Skip to contentSkip to conversation

arm64: Don't read GMID_EL1 when MTE is disabled

PATCH Applied Fuad Tabba 3 participants 3 messages Aug 27 – Sep 3

Subsystems (2)
arm64 KVM arm64
lore
Share & tools
lore

Fuad Tabba

author reviewer
#0 lore raw

PATCH v5 1/1 arm64: Don't read GMID_EL1 when MTE is disabled

__cpuinfo_store_cpu() gates the GMID_EL1 read on the raw ID_AA64PFR1_EL1, so it reads the register even when the kernel has disabled MTE (CONFIG_ARM64_MTE=n or arm64.nomte). KVM sets HCR_EL2.TID5 in that case, and pKVM injects an UNDEF the host cannot handle:

  Internal error: Oops - Undefined instruction: 0000000002000000 [#1]  SMP
  pc : __cpuinfo_store_cpu+0xf4/0x264
  Kernel panic - not syncing: Attempted to kill the idle task!

Only pKVM reaches it, and only after a CPU is offlined and brought back
online: its CPU_ON relay sets the host HCR before the CPU enters EL1, while plain nVHE sets it at CPUHP_AP_KVM_ONLINE.

Gate the read on the CPU's own ID_AA64PFR1_EL1 with the command-line override applied, and on CONFIG_ARM64_MTE, which no register reflects. The boot CPU stores its registers before init_cpu_features() strips an unsafe override, so clamp against the hardware value here too.

Fixes f35abcbb8a084 ("KVM: arm64: Trap MTE access and discovery when MTE is disabled")
Cc [email protected]
Signed-off-by Fuad Tabba <[email protected]>

---

Notes:
Changes since v4:
- Gate on the ID_AA64PFR1_EL1 that __cpuinfo_store_cpu() has already read, clamping the override against it in cpufeature.c, rather than adding a __read_sysreg_by_encoding() caller in the header (Will). The register is not read a second time.
- Dropped Suzuki's override clamp, which this no longer needs. It is worth having on its own, so I'll post it separately with the Fixes:
tag and without the update_cpu_ftr_reg() hunk (Catalin).

Tested on QEMU under pKVM, with -machine virt,mte=on.

Offline/online CPU1 with arm64.nomte: unpatched panics in __cpuinfo_store_cpu(), patched does not. Same with CONFIG_ARM64_MTE=n and no override on the command line. And with id_aa64pfr1.mte=2 on a CPU without FEAT_MTE2, where the clamp keeps the gate false and init_cpu_ftr_reg() drops the override afterwards.

 arch/arm64/include/asm/cpu.h        |  1 +
 arch/arm64/include/asm/cpufeature.h |  7 ------
 arch/arm64/kernel/cpufeature.c      | 33 +++++++++++++++++++++++++----
 arch/arm64/kernel/cpuinfo.c         |  2 +-
 4 files changed, 31 insertions(+), 12 deletions(-)
arch/arm64/include/asm/cpu.h +1 -0
index 71493b760b839..3c008821219c2 100644
@@ -78,5 +78,6 @@ void __init cpuinfo_store_boot_cpu(void);
 void __init init_cpu_features(struct cpuinfo_arm64 *info);
 void update_cpu_features(int cpu, struct cpuinfo_arm64 *info,
 				 struct cpuinfo_arm64 *boot);
+bool gmid_el1_accessible(const struct cpuinfo_arm64 *info);
 
 #endif /* __ASM_CPU_H */
arch/arm64/include/asm/cpufeature.h +0 -7
index a57870fa96db5..f6a7200700ccf 100644
@@ -627,13 +627,6 @@ static inline bool id_aa64pfr1_mpamfrac(u64 pfr1)
 	return val > 0;
 }
 
-static inline bool id_aa64pfr1_mte(u64 pfr1)
-{
-	u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_EL1_MTE_SHIFT);
-
-	return val >= ID_AA64PFR1_EL1_MTE_MTE2;
-}
-
 void __init setup_boot_cpu_features(void);
 void __init setup_system_features(void);
 void __init setup_user_features(void);
arch/arm64/kernel/cpufeature.c +29 -4
index 9a22df0c5120f..103e70d683ca2 100644
@@ -1176,6 +1176,33 @@ static bool detect_ftr_has_mpam(void)
 	return id_aa64pfr0_mpam(pfr0) || id_aa64pfr1_mpamfrac(pfr1);
 }
 
+bool gmid_el1_accessible(const struct cpuinfo_arm64 *info)
+{
+	const struct arm64_ftr_bits *ftrp;
+	s64 mte, ovr;
+	u64 ftr_mask;
+
+	/* No ID register reflects CONFIG_ARM64_MTE. */
+	if (!IS_ENABLED(CONFIG_ARM64_MTE))
+		return false;
+
+	for (ftrp = ftr_id_aa64pfr1; ftrp->width; ftrp++) {
+		if (ftrp->shift == ID_AA64PFR1_EL1_MTE_SHIFT)
+			break;
+	}
+
+	ftr_mask = arm64_ftr_mask(ftrp);
+	mte = arm64_ftr_value(ftrp, info->reg_id_aa64pfr1);
+
+	/* The boot CPU runs before init_cpu_ftr_reg() strips unsafe overrides. */
+	if ((id_aa64pfr1_override.mask & ftr_mask) == ftr_mask) {
+		ovr = arm64_ftr_value(ftrp, id_aa64pfr1_override.val);
+		mte = arm64_ftr_safe_value(ftrp, ovr, mte);
+	}
+
+	return mte >= ID_AA64PFR1_EL1_MTE_MTE2;
+}
+
 void __init init_cpu_features(struct cpuinfo_arm64 *info)
 {
 	/* Before we start using the tables, make sure it is sorted */

@@ -1228,7 +1255,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 		init_cpu_ftr_reg(SYS_MPAMIDR_EL1, info->reg_mpamidr);
 	}
 
-	if (id_aa64pfr1_mte(info->reg_id_aa64pfr1))
+	if (gmid_el1_accessible(info))
 		init_cpu_ftr_reg(SYS_GMID_EL1, info->reg_gmid);
 }
 

@@ -1490,11 +1517,9 @@ void update_cpu_features(int cpu,
 	 * they read/write depends on the GMID_EL1.BS field. Check that the
 	 * value is the same on all CPUs.
 	 */
-	if (IS_ENABLED(CONFIG_ARM64_MTE) &&
-	    id_aa64pfr1_mte(info->reg_id_aa64pfr1)) {
+	if (gmid_el1_accessible(info))
 		taint |= check_update_ftr_reg(SYS_GMID_EL1, cpu,
 					      info->reg_gmid, boot->reg_gmid);
-	}
 
 	/*
 	 * If we don't have AArch32 at all then skip the checks entirely
arch/arm64/kernel/cpuinfo.c +1 -1
index d50e2a9b066b3..45c63f3d75c53 100644
@@ -502,7 +502,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	info->reg_id_aa64smfr0 = read_cpuid(ID_AA64SMFR0_EL1);
 	info->reg_id_aa64fpfr0 = read_cpuid(ID_AA64FPFR0_EL1);
 
-	if (id_aa64pfr1_mte(info->reg_id_aa64pfr1))
+	if (gmid_el1_accessible(info))
 		info->reg_gmid = read_cpuid(GMID_EL1);
 
 	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0))
Signature · 1 line
2.39.5
maintainer Reviewed-by on v5 1/1
#1 lore raw
Quoted 13 lines · Fuad Tabba
arch/arm64/kernel/cpufeature.c +13 -0
+bool gmid_el1_accessible(const struct cpuinfo_arm64 *info)
+{
+	const struct arm64_ftr_bits *ftrp;
+	s64 mte, ovr;
+	u64 ftr_mask;
+
+	/* No ID register reflects CONFIG_ARM64_MTE. */
+	if (!IS_ENABLED(CONFIG_ARM64_MTE))
+		return false;
+
+	for (ftrp = ftr_id_aa64pfr1; ftrp->width; ftrp++) {
+		if (ftrp->shift == ID_AA64PFR1_EL1_MTE_SHIFT)
+			break;

arch/arm64/kernel/cpufeature.c static bool detect_ftr_has_mpam(void) · line 1201

Quoted 10 lines
arch/arm64/kernel/cpufeature.c +10 -0
+	}
+
+	ftr_mask = arm64_ftr_mask(ftrp);
+	mte = arm64_ftr_value(ftrp, info->reg_id_aa64pfr1);
+
+	/* The boot CPU runs before init_cpu_ftr_reg() strips unsafe overrides. */
+	if ((id_aa64pfr1_override.mask & ftr_mask) == ftr_mask) {
+		ovr = arm64_ftr_value(ftrp, id_aa64pfr1_override.val);
+		mte = arm64_ftr_safe_value(ftrp, ovr, mte);
+	}

This works. Or we could cut a few lines and just do cpuid_feature_extract_unsigned_field() for mte and ovr and do a hard-coded min(mte, ovr) as we now it's lower-safe. I don't have a strong opinion either way, so for this patch:

Reviewed-by Catalin Marinas <[email protected]>
maintainer Applied
#2 lore raw
In reply to Fuad Tabba
Quoted 10 lines · Fuad Tabba

__cpuinfo_store_cpu() gates the GMID_EL1 read on the raw ID_AA64PFR1_EL1, so it reads the register even when the kernel has disabled MTE (CONFIG_ARM64_MTE=n or arm64.nomte). KVM sets HCR_EL2.TID5 in that case, and pKVM injects an UNDEF the host cannot handle:

  Internal error: Oops - Undefined instruction: 0000000002000000 [#1]  SMP
  pc : __cpuinfo_store_cpu+0xf4/0x264
  Kernel panic - not syncing: Attempted to kill the idle task!

[...]

Applied to arm64 (for-next/fixes), thanks!

[1/1] arm64: Don't read GMID_EL1 when MTE is disabled

      https://git.kernel.org/arm64/c/5445d6419962

Cheers,

Signature · 5 lines
Will

https://fixes.arm64.dev
https://next.arm64.dev
https://will.arm64.dev