@bytedance.com>
References: <20230202215625.3248306-1-usama.arif@bytedance.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: David Woodhouse <dwmw@amazon.co.uk>

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
---
 arch/x86/include/asm/cpufeatures.h |  1 +
 arch/x86/kernel/cpu/amd.c          | 11 +++++++++++
 arch/x86/kernel/smpboot.c          | 13 +++++++++++--
 3 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 61012476d66e..ed7f32354edc 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -466,5 +466,6 @@
 #define X86_BUG_MMIO_UNKNOWN		X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */
 #define X86_BUG_RETBLEED		X86_BUG(27) /* CPU is affected by RETBleed */
 #define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
+#define X86_BUG_NO_PARALLEL_BRINGUP	X86_BUG(29) /* CPU has hardware issues with parallel AP bringup */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index f769d6d08b43..19b5c8342d7e 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -941,6 +941,17 @@ static void init_amd(struct cpuinfo_x86 *c)
 	case 0x19: init_amd_zn(c); break;
 	}
 
+	/*
+	 * Various AMD CPUs appear to not to cope with APs being brought up
+	 * in parallel. In debugging, the AP doesn't even seem to reach an
+	 * outb to port 0x3f8 right at the top of the startup trampoline.
+	 * We don't *think* there are any remaining software issues which
+	 * may contribute to this, although it's possible. So far, attempts
+	 * to get AMD to investigate this have been to no avail. So just
+	 * disable parallel bring up for all AMD CPUs for now.
+	 */
+	set_cpu_bug(c, X86_BUG_NO_PARALLEL_BRINGUP);
+
 	/*
 	 * Enable workaround for FXSAVE leak on CPUs
 	 * without a XSaveErPtr feature
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 741da8d306a4..656897b055f5 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1534,13 +1534,22 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	 * We can do 64-bit AP bringup in parallel if the CPU reports its
 	 * APIC ID in CPUID leaf 0x0B. Otherwise it's too hard. And not
 	 * for SEV-ES guests because they can't use CPUID that early.
-	 * Also, some AMD CPUs crash when doing parallel cpu bringup, disable
-	 * it for all AMD CPUs to be on the safe side.
 	 */
 	if (IS_ENABLED(CONFIG_X86_32) || boot_cpu_data.cpuid_level < 0x0B ||
 	    cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
 		do_parallel_bringup = false;
 
+	/*
+	 * Various AMD CPUs appear not to cope with APs being brought up
+	 * in parallel, so just disable parallel bring up for all AMD CPUs
+	 * for now.
+	 */
+	if (do_parallel_bringup &&
+	    boot_cpu_has_bug(X86_BUG_NO_PARALLEL_BRINGUP)) {
+		pr_info("Disabling parallel bringup due to CPU bugs\n");
+		do_parallel_bringup = false;
+	}
+
 	snp_set_wakeup_secondary_cpu();
 }
 
-- 
2.25.1