From ba386777a30b38dabcc7fb8a89ec2869a09915f7 Mon Sep 17 00:00:00 2001 From: Vignesh Balasubramanian Date: Thu, 25 Jul 2024 21:40:18 +0530 Subject: x86/elf: Add a new FPU buffer layout info to x86 core files Add a new .note section containing type, size, offset and flags of every xfeature that is present. This information will be used by debuggers to understand the XSAVE layout of the machine where the core file has been dumped, and to read XSAVE registers, especially during cross-platform debugging. The XSAVE layouts of modern AMD and Intel CPUs differ, especially since Memory Protection Keys and the AVX-512 features have been inculcated into the AMD CPUs. Since AMD never adopted (and hence never left room in the XSAVE layout for) the Intel MPX feature, tools like GDB had assumed a fixed XSAVE layout matching that of Intel (based on the XCR0 mask). Hence, core dumps from AMD CPUs didn't match the known size for the XCR0 mask. This resulted in GDB and other tools not being able to access the values of the AVX-512 and PKRU registers on AMD CPUs. To solve this, an interim solution has been accepted into GDB, and is already a part of GDB 14, see https://sourceware.org/pipermail/gdb-patches/2023-March/198081.html. But it depends on heuristics based on the total XSAVE register set size and the XCR0 mask to infer the layouts of the various register blocks for core dumps, and hence, is not a foolproof mechanism to determine the layout of the XSAVE area. Therefore, add a new core dump note in order to allow GDB/LLDB and other relevant tools to determine the layout of the XSAVE area of the machine where the corefile was dumped. The new core dump note (which is being proposed as a per-process .note section), NT_X86_XSAVE_LAYOUT (0x205) contains an array of structures. Each structure describes an individual extended feature containing offset, size and flags in this format: struct x86_xfeat_component { u32 type; u32 size; u32 offset; u32 flags; }; and in an independent manner, allowing for future extensions without depending on hw arch specifics like CPUID etc. [ bp: Massage commit message, zap trailing whitespace. ] Co-developed-by: Jini Susan George Signed-off-by: Jini Susan George Co-developed-by: Borislav Petkov (AMD) Signed-off-by: Borislav Petkov (AMD) Signed-off-by: Vignesh Balasubramanian Link: https://lore.kernel.org/r/20240725161017.112111-2-vigbalas@amd.com --- include/uapi/linux/elf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux/elf.h') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index b54b313bcf07..e30a9b47dc87 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -411,6 +411,7 @@ typedef struct elf64_shdr { #define NT_X86_XSTATE 0x202 /* x86 extended state using xsave */ /* Old binutils treats 0x203 as a CET state */ #define NT_X86_SHSTK 0x204 /* x86 SHSTK state */ +#define NT_X86_XSAVE_LAYOUT 0x205 /* XSAVE layout description */ #define NT_S390_HIGH_GPRS 0x300 /* s390 upper register halves */ #define NT_S390_TIMER 0x301 /* s390 timer register */ #define NT_S390_TODCMP 0x302 /* s390 TOD clock comparator register */ -- cgit v1.2.3 From 17519819926211e6b2834e00e4554bec0daf22ac Mon Sep 17 00:00:00 2001 From: Joey Gouly Date: Thu, 22 Aug 2024 16:11:03 +0100 Subject: arm64/ptrace: add support for FEAT_POE Add a regset for POE containing POR_EL0. Signed-off-by: Joey Gouly Cc: Catalin Marinas Cc: Will Deacon Reviewed-by: Mark Brown Reviewed-by: Catalin Marinas Reviewed-by: Anshuman Khandual Link: https://lore.kernel.org/r/20240822151113.1479789-21-joey.gouly@arm.com Signed-off-by: Will Deacon --- arch/arm64/kernel/ptrace.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/elf.h | 1 + 2 files changed, 47 insertions(+) (limited to 'include/uapi/linux/elf.h') diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 0d022599eb61..b756578aeaee 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1440,6 +1440,39 @@ static int tagged_addr_ctrl_set(struct task_struct *target, const struct } #endif +#ifdef CONFIG_ARM64_POE +static int poe_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + if (!system_supports_poe()) + return -EINVAL; + + return membuf_write(&to, &target->thread.por_el0, + sizeof(target->thread.por_el0)); +} + +static int poe_set(struct task_struct *target, const struct + user_regset *regset, unsigned int pos, + unsigned int count, const void *kbuf, const + void __user *ubuf) +{ + int ret; + long ctrl; + + if (!system_supports_poe()) + return -EINVAL; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1); + if (ret) + return ret; + + target->thread.por_el0 = ctrl; + + return 0; +} +#endif + enum aarch64_regset { REGSET_GPR, REGSET_FPR, @@ -1469,6 +1502,9 @@ enum aarch64_regset { #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI REGSET_TAGGED_ADDR_CTRL, #endif +#ifdef CONFIG_ARM64_POE + REGSET_POE +#endif }; static const struct user_regset aarch64_regsets[] = { @@ -1628,6 +1664,16 @@ static const struct user_regset aarch64_regsets[] = { .set = tagged_addr_ctrl_set, }, #endif +#ifdef CONFIG_ARM64_POE + [REGSET_POE] = { + .core_note_type = NT_ARM_POE, + .n = 1, + .size = sizeof(long), + .align = sizeof(long), + .regset_get = poe_get, + .set = poe_set, + }, +#endif }; static const struct user_regset_view user_aarch64_view = { diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index b54b313bcf07..81762ff3c99e 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -441,6 +441,7 @@ typedef struct elf64_shdr { #define NT_ARM_ZA 0x40c /* ARM SME ZA registers */ #define NT_ARM_ZT 0x40d /* ARM SME ZT registers */ #define NT_ARM_FPMR 0x40e /* ARM floating point mode register */ +#define NT_ARM_POE 0x40f /* ARM POE registers */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ -- cgit v1.2.3