[PATCH 5.15.y 00/14] arm64: errata: Speculative SSBS workaround

List overview All Threads
Download

newer

older

[PATCH 5.10.y 00/13] arm64:...

FAILED: patch "[PATCH] selftests:...

Mark Rutland

9 Aug 2024 9 Aug '24

10:09 a.m.

Hi,

This series is a v5.15-only backport (based on v5.15.164) of the upstream workaround for SSBS errata on Arm Ltd CPUs, as affected parts are likely to be used with stable kernels. This does not apply to earlier stable trees, which will receive a separate backport.

The errata mean that an MSR to the SSBS special-purpose register does not affect subsequent speculative instructions, permitting speculative store bypassing for a window of time.

The upstream support was original posted as:

* https://lore.kernel.org/linux-arm-kernel/20240508081400.235362-1-mark.rutlan... "arm64: errata: Add workaround for Arm errata 3194386 and 3312417" Present in v6.10

* https://lore.kernel.org/linux-arm-kernel/20240603111812.1514101-1-mark.rutla... "arm64: errata: Expand speculative SSBS workaround" Present in v6.11-rc1

* https://lore.kernel.org/linux-arm-kernel/20240801101803.1982459-1-mark.rutla... "arm64: errata: Expand speculative SSBS workaround (again)" Present in v6.11-rc2

This backport applies the patches which are not present in v5.15.y, and as prerequisites backports HWCAP detection based on user-visible id register values, the addition of Neoverse-V2 MIDR values, and the restoration of the spec_bar() macro.

I have tested the backport (when applied to v5.15.164), ensuring that the detection logic works and that the HWCAP and string in /proc/cpuinfo are both hidden when the relevant errata are detected.

Mark.

Besar Wicaksono (1): arm64: Add Neoverse-V2 part

James Morse (1): arm64: cpufeature: Force HWCAP to be based on the sysreg visible to user-space

Mark Rutland (12): arm64: barrier: Restore spec_bar() macro arm64: cputype: Add Cortex-X4 definitions arm64: cputype: Add Neoverse-V3 definitions arm64: errata: Add workaround for Arm errata 3194386 and 3312417 arm64: cputype: Add Cortex-X3 definitions arm64: cputype: Add Cortex-A720 definitions arm64: cputype: Add Cortex-X925 definitions arm64: errata: Unify speculative SSBS errata logic arm64: errata: Expand speculative SSBS workaround arm64: cputype: Add Cortex-X1C definitions arm64: cputype: Add Cortex-A725 definitions arm64: errata: Expand speculative SSBS workaround (again)

Documentation/arm64/silicon-errata.rst | 36 +++++++++++++++++++ arch/arm64/Kconfig | 38 ++++++++++++++++++++ arch/arm64/include/asm/barrier.h | 4 +++ arch/arm64/include/asm/cputype.h | 16 +++++++++ arch/arm64/kernel/cpu_errata.c | 31 +++++++++++++++++ arch/arm64/kernel/cpufeature.c | 48 ++++++++++++++++++++++---- arch/arm64/kernel/proton-pack.c | 12 +++++++ arch/arm64/tools/cpucaps | 1 + 8 files changed, 179 insertions(+), 7 deletions(-)

-- 2.30.2

Show replies by date

Mark Rutland

9 Aug 9 Aug

10:09 a.m.

New subject: [PATCH 5.15.y 01/14] arm64: cpufeature: Force HWCAP to be based on the sysreg visible to user-space

From: James Morse james.morse@arm.com

[ Upstream commit 237405ebef580a7352a52129b2465c117145eafa ]

arm64 advertises hardware features to user-space via HWCAPs, and by emulating access to the CPUs id registers. The cpufeature code has a sanitised system-wide view of an id register, and a sanitised user-space view of an id register, where some features use their 'safe' value instead of the hardware value.

It is currently possible for a HWCAP to be advertised where the user-space view of the id register does not show the feature as supported. Erratum workaround need to remove both the HWCAP, and the feature from the user-space view of the id register. This involves duplicating the code, and spreading it over cpufeature.c and cpu_errata.c.

Make the HWCAP code use the user-space view of id registers. This ensures the values never diverge, and allows erratum workaround to remove HWCAP by modifying the user-space view of the id register.

Signed-off-by: James Morse james.morse@arm.com Reviewed-by: Suzuki K Poulose suzuki.poulose@arm.com Link: https://lore.kernel.org/r/20220909165938.3931307-2-james.morse@arm.com Signed-off-by: Catalin Marinas catalin.marinas@arm.com [ Mark: fixup lack of 'width' parameter ] Signed-off-by: Mark Rutland mark.rutland@arm.com --- arch/arm64/kernel/cpufeature.c | 36 +++++++++++++++++++++++++++------- 1 file changed, 29 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index f17d6cdea2605..1bb55f4a3421d 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1319,17 +1319,39 @@ feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry) return val >= entry->min_field_value; }

-static bool -has_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope) +static u64 +read_scoped_sysreg(const struct arm64_cpu_capabilities *entry, int scope) { - u64 val; - WARN_ON(scope == SCOPE_LOCAL_CPU && preemptible()); if (scope == SCOPE_SYSTEM) - val = read_sanitised_ftr_reg(entry->sys_reg); + return read_sanitised_ftr_reg(entry->sys_reg); else - val = __read_sysreg_by_encoding(entry->sys_reg); + return __read_sysreg_by_encoding(entry->sys_reg); +} + +static bool +has_user_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope) +{ + int mask; + struct arm64_ftr_reg *regp; + u64 val = read_scoped_sysreg(entry, scope); + + regp = get_arm64_ftr_reg(entry->sys_reg); + if (!regp) + return false; + + mask = cpuid_feature_extract_unsigned_field(regp->user_mask, + entry->field_pos); + if (!mask) + return false; + + return feature_matches(val, entry); +}

+static bool +has_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope) +{ + u64 val = read_scoped_sysreg(entry, scope); return feature_matches(val, entry); }

@@ -2376,7 +2398,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { };

#define HWCAP_CPUID_MATCH(reg, field, s, min_value) \ - .matches = has_cpuid_feature, \ + .matches = has_user_cpuid_feature, \ .sys_reg = reg, \ .field_pos = field, \ .sign = s, \

-- 2.30.2

Mark Rutland

10:09 a.m.

New subject: [PATCH 5.15.y 02/14] arm64: Add Neoverse-V2 part

From: Besar Wicaksono bwicaksono@nvidia.com

[ Upstream commit f4d9d9dcc70b96b5e5d7801bd5fbf8491b07b13d ]

Add the part number and MIDR for Neoverse-V2

Signed-off-by: Besar Wicaksono bwicaksono@nvidia.com Reviewed-by: James Clark james.clark@arm.com Link: https://lore.kernel.org/r/20240109192310.16234-2-bwicaksono@nvidia.com Signed-off-by: Will Deacon will@kernel.org [ Mark: trivial backport ] Signed-off-by: Mark Rutland mark.rutland@arm.com --- arch/arm64/include/asm/cputype.h | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 3656bbbb7c7b6..d6d3f15c80aae 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -85,6 +85,7 @@ #define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B +#define ARM_CPU_PART_NEOVERSE_V2 0xD4F

#define APM_CPU_PART_POTENZA 0x000

@@ -139,6 +140,7 @@ #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) +#define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)

-- 2.30.2

Mark Rutland

10:09 a.m.

New subject: [PATCH 5.15.y 03/14] arm64: barrier: Restore spec_bar() macro

[ Upstream commit ebfc726eae3f31bdb5fae1bbd74ef235d71046ca ]

Upcoming errata workarounds will need to use SB from C code. Restore the spec_bar() macro so that we can use SB.

This is effectively a revert of commit:

4f30ba1cce36d413 ("arm64: barrier: Remove spec_bar() macro")

diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 1c5a005984582..6e3f4eea1f34d 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -26,6 +26,10 @@ #define __tsb_csync() asm volatile("hint #18" : : : "memory") #define csdb() asm volatile("hint #20" : : : "memory")

+#define spec_bar() asm volatile(ALTERNATIVE("dsb nsh\nisb\n", \ + SB_BARRIER_INSN"nop\n", \ + ARM64_HAS_SB)) + #ifdef CONFIG_ARM64_PSEUDO_NMI #define pmr_sync() \ do { \

-- 2.30.2

Mark Rutland

10:09 a.m.

New subject: [PATCH 5.15.y 04/14] arm64: cputype: Add Cortex-X4 definitions

[ Upstream commit 02a0a04676fa7796d9cbc9eb5ca120aaa194d2dd ]

Add cputype definitions for Cortex-X4. These will be used for errata detection in subsequent patches.

These values can be found in Table B-249 ("MIDR_EL1 bit descriptions") in issue 0002-05 of the Cortex-X4 TRM, which can be found at:

https://developer.arm.com/documentation/102484/0002/?lang=en

diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index d6d3f15c80aae..d222cd4983944 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -86,6 +86,7 @@ #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B #define ARM_CPU_PART_NEOVERSE_V2 0xD4F +#define ARM_CPU_PART_CORTEX_X4 0xD82

#define APM_CPU_PART_POTENZA 0x000

@@ -141,6 +142,7 @@ #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) #define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) +#define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)

-- 2.30.2

Mark Rutland

10:09 a.m.

New subject: [PATCH 5.15.y 05/14] arm64: cputype: Add Neoverse-V3 definitions

[ Upstream commit 0ce85db6c2141b7ffb95709d76fc55a27ff3cdc1 ]

Add cputype definitions for Neoverse-V3. These will be used for errata detection in subsequent patches.

These values can be found in Table B-249 ("MIDR_EL1 bit descriptions") in issue 0001-04 of the Neoverse-V3 TRM, which can be found at:

https://developer.arm.com/documentation/107734/0001/?lang=en

diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index d222cd4983944..17fb978191d68 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -87,6 +87,7 @@ #define ARM_CPU_PART_CORTEX_A78C 0xD4B #define ARM_CPU_PART_NEOVERSE_V2 0xD4F #define ARM_CPU_PART_CORTEX_X4 0xD82 +#define ARM_CPU_PART_NEOVERSE_V3 0xD84

#define APM_CPU_PART_POTENZA 0x000

@@ -143,6 +144,7 @@ #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) #define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) #define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) +#define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)

-- 2.30.2

Mark Rutland

10:09 a.m.

New subject: [PATCH 5.15.y 06/14] arm64: errata: Add workaround for Arm errata 3194386 and 3312417

[ Upstream commit 7187bb7d0b5c7dfa18ca82e9e5c75e13861b1d88 ]

Cortex-X4 and Neoverse-V3 suffer from errata whereby an MSR to the SSBS special-purpose register does not affect subsequent speculative instructions, permitting speculative store bypassing for a window of time. This is described in their Software Developer Errata Notice (SDEN) documents:

* Cortex-X4 SDEN v8.0, erratum 3194386: https://developer.arm.com/documentation/SDEN-2432808/0800/

* Neoverse-V3 SDEN v6.0, erratum 3312417: https://developer.arm.com/documentation/SDEN-2891958/0600/

To workaround these errata, it is necessary to place a speculation barrier (SB) after MSR to the SSBS special-purpose register. This patch adds the requisite SB after writes to SSBS within the kernel, and hides the presence of SSBS from EL0 such that userspace software which cares about SSBS will manipulate this via prctl(PR_GET_SPECULATION_CTRL, ...).

Signed-off-by: Mark Rutland mark.rutland@arm.com Cc: Catalin Marinas catalin.marinas@arm.com Cc: James Morse james.morse@arm.com Cc: Will Deacon will@kernel.org Link: https://lore.kernel.org/r/20240508081400.235362-5-mark.rutland@arm.com Signed-off-by: Will Deacon will@kernel.org [ Mark: fix conflicts & renames, drop unneeded cpucaps.h, fold in user_feature_fixup() ] Signed-off-by: Mark Rutland mark.rutland@arm.com --- Documentation/arm64/silicon-errata.rst | 4 +++ arch/arm64/Kconfig | 41 ++++++++++++++++++++++++++ arch/arm64/kernel/cpu_errata.c | 19 ++++++++++++ arch/arm64/kernel/cpufeature.c | 12 ++++++++ arch/arm64/kernel/proton-pack.c | 12 ++++++++ arch/arm64/tools/cpucaps | 1 + 6 files changed, 89 insertions(+)

diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index df7c53102a5f9..33595bc79dea6 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -108,6 +108,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A710 | #2224489 | ARM64_ERRATUM_2224489 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X4 | #3194386 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1188873,1418040| ARM64_ERRATUM_1418040 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1349291 | N/A | @@ -120,6 +122,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N2 | #2253138 | ARM64_ERRATUM_2253138 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-V3 | #3312417 | ARM64_ERRATUM_3312417 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | MMU-500 | #841119,826419 | N/A | +----------------+-----------------+-----------------+-----------------------------+ | ARM | MMU-600 | #1076982,1209401| N/A | diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 68874d3856b91..bc89287d38ed1 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -848,6 +848,47 @@ config ARM64_ERRATUM_2224489

If unsure, say Y.

+config ARM64_WORKAROUND_SPECULATIVE_SSBS + bool + +config ARM64_ERRATUM_3194386 + bool "Cortex-X4: 3194386: workaround for MSR SSBS not self-synchronizing" + select ARM64_WORKAROUND_SPECULATIVE_SSBS + default y + help + This option adds the workaround for ARM Cortex-X4 erratum 3194386. + + On affected cores "MSR SSBS, #0" instructions may not affect + subsequent speculative instructions, which may permit unexepected + speculative store bypassing. + + Work around this problem by placing a speculation barrier after + kernel changes to SSBS. The presence of the SSBS special-purpose + register is hidden from hwcaps and EL0 reads of ID_AA64PFR1_EL1, such + that userspace will use the PR_SPEC_STORE_BYPASS prctl to change + SSBS. + + If unsure, say Y. + +config ARM64_ERRATUM_3312417 + bool "Neoverse-V3: 3312417: workaround for MSR SSBS not self-synchronizing" + select ARM64_WORKAROUND_SPECULATIVE_SSBS + default y + help + This option adds the workaround for ARM Neoverse-V3 erratum 3312417. + + On affected cores "MSR SSBS, #0" instructions may not affect + subsequent speculative instructions, which may permit unexepected + speculative store bypassing. + + Work around this problem by placing a speculation barrier after + kernel changes to SSBS. The presence of the SSBS special-purpose + register is hidden from hwcaps and EL0 reads of ID_AA64PFR1_EL1, such + that userspace will use the PR_SPEC_STORE_BYPASS prctl to change + SSBS. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 4f12d8c1e55b9..0cf60010a0825 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -402,6 +402,18 @@ static struct midr_range trbe_write_out_of_range_cpus[] = { }; #endif /* CONFIG_ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE */

+#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS +static const struct midr_range erratum_spec_ssbs_list[] = { +#ifdef CONFIG_ARM64_ERRATUM_3194386 + MIDR_ALL_VERSIONS(MIDR_CORTEX_X4), +#endif +#ifdef CONFIG_ARM64_ERRATUM_3312417 + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3), +#endif + {} +}; +#endif + const struct arm64_cpu_capabilities arm64_errata[] = { #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE { @@ -648,6 +660,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE, CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus), }, +#endif +#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS + { + .desc = "ARM errata 3194386, 3312417", + .capability = ARM64_WORKAROUND_SPECULATIVE_SSBS, + ERRATA_MIDR_RANGE_LIST(erratum_spec_ssbs_list), + }, #endif { } diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 1bb55f4a3421d..299c9ac6bc818 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1939,6 +1939,17 @@ static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap) } #endif /* CONFIG_ARM64_MTE */

+static void user_feature_fixup(void) +{ + if (cpus_have_cap(ARM64_WORKAROUND_SPECULATIVE_SSBS)) { + struct arm64_ftr_reg *regp; + + regp = get_arm64_ftr_reg(SYS_ID_AA64PFR1_EL1); + if (regp) + regp->user_mask &= ~GENMASK(7, 4); /* SSBS */ + } +} + static void elf_hwcap_fixup(void) { #ifdef CONFIG_ARM64_ERRATUM_1742098 @@ -2972,6 +2983,7 @@ void __init setup_cpu_features(void) u32 cwg;

setup_system_capabilities(); + user_feature_fixup(); setup_elf_hwcaps(arm64_elf_hwcaps);

if (system_supports_32bit_el0()) { diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 7515ed1f0669a..c0149af8c9e97 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -558,6 +558,18 @@ static enum mitigation_state spectre_v4_enable_hw_mitigation(void)

/* SCTLR_EL1.DSSBS was initialised to 0 during boot */ set_pstate_ssbs(0); + + /* + * SSBS is self-synchronizing and is intended to affect subsequent + * speculative instructions, but some CPUs can speculate with a stale + * value of SSBS. + * + * Mitigate this with an unconditional speculation barrier, as CPUs + * could mis-speculate branches and bypass a conditional barrier. + */ + if (IS_ENABLED(CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS)) + spec_bar(); + return SPECTRE_MITIGATED; }

diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index fcaeec5a51258..e7f4ae17f31b0 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -70,3 +70,4 @@ WORKAROUND_NVIDIA_CARMEL_CNP WORKAROUND_QCOM_FALKOR_E1003 WORKAROUND_REPEAT_TLBI WORKAROUND_SPECULATIVE_AT +WORKAROUND_SPECULATIVE_SSBS

-- 2.30.2

Mark Rutland

10:09 a.m.

New subject: [PATCH 5.15.y 07/14] arm64: cputype: Add Cortex-X3 definitions

[ Upstream commit be5a6f238700f38b534456608588723fba96c5ab ]

Add cputype definitions for Cortex-X3. These will be used for errata detection in subsequent patches.

These values can be found in Table A-263 ("MIDR_EL1 bit descriptions") in issue 07 of the Cortex-X3 TRM, which can be found at:

https://developer.arm.com/documentation/101593/0102/?lang=en

diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 17fb978191d68..e246d7fad17a9 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -85,6 +85,7 @@ #define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B +#define ARM_CPU_PART_CORTEX_X3 0xD4E #define ARM_CPU_PART_NEOVERSE_V2 0xD4F #define ARM_CPU_PART_CORTEX_X4 0xD82 #define ARM_CPU_PART_NEOVERSE_V3 0xD84 @@ -142,6 +143,7 @@ #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) +#define MIDR_CORTEX_X3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X3) #define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) #define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) #define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3)

-- 2.30.2

Mark Rutland

10:09 a.m.

New subject: [PATCH 5.15.y 08/14] arm64: cputype: Add Cortex-A720 definitions

[ Upstream commit add332c40328cf06fe35e4b3cde8ec315c4629e5 ]

Add cputype definitions for Cortex-A720. These will be used for errata detection in subsequent patches.

These values can be found in Table A-186 ("MIDR_EL1 bit descriptions") in issue 0002-05 of the Cortex-A720 TRM, which can be found at:

https://developer.arm.com/documentation/102530/0002/?lang=en

diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index e246d7fad17a9..edfd6ac14a127 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -87,6 +87,7 @@ #define ARM_CPU_PART_CORTEX_A78C 0xD4B #define ARM_CPU_PART_CORTEX_X3 0xD4E #define ARM_CPU_PART_NEOVERSE_V2 0xD4F +#define ARM_CPU_PART_CORTEX_A720 0xD81 #define ARM_CPU_PART_CORTEX_X4 0xD82 #define ARM_CPU_PART_NEOVERSE_V3 0xD84

@@ -145,6 +146,7 @@ #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) #define MIDR_CORTEX_X3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X3) #define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) +#define MIDR_CORTEX_A720 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A720) #define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) #define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)

-- 2.30.2

Mark Rutland

10:09 a.m.

New subject: [PATCH 5.15.y 09/14] arm64: cputype: Add Cortex-X925 definitions

[ Upstream commit fd2ff5f0b320f418288e7a1f919f648fbc8a0dfc ]

Add cputype definitions for Cortex-X925. These will be used for errata detection in subsequent patches.

These values can be found in Table A-285 ("MIDR_EL1 bit descriptions") in issue 0001-05 of the Cortex-X925 TRM, which can be found at:

https://developer.arm.com/documentation/102807/0001/?lang=en

diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index edfd6ac14a127..95492fa88a244 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -90,6 +90,7 @@ #define ARM_CPU_PART_CORTEX_A720 0xD81 #define ARM_CPU_PART_CORTEX_X4 0xD82 #define ARM_CPU_PART_NEOVERSE_V3 0xD84 +#define ARM_CPU_PART_CORTEX_X925 0xD85

#define APM_CPU_PART_POTENZA 0x000

@@ -149,6 +150,7 @@ #define MIDR_CORTEX_A720 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A720) #define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) #define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) +#define MIDR_CORTEX_X925 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X925) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)

-- 2.30.2

Mark Rutland

10:09 a.m.

New subject: [PATCH 5.15.y 10/14] arm64: errata: Unify speculative SSBS errata logic

[ Upstream commit ec768766608092087dfb5c1fc45a16a6f524dee2 ]

Cortex-X4 erratum 3194386 and Neoverse-V3 erratum 3312417 are identical, with duplicate Kconfig text and some unsightly ifdeffery. While we try to share code behind CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS, having separate options results in a fair amount of boilerplate code, and this will only get worse as we expand the set of affected CPUs.

To reduce this boilerplate, unify the two behind a common Kconfig option. This removes the duplicate text and Kconfig logic, and removes the need for the intermediate ARM64_WORKAROUND_SPECULATIVE_SSBS option. The set of affected CPUs is described as a list so that this can easily be extended.

I've used ARM64_ERRATUM_3194386 (matching the Neoverse-V3 erratum ID) as the common option, matching the way we use ARM64_ERRATUM_1319367 to cover Cortex-A57 erratum 1319537 and Cortex-A72 erratum 1319367.

Signed-off-by: Mark Rutland mark.rutland@arm.com Cc: James Morse james.morse@arm.com Cc: Will Deacon will@kernel.org Link: https://lore.kernel.org/r/20240603111812.1514101-5-mark.rutland@arm.com Signed-off-by: Catalin Marinas catalin.marinas@arm.com [ Mark: fix conflicts & renames, drop unneeded cpucaps.h ] Signed-off-by: Mark Rutland mark.rutland@arm.com --- Documentation/arm64/silicon-errata.rst | 2 +- arch/arm64/Kconfig | 28 ++++---------------------- arch/arm64/kernel/cpu_errata.c | 8 ++------ arch/arm64/kernel/proton-pack.c | 2 +- 4 files changed, 8 insertions(+), 32 deletions(-)

diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 33595bc79dea6..13d77af92edf7 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -122,7 +122,7 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N2 | #2253138 | ARM64_ERRATUM_2253138 | +----------------+-----------------+-----------------+-----------------------------+ -| ARM | Neoverse-V3 | #3312417 | ARM64_ERRATUM_3312417 | +| ARM | Neoverse-V3 | #3312417 | ARM64_ERRATUM_3194386 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | MMU-500 | #841119,826419 | N/A | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index bc89287d38ed1..623b30c21c00d 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -848,34 +848,14 @@ config ARM64_ERRATUM_2224489

If unsure, say Y.

-config ARM64_WORKAROUND_SPECULATIVE_SSBS - bool - config ARM64_ERRATUM_3194386 - bool "Cortex-X4: 3194386: workaround for MSR SSBS not self-synchronizing" - select ARM64_WORKAROUND_SPECULATIVE_SSBS + bool "Cortex-X4/Neoverse-V3: workaround for MSR SSBS not self-synchronizing" default y help - This option adds the workaround for ARM Cortex-X4 erratum 3194386. - - On affected cores "MSR SSBS, #0" instructions may not affect - subsequent speculative instructions, which may permit unexepected - speculative store bypassing. - - Work around this problem by placing a speculation barrier after - kernel changes to SSBS. The presence of the SSBS special-purpose - register is hidden from hwcaps and EL0 reads of ID_AA64PFR1_EL1, such - that userspace will use the PR_SPEC_STORE_BYPASS prctl to change - SSBS. + This option adds the workaround for the following errata:

- If unsure, say Y. - -config ARM64_ERRATUM_3312417 - bool "Neoverse-V3: 3312417: workaround for MSR SSBS not self-synchronizing" - select ARM64_WORKAROUND_SPECULATIVE_SSBS - default y - help - This option adds the workaround for ARM Neoverse-V3 erratum 3312417. + * ARM Cortex-X4 erratum 3194386 + * ARM Neoverse-V3 erratum 3312417

On affected cores "MSR SSBS, #0" instructions may not affect subsequent speculative instructions, which may permit unexepected diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 0cf60010a0825..0fe2d65e646fe 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -402,14 +402,10 @@ static struct midr_range trbe_write_out_of_range_cpus[] = { }; #endif /* CONFIG_ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE */

-#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS -static const struct midr_range erratum_spec_ssbs_list[] = { #ifdef CONFIG_ARM64_ERRATUM_3194386 +static const struct midr_range erratum_spec_ssbs_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_X4), -#endif -#ifdef CONFIG_ARM64_ERRATUM_3312417 MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3), -#endif {} }; #endif @@ -661,7 +657,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus), }, #endif -#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS +#ifdef CONFIG_ARM64_ERRATUM_3194386 { .desc = "ARM errata 3194386, 3312417", .capability = ARM64_WORKAROUND_SPECULATIVE_SSBS, diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index c0149af8c9e97..ebce46c4e942c 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -567,7 +567,7 @@ static enum mitigation_state spectre_v4_enable_hw_mitigation(void) * Mitigate this with an unconditional speculation barrier, as CPUs * could mis-speculate branches and bypass a conditional barrier. */ - if (IS_ENABLED(CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS)) + if (IS_ENABLED(CONFIG_ARM64_ERRATUM_3194386)) spec_bar();

return SPECTRE_MITIGATED;

-- 2.30.2

Mark Rutland

10:09 a.m.

New subject: [PATCH 5.15.y 11/14] arm64: errata: Expand speculative SSBS workaround

[ Upstream commit 75b3c43eab594bfbd8184ec8ee1a6b820950819a ]

A number of Arm Ltd CPUs suffer from errata whereby an MSR to the SSBS special-purpose register does not affect subsequent speculative instructions, permitting speculative store bypassing for a window of time.

We worked around this for Cortex-X4 and Neoverse-V3, in commit:

7187bb7d0b5c7dfa ("arm64: errata: Add workaround for Arm errata 3194386 and 3312417")

... as per their Software Developer Errata Notice (SDEN) documents:

* Cortex-X4 SDEN v8.0, erratum 3194386: https://developer.arm.com/documentation/SDEN-2432808/0800/

* Neoverse-V3 SDEN v6.0, erratum 3312417: https://developer.arm.com/documentation/SDEN-2891958/0600/

Since then, similar errata have been published for a number of other Arm Ltd CPUs, for which the mitigation is the same. This is described in their respective SDEN documents:

* Cortex-A710 SDEN v19.0, errataum 3324338 https://developer.arm.com/documentation/SDEN-1775101/1900/?lang=en

* Cortex-A720 SDEN v11.0, erratum 3456091 https://developer.arm.com/documentation/SDEN-2439421/1100/?lang=en

* Cortex-X2 SDEN v19.0, erratum 3324338 https://developer.arm.com/documentation/SDEN-1775100/1900/?lang=en

* Cortex-X3 SDEN v14.0, erratum 3324335 https://developer.arm.com/documentation/SDEN-2055130/1400/?lang=en

* Cortex-X925 SDEN v8.0, erratum 3324334 https://developer.arm.com/documentation/109108/800/?lang=en

* Neoverse-N2 SDEN v17.0, erratum 3324339 https://developer.arm.com/documentation/SDEN-1982442/1700/?lang=en

* Neoverse-V2 SDEN v9.0, erratum 3324336 https://developer.arm.com/documentation/SDEN-2332927/900/?lang=en

Note that due to shared design lineage, some CPUs share the same erratum number.

Add these to the existing mitigation under CONFIG_ARM64_ERRATUM_3194386. As listing all of the erratum IDs in the runtime description would be unwieldy, this is reduced to:

"SSBS not fully self-synchronizing"

... matching the description of the errata in all of the SDENs.

Signed-off-by: Mark Rutland mark.rutland@arm.com Cc: James Morse james.morse@arm.com Cc: Will Deacon will@kernel.org Link: https://lore.kernel.org/r/20240603111812.1514101-6-mark.rutland@arm.com Signed-off-by: Catalin Marinas catalin.marinas@arm.com [ Mark: fix conflicts and renames ] Signed-off-by: Mark Rutland mark.rutland@arm.com --- Documentation/arm64/silicon-errata.rst | 14 ++++++++++++++ arch/arm64/Kconfig | 9 ++++++++- arch/arm64/kernel/cpu_errata.c | 9 ++++++++- 3 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 13d77af92edf7..1740c0dfd5503 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -108,8 +108,18 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A710 | #2224489 | ARM64_ERRATUM_2224489 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A710 | #3324338 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A720 | #3456091 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X2 | #3324338 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X3 | #3324335 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-X4 | #3194386 | ARM64_ERRATUM_3194386 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X925 | #3324334 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1188873,1418040| ARM64_ERRATUM_1418040 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1349291 | N/A | @@ -122,6 +132,10 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N2 | #2253138 | ARM64_ERRATUM_2253138 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-N2 | #3324339 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-V2 | #3324336 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-V3 | #3312417 | ARM64_ERRATUM_3194386 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | MMU-500 | #841119,826419 | N/A | diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 623b30c21c00d..91a956605925b 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -849,12 +849,19 @@ config ARM64_ERRATUM_2224489 If unsure, say Y.

config ARM64_ERRATUM_3194386 - bool "Cortex-X4/Neoverse-V3: workaround for MSR SSBS not self-synchronizing" + bool "Cortex-{A720,X4,X925}/Neoverse-V3: workaround for MSR SSBS not self-synchronizing" default y help This option adds the workaround for the following errata:

+ * ARM Cortex-A710 erratam 3324338 + * ARM Cortex-A720 erratum 3456091 + * ARM Cortex-X2 erratum 3324338 + * ARM Cortex-X3 erratum 3324335 * ARM Cortex-X4 erratum 3194386 + * ARM Cortex-X925 erratum 3324334 + * ARM Neoverse N2 erratum 3324339 + * ARM Neoverse V2 erratum 3324336 * ARM Neoverse-V3 erratum 3312417

On affected cores "MSR SSBS, #0" instructions may not affect diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 0fe2d65e646fe..f360ec1619bd5 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -404,8 +404,15 @@ static struct midr_range trbe_write_out_of_range_cpus[] = {

#ifdef CONFIG_ARM64_ERRATUM_3194386 static const struct midr_range erratum_spec_ssbs_list[] = { + MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A720), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X2), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X3), MIDR_ALL_VERSIONS(MIDR_CORTEX_X4), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X925), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2), {} }; #endif @@ -659,7 +666,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { #endif #ifdef CONFIG_ARM64_ERRATUM_3194386 { - .desc = "ARM errata 3194386, 3312417", + .desc = "SSBS not fully self-synchronizing", .capability = ARM64_WORKAROUND_SPECULATIVE_SSBS, ERRATA_MIDR_RANGE_LIST(erratum_spec_ssbs_list), },

-- 2.30.2

Mark Rutland

10:09 a.m.

New subject: [PATCH 5.15.y 12/14] arm64: cputype: Add Cortex-X1C definitions

[ Upstream commit 58d245e03c324d083a0ec3b9ab8ebd46ec9848d7 ]

Add cputype definitions for Cortex-X1C. These will be used for errata detection in subsequent patches.

These values can be found in the Cortex-X1C TRM:

https://developer.arm.com/documentation/101968/0002/

... in section B2.107 ("MIDR_EL1, Main ID Register, EL1").

Signed-off-by: Mark Rutland mark.rutland@arm.com Cc: James Morse james.morse@arm.com Cc: Will Deacon will@kernel.org Reviewed-by: Anshuman Khandual anshuman.khandual@arm.com Link: https://lore.kernel.org/r/20240801101803.1982459-2-mark.rutland@arm.com Signed-off-by: Catalin Marinas catalin.marinas@arm.com [ Mark: trivial backport ] Signed-off-by: Mark Rutland mark.rutland@arm.com --- arch/arm64/include/asm/cputype.h | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 95492fa88a244..d1f5ec68ec726 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -85,6 +85,7 @@ #define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B +#define ARM_CPU_PART_CORTEX_X1C 0xD4C #define ARM_CPU_PART_CORTEX_X3 0xD4E #define ARM_CPU_PART_NEOVERSE_V2 0xD4F #define ARM_CPU_PART_CORTEX_A720 0xD81 @@ -145,6 +146,7 @@ #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) +#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C) #define MIDR_CORTEX_X3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X3) #define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) #define MIDR_CORTEX_A720 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A720)

-- 2.30.2

Mark Rutland

10:09 a.m.

New subject: [PATCH 5.15.y 13/14] arm64: cputype: Add Cortex-A725 definitions

[ Upstream commit 9ef54a384526911095db465e77acc1cb5266b32c ]

Add cputype definitions for Cortex-A725. These will be used for errata detection in subsequent patches.

These values can be found in the Cortex-A725 TRM:

https://developer.arm.com/documentation/107652/0001/

... in table A-247 ("MIDR_EL1 bit descriptions").

Signed-off-by: Mark Rutland mark.rutland@arm.com Cc: James Morse james.morse@arm.com Cc: Will Deacon will@kernel.org Reviewed-by: Anshuman Khandual anshuman.khandual@arm.com Link: https://lore.kernel.org/r/20240801101803.1982459-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas catalin.marinas@arm.com [ Mark: trivial backport ] Signed-off-by: Mark Rutland mark.rutland@arm.com --- arch/arm64/include/asm/cputype.h | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index d1f5ec68ec726..59f135b280a8a 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -92,6 +92,7 @@ #define ARM_CPU_PART_CORTEX_X4 0xD82 #define ARM_CPU_PART_NEOVERSE_V3 0xD84 #define ARM_CPU_PART_CORTEX_X925 0xD85 +#define ARM_CPU_PART_CORTEX_A725 0xD87

#define APM_CPU_PART_POTENZA 0x000

@@ -153,6 +154,7 @@ #define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) #define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) #define MIDR_CORTEX_X925 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X925) +#define MIDR_CORTEX_A725 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A725) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)

-- 2.30.2

Mark Rutland

10:09 a.m.

New subject: [PATCH 5.15.y 14/14] arm64: errata: Expand speculative SSBS workaround (again)

[ Upstream commit b0672bbe133ebb6f7be21fce1d742d52f25bcdc7 ]

We worked around this for a number of CPUs in commits:

* 7187bb7d0b5c7dfa ("arm64: errata: Add workaround for Arm errata 3194386 and 3312417") * 75b3c43eab594bfb ("arm64: errata: Expand speculative SSBS workaround")

Since then, similar errata have been published for a number of other Arm Ltd CPUs, for which the same mitigation is sufficient. This is described in their respective Software Developer Errata Notice (SDEN) documents:

* Cortex-A76 (MP052) SDEN v31.0, erratum 3324349 https://developer.arm.com/documentation/SDEN-885749/3100/

* Cortex-A77 (MP074) SDEN v19.0, erratum 3324348 https://developer.arm.com/documentation/SDEN-1152370/1900/

* Cortex-A78 (MP102) SDEN v21.0, erratum 3324344 https://developer.arm.com/documentation/SDEN-1401784/2100/

* Cortex-A78C (MP138) SDEN v16.0, erratum 3324346 https://developer.arm.com/documentation/SDEN-1707916/1600/

* Cortex-A78C (MP154) SDEN v10.0, erratum 3324347 https://developer.arm.com/documentation/SDEN-2004089/1000/

* Cortex-A725 (MP190) SDEN v5.0, erratum 3456106 https://developer.arm.com/documentation/SDEN-2832921/0500/

* Cortex-X1 (MP077) SDEN v21.0, erratum 3324344 https://developer.arm.com/documentation/SDEN-1401782/2100/

* Cortex-X1C (MP136) SDEN v16.0, erratum 3324346 https://developer.arm.com/documentation/SDEN-1707914/1600/

* Neoverse-N1 (MP050) SDEN v32.0, erratum 3324349 https://developer.arm.com/documentation/SDEN-885747/3200/

* Neoverse-V1 (MP076) SDEN v19.0, erratum 3324341 https://developer.arm.com/documentation/SDEN-1401781/1900/

Note that due to the manner in which Arm develops IP and tracks errata, some CPUs share a common erratum number and some CPUs have multiple erratum numbers for the same HW issue.

On parts without SB, it is necessary to use ISB for the workaround. The spec_bar() macro used in the mitigation will expand to a "DSB SY; ISB" sequence in this case, which is sufficient on all affected parts.

Enable the existing mitigation by adding the relevant MIDRs to erratum_spec_ssbs_list. The list is sorted alphanumerically (involving moving Neoverse-V3 after Neoverse-V2) so that this is easy to audit and potentially extend again in future. The Kconfig text is also updated to clarify the set of affected parts and the mitigation.

Signed-off-by: Mark Rutland mark.rutland@arm.com Cc: James Morse james.morse@arm.com Cc: Will Deacon will@kernel.org Reviewed-by: Anshuman Khandual anshuman.khandual@arm.com Acked-by: Will Deacon will@kernel.org Link: https://lore.kernel.org/r/20240801101803.1982459-4-mark.rutland@arm.com Signed-off-by: Catalin Marinas catalin.marinas@arm.com [ Mark: fix conflicts in silicon-errata.rst ] Signed-off-by: Mark Rutland mark.rutland@arm.com --- Documentation/arm64/silicon-errata.rst | 18 ++++++++++++++++++ arch/arm64/Kconfig | 22 ++++++++++++++++------ arch/arm64/kernel/cpu_errata.c | 11 ++++++++++- 3 files changed, 44 insertions(+), 7 deletions(-)

diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 1740c0dfd5503..9868eb45c56a0 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -96,8 +96,16 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A76 | #1463225 | ARM64_ERRATUM_1463225 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A76 | #3324349 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A77 | #1508412 | ARM64_ERRATUM_1508412 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A77 | #3324348 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A78 | #3324344 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A78C | #3324346,3324347| ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A510 | #2441009 | ARM64_ERRATUM_2441009 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A510 | #2457168 | ARM64_ERRATUM_2457168 | @@ -112,6 +120,12 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A720 | #3456091 | ARM64_ERRATUM_3194386 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A725 | #3456106 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X1 | #3324344 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X1C | #3324346 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-X2 | #3324338 | ARM64_ERRATUM_3194386 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-X3 | #3324335 | ARM64_ERRATUM_3194386 | @@ -126,6 +140,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1542419 | ARM64_ERRATUM_1542419 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-N1 | #3324349 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N2 | #2139208 | ARM64_ERRATUM_2139208 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N2 | #2067961 | ARM64_ERRATUM_2067961 | @@ -134,6 +150,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N2 | #3324339 | ARM64_ERRATUM_3194386 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-V1 | #3324341 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-V2 | #3324336 | ARM64_ERRATUM_3194386 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-V3 | #3312417 | ARM64_ERRATUM_3194386 | diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 91a956605925b..2d77e9269eb50 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -849,18 +849,28 @@ config ARM64_ERRATUM_2224489 If unsure, say Y.

config ARM64_ERRATUM_3194386 - bool "Cortex-{A720,X4,X925}/Neoverse-V3: workaround for MSR SSBS not self-synchronizing" + bool "Cortex-*/Neoverse-*: workaround for MSR SSBS not self-synchronizing" default y help This option adds the workaround for the following errata:

+ * ARM Cortex-A76 erratum 3324349 + * ARM Cortex-A77 erratum 3324348 + * ARM Cortex-A78 erratum 3324344 + * ARM Cortex-A78C erratum 3324346 + * ARM Cortex-A78C erratum 3324347 * ARM Cortex-A710 erratam 3324338 * ARM Cortex-A720 erratum 3456091 + * ARM Cortex-A725 erratum 3456106 + * ARM Cortex-X1 erratum 3324344 + * ARM Cortex-X1C erratum 3324346 * ARM Cortex-X2 erratum 3324338 * ARM Cortex-X3 erratum 3324335 * ARM Cortex-X4 erratum 3194386 * ARM Cortex-X925 erratum 3324334 + * ARM Neoverse-N1 erratum 3324349 * ARM Neoverse N2 erratum 3324339 + * ARM Neoverse-V1 erratum 3324341 * ARM Neoverse V2 erratum 3324336 * ARM Neoverse-V3 erratum 3312417

@@ -868,11 +878,11 @@ config ARM64_ERRATUM_3194386 subsequent speculative instructions, which may permit unexepected speculative store bypassing.

- Work around this problem by placing a speculation barrier after - kernel changes to SSBS. The presence of the SSBS special-purpose - register is hidden from hwcaps and EL0 reads of ID_AA64PFR1_EL1, such - that userspace will use the PR_SPEC_STORE_BYPASS prctl to change - SSBS. + Work around this problem by placing a Speculation Barrier (SB) or + Instruction Synchronization Barrier (ISB) after kernel changes to + SSBS. The presence of the SSBS special-purpose register is hidden + from hwcaps and EL0 reads of ID_AA64PFR1_EL1, such that userspace + will use the PR_SPEC_STORE_BYPASS prctl to change SSBS.

If unsure, say Y.

diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index f360ec1619bd5..c358bc1c2954e 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -404,15 +404,24 @@ static struct midr_range trbe_write_out_of_range_cpus[] = {

#ifdef CONFIG_ARM64_ERRATUM_3194386 static const struct midr_range erratum_spec_ssbs_list[] = { + MIDR_ALL_VERSIONS(MIDR_CORTEX_A76), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A77), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), MIDR_ALL_VERSIONS(MIDR_CORTEX_A720), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A725), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X1C), MIDR_ALL_VERSIONS(MIDR_CORTEX_X2), MIDR_ALL_VERSIONS(MIDR_CORTEX_X3), MIDR_ALL_VERSIONS(MIDR_CORTEX_X4), MIDR_ALL_VERSIONS(MIDR_CORTEX_X925), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), - MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3), {} }; #endif

-- 2.30.2

152

days inactive

152

days old

linux-stable-mirror@lists.linaro.org

14 comments

participants

tags (0)

participants (1)

Mark Rutland