From 61da7c8e2a602f66be578cbbcebe8638c10e0f48 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 30 Jan 2024 15:43:53 +0000 Subject: [PATCH 1/7] arm64/signal: Don't assume that TIF_SVE means we saved SVE state When we are in a syscall we will only save the FPSIMD subset even though the task still has access to the full register set, and on context switch we will only remove TIF_SVE when loading the register state. This means that the signal handling code should not assume that TIF_SVE means that the register state is stored in SVE format, it should instead check the format that was recorded during save. Fixes: 8c845e273104 ("arm64/sve: Leave SVE enabled on syscall if we don't context switch") Signed-off-by: Mark Brown Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240130-arm64-sve-signal-regs-v2-1-9fc6f9502782@kernel.org Signed-off-by: Will Deacon --- arch/arm64/kernel/fpsimd.c | 2 +- arch/arm64/kernel/signal.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index a5dc6f764195..25ceaee6b025 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1635,7 +1635,7 @@ void fpsimd_preserve_current_state(void) void fpsimd_signal_preserve_current_state(void) { fpsimd_preserve_current_state(); - if (test_thread_flag(TIF_SVE)) + if (current->thread.fp_type == FP_STATE_SVE) sve_to_fpsimd(current); } diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 0e8beb3349ea..425b1bc17a3f 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -242,7 +242,7 @@ static int preserve_sve_context(struct sve_context __user *ctx) vl = task_get_sme_vl(current); vq = sve_vq_from_vl(vl); flags |= SVE_SIG_FLAG_SM; - } else if (test_thread_flag(TIF_SVE)) { + } else if (current->thread.fp_type == FP_STATE_SVE) { vq = sve_vq_from_vl(vl); } @@ -878,7 +878,7 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, if (system_supports_sve() || system_supports_sme()) { unsigned int vq = 0; - if (add_all || test_thread_flag(TIF_SVE) || + if (add_all || current->thread.fp_type == FP_STATE_SVE || thread_sm_enabled(¤t->thread)) { int vl = max(sve_max_vl(), sme_max_vl()); From 719da04f2d1285922abca72b074fb6fa75d464ea Mon Sep 17 00:00:00 2001 From: Hojin Nam Date: Thu, 8 Feb 2024 10:34:15 +0900 Subject: [PATCH 2/7] perf: CXL: fix mismatched cpmu event opcode S2M NDR BI-ConflictAck opcode is described as 4 in the CXL r3.0 3.3.9 Table 3.43. However, it is defined as 3 in macro definition. Fixes: 5d7107c72796 ("perf: CXL Performance Monitoring Unit driver") Signed-off-by: Hojin Nam Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/20240208013415epcms2p2904187c8a863f4d0d2adc980fb91a2dc@epcms2p2 Signed-off-by: Will Deacon --- drivers/perf/cxl_pmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/perf/cxl_pmu.c b/drivers/perf/cxl_pmu.c index 365d964b0f6a..bc0d414a6aff 100644 --- a/drivers/perf/cxl_pmu.c +++ b/drivers/perf/cxl_pmu.c @@ -419,7 +419,7 @@ static struct attribute *cxl_pmu_event_attrs[] = { CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmp, CXL_PMU_GID_S2M_NDR, BIT(0)), CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmps, CXL_PMU_GID_S2M_NDR, BIT(1)), CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_cmpe, CXL_PMU_GID_S2M_NDR, BIT(2)), - CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_biconflictack, CXL_PMU_GID_S2M_NDR, BIT(3)), + CXL_PMU_EVENT_CXL_ATTR(s2m_ndr_biconflictack, CXL_PMU_GID_S2M_NDR, BIT(4)), /* CXL rev 3.0 Table 3-46 S2M DRS opcodes */ CXL_PMU_EVENT_CXL_ATTR(s2m_drs_memdata, CXL_PMU_GID_S2M_DRS, BIT(0)), CXL_PMU_EVENT_CXL_ATTR(s2m_drs_memdatanxm, CXL_PMU_GID_S2M_DRS, BIT(1)), From c0b26c06ed008c0898829dda4c2783b8ec478350 Mon Sep 17 00:00:00 2001 From: Seongsu Park Date: Fri, 2 Feb 2024 10:33:06 +0900 Subject: [PATCH 3/7] arm64: fix typo in comments fix typo in comments thath -> that Signed-off-by: Seongsu Park Link: https://lore.kernel.org/r/20240202013306.883777-1-sgsu.park@samsung.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/cpufeature.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 21c824edf8ce..bd8d4ca81a48 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -83,7 +83,7 @@ struct arm64_ftr_bits { * to full-0 denotes that this field has no override * * A @mask field set to full-0 with the corresponding @val field set - * to full-1 denotes thath this field has an invalid override. + * to full-1 denotes that this field has an invalid override. */ struct arm64_ftr_override { u64 val; From f9daab0ad01cf9d165dbbbf106ca4e61d06e7fe8 Mon Sep 17 00:00:00 2001 From: Fangrui Song Date: Mon, 5 Feb 2024 23:45:52 -0800 Subject: [PATCH 4/7] arm64: jump_label: use constraints "Si" instead of "i" The generic constraint "i" seems to be copied from x86 or arm (and with a redundant generic operand modifier "c"). It works with -fno-PIE but not with -fPIE/-fPIC in GCC's aarch64 port. The machine constraint "S", which denotes a symbol or label reference with a constant offset, supports PIC and has been available in GCC since 2012 and in Clang since 7.0. However, Clang before 19 does not support "S" on a symbol with a constant offset [1] (e.g. `static_key_false(&nf_hooks_needed[pf][hook])` in include/linux/netfilter.h), so we use "i" as a fallback. Suggested-by: Ard Biesheuvel Signed-off-by: Fangrui Song Link: https://github.com/llvm/llvm-project/pull/80255 [1] Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20240206074552.541154-1-maskray@google.com Signed-off-by: Will Deacon --- arch/arm64/include/asm/jump_label.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h index 48ddc0f45d22..b7716b215f91 100644 --- a/arch/arm64/include/asm/jump_label.h +++ b/arch/arm64/include/asm/jump_label.h @@ -15,6 +15,10 @@ #define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE +/* + * Prefer the constraint "S" to support PIC with GCC. Clang before 19 does not + * support "S" on a symbol with a constant offset, so we use "i" as a fallback. + */ static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { @@ -23,9 +27,9 @@ static __always_inline bool arch_static_branch(struct static_key * const key, " .pushsection __jump_table, \"aw\" \n\t" " .align 3 \n\t" " .long 1b - ., %l[l_yes] - . \n\t" - " .quad %c0 - . \n\t" + " .quad (%[key] - .) + %[bit0] \n\t" " .popsection \n\t" - : : "i"(&((char *)key)[branch]) : : l_yes); + : : [key]"Si"(key), [bit0]"i"(branch) : : l_yes); return false; l_yes: @@ -40,9 +44,9 @@ static __always_inline bool arch_static_branch_jump(struct static_key * const ke " .pushsection __jump_table, \"aw\" \n\t" " .align 3 \n\t" " .long 1b - ., %l[l_yes] - . \n\t" - " .quad %c0 - . \n\t" + " .quad (%[key] - .) + %[bit0] \n\t" " .popsection \n\t" - : : "i"(&((char *)key)[branch]) : : l_yes); + : : [key]"Si"(key), [bit0]"i"(branch) : : l_yes); return false; l_yes: From 50572064ec7109b00eef8880e905f55861c8b3de Mon Sep 17 00:00:00 2001 From: Ilkka Koskinen Date: Fri, 9 Feb 2024 17:11:09 +0000 Subject: [PATCH 5/7] perf/arm-cmn: Workaround AmpereOneX errata AC04_MESH_1 (incorrect child count) AmpereOneX mesh implementation has a bug in HN-P nodes that makes them report incorrect child count. The failing crosspoints report 8 children while they only have two. When the driver tries to access the inexistent child nodes, it believes it has reached an invalid node type and probing fails. The workaround is to ignore those incorrect child nodes and continue normally. Signed-off-by: Ilkka Koskinen [ rm: rewrote simpler generalised version ] Tested-by: Ilkka Koskinen Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/ce4b1442135fe03d0de41859b04b268c88c854a3.1707498577.git.robin.murphy@arm.com Signed-off-by: Will Deacon --- drivers/perf/arm-cmn.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c index c584165b13ba..7e3aa7e2345f 100644 --- a/drivers/perf/arm-cmn.c +++ b/drivers/perf/arm-cmn.c @@ -2305,6 +2305,17 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset) dev_dbg(cmn->dev, "ignoring external node %llx\n", reg); continue; } + /* + * AmpereOneX erratum AC04_MESH_1 makes some XPs report a bogus + * child count larger than the number of valid child pointers. + * A child offset of 0 can only occur on CMN-600; otherwise it + * would imply the root node being its own grandchild, which + * we can safely dismiss in general. + */ + if (reg == 0 && cmn->part != PART_CMN600) { + dev_dbg(cmn->dev, "bogus child pointer?\n"); + continue; + } arm_cmn_init_node_info(cmn, reg & CMN_CHILD_NODE_ADDR, dn); From fb091ff394792c018527b3211bbdfae93ea4ac02 Mon Sep 17 00:00:00 2001 From: Easwar Hariharan Date: Wed, 14 Feb 2024 17:55:18 +0000 Subject: [PATCH 6/7] arm64: Subscribe Microsoft Azure Cobalt 100 to ARM Neoverse N2 errata Add the MIDR value of Microsoft Azure Cobalt 100, which is a Microsoft implemented CPU based on r0p0 of the ARM Neoverse N2 CPU, and therefore suffers from all the same errata. CC: stable@vger.kernel.org # 5.15+ Signed-off-by: Easwar Hariharan Reviewed-by: Anshuman Khandual Acked-by: Mark Rutland Acked-by: Marc Zyngier Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20240214175522.2457857-1-eahariha@linux.microsoft.com Signed-off-by: Will Deacon --- Documentation/arch/arm64/silicon-errata.rst | 7 +++++++ arch/arm64/include/asm/cputype.h | 4 ++++ arch/arm64/kernel/cpu_errata.c | 3 +++ 3 files changed, 14 insertions(+) diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst index e8c2ce1f9df6..45a7f4932fe0 100644 --- a/Documentation/arch/arm64/silicon-errata.rst +++ b/Documentation/arch/arm64/silicon-errata.rst @@ -243,3 +243,10 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ASR | ASR8601 | #8601001 | N/A | +----------------+-----------------+-----------------+-----------------------------+ ++----------------+-----------------+-----------------+-----------------------------+ +| Microsoft | Azure Cobalt 100| #2139208 | ARM64_ERRATUM_2139208 | ++----------------+-----------------+-----------------+-----------------------------+ +| Microsoft | Azure Cobalt 100| #2067961 | ARM64_ERRATUM_2067961 | ++----------------+-----------------+-----------------+-----------------------------+ +| Microsoft | Azure Cobalt 100| #2253138 | ARM64_ERRATUM_2253138 | ++----------------+-----------------+-----------------+-----------------------------+ diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 7c7493cb571f..52f076afeb96 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -61,6 +61,7 @@ #define ARM_CPU_IMP_HISI 0x48 #define ARM_CPU_IMP_APPLE 0x61 #define ARM_CPU_IMP_AMPERE 0xC0 +#define ARM_CPU_IMP_MICROSOFT 0x6D #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 @@ -135,6 +136,8 @@ #define AMPERE_CPU_PART_AMPERE1 0xAC3 +#define MICROSOFT_CPU_PART_AZURE_COBALT_100 0xD49 /* Based on r0p0 of ARM Neoverse N2 */ + #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) @@ -193,6 +196,7 @@ #define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX) #define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) +#define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ #define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 967c7c7a4e7d..76b8dd37092a 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -374,6 +374,7 @@ static const struct midr_range erratum_1463225[] = { static const struct midr_range trbe_overwrite_fill_mode_cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_2139208 MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100), #endif #ifdef CONFIG_ARM64_ERRATUM_2119858 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), @@ -387,6 +388,7 @@ static const struct midr_range trbe_overwrite_fill_mode_cpus[] = { static const struct midr_range tsb_flush_fail_cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_2067961 MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100), #endif #ifdef CONFIG_ARM64_ERRATUM_2054223 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), @@ -399,6 +401,7 @@ static const struct midr_range tsb_flush_fail_cpus[] = { static struct midr_range trbe_write_out_of_range_cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_2253138 MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100), #endif #ifdef CONFIG_ARM64_ERRATUM_2224489 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), From 2813926261e436d33bc74486b51cce60b76edf78 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 13 Feb 2024 18:24:38 +0000 Subject: [PATCH 7/7] arm64/sve: Lower the maximum allocation for the SVE ptrace regset Doug Anderson observed that ChromeOS crashes are being reported which include failing allocations of order 7 during core dumps due to ptrace allocating storage for regsets: chrome: page allocation failure: order:7, mode:0x40dc0(GFP_KERNEL|__GFP_COMP|__GFP_ZERO), nodemask=(null),cpuset=urgent,mems_allowed=0 ... regset_get_alloc+0x1c/0x28 elf_core_dump+0x3d8/0xd8c do_coredump+0xeb8/0x1378 with further investigation showing that this is: [ 66.957385] DOUG: Allocating 279584 bytes which is the maximum size of the SVE regset. As Doug observes it is not entirely surprising that such a large allocation of contiguous memory might fail on a long running system. The SVE regset is currently sized to hold SVE registers with a VQ of SVE_VQ_MAX which is 512, substantially more than the architectural maximum of 16 which we might see even in a system emulating the limits of the architecture. Since we don't expose the size we tell the regset core externally let's define ARCH_SVE_VQ_MAX with the actual architectural maximum and use that for the regset, we'll still overallocate most of the time but much less so which will be helpful even if the core is fixed to not require contiguous allocations. Specify ARCH_SVE_VQ_MAX in terms of the maximum value that can be written into ZCR_ELx.LEN (where this is set in the hardware). For consistency update the maximum SME vector length to be specified in the same style while we are at it. We could also teach the ptrace core about runtime discoverable regset sizes but that would be a more invasive change and this is being observed in practical systems. Reported-by: Doug Anderson Signed-off-by: Mark Brown Tested-by: Douglas Anderson Link: https://lore.kernel.org/r/20240213-arm64-sve-ptrace-regset-size-v2-1-c7600ca74b9b@kernel.org Signed-off-by: Will Deacon --- arch/arm64/include/asm/fpsimd.h | 12 ++++++------ arch/arm64/kernel/ptrace.c | 3 ++- 2 files changed, 8 insertions(+), 7 deletions(-) diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 50e5f25d3024..481d94416d69 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -62,13 +62,13 @@ static inline void cpacr_restore(unsigned long cpacr) * When we defined the maximum SVE vector length we defined the ABI so * that the maximum vector length included all the reserved for future * expansion bits in ZCR rather than those just currently defined by - * the architecture. While SME follows a similar pattern the fact that - * it includes a square matrix means that any allocations that attempt - * to cover the maximum potential vector length (such as happen with - * the regset used for ptrace) end up being extremely large. Define - * the much lower actual limit for use in such situations. + * the architecture. Using this length to allocate worst size buffers + * results in excessively large allocations, and this effect is even + * more pronounced for SME due to ZA. Define more suitable VLs for + * these situations. */ -#define SME_VQ_MAX 16 +#define ARCH_SVE_VQ_MAX ((ZCR_ELx_LEN_MASK >> ZCR_ELx_LEN_SHIFT) + 1) +#define SME_VQ_MAX ((SMCR_ELx_LEN_MASK >> SMCR_ELx_LEN_SHIFT) + 1) struct task_struct; diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index dc6cf0e37194..e3bef38fc2e2 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1500,7 +1500,8 @@ static const struct user_regset aarch64_regsets[] = { #ifdef CONFIG_ARM64_SVE [REGSET_SVE] = { /* Scalable Vector Extension */ .core_note_type = NT_ARM_SVE, - .n = DIV_ROUND_UP(SVE_PT_SIZE(SVE_VQ_MAX, SVE_PT_REGS_SVE), + .n = DIV_ROUND_UP(SVE_PT_SIZE(ARCH_SVE_VQ_MAX, + SVE_PT_REGS_SVE), SVE_VQ_BYTES), .size = SVE_VQ_BYTES, .align = SVE_VQ_BYTES,