From 5fa31af31e726c7f5a8f84800153054ca499338a Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Tue, 21 Nov 2023 08:07:30 -0800 Subject: x86/bugs: Rename CONFIG_CALL_DEPTH_TRACKING => CONFIG_MITIGATION_CALL_DEPTH_TRACKING Step 3/10 of the namespace unification of CPU mitigations related Kconfig options. Suggested-by: Josh Poimboeuf Signed-off-by: Breno Leitao Signed-off-by: Ingo Molnar Acked-by: Josh Poimboeuf Cc: Linus Torvalds Link: https://lore.kernel.org/r/20231121160740.1249350-4-leitao@debian.org --- tools/arch/x86/include/asm/disabled-features.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 702d93fdd10e..c1d3a5795618 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -69,7 +69,7 @@ # define DISABLE_UNRET (1 << (X86_FEATURE_UNRET & 31)) #endif -#ifdef CONFIG_CALL_DEPTH_TRACKING +#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING # define DISABLE_CALL_DEPTH_TRACKING 0 #else # define DISABLE_CALL_DEPTH_TRACKING (1 << (X86_FEATURE_CALL_DEPTH & 31)) -- cgit v1.2.3-70-g09d2 From ea4654e0885348f0faa47f6d7b44a08d75ad16e9 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Tue, 21 Nov 2023 08:07:31 -0800 Subject: x86/bugs: Rename CONFIG_PAGE_TABLE_ISOLATION => CONFIG_MITIGATION_PAGE_TABLE_ISOLATION Step 4/10 of the namespace unification of CPU mitigations related Kconfig options. [ mingo: Converted new uses that got added since the series was posted. ] Suggested-by: Josh Poimboeuf Signed-off-by: Breno Leitao Signed-off-by: Ingo Molnar Acked-by: Josh Poimboeuf Cc: Linus Torvalds Link: https://lore.kernel.org/r/20231121160740.1249350-5-leitao@debian.org --- Documentation/arch/x86/pti.rst | 6 +++--- arch/x86/Kconfig | 2 +- arch/x86/boot/compressed/ident_map_64.c | 4 ++-- arch/x86/entry/calling.h | 8 ++++---- arch/x86/entry/entry_64.S | 6 +++--- arch/x86/include/asm/disabled-features.h | 2 +- arch/x86/include/asm/pgalloc.h | 2 +- arch/x86/include/asm/pgtable-3level.h | 2 +- arch/x86/include/asm/pgtable.h | 18 +++++++++--------- arch/x86/include/asm/pgtable_64.h | 3 ++- arch/x86/include/asm/processor-flags.h | 2 +- arch/x86/include/asm/pti.h | 2 +- arch/x86/kernel/dumpstack.c | 2 +- arch/x86/kernel/head_32.S | 4 ++-- arch/x86/kernel/head_64.S | 2 +- arch/x86/kernel/ldt.c | 8 ++++---- arch/x86/mm/Makefile | 2 +- arch/x86/mm/debug_pagetables.c | 4 ++-- arch/x86/mm/dump_pagetables.c | 4 ++-- arch/x86/mm/pgtable.c | 4 ++-- arch/x86/mm/tlb.c | 10 +++++----- include/linux/pti.h | 2 +- tools/arch/x86/include/asm/disabled-features.h | 2 +- 23 files changed, 51 insertions(+), 50 deletions(-) (limited to 'tools') diff --git a/Documentation/arch/x86/pti.rst b/Documentation/arch/x86/pti.rst index e08d35177bc0..57e8392f61d3 100644 --- a/Documentation/arch/x86/pti.rst +++ b/Documentation/arch/x86/pti.rst @@ -26,9 +26,9 @@ comments in pti.c). This approach helps to ensure that side-channel attacks leveraging the paging structures do not function when PTI is enabled. It can be -enabled by setting CONFIG_PAGE_TABLE_ISOLATION=y at compile time. -Once enabled at compile-time, it can be disabled at boot with the -'nopti' or 'pti=' kernel parameters (see kernel-parameters.txt). +enabled by setting CONFIG_MITIGATION_PAGE_TABLE_ISOLATION=y at compile +time. Once enabled at compile-time, it can be disabled at boot with +the 'nopti' or 'pti=' kernel parameters (see kernel-parameters.txt). Page Table Management ===================== diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b4a703d45700..a1c047004390 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2484,7 +2484,7 @@ menuconfig SPECULATION_MITIGATIONS if SPECULATION_MITIGATIONS -config PAGE_TABLE_ISOLATION +config MITIGATION_PAGE_TABLE_ISOLATION bool "Remove the kernel mapping in user mode" default y depends on (X86_64 || X86_PAE) diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index d040080d7edb..ff09ca6dbb87 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -8,8 +8,8 @@ * Copyright (C) 2016 Kees Cook */ -/* No PAGE_TABLE_ISOLATION support needed either: */ -#undef CONFIG_PAGE_TABLE_ISOLATION +/* No MITIGATION_PAGE_TABLE_ISOLATION support needed either: */ +#undef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION #include "error.h" #include "misc.h" diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 9f1d94790a54..7ac2d6f946ed 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -142,10 +142,10 @@ For 32-bit we have the following conventions - kernel is built with .endif .endm -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* - * PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two + * MITIGATION_PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two * halves: */ #define PTI_USER_PGTABLE_BIT PAGE_SHIFT @@ -160,7 +160,7 @@ For 32-bit we have the following conventions - kernel is built with .macro ADJUST_KERNEL_CR3 reg:req ALTERNATIVE "", "SET_NOFLUSH_BIT \reg", X86_FEATURE_PCID - /* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */ + /* Clear PCID and "MITIGATION_PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */ andq $(~PTI_USER_PGTABLE_AND_PCID_MASK), \reg .endm @@ -275,7 +275,7 @@ For 32-bit we have the following conventions - kernel is built with .Lend_\@: .endm -#else /* CONFIG_PAGE_TABLE_ISOLATION=n: */ +#else /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION=n: */ .macro SWITCH_TO_KERNEL_CR3 scratch_reg:req .endm diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index c40f89ab1b4c..d08cb3865c8a 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -562,7 +562,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) #ifdef CONFIG_XEN_PV ALTERNATIVE "", "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV #endif -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION ALTERNATIVE "", "jmp .Lpti_restore_regs_and_return_to_usermode", X86_FEATURE_PTI #endif @@ -578,7 +578,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) jnz .Lnative_iret ud2 -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION .Lpti_restore_regs_and_return_to_usermode: POP_REGS pop_rdi=0 @@ -1096,7 +1096,7 @@ SYM_CODE_END(error_return) * * Registers: * %r14: Used to save/restore the CR3 of the interrupted context - * when PAGE_TABLE_ISOLATION is in use. Do not clobber. + * when MITIGATION_PAGE_TABLE_ISOLATION is in use. Do not clobber. */ SYM_CODE_START(asm_exc_nmi) UNWIND_HINT_IRET_ENTRY diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index c1d3a5795618..fb604ec95a5f 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -44,7 +44,7 @@ # define DISABLE_LA57 (1<<(X86_FEATURE_LA57 & 31)) #endif -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION # define DISABLE_PTI 0 #else # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index c7ec5bb88334..dcd836b59beb 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -34,7 +34,7 @@ static inline void paravirt_release_p4d(unsigned long pfn) {} */ extern gfp_t __userpte_alloc_gfp; -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* * Instead of one PGD, we acquire two PGDs. Being order-1, it is * both 8k in size and 8k-aligned. That lets us just flip bit 12 diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index 9e7c0b719c3c..dabafba957ea 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -52,7 +52,7 @@ static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) static inline void native_set_pud(pud_t *pudp, pud_t pud) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION pud.p4d.pgd = pti_set_user_pgtbl(&pudp->p4d.pgd, pud.p4d.pgd); #endif pxx_xchg64(pud, pudp, native_pud_val(pud)); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 9d077bca6a10..df0f7d4a96f3 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -909,7 +909,7 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, pmd_t *populate_extra_pmd(unsigned long vaddr); pte_t *populate_extra_pte(unsigned long vaddr); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd); /* @@ -923,12 +923,12 @@ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) return pgd; return __pti_set_user_pgtbl(pgdp, pgd); } -#else /* CONFIG_PAGE_TABLE_ISOLATION */ +#else /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { return pgd; } -#endif /* CONFIG_PAGE_TABLE_ISOLATION */ +#endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ #endif /* __ASSEMBLY__ */ @@ -1131,7 +1131,7 @@ static inline int p4d_bad(p4d_t p4d) { unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER; - if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) + if (IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; return (p4d_flags(p4d) & ~ignore_flags) != 0; @@ -1177,7 +1177,7 @@ static inline int pgd_bad(pgd_t pgd) if (!pgtable_l5_enabled()) return 0; - if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) + if (IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE; @@ -1422,9 +1422,9 @@ static inline bool pgdp_maps_userspace(void *__ptr) #define pgd_leaf pgd_large static inline int pgd_large(pgd_t pgd) { return 0; } -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* - * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages + * All top-level MITIGATION_PAGE_TABLE_ISOLATION page tables are order-1 pages * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and * the user one is in the last 4k. To switch between them, you * just need to flip the 12th bit in their addresses. @@ -1469,7 +1469,7 @@ static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) { return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); } -#endif /* CONFIG_PAGE_TABLE_ISOLATION */ +#endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ /* * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); @@ -1484,7 +1484,7 @@ static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count) { memcpy(dst, src, count * sizeof(pgd_t)); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION if (!static_cpu_has(X86_FEATURE_PTI)) return; /* Clone the user space pgd as well */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 24af25b1551a..7e9db77231ac 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -143,7 +143,8 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) { pgd_t pgd; - if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) { + if (pgtable_l5_enabled() || + !IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) { WRITE_ONCE(*p4dp, p4d); return; } diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index d8cccadc83a6..e5f204b9b33d 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -51,7 +51,7 @@ #define CR3_NOFLUSH 0 #endif -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION # define X86_CR3_PTI_PCID_USER_BIT 11 #endif diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h index 07375b476c4f..ab167c96b9ab 100644 --- a/arch/x86/include/asm/pti.h +++ b/arch/x86/include/asm/pti.h @@ -3,7 +3,7 @@ #define _ASM_X86_PTI_H #ifndef __ASSEMBLY__ -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION extern void pti_init(void); extern void pti_check_boottime_disable(void); extern void pti_finalize(void); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index f18ca44c904b..44a91ef5a23b 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -410,7 +410,7 @@ static void __die_header(const char *str, struct pt_regs *regs, long err) IS_ENABLED(CONFIG_SMP) ? " SMP" : "", debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "", IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "", - IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION) ? + IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION) ? (boot_cpu_has(X86_FEATURE_PTI) ? " PTI" : " NOPTI") : ""); } NOKPROBE_SYMBOL(__die_header); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 487ac57e2c81..b50f3641c4d6 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -414,7 +414,7 @@ __REFDATA .align 4 SYM_DATA(initial_code, .long i386_start_kernel) -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION #define PGD_ALIGN (2 * PAGE_SIZE) #define PTI_USER_PGD_FILL 1024 #else @@ -474,7 +474,7 @@ SYM_DATA_START(initial_page_table) # endif .align PAGE_SIZE /* needs to be page-sized too */ -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* * PTI needs another page so sync_initial_pagetable() works correctly * and does not scribble over the data which is placed behind the diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index d4918d03efb4..cd54313706a2 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -622,7 +622,7 @@ SYM_CODE_END(vc_no_ghcb) #define SYM_DATA_START_PAGE_ALIGNED(name) \ SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE) -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* * Each PGD needs to be 8k long and 8k aligned. We do not * ever go out to userspace with these, so we do not diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 7a814b41402d..0f19ef355f5f 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -184,7 +184,7 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries) return new_ldt; } -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION static void do_sanity_check(struct mm_struct *mm, bool had_kernel_mapping, @@ -377,7 +377,7 @@ static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt) flush_tlb_mm_range(mm, va, va + nr_pages * PAGE_SIZE, PAGE_SHIFT, false); } -#else /* !CONFIG_PAGE_TABLE_ISOLATION */ +#else /* !CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ static int map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) @@ -388,11 +388,11 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt) { } -#endif /* CONFIG_PAGE_TABLE_ISOLATION */ +#endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ static void free_ldt_pgtables(struct mm_struct *mm) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION struct mmu_gather tlb; unsigned long start = LDT_BASE_ADDR; unsigned long end = LDT_END_ADDR; diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index c80febc44cd2..031cd10ed17f 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -60,7 +60,7 @@ obj-$(CONFIG_NUMA_EMU) += numa_emulation.o obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o -obj-$(CONFIG_PAGE_TABLE_ISOLATION) += pti.o +obj-$(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION) += pti.o obj-$(CONFIG_X86_MEM_ENCRYPT) += mem_encrypt.o obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_amd.o diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c index b43301cb2a80..ae5c213a1cb0 100644 --- a/arch/x86/mm/debug_pagetables.c +++ b/arch/x86/mm/debug_pagetables.c @@ -22,7 +22,7 @@ static int ptdump_curknl_show(struct seq_file *m, void *v) DEFINE_SHOW_ATTRIBUTE(ptdump_curknl); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION static int ptdump_curusr_show(struct seq_file *m, void *v) { if (current->mm->pgd) @@ -54,7 +54,7 @@ static int __init pt_dump_debug_init(void) debugfs_create_file("current_kernel", 0400, dir, NULL, &ptdump_curknl_fops); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION debugfs_create_file("current_user", 0400, dir, NULL, &ptdump_curusr_fops); #endif diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index e1b599ecbbc2..b7b88c1d91ec 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -408,7 +408,7 @@ void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm, bool user) { pgd_t *pgd = mm->pgd; -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION if (user && boot_cpu_has(X86_FEATURE_PTI)) pgd = kernel_to_user_pgdp(pgd); #endif @@ -418,7 +418,7 @@ EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs); void ptdump_walk_user_pgd_level_checkwx(void) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION pgd_t *pgd = INIT_PGD; if (!(__supported_pte_mask & _PAGE_NX) || diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 0cbc1b8e8e3d..cceb779d882d 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -293,7 +293,7 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) for (i = 0; i < PREALLOCATED_PMDS; i++) mop_up_one_pmd(mm, &pgdp[i]); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION if (!boot_cpu_has(X86_FEATURE_PTI)) return; @@ -325,7 +325,7 @@ static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[]) } } -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION static void pgd_prepopulate_user_pmd(struct mm_struct *mm, pgd_t *k_pgd, pmd_t *pmds[]) { diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 5768d386efab..4af930947380 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -89,10 +89,10 @@ #define CR3_HW_ASID_BITS 12 /* - * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for + * When enabled, MITIGATION_PAGE_TABLE_ISOLATION consumes a single bit for * user/kernel switches */ -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION # define PTI_CONSUMED_PCID_BITS 1 #else # define PTI_CONSUMED_PCID_BITS 0 @@ -114,7 +114,7 @@ static inline u16 kern_pcid(u16 asid) { VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* * Make sure that the dynamic ASID space does not conflict with the * bit we are using to switch between user and kernel ASIDs. @@ -149,7 +149,7 @@ static inline u16 kern_pcid(u16 asid) static inline u16 user_pcid(u16 asid) { u16 ret = kern_pcid(asid); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION ret |= 1 << X86_CR3_PTI_PCID_USER_BIT; #endif return ret; @@ -262,7 +262,7 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen, static inline void invalidate_user_asid(u16 asid) { /* There is no user ASID if address space separation is off */ - if (!IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) + if (!IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) return; /* diff --git a/include/linux/pti.h b/include/linux/pti.h index 1a941efcaa62..1fbf9d6c20ef 100644 --- a/include/linux/pti.h +++ b/include/linux/pti.h @@ -2,7 +2,7 @@ #ifndef _INCLUDE_PTI_H #define _INCLUDE_PTI_H -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION #include #else static inline void pti_init(void) { } diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index c1d3a5795618..fb604ec95a5f 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -44,7 +44,7 @@ # define DISABLE_LA57 (1<<(X86_FEATURE_LA57 & 31)) #endif -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION # define DISABLE_PTI 0 #else # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) -- cgit v1.2.3-70-g09d2 From aefb2f2e619b6c334bcb31de830aa00ba0b11129 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Tue, 21 Nov 2023 08:07:32 -0800 Subject: x86/bugs: Rename CONFIG_RETPOLINE => CONFIG_MITIGATION_RETPOLINE Step 5/10 of the namespace unification of CPU mitigations related Kconfig options. [ mingo: Converted a few more uses in comments/messages as well. ] Suggested-by: Josh Poimboeuf Signed-off-by: Breno Leitao Signed-off-by: Ingo Molnar Reviewed-by: Ariel Miculas Acked-by: Josh Poimboeuf Cc: Linus Torvalds Link: https://lore.kernel.org/r/20231121160740.1249350-6-leitao@debian.org --- Documentation/admin-guide/hw-vuln/spectre.rst | 8 ++++---- Documentation/admin-guide/kernel-parameters.txt | 4 ++-- arch/x86/Kconfig | 6 +++--- arch/x86/Makefile | 4 ++-- arch/x86/entry/vdso/Makefile | 4 ++-- arch/x86/include/asm/disabled-features.h | 2 +- arch/x86/include/asm/linkage.h | 8 ++++---- arch/x86/include/asm/nospec-branch.h | 8 ++++---- arch/x86/kernel/alternative.c | 6 +++--- arch/x86/kernel/cpu/bugs.c | 6 +++--- arch/x86/kernel/ftrace.c | 2 +- arch/x86/kernel/kprobes/opt.c | 2 +- arch/x86/kernel/vmlinux.lds.S | 4 ++-- arch/x86/kvm/mmu/mmu.c | 2 +- arch/x86/kvm/mmu/mmu_internal.h | 2 +- arch/x86/kvm/svm/svm.c | 2 +- arch/x86/kvm/svm/vmenter.S | 4 ++-- arch/x86/kvm/vmx/vmx.c | 2 +- arch/x86/lib/Makefile | 2 +- arch/x86/net/bpf_jit_comp.c | 2 +- arch/x86/net/bpf_jit_comp32.c | 2 +- arch/x86/purgatory/Makefile | 2 +- include/linux/compiler-gcc.h | 2 +- include/linux/indirect_call_wrapper.h | 2 +- include/linux/module.h | 2 +- include/net/netfilter/nf_tables_core.h | 2 +- include/net/tc_wrapper.h | 2 +- kernel/trace/ring_buffer.c | 2 +- net/netfilter/Makefile | 2 +- net/netfilter/nf_tables_core.c | 6 +++--- net/netfilter/nft_ct.c | 4 ++-- net/netfilter/nft_lookup.c | 2 +- net/sched/sch_api.c | 2 +- scripts/Makefile.lib | 2 +- scripts/generate_rust_target.rs | 2 +- scripts/mod/modpost.c | 2 +- tools/arch/x86/include/asm/disabled-features.h | 2 +- tools/objtool/arch/x86/special.c | 2 +- tools/objtool/check.c | 2 +- 39 files changed, 62 insertions(+), 62 deletions(-) (limited to 'tools') diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst index 32a8893e5617..cce768afec6b 100644 --- a/Documentation/admin-guide/hw-vuln/spectre.rst +++ b/Documentation/admin-guide/hw-vuln/spectre.rst @@ -473,8 +473,8 @@ Spectre variant 2 -mindirect-branch=thunk-extern -mindirect-branch-register options. If the kernel is compiled with a Clang compiler, the compiler needs to support -mretpoline-external-thunk option. The kernel config - CONFIG_RETPOLINE needs to be turned on, and the CPU needs to run with - the latest updated microcode. + CONFIG_MITIGATION_RETPOLINE needs to be turned on, and the CPU needs + to run with the latest updated microcode. On Intel Skylake-era systems the mitigation covers most, but not all, cases. See :ref:`[3] ` for more details. @@ -609,8 +609,8 @@ kernel command line. Selecting 'on' will, and 'auto' may, choose a mitigation method at run time according to the CPU, the available microcode, the setting of the - CONFIG_RETPOLINE configuration option, and the - compiler with which the kernel was built. + CONFIG_MITIGATION_RETPOLINE configuration option, + and the compiler with which the kernel was built. Selecting 'on' will also enable the mitigation against user space to user space task attacks. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index e0891ac76ab3..d93f403777f2 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -6007,8 +6007,8 @@ Selecting 'on' will, and 'auto' may, choose a mitigation method at run time according to the CPU, the available microcode, the setting of the - CONFIG_RETPOLINE configuration option, and the - compiler with which the kernel was built. + CONFIG_MITIGATION_RETPOLINE configuration option, + and the compiler with which the kernel was built. Selecting 'on' will also enable the mitigation against user space to user space task attacks. diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index a1c047004390..2a3ebd679b0e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2457,7 +2457,7 @@ config CALL_PADDING config FINEIBT def_bool y - depends on X86_KERNEL_IBT && CFI_CLANG && RETPOLINE + depends on X86_KERNEL_IBT && CFI_CLANG && MITIGATION_RETPOLINE select CALL_PADDING config HAVE_CALL_THUNKS @@ -2495,7 +2495,7 @@ config MITIGATION_PAGE_TABLE_ISOLATION See Documentation/arch/x86/pti.rst for more details. -config RETPOLINE +config MITIGATION_RETPOLINE bool "Avoid speculative indirect branches in kernel" select OBJTOOL if HAVE_OBJTOOL default y @@ -2507,7 +2507,7 @@ config RETPOLINE config RETHUNK bool "Enable return-thunks" - depends on RETPOLINE && CC_HAS_RETURN_THUNK + depends on MITIGATION_RETPOLINE && CC_HAS_RETURN_THUNK select OBJTOOL if HAVE_OBJTOOL default y if X86_64 help diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 1a068de12a56..b8d23ed059fb 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -192,7 +192,7 @@ KBUILD_CFLAGS += -Wno-sign-compare KBUILD_CFLAGS += -fno-asynchronous-unwind-tables # Avoid indirect branches in kernel to deal with Spectre -ifdef CONFIG_RETPOLINE +ifdef CONFIG_MITIGATION_RETPOLINE KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) # Additionally, avoid generating expensive indirect jumps which # are subject to retpolines for small number of switch cases. @@ -301,7 +301,7 @@ vdso-install-$(CONFIG_IA32_EMULATION) += arch/x86/entry/vdso/vdso32.so.dbg archprepare: checkbin checkbin: -ifdef CONFIG_RETPOLINE +ifdef CONFIG_MITIGATION_RETPOLINE ifeq ($(RETPOLINE_CFLAGS),) @echo "You are building kernel with non-retpoline compiler." >&2 @echo "Please update your compiler." >&2 diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index b1b8dd1608f7..c4df99aa1615 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -87,7 +87,7 @@ CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ -fno-omit-frame-pointer -foptimize-sibling-calls \ -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO -ifdef CONFIG_RETPOLINE +ifdef CONFIG_MITIGATION_RETPOLINE ifneq ($(RETPOLINE_VDSO_CFLAGS),) CFL += $(RETPOLINE_VDSO_CFLAGS) endif @@ -164,7 +164,7 @@ KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) KBUILD_CFLAGS_32 += -fno-omit-frame-pointer KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING -ifdef CONFIG_RETPOLINE +ifdef CONFIG_MITIGATION_RETPOLINE ifneq ($(RETPOLINE_VDSO_CFLAGS),) KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS) endif diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index fb604ec95a5f..24e4010c33b6 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -50,7 +50,7 @@ # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) #endif -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE # define DISABLE_RETPOLINE 0 #else # define DISABLE_RETPOLINE ((1 << (X86_FEATURE_RETPOLINE & 31)) | \ diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 571fe4d2d232..c5165204c66f 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -42,25 +42,25 @@ #if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) #define RET jmp __x86_return_thunk -#else /* CONFIG_RETPOLINE */ +#else /* CONFIG_MITIGATION_RETPOLINE */ #ifdef CONFIG_SLS #define RET ret; int3 #else #define RET ret #endif -#endif /* CONFIG_RETPOLINE */ +#endif /* CONFIG_MITIGATION_RETPOLINE */ #else /* __ASSEMBLY__ */ #if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) #define ASM_RET "jmp __x86_return_thunk\n\t" -#else /* CONFIG_RETPOLINE */ +#else /* CONFIG_MITIGATION_RETPOLINE */ #ifdef CONFIG_SLS #define ASM_RET "ret; int3\n\t" #else #define ASM_RET "ret\n\t" #endif -#endif /* CONFIG_RETPOLINE */ +#endif /* CONFIG_MITIGATION_RETPOLINE */ #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 59810237eb42..32680cb72003 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -241,7 +241,7 @@ * instruction irrespective of kCFI. */ .macro JMP_NOSPEC reg:req -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE __CS_PREFIX \reg jmp __x86_indirect_thunk_\reg #else @@ -251,7 +251,7 @@ .endm .macro CALL_NOSPEC reg:req -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE __CS_PREFIX \reg call __x86_indirect_thunk_\reg #else @@ -378,7 +378,7 @@ static inline void call_depth_return_thunk(void) {} #endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */ -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_thunk_ ## reg; @@ -399,7 +399,7 @@ static inline void call_depth_return_thunk(void) {} /* * Inline asm uses the %V modifier which is only in newer GCC - * which is ensured when CONFIG_RETPOLINE is defined. + * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined. */ # define CALL_NOSPEC \ ALTERNATIVE_2( \ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 55e205b21271..08c182f5a0f4 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -544,7 +544,7 @@ static inline bool is_jcc32(struct insn *insn) return insn->opcode.bytes[0] == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80; } -#if defined(CONFIG_RETPOLINE) && defined(CONFIG_OBJTOOL) +#if defined(CONFIG_MITIGATION_RETPOLINE) && defined(CONFIG_OBJTOOL) /* * CALL/JMP *%\reg @@ -844,12 +844,12 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) void __init_or_module noinline apply_returns(s32 *start, s32 *end) { } #endif /* CONFIG_RETHUNK */ -#else /* !CONFIG_RETPOLINE || !CONFIG_OBJTOOL */ +#else /* !CONFIG_MITIGATION_RETPOLINE || !CONFIG_OBJTOOL */ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { } void __init_or_module noinline apply_returns(s32 *start, s32 *end) { } -#endif /* CONFIG_RETPOLINE && CONFIG_OBJTOOL */ +#endif /* CONFIG_MITIGATION_RETPOLINE && CONFIG_OBJTOOL */ #ifdef CONFIG_X86_KERNEL_IBT diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index b906ed4f3091..fc46fd6447f9 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1103,7 +1103,7 @@ static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init = static enum spectre_v2_user_mitigation spectre_v2_user_ibpb __ro_after_init = SPECTRE_V2_USER_NONE; -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE static bool spectre_v2_bad_module; bool retpoline_module_ok(bool has_retpoline) @@ -1416,7 +1416,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC || cmd == SPECTRE_V2_CMD_EIBRS_LFENCE || cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) && - !IS_ENABLED(CONFIG_RETPOLINE)) { + !IS_ENABLED(CONFIG_MITIGATION_RETPOLINE)) { pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; @@ -1470,7 +1470,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void) { - if (!IS_ENABLED(CONFIG_RETPOLINE)) { + if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE)) { pr_err("Kernel not compiled with retpoline; no mitigation available!"); return SPECTRE_V2_NONE; } diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 12df54ff0e81..93bc52d4a472 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -307,7 +307,7 @@ union ftrace_op_code_union { } __attribute__((packed)); }; -#define RET_SIZE (IS_ENABLED(CONFIG_RETPOLINE) ? 5 : 1 + IS_ENABLED(CONFIG_SLS)) +#define RET_SIZE (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) ? 5 : 1 + IS_ENABLED(CONFIG_SLS)) static unsigned long create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 517821b48391..36d6809c6c9e 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -324,7 +324,7 @@ static int can_optimize(unsigned long paddr) * However, the kernel built with retpolines or IBT has jump * tables disabled so the check can be skipped altogether. */ - if (!IS_ENABLED(CONFIG_RETPOLINE) && + if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && !IS_ENABLED(CONFIG_X86_KERNEL_IBT) && insn_is_indirect_jump(&insn)) return 0; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index a349dbfc6d5a..bb2ec03f046d 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -132,7 +132,7 @@ SECTIONS LOCK_TEXT KPROBES_TEXT SOFTIRQENTRY_TEXT -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE *(.text..__x86.indirect_thunk) *(.text..__x86.return_thunk) #endif @@ -267,7 +267,7 @@ SECTIONS } #endif -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE /* * List of instructions that call/jmp/jcc to retpoline thunks * __x86_indirect_thunk_*(). These instructions can be patched along diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 0b1f991b9a31..6fdc1cf5c33d 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -263,7 +263,7 @@ static unsigned long get_guest_cr3(struct kvm_vcpu *vcpu) static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) { - if (IS_ENABLED(CONFIG_RETPOLINE) && mmu->get_guest_pgd == get_guest_cr3) + if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && mmu->get_guest_pgd == get_guest_cr3) return kvm_read_cr3(vcpu); return mmu->get_guest_pgd(vcpu); diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index decc1f153669..bf73a121c5ef 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -312,7 +312,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, if (!prefetch) vcpu->stat.pf_taken++; - if (IS_ENABLED(CONFIG_RETPOLINE) && fault.is_tdp) + if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && fault.is_tdp) r = kvm_tdp_page_fault(vcpu, &fault); else r = vcpu->arch.mmu->page_fault(vcpu, &fault); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 7fb51424fc74..b2751b9acf03 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3455,7 +3455,7 @@ int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code) if (!svm_check_exit_valid(exit_code)) return svm_handle_invalid_exit(vcpu, exit_code); -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE if (exit_code == SVM_EXIT_MSR) return msr_interception(vcpu); else if (exit_code == SVM_EXIT_VINTR) diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index ef2ebabb059c..b9e08837ab96 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -207,7 +207,7 @@ SYM_FUNC_START(__svm_vcpu_run) 7: vmload %_ASM_AX 8: -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE #endif @@ -344,7 +344,7 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) /* Pop @svm to RDI, guest registers have been saved already. */ pop %_ASM_DI -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE #endif diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index e0f86f11c345..4e1003ba380a 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6544,7 +6544,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) if (exit_reason.basic >= kvm_vmx_max_exit_handlers) goto unexpected_vmexit; -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE if (exit_reason.basic == EXIT_REASON_MSR_WRITE) return kvm_emulate_wrmsr(vcpu); else if (exit_reason.basic == EXIT_REASON_PREEMPTION_TIMER) diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index ea3a28e7b613..72cc9c90e9f3 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -49,7 +49,7 @@ lib-$(CONFIG_ARCH_HAS_COPY_MC) += copy_mc.o copy_mc_64.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o -lib-$(CONFIG_RETPOLINE) += retpoline.o +lib-$(CONFIG_MITIGATION_RETPOLINE) += retpoline.o obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o obj-y += iomem.o diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 144a5839acfe..ad1396b1df25 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -469,7 +469,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); } else { EMIT2(0xFF, 0xE0 + reg); /* jmp *%\reg */ - if (IS_ENABLED(CONFIG_RETPOLINE) || IS_ENABLED(CONFIG_SLS)) + if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) || IS_ENABLED(CONFIG_SLS)) EMIT1(0xCC); /* int3 */ } diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index b18ce19981ec..c10083a8e68e 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1273,7 +1273,7 @@ static int emit_jmp_edx(u8 **pprog, u8 *ip) u8 *prog = *pprog; int cnt = 0; -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE EMIT1_off32(0xE9, (u8 *)__x86_indirect_thunk_edx - (ip + 5)); #else EMIT2(0xFF, 0xE2); diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 08aa0f25f12a..bc31863c5ee6 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -61,7 +61,7 @@ ifdef CONFIG_STACKPROTECTOR_STRONG PURGATORY_CFLAGS_REMOVE += -fstack-protector-strong endif -ifdef CONFIG_RETPOLINE +ifdef CONFIG_MITIGATION_RETPOLINE PURGATORY_CFLAGS_REMOVE += $(RETPOLINE_CFLAGS) endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 2ceba3fe4ec1..d24f29091f4b 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -35,7 +35,7 @@ (typeof(ptr)) (__ptr + (off)); \ }) -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE #define __noretpoline __attribute__((__indirect_branch__("keep"))) #endif diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index c1c76a70a6ce..fe050dab55a3 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -2,7 +2,7 @@ #ifndef _LINUX_INDIRECT_CALL_WRAPPER_H #define _LINUX_INDIRECT_CALL_WRAPPER_H -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE /* * INDIRECT_CALL_$NR - wrapper for indirect calls with $NR known builtin diff --git a/include/linux/module.h b/include/linux/module.h index 9cd0009bd050..087b369e8f17 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -885,7 +885,7 @@ static inline void module_bug_finalize(const Elf_Ehdr *hdr, static inline void module_bug_cleanup(struct module *mod) {} #endif /* CONFIG_GENERIC_BUG */ -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE extern bool retpoline_module_ok(bool has_retpoline); #else static inline bool retpoline_module_ok(bool has_retpoline) diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 780a5f6ad4a6..ff27cb2e1662 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -93,7 +93,7 @@ extern const struct nft_set_type nft_set_bitmap_type; extern const struct nft_set_type nft_set_pipapo_type; extern const struct nft_set_type nft_set_pipapo_avx2_type; -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext); bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, diff --git a/include/net/tc_wrapper.h b/include/net/tc_wrapper.h index a6d481b5bcbc..a13ba0326d5e 100644 --- a/include/net/tc_wrapper.h +++ b/include/net/tc_wrapper.h @@ -4,7 +4,7 @@ #include -#if IS_ENABLED(CONFIG_RETPOLINE) +#if IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) #include #include diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 9286f88fcd32..9cb69332921d 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1156,7 +1156,7 @@ static inline u64 rb_time_stamp(struct trace_buffer *buffer) u64 ts; /* Skip retpolines :-( */ - if (IS_ENABLED(CONFIG_RETPOLINE) && likely(buffer->clock == trace_clock_local)) + if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && likely(buffer->clock == trace_clock_local)) ts = trace_clock_local(); else ts = buffer->clock(); diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index d4958e7e7631..614815a3ed73 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -101,7 +101,7 @@ endif endif ifdef CONFIG_NFT_CT -ifdef CONFIG_RETPOLINE +ifdef CONFIG_MITIGATION_RETPOLINE nf_tables-objs += nft_ct_fast.o endif endif diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index c3e635364701..a48d5f0e2f3e 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -21,7 +21,7 @@ #include #include -#if defined(CONFIG_RETPOLINE) && defined(CONFIG_X86) +#if defined(CONFIG_MITIGATION_RETPOLINE) && defined(CONFIG_X86) static struct static_key_false nf_tables_skip_direct_calls; @@ -207,7 +207,7 @@ static void expr_call_ops_eval(const struct nft_expr *expr, struct nft_regs *regs, struct nft_pktinfo *pkt) { -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE unsigned long e; if (nf_skip_indirect_calls()) @@ -236,7 +236,7 @@ static void expr_call_ops_eval(const struct nft_expr *expr, X(e, nft_objref_map_eval); #undef X indirect_call: -#endif /* CONFIG_RETPOLINE */ +#endif /* CONFIG_MITIGATION_RETPOLINE */ expr->ops->eval(expr, regs, pkt); } diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 86bb9d7797d9..d3e66bcb2a91 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -751,7 +751,7 @@ static bool nft_ct_set_reduce(struct nft_regs_track *track, return false; } -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE static const struct nft_expr_ops nft_ct_get_fast_ops = { .type = &nft_ct_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_ct)), @@ -796,7 +796,7 @@ nft_ct_select_ops(const struct nft_ctx *ctx, return ERR_PTR(-EINVAL); if (tb[NFTA_CT_DREG]) { -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE u32 k = ntohl(nla_get_be32(tb[NFTA_CT_KEY])); switch (k) { diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 870e5b113d13..a0055f510e31 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -24,7 +24,7 @@ struct nft_lookup { struct nft_set_binding binding; }; -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE bool nft_set_do_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index e9eaf637220e..d577c9e1cb42 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -2353,7 +2353,7 @@ static struct pernet_operations psched_net_ops = { .exit = psched_net_exit, }; -#if IS_ENABLED(CONFIG_RETPOLINE) +#if IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) DEFINE_STATIC_KEY_FALSE(tc_skip_wrapper); #endif diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index ee233ef91696..615f2612a7ef 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -262,7 +262,7 @@ ifdef CONFIG_FTRACE_MCOUNT_USE_OBJTOOL objtool-args-$(CONFIG_HAVE_OBJTOOL_NOP_MCOUNT) += --mnop endif objtool-args-$(CONFIG_UNWINDER_ORC) += --orc -objtool-args-$(CONFIG_RETPOLINE) += --retpoline +objtool-args-$(CONFIG_MITIGATION_RETPOLINE) += --retpoline objtool-args-$(CONFIG_RETHUNK) += --rethunk objtool-args-$(CONFIG_SLS) += --sls objtool-args-$(CONFIG_STACK_VALIDATION) += --stackval diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs index 3c6cbe2b278d..eaf524603796 100644 --- a/scripts/generate_rust_target.rs +++ b/scripts/generate_rust_target.rs @@ -155,7 +155,7 @@ fn main() { "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128", ); let mut features = "-3dnow,-3dnowa,-mmx,+soft-float".to_string(); - if cfg.has("RETPOLINE") { + if cfg.has("MITIGATION_RETPOLINE") { features += ",+retpoline-external-thunk"; } ts.push("features", features); diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index cb6406f485a9..72fead5f973b 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1843,7 +1843,7 @@ static void add_header(struct buffer *b, struct module *mod) buf_printf(b, "\n" - "#ifdef CONFIG_RETPOLINE\n" + "#ifdef CONFIG_MITIGATION_RETPOLINE\n" "MODULE_INFO(retpoline, \"Y\");\n" "#endif\n"); diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index fb604ec95a5f..24e4010c33b6 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -50,7 +50,7 @@ # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) #endif -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE # define DISABLE_RETPOLINE 0 #else # define DISABLE_RETPOLINE ((1 << (X86_FEATURE_RETPOLINE & 31)) | \ diff --git a/tools/objtool/arch/x86/special.c b/tools/objtool/arch/x86/special.c index 29e949579ede..4134d27c696b 100644 --- a/tools/objtool/arch/x86/special.c +++ b/tools/objtool/arch/x86/special.c @@ -83,7 +83,7 @@ bool arch_support_alt_relocation(struct special_alt *special_alt, * TODO: Once we have DWARF CFI and smarter instruction decoding logic, * ensure the same register is used in the mov and jump instructions. * - * NOTE: RETPOLINE made it harder still to decode dynamic jumps. + * NOTE: MITIGATION_RETPOLINE made it harder still to decode dynamic jumps. */ struct reloc *arch_find_switch_table(struct objtool_file *file, struct instruction *insn) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 548ec3cd7c00..84067f018f7e 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3984,7 +3984,7 @@ static int validate_retpoline(struct objtool_file *file) } else continue; } else { - WARN_INSN(insn, "indirect %s found in RETPOLINE build", + WARN_INSN(insn, "indirect %s found in MITIGATION_RETPOLINE build", insn->type == INSN_JUMP_DYNAMIC ? "jump" : "call"); } -- cgit v1.2.3-70-g09d2 From ac61d43983a4fe8e3ee600eee44c40868c14340a Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Tue, 21 Nov 2023 08:07:34 -0800 Subject: x86/bugs: Rename CONFIG_CPU_UNRET_ENTRY => CONFIG_MITIGATION_UNRET_ENTRY Step 7/10 of the namespace unification of CPU mitigations related Kconfig options. Suggested-by: Josh Poimboeuf Signed-off-by: Breno Leitao Signed-off-by: Ingo Molnar Acked-by: Josh Poimboeuf Cc: Linus Torvalds Link: https://lore.kernel.org/r/20231121160740.1249350-8-leitao@debian.org --- arch/x86/Kconfig | 2 +- arch/x86/include/asm/disabled-features.h | 2 +- arch/x86/include/asm/nospec-branch.h | 6 +++--- arch/x86/kernel/cpu/amd.c | 2 +- arch/x86/kernel/cpu/bugs.c | 6 +++--- arch/x86/kernel/vmlinux.lds.S | 2 +- arch/x86/lib/retpoline.S | 10 +++++----- include/linux/objtool.h | 2 +- scripts/Makefile.vmlinux_o | 2 +- tools/arch/x86/include/asm/disabled-features.h | 2 +- 10 files changed, 18 insertions(+), 18 deletions(-) (limited to 'tools') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ba4546556fc5..77b8769f3026 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2516,7 +2516,7 @@ config RETHUNK Requires a compiler with -mfunction-return=thunk-extern support for full protection. The kernel may run slower. -config CPU_UNRET_ENTRY +config MITIGATION_UNRET_ENTRY bool "Enable UNRET on kernel entry" depends on CPU_SUP_AMD && RETHUNK && X86_64 default y diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 24e4010c33b6..151f0d50e7e0 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -63,7 +63,7 @@ # define DISABLE_RETHUNK (1 << (X86_FEATURE_RETHUNK & 31)) #endif -#ifdef CONFIG_CPU_UNRET_ENTRY +#ifdef CONFIG_MITIGATION_UNRET_ENTRY # define DISABLE_UNRET 0 #else # define DISABLE_UNRET (1 << (X86_FEATURE_UNRET & 31)) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 32680cb72003..97478690a579 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -212,7 +212,7 @@ */ .macro VALIDATE_UNRET_END #if defined(CONFIG_NOINSTR_VALIDATION) && \ - (defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)) + (defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)) ANNOTATE_RETPOLINE_SAFE nop #endif @@ -271,7 +271,7 @@ .Lskip_rsb_\@: .endm -#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO) +#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO) #define CALL_UNTRAIN_RET "call entry_untrain_ret" #else #define CALL_UNTRAIN_RET "" @@ -334,7 +334,7 @@ extern void __x86_return_thunk(void); static inline void __x86_return_thunk(void) {} #endif -#ifdef CONFIG_CPU_UNRET_ENTRY +#ifdef CONFIG_MITIGATION_UNRET_ENTRY extern void retbleed_return_thunk(void); #else static inline void retbleed_return_thunk(void) {} diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 9f42d1c59e09..6c7db2ec2c5e 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -928,7 +928,7 @@ static void fix_erratum_1386(struct cpuinfo_x86 *c) void init_spectral_chicken(struct cpuinfo_x86 *c) { -#ifdef CONFIG_CPU_UNRET_ENTRY +#ifdef CONFIG_MITIGATION_UNRET_ENTRY u64 value; /* diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index fc46fd6447f9..2580368c32d1 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -982,10 +982,10 @@ static void __init retbleed_select_mitigation(void) return; case RETBLEED_CMD_UNRET: - if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY)) { + if (IS_ENABLED(CONFIG_MITIGATION_UNRET_ENTRY)) { retbleed_mitigation = RETBLEED_MITIGATION_UNRET; } else { - pr_err("WARNING: kernel not compiled with CPU_UNRET_ENTRY.\n"); + pr_err("WARNING: kernel not compiled with MITIGATION_UNRET_ENTRY.\n"); goto do_cmd_auto; } break; @@ -1021,7 +1021,7 @@ do_cmd_auto: case RETBLEED_CMD_AUTO: if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) { - if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY)) + if (IS_ENABLED(CONFIG_MITIGATION_UNRET_ENTRY)) retbleed_mitigation = RETBLEED_MITIGATION_UNRET; else if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY) && boot_cpu_has(X86_FEATURE_IBPB)) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index bb2ec03f046d..9c5cca50a36f 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -504,7 +504,7 @@ INIT_PER_CPU(irq_stack_backing_store); "fixed_percpu_data is not at start of per-cpu area"); #endif -#ifdef CONFIG_CPU_UNRET_ENTRY +#ifdef CONFIG_MITIGATION_UNRET_ENTRY . = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned"); #endif diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index ff46f48a0cc4..0ad67ccadd4c 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -230,7 +230,7 @@ SYM_CODE_END(srso_return_thunk) #define JMP_SRSO_ALIAS_UNTRAIN_RET "ud2" #endif /* CONFIG_CPU_SRSO */ -#ifdef CONFIG_CPU_UNRET_ENTRY +#ifdef CONFIG_MITIGATION_UNRET_ENTRY /* * Some generic notes on the untraining sequences: @@ -312,11 +312,11 @@ SYM_CODE_END(retbleed_return_thunk) SYM_FUNC_END(retbleed_untrain_ret) #define JMP_RETBLEED_UNTRAIN_RET "jmp retbleed_untrain_ret" -#else /* !CONFIG_CPU_UNRET_ENTRY */ +#else /* !CONFIG_MITIGATION_UNRET_ENTRY */ #define JMP_RETBLEED_UNTRAIN_RET "ud2" -#endif /* CONFIG_CPU_UNRET_ENTRY */ +#endif /* CONFIG_MITIGATION_UNRET_ENTRY */ -#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO) +#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO) SYM_FUNC_START(entry_untrain_ret) ALTERNATIVE_2 JMP_RETBLEED_UNTRAIN_RET, \ @@ -325,7 +325,7 @@ SYM_FUNC_START(entry_untrain_ret) SYM_FUNC_END(entry_untrain_ret) __EXPORT_THUNK(entry_untrain_ret) -#endif /* CONFIG_CPU_UNRET_ENTRY || CONFIG_CPU_SRSO */ +#endif /* CONFIG_MITIGATION_UNRET_ENTRY || CONFIG_CPU_SRSO */ #ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 33212e93f4a6..d030671a4c49 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -131,7 +131,7 @@ */ .macro VALIDATE_UNRET_BEGIN #if defined(CONFIG_NOINSTR_VALIDATION) && \ - (defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)) + (defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)) .Lhere_\@: .pushsection .discard.validate_unret .long .Lhere_\@ - . diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o index 25b3b587d37c..6277dbd730bb 100644 --- a/scripts/Makefile.vmlinux_o +++ b/scripts/Makefile.vmlinux_o @@ -38,7 +38,7 @@ objtool-enabled := $(or $(delay-objtool),$(CONFIG_NOINSTR_VALIDATION)) vmlinux-objtool-args-$(delay-objtool) += $(objtool-args-y) vmlinux-objtool-args-$(CONFIG_GCOV_KERNEL) += --no-unreachable vmlinux-objtool-args-$(CONFIG_NOINSTR_VALIDATION) += --noinstr \ - $(if $(or $(CONFIG_CPU_UNRET_ENTRY),$(CONFIG_CPU_SRSO)), --unret) + $(if $(or $(CONFIG_MITIGATION_UNRET_ENTRY),$(CONFIG_CPU_SRSO)), --unret) objtool-args = $(vmlinux-objtool-args-y) --link diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 24e4010c33b6..151f0d50e7e0 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -63,7 +63,7 @@ # define DISABLE_RETHUNK (1 << (X86_FEATURE_RETHUNK & 31)) #endif -#ifdef CONFIG_CPU_UNRET_ENTRY +#ifdef CONFIG_MITIGATION_UNRET_ENTRY # define DISABLE_UNRET 0 #else # define DISABLE_UNRET (1 << (X86_FEATURE_UNRET & 31)) -- cgit v1.2.3-70-g09d2 From 0911b8c52c4d68c57d02f172daa55a42bce703f0 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Tue, 21 Nov 2023 08:07:37 -0800 Subject: x86/bugs: Rename CONFIG_RETHUNK => CONFIG_MITIGATION_RETHUNK Step 10/10 of the namespace unification of CPU mitigations related Kconfig options. [ mingo: Added one more case. ] Suggested-by: Josh Poimboeuf Signed-off-by: Breno Leitao Signed-off-by: Ingo Molnar Acked-by: Josh Poimboeuf Cc: Linus Torvalds Link: https://lore.kernel.org/r/20231121160740.1249350-11-leitao@debian.org --- arch/x86/Kconfig | 8 ++++---- arch/x86/Makefile | 2 +- arch/x86/configs/i386_defconfig | 2 +- arch/x86/include/asm/disabled-features.h | 2 +- arch/x86/include/asm/linkage.h | 4 ++-- arch/x86/include/asm/nospec-branch.h | 4 ++-- arch/x86/include/asm/static_call.h | 2 +- arch/x86/kernel/alternative.c | 4 ++-- arch/x86/kernel/static_call.c | 2 +- arch/x86/lib/retpoline.S | 4 ++-- scripts/Makefile.lib | 2 +- tools/arch/x86/include/asm/disabled-features.h | 2 +- tools/objtool/check.c | 2 +- 13 files changed, 20 insertions(+), 20 deletions(-) (limited to 'tools') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index a2743b7f2a18..0a9fea390ef3 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2462,7 +2462,7 @@ config FINEIBT config HAVE_CALL_THUNKS def_bool y - depends on CC_HAS_ENTRY_PADDING && RETHUNK && OBJTOOL + depends on CC_HAS_ENTRY_PADDING && MITIGATION_RETHUNK && OBJTOOL config CALL_THUNKS def_bool n @@ -2505,7 +2505,7 @@ config MITIGATION_RETPOLINE branches. Requires a compiler with -mindirect-branch=thunk-extern support for full protection. The kernel may run slower. -config RETHUNK +config MITIGATION_RETHUNK bool "Enable return-thunks" depends on MITIGATION_RETPOLINE && CC_HAS_RETURN_THUNK select OBJTOOL if HAVE_OBJTOOL @@ -2518,7 +2518,7 @@ config RETHUNK config MITIGATION_UNRET_ENTRY bool "Enable UNRET on kernel entry" - depends on CPU_SUP_AMD && RETHUNK && X86_64 + depends on CPU_SUP_AMD && MITIGATION_RETHUNK && X86_64 default y help Compile the kernel with support for the retbleed=unret mitigation. @@ -2572,7 +2572,7 @@ config MITIGATION_IBRS_ENTRY config MITIGATION_SRSO bool "Mitigate speculative RAS overflow on AMD" - depends on CPU_SUP_AMD && X86_64 && RETHUNK + depends on CPU_SUP_AMD && X86_64 && MITIGATION_RETHUNK default y help Enable the SRSO mitigation needed on AMD Zen1-4 machines. diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 5ce8c30e7701..ba046afb850e 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -22,7 +22,7 @@ RETPOLINE_VDSO_CFLAGS := -mretpoline endif RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch-cs-prefix) -ifdef CONFIG_RETHUNK +ifdef CONFIG_MITIGATION_RETHUNK RETHUNK_CFLAGS := -mfunction-return=thunk-extern RETPOLINE_CFLAGS += $(RETHUNK_CFLAGS) endif diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 73abbbdd26f8..91801138b10b 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -42,7 +42,7 @@ CONFIG_EFI_STUB=y CONFIG_HZ_1000=y CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y -# CONFIG_RETHUNK is not set +# CONFIG_MITIGATION_RETHUNK is not set CONFIG_HIBERNATION=y CONFIG_PM_DEBUG=y CONFIG_PM_TRACE_RTC=y diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 151f0d50e7e0..36d0c1e05e60 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -57,7 +57,7 @@ (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31))) #endif -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK # define DISABLE_RETHUNK 0 #else # define DISABLE_RETHUNK (1 << (X86_FEATURE_RETHUNK & 31)) diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 09e2d026df33..dc31b13b87a0 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -40,7 +40,7 @@ #ifdef __ASSEMBLY__ -#if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) +#if defined(CONFIG_MITIGATION_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) #define RET jmp __x86_return_thunk #else /* CONFIG_MITIGATION_RETPOLINE */ #ifdef CONFIG_MITIGATION_SLS @@ -52,7 +52,7 @@ #else /* __ASSEMBLY__ */ -#if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) +#if defined(CONFIG_MITIGATION_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) #define ASM_RET "jmp __x86_return_thunk\n\t" #else /* CONFIG_MITIGATION_RETPOLINE */ #ifdef CONFIG_MITIGATION_SLS diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 94c70832994f..2c0679ebe914 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -289,7 +289,7 @@ * where we have a stack but before any RET instruction. */ .macro __UNTRAIN_RET ibpb_feature, call_depth_insns -#if defined(CONFIG_RETHUNK) || defined(CONFIG_MITIGATION_IBPB_ENTRY) +#if defined(CONFIG_MITIGATION_RETHUNK) || defined(CONFIG_MITIGATION_IBPB_ENTRY) VALIDATE_UNRET_END ALTERNATIVE_3 "", \ CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \ @@ -328,7 +328,7 @@ extern retpoline_thunk_t __x86_indirect_thunk_array[]; extern retpoline_thunk_t __x86_indirect_call_thunk_array[]; extern retpoline_thunk_t __x86_indirect_jump_thunk_array[]; -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK extern void __x86_return_thunk(void); #else static inline void __x86_return_thunk(void) {} diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index 343b722ccaf2..125c407e2abe 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -46,7 +46,7 @@ #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)") -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "jmp __x86_return_thunk") #else diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index f5442d0d2ee9..df91abea3420 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -769,7 +769,7 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) } } -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK /* * Rewrite the compiler generated return thunk tail-calls. @@ -842,7 +842,7 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) } #else void __init_or_module noinline apply_returns(s32 *start, s32 *end) { } -#endif /* CONFIG_RETHUNK */ +#endif /* CONFIG_MITIGATION_RETHUNK */ #else /* !CONFIG_MITIGATION_RETPOLINE || !CONFIG_OBJTOOL */ diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 77a9316da435..4eefaac64c6c 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -172,7 +172,7 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) } EXPORT_SYMBOL_GPL(arch_static_call_transform); -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK /* * This is called by apply_returns() to fix up static call trampolines, * specifically ARCH_DEFINE_STATIC_CALL_NULL_TRAMP which is recorded as diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 67b52cbec648..0045153ba222 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -127,7 +127,7 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) #undef GEN #endif -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK /* * Be careful here: that label cannot really be removed because in @@ -386,4 +386,4 @@ SYM_CODE_START(__x86_return_thunk) SYM_CODE_END(__x86_return_thunk) EXPORT_SYMBOL(__x86_return_thunk) -#endif /* CONFIG_RETHUNK */ +#endif /* CONFIG_MITIGATION_RETHUNK */ diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index b272ca64cd75..c3f4cacad7b0 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -263,7 +263,7 @@ objtool-args-$(CONFIG_HAVE_OBJTOOL_NOP_MCOUNT) += --mnop endif objtool-args-$(CONFIG_UNWINDER_ORC) += --orc objtool-args-$(CONFIG_MITIGATION_RETPOLINE) += --retpoline -objtool-args-$(CONFIG_RETHUNK) += --rethunk +objtool-args-$(CONFIG_MITIGATION_RETHUNK) += --rethunk objtool-args-$(CONFIG_MITIGATION_SLS) += --sls objtool-args-$(CONFIG_STACK_VALIDATION) += --stackval objtool-args-$(CONFIG_HAVE_STATIC_CALL_INLINE) += --static-call diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 151f0d50e7e0..36d0c1e05e60 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -57,7 +57,7 @@ (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31))) #endif -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK # define DISABLE_RETHUNK 0 #else # define DISABLE_RETHUNK (1 << (X86_FEATURE_RETHUNK & 31)) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 84067f018f7e..8440b7bb343c 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3980,7 +3980,7 @@ static int validate_retpoline(struct objtool_file *file) if (insn->type == INSN_RETURN) { if (opts.rethunk) { - WARN_INSN(insn, "'naked' return found in RETHUNK build"); + WARN_INSN(insn, "'naked' return found in MITIGATION_RETHUNK build"); } else continue; } else { -- cgit v1.2.3-70-g09d2 From ab5e5b99a949b9f282c605d00557b2c727856485 Mon Sep 17 00:00:00 2001 From: Juri Lelli Date: Tue, 16 Jan 2024 17:19:26 +0100 Subject: tools/workqueue: Add rescuers printing to wq_dump.py Retrieving rescuers information (e.g., affinity and name) is quite useful when debugging workqueues configurations. Add printing of such information to the existing wq_dump.py script. Signed-off-by: Juri Lelli Signed-off-by: Tejun Heo --- tools/workqueue/wq_dump.py | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'tools') diff --git a/tools/workqueue/wq_dump.py b/tools/workqueue/wq_dump.py index d0df5833f2c1..6da621989e21 100644 --- a/tools/workqueue/wq_dump.py +++ b/tools/workqueue/wq_dump.py @@ -175,3 +175,32 @@ for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_( if wq.flags & WQ_UNBOUND: print(f' {wq.dfl_pwq.pool.id.value_():{max_pool_id_len}}', end='') print('') + +print('') +print('Workqueue -> rescuer') +print('=====================') +print(f'wq_unbound_cpumask={cpumask_str(wq_unbound_cpumask)}') +print('') +print('[ workqueue \ type unbound_cpumask rescuer pid cpumask]') + +for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'): + print(f'{wq.name.string_().decode()[-24:]:24}', end='') + if wq.flags & WQ_UNBOUND: + if wq.flags & WQ_ORDERED: + print(' ordered ', end='') + else: + print(' unbound', end='') + if wq.unbound_attrs.affn_strict: + print(',S ', end='') + else: + print(' ', end='') + print(f' {cpumask_str(wq.unbound_attrs.cpumask):24}', end='') + else: + print(' percpu ', end='') + print(' ', end='') + + if wq.flags & WQ_MEM_RECLAIM: + print(f' {wq.rescuer.task.comm.string_().decode()[-24:]:24}', end='') + print(f' {wq.rescuer.task.pid.value_():5}', end='') + print(f' {cpumask_str(wq.rescuer.task.cpus_ptr)}', end='') + print('') -- cgit v1.2.3-70-g09d2 From 0f05ee447949cf1b72bd7c415c803ea7f7209403 Mon Sep 17 00:00:00 2001 From: Hu Yadi Date: Fri, 12 Jan 2024 15:40:59 +0800 Subject: selftests/filesystems:fix build error in overlayfs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit One build issue comes up due to both mount.h included dev_in_maps.c In file included from dev_in_maps.c:10: /usr/include/sys/mount.h:35:3: error: expected identifier before numeric constant 35 | MS_RDONLY = 1, /* Mount read-only. */ | ^~~~~~~~~ In file included from dev_in_maps.c:13: Remove one of them to solve conflict, another error comes up: dev_in_maps.c:170:6: error: implicit declaration of function ‘mount’ [-Werror=implicit-function-declaration] 170 | if (mount(NULL, "/", NULL, MS_SLAVE | MS_REC, NULL) == -1) { | ^~~~~ cc1: all warnings being treated as errors and then , add sys_mount definition to solve it After both above, dev_in_maps.c can be built correctly on my mache(gcc 10.2,glibc-2.32,kernel-5.10) Signed-off-by: Hu Yadi Link: https://lore.kernel.org/r/20240112074059.29673-1-hu.yadi@h3c.com Acked-by: Andrei Vagin Signed-off-by: Christian Brauner --- tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c b/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c index e19ab0e85709..759f86e7d263 100644 --- a/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c +++ b/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include #include @@ -32,7 +31,11 @@ static int sys_fsmount(int fd, unsigned int flags, unsigned int attr_flags) { return syscall(__NR_fsmount, fd, flags, attr_flags); } - +static int sys_mount(const char *src, const char *tgt, const char *fst, + unsigned long flags, const void *data) +{ + return syscall(__NR_mount, src, tgt, fst, flags, data); +} static int sys_move_mount(int from_dfd, const char *from_pathname, int to_dfd, const char *to_pathname, unsigned int flags) @@ -166,8 +169,7 @@ int main(int argc, char **argv) ksft_test_result_skip("unable to create a new mount namespace\n"); return 1; } - - if (mount(NULL, "/", NULL, MS_SLAVE | MS_REC, NULL) == -1) { + if (sys_mount(NULL, "/", NULL, MS_SLAVE | MS_REC, NULL) == -1) { pr_perror("mount"); return 1; } -- cgit v1.2.3-70-g09d2 From 9e3f1c59367515e7e40675fe83645a131c05039d Mon Sep 17 00:00:00 2001 From: "Hu.Yadi" Date: Thu, 11 Jan 2024 19:32:29 +0800 Subject: selftests/move_mount_set_group:Make tests build with old libc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace SYS_ with __NR_. Using the __NR_ notation, provided by UAPI, is useful to build tests on systems without the SYS_ definitions. Replace SYS_move_mount with __NR_move_mount Similar changes: commit 87129ef13603 ("selftests/landlock: Make tests build with old libc") Acked-by: Mickaël Salaün Signed-off-by: Hu.Yadi Link: https://lore.kernel.org/r/20240111113229.10820-1-hu.yadi@h3c.com Reviewed-by: Berlin Suggested-by: Jiao Signed-off-by: Christian Brauner --- .../selftests/move_mount_set_group/move_mount_set_group_test.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c b/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c index 50ed5d475dd1..bcf51d785a37 100644 --- a/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c +++ b/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c @@ -218,7 +218,7 @@ static bool move_mount_set_group_supported(void) if (mount(NULL, SET_GROUP_FROM, NULL, MS_SHARED, 0)) return -1; - ret = syscall(SYS_move_mount, AT_FDCWD, SET_GROUP_FROM, + ret = syscall(__NR_move_mount, AT_FDCWD, SET_GROUP_FROM, AT_FDCWD, SET_GROUP_TO, MOVE_MOUNT_SET_GROUP); umount2("/tmp", MNT_DETACH); @@ -363,7 +363,7 @@ TEST_F(move_mount_set_group, complex_sharing_copying) CLONE_VM | CLONE_FILES); ASSERT_GT(pid, 0); ASSERT_EQ(wait_for_pid(pid), 0); - ASSERT_EQ(syscall(SYS_move_mount, ca_from.mntfd, "", + ASSERT_EQ(syscall(__NR_move_mount, ca_from.mntfd, "", ca_to.mntfd, "", MOVE_MOUNT_SET_GROUP | MOVE_MOUNT_F_EMPTY_PATH | MOVE_MOUNT_T_EMPTY_PATH), 0); -- cgit v1.2.3-70-g09d2 From 6727980b67852dae6b82a97e24fbadbdd218c033 Mon Sep 17 00:00:00 2001 From: Marcos Paulo de Souza Date: Fri, 12 Jan 2024 14:43:50 -0300 Subject: kselftests: lib.mk: Add TEST_GEN_MODS_DIR variable Add TEST_GEN_MODS_DIR variable for kselftests. It can point to a directory containing kernel modules that will be used by selftest scripts. The modules are built as external modules for the running kernel. As a result they are always binary compatible and the same tests can be used for older or newer kernels. The build requires "kernel-devel" package to be installed. For example, in the upstream sources, the rpm devel package is produced by "make rpm-pkg" The modules can be built independently by make -C tools/testing/selftests/livepatch/ or they will be automatically built before running the tests via make -C tools/testing/selftests/livepatch/ run_tests Note that they are _not_ built when running the standalone tests by calling, for example, ./test-state.sh. Along with TEST_GEN_MODS_DIR, it was necessary to create a new install rule. INSTALL_MODS_RULE is needed because INSTALL_SINGLE_RULE would copy the entire TEST_GEN_MODS_DIR directory to the destination, even the files created by Kbuild to compile the modules. The new install rule copies only the .ko files, as we would expect the gen_tar to work. Reviewed-by: Joe Lawrence Reviewed-by: Petr Mladek Signed-off-by: Marcos Paulo de Souza Signed-off-by: Shuah Khan --- Documentation/dev-tools/kselftest.rst | 4 ++++ tools/testing/selftests/lib.mk | 26 +++++++++++++++++++++----- 2 files changed, 25 insertions(+), 5 deletions(-) (limited to 'tools') diff --git a/Documentation/dev-tools/kselftest.rst b/Documentation/dev-tools/kselftest.rst index ab376b316c36..7f3582a67318 100644 --- a/Documentation/dev-tools/kselftest.rst +++ b/Documentation/dev-tools/kselftest.rst @@ -245,6 +245,10 @@ Contributing new tests (details) TEST_PROGS, TEST_GEN_PROGS mean it is the executable tested by default. + TEST_GEN_MODS_DIR should be used by tests that require modules to be built + before the test starts. The variable will contain the name of the directory + containing the modules. + TEST_CUSTOM_PROGS should be used by tests that require custom build rules and prevent common build rule use. diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index aa646e0661f3..0d8b7db92715 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -54,11 +54,15 @@ endif # TEST_PROGS are for test shell scripts. # TEST_CUSTOM_PROGS and TEST_PROGS will be run by common run_tests # and install targets. Common clean doesn't touch them. +# TEST_GEN_MODS_DIR is used to specify a directory with modules to be built +# before the test executes. These modules are cleaned on the clean target as well. TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) +TEST_GEN_MODS_DIR := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_MODS_DIR)) -all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) +all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) \ + $(if $(TEST_GEN_MODS_DIR),gen_mods_dir) define RUN_TESTS BASE_DIR="$(selfdir)"; \ @@ -71,8 +75,8 @@ endef run_tests: all ifdef building_out_of_srctree - @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \ - rsync -aq --copy-unsafe-links $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT); \ + @if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)$(TEST_GEN_MODS_DIR)" != "X" ]; then \ + rsync -aq --copy-unsafe-links $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(TEST_GEN_MODS_DIR) $(OUTPUT); \ fi @if [ "X$(TEST_PROGS)" != "X" ]; then \ $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) \ @@ -84,11 +88,22 @@ else @$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS)) endif +gen_mods_dir: + $(Q)$(MAKE) -C $(TEST_GEN_MODS_DIR) + +clean_mods_dir: + $(Q)$(MAKE) -C $(TEST_GEN_MODS_DIR) clean + define INSTALL_SINGLE_RULE $(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH)) $(if $(INSTALL_LIST),rsync -a --copy-unsafe-links $(INSTALL_LIST) $(INSTALL_PATH)/) endef +define INSTALL_MODS_RULE + $(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH)/$(INSTALL_LIST)) + $(if $(INSTALL_LIST),rsync -a --copy-unsafe-links $(INSTALL_LIST)/*.ko $(INSTALL_PATH)/$(INSTALL_LIST)) +endef + define INSTALL_RULE $(eval INSTALL_LIST = $(TEST_PROGS)) $(INSTALL_SINGLE_RULE) $(eval INSTALL_LIST = $(TEST_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE) @@ -97,6 +112,7 @@ define INSTALL_RULE $(eval INSTALL_LIST = $(TEST_CUSTOM_PROGS)) $(INSTALL_SINGLE_RULE) $(eval INSTALL_LIST = $(TEST_GEN_PROGS_EXTENDED)) $(INSTALL_SINGLE_RULE) $(eval INSTALL_LIST = $(TEST_GEN_FILES)) $(INSTALL_SINGLE_RULE) + $(eval INSTALL_LIST = $(notdir $(TEST_GEN_MODS_DIR))) $(INSTALL_MODS_RULE) $(eval INSTALL_LIST = $(wildcard config settings)) $(INSTALL_SINGLE_RULE) endef @@ -122,7 +138,7 @@ define CLEAN $(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN) endef -clean: +clean: $(if $(TEST_GEN_MODS_DIR),clean_mods_dir) $(CLEAN) # Enables to extend CFLAGS and LDFLAGS from command line, e.g. @@ -153,4 +169,4 @@ $(OUTPUT)/%:%.S $(LINK.S) $^ $(LDLIBS) -o $@ endif -.PHONY: run_tests all clean install emit_tests +.PHONY: run_tests all clean install emit_tests gen_mods_dir clean_mods_dir -- cgit v1.2.3-70-g09d2 From c4bbe83d27c2446a033cc0381c3fb6be5e8c41c7 Mon Sep 17 00:00:00 2001 From: Marcos Paulo de Souza Date: Fri, 12 Jan 2024 14:43:51 -0300 Subject: livepatch: Move tests from lib/livepatch to selftests/livepatch The modules are being moved from lib/livepatch to tools/testing/selftests/livepatch/test_modules. This code moving will allow writing more complex tests, like for example an userspace C code that will call a livepatched kernel function. The modules are now built as out-of-tree modules, but being part of the kernel source means they will be maintained. Another advantage of the code moving is to be able to easily change, debug and rebuild the tests by running make on the selftests/livepatch directory, which is not currently possible since the modules on lib/livepatch are build and installed using the "modules" target. The current approach also keeps the ability to execute the tests manually by executing the scripts inside selftests/livepatch directory, as it's currently supported. If the modules are modified, they needed to be rebuilt before running the scripts though. The modules are built before running the selftests when using the kselftest invocations: make kselftest TARGETS=livepatch or make -C tools/testing/selftests/livepatch run_tests Having the modules being built as out-of-modules requires changing the currently used 'modprobe' by 'insmod' and adapt the test scripts that check for the kernel message buffer. Now it is possible to only compile the modules by running: make -C tools/testing/selftests/livepatch/ This way the test modules and other test program can be built in order to be packaged if so desired. As there aren't any modules being built on lib/livepatch, remove the TEST_LIVEPATCH Kconfig and it's references. Note: "make gen_tar" packages the pre-built binaries into the tarball. It means that it will store the test modules pre-built for the kernel running on the build host. Note that these modules need not binary compatible with the kernel built from the same sources. But the same is true for other packaged selftest binaries. The entire kernel sources are needed for rebuilding the selftests on another system. Reviewed-by: Joe Lawrence Reviewed-by: Petr Mladek Signed-off-by: Marcos Paulo de Souza Acked-by: Alexander Gordeev Signed-off-by: Shuah Khan --- MAINTAINERS | 1 - arch/s390/configs/debug_defconfig | 1 - arch/s390/configs/defconfig | 1 - lib/Kconfig.debug | 22 -- lib/Makefile | 2 - lib/livepatch/Makefile | 14 - lib/livepatch/test_klp_atomic_replace.c | 57 ---- lib/livepatch/test_klp_callbacks_busy.c | 70 ----- lib/livepatch/test_klp_callbacks_demo.c | 121 --------- lib/livepatch/test_klp_callbacks_demo2.c | 93 ------- lib/livepatch/test_klp_callbacks_mod.c | 24 -- lib/livepatch/test_klp_livepatch.c | 51 ---- lib/livepatch/test_klp_shadow_vars.c | 301 --------------------- lib/livepatch/test_klp_state.c | 162 ----------- lib/livepatch/test_klp_state2.c | 191 ------------- lib/livepatch/test_klp_state3.c | 5 - tools/testing/selftests/livepatch/Makefile | 1 + tools/testing/selftests/livepatch/README | 25 +- tools/testing/selftests/livepatch/config | 1 - tools/testing/selftests/livepatch/functions.sh | 34 +-- .../testing/selftests/livepatch/test-callbacks.sh | 50 ++-- tools/testing/selftests/livepatch/test-ftrace.sh | 6 +- .../testing/selftests/livepatch/test-livepatch.sh | 10 +- .../selftests/livepatch/test-shadow-vars.sh | 2 +- tools/testing/selftests/livepatch/test-state.sh | 18 +- tools/testing/selftests/livepatch/test-sysfs.sh | 6 +- .../selftests/livepatch/test_modules/Makefile | 19 ++ .../test_modules/test_klp_atomic_replace.c | 57 ++++ .../test_modules/test_klp_callbacks_busy.c | 70 +++++ .../test_modules/test_klp_callbacks_demo.c | 121 +++++++++ .../test_modules/test_klp_callbacks_demo2.c | 93 +++++++ .../test_modules/test_klp_callbacks_mod.c | 24 ++ .../livepatch/test_modules/test_klp_livepatch.c | 51 ++++ .../livepatch/test_modules/test_klp_shadow_vars.c | 301 +++++++++++++++++++++ .../livepatch/test_modules/test_klp_state.c | 162 +++++++++++ .../livepatch/test_modules/test_klp_state2.c | 191 +++++++++++++ .../livepatch/test_modules/test_klp_state3.c | 5 + 37 files changed, 1173 insertions(+), 1190 deletions(-) delete mode 100644 lib/livepatch/Makefile delete mode 100644 lib/livepatch/test_klp_atomic_replace.c delete mode 100644 lib/livepatch/test_klp_callbacks_busy.c delete mode 100644 lib/livepatch/test_klp_callbacks_demo.c delete mode 100644 lib/livepatch/test_klp_callbacks_demo2.c delete mode 100644 lib/livepatch/test_klp_callbacks_mod.c delete mode 100644 lib/livepatch/test_klp_livepatch.c delete mode 100644 lib/livepatch/test_klp_shadow_vars.c delete mode 100644 lib/livepatch/test_klp_state.c delete mode 100644 lib/livepatch/test_klp_state2.c delete mode 100644 lib/livepatch/test_klp_state3.c create mode 100644 tools/testing/selftests/livepatch/test_modules/Makefile create mode 100644 tools/testing/selftests/livepatch/test_modules/test_klp_atomic_replace.c create mode 100644 tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_busy.c create mode 100644 tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_demo.c create mode 100644 tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_demo2.c create mode 100644 tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_mod.c create mode 100644 tools/testing/selftests/livepatch/test_modules/test_klp_livepatch.c create mode 100644 tools/testing/selftests/livepatch/test_modules/test_klp_shadow_vars.c create mode 100644 tools/testing/selftests/livepatch/test_modules/test_klp_state.c create mode 100644 tools/testing/selftests/livepatch/test_modules/test_klp_state2.c create mode 100644 tools/testing/selftests/livepatch/test_modules/test_klp_state3.c (limited to 'tools') diff --git a/MAINTAINERS b/MAINTAINERS index 8d1052fa6a69..ad5bec15bf0f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12510,7 +12510,6 @@ F: arch/powerpc/include/asm/livepatch.h F: include/linux/livepatch.h F: kernel/livepatch/ F: kernel/module/livepatch.c -F: lib/livepatch/ F: samples/livepatch/ F: tools/testing/selftests/livepatch/ diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index cae2dd34fbb4..f9c44d392125 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -886,4 +886,3 @@ CONFIG_ATOMIC64_SELFTEST=y CONFIG_STRING_SELFTEST=y CONFIG_TEST_BITOPS=m CONFIG_TEST_BPF=m -CONFIG_TEST_LIVEPATCH=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 42b988873e54..ef78734b235c 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -815,4 +815,3 @@ CONFIG_KPROBES_SANITY_TEST=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m -CONFIG_TEST_LIVEPATCH=m diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 975a07f9f1cc..c95d52853bf9 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2857,28 +2857,6 @@ config TEST_MEMCAT_P If unsure, say N. -config TEST_LIVEPATCH - tristate "Test livepatching" - default n - depends on DYNAMIC_DEBUG - depends on LIVEPATCH - depends on m - help - Test kernel livepatching features for correctness. The tests will - load test modules that will be livepatched in various scenarios. - - To run all the livepatching tests: - - make -C tools/testing/selftests TARGETS=livepatch run_tests - - Alternatively, individual tests may be invoked: - - tools/testing/selftests/livepatch/test-callbacks.sh - tools/testing/selftests/livepatch/test-livepatch.sh - tools/testing/selftests/livepatch/test-shadow-vars.sh - - If unsure, say N. - config TEST_OBJAGG tristate "Perform selftest on object aggreration manager" default n diff --git a/lib/Makefile b/lib/Makefile index 6b09731d8e61..95ed57f377fd 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -134,8 +134,6 @@ endif obj-$(CONFIG_TEST_FPU) += test_fpu.o CFLAGS_test_fpu.o += $(FPU_CFLAGS) -obj-$(CONFIG_TEST_LIVEPATCH) += livepatch/ - # Some KUnit files (hooks.o) need to be built-in even when KUnit is a module, # so we can't just use obj-$(CONFIG_KUNIT). ifdef CONFIG_KUNIT diff --git a/lib/livepatch/Makefile b/lib/livepatch/Makefile deleted file mode 100644 index dcc912b3478f..000000000000 --- a/lib/livepatch/Makefile +++ /dev/null @@ -1,14 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# Makefile for livepatch test code. - -obj-$(CONFIG_TEST_LIVEPATCH) += test_klp_atomic_replace.o \ - test_klp_callbacks_demo.o \ - test_klp_callbacks_demo2.o \ - test_klp_callbacks_busy.o \ - test_klp_callbacks_mod.o \ - test_klp_livepatch.o \ - test_klp_shadow_vars.o \ - test_klp_state.o \ - test_klp_state2.o \ - test_klp_state3.o diff --git a/lib/livepatch/test_klp_atomic_replace.c b/lib/livepatch/test_klp_atomic_replace.c deleted file mode 100644 index 5af7093ca00c..000000000000 --- a/lib/livepatch/test_klp_atomic_replace.c +++ /dev/null @@ -1,57 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (C) 2018 Joe Lawrence - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include - -static int replace; -module_param(replace, int, 0644); -MODULE_PARM_DESC(replace, "replace (default=0)"); - -#include -static int livepatch_meminfo_proc_show(struct seq_file *m, void *v) -{ - seq_printf(m, "%s: %s\n", THIS_MODULE->name, - "this has been live patched"); - return 0; -} - -static struct klp_func funcs[] = { - { - .old_name = "meminfo_proc_show", - .new_func = livepatch_meminfo_proc_show, - }, {} -}; - -static struct klp_object objs[] = { - { - /* name being NULL means vmlinux */ - .funcs = funcs, - }, {} -}; - -static struct klp_patch patch = { - .mod = THIS_MODULE, - .objs = objs, - /* set .replace in the init function below for demo purposes */ -}; - -static int test_klp_atomic_replace_init(void) -{ - patch.replace = replace; - return klp_enable_patch(&patch); -} - -static void test_klp_atomic_replace_exit(void) -{ -} - -module_init(test_klp_atomic_replace_init); -module_exit(test_klp_atomic_replace_exit); -MODULE_LICENSE("GPL"); -MODULE_INFO(livepatch, "Y"); -MODULE_AUTHOR("Joe Lawrence "); -MODULE_DESCRIPTION("Livepatch test: atomic replace"); diff --git a/lib/livepatch/test_klp_callbacks_busy.c b/lib/livepatch/test_klp_callbacks_busy.c deleted file mode 100644 index 133929e0ce8f..000000000000 --- a/lib/livepatch/test_klp_callbacks_busy.c +++ /dev/null @@ -1,70 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (C) 2018 Joe Lawrence - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include - -/* load/run-time control from sysfs writer */ -static bool block_transition; -module_param(block_transition, bool, 0644); -MODULE_PARM_DESC(block_transition, "block_transition (default=false)"); - -static void busymod_work_func(struct work_struct *work); -static DECLARE_WORK(work, busymod_work_func); -static DECLARE_COMPLETION(busymod_work_started); - -static void busymod_work_func(struct work_struct *work) -{ - pr_info("%s enter\n", __func__); - complete(&busymod_work_started); - - while (READ_ONCE(block_transition)) { - /* - * Busy-wait until the sysfs writer has acknowledged a - * blocked transition and clears the flag. - */ - msleep(20); - } - - pr_info("%s exit\n", __func__); -} - -static int test_klp_callbacks_busy_init(void) -{ - pr_info("%s\n", __func__); - schedule_work(&work); - - /* - * To synchronize kernel messages, hold the init function from - * exiting until the work function's entry message has printed. - */ - wait_for_completion(&busymod_work_started); - - if (!block_transition) { - /* - * Serialize output: print all messages from the work - * function before returning from init(). - */ - flush_work(&work); - } - - return 0; -} - -static void test_klp_callbacks_busy_exit(void) -{ - WRITE_ONCE(block_transition, false); - flush_work(&work); - pr_info("%s\n", __func__); -} - -module_init(test_klp_callbacks_busy_init); -module_exit(test_klp_callbacks_busy_exit); -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Joe Lawrence "); -MODULE_DESCRIPTION("Livepatch test: busy target module"); diff --git a/lib/livepatch/test_klp_callbacks_demo.c b/lib/livepatch/test_klp_callbacks_demo.c deleted file mode 100644 index 3fd8fe1cd1cc..000000000000 --- a/lib/livepatch/test_klp_callbacks_demo.c +++ /dev/null @@ -1,121 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (C) 2018 Joe Lawrence - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include - -static int pre_patch_ret; -module_param(pre_patch_ret, int, 0644); -MODULE_PARM_DESC(pre_patch_ret, "pre_patch_ret (default=0)"); - -static const char *const module_state[] = { - [MODULE_STATE_LIVE] = "[MODULE_STATE_LIVE] Normal state", - [MODULE_STATE_COMING] = "[MODULE_STATE_COMING] Full formed, running module_init", - [MODULE_STATE_GOING] = "[MODULE_STATE_GOING] Going away", - [MODULE_STATE_UNFORMED] = "[MODULE_STATE_UNFORMED] Still setting it up", -}; - -static void callback_info(const char *callback, struct klp_object *obj) -{ - if (obj->mod) - pr_info("%s: %s -> %s\n", callback, obj->mod->name, - module_state[obj->mod->state]); - else - pr_info("%s: vmlinux\n", callback); -} - -/* Executed on object patching (ie, patch enablement) */ -static int pre_patch_callback(struct klp_object *obj) -{ - callback_info(__func__, obj); - return pre_patch_ret; -} - -/* Executed on object unpatching (ie, patch disablement) */ -static void post_patch_callback(struct klp_object *obj) -{ - callback_info(__func__, obj); -} - -/* Executed on object unpatching (ie, patch disablement) */ -static void pre_unpatch_callback(struct klp_object *obj) -{ - callback_info(__func__, obj); -} - -/* Executed on object unpatching (ie, patch disablement) */ -static void post_unpatch_callback(struct klp_object *obj) -{ - callback_info(__func__, obj); -} - -static void patched_work_func(struct work_struct *work) -{ - pr_info("%s\n", __func__); -} - -static struct klp_func no_funcs[] = { - {} -}; - -static struct klp_func busymod_funcs[] = { - { - .old_name = "busymod_work_func", - .new_func = patched_work_func, - }, {} -}; - -static struct klp_object objs[] = { - { - .name = NULL, /* vmlinux */ - .funcs = no_funcs, - .callbacks = { - .pre_patch = pre_patch_callback, - .post_patch = post_patch_callback, - .pre_unpatch = pre_unpatch_callback, - .post_unpatch = post_unpatch_callback, - }, - }, { - .name = "test_klp_callbacks_mod", - .funcs = no_funcs, - .callbacks = { - .pre_patch = pre_patch_callback, - .post_patch = post_patch_callback, - .pre_unpatch = pre_unpatch_callback, - .post_unpatch = post_unpatch_callback, - }, - }, { - .name = "test_klp_callbacks_busy", - .funcs = busymod_funcs, - .callbacks = { - .pre_patch = pre_patch_callback, - .post_patch = post_patch_callback, - .pre_unpatch = pre_unpatch_callback, - .post_unpatch = post_unpatch_callback, - }, - }, { } -}; - -static struct klp_patch patch = { - .mod = THIS_MODULE, - .objs = objs, -}; - -static int test_klp_callbacks_demo_init(void) -{ - return klp_enable_patch(&patch); -} - -static void test_klp_callbacks_demo_exit(void) -{ -} - -module_init(test_klp_callbacks_demo_init); -module_exit(test_klp_callbacks_demo_exit); -MODULE_LICENSE("GPL"); -MODULE_INFO(livepatch, "Y"); -MODULE_AUTHOR("Joe Lawrence "); -MODULE_DESCRIPTION("Livepatch test: livepatch demo"); diff --git a/lib/livepatch/test_klp_callbacks_demo2.c b/lib/livepatch/test_klp_callbacks_demo2.c deleted file mode 100644 index 5417573e80af..000000000000 --- a/lib/livepatch/test_klp_callbacks_demo2.c +++ /dev/null @@ -1,93 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (C) 2018 Joe Lawrence - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include - -static int replace; -module_param(replace, int, 0644); -MODULE_PARM_DESC(replace, "replace (default=0)"); - -static const char *const module_state[] = { - [MODULE_STATE_LIVE] = "[MODULE_STATE_LIVE] Normal state", - [MODULE_STATE_COMING] = "[MODULE_STATE_COMING] Full formed, running module_init", - [MODULE_STATE_GOING] = "[MODULE_STATE_GOING] Going away", - [MODULE_STATE_UNFORMED] = "[MODULE_STATE_UNFORMED] Still setting it up", -}; - -static void callback_info(const char *callback, struct klp_object *obj) -{ - if (obj->mod) - pr_info("%s: %s -> %s\n", callback, obj->mod->name, - module_state[obj->mod->state]); - else - pr_info("%s: vmlinux\n", callback); -} - -/* Executed on object patching (ie, patch enablement) */ -static int pre_patch_callback(struct klp_object *obj) -{ - callback_info(__func__, obj); - return 0; -} - -/* Executed on object unpatching (ie, patch disablement) */ -static void post_patch_callback(struct klp_object *obj) -{ - callback_info(__func__, obj); -} - -/* Executed on object unpatching (ie, patch disablement) */ -static void pre_unpatch_callback(struct klp_object *obj) -{ - callback_info(__func__, obj); -} - -/* Executed on object unpatching (ie, patch disablement) */ -static void post_unpatch_callback(struct klp_object *obj) -{ - callback_info(__func__, obj); -} - -static struct klp_func no_funcs[] = { - { } -}; - -static struct klp_object objs[] = { - { - .name = NULL, /* vmlinux */ - .funcs = no_funcs, - .callbacks = { - .pre_patch = pre_patch_callback, - .post_patch = post_patch_callback, - .pre_unpatch = pre_unpatch_callback, - .post_unpatch = post_unpatch_callback, - }, - }, { } -}; - -static struct klp_patch patch = { - .mod = THIS_MODULE, - .objs = objs, - /* set .replace in the init function below for demo purposes */ -}; - -static int test_klp_callbacks_demo2_init(void) -{ - patch.replace = replace; - return klp_enable_patch(&patch); -} - -static void test_klp_callbacks_demo2_exit(void) -{ -} - -module_init(test_klp_callbacks_demo2_init); -module_exit(test_klp_callbacks_demo2_exit); -MODULE_LICENSE("GPL"); -MODULE_INFO(livepatch, "Y"); -MODULE_AUTHOR("Joe Lawrence "); -MODULE_DESCRIPTION("Livepatch test: livepatch demo2"); diff --git a/lib/livepatch/test_klp_callbacks_mod.c b/lib/livepatch/test_klp_callbacks_mod.c deleted file mode 100644 index 8fbe645b1c2c..000000000000 --- a/lib/livepatch/test_klp_callbacks_mod.c +++ /dev/null @@ -1,24 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (C) 2018 Joe Lawrence - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include - -static int test_klp_callbacks_mod_init(void) -{ - pr_info("%s\n", __func__); - return 0; -} - -static void test_klp_callbacks_mod_exit(void) -{ - pr_info("%s\n", __func__); -} - -module_init(test_klp_callbacks_mod_init); -module_exit(test_klp_callbacks_mod_exit); -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Joe Lawrence "); -MODULE_DESCRIPTION("Livepatch test: target module"); diff --git a/lib/livepatch/test_klp_livepatch.c b/lib/livepatch/test_klp_livepatch.c deleted file mode 100644 index aff08199de71..000000000000 --- a/lib/livepatch/test_klp_livepatch.c +++ /dev/null @@ -1,51 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (C) 2014 Seth Jennings - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include - -#include -static int livepatch_cmdline_proc_show(struct seq_file *m, void *v) -{ - seq_printf(m, "%s: %s\n", THIS_MODULE->name, - "this has been live patched"); - return 0; -} - -static struct klp_func funcs[] = { - { - .old_name = "cmdline_proc_show", - .new_func = livepatch_cmdline_proc_show, - }, { } -}; - -static struct klp_object objs[] = { - { - /* name being NULL means vmlinux */ - .funcs = funcs, - }, { } -}; - -static struct klp_patch patch = { - .mod = THIS_MODULE, - .objs = objs, -}; - -static int test_klp_livepatch_init(void) -{ - return klp_enable_patch(&patch); -} - -static void test_klp_livepatch_exit(void) -{ -} - -module_init(test_klp_livepatch_init); -module_exit(test_klp_livepatch_exit); -MODULE_LICENSE("GPL"); -MODULE_INFO(livepatch, "Y"); -MODULE_AUTHOR("Seth Jennings "); -MODULE_DESCRIPTION("Livepatch test: livepatch module"); diff --git a/lib/livepatch/test_klp_shadow_vars.c b/lib/livepatch/test_klp_shadow_vars.c deleted file mode 100644 index b99116490858..000000000000 --- a/lib/livepatch/test_klp_shadow_vars.c +++ /dev/null @@ -1,301 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (C) 2018 Joe Lawrence - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include - -/* - * Keep a small list of pointers so that we can print address-agnostic - * pointer values. Use a rolling integer count to differentiate the values. - * Ironically we could have used the shadow variable API to do this, but - * let's not lean too heavily on the very code we're testing. - */ -static LIST_HEAD(ptr_list); -struct shadow_ptr { - void *ptr; - int id; - struct list_head list; -}; - -static void free_ptr_list(void) -{ - struct shadow_ptr *sp, *tmp_sp; - - list_for_each_entry_safe(sp, tmp_sp, &ptr_list, list) { - list_del(&sp->list); - kfree(sp); - } -} - -static int ptr_id(void *ptr) -{ - struct shadow_ptr *sp; - static int count; - - list_for_each_entry(sp, &ptr_list, list) { - if (sp->ptr == ptr) - return sp->id; - } - - sp = kmalloc(sizeof(*sp), GFP_ATOMIC); - if (!sp) - return -ENOMEM; - sp->ptr = ptr; - sp->id = count++; - - list_add(&sp->list, &ptr_list); - - return sp->id; -} - -/* - * Shadow variable wrapper functions that echo the function and arguments - * to the kernel log for testing verification. Don't display raw pointers, - * but use the ptr_id() value instead. - */ -static void *shadow_get(void *obj, unsigned long id) -{ - int **sv; - - sv = klp_shadow_get(obj, id); - pr_info("klp_%s(obj=PTR%d, id=0x%lx) = PTR%d\n", - __func__, ptr_id(obj), id, ptr_id(sv)); - - return sv; -} - -static void *shadow_alloc(void *obj, unsigned long id, size_t size, - gfp_t gfp_flags, klp_shadow_ctor_t ctor, - void *ctor_data) -{ - int **var = ctor_data; - int **sv; - - sv = klp_shadow_alloc(obj, id, size, gfp_flags, ctor, var); - pr_info("klp_%s(obj=PTR%d, id=0x%lx, size=%zx, gfp_flags=%pGg), ctor=PTR%d, ctor_data=PTR%d = PTR%d\n", - __func__, ptr_id(obj), id, size, &gfp_flags, ptr_id(ctor), - ptr_id(*var), ptr_id(sv)); - - return sv; -} - -static void *shadow_get_or_alloc(void *obj, unsigned long id, size_t size, - gfp_t gfp_flags, klp_shadow_ctor_t ctor, - void *ctor_data) -{ - int **var = ctor_data; - int **sv; - - sv = klp_shadow_get_or_alloc(obj, id, size, gfp_flags, ctor, var); - pr_info("klp_%s(obj=PTR%d, id=0x%lx, size=%zx, gfp_flags=%pGg), ctor=PTR%d, ctor_data=PTR%d = PTR%d\n", - __func__, ptr_id(obj), id, size, &gfp_flags, ptr_id(ctor), - ptr_id(*var), ptr_id(sv)); - - return sv; -} - -static void shadow_free(void *obj, unsigned long id, klp_shadow_dtor_t dtor) -{ - klp_shadow_free(obj, id, dtor); - pr_info("klp_%s(obj=PTR%d, id=0x%lx, dtor=PTR%d)\n", - __func__, ptr_id(obj), id, ptr_id(dtor)); -} - -static void shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor) -{ - klp_shadow_free_all(id, dtor); - pr_info("klp_%s(id=0x%lx, dtor=PTR%d)\n", __func__, id, ptr_id(dtor)); -} - - -/* Shadow variable constructor - remember simple pointer data */ -static int shadow_ctor(void *obj, void *shadow_data, void *ctor_data) -{ - int **sv = shadow_data; - int **var = ctor_data; - - if (!var) - return -EINVAL; - - *sv = *var; - pr_info("%s: PTR%d -> PTR%d\n", __func__, ptr_id(sv), ptr_id(*var)); - - return 0; -} - -/* - * With more than one item to free in the list, order is not determined and - * shadow_dtor will not be passed to shadow_free_all() which would make the - * test fail. (see pass 6) - */ -static void shadow_dtor(void *obj, void *shadow_data) -{ - int **sv = shadow_data; - - pr_info("%s(obj=PTR%d, shadow_data=PTR%d)\n", - __func__, ptr_id(obj), ptr_id(sv)); -} - -/* number of objects we simulate that need shadow vars */ -#define NUM_OBJS 3 - -/* dynamically created obj fields have the following shadow var id values */ -#define SV_ID1 0x1234 -#define SV_ID2 0x1235 - -/* - * The main test case adds/removes new fields (shadow var) to each of these - * test structure instances. The last group of fields in the struct represent - * the idea that shadow variables may be added and removed to and from the - * struct during execution. - */ -struct test_object { - /* add anything here below and avoid to define an empty struct */ - struct shadow_ptr sp; - - /* these represent shadow vars added and removed with SV_ID{1,2} */ - /* char nfield1; */ - /* int nfield2; */ -}; - -static int test_klp_shadow_vars_init(void) -{ - struct test_object objs[NUM_OBJS]; - char nfields1[NUM_OBJS], *pnfields1[NUM_OBJS], **sv1[NUM_OBJS]; - char *pndup[NUM_OBJS]; - int nfields2[NUM_OBJS], *pnfields2[NUM_OBJS], **sv2[NUM_OBJS]; - void **sv; - int ret; - int i; - - ptr_id(NULL); - - /* - * With an empty shadow variable hash table, expect not to find - * any matches. - */ - sv = shadow_get(&objs[0], SV_ID1); - if (!sv) - pr_info(" got expected NULL result\n"); - - /* pass 1: init & alloc a char+int pair of svars for each objs */ - for (i = 0; i < NUM_OBJS; i++) { - pnfields1[i] = &nfields1[i]; - ptr_id(pnfields1[i]); - - if (i % 2) { - sv1[i] = shadow_alloc(&objs[i], SV_ID1, - sizeof(pnfields1[i]), GFP_KERNEL, - shadow_ctor, &pnfields1[i]); - } else { - sv1[i] = shadow_get_or_alloc(&objs[i], SV_ID1, - sizeof(pnfields1[i]), GFP_KERNEL, - shadow_ctor, &pnfields1[i]); - } - if (!sv1[i]) { - ret = -ENOMEM; - goto out; - } - - pnfields2[i] = &nfields2[i]; - ptr_id(pnfields2[i]); - sv2[i] = shadow_alloc(&objs[i], SV_ID2, sizeof(pnfields2[i]), - GFP_KERNEL, shadow_ctor, &pnfields2[i]); - if (!sv2[i]) { - ret = -ENOMEM; - goto out; - } - } - - /* pass 2: verify we find allocated svars and where they point to */ - for (i = 0; i < NUM_OBJS; i++) { - /* check the "char" svar for all objects */ - sv = shadow_get(&objs[i], SV_ID1); - if (!sv) { - ret = -EINVAL; - goto out; - } - if ((char **)sv == sv1[i] && *sv1[i] == pnfields1[i]) - pr_info(" got expected PTR%d -> PTR%d result\n", - ptr_id(sv1[i]), ptr_id(*sv1[i])); - - /* check the "int" svar for all objects */ - sv = shadow_get(&objs[i], SV_ID2); - if (!sv) { - ret = -EINVAL; - goto out; - } - if ((int **)sv == sv2[i] && *sv2[i] == pnfields2[i]) - pr_info(" got expected PTR%d -> PTR%d result\n", - ptr_id(sv2[i]), ptr_id(*sv2[i])); - } - - /* pass 3: verify that 'get_or_alloc' returns already allocated svars */ - for (i = 0; i < NUM_OBJS; i++) { - pndup[i] = &nfields1[i]; - ptr_id(pndup[i]); - - sv = shadow_get_or_alloc(&objs[i], SV_ID1, sizeof(pndup[i]), - GFP_KERNEL, shadow_ctor, &pndup[i]); - if (!sv) { - ret = -EINVAL; - goto out; - } - if ((char **)sv == sv1[i] && *sv1[i] == pnfields1[i]) - pr_info(" got expected PTR%d -> PTR%d result\n", - ptr_id(sv1[i]), ptr_id(*sv1[i])); - } - - /* pass 4: free pairs of svars, verify removal */ - for (i = 0; i < NUM_OBJS; i++) { - shadow_free(&objs[i], SV_ID1, shadow_dtor); /* 'char' pairs */ - sv = shadow_get(&objs[i], SV_ID1); - if (!sv) - pr_info(" got expected NULL result\n"); - } - - /* pass 5: check we still find svar pairs */ - for (i = 0; i < NUM_OBJS; i++) { - sv = shadow_get(&objs[i], SV_ID2); /* 'int' pairs */ - if (!sv) { - ret = -EINVAL; - goto out; - } - if ((int **)sv == sv2[i] && *sv2[i] == pnfields2[i]) - pr_info(" got expected PTR%d -> PTR%d result\n", - ptr_id(sv2[i]), ptr_id(*sv2[i])); - } - - /* pass 6: free all the svar pairs too. */ - shadow_free_all(SV_ID2, NULL); /* 'int' pairs */ - for (i = 0; i < NUM_OBJS; i++) { - sv = shadow_get(&objs[i], SV_ID2); - if (!sv) - pr_info(" got expected NULL result\n"); - } - - free_ptr_list(); - - return 0; -out: - shadow_free_all(SV_ID1, NULL); /* 'char' pairs */ - shadow_free_all(SV_ID2, NULL); /* 'int' pairs */ - free_ptr_list(); - - return ret; -} - -static void test_klp_shadow_vars_exit(void) -{ -} - -module_init(test_klp_shadow_vars_init); -module_exit(test_klp_shadow_vars_exit); -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Joe Lawrence "); -MODULE_DESCRIPTION("Livepatch test: shadow variables"); diff --git a/lib/livepatch/test_klp_state.c b/lib/livepatch/test_klp_state.c deleted file mode 100644 index 57a4253acb01..000000000000 --- a/lib/livepatch/test_klp_state.c +++ /dev/null @@ -1,162 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (C) 2019 SUSE - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include - -#define CONSOLE_LOGLEVEL_STATE 1 -/* Version 1 does not support migration. */ -#define CONSOLE_LOGLEVEL_STATE_VERSION 1 - -static const char *const module_state[] = { - [MODULE_STATE_LIVE] = "[MODULE_STATE_LIVE] Normal state", - [MODULE_STATE_COMING] = "[MODULE_STATE_COMING] Full formed, running module_init", - [MODULE_STATE_GOING] = "[MODULE_STATE_GOING] Going away", - [MODULE_STATE_UNFORMED] = "[MODULE_STATE_UNFORMED] Still setting it up", -}; - -static void callback_info(const char *callback, struct klp_object *obj) -{ - if (obj->mod) - pr_info("%s: %s -> %s\n", callback, obj->mod->name, - module_state[obj->mod->state]); - else - pr_info("%s: vmlinux\n", callback); -} - -static struct klp_patch patch; - -static int allocate_loglevel_state(void) -{ - struct klp_state *loglevel_state; - - loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE); - if (!loglevel_state) - return -EINVAL; - - loglevel_state->data = kzalloc(sizeof(console_loglevel), GFP_KERNEL); - if (!loglevel_state->data) - return -ENOMEM; - - pr_info("%s: allocating space to store console_loglevel\n", - __func__); - return 0; -} - -static void fix_console_loglevel(void) -{ - struct klp_state *loglevel_state; - - loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE); - if (!loglevel_state) - return; - - pr_info("%s: fixing console_loglevel\n", __func__); - *(int *)loglevel_state->data = console_loglevel; - console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; -} - -static void restore_console_loglevel(void) -{ - struct klp_state *loglevel_state; - - loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE); - if (!loglevel_state) - return; - - pr_info("%s: restoring console_loglevel\n", __func__); - console_loglevel = *(int *)loglevel_state->data; -} - -static void free_loglevel_state(void) -{ - struct klp_state *loglevel_state; - - loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE); - if (!loglevel_state) - return; - - pr_info("%s: freeing space for the stored console_loglevel\n", - __func__); - kfree(loglevel_state->data); -} - -/* Executed on object patching (ie, patch enablement) */ -static int pre_patch_callback(struct klp_object *obj) -{ - callback_info(__func__, obj); - return allocate_loglevel_state(); -} - -/* Executed on object unpatching (ie, patch disablement) */ -static void post_patch_callback(struct klp_object *obj) -{ - callback_info(__func__, obj); - fix_console_loglevel(); -} - -/* Executed on object unpatching (ie, patch disablement) */ -static void pre_unpatch_callback(struct klp_object *obj) -{ - callback_info(__func__, obj); - restore_console_loglevel(); -} - -/* Executed on object unpatching (ie, patch disablement) */ -static void post_unpatch_callback(struct klp_object *obj) -{ - callback_info(__func__, obj); - free_loglevel_state(); -} - -static struct klp_func no_funcs[] = { - {} -}; - -static struct klp_object objs[] = { - { - .name = NULL, /* vmlinux */ - .funcs = no_funcs, - .callbacks = { - .pre_patch = pre_patch_callback, - .post_patch = post_patch_callback, - .pre_unpatch = pre_unpatch_callback, - .post_unpatch = post_unpatch_callback, - }, - }, { } -}; - -static struct klp_state states[] = { - { - .id = CONSOLE_LOGLEVEL_STATE, - .version = CONSOLE_LOGLEVEL_STATE_VERSION, - }, { } -}; - -static struct klp_patch patch = { - .mod = THIS_MODULE, - .objs = objs, - .states = states, - .replace = true, -}; - -static int test_klp_callbacks_demo_init(void) -{ - return klp_enable_patch(&patch); -} - -static void test_klp_callbacks_demo_exit(void) -{ -} - -module_init(test_klp_callbacks_demo_init); -module_exit(test_klp_callbacks_demo_exit); -MODULE_LICENSE("GPL"); -MODULE_INFO(livepatch, "Y"); -MODULE_AUTHOR("Petr Mladek "); -MODULE_DESCRIPTION("Livepatch test: system state modification"); diff --git a/lib/livepatch/test_klp_state2.c b/lib/livepatch/test_klp_state2.c deleted file mode 100644 index c978ea4d5e67..000000000000 --- a/lib/livepatch/test_klp_state2.c +++ /dev/null @@ -1,191 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (C) 2019 SUSE - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include - -#define CONSOLE_LOGLEVEL_STATE 1 -/* Version 2 supports migration. */ -#define CONSOLE_LOGLEVEL_STATE_VERSION 2 - -static const char *const module_state[] = { - [MODULE_STATE_LIVE] = "[MODULE_STATE_LIVE] Normal state", - [MODULE_STATE_COMING] = "[MODULE_STATE_COMING] Full formed, running module_init", - [MODULE_STATE_GOING] = "[MODULE_STATE_GOING] Going away", - [MODULE_STATE_UNFORMED] = "[MODULE_STATE_UNFORMED] Still setting it up", -}; - -static void callback_info(const char *callback, struct klp_object *obj) -{ - if (obj->mod) - pr_info("%s: %s -> %s\n", callback, obj->mod->name, - module_state[obj->mod->state]); - else - pr_info("%s: vmlinux\n", callback); -} - -static struct klp_patch patch; - -static int allocate_loglevel_state(void) -{ - struct klp_state *loglevel_state, *prev_loglevel_state; - - prev_loglevel_state = klp_get_prev_state(CONSOLE_LOGLEVEL_STATE); - if (prev_loglevel_state) { - pr_info("%s: space to store console_loglevel already allocated\n", - __func__); - return 0; - } - - loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE); - if (!loglevel_state) - return -EINVAL; - - loglevel_state->data = kzalloc(sizeof(console_loglevel), GFP_KERNEL); - if (!loglevel_state->data) - return -ENOMEM; - - pr_info("%s: allocating space to store console_loglevel\n", - __func__); - return 0; -} - -static void fix_console_loglevel(void) -{ - struct klp_state *loglevel_state, *prev_loglevel_state; - - loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE); - if (!loglevel_state) - return; - - prev_loglevel_state = klp_get_prev_state(CONSOLE_LOGLEVEL_STATE); - if (prev_loglevel_state) { - pr_info("%s: taking over the console_loglevel change\n", - __func__); - loglevel_state->data = prev_loglevel_state->data; - return; - } - - pr_info("%s: fixing console_loglevel\n", __func__); - *(int *)loglevel_state->data = console_loglevel; - console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; -} - -static void restore_console_loglevel(void) -{ - struct klp_state *loglevel_state, *prev_loglevel_state; - - prev_loglevel_state = klp_get_prev_state(CONSOLE_LOGLEVEL_STATE); - if (prev_loglevel_state) { - pr_info("%s: passing the console_loglevel change back to the old livepatch\n", - __func__); - return; - } - - loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE); - if (!loglevel_state) - return; - - pr_info("%s: restoring console_loglevel\n", __func__); - console_loglevel = *(int *)loglevel_state->data; -} - -static void free_loglevel_state(void) -{ - struct klp_state *loglevel_state, *prev_loglevel_state; - - prev_loglevel_state = klp_get_prev_state(CONSOLE_LOGLEVEL_STATE); - if (prev_loglevel_state) { - pr_info("%s: keeping space to store console_loglevel\n", - __func__); - return; - } - - loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE); - if (!loglevel_state) - return; - - pr_info("%s: freeing space for the stored console_loglevel\n", - __func__); - kfree(loglevel_state->data); -} - -/* Executed on object patching (ie, patch enablement) */ -static int pre_patch_callback(struct klp_object *obj) -{ - callback_info(__func__, obj); - return allocate_loglevel_state(); -} - -/* Executed on object unpatching (ie, patch disablement) */ -static void post_patch_callback(struct klp_object *obj) -{ - callback_info(__func__, obj); - fix_console_loglevel(); -} - -/* Executed on object unpatching (ie, patch disablement) */ -static void pre_unpatch_callback(struct klp_object *obj) -{ - callback_info(__func__, obj); - restore_console_loglevel(); -} - -/* Executed on object unpatching (ie, patch disablement) */ -static void post_unpatch_callback(struct klp_object *obj) -{ - callback_info(__func__, obj); - free_loglevel_state(); -} - -static struct klp_func no_funcs[] = { - {} -}; - -static struct klp_object objs[] = { - { - .name = NULL, /* vmlinux */ - .funcs = no_funcs, - .callbacks = { - .pre_patch = pre_patch_callback, - .post_patch = post_patch_callback, - .pre_unpatch = pre_unpatch_callback, - .post_unpatch = post_unpatch_callback, - }, - }, { } -}; - -static struct klp_state states[] = { - { - .id = CONSOLE_LOGLEVEL_STATE, - .version = CONSOLE_LOGLEVEL_STATE_VERSION, - }, { } -}; - -static struct klp_patch patch = { - .mod = THIS_MODULE, - .objs = objs, - .states = states, - .replace = true, -}; - -static int test_klp_callbacks_demo_init(void) -{ - return klp_enable_patch(&patch); -} - -static void test_klp_callbacks_demo_exit(void) -{ -} - -module_init(test_klp_callbacks_demo_init); -module_exit(test_klp_callbacks_demo_exit); -MODULE_LICENSE("GPL"); -MODULE_INFO(livepatch, "Y"); -MODULE_AUTHOR("Petr Mladek "); -MODULE_DESCRIPTION("Livepatch test: system state modification"); diff --git a/lib/livepatch/test_klp_state3.c b/lib/livepatch/test_klp_state3.c deleted file mode 100644 index 9226579d10c5..000000000000 --- a/lib/livepatch/test_klp_state3.c +++ /dev/null @@ -1,5 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (C) 2019 SUSE - -/* The console loglevel fix is the same in the next cumulative patch. */ -#include "test_klp_state2.c" diff --git a/tools/testing/selftests/livepatch/Makefile b/tools/testing/selftests/livepatch/Makefile index 02fadc9d55e0..119e2bbebe5d 100644 --- a/tools/testing/selftests/livepatch/Makefile +++ b/tools/testing/selftests/livepatch/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 +TEST_GEN_MODS_DIR := test_modules TEST_PROGS_EXTENDED := functions.sh TEST_PROGS := \ test-livepatch.sh \ diff --git a/tools/testing/selftests/livepatch/README b/tools/testing/selftests/livepatch/README index 0942dd5826f8..d2035dd64a2b 100644 --- a/tools/testing/selftests/livepatch/README +++ b/tools/testing/selftests/livepatch/README @@ -13,23 +13,36 @@ the message buffer for only the duration of each individual test.) Config ------ -Set these config options and their prerequisites: +Set CONFIG_LIVEPATCH=y option and it's prerequisites. -CONFIG_LIVEPATCH=y -CONFIG_TEST_LIVEPATCH=m +Building the tests +------------------ + +To only build the tests without running them, run: + + % make -C tools/testing/selftests/livepatch + +The command above will compile all test modules and test programs, making them +ready to be packaged if so desired. Running the tests ----------------- -Test kernel modules are built as part of lib/ (make modules) and need to -be installed (make modules_install) as the test scripts will modprobe -them. +Test kernel modules are built before running the livepatch selftests. The +modules are located under test_modules directory, and are built as out-of-tree +modules. This is specially useful since the same sources can be built and +tested on systems with different kABI, ensuring they the tests are backwards +compatible. The modules will be loaded by the test scripts using insmod. To run the livepatch selftests, from the top of the kernel source tree: % make -C tools/testing/selftests TARGETS=livepatch run_tests +or + + % make kselftest TARGETS=livepatch + Adding tests ------------ diff --git a/tools/testing/selftests/livepatch/config b/tools/testing/selftests/livepatch/config index ad23100cb27c..e88bf518a23a 100644 --- a/tools/testing/selftests/livepatch/config +++ b/tools/testing/selftests/livepatch/config @@ -1,3 +1,2 @@ CONFIG_LIVEPATCH=y CONFIG_DYNAMIC_DEBUG=y -CONFIG_TEST_LIVEPATCH=m diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh index c8416c54b463..e60cf09491a6 100644 --- a/tools/testing/selftests/livepatch/functions.sh +++ b/tools/testing/selftests/livepatch/functions.sh @@ -127,16 +127,14 @@ function loop_until() { done } -function assert_mod() { - local mod="$1" - - modprobe --dry-run "$mod" &>/dev/null -} - function is_livepatch_mod() { local mod="$1" - if [[ $(modinfo "$mod" | awk '/^livepatch:/{print $NF}') == "Y" ]]; then + if [[ ! -f "test_modules/$mod.ko" ]]; then + die "Can't find \"test_modules/$mod.ko\", try \"make\"" + fi + + if [[ $(modinfo "test_modules/$mod.ko" | awk '/^livepatch:/{print $NF}') == "Y" ]]; then return 0 fi @@ -146,9 +144,9 @@ function is_livepatch_mod() { function __load_mod() { local mod="$1"; shift - local msg="% modprobe $mod $*" + local msg="% insmod test_modules/$mod.ko $*" log "${msg%% }" - ret=$(modprobe "$mod" "$@" 2>&1) + ret=$(insmod "test_modules/$mod.ko" "$@" 2>&1) if [[ "$ret" != "" ]]; then die "$ret" fi @@ -161,13 +159,10 @@ function __load_mod() { # load_mod(modname, params) - load a kernel module # modname - module name to load -# params - module parameters to pass to modprobe +# params - module parameters to pass to insmod function load_mod() { local mod="$1"; shift - assert_mod "$mod" || - skip "unable to load module ${mod}, verify CONFIG_TEST_LIVEPATCH=m and run self-tests as root" - is_livepatch_mod "$mod" && die "use load_lp() to load the livepatch module $mod" @@ -177,13 +172,10 @@ function load_mod() { # load_lp_nowait(modname, params) - load a kernel module with a livepatch # but do not wait on until the transition finishes # modname - module name to load -# params - module parameters to pass to modprobe +# params - module parameters to pass to insmod function load_lp_nowait() { local mod="$1"; shift - assert_mod "$mod" || - skip "unable to load module ${mod}, verify CONFIG_TEST_LIVEPATCH=m and run self-tests as root" - is_livepatch_mod "$mod" || die "module $mod is not a livepatch" @@ -196,7 +188,7 @@ function load_lp_nowait() { # load_lp(modname, params) - load a kernel module with a livepatch # modname - module name to load -# params - module parameters to pass to modprobe +# params - module parameters to pass to insmod function load_lp() { local mod="$1"; shift @@ -209,13 +201,13 @@ function load_lp() { # load_failing_mod(modname, params) - load a kernel module, expect to fail # modname - module name to load -# params - module parameters to pass to modprobe +# params - module parameters to pass to insmod function load_failing_mod() { local mod="$1"; shift - local msg="% modprobe $mod $*" + local msg="% insmod test_modules/$mod.ko $*" log "${msg%% }" - ret=$(modprobe "$mod" "$@" 2>&1) + ret=$(insmod "test_modules/$mod.ko" "$@" 2>&1) if [[ "$ret" == "" ]]; then die "$mod unexpectedly loaded" fi diff --git a/tools/testing/selftests/livepatch/test-callbacks.sh b/tools/testing/selftests/livepatch/test-callbacks.sh index 90b26dbb2626..32b150e25b10 100755 --- a/tools/testing/selftests/livepatch/test-callbacks.sh +++ b/tools/testing/selftests/livepatch/test-callbacks.sh @@ -34,9 +34,9 @@ disable_lp $MOD_LIVEPATCH unload_lp $MOD_LIVEPATCH unload_mod $MOD_TARGET -check_result "% modprobe $MOD_TARGET +check_result "% insmod test_modules/$MOD_TARGET.ko $MOD_TARGET: ${MOD_TARGET}_init -% modprobe $MOD_LIVEPATCH +% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux @@ -81,7 +81,7 @@ disable_lp $MOD_LIVEPATCH unload_lp $MOD_LIVEPATCH unload_mod $MOD_TARGET -check_result "% modprobe $MOD_LIVEPATCH +check_result "% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux @@ -89,7 +89,7 @@ livepatch: '$MOD_LIVEPATCH': starting patching transition livepatch: '$MOD_LIVEPATCH': completing patching transition $MOD_LIVEPATCH: post_patch_callback: vmlinux livepatch: '$MOD_LIVEPATCH': patching complete -% modprobe $MOD_TARGET +% insmod test_modules/$MOD_TARGET.ko livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET' $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init $MOD_LIVEPATCH: post_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init @@ -129,9 +129,9 @@ unload_mod $MOD_TARGET disable_lp $MOD_LIVEPATCH unload_lp $MOD_LIVEPATCH -check_result "% modprobe $MOD_TARGET +check_result "% insmod test_modules/$MOD_TARGET.ko $MOD_TARGET: ${MOD_TARGET}_init -% modprobe $MOD_LIVEPATCH +% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux @@ -177,7 +177,7 @@ unload_mod $MOD_TARGET disable_lp $MOD_LIVEPATCH unload_lp $MOD_LIVEPATCH -check_result "% modprobe $MOD_LIVEPATCH +check_result "% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux @@ -185,7 +185,7 @@ livepatch: '$MOD_LIVEPATCH': starting patching transition livepatch: '$MOD_LIVEPATCH': completing patching transition $MOD_LIVEPATCH: post_patch_callback: vmlinux livepatch: '$MOD_LIVEPATCH': patching complete -% modprobe $MOD_TARGET +% insmod test_modules/$MOD_TARGET.ko livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET' $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init $MOD_LIVEPATCH: post_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init @@ -219,7 +219,7 @@ load_lp $MOD_LIVEPATCH disable_lp $MOD_LIVEPATCH unload_lp $MOD_LIVEPATCH -check_result "% modprobe $MOD_LIVEPATCH +check_result "% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux @@ -254,9 +254,9 @@ load_mod $MOD_TARGET load_failing_mod $MOD_LIVEPATCH pre_patch_ret=-19 unload_mod $MOD_TARGET -check_result "% modprobe $MOD_TARGET +check_result "% insmod test_modules/$MOD_TARGET.ko $MOD_TARGET: ${MOD_TARGET}_init -% modprobe $MOD_LIVEPATCH pre_patch_ret=-19 +% insmod test_modules/$MOD_LIVEPATCH.ko pre_patch_ret=-19 livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition test_klp_callbacks_demo: pre_patch_callback: vmlinux @@ -265,7 +265,7 @@ livepatch: failed to enable patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': canceling patching transition, going to unpatch livepatch: '$MOD_LIVEPATCH': completing unpatching transition livepatch: '$MOD_LIVEPATCH': unpatching complete -modprobe: ERROR: could not insert '$MOD_LIVEPATCH': No such device +insmod: ERROR: could not insert module test_modules/$MOD_LIVEPATCH.ko: No such device % rmmod $MOD_TARGET $MOD_TARGET: ${MOD_TARGET}_exit" @@ -295,7 +295,7 @@ load_failing_mod $MOD_TARGET disable_lp $MOD_LIVEPATCH unload_lp $MOD_LIVEPATCH -check_result "% modprobe $MOD_LIVEPATCH +check_result "% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux @@ -304,12 +304,12 @@ livepatch: '$MOD_LIVEPATCH': completing patching transition $MOD_LIVEPATCH: post_patch_callback: vmlinux livepatch: '$MOD_LIVEPATCH': patching complete % echo -19 > /sys/module/$MOD_LIVEPATCH/parameters/pre_patch_ret -% modprobe $MOD_TARGET +% insmod test_modules/$MOD_TARGET.ko livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET' $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init livepatch: pre-patch callback failed for object '$MOD_TARGET' livepatch: patch '$MOD_LIVEPATCH' failed for module '$MOD_TARGET', refusing to load module '$MOD_TARGET' -modprobe: ERROR: could not insert '$MOD_TARGET': No such device +insmod: ERROR: could not insert module test_modules/$MOD_TARGET.ko: No such device % echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH/enabled livepatch: '$MOD_LIVEPATCH': initializing unpatching transition $MOD_LIVEPATCH: pre_unpatch_callback: vmlinux @@ -340,11 +340,11 @@ disable_lp $MOD_LIVEPATCH unload_lp $MOD_LIVEPATCH unload_mod $MOD_TARGET_BUSY -check_result "% modprobe $MOD_TARGET_BUSY block_transition=N +check_result "% insmod test_modules/$MOD_TARGET_BUSY.ko block_transition=N $MOD_TARGET_BUSY: ${MOD_TARGET_BUSY}_init $MOD_TARGET_BUSY: busymod_work_func enter $MOD_TARGET_BUSY: busymod_work_func exit -% modprobe $MOD_LIVEPATCH +% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux @@ -354,7 +354,7 @@ livepatch: '$MOD_LIVEPATCH': completing patching transition $MOD_LIVEPATCH: post_patch_callback: vmlinux $MOD_LIVEPATCH: post_patch_callback: $MOD_TARGET_BUSY -> [MODULE_STATE_LIVE] Normal state livepatch: '$MOD_LIVEPATCH': patching complete -% modprobe $MOD_TARGET +% insmod test_modules/$MOD_TARGET.ko livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET' $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init $MOD_LIVEPATCH: post_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init @@ -421,16 +421,16 @@ disable_lp $MOD_LIVEPATCH unload_lp $MOD_LIVEPATCH unload_mod $MOD_TARGET_BUSY -check_result "% modprobe $MOD_TARGET_BUSY block_transition=Y +check_result "% insmod test_modules/$MOD_TARGET_BUSY.ko block_transition=Y $MOD_TARGET_BUSY: ${MOD_TARGET_BUSY}_init $MOD_TARGET_BUSY: busymod_work_func enter -% modprobe $MOD_LIVEPATCH +% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET_BUSY -> [MODULE_STATE_LIVE] Normal state livepatch: '$MOD_LIVEPATCH': starting patching transition -% modprobe $MOD_TARGET +% insmod test_modules/$MOD_TARGET.ko livepatch: applying patch '$MOD_LIVEPATCH' to loading module '$MOD_TARGET' $MOD_LIVEPATCH: pre_patch_callback: $MOD_TARGET -> [MODULE_STATE_COMING] Full formed, running module_init $MOD_TARGET: ${MOD_TARGET}_init @@ -467,7 +467,7 @@ disable_lp $MOD_LIVEPATCH unload_lp $MOD_LIVEPATCH2 unload_lp $MOD_LIVEPATCH -check_result "% modprobe $MOD_LIVEPATCH +check_result "% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux @@ -475,7 +475,7 @@ livepatch: '$MOD_LIVEPATCH': starting patching transition livepatch: '$MOD_LIVEPATCH': completing patching transition $MOD_LIVEPATCH: post_patch_callback: vmlinux livepatch: '$MOD_LIVEPATCH': patching complete -% modprobe $MOD_LIVEPATCH2 +% insmod test_modules/$MOD_LIVEPATCH2.ko livepatch: enabling patch '$MOD_LIVEPATCH2' livepatch: '$MOD_LIVEPATCH2': initializing patching transition $MOD_LIVEPATCH2: pre_patch_callback: vmlinux @@ -523,7 +523,7 @@ disable_lp $MOD_LIVEPATCH2 unload_lp $MOD_LIVEPATCH2 unload_lp $MOD_LIVEPATCH -check_result "% modprobe $MOD_LIVEPATCH +check_result "% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux @@ -531,7 +531,7 @@ livepatch: '$MOD_LIVEPATCH': starting patching transition livepatch: '$MOD_LIVEPATCH': completing patching transition $MOD_LIVEPATCH: post_patch_callback: vmlinux livepatch: '$MOD_LIVEPATCH': patching complete -% modprobe $MOD_LIVEPATCH2 replace=1 +% insmod test_modules/$MOD_LIVEPATCH2.ko replace=1 livepatch: enabling patch '$MOD_LIVEPATCH2' livepatch: '$MOD_LIVEPATCH2': initializing patching transition $MOD_LIVEPATCH2: pre_patch_callback: vmlinux diff --git a/tools/testing/selftests/livepatch/test-ftrace.sh b/tools/testing/selftests/livepatch/test-ftrace.sh index 825540a5194d..730218bce99c 100755 --- a/tools/testing/selftests/livepatch/test-ftrace.sh +++ b/tools/testing/selftests/livepatch/test-ftrace.sh @@ -35,7 +35,7 @@ disable_lp $MOD_LIVEPATCH unload_lp $MOD_LIVEPATCH check_result "livepatch: kernel.ftrace_enabled = 0 -% modprobe $MOD_LIVEPATCH +% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition livepatch: failed to register ftrace handler for function 'cmdline_proc_show' (-16) @@ -44,9 +44,9 @@ livepatch: failed to enable patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': canceling patching transition, going to unpatch livepatch: '$MOD_LIVEPATCH': completing unpatching transition livepatch: '$MOD_LIVEPATCH': unpatching complete -modprobe: ERROR: could not insert '$MOD_LIVEPATCH': Device or resource busy +insmod: ERROR: could not insert module test_modules/$MOD_LIVEPATCH.ko: Device or resource busy livepatch: kernel.ftrace_enabled = 1 -% modprobe $MOD_LIVEPATCH +% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition livepatch: '$MOD_LIVEPATCH': starting patching transition diff --git a/tools/testing/selftests/livepatch/test-livepatch.sh b/tools/testing/selftests/livepatch/test-livepatch.sh index 5fe79ac34be1..e3455a6b1158 100755 --- a/tools/testing/selftests/livepatch/test-livepatch.sh +++ b/tools/testing/selftests/livepatch/test-livepatch.sh @@ -31,7 +31,7 @@ if [[ "$(cat /proc/cmdline)" == "$MOD_LIVEPATCH: this has been live patched" ]] die "livepatch kselftest(s) failed" fi -check_result "% modprobe $MOD_LIVEPATCH +check_result "% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition livepatch: '$MOD_LIVEPATCH': starting patching transition @@ -75,14 +75,14 @@ unload_lp $MOD_LIVEPATCH grep 'live patched' /proc/cmdline > /dev/kmsg grep 'live patched' /proc/meminfo > /dev/kmsg -check_result "% modprobe $MOD_LIVEPATCH +check_result "% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition livepatch: '$MOD_LIVEPATCH': starting patching transition livepatch: '$MOD_LIVEPATCH': completing patching transition livepatch: '$MOD_LIVEPATCH': patching complete $MOD_LIVEPATCH: this has been live patched -% modprobe $MOD_REPLACE replace=0 +% insmod test_modules/$MOD_REPLACE.ko replace=0 livepatch: enabling patch '$MOD_REPLACE' livepatch: '$MOD_REPLACE': initializing patching transition livepatch: '$MOD_REPLACE': starting patching transition @@ -135,14 +135,14 @@ unload_lp $MOD_REPLACE grep 'live patched' /proc/cmdline > /dev/kmsg grep 'live patched' /proc/meminfo > /dev/kmsg -check_result "% modprobe $MOD_LIVEPATCH +check_result "% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition livepatch: '$MOD_LIVEPATCH': starting patching transition livepatch: '$MOD_LIVEPATCH': completing patching transition livepatch: '$MOD_LIVEPATCH': patching complete $MOD_LIVEPATCH: this has been live patched -% modprobe $MOD_REPLACE replace=1 +% insmod test_modules/$MOD_REPLACE.ko replace=1 livepatch: enabling patch '$MOD_REPLACE' livepatch: '$MOD_REPLACE': initializing patching transition livepatch: '$MOD_REPLACE': starting patching transition diff --git a/tools/testing/selftests/livepatch/test-shadow-vars.sh b/tools/testing/selftests/livepatch/test-shadow-vars.sh index e04cb354f56b..1218c155bffe 100755 --- a/tools/testing/selftests/livepatch/test-shadow-vars.sh +++ b/tools/testing/selftests/livepatch/test-shadow-vars.sh @@ -16,7 +16,7 @@ start_test "basic shadow variable API" load_mod $MOD_TEST unload_mod $MOD_TEST -check_result "% modprobe $MOD_TEST +check_result "% insmod test_modules/$MOD_TEST.ko $MOD_TEST: klp_shadow_get(obj=PTR1, id=0x1234) = PTR0 $MOD_TEST: got expected NULL result $MOD_TEST: shadow_ctor: PTR3 -> PTR2 diff --git a/tools/testing/selftests/livepatch/test-state.sh b/tools/testing/selftests/livepatch/test-state.sh index 38656721c958..10a52ac06185 100755 --- a/tools/testing/selftests/livepatch/test-state.sh +++ b/tools/testing/selftests/livepatch/test-state.sh @@ -19,7 +19,7 @@ load_lp $MOD_LIVEPATCH disable_lp $MOD_LIVEPATCH unload_lp $MOD_LIVEPATCH -check_result "% modprobe $MOD_LIVEPATCH +check_result "% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux @@ -51,7 +51,7 @@ unload_lp $MOD_LIVEPATCH disable_lp $MOD_LIVEPATCH2 unload_lp $MOD_LIVEPATCH2 -check_result "% modprobe $MOD_LIVEPATCH +check_result "% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition $MOD_LIVEPATCH: pre_patch_callback: vmlinux @@ -61,7 +61,7 @@ livepatch: '$MOD_LIVEPATCH': completing patching transition $MOD_LIVEPATCH: post_patch_callback: vmlinux $MOD_LIVEPATCH: fix_console_loglevel: fixing console_loglevel livepatch: '$MOD_LIVEPATCH': patching complete -% modprobe $MOD_LIVEPATCH2 +% insmod test_modules/$MOD_LIVEPATCH2.ko livepatch: enabling patch '$MOD_LIVEPATCH2' livepatch: '$MOD_LIVEPATCH2': initializing patching transition $MOD_LIVEPATCH2: pre_patch_callback: vmlinux @@ -96,7 +96,7 @@ disable_lp $MOD_LIVEPATCH2 unload_lp $MOD_LIVEPATCH2 unload_lp $MOD_LIVEPATCH3 -check_result "% modprobe $MOD_LIVEPATCH2 +check_result "% insmod test_modules/$MOD_LIVEPATCH2.ko livepatch: enabling patch '$MOD_LIVEPATCH2' livepatch: '$MOD_LIVEPATCH2': initializing patching transition $MOD_LIVEPATCH2: pre_patch_callback: vmlinux @@ -106,7 +106,7 @@ livepatch: '$MOD_LIVEPATCH2': completing patching transition $MOD_LIVEPATCH2: post_patch_callback: vmlinux $MOD_LIVEPATCH2: fix_console_loglevel: fixing console_loglevel livepatch: '$MOD_LIVEPATCH2': patching complete -% modprobe $MOD_LIVEPATCH3 +% insmod test_modules/$MOD_LIVEPATCH3.ko livepatch: enabling patch '$MOD_LIVEPATCH3' livepatch: '$MOD_LIVEPATCH3': initializing patching transition $MOD_LIVEPATCH3: pre_patch_callback: vmlinux @@ -117,7 +117,7 @@ $MOD_LIVEPATCH3: post_patch_callback: vmlinux $MOD_LIVEPATCH3: fix_console_loglevel: taking over the console_loglevel change livepatch: '$MOD_LIVEPATCH3': patching complete % rmmod $MOD_LIVEPATCH2 -% modprobe $MOD_LIVEPATCH2 +% insmod test_modules/$MOD_LIVEPATCH2.ko livepatch: enabling patch '$MOD_LIVEPATCH2' livepatch: '$MOD_LIVEPATCH2': initializing patching transition $MOD_LIVEPATCH2: pre_patch_callback: vmlinux @@ -149,7 +149,7 @@ load_failing_mod $MOD_LIVEPATCH disable_lp $MOD_LIVEPATCH2 unload_lp $MOD_LIVEPATCH2 -check_result "% modprobe $MOD_LIVEPATCH2 +check_result "% insmod test_modules/$MOD_LIVEPATCH2.ko livepatch: enabling patch '$MOD_LIVEPATCH2' livepatch: '$MOD_LIVEPATCH2': initializing patching transition $MOD_LIVEPATCH2: pre_patch_callback: vmlinux @@ -159,9 +159,9 @@ livepatch: '$MOD_LIVEPATCH2': completing patching transition $MOD_LIVEPATCH2: post_patch_callback: vmlinux $MOD_LIVEPATCH2: fix_console_loglevel: fixing console_loglevel livepatch: '$MOD_LIVEPATCH2': patching complete -% modprobe $MOD_LIVEPATCH +% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: Livepatch patch ($MOD_LIVEPATCH) is not compatible with the already installed livepatches. -modprobe: ERROR: could not insert '$MOD_LIVEPATCH': Invalid argument +insmod: ERROR: could not insert module test_modules/$MOD_LIVEPATCH.ko: Invalid parameters % echo 0 > /sys/kernel/livepatch/$MOD_LIVEPATCH2/enabled livepatch: '$MOD_LIVEPATCH2': initializing unpatching transition $MOD_LIVEPATCH2: pre_unpatch_callback: vmlinux diff --git a/tools/testing/selftests/livepatch/test-sysfs.sh b/tools/testing/selftests/livepatch/test-sysfs.sh index 7f76f280189a..6c646afa7395 100755 --- a/tools/testing/selftests/livepatch/test-sysfs.sh +++ b/tools/testing/selftests/livepatch/test-sysfs.sh @@ -27,7 +27,7 @@ disable_lp $MOD_LIVEPATCH unload_lp $MOD_LIVEPATCH -check_result "% modprobe $MOD_LIVEPATCH +check_result "% insmod test_modules/$MOD_LIVEPATCH.ko livepatch: enabling patch '$MOD_LIVEPATCH' livepatch: '$MOD_LIVEPATCH': initializing patching transition livepatch: '$MOD_LIVEPATCH': starting patching transition @@ -56,7 +56,7 @@ check_sysfs_value "$MOD_LIVEPATCH" "$MOD_TARGET/patched" "0" disable_lp $MOD_LIVEPATCH unload_lp $MOD_LIVEPATCH -check_result "% modprobe test_klp_callbacks_demo +check_result "% insmod test_modules/test_klp_callbacks_demo.ko livepatch: enabling patch 'test_klp_callbacks_demo' livepatch: 'test_klp_callbacks_demo': initializing patching transition test_klp_callbacks_demo: pre_patch_callback: vmlinux @@ -64,7 +64,7 @@ livepatch: 'test_klp_callbacks_demo': starting patching transition livepatch: 'test_klp_callbacks_demo': completing patching transition test_klp_callbacks_demo: post_patch_callback: vmlinux livepatch: 'test_klp_callbacks_demo': patching complete -% modprobe test_klp_callbacks_mod +% insmod test_modules/test_klp_callbacks_mod.ko livepatch: applying patch 'test_klp_callbacks_demo' to loading module 'test_klp_callbacks_mod' test_klp_callbacks_demo: pre_patch_callback: test_klp_callbacks_mod -> [MODULE_STATE_COMING] Full formed, running module_init test_klp_callbacks_demo: post_patch_callback: test_klp_callbacks_mod -> [MODULE_STATE_COMING] Full formed, running module_init diff --git a/tools/testing/selftests/livepatch/test_modules/Makefile b/tools/testing/selftests/livepatch/test_modules/Makefile new file mode 100644 index 000000000000..6f7c2103d27d --- /dev/null +++ b/tools/testing/selftests/livepatch/test_modules/Makefile @@ -0,0 +1,19 @@ +TESTMODS_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= /lib/modules/$(shell uname -r)/build + +obj-m += test_klp_atomic_replace.o \ + test_klp_callbacks_busy.o \ + test_klp_callbacks_demo.o \ + test_klp_callbacks_demo2.o \ + test_klp_callbacks_mod.o \ + test_klp_livepatch.o \ + test_klp_state.o \ + test_klp_state2.o \ + test_klp_state3.o \ + test_klp_shadow_vars.o + +modules: + $(Q)$(MAKE) -C $(KDIR) modules KBUILD_EXTMOD=$(TESTMODS_DIR) + +clean: + $(Q)$(MAKE) -C $(KDIR) clean KBUILD_EXTMOD=$(TESTMODS_DIR) diff --git a/tools/testing/selftests/livepatch/test_modules/test_klp_atomic_replace.c b/tools/testing/selftests/livepatch/test_modules/test_klp_atomic_replace.c new file mode 100644 index 000000000000..5af7093ca00c --- /dev/null +++ b/tools/testing/selftests/livepatch/test_modules/test_klp_atomic_replace.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018 Joe Lawrence + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include + +static int replace; +module_param(replace, int, 0644); +MODULE_PARM_DESC(replace, "replace (default=0)"); + +#include +static int livepatch_meminfo_proc_show(struct seq_file *m, void *v) +{ + seq_printf(m, "%s: %s\n", THIS_MODULE->name, + "this has been live patched"); + return 0; +} + +static struct klp_func funcs[] = { + { + .old_name = "meminfo_proc_show", + .new_func = livepatch_meminfo_proc_show, + }, {} +}; + +static struct klp_object objs[] = { + { + /* name being NULL means vmlinux */ + .funcs = funcs, + }, {} +}; + +static struct klp_patch patch = { + .mod = THIS_MODULE, + .objs = objs, + /* set .replace in the init function below for demo purposes */ +}; + +static int test_klp_atomic_replace_init(void) +{ + patch.replace = replace; + return klp_enable_patch(&patch); +} + +static void test_klp_atomic_replace_exit(void) +{ +} + +module_init(test_klp_atomic_replace_init); +module_exit(test_klp_atomic_replace_exit); +MODULE_LICENSE("GPL"); +MODULE_INFO(livepatch, "Y"); +MODULE_AUTHOR("Joe Lawrence "); +MODULE_DESCRIPTION("Livepatch test: atomic replace"); diff --git a/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_busy.c b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_busy.c new file mode 100644 index 000000000000..133929e0ce8f --- /dev/null +++ b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_busy.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018 Joe Lawrence + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include + +/* load/run-time control from sysfs writer */ +static bool block_transition; +module_param(block_transition, bool, 0644); +MODULE_PARM_DESC(block_transition, "block_transition (default=false)"); + +static void busymod_work_func(struct work_struct *work); +static DECLARE_WORK(work, busymod_work_func); +static DECLARE_COMPLETION(busymod_work_started); + +static void busymod_work_func(struct work_struct *work) +{ + pr_info("%s enter\n", __func__); + complete(&busymod_work_started); + + while (READ_ONCE(block_transition)) { + /* + * Busy-wait until the sysfs writer has acknowledged a + * blocked transition and clears the flag. + */ + msleep(20); + } + + pr_info("%s exit\n", __func__); +} + +static int test_klp_callbacks_busy_init(void) +{ + pr_info("%s\n", __func__); + schedule_work(&work); + + /* + * To synchronize kernel messages, hold the init function from + * exiting until the work function's entry message has printed. + */ + wait_for_completion(&busymod_work_started); + + if (!block_transition) { + /* + * Serialize output: print all messages from the work + * function before returning from init(). + */ + flush_work(&work); + } + + return 0; +} + +static void test_klp_callbacks_busy_exit(void) +{ + WRITE_ONCE(block_transition, false); + flush_work(&work); + pr_info("%s\n", __func__); +} + +module_init(test_klp_callbacks_busy_init); +module_exit(test_klp_callbacks_busy_exit); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Joe Lawrence "); +MODULE_DESCRIPTION("Livepatch test: busy target module"); diff --git a/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_demo.c b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_demo.c new file mode 100644 index 000000000000..3fd8fe1cd1cc --- /dev/null +++ b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_demo.c @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018 Joe Lawrence + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include + +static int pre_patch_ret; +module_param(pre_patch_ret, int, 0644); +MODULE_PARM_DESC(pre_patch_ret, "pre_patch_ret (default=0)"); + +static const char *const module_state[] = { + [MODULE_STATE_LIVE] = "[MODULE_STATE_LIVE] Normal state", + [MODULE_STATE_COMING] = "[MODULE_STATE_COMING] Full formed, running module_init", + [MODULE_STATE_GOING] = "[MODULE_STATE_GOING] Going away", + [MODULE_STATE_UNFORMED] = "[MODULE_STATE_UNFORMED] Still setting it up", +}; + +static void callback_info(const char *callback, struct klp_object *obj) +{ + if (obj->mod) + pr_info("%s: %s -> %s\n", callback, obj->mod->name, + module_state[obj->mod->state]); + else + pr_info("%s: vmlinux\n", callback); +} + +/* Executed on object patching (ie, patch enablement) */ +static int pre_patch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); + return pre_patch_ret; +} + +/* Executed on object unpatching (ie, patch disablement) */ +static void post_patch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); +} + +/* Executed on object unpatching (ie, patch disablement) */ +static void pre_unpatch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); +} + +/* Executed on object unpatching (ie, patch disablement) */ +static void post_unpatch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); +} + +static void patched_work_func(struct work_struct *work) +{ + pr_info("%s\n", __func__); +} + +static struct klp_func no_funcs[] = { + {} +}; + +static struct klp_func busymod_funcs[] = { + { + .old_name = "busymod_work_func", + .new_func = patched_work_func, + }, {} +}; + +static struct klp_object objs[] = { + { + .name = NULL, /* vmlinux */ + .funcs = no_funcs, + .callbacks = { + .pre_patch = pre_patch_callback, + .post_patch = post_patch_callback, + .pre_unpatch = pre_unpatch_callback, + .post_unpatch = post_unpatch_callback, + }, + }, { + .name = "test_klp_callbacks_mod", + .funcs = no_funcs, + .callbacks = { + .pre_patch = pre_patch_callback, + .post_patch = post_patch_callback, + .pre_unpatch = pre_unpatch_callback, + .post_unpatch = post_unpatch_callback, + }, + }, { + .name = "test_klp_callbacks_busy", + .funcs = busymod_funcs, + .callbacks = { + .pre_patch = pre_patch_callback, + .post_patch = post_patch_callback, + .pre_unpatch = pre_unpatch_callback, + .post_unpatch = post_unpatch_callback, + }, + }, { } +}; + +static struct klp_patch patch = { + .mod = THIS_MODULE, + .objs = objs, +}; + +static int test_klp_callbacks_demo_init(void) +{ + return klp_enable_patch(&patch); +} + +static void test_klp_callbacks_demo_exit(void) +{ +} + +module_init(test_klp_callbacks_demo_init); +module_exit(test_klp_callbacks_demo_exit); +MODULE_LICENSE("GPL"); +MODULE_INFO(livepatch, "Y"); +MODULE_AUTHOR("Joe Lawrence "); +MODULE_DESCRIPTION("Livepatch test: livepatch demo"); diff --git a/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_demo2.c b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_demo2.c new file mode 100644 index 000000000000..5417573e80af --- /dev/null +++ b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_demo2.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018 Joe Lawrence + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include + +static int replace; +module_param(replace, int, 0644); +MODULE_PARM_DESC(replace, "replace (default=0)"); + +static const char *const module_state[] = { + [MODULE_STATE_LIVE] = "[MODULE_STATE_LIVE] Normal state", + [MODULE_STATE_COMING] = "[MODULE_STATE_COMING] Full formed, running module_init", + [MODULE_STATE_GOING] = "[MODULE_STATE_GOING] Going away", + [MODULE_STATE_UNFORMED] = "[MODULE_STATE_UNFORMED] Still setting it up", +}; + +static void callback_info(const char *callback, struct klp_object *obj) +{ + if (obj->mod) + pr_info("%s: %s -> %s\n", callback, obj->mod->name, + module_state[obj->mod->state]); + else + pr_info("%s: vmlinux\n", callback); +} + +/* Executed on object patching (ie, patch enablement) */ +static int pre_patch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); + return 0; +} + +/* Executed on object unpatching (ie, patch disablement) */ +static void post_patch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); +} + +/* Executed on object unpatching (ie, patch disablement) */ +static void pre_unpatch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); +} + +/* Executed on object unpatching (ie, patch disablement) */ +static void post_unpatch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); +} + +static struct klp_func no_funcs[] = { + { } +}; + +static struct klp_object objs[] = { + { + .name = NULL, /* vmlinux */ + .funcs = no_funcs, + .callbacks = { + .pre_patch = pre_patch_callback, + .post_patch = post_patch_callback, + .pre_unpatch = pre_unpatch_callback, + .post_unpatch = post_unpatch_callback, + }, + }, { } +}; + +static struct klp_patch patch = { + .mod = THIS_MODULE, + .objs = objs, + /* set .replace in the init function below for demo purposes */ +}; + +static int test_klp_callbacks_demo2_init(void) +{ + patch.replace = replace; + return klp_enable_patch(&patch); +} + +static void test_klp_callbacks_demo2_exit(void) +{ +} + +module_init(test_klp_callbacks_demo2_init); +module_exit(test_klp_callbacks_demo2_exit); +MODULE_LICENSE("GPL"); +MODULE_INFO(livepatch, "Y"); +MODULE_AUTHOR("Joe Lawrence "); +MODULE_DESCRIPTION("Livepatch test: livepatch demo2"); diff --git a/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_mod.c b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_mod.c new file mode 100644 index 000000000000..8fbe645b1c2c --- /dev/null +++ b/tools/testing/selftests/livepatch/test_modules/test_klp_callbacks_mod.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018 Joe Lawrence + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include + +static int test_klp_callbacks_mod_init(void) +{ + pr_info("%s\n", __func__); + return 0; +} + +static void test_klp_callbacks_mod_exit(void) +{ + pr_info("%s\n", __func__); +} + +module_init(test_klp_callbacks_mod_init); +module_exit(test_klp_callbacks_mod_exit); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Joe Lawrence "); +MODULE_DESCRIPTION("Livepatch test: target module"); diff --git a/tools/testing/selftests/livepatch/test_modules/test_klp_livepatch.c b/tools/testing/selftests/livepatch/test_modules/test_klp_livepatch.c new file mode 100644 index 000000000000..aff08199de71 --- /dev/null +++ b/tools/testing/selftests/livepatch/test_modules/test_klp_livepatch.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2014 Seth Jennings + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include + +#include +static int livepatch_cmdline_proc_show(struct seq_file *m, void *v) +{ + seq_printf(m, "%s: %s\n", THIS_MODULE->name, + "this has been live patched"); + return 0; +} + +static struct klp_func funcs[] = { + { + .old_name = "cmdline_proc_show", + .new_func = livepatch_cmdline_proc_show, + }, { } +}; + +static struct klp_object objs[] = { + { + /* name being NULL means vmlinux */ + .funcs = funcs, + }, { } +}; + +static struct klp_patch patch = { + .mod = THIS_MODULE, + .objs = objs, +}; + +static int test_klp_livepatch_init(void) +{ + return klp_enable_patch(&patch); +} + +static void test_klp_livepatch_exit(void) +{ +} + +module_init(test_klp_livepatch_init); +module_exit(test_klp_livepatch_exit); +MODULE_LICENSE("GPL"); +MODULE_INFO(livepatch, "Y"); +MODULE_AUTHOR("Seth Jennings "); +MODULE_DESCRIPTION("Livepatch test: livepatch module"); diff --git a/tools/testing/selftests/livepatch/test_modules/test_klp_shadow_vars.c b/tools/testing/selftests/livepatch/test_modules/test_klp_shadow_vars.c new file mode 100644 index 000000000000..b99116490858 --- /dev/null +++ b/tools/testing/selftests/livepatch/test_modules/test_klp_shadow_vars.c @@ -0,0 +1,301 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018 Joe Lawrence + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include + +/* + * Keep a small list of pointers so that we can print address-agnostic + * pointer values. Use a rolling integer count to differentiate the values. + * Ironically we could have used the shadow variable API to do this, but + * let's not lean too heavily on the very code we're testing. + */ +static LIST_HEAD(ptr_list); +struct shadow_ptr { + void *ptr; + int id; + struct list_head list; +}; + +static void free_ptr_list(void) +{ + struct shadow_ptr *sp, *tmp_sp; + + list_for_each_entry_safe(sp, tmp_sp, &ptr_list, list) { + list_del(&sp->list); + kfree(sp); + } +} + +static int ptr_id(void *ptr) +{ + struct shadow_ptr *sp; + static int count; + + list_for_each_entry(sp, &ptr_list, list) { + if (sp->ptr == ptr) + return sp->id; + } + + sp = kmalloc(sizeof(*sp), GFP_ATOMIC); + if (!sp) + return -ENOMEM; + sp->ptr = ptr; + sp->id = count++; + + list_add(&sp->list, &ptr_list); + + return sp->id; +} + +/* + * Shadow variable wrapper functions that echo the function and arguments + * to the kernel log for testing verification. Don't display raw pointers, + * but use the ptr_id() value instead. + */ +static void *shadow_get(void *obj, unsigned long id) +{ + int **sv; + + sv = klp_shadow_get(obj, id); + pr_info("klp_%s(obj=PTR%d, id=0x%lx) = PTR%d\n", + __func__, ptr_id(obj), id, ptr_id(sv)); + + return sv; +} + +static void *shadow_alloc(void *obj, unsigned long id, size_t size, + gfp_t gfp_flags, klp_shadow_ctor_t ctor, + void *ctor_data) +{ + int **var = ctor_data; + int **sv; + + sv = klp_shadow_alloc(obj, id, size, gfp_flags, ctor, var); + pr_info("klp_%s(obj=PTR%d, id=0x%lx, size=%zx, gfp_flags=%pGg), ctor=PTR%d, ctor_data=PTR%d = PTR%d\n", + __func__, ptr_id(obj), id, size, &gfp_flags, ptr_id(ctor), + ptr_id(*var), ptr_id(sv)); + + return sv; +} + +static void *shadow_get_or_alloc(void *obj, unsigned long id, size_t size, + gfp_t gfp_flags, klp_shadow_ctor_t ctor, + void *ctor_data) +{ + int **var = ctor_data; + int **sv; + + sv = klp_shadow_get_or_alloc(obj, id, size, gfp_flags, ctor, var); + pr_info("klp_%s(obj=PTR%d, id=0x%lx, size=%zx, gfp_flags=%pGg), ctor=PTR%d, ctor_data=PTR%d = PTR%d\n", + __func__, ptr_id(obj), id, size, &gfp_flags, ptr_id(ctor), + ptr_id(*var), ptr_id(sv)); + + return sv; +} + +static void shadow_free(void *obj, unsigned long id, klp_shadow_dtor_t dtor) +{ + klp_shadow_free(obj, id, dtor); + pr_info("klp_%s(obj=PTR%d, id=0x%lx, dtor=PTR%d)\n", + __func__, ptr_id(obj), id, ptr_id(dtor)); +} + +static void shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor) +{ + klp_shadow_free_all(id, dtor); + pr_info("klp_%s(id=0x%lx, dtor=PTR%d)\n", __func__, id, ptr_id(dtor)); +} + + +/* Shadow variable constructor - remember simple pointer data */ +static int shadow_ctor(void *obj, void *shadow_data, void *ctor_data) +{ + int **sv = shadow_data; + int **var = ctor_data; + + if (!var) + return -EINVAL; + + *sv = *var; + pr_info("%s: PTR%d -> PTR%d\n", __func__, ptr_id(sv), ptr_id(*var)); + + return 0; +} + +/* + * With more than one item to free in the list, order is not determined and + * shadow_dtor will not be passed to shadow_free_all() which would make the + * test fail. (see pass 6) + */ +static void shadow_dtor(void *obj, void *shadow_data) +{ + int **sv = shadow_data; + + pr_info("%s(obj=PTR%d, shadow_data=PTR%d)\n", + __func__, ptr_id(obj), ptr_id(sv)); +} + +/* number of objects we simulate that need shadow vars */ +#define NUM_OBJS 3 + +/* dynamically created obj fields have the following shadow var id values */ +#define SV_ID1 0x1234 +#define SV_ID2 0x1235 + +/* + * The main test case adds/removes new fields (shadow var) to each of these + * test structure instances. The last group of fields in the struct represent + * the idea that shadow variables may be added and removed to and from the + * struct during execution. + */ +struct test_object { + /* add anything here below and avoid to define an empty struct */ + struct shadow_ptr sp; + + /* these represent shadow vars added and removed with SV_ID{1,2} */ + /* char nfield1; */ + /* int nfield2; */ +}; + +static int test_klp_shadow_vars_init(void) +{ + struct test_object objs[NUM_OBJS]; + char nfields1[NUM_OBJS], *pnfields1[NUM_OBJS], **sv1[NUM_OBJS]; + char *pndup[NUM_OBJS]; + int nfields2[NUM_OBJS], *pnfields2[NUM_OBJS], **sv2[NUM_OBJS]; + void **sv; + int ret; + int i; + + ptr_id(NULL); + + /* + * With an empty shadow variable hash table, expect not to find + * any matches. + */ + sv = shadow_get(&objs[0], SV_ID1); + if (!sv) + pr_info(" got expected NULL result\n"); + + /* pass 1: init & alloc a char+int pair of svars for each objs */ + for (i = 0; i < NUM_OBJS; i++) { + pnfields1[i] = &nfields1[i]; + ptr_id(pnfields1[i]); + + if (i % 2) { + sv1[i] = shadow_alloc(&objs[i], SV_ID1, + sizeof(pnfields1[i]), GFP_KERNEL, + shadow_ctor, &pnfields1[i]); + } else { + sv1[i] = shadow_get_or_alloc(&objs[i], SV_ID1, + sizeof(pnfields1[i]), GFP_KERNEL, + shadow_ctor, &pnfields1[i]); + } + if (!sv1[i]) { + ret = -ENOMEM; + goto out; + } + + pnfields2[i] = &nfields2[i]; + ptr_id(pnfields2[i]); + sv2[i] = shadow_alloc(&objs[i], SV_ID2, sizeof(pnfields2[i]), + GFP_KERNEL, shadow_ctor, &pnfields2[i]); + if (!sv2[i]) { + ret = -ENOMEM; + goto out; + } + } + + /* pass 2: verify we find allocated svars and where they point to */ + for (i = 0; i < NUM_OBJS; i++) { + /* check the "char" svar for all objects */ + sv = shadow_get(&objs[i], SV_ID1); + if (!sv) { + ret = -EINVAL; + goto out; + } + if ((char **)sv == sv1[i] && *sv1[i] == pnfields1[i]) + pr_info(" got expected PTR%d -> PTR%d result\n", + ptr_id(sv1[i]), ptr_id(*sv1[i])); + + /* check the "int" svar for all objects */ + sv = shadow_get(&objs[i], SV_ID2); + if (!sv) { + ret = -EINVAL; + goto out; + } + if ((int **)sv == sv2[i] && *sv2[i] == pnfields2[i]) + pr_info(" got expected PTR%d -> PTR%d result\n", + ptr_id(sv2[i]), ptr_id(*sv2[i])); + } + + /* pass 3: verify that 'get_or_alloc' returns already allocated svars */ + for (i = 0; i < NUM_OBJS; i++) { + pndup[i] = &nfields1[i]; + ptr_id(pndup[i]); + + sv = shadow_get_or_alloc(&objs[i], SV_ID1, sizeof(pndup[i]), + GFP_KERNEL, shadow_ctor, &pndup[i]); + if (!sv) { + ret = -EINVAL; + goto out; + } + if ((char **)sv == sv1[i] && *sv1[i] == pnfields1[i]) + pr_info(" got expected PTR%d -> PTR%d result\n", + ptr_id(sv1[i]), ptr_id(*sv1[i])); + } + + /* pass 4: free pairs of svars, verify removal */ + for (i = 0; i < NUM_OBJS; i++) { + shadow_free(&objs[i], SV_ID1, shadow_dtor); /* 'char' pairs */ + sv = shadow_get(&objs[i], SV_ID1); + if (!sv) + pr_info(" got expected NULL result\n"); + } + + /* pass 5: check we still find svar pairs */ + for (i = 0; i < NUM_OBJS; i++) { + sv = shadow_get(&objs[i], SV_ID2); /* 'int' pairs */ + if (!sv) { + ret = -EINVAL; + goto out; + } + if ((int **)sv == sv2[i] && *sv2[i] == pnfields2[i]) + pr_info(" got expected PTR%d -> PTR%d result\n", + ptr_id(sv2[i]), ptr_id(*sv2[i])); + } + + /* pass 6: free all the svar pairs too. */ + shadow_free_all(SV_ID2, NULL); /* 'int' pairs */ + for (i = 0; i < NUM_OBJS; i++) { + sv = shadow_get(&objs[i], SV_ID2); + if (!sv) + pr_info(" got expected NULL result\n"); + } + + free_ptr_list(); + + return 0; +out: + shadow_free_all(SV_ID1, NULL); /* 'char' pairs */ + shadow_free_all(SV_ID2, NULL); /* 'int' pairs */ + free_ptr_list(); + + return ret; +} + +static void test_klp_shadow_vars_exit(void) +{ +} + +module_init(test_klp_shadow_vars_init); +module_exit(test_klp_shadow_vars_exit); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Joe Lawrence "); +MODULE_DESCRIPTION("Livepatch test: shadow variables"); diff --git a/tools/testing/selftests/livepatch/test_modules/test_klp_state.c b/tools/testing/selftests/livepatch/test_modules/test_klp_state.c new file mode 100644 index 000000000000..57a4253acb01 --- /dev/null +++ b/tools/testing/selftests/livepatch/test_modules/test_klp_state.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2019 SUSE + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include + +#define CONSOLE_LOGLEVEL_STATE 1 +/* Version 1 does not support migration. */ +#define CONSOLE_LOGLEVEL_STATE_VERSION 1 + +static const char *const module_state[] = { + [MODULE_STATE_LIVE] = "[MODULE_STATE_LIVE] Normal state", + [MODULE_STATE_COMING] = "[MODULE_STATE_COMING] Full formed, running module_init", + [MODULE_STATE_GOING] = "[MODULE_STATE_GOING] Going away", + [MODULE_STATE_UNFORMED] = "[MODULE_STATE_UNFORMED] Still setting it up", +}; + +static void callback_info(const char *callback, struct klp_object *obj) +{ + if (obj->mod) + pr_info("%s: %s -> %s\n", callback, obj->mod->name, + module_state[obj->mod->state]); + else + pr_info("%s: vmlinux\n", callback); +} + +static struct klp_patch patch; + +static int allocate_loglevel_state(void) +{ + struct klp_state *loglevel_state; + + loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE); + if (!loglevel_state) + return -EINVAL; + + loglevel_state->data = kzalloc(sizeof(console_loglevel), GFP_KERNEL); + if (!loglevel_state->data) + return -ENOMEM; + + pr_info("%s: allocating space to store console_loglevel\n", + __func__); + return 0; +} + +static void fix_console_loglevel(void) +{ + struct klp_state *loglevel_state; + + loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE); + if (!loglevel_state) + return; + + pr_info("%s: fixing console_loglevel\n", __func__); + *(int *)loglevel_state->data = console_loglevel; + console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; +} + +static void restore_console_loglevel(void) +{ + struct klp_state *loglevel_state; + + loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE); + if (!loglevel_state) + return; + + pr_info("%s: restoring console_loglevel\n", __func__); + console_loglevel = *(int *)loglevel_state->data; +} + +static void free_loglevel_state(void) +{ + struct klp_state *loglevel_state; + + loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE); + if (!loglevel_state) + return; + + pr_info("%s: freeing space for the stored console_loglevel\n", + __func__); + kfree(loglevel_state->data); +} + +/* Executed on object patching (ie, patch enablement) */ +static int pre_patch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); + return allocate_loglevel_state(); +} + +/* Executed on object unpatching (ie, patch disablement) */ +static void post_patch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); + fix_console_loglevel(); +} + +/* Executed on object unpatching (ie, patch disablement) */ +static void pre_unpatch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); + restore_console_loglevel(); +} + +/* Executed on object unpatching (ie, patch disablement) */ +static void post_unpatch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); + free_loglevel_state(); +} + +static struct klp_func no_funcs[] = { + {} +}; + +static struct klp_object objs[] = { + { + .name = NULL, /* vmlinux */ + .funcs = no_funcs, + .callbacks = { + .pre_patch = pre_patch_callback, + .post_patch = post_patch_callback, + .pre_unpatch = pre_unpatch_callback, + .post_unpatch = post_unpatch_callback, + }, + }, { } +}; + +static struct klp_state states[] = { + { + .id = CONSOLE_LOGLEVEL_STATE, + .version = CONSOLE_LOGLEVEL_STATE_VERSION, + }, { } +}; + +static struct klp_patch patch = { + .mod = THIS_MODULE, + .objs = objs, + .states = states, + .replace = true, +}; + +static int test_klp_callbacks_demo_init(void) +{ + return klp_enable_patch(&patch); +} + +static void test_klp_callbacks_demo_exit(void) +{ +} + +module_init(test_klp_callbacks_demo_init); +module_exit(test_klp_callbacks_demo_exit); +MODULE_LICENSE("GPL"); +MODULE_INFO(livepatch, "Y"); +MODULE_AUTHOR("Petr Mladek "); +MODULE_DESCRIPTION("Livepatch test: system state modification"); diff --git a/tools/testing/selftests/livepatch/test_modules/test_klp_state2.c b/tools/testing/selftests/livepatch/test_modules/test_klp_state2.c new file mode 100644 index 000000000000..c978ea4d5e67 --- /dev/null +++ b/tools/testing/selftests/livepatch/test_modules/test_klp_state2.c @@ -0,0 +1,191 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2019 SUSE + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include + +#define CONSOLE_LOGLEVEL_STATE 1 +/* Version 2 supports migration. */ +#define CONSOLE_LOGLEVEL_STATE_VERSION 2 + +static const char *const module_state[] = { + [MODULE_STATE_LIVE] = "[MODULE_STATE_LIVE] Normal state", + [MODULE_STATE_COMING] = "[MODULE_STATE_COMING] Full formed, running module_init", + [MODULE_STATE_GOING] = "[MODULE_STATE_GOING] Going away", + [MODULE_STATE_UNFORMED] = "[MODULE_STATE_UNFORMED] Still setting it up", +}; + +static void callback_info(const char *callback, struct klp_object *obj) +{ + if (obj->mod) + pr_info("%s: %s -> %s\n", callback, obj->mod->name, + module_state[obj->mod->state]); + else + pr_info("%s: vmlinux\n", callback); +} + +static struct klp_patch patch; + +static int allocate_loglevel_state(void) +{ + struct klp_state *loglevel_state, *prev_loglevel_state; + + prev_loglevel_state = klp_get_prev_state(CONSOLE_LOGLEVEL_STATE); + if (prev_loglevel_state) { + pr_info("%s: space to store console_loglevel already allocated\n", + __func__); + return 0; + } + + loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE); + if (!loglevel_state) + return -EINVAL; + + loglevel_state->data = kzalloc(sizeof(console_loglevel), GFP_KERNEL); + if (!loglevel_state->data) + return -ENOMEM; + + pr_info("%s: allocating space to store console_loglevel\n", + __func__); + return 0; +} + +static void fix_console_loglevel(void) +{ + struct klp_state *loglevel_state, *prev_loglevel_state; + + loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE); + if (!loglevel_state) + return; + + prev_loglevel_state = klp_get_prev_state(CONSOLE_LOGLEVEL_STATE); + if (prev_loglevel_state) { + pr_info("%s: taking over the console_loglevel change\n", + __func__); + loglevel_state->data = prev_loglevel_state->data; + return; + } + + pr_info("%s: fixing console_loglevel\n", __func__); + *(int *)loglevel_state->data = console_loglevel; + console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; +} + +static void restore_console_loglevel(void) +{ + struct klp_state *loglevel_state, *prev_loglevel_state; + + prev_loglevel_state = klp_get_prev_state(CONSOLE_LOGLEVEL_STATE); + if (prev_loglevel_state) { + pr_info("%s: passing the console_loglevel change back to the old livepatch\n", + __func__); + return; + } + + loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE); + if (!loglevel_state) + return; + + pr_info("%s: restoring console_loglevel\n", __func__); + console_loglevel = *(int *)loglevel_state->data; +} + +static void free_loglevel_state(void) +{ + struct klp_state *loglevel_state, *prev_loglevel_state; + + prev_loglevel_state = klp_get_prev_state(CONSOLE_LOGLEVEL_STATE); + if (prev_loglevel_state) { + pr_info("%s: keeping space to store console_loglevel\n", + __func__); + return; + } + + loglevel_state = klp_get_state(&patch, CONSOLE_LOGLEVEL_STATE); + if (!loglevel_state) + return; + + pr_info("%s: freeing space for the stored console_loglevel\n", + __func__); + kfree(loglevel_state->data); +} + +/* Executed on object patching (ie, patch enablement) */ +static int pre_patch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); + return allocate_loglevel_state(); +} + +/* Executed on object unpatching (ie, patch disablement) */ +static void post_patch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); + fix_console_loglevel(); +} + +/* Executed on object unpatching (ie, patch disablement) */ +static void pre_unpatch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); + restore_console_loglevel(); +} + +/* Executed on object unpatching (ie, patch disablement) */ +static void post_unpatch_callback(struct klp_object *obj) +{ + callback_info(__func__, obj); + free_loglevel_state(); +} + +static struct klp_func no_funcs[] = { + {} +}; + +static struct klp_object objs[] = { + { + .name = NULL, /* vmlinux */ + .funcs = no_funcs, + .callbacks = { + .pre_patch = pre_patch_callback, + .post_patch = post_patch_callback, + .pre_unpatch = pre_unpatch_callback, + .post_unpatch = post_unpatch_callback, + }, + }, { } +}; + +static struct klp_state states[] = { + { + .id = CONSOLE_LOGLEVEL_STATE, + .version = CONSOLE_LOGLEVEL_STATE_VERSION, + }, { } +}; + +static struct klp_patch patch = { + .mod = THIS_MODULE, + .objs = objs, + .states = states, + .replace = true, +}; + +static int test_klp_callbacks_demo_init(void) +{ + return klp_enable_patch(&patch); +} + +static void test_klp_callbacks_demo_exit(void) +{ +} + +module_init(test_klp_callbacks_demo_init); +module_exit(test_klp_callbacks_demo_exit); +MODULE_LICENSE("GPL"); +MODULE_INFO(livepatch, "Y"); +MODULE_AUTHOR("Petr Mladek "); +MODULE_DESCRIPTION("Livepatch test: system state modification"); diff --git a/tools/testing/selftests/livepatch/test_modules/test_klp_state3.c b/tools/testing/selftests/livepatch/test_modules/test_klp_state3.c new file mode 100644 index 000000000000..9226579d10c5 --- /dev/null +++ b/tools/testing/selftests/livepatch/test_modules/test_klp_state3.c @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2019 SUSE + +/* The console loglevel fix is the same in the next cumulative patch. */ +#include "test_klp_state2.c" -- cgit v1.2.3-70-g09d2 From 6a71770442b5b7cf8f880ca1c0a72456c918c757 Mon Sep 17 00:00:00 2001 From: Marcos Paulo de Souza Date: Fri, 12 Jan 2024 14:43:52 -0300 Subject: selftests: livepatch: Test livepatching a heavily called syscall The test proves that a syscall can be livepatched. It is interesting because syscalls are called a tricky way. Also the process gets livepatched either when sleeping in the userspace or when entering or leaving the kernel space. The livepatch is a bit tricky: 1. The syscall function name is architecture specific. Also ARCH_HAS_SYSCALL_WRAPPER must be taken in account. 2. The syscall must stay working the same way for other processes on the system. It is solved by decrementing a counter only for PIDs of the test processes. It means that the test processes has to call the livepatched syscall at least once. The test creates one userspace process per online cpu. The processes are calling getpid in a busy loop. The intention is to create random locations when the livepatch gets enabled. Nothing is guarantted. The magic is in the randomness. Reviewed-by: Joe Lawrence Reviewed-by: Petr Mladek Signed-off-by: Marcos Paulo de Souza Signed-off-by: Shuah Khan --- tools/testing/selftests/livepatch/Makefile | 4 +- tools/testing/selftests/livepatch/test-syscall.sh | 53 ++++++++++ .../selftests/livepatch/test_klp-call_getpid.c | 44 ++++++++ .../selftests/livepatch/test_modules/Makefile | 3 +- .../livepatch/test_modules/test_klp_syscall.c | 116 +++++++++++++++++++++ 5 files changed, 218 insertions(+), 2 deletions(-) create mode 100755 tools/testing/selftests/livepatch/test-syscall.sh create mode 100644 tools/testing/selftests/livepatch/test_klp-call_getpid.c create mode 100644 tools/testing/selftests/livepatch/test_modules/test_klp_syscall.c (limited to 'tools') diff --git a/tools/testing/selftests/livepatch/Makefile b/tools/testing/selftests/livepatch/Makefile index 119e2bbebe5d..35418a4790be 100644 --- a/tools/testing/selftests/livepatch/Makefile +++ b/tools/testing/selftests/livepatch/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 +TEST_GEN_FILES := test_klp-call_getpid TEST_GEN_MODS_DIR := test_modules TEST_PROGS_EXTENDED := functions.sh TEST_PROGS := \ @@ -8,7 +9,8 @@ TEST_PROGS := \ test-shadow-vars.sh \ test-state.sh \ test-ftrace.sh \ - test-sysfs.sh + test-sysfs.sh \ + test-syscall.sh TEST_FILES := settings diff --git a/tools/testing/selftests/livepatch/test-syscall.sh b/tools/testing/selftests/livepatch/test-syscall.sh new file mode 100755 index 000000000000..b76a881d4013 --- /dev/null +++ b/tools/testing/selftests/livepatch/test-syscall.sh @@ -0,0 +1,53 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Copyright (C) 2023 SUSE +# Author: Marcos Paulo de Souza + +. $(dirname $0)/functions.sh + +MOD_SYSCALL=test_klp_syscall + +setup_config + +# - Start _NRPROC processes calling getpid and load a livepatch to patch the +# getpid syscall. Check if all the processes transitioned to the livepatched +# state. + +start_test "patch getpid syscall while being heavily hammered" + +for i in $(seq 1 $(getconf _NPROCESSORS_ONLN)); do + ./test_klp-call_getpid & + pids[$i]="$!" +done + +pid_list=$(echo ${pids[@]} | tr ' ' ',') +load_lp $MOD_SYSCALL klp_pids=$pid_list + +# wait for all tasks to transition to patched state +loop_until 'grep -q '^0$' /sys/kernel/test_klp_syscall/npids' + +pending_pids=$(cat /sys/kernel/test_klp_syscall/npids) +log "$MOD_SYSCALL: Remaining not livepatched processes: $pending_pids" + +for pid in ${pids[@]}; do + kill $pid || true +done + +disable_lp $MOD_SYSCALL +unload_lp $MOD_SYSCALL + +check_result "% insmod test_modules/$MOD_SYSCALL.ko klp_pids=$pid_list +livepatch: enabling patch '$MOD_SYSCALL' +livepatch: '$MOD_SYSCALL': initializing patching transition +livepatch: '$MOD_SYSCALL': starting patching transition +livepatch: '$MOD_SYSCALL': completing patching transition +livepatch: '$MOD_SYSCALL': patching complete +$MOD_SYSCALL: Remaining not livepatched processes: 0 +% echo 0 > /sys/kernel/livepatch/$MOD_SYSCALL/enabled +livepatch: '$MOD_SYSCALL': initializing unpatching transition +livepatch: '$MOD_SYSCALL': starting unpatching transition +livepatch: '$MOD_SYSCALL': completing unpatching transition +livepatch: '$MOD_SYSCALL': unpatching complete +% rmmod $MOD_SYSCALL" + +exit 0 diff --git a/tools/testing/selftests/livepatch/test_klp-call_getpid.c b/tools/testing/selftests/livepatch/test_klp-call_getpid.c new file mode 100644 index 000000000000..ce321a2d7308 --- /dev/null +++ b/tools/testing/selftests/livepatch/test_klp-call_getpid.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 SUSE + * Authors: Libor Pechacek + * Marcos Paulo de Souza + */ + +#include +#include +#include +#include +#include + +static int stop; +static int sig_int; + +void hup_handler(int signum) +{ + stop = 1; +} + +void int_handler(int signum) +{ + stop = 1; + sig_int = 1; +} + +int main(int argc, char *argv[]) +{ + long count = 0; + + signal(SIGHUP, &hup_handler); + signal(SIGINT, &int_handler); + + while (!stop) { + (void)syscall(SYS_getpid); + count++; + } + + if (sig_int) + printf("%ld iterations done\n", count); + + return 0; +} diff --git a/tools/testing/selftests/livepatch/test_modules/Makefile b/tools/testing/selftests/livepatch/test_modules/Makefile index 6f7c2103d27d..f5e880269bff 100644 --- a/tools/testing/selftests/livepatch/test_modules/Makefile +++ b/tools/testing/selftests/livepatch/test_modules/Makefile @@ -10,7 +10,8 @@ obj-m += test_klp_atomic_replace.o \ test_klp_state.o \ test_klp_state2.o \ test_klp_state3.o \ - test_klp_shadow_vars.o + test_klp_shadow_vars.o \ + test_klp_syscall.o modules: $(Q)$(MAKE) -C $(KDIR) modules KBUILD_EXTMOD=$(TESTMODS_DIR) diff --git a/tools/testing/selftests/livepatch/test_modules/test_klp_syscall.c b/tools/testing/selftests/livepatch/test_modules/test_klp_syscall.c new file mode 100644 index 000000000000..dd802783ea84 --- /dev/null +++ b/tools/testing/selftests/livepatch/test_modules/test_klp_syscall.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2017-2023 SUSE + * Authors: Libor Pechacek + * Nicolai Stange + * Marcos Paulo de Souza + */ + +#include +#include +#include +#include +#include + +#if defined(__x86_64__) +#define FN_PREFIX __x64_ +#elif defined(__s390x__) +#define FN_PREFIX __s390x_ +#elif defined(__aarch64__) +#define FN_PREFIX __arm64_ +#else +/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER */ +#define FN_PREFIX +#endif + +/* Protects klp_pids */ +static DEFINE_MUTEX(kpid_mutex); + +static unsigned int npids, npids_pending; +static int klp_pids[NR_CPUS]; +module_param_array(klp_pids, int, &npids_pending, 0); +MODULE_PARM_DESC(klp_pids, "Array of pids to be transitioned to livepatched state."); + +static ssize_t npids_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", npids_pending); +} + +static struct kobj_attribute klp_attr = __ATTR_RO(npids); +static struct kobject *klp_kobj; + +static asmlinkage long lp_sys_getpid(void) +{ + int i; + + mutex_lock(&kpid_mutex); + if (npids_pending > 0) { + for (i = 0; i < npids; i++) { + if (current->pid == klp_pids[i]) { + klp_pids[i] = 0; + npids_pending--; + break; + } + } + } + mutex_unlock(&kpid_mutex); + + return task_tgid_vnr(current); +} + +static struct klp_func vmlinux_funcs[] = { + { + .old_name = __stringify(FN_PREFIX) "sys_getpid", + .new_func = lp_sys_getpid, + }, {} +}; + +static struct klp_object objs[] = { + { + /* name being NULL means vmlinux */ + .funcs = vmlinux_funcs, + }, {} +}; + +static struct klp_patch patch = { + .mod = THIS_MODULE, + .objs = objs, +}; + +static int livepatch_init(void) +{ + int ret; + + klp_kobj = kobject_create_and_add("test_klp_syscall", kernel_kobj); + if (!klp_kobj) + return -ENOMEM; + + ret = sysfs_create_file(klp_kobj, &klp_attr.attr); + if (ret) { + kobject_put(klp_kobj); + return ret; + } + + /* + * Save the number pids to transition to livepatched state before the + * number of pending pids is decremented. + */ + npids = npids_pending; + + return klp_enable_patch(&patch); +} + +static void livepatch_exit(void) +{ + kobject_put(klp_kobj); +} + +module_init(livepatch_init); +module_exit(livepatch_exit); +MODULE_LICENSE("GPL"); +MODULE_INFO(livepatch, "Y"); +MODULE_AUTHOR("Libor Pechacek "); +MODULE_AUTHOR("Nicolai Stange "); +MODULE_AUTHOR("Marcos Paulo de Souza "); +MODULE_DESCRIPTION("Livepatch test: syscall transition"); -- cgit v1.2.3-70-g09d2 From a6b48c83d28e21ddcd6a080128bb73f9e3d130ac Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 25 Jan 2024 06:21:56 -1000 Subject: tools/workqueue/wq_dump.py: Clean up code and drop duplicate information - Factor out wq_type_str() - Improve formatting so that it adapts to actual field widths. - Drop duplicate information from "Workqueue -> rescuer" section. If anything, we should add more rescuer-specific info - e.g. the number of work items rescued. Signed-off-by: Tejun Heo Cc: Juri Lelli --- tools/workqueue/wq_dump.py | 69 +++++++++++++++++++++++----------------------- 1 file changed, 35 insertions(+), 34 deletions(-) (limited to 'tools') diff --git a/tools/workqueue/wq_dump.py b/tools/workqueue/wq_dump.py index 6da621989e21..333b2fc00b82 100644 --- a/tools/workqueue/wq_dump.py +++ b/tools/workqueue/wq_dump.py @@ -75,6 +75,20 @@ def cpumask_str(cpumask): output += f'{v:08x}' return output.strip() +wq_type_len = 9 + +def wq_type_str(wq): + if wq.flags & WQ_UNBOUND: + if wq.flags & WQ_ORDERED: + return f'{"ordered":{wq_type_len}}' + else: + if wq.unbound_attrs.affn_strict: + return f'{"unbound,S":{wq_type_len}}' + else: + return f'{"unbound":{wq_type_len}}' + else: + return f'{"percpu":{wq_type_len}}' + worker_pool_idr = prog['worker_pool_idr'] workqueues = prog['workqueues'] wq_unbound_cpumask = prog['wq_unbound_cpumask'] @@ -92,6 +106,10 @@ WQ_AFFN_CACHE = prog['WQ_AFFN_CACHE'] WQ_AFFN_NUMA = prog['WQ_AFFN_NUMA'] WQ_AFFN_SYSTEM = prog['WQ_AFFN_SYSTEM'] +WQ_NAME_LEN = prog['WQ_NAME_LEN'].value_() + +cpumask_str_len = len(cpumask_str(wq_unbound_cpumask)) + print('Affinity Scopes') print('===============') @@ -148,24 +166,13 @@ print('') print('Workqueue CPU -> pool') print('=====================') -print('[ workqueue \ type CPU', end='') +print(f'[{"workqueue":^{WQ_NAME_LEN-2}}\\ {"type CPU":{wq_type_len}}', end='') for cpu in for_each_possible_cpu(prog): print(f' {cpu:{max_pool_id_len}}', end='') print(' dfl]') for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'): - print(f'{wq.name.string_().decode()[-24:]:24}', end='') - if wq.flags & WQ_UNBOUND: - if wq.flags & WQ_ORDERED: - print(' ordered ', end='') - else: - print(' unbound', end='') - if wq.unbound_attrs.affn_strict: - print(',S ', end='') - else: - print(' ', end='') - else: - print(' percpu ', end='') + print(f'{wq.name.string_().decode():{WQ_NAME_LEN}} {wq_type_str(wq):10}', end='') for cpu in for_each_possible_cpu(prog): pool_id = per_cpu_ptr(wq.cpu_pwq, cpu)[0].pool.id.value_() @@ -178,29 +185,23 @@ for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_( print('') print('Workqueue -> rescuer') -print('=====================') -print(f'wq_unbound_cpumask={cpumask_str(wq_unbound_cpumask)}') -print('') -print('[ workqueue \ type unbound_cpumask rescuer pid cpumask]') +print('====================') + +ucpus_len = max(cpumask_str_len, len("unbound_cpus")) +rcpus_len = max(cpumask_str_len, len("rescuer_cpus")) + +print(f'[{"workqueue":^{WQ_NAME_LEN-2}}\\ {"unbound_cpus":{ucpus_len}} pid {"rescuer_cpus":{rcpus_len}} ]') for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'): - print(f'{wq.name.string_().decode()[-24:]:24}', end='') - if wq.flags & WQ_UNBOUND: - if wq.flags & WQ_ORDERED: - print(' ordered ', end='') - else: - print(' unbound', end='') - if wq.unbound_attrs.affn_strict: - print(',S ', end='') - else: - print(' ', end='') - print(f' {cpumask_str(wq.unbound_attrs.cpumask):24}', end='') + if not (wq.flags & WQ_MEM_RECLAIM): + continue + + print(f'{wq.name.string_().decode():{WQ_NAME_LEN}}', end='') + if wq.unbound_attrs.value_() != 0: + print(f' {cpumask_str(wq.unbound_attrs.cpumask):{ucpus_len}}', end='') else: - print(' percpu ', end='') - print(' ', end='') + print(f' {"":{ucpus_len}}', end='') - if wq.flags & WQ_MEM_RECLAIM: - print(f' {wq.rescuer.task.comm.string_().decode()[-24:]:24}', end='') - print(f' {wq.rescuer.task.pid.value_():5}', end='') - print(f' {cpumask_str(wq.rescuer.task.cpus_ptr)}', end='') + print(f' {wq.rescuer.task.pid.value_():6}', end='') + print(f' {cpumask_str(wq.rescuer.task.cpus_ptr):{rcpus_len}}', end='') print('') -- cgit v1.2.3-70-g09d2 From a4cb5ece145828cae35503857debf3d49c9d1c5f Mon Sep 17 00:00:00 2001 From: Xin Li Date: Tue, 5 Dec 2023 02:49:50 -0800 Subject: x86/cpufeatures,opcode,msr: Add the WRMSRNS instruction support WRMSRNS is an instruction that behaves exactly like WRMSR, with the only difference being that it is not a serializing instruction by default. Under certain conditions, WRMSRNS may replace WRMSR to improve performance. Add its CPU feature bit, opcode to the x86 opcode map, and an always inline API __wrmsrns() to embed WRMSRNS into the code. Signed-off-by: Xin Li Signed-off-by: Thomas Gleixner Tested-by: Shan Kang Acked-by: Masami Hiramatsu (Google) Acked-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20231205105030.8698-2-xin3.li@intel.com --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/msr.h | 18 ++++++++++++++++++ arch/x86/lib/x86-opcode-map.txt | 2 +- tools/arch/x86/include/asm/cpufeatures.h | 1 + tools/arch/x86/lib/x86-opcode-map.txt | 2 +- 5 files changed, 22 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 29cb275a219d..bd05c75c62aa 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -327,6 +327,7 @@ #define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ #define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ #define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ +#define X86_FEATURE_WRMSRNS (12*32+19) /* "" Non-serializing WRMSR */ #define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ #define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ #define X86_FEATURE_LAM (12*32+26) /* Linear Address Masking */ diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 65ec1965cd28..c284ff9ebe67 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -97,6 +97,19 @@ static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high) : : "c" (msr), "a"(low), "d" (high) : "memory"); } +/* + * WRMSRNS behaves exactly like WRMSR with the only difference being + * that it is not a serializing instruction by default. + */ +static __always_inline void __wrmsrns(u32 msr, u32 low, u32 high) +{ + /* Instruction opcode for WRMSRNS; supported in binutils >= 2.40. */ + asm volatile("1: .byte 0x0f,0x01,0xc6\n" + "2:\n" + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR) + : : "c" (msr), "a"(low), "d" (high)); +} + #define native_rdmsr(msr, val1, val2) \ do { \ u64 __val = __rdmsr((msr)); \ @@ -297,6 +310,11 @@ do { \ #endif /* !CONFIG_PARAVIRT_XXL */ +static __always_inline void wrmsrns(u32 msr, u64 val) +{ + __wrmsrns(msr, val, val >> 32); +} + /* * 64-bit version of wrmsr_safe(): */ diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 5168ee0360b2..1efe1d9bf5ce 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -1051,7 +1051,7 @@ GrpTable: Grp6 EndTable GrpTable: Grp7 -0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) +0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) | WRMSRNS (110),(11B) 1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B) 3: LIDT Ms diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index f4542d2718f4..879284101603 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -322,6 +322,7 @@ #define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ #define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ #define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ +#define X86_FEATURE_WRMSRNS (12*32+19) /* "" Non-serializing WRMSR */ #define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ #define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ #define X86_FEATURE_LAM (12*32+26) /* Linear Address Masking */ diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt index 5168ee0360b2..1efe1d9bf5ce 100644 --- a/tools/arch/x86/lib/x86-opcode-map.txt +++ b/tools/arch/x86/lib/x86-opcode-map.txt @@ -1051,7 +1051,7 @@ GrpTable: Grp6 EndTable GrpTable: Grp7 -0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) +0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) | WRMSRNS (110),(11B) 1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B) 3: LIDT Ms -- cgit v1.2.3-70-g09d2 From 51c158f7aaccc6f6423a61a1df4a0d4c0d9d22a9 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin (Intel)" Date: Tue, 5 Dec 2023 02:49:55 -0800 Subject: x86/cpufeatures: Add the CPU feature bit for FRED MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Any FRED enabled CPU will always have the following features as its baseline: 1) LKGS, load attributes of the GS segment but the base address into the IA32_KERNEL_GS_BASE MSR instead of the GS segment’s descriptor cache. 2) WRMSRNS, non-serializing WRMSR for faster MSR writes. Signed-off-by: H. Peter Anvin (Intel) Signed-off-by: Xin Li Signed-off-by: Thomas Gleixner Tested-by: Shan Kang Link: https://lore.kernel.org/r/20231205105030.8698-7-xin3.li@intel.com --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/kernel/cpu/cpuid-deps.c | 2 ++ tools/arch/x86/include/asm/cpufeatures.h | 1 + 3 files changed, 4 insertions(+) (limited to 'tools') diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index bd05c75c62aa..ccbf914b3d1a 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -326,6 +326,7 @@ #define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */ #define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ #define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ +#define X86_FEATURE_FRED (12*32+17) /* Flexible Return and Event Delivery */ #define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ #define X86_FEATURE_WRMSRNS (12*32+19) /* "" Non-serializing WRMSR */ #define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index e462c1d3800a..b7174209d855 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -82,6 +82,8 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_XFD, X86_FEATURE_XGETBV1 }, { X86_FEATURE_AMX_TILE, X86_FEATURE_XFD }, { X86_FEATURE_SHSTK, X86_FEATURE_XSAVES }, + { X86_FEATURE_FRED, X86_FEATURE_LKGS }, + { X86_FEATURE_FRED, X86_FEATURE_WRMSRNS }, {} }; diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 879284101603..953e6efead26 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -321,6 +321,7 @@ #define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */ #define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ #define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ +#define X86_FEATURE_FRED (12*32+17) /* Flexible Return and Event Delivery */ #define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ #define X86_FEATURE_WRMSRNS (12*32+19) /* "" Non-serializing WRMSR */ #define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ -- cgit v1.2.3-70-g09d2 From e554a8ca49d6d6d782f546ae4d7f036946e7dd87 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin (Intel)" Date: Tue, 5 Dec 2023 02:49:56 -0800 Subject: x86/fred: Disable FRED support if CONFIG_X86_FRED is disabled Add CONFIG_X86_FRED to to make cpu_feature_enabled() work correctly with FRED. Originally-by: Megha Dey Signed-off-by: H. Peter Anvin (Intel) Signed-off-by: Xin Li Signed-off-by: Thomas Gleixner Tested-by: Shan Kang Link: https://lore.kernel.org/r/20231205105030.8698-8-xin3.li@intel.com --- arch/x86/include/asm/disabled-features.h | 8 +++++++- tools/arch/x86/include/asm/disabled-features.h | 8 +++++++- 2 files changed, 14 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 702d93fdd10e..f40b29d3abad 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -117,6 +117,12 @@ #define DISABLE_IBT (1 << (X86_FEATURE_IBT & 31)) #endif +#ifdef CONFIG_X86_FRED +# define DISABLE_FRED 0 +#else +# define DISABLE_FRED (1 << (X86_FEATURE_FRED & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -133,7 +139,7 @@ #define DISABLED_MASK10 0 #define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \ DISABLE_CALL_DEPTH_TRACKING|DISABLE_USER_SHSTK) -#define DISABLED_MASK12 (DISABLE_LAM) +#define DISABLED_MASK12 (DISABLE_FRED|DISABLE_LAM) #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 702d93fdd10e..f40b29d3abad 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -117,6 +117,12 @@ #define DISABLE_IBT (1 << (X86_FEATURE_IBT & 31)) #endif +#ifdef CONFIG_X86_FRED +# define DISABLE_FRED 0 +#else +# define DISABLE_FRED (1 << (X86_FEATURE_FRED & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -133,7 +139,7 @@ #define DISABLED_MASK10 0 #define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \ DISABLE_CALL_DEPTH_TRACKING|DISABLE_USER_SHSTK) -#define DISABLED_MASK12 (DISABLE_LAM) +#define DISABLED_MASK12 (DISABLE_FRED|DISABLE_LAM) #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 -- cgit v1.2.3-70-g09d2 From 07daa99b7fd7adfffa22180184e39ec124e73013 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 29 Jan 2024 08:11:25 -1000 Subject: tools/workqueue/wq_dump.py: Add node_nr/max_active dump Print out per-node nr/max_active numbers to improve visibility into node_nr_active operations. Signed-off-by: Tejun Heo --- tools/workqueue/wq_dump.py | 41 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 40 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/workqueue/wq_dump.py b/tools/workqueue/wq_dump.py index 333b2fc00b82..bd381511bd9a 100644 --- a/tools/workqueue/wq_dump.py +++ b/tools/workqueue/wq_dump.py @@ -50,6 +50,7 @@ import drgn from drgn.helpers.linux.list import list_for_each_entry,list_empty from drgn.helpers.linux.percpu import per_cpu_ptr from drgn.helpers.linux.cpumask import for_each_cpu,for_each_possible_cpu +from drgn.helpers.linux.nodemask import for_each_node from drgn.helpers.linux.idr import idr_for_each import argparse @@ -107,7 +108,6 @@ WQ_AFFN_NUMA = prog['WQ_AFFN_NUMA'] WQ_AFFN_SYSTEM = prog['WQ_AFFN_SYSTEM'] WQ_NAME_LEN = prog['WQ_NAME_LEN'].value_() - cpumask_str_len = len(cpumask_str(wq_unbound_cpumask)) print('Affinity Scopes') @@ -205,3 +205,42 @@ for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_( print(f' {wq.rescuer.task.pid.value_():6}', end='') print(f' {cpumask_str(wq.rescuer.task.cpus_ptr):{rcpus_len}}', end='') print('') + +print('') +print('Unbound workqueue -> node_nr/max_active') +print('=======================================') + +if 'node_to_cpumask_map' in prog: + __cpu_online_mask = prog['__cpu_online_mask'] + node_to_cpumask_map = prog['node_to_cpumask_map'] + nr_node_ids = prog['nr_node_ids'].value_() + + print(f'online_cpus={cpumask_str(__cpu_online_mask.address_of_())}') + for node in for_each_node(): + print(f'NODE[{node:02}]={cpumask_str(node_to_cpumask_map[node])}') + print('') + + print(f'[{"workqueue":^{WQ_NAME_LEN-2}}\\ min max', end='') + first = True + for node in for_each_node(): + if first: + print(f' NODE {node}', end='') + first = False + else: + print(f' {node:7}', end='') + print(f' {"dfl":>7} ]') + print('') + + for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'): + if not (wq.flags & WQ_UNBOUND): + continue + + print(f'{wq.name.string_().decode():{WQ_NAME_LEN}} ', end='') + print(f'{wq.min_active.value_():3} {wq.max_active.value_():3}', end='') + for node in for_each_node(): + nna = wq.node_nr_active[node] + print(f' {nna.nr.counter.value_():3}/{nna.max.value_():3}', end='') + nna = wq.node_nr_active[nr_node_ids] + print(f' {nna.nr.counter.value_():3}/{nna.max.value_():3}') +else: + printf(f'node_to_cpumask_map not present, is NUMA enabled?') -- cgit v1.2.3-70-g09d2 From 0115f8b1a26ef49338cdb0bd98ad374b8586d0fd Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin (Intel)" Date: Tue, 5 Dec 2023 02:49:58 -0800 Subject: x86/opcode: Add ERET[US] instructions to the x86 opcode map ERETU returns from an event handler while making a transition to ring 3, and ERETS returns from an event handler while staying in ring 0. Add instruction opcodes used by ERET[US] to the x86 opcode map; opcode numbers are per FRED spec v5.0. Signed-off-by: H. Peter Anvin (Intel) Signed-off-by: Xin Li Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov (AMD) Tested-by: Shan Kang Reviewed-by: Masami Hiramatsu (Google) Link: https://lore.kernel.org/r/20231205105030.8698-10-xin3.li@intel.com --- arch/x86/lib/x86-opcode-map.txt | 2 +- tools/arch/x86/lib/x86-opcode-map.txt | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 1efe1d9bf5ce..12af572201a2 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -1052,7 +1052,7 @@ EndTable GrpTable: Grp7 0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) | WRMSRNS (110),(11B) -1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) +1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) | ERETU (F3),(010),(11B) | ERETS (F2),(010),(11B) 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B) 3: LIDT Ms 4: SMSW Mw/Rv diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt index 1efe1d9bf5ce..12af572201a2 100644 --- a/tools/arch/x86/lib/x86-opcode-map.txt +++ b/tools/arch/x86/lib/x86-opcode-map.txt @@ -1052,7 +1052,7 @@ EndTable GrpTable: Grp7 0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) | WRMSRNS (110),(11B) -1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) +1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) | ERETU (F3),(010),(11B) | ERETS (F2),(010),(11B) 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B) 3: LIDT Ms 4: SMSW Mw/Rv -- cgit v1.2.3-70-g09d2 From cd19bab825bda5bb192ef1d22e67d069daf2efb8 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin (Intel)" Date: Tue, 5 Dec 2023 02:49:59 -0800 Subject: x86/objtool: Teach objtool about ERET[US] Update the objtool decoder to know about the ERET[US] instructions (type INSN_CONTEXT_SWITCH). Signed-off-by: H. Peter Anvin (Intel) Signed-off-by: Xin Li Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov (AMD) Tested-by: Shan Kang Link: https://lore.kernel.org/r/20231205105030.8698-11-xin3.li@intel.com --- tools/objtool/arch/x86/decode.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) (limited to 'tools') diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index e327cd827135..3a1d80a7878d 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -509,11 +509,20 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec if (op2 == 0x01) { - if (modrm == 0xca) - insn->type = INSN_CLAC; - else if (modrm == 0xcb) - insn->type = INSN_STAC; - + switch (insn_last_prefix_id(&ins)) { + case INAT_PFX_REPE: + case INAT_PFX_REPNE: + if (modrm == 0xca) + /* eretu/erets */ + insn->type = INSN_CONTEXT_SWITCH; + break; + default: + if (modrm == 0xca) + insn->type = INSN_CLAC; + else if (modrm == 0xcb) + insn->type = INSN_STAC; + break; + } } else if (op2 >= 0x80 && op2 <= 0x8f) { insn->type = INSN_JUMP_CONDITIONAL; -- cgit v1.2.3-70-g09d2 From cd6df3f378f63f5d6dce0987169b182be1cb427c Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin (Intel)" Date: Tue, 5 Dec 2023 02:50:01 -0800 Subject: x86/cpu: Add MSR numbers for FRED configuration Add MSR numbers for the FRED configuration registers per FRED spec 5.0. Originally-by: Megha Dey Signed-off-by: H. Peter Anvin (Intel) Signed-off-by: Xin Li Signed-off-by: Thomas Gleixner Signed-off-by: Borislav Petkov (AMD) Tested-by: Shan Kang Link: https://lore.kernel.org/r/20231205105030.8698-13-xin3.li@intel.com --- arch/x86/include/asm/msr-index.h | 13 ++++++++++++- tools/arch/x86/include/asm/msr-index.h | 13 ++++++++++++- 2 files changed, 24 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index f1bd7b91b3c6..1f9dc9bd13eb 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -36,8 +36,19 @@ #define EFER_FFXSR (1<<_EFER_FFXSR) #define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS) -/* Intel MSRs. Some also available on other CPUs */ +/* FRED MSRs */ +#define MSR_IA32_FRED_RSP0 0x1cc /* Level 0 stack pointer */ +#define MSR_IA32_FRED_RSP1 0x1cd /* Level 1 stack pointer */ +#define MSR_IA32_FRED_RSP2 0x1ce /* Level 2 stack pointer */ +#define MSR_IA32_FRED_RSP3 0x1cf /* Level 3 stack pointer */ +#define MSR_IA32_FRED_STKLVLS 0x1d0 /* Exception stack levels */ +#define MSR_IA32_FRED_SSP0 MSR_IA32_PL0_SSP /* Level 0 shadow stack pointer */ +#define MSR_IA32_FRED_SSP1 0x1d1 /* Level 1 shadow stack pointer */ +#define MSR_IA32_FRED_SSP2 0x1d2 /* Level 2 shadow stack pointer */ +#define MSR_IA32_FRED_SSP3 0x1d3 /* Level 3 shadow stack pointer */ +#define MSR_IA32_FRED_CONFIG 0x1d4 /* Entrypoint and interrupt stack level */ +/* Intel MSRs. Some also available on other CPUs */ #define MSR_TEST_CTRL 0x00000033 #define MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT 29 #define MSR_TEST_CTRL_SPLIT_LOCK_DETECT BIT(MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT) diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 1d51e1850ed0..74f2c63ce717 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -36,8 +36,19 @@ #define EFER_FFXSR (1<<_EFER_FFXSR) #define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS) -/* Intel MSRs. Some also available on other CPUs */ +/* FRED MSRs */ +#define MSR_IA32_FRED_RSP0 0x1cc /* Level 0 stack pointer */ +#define MSR_IA32_FRED_RSP1 0x1cd /* Level 1 stack pointer */ +#define MSR_IA32_FRED_RSP2 0x1ce /* Level 2 stack pointer */ +#define MSR_IA32_FRED_RSP3 0x1cf /* Level 3 stack pointer */ +#define MSR_IA32_FRED_STKLVLS 0x1d0 /* Exception stack levels */ +#define MSR_IA32_FRED_SSP0 MSR_IA32_PL0_SSP /* Level 0 shadow stack pointer */ +#define MSR_IA32_FRED_SSP1 0x1d1 /* Level 1 shadow stack pointer */ +#define MSR_IA32_FRED_SSP2 0x1d2 /* Level 2 shadow stack pointer */ +#define MSR_IA32_FRED_SSP3 0x1d3 /* Level 3 shadow stack pointer */ +#define MSR_IA32_FRED_CONFIG 0x1d4 /* Entrypoint and interrupt stack level */ +/* Intel MSRs. Some also available on other CPUs */ #define MSR_TEST_CTRL 0x00000033 #define MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT 29 #define MSR_TEST_CTRL_SPLIT_LOCK_DETECT BIT(MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT) -- cgit v1.2.3-70-g09d2 From 4cb1ef64609f9b0254184b2947824f4b46ccab22 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 4 Feb 2024 11:28:06 -1000 Subject: workqueue: Implement BH workqueues to eventually replace tasklets The only generic interface to execute asynchronously in the BH context is tasklet; however, it's marked deprecated and has some design flaws such as the execution code accessing the tasklet item after the execution is complete which can lead to subtle use-after-free in certain usage scenarios and less-developed flush and cancel mechanisms. This patch implements BH workqueues which share the same semantics and features of regular workqueues but execute their work items in the softirq context. As there is always only one BH execution context per CPU, none of the concurrency management mechanisms applies and a BH workqueue can be thought of as a convenience wrapper around softirq. Except for the inability to sleep while executing and lack of max_active adjustments, BH workqueues and work items should behave the same as regular workqueues and work items. Currently, the execution is hooked to tasklet[_hi]. However, the goal is to convert all tasklet users over to BH workqueues. Once the conversion is complete, tasklet can be removed and BH workqueues can directly take over the tasklet softirqs. system_bh[_highpri]_wq are added. As queue-wide flushing doesn't exist in tasklet, all existing tasklet users should be able to use the system BH workqueues without creating their own workqueues. v3: - Add missing interrupt.h include. v2: - Instead of using tasklets, hook directly into its softirq action functions - tasklet[_hi]_action(). This is slightly cheaper and closer to the eventual code structure we want to arrive at. Suggested by Lai. - Lai also pointed out several places which need NULL worker->task handling or can use clarification. Updated. Signed-off-by: Tejun Heo Suggested-by: Linus Torvalds Link: http://lkml.kernel.org/r/CAHk-=wjDW53w4-YcSmgKC5RruiRLHmJ1sXeYdp_ZgVoBw=5byA@mail.gmail.com Tested-by: Allen Pais Reviewed-by: Lai Jiangshan --- Documentation/core-api/workqueue.rst | 29 +++- include/linux/workqueue.h | 11 ++ kernel/softirq.c | 3 + kernel/workqueue.c | 291 ++++++++++++++++++++++++++++------- tools/workqueue/wq_dump.py | 11 +- 5 files changed, 285 insertions(+), 60 deletions(-) (limited to 'tools') diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst index 33c4539155d9..2d6af6c4665c 100644 --- a/Documentation/core-api/workqueue.rst +++ b/Documentation/core-api/workqueue.rst @@ -77,10 +77,12 @@ wants a function to be executed asynchronously it has to set up a work item pointing to that function and queue that work item on a workqueue. -Special purpose threads, called worker threads, execute the functions -off of the queue, one after the other. If no work is queued, the -worker threads become idle. These worker threads are managed in so -called worker-pools. +A work item can be executed in either a thread or the BH (softirq) context. + +For threaded workqueues, special purpose threads, called [k]workers, execute +the functions off of the queue, one after the other. If no work is queued, +the worker threads become idle. These worker threads are managed in +worker-pools. The cmwq design differentiates between the user-facing workqueues that subsystems and drivers queue work items on and the backend mechanism @@ -91,6 +93,12 @@ for high priority ones, for each possible CPU and some extra worker-pools to serve work items queued on unbound workqueues - the number of these backing pools is dynamic. +BH workqueues use the same framework. However, as there can only be one +concurrent execution context, there's no need to worry about concurrency. +Each per-CPU BH worker pool contains only one pseudo worker which represents +the BH execution context. A BH workqueue can be considered a convenience +interface to softirq. + Subsystems and drivers can create and queue work items through special workqueue API functions as they see fit. They can influence some aspects of the way the work items are executed by setting flags on the @@ -106,7 +114,7 @@ unless specifically overridden, a work item of a bound workqueue will be queued on the worklist of either normal or highpri worker-pool that is associated to the CPU the issuer is running on. -For any worker pool implementation, managing the concurrency level +For any thread pool implementation, managing the concurrency level (how many execution contexts are active) is an important issue. cmwq tries to keep the concurrency at a minimal but sufficient level. Minimal to save resources and sufficient in that the system is used at @@ -164,6 +172,17 @@ resources, scheduled and executed. ``flags`` --------- +``WQ_BH`` + BH workqueues can be considered a convenience interface to softirq. BH + workqueues are always per-CPU and all BH work items are executed in the + queueing CPU's softirq context in the queueing order. + + All BH workqueues must have 0 ``max_active`` and ``WQ_HIGHPRI`` is the + only allowed additional flag. + + BH work items cannot sleep. All other features such as delayed queueing, + flushing and canceling are supported. + ``WQ_UNBOUND`` Work items queued to an unbound wq are served by the special worker-pools which host workers which are not bound to any diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 232baea90a1d..283d7891b4c4 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -353,6 +353,7 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } * Documentation/core-api/workqueue.rst. */ enum wq_flags { + WQ_BH = 1 << 0, /* execute in bottom half (softirq) context */ WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ WQ_FREEZABLE = 1 << 2, /* freeze during suspend */ WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ @@ -392,6 +393,9 @@ enum wq_flags { __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */ __WQ_ORDERED_EXPLICIT = 1 << 19, /* internal: alloc_ordered_workqueue() */ + + /* BH wq only allows the following flags */ + __WQ_BH_ALLOWS = WQ_BH | WQ_HIGHPRI, }; enum wq_consts { @@ -434,6 +438,9 @@ enum wq_consts { * they are same as their non-power-efficient counterparts - e.g. * system_power_efficient_wq is identical to system_wq if * 'wq_power_efficient' is disabled. See WQ_POWER_EFFICIENT for more info. + * + * system_bh[_highpri]_wq are convenience interface to softirq. BH work items + * are executed in the queueing CPU's BH context in the queueing order. */ extern struct workqueue_struct *system_wq; extern struct workqueue_struct *system_highpri_wq; @@ -442,6 +449,10 @@ extern struct workqueue_struct *system_unbound_wq; extern struct workqueue_struct *system_freezable_wq; extern struct workqueue_struct *system_power_efficient_wq; extern struct workqueue_struct *system_freezable_power_efficient_wq; +extern struct workqueue_struct *system_bh_wq; +extern struct workqueue_struct *system_bh_highpri_wq; + +void workqueue_softirq_action(bool highpri); /** * alloc_workqueue - allocate a workqueue diff --git a/kernel/softirq.c b/kernel/softirq.c index 210cf5f8d92c..547d282548a8 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -27,6 +27,7 @@ #include #include #include +#include #include @@ -802,11 +803,13 @@ static void tasklet_action_common(struct softirq_action *a, static __latent_entropy void tasklet_action(struct softirq_action *a) { + workqueue_softirq_action(false); tasklet_action_common(a, this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ); } static __latent_entropy void tasklet_hi_action(struct softirq_action *a) { + workqueue_softirq_action(true); tasklet_action_common(a, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ); } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 767971a29c7a..78b4b992e1a3 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include #include @@ -72,8 +73,12 @@ enum worker_pool_flags { * Note that DISASSOCIATED should be flipped only while holding * wq_pool_attach_mutex to avoid changing binding state while * worker_attach_to_pool() is in progress. + * + * As there can only be one concurrent BH execution context per CPU, a + * BH pool is per-CPU and always DISASSOCIATED. */ - POOL_MANAGER_ACTIVE = 1 << 0, /* being managed */ + POOL_BH = 1 << 0, /* is a BH pool */ + POOL_MANAGER_ACTIVE = 1 << 1, /* being managed */ POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ }; @@ -115,6 +120,14 @@ enum wq_internal_consts { WQ_NAME_LEN = 32, }; +/* + * We don't want to trap softirq for too long. See MAX_SOFTIRQ_TIME and + * MAX_SOFTIRQ_RESTART in kernel/softirq.c. These are macros because + * msecs_to_jiffies() can't be an initializer. + */ +#define BH_WORKER_JIFFIES msecs_to_jiffies(2) +#define BH_WORKER_RESTARTS 10 + /* * Structure fields follow one of the following exclusion rules. * @@ -443,8 +456,13 @@ static bool wq_debug_force_rr_cpu = false; #endif module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644); +/* the BH worker pools */ +static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], + bh_worker_pools); + /* the per-cpu worker pools */ -static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], cpu_worker_pools); +static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], + cpu_worker_pools); static DEFINE_IDR(worker_pool_idr); /* PR: idr of all pools */ @@ -478,6 +496,10 @@ struct workqueue_struct *system_power_efficient_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_power_efficient_wq); struct workqueue_struct *system_freezable_power_efficient_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); +struct workqueue_struct *system_bh_wq; +EXPORT_SYMBOL_GPL(system_bh_wq); +struct workqueue_struct *system_bh_highpri_wq; +EXPORT_SYMBOL_GPL(system_bh_highpri_wq); static int worker_thread(void *__worker); static void workqueue_sysfs_unregister(struct workqueue_struct *wq); @@ -498,6 +520,11 @@ static void show_one_worker_pool(struct worker_pool *pool); !lockdep_is_held(&wq_pool_mutex), \ "RCU, wq->mutex or wq_pool_mutex should be held") +#define for_each_bh_worker_pool(pool, cpu) \ + for ((pool) = &per_cpu(bh_worker_pools, cpu)[0]; \ + (pool) < &per_cpu(bh_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ + (pool)++) + #define for_each_cpu_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ (pool) < &per_cpu(cpu_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ @@ -1186,6 +1213,14 @@ static bool kick_pool(struct worker_pool *pool) if (!need_more_worker(pool) || !worker) return false; + if (pool->flags & POOL_BH) { + if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) + raise_softirq_irqoff(HI_SOFTIRQ); + else + raise_softirq_irqoff(TASKLET_SOFTIRQ); + return true; + } + p = worker->task; #ifdef CONFIG_SMP @@ -1668,7 +1703,7 @@ static bool pwq_tryinc_nr_active(struct pool_workqueue *pwq, bool fill) lockdep_assert_held(&pool->lock); if (!nna) { - /* per-cpu workqueue, pwq->nr_active is sufficient */ + /* BH or per-cpu workqueue, pwq->nr_active is sufficient */ obtained = pwq->nr_active < READ_ONCE(wq->max_active); goto out; } @@ -2523,19 +2558,21 @@ static cpumask_t *pool_allowed_cpus(struct worker_pool *pool) * cpu-[un]hotplugs. */ static void worker_attach_to_pool(struct worker *worker, - struct worker_pool *pool) + struct worker_pool *pool) { mutex_lock(&wq_pool_attach_mutex); /* - * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains - * stable across this function. See the comments above the flag - * definition for details. + * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains stable + * across this function. See the comments above the flag definition for + * details. BH workers are, while per-CPU, always DISASSOCIATED. */ - if (pool->flags & POOL_DISASSOCIATED) + if (pool->flags & POOL_DISASSOCIATED) { worker->flags |= WORKER_UNBOUND; - else + } else { + WARN_ON_ONCE(pool->flags & POOL_BH); kthread_set_per_cpu(worker->task, pool->cpu); + } if (worker->rescue_wq) set_cpus_allowed_ptr(worker->task, pool_allowed_cpus(pool)); @@ -2559,6 +2596,9 @@ static void worker_detach_from_pool(struct worker *worker) struct worker_pool *pool = worker->pool; struct completion *detach_completion = NULL; + /* there is one permanent BH worker per CPU which should never detach */ + WARN_ON_ONCE(pool->flags & POOL_BH); + mutex_lock(&wq_pool_attach_mutex); kthread_set_per_cpu(worker->task, -1); @@ -2610,27 +2650,29 @@ static struct worker *create_worker(struct worker_pool *pool) worker->id = id; - if (pool->cpu >= 0) - snprintf(id_buf, sizeof(id_buf), "%d:%d%s", pool->cpu, id, - pool->attrs->nice < 0 ? "H" : ""); - else - snprintf(id_buf, sizeof(id_buf), "u%d:%d", pool->id, id); - - worker->task = kthread_create_on_node(worker_thread, worker, pool->node, - "kworker/%s", id_buf); - if (IS_ERR(worker->task)) { - if (PTR_ERR(worker->task) == -EINTR) { - pr_err("workqueue: Interrupted when creating a worker thread \"kworker/%s\"\n", - id_buf); - } else { - pr_err_once("workqueue: Failed to create a worker thread: %pe", - worker->task); + if (!(pool->flags & POOL_BH)) { + if (pool->cpu >= 0) + snprintf(id_buf, sizeof(id_buf), "%d:%d%s", pool->cpu, id, + pool->attrs->nice < 0 ? "H" : ""); + else + snprintf(id_buf, sizeof(id_buf), "u%d:%d", pool->id, id); + + worker->task = kthread_create_on_node(worker_thread, worker, + pool->node, "kworker/%s", id_buf); + if (IS_ERR(worker->task)) { + if (PTR_ERR(worker->task) == -EINTR) { + pr_err("workqueue: Interrupted when creating a worker thread \"kworker/%s\"\n", + id_buf); + } else { + pr_err_once("workqueue: Failed to create a worker thread: %pe", + worker->task); + } + goto fail; } - goto fail; - } - set_user_nice(worker->task, pool->attrs->nice); - kthread_bind_mask(worker->task, pool_allowed_cpus(pool)); + set_user_nice(worker->task, pool->attrs->nice); + kthread_bind_mask(worker->task, pool_allowed_cpus(pool)); + } /* successful, attach the worker to the pool */ worker_attach_to_pool(worker, pool); @@ -2646,7 +2688,8 @@ static struct worker *create_worker(struct worker_pool *pool) * check if not woken up soon. As kick_pool() is noop if @pool is empty, * wake it up explicitly. */ - wake_up_process(worker->task); + if (worker->task) + wake_up_process(worker->task); raw_spin_unlock_irq(&pool->lock); @@ -2988,7 +3031,8 @@ __acquires(&pool->lock) worker->current_work = work; worker->current_func = work->func; worker->current_pwq = pwq; - worker->current_at = worker->task->se.sum_exec_runtime; + if (worker->task) + worker->current_at = worker->task->se.sum_exec_runtime; work_data = *work_data_bits(work); worker->current_color = get_work_color(work_data); @@ -3086,7 +3130,8 @@ __acquires(&pool->lock) * stop_machine. At the same time, report a quiescent RCU state so * the same condition doesn't freeze RCU. */ - cond_resched(); + if (worker->task) + cond_resched(); raw_spin_lock_irq(&pool->lock); @@ -3369,6 +3414,61 @@ repeat: goto repeat; } +static void bh_worker(struct worker *worker) +{ + struct worker_pool *pool = worker->pool; + int nr_restarts = BH_WORKER_RESTARTS; + unsigned long end = jiffies + BH_WORKER_JIFFIES; + + raw_spin_lock_irq(&pool->lock); + worker_leave_idle(worker); + + /* + * This function follows the structure of worker_thread(). See there for + * explanations on each step. + */ + if (!need_more_worker(pool)) + goto done; + + WARN_ON_ONCE(!list_empty(&worker->scheduled)); + worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); + + do { + struct work_struct *work = + list_first_entry(&pool->worklist, + struct work_struct, entry); + + if (assign_work(work, worker, NULL)) + process_scheduled_works(worker); + } while (keep_working(pool) && + --nr_restarts && time_before(jiffies, end)); + + worker_set_flags(worker, WORKER_PREP); +done: + worker_enter_idle(worker); + kick_pool(pool); + raw_spin_unlock_irq(&pool->lock); +} + +/* + * TODO: Convert all tasklet users to workqueue and use softirq directly. + * + * This is currently called from tasklet[_hi]action() and thus is also called + * whenever there are tasklets to run. Let's do an early exit if there's nothing + * queued. Once conversion from tasklet is complete, the need_more_worker() test + * can be dropped. + * + * After full conversion, we'll add worker->softirq_action, directly use the + * softirq action and obtain the worker pointer from the softirq_action pointer. + */ +void workqueue_softirq_action(bool highpri) +{ + struct worker_pool *pool = + &per_cpu(bh_worker_pools, smp_processor_id())[highpri]; + if (need_more_worker(pool)) + bh_worker(list_first_entry(&pool->workers, struct worker, node)); +} + /** * check_flush_dependency - check for flush dependency sanity * @target_wq: workqueue being flushed @@ -3441,6 +3541,7 @@ static void insert_wq_barrier(struct pool_workqueue *pwq, struct wq_barrier *barr, struct work_struct *target, struct worker *worker) { + static __maybe_unused struct lock_class_key bh_key, thr_key; unsigned int work_flags = 0; unsigned int work_color; struct list_head *head; @@ -3450,8 +3551,13 @@ static void insert_wq_barrier(struct pool_workqueue *pwq, * as we know for sure that this will not trigger any of the * checks and call back into the fixup functions where we * might deadlock. + * + * BH and threaded workqueues need separate lockdep keys to avoid + * spuriously triggering "inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} + * usage". */ - INIT_WORK_ONSTACK(&barr->work, wq_barrier_func); + INIT_WORK_ONSTACK_KEY(&barr->work, wq_barrier_func, + (pwq->wq->flags & WQ_BH) ? &bh_key : &thr_key); __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion_map(&barr->done, &target->lockdep_map); @@ -3557,15 +3663,31 @@ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq, static void touch_wq_lockdep_map(struct workqueue_struct *wq) { +#ifdef CONFIG_LOCKDEP + if (wq->flags & WQ_BH) + local_bh_disable(); + lock_map_acquire(&wq->lockdep_map); lock_map_release(&wq->lockdep_map); + + if (wq->flags & WQ_BH) + local_bh_enable(); +#endif } static void touch_work_lockdep_map(struct work_struct *work, struct workqueue_struct *wq) { +#ifdef CONFIG_LOCKDEP + if (wq->flags & WQ_BH) + local_bh_disable(); + lock_map_acquire(&work->lockdep_map); lock_map_release(&work->lockdep_map); + + if (wq->flags & WQ_BH) + local_bh_enable(); +#endif } /** @@ -5019,10 +5141,17 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) if (!(wq->flags & WQ_UNBOUND)) { for_each_possible_cpu(cpu) { - struct pool_workqueue **pwq_p = - per_cpu_ptr(wq->cpu_pwq, cpu); - struct worker_pool *pool = - &(per_cpu_ptr(cpu_worker_pools, cpu)[highpri]); + struct pool_workqueue **pwq_p; + struct worker_pool __percpu *pools; + struct worker_pool *pool; + + if (wq->flags & WQ_BH) + pools = bh_worker_pools; + else + pools = cpu_worker_pools; + + pool = &(per_cpu_ptr(pools, cpu)[highpri]); + pwq_p = per_cpu_ptr(wq->cpu_pwq, cpu); *pwq_p = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); @@ -5197,6 +5326,13 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, size_t wq_size; int name_len; + if (flags & WQ_BH) { + if (WARN_ON_ONCE(flags & ~__WQ_BH_ALLOWS)) + return NULL; + if (WARN_ON_ONCE(max_active)) + return NULL; + } + /* * Unbound && max_active == 1 used to imply ordered, which is no longer * the case on many machines due to per-pod pools. While @@ -5234,8 +5370,16 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, pr_warn_once("workqueue: name exceeds WQ_NAME_LEN. Truncating to: %s\n", wq->name); - max_active = max_active ?: WQ_DFL_ACTIVE; - max_active = wq_clamp_max_active(max_active, flags, wq->name); + if (flags & WQ_BH) { + /* + * BH workqueues always share a single execution context per CPU + * and don't impose any max_active limit. + */ + max_active = INT_MAX; + } else { + max_active = max_active ?: WQ_DFL_ACTIVE; + max_active = wq_clamp_max_active(max_active, flags, wq->name); + } /* init wq */ wq->flags = flags; @@ -5416,6 +5560,9 @@ EXPORT_SYMBOL_GPL(destroy_workqueue); */ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) { + /* max_active doesn't mean anything for BH workqueues */ + if (WARN_ON(wq->flags & WQ_BH)) + return; /* disallow meddling with max_active for ordered workqueues */ if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) return; @@ -5617,7 +5764,24 @@ static void pr_cont_pool_info(struct worker_pool *pool) pr_cont(" cpus=%*pbl", nr_cpumask_bits, pool->attrs->cpumask); if (pool->node != NUMA_NO_NODE) pr_cont(" node=%d", pool->node); - pr_cont(" flags=0x%x nice=%d", pool->flags, pool->attrs->nice); + pr_cont(" flags=0x%x", pool->flags); + if (pool->flags & POOL_BH) + pr_cont(" bh%s", + pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); + else + pr_cont(" nice=%d", pool->attrs->nice); +} + +static void pr_cont_worker_id(struct worker *worker) +{ + struct worker_pool *pool = worker->pool; + + if (pool->flags & WQ_BH) + pr_cont("bh%s", + pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); + else + pr_cont("%d%s", task_pid_nr(worker->task), + worker->rescue_wq ? "(RESCUER)" : ""); } struct pr_cont_work_struct { @@ -5694,10 +5858,9 @@ static void show_pwq(struct pool_workqueue *pwq) if (worker->current_pwq != pwq) continue; - pr_cont("%s %d%s:%ps", comma ? "," : "", - task_pid_nr(worker->task), - worker->rescue_wq ? "(RESCUER)" : "", - worker->current_func); + pr_cont(" %s", comma ? "," : ""); + pr_cont_worker_id(worker); + pr_cont(":%ps", worker->current_func); list_for_each_entry(work, &worker->scheduled, entry) pr_cont_work(false, work, &pcws); pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); @@ -5816,8 +5979,8 @@ static void show_one_worker_pool(struct worker_pool *pool) pr_cont(" manager: %d", task_pid_nr(pool->manager->task)); list_for_each_entry(worker, &pool->idle_list, entry) { - pr_cont(" %s%d", first ? "idle: " : "", - task_pid_nr(worker->task)); + pr_cont(" %s", first ? "idle: " : ""); + pr_cont_worker_id(worker); first = false; } pr_cont("\n"); @@ -6090,13 +6253,15 @@ int workqueue_online_cpu(unsigned int cpu) mutex_lock(&wq_pool_mutex); for_each_pool(pool, pi) { - mutex_lock(&wq_pool_attach_mutex); + /* BH pools aren't affected by hotplug */ + if (pool->flags & POOL_BH) + continue; + mutex_lock(&wq_pool_attach_mutex); if (pool->cpu == cpu) rebind_workers(pool); else if (pool->cpu < 0) restore_unbound_workers_cpumask(pool, cpu); - mutex_unlock(&wq_pool_attach_mutex); } @@ -7053,7 +7218,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) /* did we stall? */ if (time_after(now, ts + thresh)) { lockup_detected = true; - if (pool->cpu >= 0) { + if (pool->cpu >= 0 && !(pool->flags & POOL_BH)) { pool->cpu_stall = true; cpu_pool_stall = true; } @@ -7218,10 +7383,16 @@ void __init workqueue_init_early(void) pt->pod_node[0] = NUMA_NO_NODE; pt->cpu_pod[0] = 0; - /* initialize CPU pools */ + /* initialize BH and CPU pools */ for_each_possible_cpu(cpu) { struct worker_pool *pool; + i = 0; + for_each_bh_worker_pool(pool, cpu) { + init_cpu_worker_pool(pool, cpu, std_nice[i++]); + pool->flags |= POOL_BH; + } + i = 0; for_each_cpu_worker_pool(pool, cpu) init_cpu_worker_pool(pool, cpu, std_nice[i++]); @@ -7257,10 +7428,14 @@ void __init workqueue_init_early(void) system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_pwr_efficient", WQ_FREEZABLE | WQ_POWER_EFFICIENT, 0); + system_bh_wq = alloc_workqueue("events_bh", WQ_BH, 0); + system_bh_highpri_wq = alloc_workqueue("events_bh_highpri", + WQ_BH | WQ_HIGHPRI, 0); BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq || !system_unbound_wq || !system_freezable_wq || !system_power_efficient_wq || - !system_freezable_power_efficient_wq); + !system_freezable_power_efficient_wq || + !system_bh_wq || !system_bh_highpri_wq); } static void __init wq_cpu_intensive_thresh_init(void) @@ -7326,9 +7501,10 @@ void __init workqueue_init(void) * up. Also, create a rescuer for workqueues that requested it. */ for_each_possible_cpu(cpu) { - for_each_cpu_worker_pool(pool, cpu) { + for_each_bh_worker_pool(pool, cpu) + pool->node = cpu_to_node(cpu); + for_each_cpu_worker_pool(pool, cpu) pool->node = cpu_to_node(cpu); - } } list_for_each_entry(wq, &workqueues, list) { @@ -7339,7 +7515,16 @@ void __init workqueue_init(void) mutex_unlock(&wq_pool_mutex); - /* create the initial workers */ + /* + * Create the initial workers. A BH pool has one pseudo worker that + * represents the shared BH execution context and thus doesn't get + * affected by hotplug events. Create the BH pseudo workers for all + * possible CPUs here. + */ + for_each_possible_cpu(cpu) + for_each_bh_worker_pool(pool, cpu) + BUG_ON(!create_worker(pool)); + for_each_online_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { pool->flags &= ~POOL_DISASSOCIATED; diff --git a/tools/workqueue/wq_dump.py b/tools/workqueue/wq_dump.py index bd381511bd9a..d29b918306b4 100644 --- a/tools/workqueue/wq_dump.py +++ b/tools/workqueue/wq_dump.py @@ -79,7 +79,9 @@ def cpumask_str(cpumask): wq_type_len = 9 def wq_type_str(wq): - if wq.flags & WQ_UNBOUND: + if wq.flags & WQ_BH: + return f'{"bh":{wq_type_len}}' + elif wq.flags & WQ_UNBOUND: if wq.flags & WQ_ORDERED: return f'{"ordered":{wq_type_len}}' else: @@ -97,6 +99,7 @@ wq_pod_types = prog['wq_pod_types'] wq_affn_dfl = prog['wq_affn_dfl'] wq_affn_names = prog['wq_affn_names'] +WQ_BH = prog['WQ_BH'] WQ_UNBOUND = prog['WQ_UNBOUND'] WQ_ORDERED = prog['__WQ_ORDERED'] WQ_MEM_RECLAIM = prog['WQ_MEM_RECLAIM'] @@ -107,6 +110,8 @@ WQ_AFFN_CACHE = prog['WQ_AFFN_CACHE'] WQ_AFFN_NUMA = prog['WQ_AFFN_NUMA'] WQ_AFFN_SYSTEM = prog['WQ_AFFN_SYSTEM'] +POOL_BH = prog['POOL_BH'] + WQ_NAME_LEN = prog['WQ_NAME_LEN'].value_() cpumask_str_len = len(cpumask_str(wq_unbound_cpumask)) @@ -151,10 +156,12 @@ for pi, pool in idr_for_each(worker_pool_idr): for pi, pool in idr_for_each(worker_pool_idr): pool = drgn.Object(prog, 'struct worker_pool', address=pool) - print(f'pool[{pi:0{max_pool_id_len}}] ref={pool.refcnt.value_():{max_ref_len}} nice={pool.attrs.nice.value_():3} ', end='') + print(f'pool[{pi:0{max_pool_id_len}}] flags=0x{pool.flags.value_():02x} ref={pool.refcnt.value_():{max_ref_len}} nice={pool.attrs.nice.value_():3} ', end='') print(f'idle/workers={pool.nr_idle.value_():3}/{pool.nr_workers.value_():3} ', end='') if pool.cpu >= 0: print(f'cpu={pool.cpu.value_():3}', end='') + if pool.flags & POOL_BH: + print(' bh', end='') else: print(f'cpus={cpumask_str(pool.attrs.cpumask)}', end='') print(f' pod_cpus={cpumask_str(pool.attrs.__pod_cpumask)}', end='') -- cgit v1.2.3-70-g09d2 From f0ece18e994144b7daa025b68ead97de26a2df1f Mon Sep 17 00:00:00 2001 From: Tycho Andersen Date: Wed, 7 Feb 2024 10:19:44 +0100 Subject: selftests: add ESRCH tests for pidfd_getfd() Ensure that pidfd_getfd() reports -ESRCH if the task is already exiting. Signed-off-by: Tycho Andersen Link: https://lore.kernel.org/r/20240206192357.81942-1-tycho@tycho.pizza Signed-off-by: Christian Brauner --- tools/testing/selftests/pidfd/pidfd_getfd_test.c | 31 +++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/testing/selftests/pidfd/pidfd_getfd_test.c b/tools/testing/selftests/pidfd/pidfd_getfd_test.c index 0930e2411dfb..cd51d547b751 100644 --- a/tools/testing/selftests/pidfd/pidfd_getfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_getfd_test.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -129,6 +130,7 @@ FIXTURE(child) * When it is closed, the child will exit. */ int sk; + bool ignore_child_result; }; FIXTURE_SETUP(child) @@ -165,10 +167,14 @@ FIXTURE_SETUP(child) FIXTURE_TEARDOWN(child) { + int ret; + EXPECT_EQ(0, close(self->pidfd)); EXPECT_EQ(0, close(self->sk)); - EXPECT_EQ(0, wait_for_pid(self->pid)); + ret = wait_for_pid(self->pid); + if (!self->ignore_child_result) + EXPECT_EQ(0, ret); } TEST_F(child, disable_ptrace) @@ -235,6 +241,29 @@ TEST(flags_set) EXPECT_EQ(errno, EINVAL); } +TEST_F(child, no_strange_EBADF) +{ + struct pollfd fds; + + self->ignore_child_result = true; + + fds.fd = self->pidfd; + fds.events = POLLIN; + + ASSERT_EQ(kill(self->pid, SIGKILL), 0); + ASSERT_EQ(poll(&fds, 1, 5000), 1); + + /* + * It used to be that pidfd_getfd() could race with the exiting thread + * between exit_files() and release_task(), and get a non-null task + * with a NULL files struct, and you'd get EBADF, which was slightly + * confusing. + */ + errno = 0; + EXPECT_EQ(sys_pidfd_getfd(self->pidfd, self->remote_fd, 0), -1); + EXPECT_EQ(errno, ESRCH); +} + #if __NR_pidfd_getfd == -1 int main(void) { -- cgit v1.2.3-70-g09d2 From cc8ff7f5c85c076297b18fb9f6d45ec5569d3d44 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:04:47 +0200 Subject: selftests/resctrl: Convert perror() to ksft_perror() or ksft_print_msg() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The resctrl selftest code contains a number of perror() calls. Some of them come with hash character and some don't. The kselftest framework provides ksft_perror() that is compatible with test output formatting so it should be used instead of adding custom hash signs. Some perror() calls are too far away from anything that sets error. For those call sites, ksft_print_msg() must be used instead. Convert perror() to ksft_perror() or ksft_print_msg(). Other related changes: - Remove hash signs - Remove trailing stops & newlines from ksft_perror() - Add terminating newlines for converted ksft_print_msg() - Use consistent capitalization - Small fixes/tweaks to typos & grammar of the messages - Extract error printing out of PARENT_EXIT() to be able to differentiate Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cache.c | 10 ++-- tools/testing/selftests/resctrl/cat_test.c | 8 +-- tools/testing/selftests/resctrl/cmt_test.c | 2 +- tools/testing/selftests/resctrl/fill_buf.c | 2 +- tools/testing/selftests/resctrl/mba_test.c | 2 +- tools/testing/selftests/resctrl/mbm_test.c | 2 +- tools/testing/selftests/resctrl/resctrl.h | 3 +- tools/testing/selftests/resctrl/resctrl_val.c | 76 +++++++++++++++------------ tools/testing/selftests/resctrl/resctrlfs.c | 42 +++++++-------- 9 files changed, 77 insertions(+), 70 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c index bcbca356d56a..992bac8c352b 100644 --- a/tools/testing/selftests/resctrl/cache.c +++ b/tools/testing/selftests/resctrl/cache.c @@ -40,7 +40,7 @@ static int perf_event_open_llc_miss(pid_t pid, int cpu_no) fd_lm = perf_event_open(&pea_llc_miss, pid, cpu_no, -1, PERF_FLAG_FD_CLOEXEC); if (fd_lm == -1) { - perror("Error opening leader"); + ksft_perror("Error opening leader"); ctrlc_handler(0, NULL, NULL); return -1; } @@ -95,7 +95,7 @@ static int get_llc_perf(unsigned long *llc_perf_miss) ret = read(fd_lm, &rf_cqm, sizeof(struct read_format)); if (ret == -1) { - perror("Could not get llc misses through perf"); + ksft_perror("Could not get llc misses through perf"); return -1; } @@ -124,12 +124,12 @@ static int get_llc_occu_resctrl(unsigned long *llc_occupancy) fp = fopen(llc_occup_path, "r"); if (!fp) { - perror("Failed to open results file"); + ksft_perror("Failed to open results file"); return errno; } if (fscanf(fp, "%lu", llc_occupancy) <= 0) { - perror("Could not get llc occupancy"); + ksft_perror("Could not get llc occupancy"); fclose(fp); return -1; @@ -159,7 +159,7 @@ static int print_results_cache(char *filename, int bm_pid, } else { fp = fopen(filename, "a"); if (!fp) { - perror("Cannot open results file"); + ksft_perror("Cannot open results file"); return errno; } diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index 224ba8544d8a..9bb8ba93f433 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -51,7 +51,7 @@ static int check_results(struct resctrl_val_param *param, size_t span) ksft_print_msg("Checking for pass/fail\n"); fp = fopen(param->filename, "r"); if (!fp) { - perror("# Cannot open file"); + ksft_perror("Cannot open file"); return errno; } @@ -149,7 +149,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) param.num_of_runs = 0; if (pipe(pipefd)) { - perror("# Unable to create pipe"); + ksft_perror("Unable to create pipe"); return errno; } @@ -185,7 +185,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) * Just print the error message. * Let while(1) run and wait for itself to be killed. */ - perror("# failed signaling parent process"); + ksft_perror("Failed signaling parent process"); close(pipefd[1]); while (1) @@ -197,7 +197,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) while (pipe_message != 1) { if (read(pipefd[0], &pipe_message, sizeof(pipe_message)) < sizeof(pipe_message)) { - perror("# failed reading from child process"); + ksft_perror("Failed reading from child process"); break; } } diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c index 50bdbce9fba9..16fc0488e0a5 100644 --- a/tools/testing/selftests/resctrl/cmt_test.c +++ b/tools/testing/selftests/resctrl/cmt_test.c @@ -37,7 +37,7 @@ static int check_results(struct resctrl_val_param *param, size_t span, int no_of ksft_print_msg("Checking for pass/fail\n"); fp = fopen(param->filename, "r"); if (!fp) { - perror("# Error in opening file\n"); + ksft_perror("Error in opening file"); return errno; } diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c index 0d425f26583a..0f6cca61ec94 100644 --- a/tools/testing/selftests/resctrl/fill_buf.c +++ b/tools/testing/selftests/resctrl/fill_buf.c @@ -115,7 +115,7 @@ static int fill_cache_read(unsigned char *buf, size_t buf_size, bool once) /* Consume read result so that reading memory is not optimized out. */ fp = fopen("/dev/null", "w"); if (!fp) { - perror("Unable to write to /dev/null"); + ksft_perror("Unable to write to /dev/null"); return -1; } fprintf(fp, "Sum: %d ", ret); diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c index d3bf4368341e..4988b93add6a 100644 --- a/tools/testing/selftests/resctrl/mba_test.c +++ b/tools/testing/selftests/resctrl/mba_test.c @@ -109,7 +109,7 @@ static int check_results(void) fp = fopen(output, "r"); if (!fp) { - perror(output); + ksft_perror(output); return errno; } diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c index 741533f2b075..045cd7818c79 100644 --- a/tools/testing/selftests/resctrl/mbm_test.c +++ b/tools/testing/selftests/resctrl/mbm_test.c @@ -59,7 +59,7 @@ static int check_results(size_t span) fp = fopen(output, "r"); if (!fp) { - perror(output); + ksft_perror(output); return errno; } diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index a33f414f6019..dd3546655657 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -37,9 +37,8 @@ #define DEFAULT_SPAN (250 * MB) -#define PARENT_EXIT(err_msg) \ +#define PARENT_EXIT() \ do { \ - perror(err_msg); \ kill(ppid, SIGKILL); \ umount_resctrlfs(); \ exit(EXIT_FAILURE); \ diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c index 88789678917b..231d2012de2b 100644 --- a/tools/testing/selftests/resctrl/resctrl_val.c +++ b/tools/testing/selftests/resctrl/resctrl_val.c @@ -156,12 +156,12 @@ static int read_from_imc_dir(char *imc_dir, int count) sprintf(imc_counter_type, "%s%s", imc_dir, "type"); fp = fopen(imc_counter_type, "r"); if (!fp) { - perror("Failed to open imc counter type file"); + ksft_perror("Failed to open iMC counter type file"); return -1; } if (fscanf(fp, "%u", &imc_counters_config[count][READ].type) <= 0) { - perror("Could not get imc type"); + ksft_perror("Could not get iMC type"); fclose(fp); return -1; @@ -175,12 +175,12 @@ static int read_from_imc_dir(char *imc_dir, int count) sprintf(imc_counter_cfg, "%s%s", imc_dir, READ_FILE_NAME); fp = fopen(imc_counter_cfg, "r"); if (!fp) { - perror("Failed to open imc config file"); + ksft_perror("Failed to open iMC config file"); return -1; } if (fscanf(fp, "%s", cas_count_cfg) <= 0) { - perror("Could not get imc cas count read"); + ksft_perror("Could not get iMC cas count read"); fclose(fp); return -1; @@ -193,12 +193,12 @@ static int read_from_imc_dir(char *imc_dir, int count) sprintf(imc_counter_cfg, "%s%s", imc_dir, WRITE_FILE_NAME); fp = fopen(imc_counter_cfg, "r"); if (!fp) { - perror("Failed to open imc config file"); + ksft_perror("Failed to open iMC config file"); return -1; } if (fscanf(fp, "%s", cas_count_cfg) <= 0) { - perror("Could not get imc cas count write"); + ksft_perror("Could not get iMC cas count write"); fclose(fp); return -1; @@ -262,12 +262,12 @@ static int num_of_imcs(void) } closedir(dp); if (count == 0) { - perror("Unable find iMC counters!\n"); + ksft_print_msg("Unable to find iMC counters\n"); return -1; } } else { - perror("Unable to open PMU directory!\n"); + ksft_perror("Unable to open PMU directory"); return -1; } @@ -339,14 +339,14 @@ static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc) if (read(r->fd, &r->return_value, sizeof(struct membw_read_format)) == -1) { - perror("Couldn't get read b/w through iMC"); + ksft_perror("Couldn't get read b/w through iMC"); return -1; } if (read(w->fd, &w->return_value, sizeof(struct membw_read_format)) == -1) { - perror("Couldn't get write bw through iMC"); + ksft_perror("Couldn't get write bw through iMC"); return -1; } @@ -416,7 +416,7 @@ static void initialize_mem_bw_resctrl(const char *ctrlgrp, const char *mongrp, int resource_id; if (get_resource_id(cpu_no, &resource_id) < 0) { - perror("Could not get resource_id"); + ksft_print_msg("Could not get resource_id\n"); return; } @@ -449,12 +449,12 @@ static int get_mem_bw_resctrl(unsigned long *mbm_total) fp = fopen(mbm_total_path, "r"); if (!fp) { - perror("Failed to open total bw file"); + ksft_perror("Failed to open total bw file"); return -1; } if (fscanf(fp, "%lu", mbm_total) <= 0) { - perror("Could not get mbm local bytes"); + ksft_perror("Could not get mbm local bytes"); fclose(fp); return -1; @@ -495,7 +495,7 @@ int signal_handler_register(void) if (sigaction(SIGINT, &sigact, NULL) || sigaction(SIGTERM, &sigact, NULL) || sigaction(SIGHUP, &sigact, NULL)) { - perror("# sigaction"); + ksft_perror("sigaction"); ret = -1; } return ret; @@ -515,7 +515,7 @@ void signal_handler_unregister(void) if (sigaction(SIGINT, &sigact, NULL) || sigaction(SIGTERM, &sigact, NULL) || sigaction(SIGHUP, &sigact, NULL)) { - perror("# sigaction"); + ksft_perror("sigaction"); } } @@ -540,14 +540,14 @@ static int print_results_bw(char *filename, int bm_pid, float bw_imc, } else { fp = fopen(filename, "a"); if (!fp) { - perror("Cannot open results file"); + ksft_perror("Cannot open results file"); return errno; } if (fprintf(fp, "Pid: %d \t Mem_BW_iMC: %f \t Mem_BW_resc: %lu \t Difference: %lu\n", bm_pid, bw_imc, bw_resc, diff) <= 0) { + ksft_print_msg("Could not log results\n"); fclose(fp); - perror("Could not log results."); return errno; } @@ -585,7 +585,7 @@ static void initialize_llc_occu_resctrl(const char *ctrlgrp, const char *mongrp, int resource_id; if (get_resource_id(cpu_no, &resource_id) < 0) { - perror("# Unable to resource_id"); + ksft_print_msg("Could not get resource_id\n"); return; } @@ -647,20 +647,24 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext) * stdio (console) */ fp = freopen("/dev/null", "w", stdout); - if (!fp) - PARENT_EXIT("Unable to direct benchmark status to /dev/null"); + if (!fp) { + ksft_perror("Unable to direct benchmark status to /dev/null"); + PARENT_EXIT(); + } if (strcmp(benchmark_cmd[0], "fill_buf") == 0) { /* Execute default fill_buf benchmark */ span = strtoul(benchmark_cmd[1], NULL, 10); memflush = atoi(benchmark_cmd[2]); operation = atoi(benchmark_cmd[3]); - if (!strcmp(benchmark_cmd[4], "true")) + if (!strcmp(benchmark_cmd[4], "true")) { once = true; - else if (!strcmp(benchmark_cmd[4], "false")) + } else if (!strcmp(benchmark_cmd[4], "false")) { once = false; - else - PARENT_EXIT("Invalid once parameter"); + } else { + ksft_print_msg("Invalid once parameter\n"); + PARENT_EXIT(); + } if (run_fill_buf(span, memflush, operation, once)) fprintf(stderr, "Error in running fill buffer\n"); @@ -668,11 +672,12 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext) /* Execute specified benchmark */ ret = execvp(benchmark_cmd[0], benchmark_cmd); if (ret) - perror("wrong\n"); + ksft_perror("execvp"); } fclose(stdout); - PARENT_EXIT("Unable to run specified benchmark"); + ksft_print_msg("Unable to run specified benchmark\n"); + PARENT_EXIT(); } /* @@ -709,7 +714,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par ppid = getpid(); if (pipe(pipefd)) { - perror("# Unable to create pipe"); + ksft_perror("Unable to create pipe"); return -1; } @@ -721,7 +726,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par fflush(stdout); bm_pid = fork(); if (bm_pid == -1) { - perror("# Unable to fork"); + ksft_perror("Unable to fork"); return -1; } @@ -738,15 +743,17 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par sigact.sa_flags = SA_SIGINFO; /* Register for "SIGUSR1" signal from parent */ - if (sigaction(SIGUSR1, &sigact, NULL)) - PARENT_EXIT("Can't register child for signal"); + if (sigaction(SIGUSR1, &sigact, NULL)) { + ksft_perror("Can't register child for signal"); + PARENT_EXIT(); + } /* Tell parent that child is ready */ close(pipefd[0]); pipe_message = 1; if (write(pipefd[1], &pipe_message, sizeof(pipe_message)) < sizeof(pipe_message)) { - perror("# failed signaling parent process"); + ksft_perror("Failed signaling parent process"); close(pipefd[1]); return -1; } @@ -755,7 +762,8 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par /* Suspend child until delivery of "SIGUSR1" from parent */ sigsuspend(&sigact.sa_mask); - PARENT_EXIT("Child is done"); + ksft_perror("Child is done"); + PARENT_EXIT(); } ksft_print_msg("Benchmark PID: %d\n", bm_pid); @@ -796,7 +804,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par while (pipe_message != 1) { if (read(pipefd[0], &pipe_message, sizeof(pipe_message)) < sizeof(pipe_message)) { - perror("# failed reading message from child process"); + ksft_perror("Failed reading message from child process"); close(pipefd[0]); goto out; } @@ -805,7 +813,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par /* Signal child to start benchmark */ if (sigqueue(bm_pid, SIGUSR1, value) == -1) { - perror("# sigqueue SIGUSR1 to child"); + ksft_perror("sigqueue SIGUSR1 to child"); ret = errno; goto out; } diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index 5ebd43683876..77023d342a12 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -20,7 +20,7 @@ static int find_resctrl_mount(char *buffer) mounts = fopen("/proc/mounts", "r"); if (!mounts) { - perror("/proc/mounts"); + ksft_perror("/proc/mounts"); return -ENXIO; } while (!feof(mounts)) { @@ -69,7 +69,7 @@ int mount_resctrlfs(void) ksft_print_msg("Mounting resctrl to \"%s\"\n", RESCTRL_PATH); ret = mount("resctrl", RESCTRL_PATH, "resctrl", 0, NULL); if (ret) - perror("# mount"); + ksft_perror("mount"); return ret; } @@ -86,7 +86,7 @@ int umount_resctrlfs(void) return ret; if (umount(mountpoint)) { - perror("# Unable to umount resctrl"); + ksft_perror("Unable to umount resctrl"); return errno; } @@ -115,12 +115,12 @@ int get_resource_id(int cpu_no, int *resource_id) fp = fopen(phys_pkg_path, "r"); if (!fp) { - perror("Failed to open physical_package_id"); + ksft_perror("Failed to open physical_package_id"); return -1; } if (fscanf(fp, "%d", resource_id) <= 0) { - perror("Could not get socket number or l3 id"); + ksft_perror("Could not get socket number or l3 id"); fclose(fp); return -1; @@ -149,7 +149,7 @@ int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size) } else if (!strcmp(cache_type, "L2")) { cache_num = 2; } else { - perror("Invalid cache level"); + ksft_print_msg("Invalid cache level\n"); return -1; } @@ -157,12 +157,12 @@ int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size) cpu_no, cache_num); fp = fopen(cache_path, "r"); if (!fp) { - perror("Failed to open cache size"); + ksft_perror("Failed to open cache size"); return -1; } if (fscanf(fp, "%s", cache_str) <= 0) { - perror("Could not get cache_size"); + ksft_perror("Could not get cache_size"); fclose(fp); return -1; @@ -214,12 +214,12 @@ int get_cbm_mask(char *cache_type, char *cbm_mask) fp = fopen(cbm_mask_path, "r"); if (!fp) { - perror("Failed to open cache level"); + ksft_perror("Failed to open cache level"); return -1; } if (fscanf(fp, "%s", cbm_mask) <= 0) { - perror("Could not get max cbm_mask"); + ksft_perror("Could not get max cbm_mask"); fclose(fp); return -1; @@ -246,12 +246,12 @@ int get_core_sibling(int cpu_no) fp = fopen(core_siblings_path, "r"); if (!fp) { - perror("Failed to open core siblings path"); + ksft_perror("Failed to open core siblings path"); return -1; } if (fscanf(fp, "%s", cpu_list_str) <= 0) { - perror("Could not get core_siblings list"); + ksft_perror("Could not get core_siblings list"); fclose(fp); return -1; @@ -286,7 +286,7 @@ int taskset_benchmark(pid_t bm_pid, int cpu_no) CPU_SET(cpu_no, &my_set); if (sched_setaffinity(bm_pid, sizeof(cpu_set_t), &my_set)) { - perror("Unable to taskset benchmark"); + ksft_perror("Unable to taskset benchmark"); return -1; } @@ -325,7 +325,7 @@ static int create_grp(const char *grp_name, char *grp, const char *parent_grp) } closedir(dp); } else { - perror("Unable to open resctrl for group"); + ksft_perror("Unable to open resctrl for group"); return -1; } @@ -333,7 +333,7 @@ static int create_grp(const char *grp_name, char *grp, const char *parent_grp) /* Requested grp doesn't exist, hence create it */ if (found_grp == 0) { if (mkdir(grp, 0) == -1) { - perror("Unable to create group"); + ksft_perror("Unable to create group"); return -1; } @@ -348,12 +348,12 @@ static int write_pid_to_tasks(char *tasks, pid_t pid) fp = fopen(tasks, "w"); if (!fp) { - perror("Failed to open tasks file"); + ksft_perror("Failed to open tasks file"); return -1; } if (fprintf(fp, "%d\n", pid) < 0) { - perror("Failed to wr pid to tasks file"); + ksft_print_msg("Failed to write pid to tasks file\n"); fclose(fp); return -1; @@ -420,7 +420,7 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp, out: ksft_print_msg("Writing benchmark parameters to resctrl FS\n"); if (ret) - perror("# writing to resctrlfs"); + ksft_print_msg("Failed writing to resctrlfs\n"); return ret; } @@ -617,7 +617,7 @@ int filter_dmesg(void) ret = pipe(pipefds); if (ret) { - perror("pipe"); + ksft_perror("pipe"); return ret; } fflush(stdout); @@ -626,13 +626,13 @@ int filter_dmesg(void) close(pipefds[0]); dup2(pipefds[1], STDOUT_FILENO); execlp("dmesg", "dmesg", NULL); - perror("executing dmesg"); + ksft_perror("Executing dmesg"); exit(1); } close(pipefds[1]); fp = fdopen(pipefds[0], "r"); if (!fp) { - perror("fdopen(pipe)"); + ksft_perror("fdopen(pipe)"); kill(pid, SIGTERM); return -1; -- cgit v1.2.3-70-g09d2 From c90fba60f274b182f8b4df0f5a5dd23a2457f4a3 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:04:48 +0200 Subject: selftests/resctrl: Return -1 instead of errno on error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A number of functions in the resctrl selftests return errno. It is problematic because errno is positive which is often counterintuitive. Also, every site returning errno prints the error message already with ksft_perror() so there is not much added value in returning the precise error code. Simply convert all places returning errno to return -1 that is typical userspace error code in case of failures. While at it, improve resctrl_val() comment to state that 0 means the test was run (either pass or fail). Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cache.c | 6 +++--- tools/testing/selftests/resctrl/cat_test.c | 4 ++-- tools/testing/selftests/resctrl/cmt_test.c | 2 +- tools/testing/selftests/resctrl/mba_test.c | 2 +- tools/testing/selftests/resctrl/mbm_test.c | 2 +- tools/testing/selftests/resctrl/resctrl_val.c | 10 +++++----- tools/testing/selftests/resctrl/resctrlfs.c | 2 +- 7 files changed, 14 insertions(+), 14 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c index 992bac8c352b..1fa4b86e1459 100644 --- a/tools/testing/selftests/resctrl/cache.c +++ b/tools/testing/selftests/resctrl/cache.c @@ -126,7 +126,7 @@ static int get_llc_occu_resctrl(unsigned long *llc_occupancy) if (!fp) { ksft_perror("Failed to open results file"); - return errno; + return -1; } if (fscanf(fp, "%lu", llc_occupancy) <= 0) { ksft_perror("Could not get llc occupancy"); @@ -146,7 +146,7 @@ static int get_llc_occu_resctrl(unsigned long *llc_occupancy) * @llc_value: perf miss value / * llc occupancy value reported by resctrl FS * - * Return: 0 on success. non-zero on failure. + * Return: 0 on success, < 0 on error. */ static int print_results_cache(char *filename, int bm_pid, unsigned long llc_value) @@ -161,7 +161,7 @@ static int print_results_cache(char *filename, int bm_pid, if (!fp) { ksft_perror("Cannot open results file"); - return errno; + return -1; } fprintf(fp, "Pid: %d \t llc_value: %lu\n", bm_pid, llc_value); fclose(fp); diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index 9bb8ba93f433..fabb56ff68d1 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -53,7 +53,7 @@ static int check_results(struct resctrl_val_param *param, size_t span) if (!fp) { ksft_perror("Cannot open file"); - return errno; + return -1; } while (fgets(temp, sizeof(temp), fp)) { @@ -150,7 +150,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) if (pipe(pipefd)) { ksft_perror("Unable to create pipe"); - return errno; + return -1; } fflush(stdout); diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c index 16fc0488e0a5..ffd302bd5c73 100644 --- a/tools/testing/selftests/resctrl/cmt_test.c +++ b/tools/testing/selftests/resctrl/cmt_test.c @@ -39,7 +39,7 @@ static int check_results(struct resctrl_val_param *param, size_t span, int no_of if (!fp) { ksft_perror("Error in opening file"); - return errno; + return -1; } while (fgets(temp, sizeof(temp), fp)) { diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c index 4988b93add6a..e907adf7cd25 100644 --- a/tools/testing/selftests/resctrl/mba_test.c +++ b/tools/testing/selftests/resctrl/mba_test.c @@ -111,7 +111,7 @@ static int check_results(void) if (!fp) { ksft_perror(output); - return errno; + return -1; } runs = 0; diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c index 045cd7818c79..721b3ecbc158 100644 --- a/tools/testing/selftests/resctrl/mbm_test.c +++ b/tools/testing/selftests/resctrl/mbm_test.c @@ -61,7 +61,7 @@ static int check_results(size_t span) if (!fp) { ksft_perror(output); - return errno; + return -1; } runs = 0; diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c index 231d2012de2b..7fd9f1010135 100644 --- a/tools/testing/selftests/resctrl/resctrl_val.c +++ b/tools/testing/selftests/resctrl/resctrl_val.c @@ -526,7 +526,7 @@ void signal_handler_unregister(void) * @bw_imc: perf imc counter value * @bw_resc: memory bandwidth value * - * Return: 0 on success. non-zero on failure. + * Return: 0 on success, < 0 on error. */ static int print_results_bw(char *filename, int bm_pid, float bw_imc, unsigned long bw_resc) @@ -542,14 +542,14 @@ static int print_results_bw(char *filename, int bm_pid, float bw_imc, if (!fp) { ksft_perror("Cannot open results file"); - return errno; + return -1; } if (fprintf(fp, "Pid: %d \t Mem_BW_iMC: %f \t Mem_BW_resc: %lu \t Difference: %lu\n", bm_pid, bw_imc, bw_resc, diff) <= 0) { ksft_print_msg("Could not log results\n"); fclose(fp); - return errno; + return -1; } fclose(fp); } @@ -686,7 +686,7 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext) * @benchmark_cmd: benchmark command and its arguments * @param: parameters passed to resctrl_val() * - * Return: 0 on success. non-zero on failure. + * Return: 0 when the test was run, < 0 on error. */ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param) { @@ -814,7 +814,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par /* Signal child to start benchmark */ if (sigqueue(bm_pid, SIGUSR1, value) == -1) { ksft_perror("sigqueue SIGUSR1 to child"); - ret = errno; + ret = -1; goto out; } diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index 77023d342a12..5fb595ed8843 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -88,7 +88,7 @@ int umount_resctrlfs(void) if (umount(mountpoint)) { ksft_perror("Unable to umount resctrl"); - return errno; + return -1; } return 0; -- cgit v1.2.3-70-g09d2 From bcd8a929a5387178d917da785896e53b0845ab37 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:04:49 +0200 Subject: selftests/resctrl: Don't use ctrlc_handler() outside signal handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit perf_event_open_llc_miss() calls ctrlc_handler() to cleanup if perf_event_open() returns an error. Those cleanups, however, are not the responsibility of perf_event_open_llc_miss() and it thus interferes unnecessarily with the usual cleanup pattern. Worse yet, ctrlc_handler() calls exit() in the end preventing the ordinary cleanup done in the calling function from executing. ctrlc_handler() should only be used as a signal handler, not during normal error handling. Remove call to ctrlc_handler() from perf_event_open_llc_miss(). As unmounting resctrlfs and test cleanup are already handled properly by error rollbacks in the calling functions, no other changes are necessary. Suggested-by: Reinette Chatre Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cache.c | 1 - 1 file changed, 1 deletion(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c index 1fa4b86e1459..6d60a2f1b3aa 100644 --- a/tools/testing/selftests/resctrl/cache.c +++ b/tools/testing/selftests/resctrl/cache.c @@ -41,7 +41,6 @@ static int perf_event_open_llc_miss(pid_t pid, int cpu_no) PERF_FLAG_FD_CLOEXEC); if (fd_lm == -1) { ksft_perror("Error opening leader"); - ctrlc_handler(0, NULL, NULL); return -1; } -- cgit v1.2.3-70-g09d2 From 348139384ba30eccd4ce4f01fcf575b08ce81b83 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:04:50 +0200 Subject: selftests/resctrl: Change function comments to say < 0 on error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A number function comments state the function return non-zero on failure but in reality they can only return 0 on success and < 0 on error. Update the comments to say < 0 on error to match the behavior. While at it, improve cat_val() comment to state that 0 means the test was run (either pass or fail). Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cache.c | 2 +- tools/testing/selftests/resctrl/resctrlfs.c | 10 +++++----- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c index 6d60a2f1b3aa..a9a0394b3d08 100644 --- a/tools/testing/selftests/resctrl/cache.c +++ b/tools/testing/selftests/resctrl/cache.c @@ -206,7 +206,7 @@ int measure_cache_vals(struct resctrl_val_param *param, int bm_pid) * @param: parameters passed to cache_val() * @span: buffer size for the benchmark * - * Return: 0 on success. non-zero on failure. + * Return: 0 when the test was run, < 0 on error. */ int cat_val(struct resctrl_val_param *param, size_t span) { diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index 5fb595ed8843..81d1e043e17a 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -56,7 +56,7 @@ static int find_resctrl_mount(char *buffer) * Mounts resctrl FS. Fails if resctrl FS is already mounted to avoid * pre-existing settings interfering with the test results. * - * Return: 0 on success, non-zero on failure + * Return: 0 on success, < 0 on error. */ int mount_resctrlfs(void) { @@ -276,7 +276,7 @@ int get_core_sibling(int cpu_no) * @bm_pid: PID that should be binded * @cpu_no: CPU number at which the PID would be binded * - * Return: 0 on success, non-zero on failure + * Return: 0 on success, < 0 on error. */ int taskset_benchmark(pid_t bm_pid, int cpu_no) { @@ -300,7 +300,7 @@ int taskset_benchmark(pid_t bm_pid, int cpu_no) * @grp: Full path and name of the group * @parent_grp: Full path and name of the parent group * - * Return: 0 on success, non-zero on failure + * Return: 0 on success, < 0 on error. */ static int create_grp(const char *grp_name, char *grp, const char *parent_grp) { @@ -376,7 +376,7 @@ static int write_pid_to_tasks(char *tasks, pid_t pid) * pid is not written, this means that pid is in con_mon grp and hence * should consult con_mon grp's mon_data directory for results. * - * Return: 0 on success, non-zero on failure + * Return: 0 on success, < 0 on error. */ int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp, char *resctrl_val) @@ -435,7 +435,7 @@ out: * Update schemata of a con_mon grp *only* if requested resctrl feature is * allocation type * - * Return: 0 on success, non-zero on failure + * Return: 0 on success, < 0 on error. */ int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val) { -- cgit v1.2.3-70-g09d2 From f8f669699977db503569465b64dc5220ab21bb41 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:04:51 +0200 Subject: selftests/resctrl: Split fill_buf to allow tests finer-grained control MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit MBM, MBA and CMT test cases call run_fill_buf() that in turn calls fill_cache() to alloc and loop indefinitely around the buffer. This binds buffer allocation and running the benchmark into a single bundle so that a selftest cannot allocate a buffer once and reuse it. CAT test doesn't want to loop around the buffer continuously and after rewrite it needs the ability to allocate the buffer separately. Split buffer allocation out of fill_cache() into alloc_buffer(). This change is part of preparation for the new CAT test that allocates a buffer and does multiple passes over the same buffer (but not in an infinite loop). Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/fill_buf.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c index 0f6cca61ec94..6d1d5eed595c 100644 --- a/tools/testing/selftests/resctrl/fill_buf.c +++ b/tools/testing/selftests/resctrl/fill_buf.c @@ -135,24 +135,34 @@ static int fill_cache_write(unsigned char *buf, size_t buf_size, bool once) return 0; } -static int fill_cache(size_t buf_size, int memflush, int op, bool once) +static unsigned char *alloc_buffer(size_t buf_size, int memflush) { unsigned char *buf; - int ret; buf = malloc_and_init_memory(buf_size); if (!buf) - return -1; + return NULL; /* Flush the memory before using to avoid "cache hot pages" effect */ if (memflush) mem_flush(buf, buf_size); + return buf; +} + +static int fill_cache(size_t buf_size, int memflush, int op, bool once) +{ + unsigned char *buf; + int ret; + + buf = alloc_buffer(buf_size, memflush); + if (!buf) + return -1; + if (op == 0) ret = fill_cache_read(buf, buf_size, once); else ret = fill_cache_write(buf, buf_size, once); - free(buf); if (ret) { @@ -160,8 +170,7 @@ static int fill_cache(size_t buf_size, int memflush, int op, bool once) return -1; } - - return 0; + return ret; } int run_fill_buf(size_t span, int memflush, int op, bool once) -- cgit v1.2.3-70-g09d2 From 24be05591fb7a2a3edd639092c045298dd57aeea Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:04:52 +0200 Subject: selftests/resctrl: Refactor fill_buf functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are unnecessary nested calls in fill_buf.c: - run_fill_buf() calls fill_cache() - alloc_buffer() calls malloc_and_init_memory() Simplify the code flow and remove those unnecessary call levels by moving the called code inside the calling function and remove the duplicated error print. Resolve the difference in run_fill_buf() and fill_cache() parameter name into 'buf_size' which is more descriptive than 'span'. Also, while moving the allocation related code, rename 'p' into 'buf' to be consistent in naming the variables. Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/fill_buf.c | 59 +++++++++--------------------- tools/testing/selftests/resctrl/resctrl.h | 2 +- 2 files changed, 18 insertions(+), 43 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c index 6d1d5eed595c..635f938b11f0 100644 --- a/tools/testing/selftests/resctrl/fill_buf.c +++ b/tools/testing/selftests/resctrl/fill_buf.c @@ -51,29 +51,6 @@ static void mem_flush(unsigned char *buf, size_t buf_size) sb(); } -static void *malloc_and_init_memory(size_t buf_size) -{ - void *p = NULL; - uint64_t *p64; - size_t s64; - int ret; - - ret = posix_memalign(&p, PAGE_SIZE, buf_size); - if (ret < 0) - return NULL; - - p64 = (uint64_t *)p; - s64 = buf_size / sizeof(uint64_t); - - while (s64 > 0) { - *p64 = (uint64_t)rand(); - p64 += (CL_SIZE / sizeof(uint64_t)); - s64 -= (CL_SIZE / sizeof(uint64_t)); - } - - return p; -} - static int fill_one_span_read(unsigned char *buf, size_t buf_size) { unsigned char *end_ptr = buf + buf_size; @@ -137,12 +114,25 @@ static int fill_cache_write(unsigned char *buf, size_t buf_size, bool once) static unsigned char *alloc_buffer(size_t buf_size, int memflush) { - unsigned char *buf; + void *buf = NULL; + uint64_t *p64; + size_t s64; + int ret; - buf = malloc_and_init_memory(buf_size); - if (!buf) + ret = posix_memalign(&buf, PAGE_SIZE, buf_size); + if (ret < 0) return NULL; + /* Initialize the buffer */ + p64 = buf; + s64 = buf_size / sizeof(uint64_t); + + while (s64 > 0) { + *p64 = (uint64_t)rand(); + p64 += (CL_SIZE / sizeof(uint64_t)); + s64 -= (CL_SIZE / sizeof(uint64_t)); + } + /* Flush the memory before using to avoid "cache hot pages" effect */ if (memflush) mem_flush(buf, buf_size); @@ -150,7 +140,7 @@ static unsigned char *alloc_buffer(size_t buf_size, int memflush) return buf; } -static int fill_cache(size_t buf_size, int memflush, int op, bool once) +int run_fill_buf(size_t buf_size, int memflush, int op, bool once) { unsigned char *buf; int ret; @@ -164,21 +154,6 @@ static int fill_cache(size_t buf_size, int memflush, int op, bool once) else ret = fill_cache_write(buf, buf_size, once); free(buf); - - if (ret) { - printf("\n Error in fill cache read/write...\n"); - return -1; - } - - return ret; -} - -int run_fill_buf(size_t span, int memflush, int op, bool once) -{ - size_t cache_size = span; - int ret; - - ret = fill_cache(cache_size, memflush, op, once); if (ret) { printf("\n Error in fill cache\n"); return -1; diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index dd3546655657..a848e9c75578 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -91,7 +91,7 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp, char *resctrl_val); int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu, int group_fd, unsigned long flags); -int run_fill_buf(size_t span, int memflush, int op, bool once); +int run_fill_buf(size_t buf_size, int memflush, int op, bool once); int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param); int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd); void tests_cleanup(void); -- cgit v1.2.3-70-g09d2 From 4b357e2a6d6c364a88d50526675fe596a30766cb Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:04:53 +0200 Subject: selftests/resctrl: Refactor get_cbm_mask() and rename to get_full_cbm() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Callers of get_cbm_mask() are required to pass a string into which the capacity bitmask (CBM) is read. Neither CAT nor CMT tests need the bitmask as string but just convert it into an unsigned long value. Another limitation is that the bit mask reader can only read .../cbm_mask files. Generalize the bit mask reading function into get_bit_mask() such that it can be used to handle other files besides the .../cbm_mask and handles the unsigned long conversion within get_bit_mask() using fscanf(). Change get_cbm_mask() to use get_bit_mask() and rename it to get_full_cbm() to better indicate what the function does. Return error from get_full_cbm() if the bitmask is zero for some reason because it makes the code more robust as the selftests naturally assume the bitmask has some bits. Also mark cache_type const while at it and remove useless comments that are related to processing of CBM bits. Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cat_test.c | 7 +--- tools/testing/selftests/resctrl/cmt_test.c | 5 +-- tools/testing/selftests/resctrl/resctrl.h | 2 +- tools/testing/selftests/resctrl/resctrlfs.c | 51 +++++++++++++++++++++-------- 4 files changed, 41 insertions(+), 24 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index fabb56ff68d1..242c4c6200aa 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -93,25 +93,20 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) int ret, pipefd[2], sibling_cpu_no; unsigned long cache_size = 0; unsigned long long_mask; - char cbm_mask[256]; int count_of_bits; char pipe_message; size_t span; - /* Get default cbm mask for L3/L2 cache */ - ret = get_cbm_mask(cache_type, cbm_mask); + ret = get_full_cbm(cache_type, &long_mask); if (ret) return ret; - long_mask = strtoul(cbm_mask, NULL, 16); - /* Get L3/L2 cache size */ ret = get_cache_size(cpu_no, cache_type, &cache_size); if (ret) return ret; ksft_print_msg("Cache size :%lu\n", cache_size); - /* Get max number of bits from default-cabm mask */ count_of_bits = count_bits(long_mask); if (!n) diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c index ffd302bd5c73..a18c6825802c 100644 --- a/tools/testing/selftests/resctrl/cmt_test.c +++ b/tools/testing/selftests/resctrl/cmt_test.c @@ -75,17 +75,14 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd) unsigned long cache_size = 0; unsigned long long_mask; char *span_str = NULL; - char cbm_mask[256]; int count_of_bits; size_t span; int ret, i; - ret = get_cbm_mask("L3", cbm_mask); + ret = get_full_cbm("L3", &long_mask); if (ret) return ret; - long_mask = strtoul(cbm_mask, NULL, 16); - ret = get_cache_size(cpu_no, "L3", &cache_size); if (ret) return ret; diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index a848e9c75578..89cd89507891 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -98,7 +98,7 @@ void tests_cleanup(void); void mbm_test_cleanup(void); int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd); void mba_test_cleanup(void); -int get_cbm_mask(char *cache_type, char *cbm_mask); +int get_full_cbm(const char *cache_type, unsigned long *mask); int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size); void ctrlc_handler(int signum, siginfo_t *info, void *ptr); int signal_handler_register(void); diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index 81d1e043e17a..a74be17eaa4e 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -196,30 +196,29 @@ int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size) #define CORE_SIBLINGS_PATH "/sys/bus/cpu/devices/cpu" /* - * get_cbm_mask - Get cbm mask for given cache - * @cache_type: Cache level L2/L3 - * @cbm_mask: cbm_mask returned as a string + * get_bit_mask - Get bit mask from given file + * @filename: File containing the mask + * @mask: The bit mask returned as unsigned long * * Return: = 0 on success, < 0 on failure. */ -int get_cbm_mask(char *cache_type, char *cbm_mask) +static int get_bit_mask(const char *filename, unsigned long *mask) { - char cbm_mask_path[1024]; FILE *fp; - if (!cbm_mask) + if (!filename || !mask) return -1; - sprintf(cbm_mask_path, "%s/%s/cbm_mask", INFO_PATH, cache_type); - - fp = fopen(cbm_mask_path, "r"); + fp = fopen(filename, "r"); if (!fp) { - ksft_perror("Failed to open cache level"); - + ksft_print_msg("Failed to open bit mask file '%s': %s\n", + filename, strerror(errno)); return -1; } - if (fscanf(fp, "%s", cbm_mask) <= 0) { - ksft_perror("Could not get max cbm_mask"); + + if (fscanf(fp, "%lx", mask) <= 0) { + ksft_print_msg("Could not read bit mask file '%s': %s\n", + filename, strerror(errno)); fclose(fp); return -1; @@ -229,6 +228,32 @@ int get_cbm_mask(char *cache_type, char *cbm_mask) return 0; } +/* + * get_full_cbm - Get full Cache Bit Mask (CBM) + * @cache_type: Cache type as "L2" or "L3" + * @mask: Full cache bit mask representing the maximal portion of cache + * available for allocation, returned as unsigned long. + * + * Return: = 0 on success, < 0 on failure. + */ +int get_full_cbm(const char *cache_type, unsigned long *mask) +{ + char cbm_path[PATH_MAX]; + int ret; + + if (!cache_type) + return -1; + + snprintf(cbm_path, sizeof(cbm_path), "%s/%s/cbm_mask", + INFO_PATH, cache_type); + + ret = get_bit_mask(cbm_path, mask); + if (ret || !*mask) + return -1; + + return 0; +} + /* * get_core_sibling - Get sibling core id from the same socket for given CPU * @cpu_no: CPU number -- cgit v1.2.3-70-g09d2 From 60c2a6926cc94dcd8a60ab593b4092bc354061c3 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:04:54 +0200 Subject: selftests/resctrl: Mark get_cache_size() cache_type const MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit get_cache_size() does not modify cache_type so it could be const. Mark cache_type const so that const char * can be passed to it. This prevents warnings once many of the test parameters are marked const. Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/resctrl.h | 2 +- tools/testing/selftests/resctrl/resctrlfs.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 89cd89507891..9e5777e1eee3 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -99,7 +99,7 @@ void mbm_test_cleanup(void); int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd); void mba_test_cleanup(void); int get_full_cbm(const char *cache_type, unsigned long *mask); -int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size); +int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size); void ctrlc_handler(int signum, siginfo_t *info, void *ptr); int signal_handler_register(void); void signal_handler_unregister(void); diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index a74be17eaa4e..1bbeb4dccf05 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -138,7 +138,7 @@ int get_resource_id(int cpu_no, int *resource_id) * * Return: = 0 on success, < 0 on failure. */ -int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size) +int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size) { char cache_path[1024], cache_str[64]; int length, i, cache_num; -- cgit v1.2.3-70-g09d2 From 19e94a2333c2babc773e51a9ed844cfc35a36064 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:04:55 +0200 Subject: selftests/resctrl: Create cache_portion_size() helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit CAT and CMT tests calculate size of the cache portion for the n-bits cache allocation on their own. Add cache_portion_size() helper that calculates size of the cache portion for the given number of bits and use it to replace the existing span calculations. This also prepares for the new CAT test that will need to determine the size of the cache portion also during results processing. Rename also 'cache_size' local variables to 'cache_total_size' to prevent misinterpretations. Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cat_test.c | 10 +++++----- tools/testing/selftests/resctrl/cmt_test.c | 8 ++++---- tools/testing/selftests/resctrl/resctrl.h | 24 ++++++++++++++++++++++++ 3 files changed, 33 insertions(+), 9 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index 242c4c6200aa..f18c95dda5d3 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -91,7 +91,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) { unsigned long l_mask, l_mask_1; int ret, pipefd[2], sibling_cpu_no; - unsigned long cache_size = 0; + unsigned long cache_total_size = 0; unsigned long long_mask; int count_of_bits; char pipe_message; @@ -102,10 +102,10 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) return ret; /* Get L3/L2 cache size */ - ret = get_cache_size(cpu_no, cache_type, &cache_size); + ret = get_cache_size(cpu_no, cache_type, &cache_total_size); if (ret) return ret; - ksft_print_msg("Cache size :%lu\n", cache_size); + ksft_print_msg("Cache size :%lu\n", cache_total_size); count_of_bits = count_bits(long_mask); @@ -136,7 +136,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) /* Set param values for parent thread which will be allocated bitmask * with (max_bits - n) bits */ - span = cache_size * (count_of_bits - n) / count_of_bits; + span = cache_portion_size(cache_total_size, l_mask, long_mask); strcpy(param.ctrlgrp, "c2"); strcpy(param.mongrp, "m2"); strcpy(param.filename, RESULT_FILE_NAME2); @@ -158,7 +158,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) param.mask = l_mask_1; strcpy(param.ctrlgrp, "c1"); strcpy(param.mongrp, "m1"); - span = cache_size * n / count_of_bits; + span = cache_portion_size(cache_total_size, l_mask_1, long_mask); strcpy(param.filename, RESULT_FILE_NAME1); param.num_of_runs = 0; param.cpu_no = sibling_cpu_no; diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c index a18c6825802c..a14d46353865 100644 --- a/tools/testing/selftests/resctrl/cmt_test.c +++ b/tools/testing/selftests/resctrl/cmt_test.c @@ -72,7 +72,7 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd) { const char * const *cmd = benchmark_cmd; const char *new_cmd[BENCHMARK_ARGS]; - unsigned long cache_size = 0; + unsigned long cache_total_size = 0; unsigned long long_mask; char *span_str = NULL; int count_of_bits; @@ -83,10 +83,10 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd) if (ret) return ret; - ret = get_cache_size(cpu_no, "L3", &cache_size); + ret = get_cache_size(cpu_no, "L3", &cache_total_size); if (ret) return ret; - ksft_print_msg("Cache size :%lu\n", cache_size); + ksft_print_msg("Cache size :%lu\n", cache_total_size); count_of_bits = count_bits(long_mask); @@ -107,7 +107,7 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd) .setup = cmt_setup, }; - span = cache_size * n / count_of_bits; + span = cache_portion_size(cache_total_size, param.mask, long_mask); if (strcmp(cmd[0], "fill_buf") == 0) { /* Duplicate the command to be able to replace span in it */ diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 9e5777e1eee3..08647f2c07f5 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -116,4 +116,28 @@ int show_cache_info(unsigned long sum_llc_val, int no_of_bits, unsigned long max_diff_percent, unsigned long num_of_runs, bool platform, bool cmt); +/* + * cache_portion_size - Calculate the size of a cache portion + * @cache_size: Total cache size in bytes + * @portion_mask: Cache portion mask + * @full_cache_mask: Full Cache Bit Mask (CBM) for the cache + * + * Return: The size of the cache portion in bytes. + */ +static inline unsigned long cache_portion_size(unsigned long cache_size, + unsigned long portion_mask, + unsigned long full_cache_mask) +{ + unsigned int bits = count_bits(full_cache_mask); + + /* + * With no bits the full CBM, assume cache cannot be split into + * smaller portions. To avoid divide by zero, return cache_size. + */ + if (!bits) + return cache_size; + + return cache_size * count_bits(portion_mask) / bits; +} + #endif /* RESCTRL_H */ -- cgit v1.2.3-70-g09d2 From b6dfac948686799169c899557a179b84d0d1f47e Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:04:56 +0200 Subject: selftests/resctrl: Exclude shareable bits from schemata in CAT test MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit CAT test doesn't take shareable bits into account, i.e., the test might be sharing cache with some devices (e.g., graphics). Introduce get_mask_no_shareable() and use it to provision an environment for CAT test where the allocated LLC is isolated better. Excluding shareable_bits may create hole(s) into the cbm_mask, thus add a new helper count_contiguous_bits() to find the longest contiguous set of CBM bits. create_bit_mask() is needed by an upcoming CAT test rewrite so make it available in resctrl.h right away. Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cat_test.c | 12 ++-- tools/testing/selftests/resctrl/resctrl.h | 2 + tools/testing/selftests/resctrl/resctrlfs.c | 89 +++++++++++++++++++++++++++++ 3 files changed, 99 insertions(+), 4 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index f18c95dda5d3..1e3c5432ecff 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -89,15 +89,19 @@ void cat_test_cleanup(void) int cat_perf_miss_val(int cpu_no, int n, char *cache_type) { + unsigned long full_cache_mask, long_mask; unsigned long l_mask, l_mask_1; int ret, pipefd[2], sibling_cpu_no; unsigned long cache_total_size = 0; - unsigned long long_mask; int count_of_bits; char pipe_message; size_t span; - ret = get_full_cbm(cache_type, &long_mask); + ret = get_full_cbm(cache_type, &full_cache_mask); + if (ret) + return ret; + /* Get the largest contiguous exclusive portion of the cache */ + ret = get_mask_no_shareable(cache_type, &long_mask); if (ret) return ret; @@ -136,7 +140,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) /* Set param values for parent thread which will be allocated bitmask * with (max_bits - n) bits */ - span = cache_portion_size(cache_total_size, l_mask, long_mask); + span = cache_portion_size(cache_total_size, l_mask, full_cache_mask); strcpy(param.ctrlgrp, "c2"); strcpy(param.mongrp, "m2"); strcpy(param.filename, RESULT_FILE_NAME2); @@ -158,7 +162,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) param.mask = l_mask_1; strcpy(param.ctrlgrp, "c1"); strcpy(param.mongrp, "m1"); - span = cache_portion_size(cache_total_size, l_mask_1, long_mask); + span = cache_portion_size(cache_total_size, l_mask_1, full_cache_mask); strcpy(param.filename, RESULT_FILE_NAME1); param.num_of_runs = 0; param.cpu_no = sibling_cpu_no; diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 08647f2c07f5..72381b51cf5f 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -98,7 +98,9 @@ void tests_cleanup(void); void mbm_test_cleanup(void); int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd); void mba_test_cleanup(void); +unsigned long create_bit_mask(unsigned int start, unsigned int len); int get_full_cbm(const char *cache_type, unsigned long *mask); +int get_mask_no_shareable(const char *cache_type, unsigned long *mask); int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size); void ctrlc_handler(int signum, siginfo_t *info, void *ptr); int signal_handler_register(void); diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index 1bbeb4dccf05..3ec09688cfc3 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -228,6 +228,44 @@ static int get_bit_mask(const char *filename, unsigned long *mask) return 0; } +/* + * create_bit_mask- Create bit mask from start, len pair + * @start: LSB of the mask + * @len Number of bits in the mask + */ +unsigned long create_bit_mask(unsigned int start, unsigned int len) +{ + return ((1UL << len) - 1UL) << start; +} + +/* + * count_contiguous_bits - Returns the longest train of bits in a bit mask + * @val A bit mask + * @start The location of the least-significant bit of the longest train + * + * Return: The length of the contiguous bits in the longest train of bits + */ +static unsigned int count_contiguous_bits(unsigned long val, unsigned int *start) +{ + unsigned long last_val; + unsigned int count = 0; + + while (val) { + last_val = val; + val &= (val >> 1); + count++; + } + + if (start) { + if (count) + *start = ffsl(last_val) - 1; + else + *start = 0; + } + + return count; +} + /* * get_full_cbm - Get full Cache Bit Mask (CBM) * @cache_type: Cache type as "L2" or "L3" @@ -254,6 +292,57 @@ int get_full_cbm(const char *cache_type, unsigned long *mask) return 0; } +/* + * get_shareable_mask - Get shareable mask from shareable_bits + * @cache_type: Cache type as "L2" or "L3" + * @shareable_mask: Shareable mask returned as unsigned long + * + * Return: = 0 on success, < 0 on failure. + */ +static int get_shareable_mask(const char *cache_type, unsigned long *shareable_mask) +{ + char mask_path[PATH_MAX]; + + if (!cache_type) + return -1; + + snprintf(mask_path, sizeof(mask_path), "%s/%s/shareable_bits", + INFO_PATH, cache_type); + + return get_bit_mask(mask_path, shareable_mask); +} + +/* + * get_mask_no_shareable - Get Cache Bit Mask (CBM) without shareable bits + * @cache_type: Cache type as "L2" or "L3" + * @mask: The largest exclusive portion of the cache out of the + * full CBM, returned as unsigned long + * + * Parts of a cache may be shared with other devices such as GPU. This function + * calculates the largest exclusive portion of the cache where no other devices + * besides CPU have access to the cache portion. + * + * Return: = 0 on success, < 0 on failure. + */ +int get_mask_no_shareable(const char *cache_type, unsigned long *mask) +{ + unsigned long full_mask, shareable_mask; + unsigned int start, len; + + if (get_full_cbm(cache_type, &full_mask) < 0) + return -1; + if (get_shareable_mask(cache_type, &shareable_mask) < 0) + return -1; + + len = count_contiguous_bits(full_mask & ~shareable_mask, &start); + if (!len) + return -1; + + *mask = create_bit_mask(start, len); + + return 0; +} + /* * get_core_sibling - Get sibling core id from the same socket for given CPU * @cpu_no: CPU number -- cgit v1.2.3-70-g09d2 From a575c9734f3021f1fc81c2477ecaee4d9841fd59 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:04:57 +0200 Subject: selftests/resctrl: Split measure_cache_vals() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit measure_cache_vals() does a different thing depending on the test case that called it: - For CAT, it measures LLC misses through perf. - For CMT, it measures LLC occupancy through resctrl. Split these two functionalities into own functions the CAT and CMT tests can call directly. Replace passing the struct resctrl_val_param parameter with the filename because it's more generic and all those functions need out of resctrl_val. Co-developed-by: Fenghua Yu Signed-off-by: Fenghua Yu Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cache.c | 64 ++++++++++++++++----------- tools/testing/selftests/resctrl/resctrl.h | 2 +- tools/testing/selftests/resctrl/resctrl_val.c | 2 +- 3 files changed, 41 insertions(+), 27 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c index a9a0394b3d08..0c18603435c8 100644 --- a/tools/testing/selftests/resctrl/cache.c +++ b/tools/testing/selftests/resctrl/cache.c @@ -147,7 +147,7 @@ static int get_llc_occu_resctrl(unsigned long *llc_occupancy) * * Return: 0 on success, < 0 on error. */ -static int print_results_cache(char *filename, int bm_pid, +static int print_results_cache(const char *filename, int bm_pid, unsigned long llc_value) { FILE *fp; @@ -169,35 +169,49 @@ static int print_results_cache(char *filename, int bm_pid, return 0; } -int measure_cache_vals(struct resctrl_val_param *param, int bm_pid) +/* + * perf_event_measure - Measure perf events + * @filename: Filename for writing the results + * @bm_pid: PID that runs the benchmark + * + * Measures perf events (e.g., cache misses) and writes the results into + * @filename. @bm_pid is written to the results file along with the measured + * value. + * + * Return: =0 on success. <0 on failure. + */ +static int perf_event_measure(const char *filename, int bm_pid) { - unsigned long llc_perf_miss = 0, llc_occu_resc = 0, llc_value = 0; + unsigned long llc_perf_miss = 0; int ret; - /* - * Measure cache miss from perf. - */ - if (!strncmp(param->resctrl_val, CAT_STR, sizeof(CAT_STR))) { - ret = get_llc_perf(&llc_perf_miss); - if (ret < 0) - return ret; - llc_value = llc_perf_miss; - } + ret = get_llc_perf(&llc_perf_miss); + if (ret < 0) + return ret; - /* - * Measure llc occupancy from resctrl. - */ - if (!strncmp(param->resctrl_val, CMT_STR, sizeof(CMT_STR))) { - ret = get_llc_occu_resctrl(&llc_occu_resc); - if (ret < 0) - return ret; - llc_value = llc_occu_resc; - } - ret = print_results_cache(param->filename, bm_pid, llc_value); - if (ret) + return print_results_cache(filename, bm_pid, llc_perf_miss); +} + +/* + * measure_llc_resctrl - Measure resctrl LLC value from resctrl + * @filename: Filename for writing the results + * @bm_pid: PID that runs the benchmark + * + * Measures LLC occupancy from resctrl and writes the results into @filename. + * @bm_pid is written to the results file along with the measured value. + * + * Return: =0 on success. <0 on failure. + */ +int measure_llc_resctrl(const char *filename, int bm_pid) +{ + unsigned long llc_occu_resc = 0; + int ret; + + ret = get_llc_occu_resctrl(&llc_occu_resc); + if (ret < 0) return ret; - return 0; + return print_results_cache(filename, bm_pid, llc_occu_resc); } /* @@ -252,7 +266,7 @@ int cat_val(struct resctrl_val_param *param, size_t span) } sleep(1); - ret = measure_cache_vals(param, bm_pid); + ret = perf_event_measure(param->filename, bm_pid); if (ret) goto pe_close; } diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 72381b51cf5f..3983226065f3 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -112,7 +112,7 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd); unsigned int count_bits(unsigned long n); void cmt_test_cleanup(void); int get_core_sibling(int cpu_no); -int measure_cache_vals(struct resctrl_val_param *param, int bm_pid); +int measure_llc_resctrl(const char *filename, int bm_pid); int show_cache_info(unsigned long sum_llc_val, int no_of_bits, size_t cache_span, unsigned long max_diff, unsigned long max_diff_percent, unsigned long num_of_runs, diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c index 7fd9f1010135..f6859fe433d9 100644 --- a/tools/testing/selftests/resctrl/resctrl_val.c +++ b/tools/testing/selftests/resctrl/resctrl_val.c @@ -838,7 +838,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par break; } else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) { sleep(1); - ret = measure_cache_vals(param, bm_pid); + ret = measure_llc_resctrl(param->filename, bm_pid); if (ret) break; } -- cgit v1.2.3-70-g09d2 From 5caf1b6400d30a31363063314bddea4e5680d639 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:04:58 +0200 Subject: selftests/resctrl: Split show_cache_info() to test specific and generic parts MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit show_cache_info() calculates results and provides generic cache information. This makes it hard to alter pass/fail conditions. Separate the test specific checks into CAT and CMT test files and leave only the generic information part into show_cache_info(). Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cache.c | 42 ++++++------------------------ tools/testing/selftests/resctrl/cat_test.c | 30 ++++++++++++++++++--- tools/testing/selftests/resctrl/cmt_test.c | 32 ++++++++++++++++++++--- tools/testing/selftests/resctrl/resctrl.h | 6 ++--- 4 files changed, 66 insertions(+), 44 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c index 0c18603435c8..32e262fa2a6c 100644 --- a/tools/testing/selftests/resctrl/cache.c +++ b/tools/testing/selftests/resctrl/cache.c @@ -279,43 +279,17 @@ pe_close: } /* - * show_cache_info: show cache test result information - * @sum_llc_val: sum of LLC cache result data - * @no_of_bits: number of bits - * @cache_span: cache span in bytes for CMT or in lines for CAT - * @max_diff: max difference - * @max_diff_percent: max difference percentage - * @num_of_runs: number of runs - * @platform: show test information on this platform - * @cmt: CMT test or CAT test - * - * Return: 0 on success. non-zero on failure. + * show_cache_info - Show generic cache test information + * @no_of_bits: Number of bits + * @avg_llc_val: Average of LLC cache result data + * @cache_span: Cache span + * @lines: @cache_span in lines or bytes */ -int show_cache_info(unsigned long sum_llc_val, int no_of_bits, - size_t cache_span, unsigned long max_diff, - unsigned long max_diff_percent, unsigned long num_of_runs, - bool platform, bool cmt) +void show_cache_info(int no_of_bits, unsigned long avg_llc_val, + size_t cache_span, bool lines) { - unsigned long avg_llc_val = 0; - float diff_percent; - long avg_diff = 0; - int ret; - - avg_llc_val = sum_llc_val / num_of_runs; - avg_diff = (long)abs(cache_span - avg_llc_val); - diff_percent = ((float)cache_span - avg_llc_val) / cache_span * 100; - - ret = platform && abs((int)diff_percent) > max_diff_percent && - (cmt ? (abs(avg_diff) > max_diff) : true); - - ksft_print_msg("%s Check cache miss rate within %lu%%\n", - ret ? "Fail:" : "Pass:", max_diff_percent); - - ksft_print_msg("Percent diff=%d\n", abs((int)diff_percent)); ksft_print_msg("Number of bits: %d\n", no_of_bits); ksft_print_msg("Average LLC val: %lu\n", avg_llc_val); - ksft_print_msg("Cache span (%s): %zu\n", cmt ? "bytes" : "lines", + ksft_print_msg("Cache span (%s): %zu\n", lines ? "lines" : "bytes", cache_span); - - return ret; } diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index 1e3c5432ecff..0955f819bd83 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -41,6 +41,30 @@ static int cat_setup(struct resctrl_val_param *p) return ret; } +static int show_results_info(unsigned long sum_llc_val, int no_of_bits, + unsigned long cache_span, unsigned long max_diff, + unsigned long max_diff_percent, unsigned long num_of_runs, + bool platform) +{ + unsigned long avg_llc_val = 0; + float diff_percent; + int ret; + + avg_llc_val = sum_llc_val / num_of_runs; + diff_percent = ((float)cache_span - avg_llc_val) / cache_span * 100; + + ret = platform && abs((int)diff_percent) > max_diff_percent; + + ksft_print_msg("%s Check cache miss rate within %lu%%\n", + ret ? "Fail:" : "Pass:", max_diff_percent); + + ksft_print_msg("Percent diff=%d\n", abs((int)diff_percent)); + + show_cache_info(no_of_bits, avg_llc_val, cache_span, true); + + return ret; +} + static int check_results(struct resctrl_val_param *param, size_t span) { char *token_array[8], temp[512]; @@ -76,9 +100,9 @@ static int check_results(struct resctrl_val_param *param, size_t span) fclose(fp); no_of_bits = count_bits(param->mask); - return show_cache_info(sum_llc_perf_miss, no_of_bits, span / 64, - MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, - get_vendor() == ARCH_INTEL, false); + return show_results_info(sum_llc_perf_miss, no_of_bits, span / 64, + MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, + get_vendor() == ARCH_INTEL); } void cat_test_cleanup(void) diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c index a14d46353865..604690cd8b3e 100644 --- a/tools/testing/selftests/resctrl/cmt_test.c +++ b/tools/testing/selftests/resctrl/cmt_test.c @@ -27,6 +27,33 @@ static int cmt_setup(struct resctrl_val_param *p) return 0; } +static int show_results_info(unsigned long sum_llc_val, int no_of_bits, + unsigned long cache_span, unsigned long max_diff, + unsigned long max_diff_percent, unsigned long num_of_runs, + bool platform) +{ + unsigned long avg_llc_val = 0; + float diff_percent; + long avg_diff = 0; + int ret; + + avg_llc_val = sum_llc_val / num_of_runs; + avg_diff = (long)abs(cache_span - avg_llc_val); + diff_percent = ((float)cache_span - avg_llc_val) / cache_span * 100; + + ret = platform && abs((int)diff_percent) > max_diff_percent && + abs(avg_diff) > max_diff; + + ksft_print_msg("%s Check cache miss rate within %lu%%\n", + ret ? "Fail:" : "Pass:", max_diff_percent); + + ksft_print_msg("Percent diff=%d\n", abs((int)diff_percent)); + + show_cache_info(no_of_bits, avg_llc_val, cache_span, false); + + return ret; +} + static int check_results(struct resctrl_val_param *param, size_t span, int no_of_bits) { char *token_array[8], temp[512]; @@ -58,9 +85,8 @@ static int check_results(struct resctrl_val_param *param, size_t span, int no_of } fclose(fp); - return show_cache_info(sum_llc_occu_resc, no_of_bits, span, - MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, - true, true); + return show_results_info(sum_llc_occu_resc, no_of_bits, span, + MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, true); } void cmt_test_cleanup(void) diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 3983226065f3..47b871df2b0e 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -113,10 +113,8 @@ unsigned int count_bits(unsigned long n); void cmt_test_cleanup(void); int get_core_sibling(int cpu_no); int measure_llc_resctrl(const char *filename, int bm_pid); -int show_cache_info(unsigned long sum_llc_val, int no_of_bits, - size_t cache_span, unsigned long max_diff, - unsigned long max_diff_percent, unsigned long num_of_runs, - bool platform, bool cmt); +void show_cache_info(int no_of_bits, unsigned long avg_llc_val, + size_t cache_span, bool lines); /* * cache_portion_size - Calculate the size of a cache portion -- cgit v1.2.3-70-g09d2 From 33403bc7fe2ec35cd87e4f11db4d1a1da1e5ce12 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:04:59 +0200 Subject: selftests/resctrl: Remove unnecessary __u64 -> unsigned long conversion MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Perf counters are __u64 but the code converts them to unsigned long before printing them out. Remove unnecessary type conversion and retain the perf originating value as __u64. Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cache.c | 21 ++++++++------------- tools/testing/selftests/resctrl/cat_test.c | 8 ++++---- tools/testing/selftests/resctrl/resctrl.h | 3 +-- 3 files changed, 13 insertions(+), 19 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c index 32e262fa2a6c..11d1a6ce14c2 100644 --- a/tools/testing/selftests/resctrl/cache.c +++ b/tools/testing/selftests/resctrl/cache.c @@ -83,9 +83,8 @@ static int reset_enable_llc_perf(pid_t pid, int cpu_no) * * Return: =0 on success. <0 on failure. */ -static int get_llc_perf(unsigned long *llc_perf_miss) +static int get_llc_perf(__u64 *llc_perf_miss) { - __u64 total_misses; int ret; /* Stop counters after one span to get miss rate */ @@ -98,8 +97,7 @@ static int get_llc_perf(unsigned long *llc_perf_miss) return -1; } - total_misses = rf_cqm.values[0].value; - *llc_perf_miss = total_misses; + *llc_perf_miss = rf_cqm.values[0].value; return 0; } @@ -147,14 +145,12 @@ static int get_llc_occu_resctrl(unsigned long *llc_occupancy) * * Return: 0 on success, < 0 on error. */ -static int print_results_cache(const char *filename, int bm_pid, - unsigned long llc_value) +static int print_results_cache(const char *filename, int bm_pid, __u64 llc_value) { FILE *fp; if (strcmp(filename, "stdio") == 0 || strcmp(filename, "stderr") == 0) { - printf("Pid: %d \t LLC_value: %lu\n", bm_pid, - llc_value); + printf("Pid: %d \t LLC_value: %llu\n", bm_pid, llc_value); } else { fp = fopen(filename, "a"); if (!fp) { @@ -162,7 +158,7 @@ static int print_results_cache(const char *filename, int bm_pid, return -1; } - fprintf(fp, "Pid: %d \t llc_value: %lu\n", bm_pid, llc_value); + fprintf(fp, "Pid: %d \t llc_value: %llu\n", bm_pid, llc_value); fclose(fp); } @@ -182,7 +178,7 @@ static int print_results_cache(const char *filename, int bm_pid, */ static int perf_event_measure(const char *filename, int bm_pid) { - unsigned long llc_perf_miss = 0; + __u64 llc_perf_miss = 0; int ret; ret = get_llc_perf(&llc_perf_miss); @@ -285,11 +281,10 @@ pe_close: * @cache_span: Cache span * @lines: @cache_span in lines or bytes */ -void show_cache_info(int no_of_bits, unsigned long avg_llc_val, - size_t cache_span, bool lines) +void show_cache_info(int no_of_bits, __u64 avg_llc_val, size_t cache_span, bool lines) { ksft_print_msg("Number of bits: %d\n", no_of_bits); - ksft_print_msg("Average LLC val: %lu\n", avg_llc_val); + ksft_print_msg("Average LLC val: %llu\n", avg_llc_val); ksft_print_msg("Cache span (%s): %zu\n", lines ? "lines" : "bytes", cache_span); } diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index 0955f819bd83..516eaa08e967 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -41,12 +41,12 @@ static int cat_setup(struct resctrl_val_param *p) return ret; } -static int show_results_info(unsigned long sum_llc_val, int no_of_bits, +static int show_results_info(__u64 sum_llc_val, int no_of_bits, unsigned long cache_span, unsigned long max_diff, unsigned long max_diff_percent, unsigned long num_of_runs, bool platform) { - unsigned long avg_llc_val = 0; + __u64 avg_llc_val = 0; float diff_percent; int ret; @@ -68,8 +68,8 @@ static int show_results_info(unsigned long sum_llc_val, int no_of_bits, static int check_results(struct resctrl_val_param *param, size_t span) { char *token_array[8], temp[512]; - unsigned long sum_llc_perf_miss = 0; int runs = 0, no_of_bits = 0; + __u64 sum_llc_perf_miss = 0; FILE *fp; ksft_print_msg("Checking for pass/fail\n"); @@ -93,7 +93,7 @@ static int check_results(struct resctrl_val_param *param, size_t span) * setup transition phase. */ if (runs > 0) - sum_llc_perf_miss += strtoul(token_array[3], NULL, 0); + sum_llc_perf_miss += strtoull(token_array[3], NULL, 0); runs++; } diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 47b871df2b0e..f813fcdcb5e0 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -113,8 +113,7 @@ unsigned int count_bits(unsigned long n); void cmt_test_cleanup(void); int get_core_sibling(int cpu_no); int measure_llc_resctrl(const char *filename, int bm_pid); -void show_cache_info(int no_of_bits, unsigned long avg_llc_val, - size_t cache_span, bool lines); +void show_cache_info(int no_of_bits, __u64 avg_llc_val, size_t cache_span, bool lines); /* * cache_portion_size - Calculate the size of a cache portion -- cgit v1.2.3-70-g09d2 From 3c6bfc9cc7f0e3bed76ff0a7ed5bf89059b7b0bd Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:05:00 +0200 Subject: selftests/resctrl: Remove nested calls in perf event handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Perf event handling has functions that are the sole caller of another perf event handling related function: - reset_enable_llc_perf() calls perf_event_open_llc_miss() - perf_event_measure() calls get_llc_perf() Remove the extra layer of calls to make the code easier to follow by moving the code into the calling function. Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cache.c | 64 ++++++++------------------------- 1 file changed, 14 insertions(+), 50 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c index 11d1a6ce14c2..4f846a2e5e26 100644 --- a/tools/testing/selftests/resctrl/cache.c +++ b/tools/testing/selftests/resctrl/cache.c @@ -29,24 +29,13 @@ static void initialize_perf_event_attr(void) pea_llc_miss.disabled = 1; } +/* Start counters to log values */ static void ioctl_perf_event_ioc_reset_enable(void) { ioctl(fd_lm, PERF_EVENT_IOC_RESET, 0); ioctl(fd_lm, PERF_EVENT_IOC_ENABLE, 0); } -static int perf_event_open_llc_miss(pid_t pid, int cpu_no) -{ - fd_lm = perf_event_open(&pea_llc_miss, pid, cpu_no, -1, - PERF_FLAG_FD_CLOEXEC); - if (fd_lm == -1) { - ksft_perror("Error opening leader"); - return -1; - } - - return 0; -} - static void initialize_llc_perf(void) { memset(&pea_llc_miss, 0, sizeof(struct perf_event_attr)); @@ -62,42 +51,13 @@ static void initialize_llc_perf(void) static int reset_enable_llc_perf(pid_t pid, int cpu_no) { - int ret = 0; - - ret = perf_event_open_llc_miss(pid, cpu_no); - if (ret < 0) - return ret; - - /* Start counters to log values */ - ioctl_perf_event_ioc_reset_enable(); - - return 0; -} - -/* - * get_llc_perf: llc cache miss through perf events - * @llc_perf_miss: LLC miss counter that is filled on success - * - * Perf events like HW_CACHE_MISSES could be used to validate number of - * cache lines allocated. - * - * Return: =0 on success. <0 on failure. - */ -static int get_llc_perf(__u64 *llc_perf_miss) -{ - int ret; - - /* Stop counters after one span to get miss rate */ - - ioctl(fd_lm, PERF_EVENT_IOC_DISABLE, 0); - - ret = read(fd_lm, &rf_cqm, sizeof(struct read_format)); - if (ret == -1) { - ksft_perror("Could not get llc misses through perf"); + fd_lm = perf_event_open(&pea_llc_miss, pid, cpu_no, -1, PERF_FLAG_FD_CLOEXEC); + if (fd_lm == -1) { + ksft_perror("Error opening leader"); return -1; } - *llc_perf_miss = rf_cqm.values[0].value; + ioctl_perf_event_ioc_reset_enable(); return 0; } @@ -178,14 +138,18 @@ static int print_results_cache(const char *filename, int bm_pid, __u64 llc_value */ static int perf_event_measure(const char *filename, int bm_pid) { - __u64 llc_perf_miss = 0; int ret; - ret = get_llc_perf(&llc_perf_miss); - if (ret < 0) - return ret; + /* Stop counters after one span to get miss rate */ + ioctl(fd_lm, PERF_EVENT_IOC_DISABLE, 0); + + ret = read(fd_lm, &rf_cqm, sizeof(struct read_format)); + if (ret == -1) { + ksft_perror("Could not get perf value"); + return -1; + } - return print_results_cache(filename, bm_pid, llc_perf_miss); + return print_results_cache(filename, bm_pid, rf_cqm.values[0].value); } /* -- cgit v1.2.3-70-g09d2 From b6e6a582f2b357b6f74849b715de12cc38b1ee91 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:05:01 +0200 Subject: selftests/resctrl: Consolidate naming of perf event related things MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Naming for perf event related functions, types, and variables is inconsistent. Make struct read_format and all functions related to perf events start with "perf_". Adjust variable names towards the same direction but use shorter names for variables where appropriate (pe prefix). Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cache.c | 42 ++++++++++++++++----------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c index 4f846a2e5e26..7f45c4957f81 100644 --- a/tools/testing/selftests/resctrl/cache.c +++ b/tools/testing/selftests/resctrl/cache.c @@ -3,7 +3,7 @@ #include #include "resctrl.h" -struct read_format { +struct perf_event_read { __u64 nr; /* The number of events */ struct { __u64 value; /* The value of the event */ @@ -11,11 +11,11 @@ struct read_format { }; static struct perf_event_attr pea_llc_miss; -static struct read_format rf_cqm; -static int fd_lm; +static struct perf_event_read pe_read; +static int pe_fd; char llc_occup_path[1024]; -static void initialize_perf_event_attr(void) +static void perf_event_attr_initialize(void) { pea_llc_miss.type = PERF_TYPE_HARDWARE; pea_llc_miss.size = sizeof(struct perf_event_attr); @@ -30,34 +30,34 @@ static void initialize_perf_event_attr(void) } /* Start counters to log values */ -static void ioctl_perf_event_ioc_reset_enable(void) +static void perf_event_reset_enable(void) { - ioctl(fd_lm, PERF_EVENT_IOC_RESET, 0); - ioctl(fd_lm, PERF_EVENT_IOC_ENABLE, 0); + ioctl(pe_fd, PERF_EVENT_IOC_RESET, 0); + ioctl(pe_fd, PERF_EVENT_IOC_ENABLE, 0); } -static void initialize_llc_perf(void) +static void perf_event_initialize(void) { memset(&pea_llc_miss, 0, sizeof(struct perf_event_attr)); - memset(&rf_cqm, 0, sizeof(struct read_format)); + memset(&pe_read, 0, sizeof(struct perf_event_read)); /* Initialize perf_event_attr structures for HW_CACHE_MISSES */ - initialize_perf_event_attr(); + perf_event_attr_initialize(); pea_llc_miss.config = PERF_COUNT_HW_CACHE_MISSES; - rf_cqm.nr = 1; + pe_read.nr = 1; } -static int reset_enable_llc_perf(pid_t pid, int cpu_no) +static int perf_open(pid_t pid, int cpu_no) { - fd_lm = perf_event_open(&pea_llc_miss, pid, cpu_no, -1, PERF_FLAG_FD_CLOEXEC); - if (fd_lm == -1) { + pe_fd = perf_event_open(&pea_llc_miss, pid, cpu_no, -1, PERF_FLAG_FD_CLOEXEC); + if (pe_fd == -1) { ksft_perror("Error opening leader"); return -1; } - ioctl_perf_event_ioc_reset_enable(); + perf_event_reset_enable(); return 0; } @@ -141,15 +141,15 @@ static int perf_event_measure(const char *filename, int bm_pid) int ret; /* Stop counters after one span to get miss rate */ - ioctl(fd_lm, PERF_EVENT_IOC_DISABLE, 0); + ioctl(pe_fd, PERF_EVENT_IOC_DISABLE, 0); - ret = read(fd_lm, &rf_cqm, sizeof(struct read_format)); + ret = read(pe_fd, &pe_read, sizeof(struct perf_event_read)); if (ret == -1) { ksft_perror("Could not get perf value"); return -1; } - return print_results_cache(filename, bm_pid, rf_cqm.values[0].value); + return print_results_cache(filename, bm_pid, pe_read.values[0].value); } /* @@ -204,7 +204,7 @@ int cat_val(struct resctrl_val_param *param, size_t span) if (ret) return ret; - initialize_llc_perf(); + perf_event_initialize(); /* Test runs until the callback setup() tells the test to stop. */ while (1) { @@ -215,7 +215,7 @@ int cat_val(struct resctrl_val_param *param, size_t span) } if (ret < 0) break; - ret = reset_enable_llc_perf(bm_pid, param->cpu_no); + ret = perf_open(bm_pid, param->cpu_no); if (ret) break; @@ -234,7 +234,7 @@ int cat_val(struct resctrl_val_param *param, size_t span) return ret; pe_close: - close(fd_lm); + close(pe_fd); return ret; } -- cgit v1.2.3-70-g09d2 From 038ce802e248a985150156da84bc3f118236b898 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:05:02 +0200 Subject: selftests/resctrl: Improve perf init MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit struct perf_event_attr initialization is spread into perf_event_initialize() and perf_event_attr_initialize() and setting ->config is hardcoded by the deepest level. perf_event_attr init belongs to perf_event_attr_initialize() so move it entirely there. Rename the other function perf_event_initialized_read_format(). Call each init function directly from the test as they will take different parameters (especially true after the perf related global variables are moved to local variables). Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cache.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c index 7f45c4957f81..58ee6f6b0edf 100644 --- a/tools/testing/selftests/resctrl/cache.c +++ b/tools/testing/selftests/resctrl/cache.c @@ -15,8 +15,9 @@ static struct perf_event_read pe_read; static int pe_fd; char llc_occup_path[1024]; -static void perf_event_attr_initialize(void) +static void perf_event_attr_initialize(__u64 config) { + memset(&pea_llc_miss, 0, sizeof(struct perf_event_attr)); pea_llc_miss.type = PERF_TYPE_HARDWARE; pea_llc_miss.size = sizeof(struct perf_event_attr); pea_llc_miss.read_format = PERF_FORMAT_GROUP; @@ -27,6 +28,7 @@ static void perf_event_attr_initialize(void) pea_llc_miss.inherit = 1; pea_llc_miss.exclude_guest = 1; pea_llc_miss.disabled = 1; + pea_llc_miss.config = config; } /* Start counters to log values */ @@ -36,16 +38,9 @@ static void perf_event_reset_enable(void) ioctl(pe_fd, PERF_EVENT_IOC_ENABLE, 0); } -static void perf_event_initialize(void) +static void perf_event_initialize_read_format(void) { - memset(&pea_llc_miss, 0, sizeof(struct perf_event_attr)); memset(&pe_read, 0, sizeof(struct perf_event_read)); - - /* Initialize perf_event_attr structures for HW_CACHE_MISSES */ - perf_event_attr_initialize(); - - pea_llc_miss.config = PERF_COUNT_HW_CACHE_MISSES; - pe_read.nr = 1; } @@ -204,7 +199,8 @@ int cat_val(struct resctrl_val_param *param, size_t span) if (ret) return ret; - perf_event_initialize(); + perf_event_attr_initialize(PERF_COUNT_HW_CACHE_MISSES); + perf_event_initialize_read_format(); /* Test runs until the callback setup() tells the test to stop. */ while (1) { -- cgit v1.2.3-70-g09d2 From 3cdad0a5a6cf581519748612cb449b43379510a4 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:05:03 +0200 Subject: selftests/resctrl: Convert perf related globals to locals MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Perf related variables pea_llc_miss, pe_read, and pe_fd are globals in cache.c. Convert them to locals for better scoping and make pea_llc_miss simpler by renaming it to pea. Make close(pe_fd) handling easier to understand by doing it inside cat_val(). Make also sizeof()s use safer way to determine the right struct. Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cache.c | 72 ++++++++++++++++++--------------- 1 file changed, 40 insertions(+), 32 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c index 58ee6f6b0edf..335415eaa406 100644 --- a/tools/testing/selftests/resctrl/cache.c +++ b/tools/testing/selftests/resctrl/cache.c @@ -10,51 +10,50 @@ struct perf_event_read { } values[2]; }; -static struct perf_event_attr pea_llc_miss; -static struct perf_event_read pe_read; -static int pe_fd; char llc_occup_path[1024]; -static void perf_event_attr_initialize(__u64 config) +static void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config) { - memset(&pea_llc_miss, 0, sizeof(struct perf_event_attr)); - pea_llc_miss.type = PERF_TYPE_HARDWARE; - pea_llc_miss.size = sizeof(struct perf_event_attr); - pea_llc_miss.read_format = PERF_FORMAT_GROUP; - pea_llc_miss.exclude_kernel = 1; - pea_llc_miss.exclude_hv = 1; - pea_llc_miss.exclude_idle = 1; - pea_llc_miss.exclude_callchain_kernel = 1; - pea_llc_miss.inherit = 1; - pea_llc_miss.exclude_guest = 1; - pea_llc_miss.disabled = 1; - pea_llc_miss.config = config; + memset(pea, 0, sizeof(*pea)); + pea->type = PERF_TYPE_HARDWARE; + pea->size = sizeof(*pea); + pea->read_format = PERF_FORMAT_GROUP; + pea->exclude_kernel = 1; + pea->exclude_hv = 1; + pea->exclude_idle = 1; + pea->exclude_callchain_kernel = 1; + pea->inherit = 1; + pea->exclude_guest = 1; + pea->disabled = 1; + pea->config = config; } /* Start counters to log values */ -static void perf_event_reset_enable(void) +static void perf_event_reset_enable(int pe_fd) { ioctl(pe_fd, PERF_EVENT_IOC_RESET, 0); ioctl(pe_fd, PERF_EVENT_IOC_ENABLE, 0); } -static void perf_event_initialize_read_format(void) +static void perf_event_initialize_read_format(struct perf_event_read *pe_read) { - memset(&pe_read, 0, sizeof(struct perf_event_read)); - pe_read.nr = 1; + memset(pe_read, 0, sizeof(*pe_read)); + pe_read->nr = 1; } -static int perf_open(pid_t pid, int cpu_no) +static int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no) { - pe_fd = perf_event_open(&pea_llc_miss, pid, cpu_no, -1, PERF_FLAG_FD_CLOEXEC); + int pe_fd; + + pe_fd = perf_event_open(pea, pid, cpu_no, -1, PERF_FLAG_FD_CLOEXEC); if (pe_fd == -1) { ksft_perror("Error opening leader"); return -1; } - perf_event_reset_enable(); + perf_event_reset_enable(pe_fd); - return 0; + return pe_fd; } /* @@ -131,20 +130,21 @@ static int print_results_cache(const char *filename, int bm_pid, __u64 llc_value * * Return: =0 on success. <0 on failure. */ -static int perf_event_measure(const char *filename, int bm_pid) +static int perf_event_measure(int pe_fd, struct perf_event_read *pe_read, + const char *filename, int bm_pid) { int ret; /* Stop counters after one span to get miss rate */ ioctl(pe_fd, PERF_EVENT_IOC_DISABLE, 0); - ret = read(pe_fd, &pe_read, sizeof(struct perf_event_read)); + ret = read(pe_fd, pe_read, sizeof(*pe_read)); if (ret == -1) { ksft_perror("Could not get perf value"); return -1; } - return print_results_cache(filename, bm_pid, pe_read.values[0].value); + return print_results_cache(filename, bm_pid, pe_read->values[0].value); } /* @@ -181,7 +181,10 @@ int cat_val(struct resctrl_val_param *param, size_t span) { int memflush = 1, operation = 0, ret = 0; char *resctrl_val = param->resctrl_val; + struct perf_event_read pe_read; + struct perf_event_attr pea; pid_t bm_pid; + int pe_fd; if (strcmp(param->filename, "") == 0) sprintf(param->filename, "stdio"); @@ -199,8 +202,8 @@ int cat_val(struct resctrl_val_param *param, size_t span) if (ret) return ret; - perf_event_attr_initialize(PERF_COUNT_HW_CACHE_MISSES); - perf_event_initialize_read_format(); + perf_event_attr_initialize(&pea, PERF_COUNT_HW_CACHE_MISSES); + perf_event_initialize_read_format(&pe_read); /* Test runs until the callback setup() tells the test to stop. */ while (1) { @@ -211,9 +214,12 @@ int cat_val(struct resctrl_val_param *param, size_t span) } if (ret < 0) break; - ret = perf_open(bm_pid, param->cpu_no); - if (ret) + + pe_fd = perf_open(&pea, bm_pid, param->cpu_no); + if (pe_fd < 0) { + ret = -1; break; + } if (run_fill_buf(span, memflush, operation, true)) { fprintf(stderr, "Error-running fill buffer\n"); @@ -222,9 +228,11 @@ int cat_val(struct resctrl_val_param *param, size_t span) } sleep(1); - ret = perf_event_measure(param->filename, bm_pid); + ret = perf_event_measure(pe_fd, &pe_read, param->filename, bm_pid); if (ret) goto pe_close; + + close(pe_fd); } return ret; -- cgit v1.2.3-70-g09d2 From 433f437b3ae2ed4e318ecd5233c82f6936e78e82 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:05:04 +0200 Subject: selftests/resctrl: Move cat_val() to cat_test.c and rename to cat_test() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The main CAT test function is called cat_val() and resides in cache.c which is illogical. Rename the function to cat_test() and move it into cat_test.c. Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cache.c | 90 ++---------------------------- tools/testing/selftests/resctrl/cat_test.c | 73 +++++++++++++++++++++++- tools/testing/selftests/resctrl/resctrl.h | 14 ++++- 3 files changed, 90 insertions(+), 87 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c index 335415eaa406..319d0cdd7225 100644 --- a/tools/testing/selftests/resctrl/cache.c +++ b/tools/testing/selftests/resctrl/cache.c @@ -3,16 +3,9 @@ #include #include "resctrl.h" -struct perf_event_read { - __u64 nr; /* The number of events */ - struct { - __u64 value; /* The value of the event */ - } values[2]; -}; - char llc_occup_path[1024]; -static void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config) +void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config) { memset(pea, 0, sizeof(*pea)); pea->type = PERF_TYPE_HARDWARE; @@ -35,13 +28,13 @@ static void perf_event_reset_enable(int pe_fd) ioctl(pe_fd, PERF_EVENT_IOC_ENABLE, 0); } -static void perf_event_initialize_read_format(struct perf_event_read *pe_read) +void perf_event_initialize_read_format(struct perf_event_read *pe_read) { memset(pe_read, 0, sizeof(*pe_read)); pe_read->nr = 1; } -static int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no) +int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no) { int pe_fd; @@ -130,8 +123,8 @@ static int print_results_cache(const char *filename, int bm_pid, __u64 llc_value * * Return: =0 on success. <0 on failure. */ -static int perf_event_measure(int pe_fd, struct perf_event_read *pe_read, - const char *filename, int bm_pid) +int perf_event_measure(int pe_fd, struct perf_event_read *pe_read, + const char *filename, int bm_pid) { int ret; @@ -169,79 +162,6 @@ int measure_llc_resctrl(const char *filename, int bm_pid) return print_results_cache(filename, bm_pid, llc_occu_resc); } -/* - * cache_val: execute benchmark and measure LLC occupancy resctrl - * and perf cache miss for the benchmark - * @param: parameters passed to cache_val() - * @span: buffer size for the benchmark - * - * Return: 0 when the test was run, < 0 on error. - */ -int cat_val(struct resctrl_val_param *param, size_t span) -{ - int memflush = 1, operation = 0, ret = 0; - char *resctrl_val = param->resctrl_val; - struct perf_event_read pe_read; - struct perf_event_attr pea; - pid_t bm_pid; - int pe_fd; - - if (strcmp(param->filename, "") == 0) - sprintf(param->filename, "stdio"); - - bm_pid = getpid(); - - /* Taskset benchmark to specified cpu */ - ret = taskset_benchmark(bm_pid, param->cpu_no); - if (ret) - return ret; - - /* Write benchmark to specified con_mon grp, mon_grp in resctrl FS*/ - ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp, - resctrl_val); - if (ret) - return ret; - - perf_event_attr_initialize(&pea, PERF_COUNT_HW_CACHE_MISSES); - perf_event_initialize_read_format(&pe_read); - - /* Test runs until the callback setup() tells the test to stop. */ - while (1) { - ret = param->setup(param); - if (ret == END_OF_TESTS) { - ret = 0; - break; - } - if (ret < 0) - break; - - pe_fd = perf_open(&pea, bm_pid, param->cpu_no); - if (pe_fd < 0) { - ret = -1; - break; - } - - if (run_fill_buf(span, memflush, operation, true)) { - fprintf(stderr, "Error-running fill buffer\n"); - ret = -1; - goto pe_close; - } - - sleep(1); - ret = perf_event_measure(pe_fd, &pe_read, param->filename, bm_pid); - if (ret) - goto pe_close; - - close(pe_fd); - } - - return ret; - -pe_close: - close(pe_fd); - return ret; -} - /* * show_cache_info - Show generic cache test information * @no_of_bits: Number of bits diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index 516eaa08e967..bfb607b13491 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -111,6 +111,77 @@ void cat_test_cleanup(void) remove(RESULT_FILE_NAME2); } +/* + * cat_test - Execute CAT benchmark and measure cache misses + * @param: Parameters passed to cat_test() + * @span: Buffer size for the benchmark + * + * Return: 0 when the test was run, < 0 on error. + */ +static int cat_test(struct resctrl_val_param *param, size_t span) +{ + int memflush = 1, operation = 0, ret = 0; + char *resctrl_val = param->resctrl_val; + struct perf_event_read pe_read; + struct perf_event_attr pea; + pid_t bm_pid; + int pe_fd; + + if (strcmp(param->filename, "") == 0) + sprintf(param->filename, "stdio"); + + bm_pid = getpid(); + + /* Taskset benchmark to specified cpu */ + ret = taskset_benchmark(bm_pid, param->cpu_no); + if (ret) + return ret; + + /* Write benchmark to specified con_mon grp, mon_grp in resctrl FS*/ + ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp, + resctrl_val); + if (ret) + return ret; + + perf_event_attr_initialize(&pea, PERF_COUNT_HW_CACHE_MISSES); + perf_event_initialize_read_format(&pe_read); + + /* Test runs until the callback setup() tells the test to stop. */ + while (1) { + ret = param->setup(param); + if (ret == END_OF_TESTS) { + ret = 0; + break; + } + if (ret < 0) + break; + pe_fd = perf_open(&pea, bm_pid, param->cpu_no); + if (pe_fd < 0) { + ret = -1; + break; + } + + if (run_fill_buf(span, memflush, operation, true)) { + fprintf(stderr, "Error-running fill buffer\n"); + ret = -1; + goto pe_close; + } + + sleep(1); + ret = perf_event_measure(pe_fd, &pe_read, param->filename, bm_pid); + if (ret) + goto pe_close; + + close(pe_fd); + } + + return ret; + +pe_close: + close(pe_fd); + return ret; +} + int cat_perf_miss_val(int cpu_no, int n, char *cache_type) { unsigned long full_cache_mask, long_mask; @@ -194,7 +265,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) remove(param.filename); - ret = cat_val(¶m, span); + ret = cat_test(¶m, span); if (ret == 0) ret = check_results(¶m, span); diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index f813fcdcb5e0..4aabf7ac0ab9 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -66,6 +66,13 @@ struct resctrl_val_param { int (*setup)(struct resctrl_val_param *param); }; +struct perf_event_read { + __u64 nr; /* The number of events */ + struct { + __u64 value; /* The value of the event */ + } values[2]; +}; + #define MBM_STR "mbm" #define MBA_STR "mba" #define CMT_STR "cmt" @@ -105,13 +112,18 @@ int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size void ctrlc_handler(int signum, siginfo_t *info, void *ptr); int signal_handler_register(void); void signal_handler_unregister(void); -int cat_val(struct resctrl_val_param *param, size_t span); void cat_test_cleanup(void); int cat_perf_miss_val(int cpu_no, int no_of_bits, char *cache_type); int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd); unsigned int count_bits(unsigned long n); void cmt_test_cleanup(void); int get_core_sibling(int cpu_no); + +void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config); +void perf_event_initialize_read_format(struct perf_event_read *pe_read); +int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no); +int perf_event_measure(int pe_fd, struct perf_event_read *pe_read, + const char *filename, int bm_pid); int measure_llc_resctrl(const char *filename, int bm_pid); void show_cache_info(int no_of_bits, __u64 avg_llc_val, size_t cache_span, bool lines); -- cgit v1.2.3-70-g09d2 From 2892731ec2893252cdbc256a2bd5436b7fd94cf7 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:05:05 +0200 Subject: selftests/resctrl: Open perf fd before start & add error handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Perf fd (pe_fd) is opened, reset, and enabled during every test the CAT selftest runs. Also, ioctl(pe_fd, ...) calls are not error checked even if ioctl() could return an error. Open perf fd only once before the tests and only reset and enable the counter within the test loop. Add error checking to pe_fd ioctl() calls. Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cache.c | 19 +++++++++++++++---- tools/testing/selftests/resctrl/cat_test.c | 14 +++++++------- tools/testing/selftests/resctrl/resctrl.h | 1 + 3 files changed, 23 insertions(+), 11 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c index 319d0cdd7225..1b339d6bbff1 100644 --- a/tools/testing/selftests/resctrl/cache.c +++ b/tools/testing/selftests/resctrl/cache.c @@ -22,10 +22,19 @@ void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config) } /* Start counters to log values */ -static void perf_event_reset_enable(int pe_fd) +int perf_event_reset_enable(int pe_fd) { - ioctl(pe_fd, PERF_EVENT_IOC_RESET, 0); - ioctl(pe_fd, PERF_EVENT_IOC_ENABLE, 0); + int ret; + + ret = ioctl(pe_fd, PERF_EVENT_IOC_RESET, 0); + if (ret < 0) + return ret; + + ret = ioctl(pe_fd, PERF_EVENT_IOC_ENABLE, 0); + if (ret < 0) + return ret; + + return 0; } void perf_event_initialize_read_format(struct perf_event_read *pe_read) @@ -129,7 +138,9 @@ int perf_event_measure(int pe_fd, struct perf_event_read *pe_read, int ret; /* Stop counters after one span to get miss rate */ - ioctl(pe_fd, PERF_EVENT_IOC_DISABLE, 0); + ret = ioctl(pe_fd, PERF_EVENT_IOC_DISABLE, 0); + if (ret < 0) + return ret; ret = read(pe_fd, pe_read, sizeof(*pe_read)); if (ret == -1) { diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index bfb607b13491..36e62baebf4f 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -145,6 +145,9 @@ static int cat_test(struct resctrl_val_param *param, size_t span) perf_event_attr_initialize(&pea, PERF_COUNT_HW_CACHE_MISSES); perf_event_initialize_read_format(&pe_read); + pe_fd = perf_open(&pea, bm_pid, param->cpu_no); + if (pe_fd < 0) + return pe_fd; /* Test runs until the callback setup() tells the test to stop. */ while (1) { @@ -155,11 +158,10 @@ static int cat_test(struct resctrl_val_param *param, size_t span) } if (ret < 0) break; - pe_fd = perf_open(&pea, bm_pid, param->cpu_no); - if (pe_fd < 0) { - ret = -1; - break; - } + + ret = perf_event_reset_enable(pe_fd); + if (ret) + goto pe_close; if (run_fill_buf(span, memflush, operation, true)) { fprintf(stderr, "Error-running fill buffer\n"); @@ -171,8 +173,6 @@ static int cat_test(struct resctrl_val_param *param, size_t span) ret = perf_event_measure(pe_fd, &pe_read, param->filename, bm_pid); if (ret) goto pe_close; - - close(pe_fd); } return ret; diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 4aabf7ac0ab9..f22b7897251e 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -122,6 +122,7 @@ int get_core_sibling(int cpu_no); void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config); void perf_event_initialize_read_format(struct perf_event_read *pe_read); int perf_open(struct perf_event_attr *pea, pid_t pid, int cpu_no); +int perf_event_reset_enable(int pe_fd); int perf_event_measure(int pe_fd, struct perf_event_read *pe_read, const char *filename, int bm_pid); int measure_llc_resctrl(const char *filename, int bm_pid); -- cgit v1.2.3-70-g09d2 From 90a009db09e2b91990df28e47844d44ae0ef9aa8 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:05:06 +0200 Subject: selftests/resctrl: Replace file write with volatile variable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The fill_buf code prevents compiler optimizating the entire read loop away by writing the final value of the variable into a file. While it achieves the goal, writing into a file requires significant amount of work within the innermost test loop and also error handling. A simpler approach is to take advantage of volatile. Writing through a pointer to a volatile variable is enough to prevent compiler from optimizing the write away, and therefore compiler cannot remove the read loop either. Add a volatile 'value_sink' into resctrl_tests.c and make fill_buf to write into it. As a result, the error handling in fill_buf.c can be simplified. Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/fill_buf.c | 26 +++++-------------------- tools/testing/selftests/resctrl/resctrl.h | 7 +++++++ tools/testing/selftests/resctrl/resctrl_tests.c | 4 ++++ 3 files changed, 16 insertions(+), 21 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c index 635f938b11f0..8fe9574db9d8 100644 --- a/tools/testing/selftests/resctrl/fill_buf.c +++ b/tools/testing/selftests/resctrl/fill_buf.c @@ -78,10 +78,9 @@ static void fill_one_span_write(unsigned char *buf, size_t buf_size) } } -static int fill_cache_read(unsigned char *buf, size_t buf_size, bool once) +static void fill_cache_read(unsigned char *buf, size_t buf_size, bool once) { int ret = 0; - FILE *fp; while (1) { ret = fill_one_span_read(buf, buf_size); @@ -90,26 +89,16 @@ static int fill_cache_read(unsigned char *buf, size_t buf_size, bool once) } /* Consume read result so that reading memory is not optimized out. */ - fp = fopen("/dev/null", "w"); - if (!fp) { - ksft_perror("Unable to write to /dev/null"); - return -1; - } - fprintf(fp, "Sum: %d ", ret); - fclose(fp); - - return 0; + *value_sink = ret; } -static int fill_cache_write(unsigned char *buf, size_t buf_size, bool once) +static void fill_cache_write(unsigned char *buf, size_t buf_size, bool once) { while (1) { fill_one_span_write(buf, buf_size); if (once) break; } - - return 0; } static unsigned char *alloc_buffer(size_t buf_size, int memflush) @@ -143,21 +132,16 @@ static unsigned char *alloc_buffer(size_t buf_size, int memflush) int run_fill_buf(size_t buf_size, int memflush, int op, bool once) { unsigned char *buf; - int ret; buf = alloc_buffer(buf_size, memflush); if (!buf) return -1; if (op == 0) - ret = fill_cache_read(buf, buf_size, once); + fill_cache_read(buf, buf_size, once); else - ret = fill_cache_write(buf, buf_size, once); + fill_cache_write(buf, buf_size, once); free(buf); - if (ret) { - printf("\n Error in fill cache\n"); - return -1; - } return 0; } diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index f22b7897251e..5b9bea505120 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -78,6 +78,13 @@ struct perf_event_read { #define CMT_STR "cmt" #define CAT_STR "cat" +/* + * Memory location that consumes values compiler must not optimize away. + * Volatile ensures writes to this location cannot be optimized away by + * compiler. + */ +extern volatile int *value_sink; + extern pid_t bm_pid, ppid; extern char llc_occup_path[1024]; diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c index 2bbe3045a018..f0d573aa363b 100644 --- a/tools/testing/selftests/resctrl/resctrl_tests.c +++ b/tools/testing/selftests/resctrl/resctrl_tests.c @@ -10,6 +10,10 @@ */ #include "resctrl.h" +/* Volatile memory sink to prevent compiler optimizations */ +static volatile int sink_target; +volatile int *value_sink = &sink_target; + static int detect_vendor(void) { FILE *inf = fopen("/proc/cpuinfo", "r"); -- cgit v1.2.3-70-g09d2 From bcdb2e9d9f319935938a5addee040e37b60192ff Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:05:07 +0200 Subject: selftests/resctrl: Read in less obvious order to defeat prefetch optimizations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When reading memory in order, HW prefetching optimizations will interfere with measuring how caches and memory are being accessed. This adds noise into the results. Change the fill_buf reading loop to not use an obvious in-order access using multiply by a prime and modulo. Using a prime multiplier with modulo ensures the entire buffer is eventually read. 23 is small enough that the reads are spread out but wrapping does not occur very frequently (wrapping too often can trigger L2 hits more frequently which causes noise to the test because getting the data from LLC is not required). It was discovered that not all primes work equally well and some can cause wildly unstable results (e.g., in an earlier version of this patch, the reads were done in reversed order and 59 was used as the prime resulting in unacceptably high and unstable results in MBA and MBM test on some architectures). Link: https://lore.kernel.org/linux-kselftest/TYAPR01MB6330025B5E6537F94DA49ACB8B499@TYAPR01MB6330.jpnprd01.prod.outlook.com/ Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/fill_buf.c | 38 +++++++++++++++++++++++------- 1 file changed, 30 insertions(+), 8 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c index 8fe9574db9d8..93a3d408339c 100644 --- a/tools/testing/selftests/resctrl/fill_buf.c +++ b/tools/testing/selftests/resctrl/fill_buf.c @@ -51,16 +51,38 @@ static void mem_flush(unsigned char *buf, size_t buf_size) sb(); } +/* + * Buffer index step advance to workaround HW prefetching interfering with + * the measurements. + * + * Must be a prime to step through all indexes of the buffer. + * + * Some primes work better than others on some architectures (from MBA/MBM + * result stability point of view). + */ +#define FILL_IDX_MULT 23 + static int fill_one_span_read(unsigned char *buf, size_t buf_size) { - unsigned char *end_ptr = buf + buf_size; - unsigned char sum, *p; - - sum = 0; - p = buf; - while (p < end_ptr) { - sum += *p; - p += (CL_SIZE / 2); + unsigned int size = buf_size / (CL_SIZE / 2); + unsigned int i, idx = 0; + unsigned char sum = 0; + + /* + * Read the buffer in an order that is unexpected by HW prefetching + * optimizations to prevent them interfering with the caching pattern. + * + * The read order is (in terms of halves of cachelines): + * i * FILL_IDX_MULT % size + * The formula is open-coded below to avoiding modulo inside the loop + * as it improves MBA/MBM result stability on some architectures. + */ + for (i = 0; i < size; i++) { + sum += buf[idx * (CL_SIZE / 2)]; + + idx += FILL_IDX_MULT; + while (idx >= size) + idx -= size; } return sum; -- cgit v1.2.3-70-g09d2 From 205de6ddd7fff9340bd5e4b68105f28120671c6b Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:05:08 +0200 Subject: selftests/resctrl: Rewrite Cache Allocation Technology (CAT) test MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit CAT test spawns two processes into two different control groups with exclusive schemata. Both the processes alloc a buffer from memory matching their allocated LLC block size and flush the entire buffer out of caches. Since the processes are reading through the buffer only once during the measurement and initially all the buffer was flushed, the test isn't testing CAT. Rewrite the CAT test to allocate a buffer sized to half of LLC. Then perform a sequence of tests with different LLC alloc sizes starting from half of the CBM bits down to 1-bit CBM. Flush the buffer before each test and read the buffer twice. Observe the LLC misses on the second read through the buffer. As the allocated LLC block gets smaller and smaller, the LLC misses will become larger and larger giving a strong signal on CAT working properly. The new CAT test is using only a single process because it relies on measured effect against another run of itself rather than another process adding noise. The rest of the system is set to use the CBM bits not used by the CAT test to keep the test isolated. Replace count_bits() with count_contiguous_bits() to get the first bit position in order to be able to calculate masks based on it. This change has been tested with a number of systems from different generations. Suggested-by: Reinette Chatre Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cat_test.c | 283 +++++++++++++--------------- tools/testing/selftests/resctrl/fill_buf.c | 6 +- tools/testing/selftests/resctrl/resctrl.h | 5 +- tools/testing/selftests/resctrl/resctrlfs.c | 44 +---- 4 files changed, 139 insertions(+), 199 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index 36e62baebf4f..b79916069788 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -11,65 +11,70 @@ #include "resctrl.h" #include -#define RESULT_FILE_NAME1 "result_cat1" -#define RESULT_FILE_NAME2 "result_cat2" +#define RESULT_FILE_NAME "result_cat" #define NUM_OF_RUNS 5 -#define MAX_DIFF_PERCENT 4 -#define MAX_DIFF 1000000 /* - * Change schemata. Write schemata to specified - * con_mon grp, mon_grp in resctrl FS. - * Run 5 times in order to get average values. + * Minimum difference in LLC misses between a test with n+1 bits CBM to the + * test with n bits is MIN_DIFF_PERCENT_PER_BIT * (n - 1). With e.g. 5 vs 4 + * bits in the CBM mask, the minimum difference must be at least + * MIN_DIFF_PERCENT_PER_BIT * (4 - 1) = 3 percent. + * + * The relationship between number of used CBM bits and difference in LLC + * misses is not expected to be linear. With a small number of bits, the + * margin is smaller than with larger number of bits. For selftest purposes, + * however, linear approach is enough because ultimately only pass/fail + * decision has to be made and distinction between strong and stronger + * signal is irrelevant. */ -static int cat_setup(struct resctrl_val_param *p) -{ - char schemata[64]; - int ret = 0; - - /* Run NUM_OF_RUNS times */ - if (p->num_of_runs >= NUM_OF_RUNS) - return END_OF_TESTS; - - if (p->num_of_runs == 0) { - sprintf(schemata, "%lx", p->mask); - ret = write_schemata(p->ctrlgrp, schemata, p->cpu_no, - p->resctrl_val); - } - p->num_of_runs++; - - return ret; -} +#define MIN_DIFF_PERCENT_PER_BIT 1UL static int show_results_info(__u64 sum_llc_val, int no_of_bits, - unsigned long cache_span, unsigned long max_diff, - unsigned long max_diff_percent, unsigned long num_of_runs, - bool platform) + unsigned long cache_span, + unsigned long min_diff_percent, + unsigned long num_of_runs, bool platform, + __s64 *prev_avg_llc_val) { __u64 avg_llc_val = 0; - float diff_percent; - int ret; + float avg_diff; + int ret = 0; avg_llc_val = sum_llc_val / num_of_runs; - diff_percent = ((float)cache_span - avg_llc_val) / cache_span * 100; + if (*prev_avg_llc_val) { + float delta = (__s64)(avg_llc_val - *prev_avg_llc_val); - ret = platform && abs((int)diff_percent) > max_diff_percent; + avg_diff = delta / *prev_avg_llc_val; + ret = platform && (avg_diff * 100) < (float)min_diff_percent; - ksft_print_msg("%s Check cache miss rate within %lu%%\n", - ret ? "Fail:" : "Pass:", max_diff_percent); + ksft_print_msg("%s Check cache miss rate changed more than %.1f%%\n", + ret ? "Fail:" : "Pass:", (float)min_diff_percent); - ksft_print_msg("Percent diff=%d\n", abs((int)diff_percent)); + ksft_print_msg("Percent diff=%.1f\n", avg_diff * 100); + } + *prev_avg_llc_val = avg_llc_val; show_cache_info(no_of_bits, avg_llc_val, cache_span, true); return ret; } -static int check_results(struct resctrl_val_param *param, size_t span) +/* Remove the highest bit from CBM */ +static unsigned long next_mask(unsigned long current_mask) +{ + return current_mask & (current_mask >> 1); +} + +static int check_results(struct resctrl_val_param *param, const char *cache_type, + unsigned long cache_total_size, unsigned long full_cache_mask, + unsigned long current_mask) { char *token_array[8], temp[512]; - int runs = 0, no_of_bits = 0; __u64 sum_llc_perf_miss = 0; + __s64 prev_avg_llc_val = 0; + unsigned long alloc_size; + int runs = 0; + int fail = 0; + int ret; FILE *fp; ksft_print_msg("Checking for pass/fail\n"); @@ -83,49 +88,78 @@ static int check_results(struct resctrl_val_param *param, size_t span) while (fgets(temp, sizeof(temp), fp)) { char *token = strtok(temp, ":\t"); int fields = 0; + int bits; while (token) { token_array[fields++] = token; token = strtok(NULL, ":\t"); } - /* - * Discard the first value which is inaccurate due to monitoring - * setup transition phase. - */ - if (runs > 0) - sum_llc_perf_miss += strtoull(token_array[3], NULL, 0); + + sum_llc_perf_miss += strtoull(token_array[3], NULL, 0); runs++; + + if (runs < NUM_OF_RUNS) + continue; + + if (!current_mask) { + ksft_print_msg("Unexpected empty cache mask\n"); + break; + } + + alloc_size = cache_portion_size(cache_total_size, current_mask, full_cache_mask); + + bits = count_bits(current_mask); + + ret = show_results_info(sum_llc_perf_miss, bits, + alloc_size / 64, + MIN_DIFF_PERCENT_PER_BIT * (bits - 1), + runs, get_vendor() == ARCH_INTEL, + &prev_avg_llc_val); + if (ret) + fail = 1; + + runs = 0; + sum_llc_perf_miss = 0; + current_mask = next_mask(current_mask); } fclose(fp); - no_of_bits = count_bits(param->mask); - return show_results_info(sum_llc_perf_miss, no_of_bits, span / 64, - MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, - get_vendor() == ARCH_INTEL); + return fail; } void cat_test_cleanup(void) { - remove(RESULT_FILE_NAME1); - remove(RESULT_FILE_NAME2); + remove(RESULT_FILE_NAME); } /* * cat_test - Execute CAT benchmark and measure cache misses * @param: Parameters passed to cat_test() * @span: Buffer size for the benchmark + * @current_mask Start mask for the first iteration + * + * Run CAT selftest by varying the allocated cache portion and comparing the + * impact on cache misses (the result analysis is done in check_results() + * and show_results_info(), not in this function). + * + * One bit is removed from the CAT allocation bit mask (in current_mask) for + * each subsequent test which keeps reducing the size of the allocated cache + * portion. A single test flushes the buffer, reads it to warm up the cache, + * and reads the buffer again. The cache misses are measured during the last + * read pass. * * Return: 0 when the test was run, < 0 on error. */ -static int cat_test(struct resctrl_val_param *param, size_t span) +static int cat_test(struct resctrl_val_param *param, size_t span, unsigned long current_mask) { - int memflush = 1, operation = 0, ret = 0; char *resctrl_val = param->resctrl_val; struct perf_event_read pe_read; struct perf_event_attr pea; + unsigned char *buf; + char schemata[64]; + int ret, i, pe_fd; pid_t bm_pid; - int pe_fd; if (strcmp(param->filename, "") == 0) sprintf(param->filename, "stdio"); @@ -149,48 +183,55 @@ static int cat_test(struct resctrl_val_param *param, size_t span) if (pe_fd < 0) return pe_fd; - /* Test runs until the callback setup() tells the test to stop. */ - while (1) { - ret = param->setup(param); - if (ret == END_OF_TESTS) { - ret = 0; - break; - } - if (ret < 0) - break; + buf = alloc_buffer(span, 1); + if (!buf) { + ret = -1; + goto pe_close; + } - ret = perf_event_reset_enable(pe_fd); + while (current_mask) { + snprintf(schemata, sizeof(schemata), "%lx", param->mask & ~current_mask); + ret = write_schemata("", schemata, param->cpu_no, param->resctrl_val); if (ret) - goto pe_close; + goto free_buf; + snprintf(schemata, sizeof(schemata), "%lx", current_mask); + ret = write_schemata(param->ctrlgrp, schemata, param->cpu_no, param->resctrl_val); + if (ret) + goto free_buf; - if (run_fill_buf(span, memflush, operation, true)) { - fprintf(stderr, "Error-running fill buffer\n"); - ret = -1; - goto pe_close; - } + for (i = 0; i < NUM_OF_RUNS; i++) { + mem_flush(buf, span); + fill_cache_read(buf, span, true); - sleep(1); - ret = perf_event_measure(pe_fd, &pe_read, param->filename, bm_pid); - if (ret) - goto pe_close; - } + ret = perf_event_reset_enable(pe_fd); + if (ret) + goto free_buf; - return ret; + fill_cache_read(buf, span, true); + ret = perf_event_measure(pe_fd, &pe_read, param->filename, bm_pid); + if (ret) + goto free_buf; + } + current_mask = next_mask(current_mask); + } + +free_buf: + free(buf); pe_close: close(pe_fd); + return ret; } int cat_perf_miss_val(int cpu_no, int n, char *cache_type) { - unsigned long full_cache_mask, long_mask; - unsigned long l_mask, l_mask_1; - int ret, pipefd[2], sibling_cpu_no; + unsigned long long_mask, start_mask, full_cache_mask; unsigned long cache_total_size = 0; + unsigned int start; int count_of_bits; - char pipe_message; size_t span; + int ret; ret = get_full_cbm(cache_type, &full_cache_mask); if (ret) @@ -206,7 +247,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) return ret; ksft_print_msg("Cache size :%lu\n", cache_total_size); - count_of_bits = count_bits(long_mask); + count_of_bits = count_contiguous_bits(long_mask, &start); if (!n) n = count_of_bits / 2; @@ -217,88 +258,26 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) count_of_bits - 1); return -1; } - - /* Get core id from same socket for running another thread */ - sibling_cpu_no = get_core_sibling(cpu_no); - if (sibling_cpu_no < 0) - return -1; + start_mask = create_bit_mask(start, n); struct resctrl_val_param param = { .resctrl_val = CAT_STR, .cpu_no = cpu_no, - .setup = cat_setup, + .ctrlgrp = "c1", + .filename = RESULT_FILE_NAME, + .num_of_runs = 0, }; - - l_mask = long_mask >> n; - l_mask_1 = ~l_mask & long_mask; - - /* Set param values for parent thread which will be allocated bitmask - * with (max_bits - n) bits - */ - span = cache_portion_size(cache_total_size, l_mask, full_cache_mask); - strcpy(param.ctrlgrp, "c2"); - strcpy(param.mongrp, "m2"); - strcpy(param.filename, RESULT_FILE_NAME2); - param.mask = l_mask; - param.num_of_runs = 0; - - if (pipe(pipefd)) { - ksft_perror("Unable to create pipe"); - return -1; - } - - fflush(stdout); - bm_pid = fork(); - - /* Set param values for child thread which will be allocated bitmask - * with n bits - */ - if (bm_pid == 0) { - param.mask = l_mask_1; - strcpy(param.ctrlgrp, "c1"); - strcpy(param.mongrp, "m1"); - span = cache_portion_size(cache_total_size, l_mask_1, full_cache_mask); - strcpy(param.filename, RESULT_FILE_NAME1); - param.num_of_runs = 0; - param.cpu_no = sibling_cpu_no; - } + param.mask = long_mask; + span = cache_portion_size(cache_total_size, start_mask, full_cache_mask); remove(param.filename); - ret = cat_test(¶m, span); - if (ret == 0) - ret = check_results(¶m, span); - - if (bm_pid == 0) { - /* Tell parent that child is ready */ - close(pipefd[0]); - pipe_message = 1; - if (write(pipefd[1], &pipe_message, sizeof(pipe_message)) < - sizeof(pipe_message)) - /* - * Just print the error message. - * Let while(1) run and wait for itself to be killed. - */ - ksft_perror("Failed signaling parent process"); - - close(pipefd[1]); - while (1) - ; - } else { - /* Parent waits for child to be ready. */ - close(pipefd[1]); - pipe_message = 0; - while (pipe_message != 1) { - if (read(pipefd[0], &pipe_message, - sizeof(pipe_message)) < sizeof(pipe_message)) { - ksft_perror("Failed reading from child process"); - break; - } - } - close(pipefd[0]); - kill(bm_pid, SIGKILL); - } + ret = cat_test(¶m, span, start_mask); + if (ret) + goto out; + ret = check_results(¶m, cache_type, cache_total_size, full_cache_mask, start_mask); +out: cat_test_cleanup(); return ret; diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c index 93a3d408339c..ae120f1735c0 100644 --- a/tools/testing/selftests/resctrl/fill_buf.c +++ b/tools/testing/selftests/resctrl/fill_buf.c @@ -38,7 +38,7 @@ static void cl_flush(void *p) #endif } -static void mem_flush(unsigned char *buf, size_t buf_size) +void mem_flush(unsigned char *buf, size_t buf_size) { unsigned char *cp = buf; size_t i = 0; @@ -100,7 +100,7 @@ static void fill_one_span_write(unsigned char *buf, size_t buf_size) } } -static void fill_cache_read(unsigned char *buf, size_t buf_size, bool once) +void fill_cache_read(unsigned char *buf, size_t buf_size, bool once) { int ret = 0; @@ -123,7 +123,7 @@ static void fill_cache_write(unsigned char *buf, size_t buf_size, bool once) } } -static unsigned char *alloc_buffer(size_t buf_size, int memflush) +unsigned char *alloc_buffer(size_t buf_size, int memflush) { void *buf = NULL; uint64_t *p64; diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 5b9bea505120..4f040e999eea 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -105,6 +105,9 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp, char *resctrl_val); int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu, int group_fd, unsigned long flags); +unsigned char *alloc_buffer(size_t buf_size, int memflush); +void mem_flush(unsigned char *buf, size_t buf_size); +void fill_cache_read(unsigned char *buf, size_t buf_size, bool once); int run_fill_buf(size_t buf_size, int memflush, int op, bool once); int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param); int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd); @@ -113,6 +116,7 @@ void mbm_test_cleanup(void); int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd); void mba_test_cleanup(void); unsigned long create_bit_mask(unsigned int start, unsigned int len); +unsigned int count_contiguous_bits(unsigned long val, unsigned int *start); int get_full_cbm(const char *cache_type, unsigned long *mask); int get_mask_no_shareable(const char *cache_type, unsigned long *mask); int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size); @@ -124,7 +128,6 @@ int cat_perf_miss_val(int cpu_no, int no_of_bits, char *cache_type); int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd); unsigned int count_bits(unsigned long n); void cmt_test_cleanup(void); -int get_core_sibling(int cpu_no); void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config); void perf_event_initialize_read_format(struct perf_event_read *pe_read); diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index 3ec09688cfc3..846281e429ca 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -245,7 +245,7 @@ unsigned long create_bit_mask(unsigned int start, unsigned int len) * * Return: The length of the contiguous bits in the longest train of bits */ -static unsigned int count_contiguous_bits(unsigned long val, unsigned int *start) +unsigned int count_contiguous_bits(unsigned long val, unsigned int *start) { unsigned long last_val; unsigned int count = 0; @@ -343,48 +343,6 @@ int get_mask_no_shareable(const char *cache_type, unsigned long *mask) return 0; } -/* - * get_core_sibling - Get sibling core id from the same socket for given CPU - * @cpu_no: CPU number - * - * Return: > 0 on success, < 0 on failure. - */ -int get_core_sibling(int cpu_no) -{ - char core_siblings_path[1024], cpu_list_str[64]; - int sibling_cpu_no = -1; - FILE *fp; - - sprintf(core_siblings_path, "%s%d/topology/core_siblings_list", - CORE_SIBLINGS_PATH, cpu_no); - - fp = fopen(core_siblings_path, "r"); - if (!fp) { - ksft_perror("Failed to open core siblings path"); - - return -1; - } - if (fscanf(fp, "%s", cpu_list_str) <= 0) { - ksft_perror("Could not get core_siblings list"); - fclose(fp); - - return -1; - } - fclose(fp); - - char *token = strtok(cpu_list_str, "-,"); - - while (token) { - sibling_cpu_no = atoi(token); - /* Skipping core 0 as we don't want to run test on core 0 */ - if (sibling_cpu_no != 0 && sibling_cpu_no != cpu_no) - break; - token = strtok(NULL, "-,"); - } - - return sibling_cpu_no; -} - /* * taskset_benchmark - Taskset PID (i.e. benchmark) to a specified cpu * @bm_pid: PID that should be binded -- cgit v1.2.3-70-g09d2 From 6c8cb747d071cf72c2930e09bb20ab3eabfe62ff Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:05:09 +0200 Subject: selftests/resctrl: Restore the CPU affinity after CAT test MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit CAT test does not reset the CPU affinity after the benchmark. This is relatively harmless as is because CAT test is the last benchmark to run, however, more tests may be added later. Store the CPU affinity the first time taskset_benchmark() is run and add taskset_restore() which the test can call to reset the CPU mask to its original value. Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cat_test.c | 13 +++++++---- tools/testing/selftests/resctrl/resctrl.h | 3 ++- tools/testing/selftests/resctrl/resctrl_val.c | 2 +- tools/testing/selftests/resctrl/resctrlfs.c | 33 ++++++++++++++++++++++++--- 4 files changed, 42 insertions(+), 9 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index b79916069788..fa95433297c9 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -156,6 +156,7 @@ static int cat_test(struct resctrl_val_param *param, size_t span, unsigned long char *resctrl_val = param->resctrl_val; struct perf_event_read pe_read; struct perf_event_attr pea; + cpu_set_t old_affinity; unsigned char *buf; char schemata[64]; int ret, i, pe_fd; @@ -167,7 +168,7 @@ static int cat_test(struct resctrl_val_param *param, size_t span, unsigned long bm_pid = getpid(); /* Taskset benchmark to specified cpu */ - ret = taskset_benchmark(bm_pid, param->cpu_no); + ret = taskset_benchmark(bm_pid, param->cpu_no, &old_affinity); if (ret) return ret; @@ -175,13 +176,15 @@ static int cat_test(struct resctrl_val_param *param, size_t span, unsigned long ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp, resctrl_val); if (ret) - return ret; + goto reset_affinity; perf_event_attr_initialize(&pea, PERF_COUNT_HW_CACHE_MISSES); perf_event_initialize_read_format(&pe_read); pe_fd = perf_open(&pea, bm_pid, param->cpu_no); - if (pe_fd < 0) - return pe_fd; + if (pe_fd < 0) { + ret = -1; + goto reset_affinity; + } buf = alloc_buffer(span, 1); if (!buf) { @@ -220,6 +223,8 @@ free_buf: free(buf); pe_close: close(pe_fd); +reset_affinity: + taskset_restore(bm_pid, &old_affinity); return ret; } diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 4f040e999eea..94347acafe55 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -98,7 +98,8 @@ int umount_resctrlfs(void); int validate_bw_report_request(char *bw_report); bool validate_resctrl_feature_request(const char *resource, const char *feature); char *fgrep(FILE *inf, const char *str); -int taskset_benchmark(pid_t bm_pid, int cpu_no); +int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity); +int taskset_restore(pid_t bm_pid, cpu_set_t *old_affinity); int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val); int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp, diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c index f6859fe433d9..6574a13f3919 100644 --- a/tools/testing/selftests/resctrl/resctrl_val.c +++ b/tools/testing/selftests/resctrl/resctrl_val.c @@ -777,7 +777,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par value.sival_ptr = (void *)benchmark_cmd; /* Taskset benchmark to specified cpu */ - ret = taskset_benchmark(bm_pid, param->cpu_no); + ret = taskset_benchmark(bm_pid, param->cpu_no, NULL); if (ret) goto out; diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index 846281e429ca..1bcb9aa96cc2 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -345,15 +345,25 @@ int get_mask_no_shareable(const char *cache_type, unsigned long *mask) /* * taskset_benchmark - Taskset PID (i.e. benchmark) to a specified cpu - * @bm_pid: PID that should be binded - * @cpu_no: CPU number at which the PID would be binded + * @bm_pid: PID that should be binded + * @cpu_no: CPU number at which the PID would be binded + * @old_affinity: When not NULL, set to old CPU affinity * * Return: 0 on success, < 0 on error. */ -int taskset_benchmark(pid_t bm_pid, int cpu_no) +int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity) { cpu_set_t my_set; + if (old_affinity) { + CPU_ZERO(old_affinity); + if (sched_getaffinity(bm_pid, sizeof(*old_affinity), + old_affinity)) { + ksft_perror("Unable to read CPU affinity"); + return -1; + } + } + CPU_ZERO(&my_set); CPU_SET(cpu_no, &my_set); @@ -366,6 +376,23 @@ int taskset_benchmark(pid_t bm_pid, int cpu_no) return 0; } +/* + * taskset_restore - Taskset PID to the earlier CPU affinity + * @bm_pid: PID that should be reset + * @old_affinity: The old CPU affinity to restore + * + * Return: 0 on success, < 0 on error. + */ +int taskset_restore(pid_t bm_pid, cpu_set_t *old_affinity) +{ + if (sched_setaffinity(bm_pid, sizeof(*old_affinity), old_affinity)) { + ksft_perror("Unable to restore CPU affinity"); + return -1; + } + + return 0; +} + /* * create_grp - Create a group only if one doesn't exist * @grp_name: Name of the group -- cgit v1.2.3-70-g09d2 From 15f298821289d3efba87bb34db29d0ba9780a443 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:05:10 +0200 Subject: selftests/resctrl: Create struct for input parameters MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit resctrl_tests reads a set of parameters and passes them individually for each tests which causes variations in the call signature between the tests. Add struct input_params to hold all input parameters. It can be easily passed to every test without varying the call signature. Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cat_test.c | 20 ++++---- tools/testing/selftests/resctrl/cmt_test.c | 16 +++---- tools/testing/selftests/resctrl/mba_test.c | 9 ++-- tools/testing/selftests/resctrl/mbm_test.c | 9 ++-- tools/testing/selftests/resctrl/resctrl.h | 28 +++++++---- tools/testing/selftests/resctrl/resctrl_tests.c | 63 ++++++++++++++----------- tools/testing/selftests/resctrl/resctrl_val.c | 21 +++++---- 7 files changed, 95 insertions(+), 71 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index fa95433297c9..272132ff7337 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -135,6 +135,7 @@ void cat_test_cleanup(void) /* * cat_test - Execute CAT benchmark and measure cache misses + * @uparams: User supplied parameters * @param: Parameters passed to cat_test() * @span: Buffer size for the benchmark * @current_mask Start mask for the first iteration @@ -151,7 +152,8 @@ void cat_test_cleanup(void) * * Return: 0 when the test was run, < 0 on error. */ -static int cat_test(struct resctrl_val_param *param, size_t span, unsigned long current_mask) +static int cat_test(const struct user_params *uparams, struct resctrl_val_param *param, + size_t span, unsigned long current_mask) { char *resctrl_val = param->resctrl_val; struct perf_event_read pe_read; @@ -168,7 +170,7 @@ static int cat_test(struct resctrl_val_param *param, size_t span, unsigned long bm_pid = getpid(); /* Taskset benchmark to specified cpu */ - ret = taskset_benchmark(bm_pid, param->cpu_no, &old_affinity); + ret = taskset_benchmark(bm_pid, uparams->cpu, &old_affinity); if (ret) return ret; @@ -180,7 +182,7 @@ static int cat_test(struct resctrl_val_param *param, size_t span, unsigned long perf_event_attr_initialize(&pea, PERF_COUNT_HW_CACHE_MISSES); perf_event_initialize_read_format(&pe_read); - pe_fd = perf_open(&pea, bm_pid, param->cpu_no); + pe_fd = perf_open(&pea, bm_pid, uparams->cpu); if (pe_fd < 0) { ret = -1; goto reset_affinity; @@ -194,11 +196,11 @@ static int cat_test(struct resctrl_val_param *param, size_t span, unsigned long while (current_mask) { snprintf(schemata, sizeof(schemata), "%lx", param->mask & ~current_mask); - ret = write_schemata("", schemata, param->cpu_no, param->resctrl_val); + ret = write_schemata("", schemata, uparams->cpu, param->resctrl_val); if (ret) goto free_buf; snprintf(schemata, sizeof(schemata), "%lx", current_mask); - ret = write_schemata(param->ctrlgrp, schemata, param->cpu_no, param->resctrl_val); + ret = write_schemata(param->ctrlgrp, schemata, uparams->cpu, param->resctrl_val); if (ret) goto free_buf; @@ -229,10 +231,11 @@ reset_affinity: return ret; } -int cat_perf_miss_val(int cpu_no, int n, char *cache_type) +int cat_perf_miss_val(const struct user_params *uparams, char *cache_type) { unsigned long long_mask, start_mask, full_cache_mask; unsigned long cache_total_size = 0; + int n = uparams->bits; unsigned int start; int count_of_bits; size_t span; @@ -247,7 +250,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) return ret; /* Get L3/L2 cache size */ - ret = get_cache_size(cpu_no, cache_type, &cache_total_size); + ret = get_cache_size(uparams->cpu, cache_type, &cache_total_size); if (ret) return ret; ksft_print_msg("Cache size :%lu\n", cache_total_size); @@ -267,7 +270,6 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) struct resctrl_val_param param = { .resctrl_val = CAT_STR, - .cpu_no = cpu_no, .ctrlgrp = "c1", .filename = RESULT_FILE_NAME, .num_of_runs = 0, @@ -277,7 +279,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) remove(param.filename); - ret = cat_test(¶m, span, start_mask); + ret = cat_test(uparams, ¶m, span, start_mask); if (ret) goto out; diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c index 604690cd8b3e..a5d0c0878c42 100644 --- a/tools/testing/selftests/resctrl/cmt_test.c +++ b/tools/testing/selftests/resctrl/cmt_test.c @@ -16,7 +16,7 @@ #define MAX_DIFF 2000000 #define MAX_DIFF_PERCENT 15 -static int cmt_setup(struct resctrl_val_param *p) +static int cmt_setup(const struct user_params *uparams, struct resctrl_val_param *p) { /* Run NUM_OF_RUNS times */ if (p->num_of_runs >= NUM_OF_RUNS) @@ -94,11 +94,12 @@ void cmt_test_cleanup(void) remove(RESULT_FILE_NAME); } -int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd) +int cmt_resctrl_val(const struct user_params *uparams) { - const char * const *cmd = benchmark_cmd; + const char * const *cmd = uparams->benchmark_cmd; const char *new_cmd[BENCHMARK_ARGS]; unsigned long cache_total_size = 0; + int n = uparams->bits ? : 5; unsigned long long_mask; char *span_str = NULL; int count_of_bits; @@ -109,7 +110,7 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd) if (ret) return ret; - ret = get_cache_size(cpu_no, "L3", &cache_total_size); + ret = get_cache_size(uparams->cpu, "L3", &cache_total_size); if (ret) return ret; ksft_print_msg("Cache size :%lu\n", cache_total_size); @@ -126,7 +127,6 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd) .resctrl_val = CMT_STR, .ctrlgrp = "c1", .mongrp = "m1", - .cpu_no = cpu_no, .filename = RESULT_FILE_NAME, .mask = ~(long_mask << n) & long_mask, .num_of_runs = 0, @@ -137,8 +137,8 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd) if (strcmp(cmd[0], "fill_buf") == 0) { /* Duplicate the command to be able to replace span in it */ - for (i = 0; benchmark_cmd[i]; i++) - new_cmd[i] = benchmark_cmd[i]; + for (i = 0; uparams->benchmark_cmd[i]; i++) + new_cmd[i] = uparams->benchmark_cmd[i]; new_cmd[i] = NULL; ret = asprintf(&span_str, "%zu", span); @@ -150,7 +150,7 @@ int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd) remove(RESULT_FILE_NAME); - ret = resctrl_val(cmd, ¶m); + ret = resctrl_val(uparams, cmd, ¶m); if (ret) goto out; diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c index e907adf7cd25..8e54bc508a75 100644 --- a/tools/testing/selftests/resctrl/mba_test.c +++ b/tools/testing/selftests/resctrl/mba_test.c @@ -22,7 +22,7 @@ * con_mon grp, mon_grp in resctrl FS. * For each allocation, run 5 times in order to get average values. */ -static int mba_setup(struct resctrl_val_param *p) +static int mba_setup(const struct user_params *uparams, struct resctrl_val_param *p) { static int runs_per_allocation, allocation = 100; char allocation_str[64]; @@ -40,7 +40,7 @@ static int mba_setup(struct resctrl_val_param *p) sprintf(allocation_str, "%d", allocation); - ret = write_schemata(p->ctrlgrp, allocation_str, p->cpu_no, + ret = write_schemata(p->ctrlgrp, allocation_str, uparams->cpu, p->resctrl_val); if (ret < 0) return ret; @@ -141,13 +141,12 @@ void mba_test_cleanup(void) remove(RESULT_FILE_NAME); } -int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd) +int mba_schemata_change(const struct user_params *uparams) { struct resctrl_val_param param = { .resctrl_val = MBA_STR, .ctrlgrp = "c1", .mongrp = "m1", - .cpu_no = cpu_no, .filename = RESULT_FILE_NAME, .bw_report = "reads", .setup = mba_setup @@ -156,7 +155,7 @@ int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd) remove(RESULT_FILE_NAME); - ret = resctrl_val(benchmark_cmd, ¶m); + ret = resctrl_val(uparams, uparams->benchmark_cmd, ¶m); if (ret) goto out; diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c index 721b3ecbc158..ea951cfae5fe 100644 --- a/tools/testing/selftests/resctrl/mbm_test.c +++ b/tools/testing/selftests/resctrl/mbm_test.c @@ -86,7 +86,7 @@ static int check_results(size_t span) return ret; } -static int mbm_setup(struct resctrl_val_param *p) +static int mbm_setup(const struct user_params *uparams, struct resctrl_val_param *p) { int ret = 0; @@ -96,7 +96,7 @@ static int mbm_setup(struct resctrl_val_param *p) /* Set up shemata with 100% allocation on the first run. */ if (p->num_of_runs == 0 && validate_resctrl_feature_request("MB", NULL)) - ret = write_schemata(p->ctrlgrp, "100", p->cpu_no, + ret = write_schemata(p->ctrlgrp, "100", uparams->cpu, p->resctrl_val); p->num_of_runs++; @@ -109,13 +109,12 @@ void mbm_test_cleanup(void) remove(RESULT_FILE_NAME); } -int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd) +int mbm_bw_change(const struct user_params *uparams) { struct resctrl_val_param param = { .resctrl_val = MBM_STR, .ctrlgrp = "c1", .mongrp = "m1", - .cpu_no = cpu_no, .filename = RESULT_FILE_NAME, .bw_report = "reads", .setup = mbm_setup @@ -124,7 +123,7 @@ int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd) remove(RESULT_FILE_NAME); - ret = resctrl_val(benchmark_cmd, ¶m); + ret = resctrl_val(uparams, uparams->benchmark_cmd, ¶m); if (ret) goto out; diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 94347acafe55..199ba91a78f7 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -44,12 +44,23 @@ exit(EXIT_FAILURE); \ } while (0) +/* + * user_params: User supplied parameters + * @cpu: CPU number to which the benchmark will be bound to + * @bits: Number of bits used for cache allocation size + * @benchmark_cmd: Benchmark command to run during (some of the) tests + */ +struct user_params { + int cpu; + int bits; + const char *benchmark_cmd[BENCHMARK_ARGS]; +}; + /* * resctrl_val_param: resctrl test parameters * @resctrl_val: Resctrl feature (Eg: mbm, mba.. etc) * @ctrlgrp: Name of the control monitor group (con_mon grp) * @mongrp: Name of the monitor group (mon grp) - * @cpu_no: CPU number to which the benchmark would be binded * @filename: Name of file to which the o/p should be written * @bw_report: Bandwidth report type (reads vs writes) * @setup: Call back function to setup test environment @@ -58,12 +69,12 @@ struct resctrl_val_param { char *resctrl_val; char ctrlgrp[64]; char mongrp[64]; - int cpu_no; char filename[64]; char *bw_report; unsigned long mask; int num_of_runs; - int (*setup)(struct resctrl_val_param *param); + int (*setup)(const struct user_params *uparams, + struct resctrl_val_param *param); }; struct perf_event_read { @@ -110,11 +121,12 @@ unsigned char *alloc_buffer(size_t buf_size, int memflush); void mem_flush(unsigned char *buf, size_t buf_size); void fill_cache_read(unsigned char *buf, size_t buf_size, bool once); int run_fill_buf(size_t buf_size, int memflush, int op, bool once); -int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param); -int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd); +int resctrl_val(const struct user_params *uparams, const char * const *benchmark_cmd, + struct resctrl_val_param *param); +int mbm_bw_change(const struct user_params *uparams); void tests_cleanup(void); void mbm_test_cleanup(void); -int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd); +int mba_schemata_change(const struct user_params *uparams); void mba_test_cleanup(void); unsigned long create_bit_mask(unsigned int start, unsigned int len); unsigned int count_contiguous_bits(unsigned long val, unsigned int *start); @@ -125,8 +137,8 @@ void ctrlc_handler(int signum, siginfo_t *info, void *ptr); int signal_handler_register(void); void signal_handler_unregister(void); void cat_test_cleanup(void); -int cat_perf_miss_val(int cpu_no, int no_of_bits, char *cache_type); -int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd); +int cat_perf_miss_val(const struct user_params *uparams, char *cache_type); +int cmt_resctrl_val(const struct user_params *uparams); unsigned int count_bits(unsigned long n); void cmt_test_cleanup(void); diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c index f0d573aa363b..3059a124ac59 100644 --- a/tools/testing/selftests/resctrl/resctrl_tests.c +++ b/tools/testing/selftests/resctrl/resctrl_tests.c @@ -96,7 +96,7 @@ static void test_cleanup(void) signal_handler_unregister(); } -static void run_mbm_test(const char * const *benchmark_cmd, int cpu_no) +static void run_mbm_test(const struct user_params *uparams) { int res; @@ -114,7 +114,7 @@ static void run_mbm_test(const char * const *benchmark_cmd, int cpu_no) goto cleanup; } - res = mbm_bw_change(cpu_no, benchmark_cmd); + res = mbm_bw_change(uparams); ksft_test_result(!res, "MBM: bw change\n"); if ((get_vendor() == ARCH_INTEL) && res) ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); @@ -123,7 +123,7 @@ cleanup: test_cleanup(); } -static void run_mba_test(const char * const *benchmark_cmd, int cpu_no) +static void run_mba_test(const struct user_params *uparams) { int res; @@ -141,14 +141,14 @@ static void run_mba_test(const char * const *benchmark_cmd, int cpu_no) goto cleanup; } - res = mba_schemata_change(cpu_no, benchmark_cmd); + res = mba_schemata_change(uparams); ksft_test_result(!res, "MBA: schemata change\n"); cleanup: test_cleanup(); } -static void run_cmt_test(const char * const *benchmark_cmd, int cpu_no) +static void run_cmt_test(const struct user_params *uparams) { int res; @@ -165,7 +165,7 @@ static void run_cmt_test(const char * const *benchmark_cmd, int cpu_no) goto cleanup; } - res = cmt_resctrl_val(cpu_no, 5, benchmark_cmd); + res = cmt_resctrl_val(uparams); ksft_test_result(!res, "CMT: test\n"); if ((get_vendor() == ARCH_INTEL) && res) ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); @@ -174,7 +174,7 @@ cleanup: test_cleanup(); } -static void run_cat_test(int cpu_no, int no_of_bits) +static void run_cat_test(const struct user_params *uparams) { int res; @@ -190,22 +190,31 @@ static void run_cat_test(int cpu_no, int no_of_bits) goto cleanup; } - res = cat_perf_miss_val(cpu_no, no_of_bits, "L3"); + res = cat_perf_miss_val(uparams, "L3"); ksft_test_result(!res, "CAT: test\n"); cleanup: test_cleanup(); } +static void init_user_params(struct user_params *uparams) +{ + memset(uparams, 0, sizeof(*uparams)); + + uparams->cpu = 1; + uparams->bits = 0; +} + int main(int argc, char **argv) { bool mbm_test = true, mba_test = true, cmt_test = true; - const char *benchmark_cmd[BENCHMARK_ARGS] = {}; - int c, cpu_no = 1, i, no_of_bits = 0; + struct user_params uparams; char *span_str = NULL; bool cat_test = true; int tests = 0; - int ret; + int ret, c, i; + + init_user_params(&uparams); while ((c = getopt(argc, argv, "ht:b:n:p:")) != -1) { char *token; @@ -223,8 +232,8 @@ int main(int argc, char **argv) /* Extract benchmark command from command line. */ for (i = 0; i < argc - optind; i++) - benchmark_cmd[i] = argv[i + optind]; - benchmark_cmd[i] = NULL; + uparams.benchmark_cmd[i] = argv[i + optind]; + uparams.benchmark_cmd[i] = NULL; goto last_arg; case 't': @@ -256,11 +265,11 @@ int main(int argc, char **argv) } break; case 'p': - cpu_no = atoi(optarg); + uparams.cpu = atoi(optarg); break; case 'n': - no_of_bits = atoi(optarg); - if (no_of_bits <= 0) { + uparams.bits = atoi(optarg); + if (uparams.bits <= 0) { printf("Bail out! invalid argument for no_of_bits\n"); return -1; } @@ -295,32 +304,32 @@ last_arg: filter_dmesg(); - if (!benchmark_cmd[0]) { + if (!uparams.benchmark_cmd[0]) { /* If no benchmark is given by "-b" argument, use fill_buf. */ - benchmark_cmd[0] = "fill_buf"; + uparams.benchmark_cmd[0] = "fill_buf"; ret = asprintf(&span_str, "%u", DEFAULT_SPAN); if (ret < 0) ksft_exit_fail_msg("Out of memory!\n"); - benchmark_cmd[1] = span_str; - benchmark_cmd[2] = "1"; - benchmark_cmd[3] = "0"; - benchmark_cmd[4] = "false"; - benchmark_cmd[5] = NULL; + uparams.benchmark_cmd[1] = span_str; + uparams.benchmark_cmd[2] = "1"; + uparams.benchmark_cmd[3] = "0"; + uparams.benchmark_cmd[4] = "false"; + uparams.benchmark_cmd[5] = NULL; } ksft_set_plan(tests ? : 4); if (mbm_test) - run_mbm_test(benchmark_cmd, cpu_no); + run_mbm_test(&uparams); if (mba_test) - run_mba_test(benchmark_cmd, cpu_no); + run_mba_test(&uparams); if (cmt_test) - run_cmt_test(benchmark_cmd, cpu_no); + run_cmt_test(&uparams); if (cat_test) - run_cat_test(cpu_no, no_of_bits); + run_cat_test(&uparams); free(span_str); ksft_finished(); diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c index 6574a13f3919..6d0a35e8bd02 100644 --- a/tools/testing/selftests/resctrl/resctrl_val.c +++ b/tools/testing/selftests/resctrl/resctrl_val.c @@ -593,8 +593,9 @@ static void initialize_llc_occu_resctrl(const char *ctrlgrp, const char *mongrp, set_cmt_path(ctrlgrp, mongrp, resource_id); } -static int -measure_vals(struct resctrl_val_param *param, unsigned long *bw_resc_start) +static int measure_vals(const struct user_params *uparams, + struct resctrl_val_param *param, + unsigned long *bw_resc_start) { unsigned long bw_resc, bw_resc_end; float bw_imc; @@ -607,7 +608,7 @@ measure_vals(struct resctrl_val_param *param, unsigned long *bw_resc_start) * Compare the two values to validate resctrl value. * It takes 1sec to measure the data. */ - ret = get_mem_bw_imc(param->cpu_no, param->bw_report, &bw_imc); + ret = get_mem_bw_imc(uparams->cpu, param->bw_report, &bw_imc); if (ret < 0) return ret; @@ -683,12 +684,14 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext) /* * resctrl_val: execute benchmark and measure memory bandwidth on * the benchmark + * @uparams: user supplied parameters * @benchmark_cmd: benchmark command and its arguments * @param: parameters passed to resctrl_val() * * Return: 0 when the test was run, < 0 on error. */ -int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param) +int resctrl_val(const struct user_params *uparams, const char * const *benchmark_cmd, + struct resctrl_val_param *param) { char *resctrl_val = param->resctrl_val; unsigned long bw_resc_start = 0; @@ -777,7 +780,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par value.sival_ptr = (void *)benchmark_cmd; /* Taskset benchmark to specified cpu */ - ret = taskset_benchmark(bm_pid, param->cpu_no, NULL); + ret = taskset_benchmark(bm_pid, uparams->cpu, NULL); if (ret) goto out; @@ -794,10 +797,10 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par goto out; initialize_mem_bw_resctrl(param->ctrlgrp, param->mongrp, - param->cpu_no, resctrl_val); + uparams->cpu, resctrl_val); } else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) initialize_llc_occu_resctrl(param->ctrlgrp, param->mongrp, - param->cpu_no, resctrl_val); + uparams->cpu, resctrl_val); /* Parent waits for child to be ready. */ close(pipefd[1]); @@ -823,7 +826,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par /* Test runs until the callback setup() tells the test to stop. */ while (1) { - ret = param->setup(param); + ret = param->setup(uparams, param); if (ret == END_OF_TESTS) { ret = 0; break; @@ -833,7 +836,7 @@ int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *par if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) || !strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) { - ret = measure_vals(param, &bw_resc_start); + ret = measure_vals(uparams, param, &bw_resc_start); if (ret) break; } else if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) { -- cgit v1.2.3-70-g09d2 From c603ff5bb830b8c22dae56ca3ca5ceb5c103525b Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:05:11 +0200 Subject: selftests/resctrl: Introduce generalized test framework MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Each test currently has a "run test" function in per test file and another resctrl_tests.c. The functions in resctrl_tests.c are almost identical. Generalize the one in resctrl_tests.c such that it can be shared between all of the tests. It makes adding new tests easier and removes the per test if () forests. Also add comment to CPU vendor IDs that they must be defined as bits for a bitmask. Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cat_test.c | 18 ++- tools/testing/selftests/resctrl/cmt_test.c | 17 ++- tools/testing/selftests/resctrl/mba_test.c | 16 ++- tools/testing/selftests/resctrl/mbm_test.c | 18 ++- tools/testing/selftests/resctrl/resctrl.h | 35 +++++- tools/testing/selftests/resctrl/resctrl_tests.c | 160 ++++++++---------------- tools/testing/selftests/resctrl/resctrlfs.c | 5 + 7 files changed, 148 insertions(+), 121 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index 272132ff7337..a9b4583620d0 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -231,7 +231,7 @@ reset_affinity: return ret; } -int cat_perf_miss_val(const struct user_params *uparams, char *cache_type) +static int cat_run_test(const struct resctrl_test *test, const struct user_params *uparams) { unsigned long long_mask, start_mask, full_cache_mask; unsigned long cache_total_size = 0; @@ -241,16 +241,16 @@ int cat_perf_miss_val(const struct user_params *uparams, char *cache_type) size_t span; int ret; - ret = get_full_cbm(cache_type, &full_cache_mask); + ret = get_full_cbm(test->resource, &full_cache_mask); if (ret) return ret; /* Get the largest contiguous exclusive portion of the cache */ - ret = get_mask_no_shareable(cache_type, &long_mask); + ret = get_mask_no_shareable(test->resource, &long_mask); if (ret) return ret; /* Get L3/L2 cache size */ - ret = get_cache_size(uparams->cpu, cache_type, &cache_total_size); + ret = get_cache_size(uparams->cpu, test->resource, &cache_total_size); if (ret) return ret; ksft_print_msg("Cache size :%lu\n", cache_total_size); @@ -283,9 +283,17 @@ int cat_perf_miss_val(const struct user_params *uparams, char *cache_type) if (ret) goto out; - ret = check_results(¶m, cache_type, cache_total_size, full_cache_mask, start_mask); + ret = check_results(¶m, test->resource, + cache_total_size, full_cache_mask, start_mask); out: cat_test_cleanup(); return ret; } + +struct resctrl_test l3_cat_test = { + .name = "CAT", + .resource = "L3", + .feature_check = test_resource_feature_check, + .run_test = cat_run_test, +}; diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c index a5d0c0878c42..c01980039118 100644 --- a/tools/testing/selftests/resctrl/cmt_test.c +++ b/tools/testing/selftests/resctrl/cmt_test.c @@ -94,7 +94,7 @@ void cmt_test_cleanup(void) remove(RESULT_FILE_NAME); } -int cmt_resctrl_val(const struct user_params *uparams) +static int cmt_run_test(const struct resctrl_test *test, const struct user_params *uparams) { const char * const *cmd = uparams->benchmark_cmd; const char *new_cmd[BENCHMARK_ARGS]; @@ -155,6 +155,8 @@ int cmt_resctrl_val(const struct user_params *uparams) goto out; ret = check_results(¶m, span, n); + if (ret && (get_vendor() == ARCH_INTEL)) + ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); out: cmt_test_cleanup(); @@ -162,3 +164,16 @@ out: return ret; } + +static bool cmt_feature_check(const struct resctrl_test *test) +{ + return test_resource_feature_check(test) && + validate_resctrl_feature_request("L3_MON", "llc_occupancy"); +} + +struct resctrl_test cmt_test = { + .name = "CMT", + .resource = "L3", + .feature_check = cmt_feature_check, + .run_test = cmt_run_test, +}; diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c index 8e54bc508a75..c218af24f91d 100644 --- a/tools/testing/selftests/resctrl/mba_test.c +++ b/tools/testing/selftests/resctrl/mba_test.c @@ -141,7 +141,7 @@ void mba_test_cleanup(void) remove(RESULT_FILE_NAME); } -int mba_schemata_change(const struct user_params *uparams) +static int mba_run_test(const struct resctrl_test *test, const struct user_params *uparams) { struct resctrl_val_param param = { .resctrl_val = MBA_STR, @@ -166,3 +166,17 @@ out: return ret; } + +static bool mba_feature_check(const struct resctrl_test *test) +{ + return test_resource_feature_check(test) && + validate_resctrl_feature_request("L3_MON", "mbm_local_bytes"); +} + +struct resctrl_test mba_test = { + .name = "MBA", + .resource = "MB", + .vendor_specific = ARCH_INTEL, + .feature_check = mba_feature_check, + .run_test = mba_run_test, +}; diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c index ea951cfae5fe..919b10459c22 100644 --- a/tools/testing/selftests/resctrl/mbm_test.c +++ b/tools/testing/selftests/resctrl/mbm_test.c @@ -109,7 +109,7 @@ void mbm_test_cleanup(void) remove(RESULT_FILE_NAME); } -int mbm_bw_change(const struct user_params *uparams) +static int mbm_run_test(const struct resctrl_test *test, const struct user_params *uparams) { struct resctrl_val_param param = { .resctrl_val = MBM_STR, @@ -128,9 +128,25 @@ int mbm_bw_change(const struct user_params *uparams) goto out; ret = check_results(DEFAULT_SPAN); + if (ret && (get_vendor() == ARCH_INTEL)) + ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); out: mbm_test_cleanup(); return ret; } + +static bool mbm_feature_check(const struct resctrl_test *test) +{ + return validate_resctrl_feature_request("L3_MON", "mbm_total_bytes") && + validate_resctrl_feature_request("L3_MON", "mbm_local_bytes"); +} + +struct resctrl_test mbm_test = { + .name = "MBM", + .resource = "MB", + .vendor_specific = ARCH_INTEL, + .feature_check = mbm_feature_check, + .run_test = mbm_run_test, +}; diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 199ba91a78f7..1168364b4cc2 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -28,6 +28,12 @@ #define PHYS_ID_PATH "/sys/devices/system/cpu/cpu" #define INFO_PATH "/sys/fs/resctrl/info" +/* + * CPU vendor IDs + * + * Define as bits because they're used for vendor_specific bitmask in + * the struct resctrl_test. + */ #define ARCH_INTEL 1 #define ARCH_AMD 2 @@ -56,6 +62,25 @@ struct user_params { const char *benchmark_cmd[BENCHMARK_ARGS]; }; +/* + * resctrl_test: resctrl test definition + * @name: Test name + * @resource: Resource to test (e.g., MB, L3, L2, etc.) + * @vendor_specific: Bitmask for vendor-specific tests (can be 0 for universal tests) + * @disabled: Test is disabled + * @feature_check: Callback to check required resctrl features + * @run_test: Callback to run the test + */ +struct resctrl_test { + const char *name; + const char *resource; + unsigned int vendor_specific; + bool disabled; + bool (*feature_check)(const struct resctrl_test *test); + int (*run_test)(const struct resctrl_test *test, + const struct user_params *uparams); +}; + /* * resctrl_val_param: resctrl test parameters * @resctrl_val: Resctrl feature (Eg: mbm, mba.. etc) @@ -108,6 +133,7 @@ int mount_resctrlfs(void); int umount_resctrlfs(void); int validate_bw_report_request(char *bw_report); bool validate_resctrl_feature_request(const char *resource, const char *feature); +bool test_resource_feature_check(const struct resctrl_test *test); char *fgrep(FILE *inf, const char *str); int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity); int taskset_restore(pid_t bm_pid, cpu_set_t *old_affinity); @@ -123,10 +149,8 @@ void fill_cache_read(unsigned char *buf, size_t buf_size, bool once); int run_fill_buf(size_t buf_size, int memflush, int op, bool once); int resctrl_val(const struct user_params *uparams, const char * const *benchmark_cmd, struct resctrl_val_param *param); -int mbm_bw_change(const struct user_params *uparams); void tests_cleanup(void); void mbm_test_cleanup(void); -int mba_schemata_change(const struct user_params *uparams); void mba_test_cleanup(void); unsigned long create_bit_mask(unsigned int start, unsigned int len); unsigned int count_contiguous_bits(unsigned long val, unsigned int *start); @@ -137,8 +161,6 @@ void ctrlc_handler(int signum, siginfo_t *info, void *ptr); int signal_handler_register(void); void signal_handler_unregister(void); void cat_test_cleanup(void); -int cat_perf_miss_val(const struct user_params *uparams, char *cache_type); -int cmt_resctrl_val(const struct user_params *uparams); unsigned int count_bits(unsigned long n); void cmt_test_cleanup(void); @@ -175,4 +197,9 @@ static inline unsigned long cache_portion_size(unsigned long cache_size, return cache_size * count_bits(portion_mask) / bits; } +extern struct resctrl_test mbm_test; +extern struct resctrl_test mba_test; +extern struct resctrl_test cmt_test; +extern struct resctrl_test l3_cat_test; + #endif /* RESCTRL_H */ diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c index 3059a124ac59..75fc49ba3efb 100644 --- a/tools/testing/selftests/resctrl/resctrl_tests.c +++ b/tools/testing/selftests/resctrl/resctrl_tests.c @@ -14,6 +14,13 @@ static volatile int sink_target; volatile int *value_sink = &sink_target; +static struct resctrl_test *resctrl_tests[] = { + &mbm_test, + &mba_test, + &cmt_test, + &l3_cat_test, +}; + static int detect_vendor(void) { FILE *inf = fopen("/proc/cpuinfo", "r"); @@ -53,11 +60,16 @@ int get_vendor(void) static void cmd_help(void) { + int i; + printf("usage: resctrl_tests [-h] [-t test list] [-n no_of_bits] [-b benchmark_cmd [option]...]\n"); printf("\t-b benchmark_cmd [option]...: run specified benchmark for MBM, MBA and CMT\n"); printf("\t default benchmark is builtin fill_buf\n"); printf("\t-t test list: run tests specified in the test list, "); printf("e.g. -t mbm,mba,cmt,cat\n"); + printf("\t\tSupported tests:\n"); + for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) + printf("\t\t\t%s\n", resctrl_tests[i]->name); printf("\t-n no_of_bits: run cache tests using specified no of bits in cache bit mask\n"); printf("\t-p cpu_no: specify CPU number to run the test. 1 is default\n"); printf("\t-h: help\n"); @@ -96,102 +108,41 @@ static void test_cleanup(void) signal_handler_unregister(); } -static void run_mbm_test(const struct user_params *uparams) +static bool test_vendor_specific_check(const struct resctrl_test *test) { - int res; - - ksft_print_msg("Starting MBM BW change ...\n"); - - if (test_prepare()) { - ksft_exit_fail_msg("Abnormal failure when preparing for the test\n"); - return; - } - - if (!validate_resctrl_feature_request("L3_MON", "mbm_total_bytes") || - !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") || - (get_vendor() != ARCH_INTEL)) { - ksft_test_result_skip("Hardware does not support MBM or MBM is disabled\n"); - goto cleanup; - } - - res = mbm_bw_change(uparams); - ksft_test_result(!res, "MBM: bw change\n"); - if ((get_vendor() == ARCH_INTEL) && res) - ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); + if (!test->vendor_specific) + return true; -cleanup: - test_cleanup(); + return get_vendor() & test->vendor_specific; } -static void run_mba_test(const struct user_params *uparams) +static void run_single_test(const struct resctrl_test *test, const struct user_params *uparams) { - int res; - - ksft_print_msg("Starting MBA Schemata change ...\n"); + int ret; - if (test_prepare()) { - ksft_exit_fail_msg("Abnormal failure when preparing for the test\n"); + if (test->disabled) return; - } - if (!validate_resctrl_feature_request("MB", NULL) || - !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") || - (get_vendor() != ARCH_INTEL)) { - ksft_test_result_skip("Hardware does not support MBA or MBA is disabled\n"); - goto cleanup; - } - - res = mba_schemata_change(uparams); - ksft_test_result(!res, "MBA: schemata change\n"); - -cleanup: - test_cleanup(); -} - -static void run_cmt_test(const struct user_params *uparams) -{ - int res; - - ksft_print_msg("Starting CMT test ...\n"); - - if (test_prepare()) { - ksft_exit_fail_msg("Abnormal failure when preparing for the test\n"); + if (!test_vendor_specific_check(test)) { + ksft_test_result_skip("Hardware does not support %s\n", test->name); return; } - if (!validate_resctrl_feature_request("L3_MON", "llc_occupancy") || - !validate_resctrl_feature_request("L3", NULL)) { - ksft_test_result_skip("Hardware does not support CMT or CMT is disabled\n"); - goto cleanup; - } - - res = cmt_resctrl_val(uparams); - ksft_test_result(!res, "CMT: test\n"); - if ((get_vendor() == ARCH_INTEL) && res) - ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); - -cleanup: - test_cleanup(); -} - -static void run_cat_test(const struct user_params *uparams) -{ - int res; - - ksft_print_msg("Starting CAT test ...\n"); + ksft_print_msg("Starting %s test ...\n", test->name); if (test_prepare()) { ksft_exit_fail_msg("Abnormal failure when preparing for the test\n"); return; } - if (!validate_resctrl_feature_request("L3", NULL)) { - ksft_test_result_skip("Hardware does not support CAT or CAT is disabled\n"); + if (!test->feature_check(test)) { + ksft_test_result_skip("Hardware does not support %s or %s is disabled\n", + test->name, test->name); goto cleanup; } - res = cat_perf_miss_val(uparams, "L3"); - ksft_test_result(!res, "CAT: test\n"); + ret = test->run_test(test, uparams); + ksft_test_result(!ret, "%s: test\n", test->name); cleanup: test_cleanup(); @@ -207,11 +158,10 @@ static void init_user_params(struct user_params *uparams) int main(int argc, char **argv) { - bool mbm_test = true, mba_test = true, cmt_test = true; + int tests = ARRAY_SIZE(resctrl_tests); + bool test_param_seen = false; struct user_params uparams; char *span_str = NULL; - bool cat_test = true; - int tests = 0; int ret, c, i; init_user_params(&uparams); @@ -239,25 +189,26 @@ int main(int argc, char **argv) case 't': token = strtok(optarg, ","); - mbm_test = false; - mba_test = false; - cmt_test = false; - cat_test = false; + if (!test_param_seen) { + for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) + resctrl_tests[i]->disabled = true; + tests = 0; + test_param_seen = true; + } while (token) { - if (!strncmp(token, MBM_STR, sizeof(MBM_STR))) { - mbm_test = true; - tests++; - } else if (!strncmp(token, MBA_STR, sizeof(MBA_STR))) { - mba_test = true; - tests++; - } else if (!strncmp(token, CMT_STR, sizeof(CMT_STR))) { - cmt_test = true; - tests++; - } else if (!strncmp(token, CAT_STR, sizeof(CAT_STR))) { - cat_test = true; - tests++; - } else { - printf("invalid argument\n"); + bool found = false; + + for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) { + if (!strcasecmp(token, resctrl_tests[i]->name)) { + if (resctrl_tests[i]->disabled) + tests++; + resctrl_tests[i]->disabled = false; + found = true; + } + } + + if (!found) { + printf("invalid test: %s\n", token); return -1; } @@ -317,19 +268,10 @@ last_arg: uparams.benchmark_cmd[5] = NULL; } - ksft_set_plan(tests ? : 4); - - if (mbm_test) - run_mbm_test(&uparams); - - if (mba_test) - run_mba_test(&uparams); - - if (cmt_test) - run_cmt_test(&uparams); + ksft_set_plan(tests); - if (cat_test) - run_cat_test(&uparams); + for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) + run_single_test(resctrl_tests[i], &uparams); free(span_str); ksft_finished(); diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index 1bcb9aa96cc2..140f65467ddb 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -706,6 +706,11 @@ bool validate_resctrl_feature_request(const char *resource, const char *feature) return !!res; } +bool test_resource_feature_check(const struct resctrl_test *test) +{ + return validate_resctrl_feature_request(test->resource, NULL); +} + int filter_dmesg(void) { char line[1024]; -- cgit v1.2.3-70-g09d2 From ca1608875ae21bb40a7731b81bc0e2c95622d502 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:05:12 +0200 Subject: selftests/resctrl: Pass write_schemata() resource instead of test name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit write_schemata() takes the test name as an argument and determines the relevant resource based on the test name. Such mapping from name to resource does not really belong to resctrlfs.c that should provide only generic, test-independent functions. Pass the resource stored in the test information structure to write_schemata() instead of the test name. The new API is also more flexible as it enables to use write_schemata() for more than one resource within a test. While touching the sprintf(), move the unnecessary %c that is always '=' directly into the format string. Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cat_test.c | 11 +++++++---- tools/testing/selftests/resctrl/cmt_test.c | 6 ++++-- tools/testing/selftests/resctrl/mba_test.c | 9 +++++---- tools/testing/selftests/resctrl/mbm_test.c | 9 +++++---- tools/testing/selftests/resctrl/resctrl.h | 10 ++++++---- tools/testing/selftests/resctrl/resctrl_val.c | 7 +++++-- tools/testing/selftests/resctrl/resctrlfs.c | 24 ++++++------------------ 7 files changed, 38 insertions(+), 38 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index a9b4583620d0..24af8310288a 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -135,6 +135,7 @@ void cat_test_cleanup(void) /* * cat_test - Execute CAT benchmark and measure cache misses + * @test: Test information structure * @uparams: User supplied parameters * @param: Parameters passed to cat_test() * @span: Buffer size for the benchmark @@ -152,7 +153,9 @@ void cat_test_cleanup(void) * * Return: 0 when the test was run, < 0 on error. */ -static int cat_test(const struct user_params *uparams, struct resctrl_val_param *param, +static int cat_test(const struct resctrl_test *test, + const struct user_params *uparams, + struct resctrl_val_param *param, size_t span, unsigned long current_mask) { char *resctrl_val = param->resctrl_val; @@ -196,11 +199,11 @@ static int cat_test(const struct user_params *uparams, struct resctrl_val_param while (current_mask) { snprintf(schemata, sizeof(schemata), "%lx", param->mask & ~current_mask); - ret = write_schemata("", schemata, uparams->cpu, param->resctrl_val); + ret = write_schemata("", schemata, uparams->cpu, test->resource); if (ret) goto free_buf; snprintf(schemata, sizeof(schemata), "%lx", current_mask); - ret = write_schemata(param->ctrlgrp, schemata, uparams->cpu, param->resctrl_val); + ret = write_schemata(param->ctrlgrp, schemata, uparams->cpu, test->resource); if (ret) goto free_buf; @@ -279,7 +282,7 @@ static int cat_run_test(const struct resctrl_test *test, const struct user_param remove(param.filename); - ret = cat_test(uparams, ¶m, span, start_mask); + ret = cat_test(test, uparams, ¶m, span, start_mask); if (ret) goto out; diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c index c01980039118..dd5ca343c469 100644 --- a/tools/testing/selftests/resctrl/cmt_test.c +++ b/tools/testing/selftests/resctrl/cmt_test.c @@ -16,7 +16,9 @@ #define MAX_DIFF 2000000 #define MAX_DIFF_PERCENT 15 -static int cmt_setup(const struct user_params *uparams, struct resctrl_val_param *p) +static int cmt_setup(const struct resctrl_test *test, + const struct user_params *uparams, + struct resctrl_val_param *p) { /* Run NUM_OF_RUNS times */ if (p->num_of_runs >= NUM_OF_RUNS) @@ -150,7 +152,7 @@ static int cmt_run_test(const struct resctrl_test *test, const struct user_param remove(RESULT_FILE_NAME); - ret = resctrl_val(uparams, cmd, ¶m); + ret = resctrl_val(test, uparams, cmd, ¶m); if (ret) goto out; diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c index c218af24f91d..da256d2dbe5c 100644 --- a/tools/testing/selftests/resctrl/mba_test.c +++ b/tools/testing/selftests/resctrl/mba_test.c @@ -22,7 +22,9 @@ * con_mon grp, mon_grp in resctrl FS. * For each allocation, run 5 times in order to get average values. */ -static int mba_setup(const struct user_params *uparams, struct resctrl_val_param *p) +static int mba_setup(const struct resctrl_test *test, + const struct user_params *uparams, + struct resctrl_val_param *p) { static int runs_per_allocation, allocation = 100; char allocation_str[64]; @@ -40,8 +42,7 @@ static int mba_setup(const struct user_params *uparams, struct resctrl_val_param sprintf(allocation_str, "%d", allocation); - ret = write_schemata(p->ctrlgrp, allocation_str, uparams->cpu, - p->resctrl_val); + ret = write_schemata(p->ctrlgrp, allocation_str, uparams->cpu, test->resource); if (ret < 0) return ret; @@ -155,7 +156,7 @@ static int mba_run_test(const struct resctrl_test *test, const struct user_param remove(RESULT_FILE_NAME); - ret = resctrl_val(uparams, uparams->benchmark_cmd, ¶m); + ret = resctrl_val(test, uparams, uparams->benchmark_cmd, ¶m); if (ret) goto out; diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c index 919b10459c22..34879e7b71a0 100644 --- a/tools/testing/selftests/resctrl/mbm_test.c +++ b/tools/testing/selftests/resctrl/mbm_test.c @@ -86,7 +86,9 @@ static int check_results(size_t span) return ret; } -static int mbm_setup(const struct user_params *uparams, struct resctrl_val_param *p) +static int mbm_setup(const struct resctrl_test *test, + const struct user_params *uparams, + struct resctrl_val_param *p) { int ret = 0; @@ -96,8 +98,7 @@ static int mbm_setup(const struct user_params *uparams, struct resctrl_val_param /* Set up shemata with 100% allocation on the first run. */ if (p->num_of_runs == 0 && validate_resctrl_feature_request("MB", NULL)) - ret = write_schemata(p->ctrlgrp, "100", uparams->cpu, - p->resctrl_val); + ret = write_schemata(p->ctrlgrp, "100", uparams->cpu, test->resource); p->num_of_runs++; @@ -123,7 +124,7 @@ static int mbm_run_test(const struct resctrl_test *test, const struct user_param remove(RESULT_FILE_NAME); - ret = resctrl_val(uparams, uparams->benchmark_cmd, ¶m); + ret = resctrl_val(test, uparams, uparams->benchmark_cmd, ¶m); if (ret) goto out; diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 1168364b4cc2..97d16daf8190 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -98,7 +98,8 @@ struct resctrl_val_param { char *bw_report; unsigned long mask; int num_of_runs; - int (*setup)(const struct user_params *uparams, + int (*setup)(const struct resctrl_test *test, + const struct user_params *uparams, struct resctrl_val_param *param); }; @@ -137,8 +138,7 @@ bool test_resource_feature_check(const struct resctrl_test *test); char *fgrep(FILE *inf, const char *str); int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity); int taskset_restore(pid_t bm_pid, cpu_set_t *old_affinity); -int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, - char *resctrl_val); +int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resource); int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp, char *resctrl_val); int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu, @@ -147,7 +147,9 @@ unsigned char *alloc_buffer(size_t buf_size, int memflush); void mem_flush(unsigned char *buf, size_t buf_size); void fill_cache_read(unsigned char *buf, size_t buf_size, bool once); int run_fill_buf(size_t buf_size, int memflush, int op, bool once); -int resctrl_val(const struct user_params *uparams, const char * const *benchmark_cmd, +int resctrl_val(const struct resctrl_test *test, + const struct user_params *uparams, + const char * const *benchmark_cmd, struct resctrl_val_param *param); void tests_cleanup(void); void mbm_test_cleanup(void); diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c index 6d0a35e8bd02..16ad91ccbcd3 100644 --- a/tools/testing/selftests/resctrl/resctrl_val.c +++ b/tools/testing/selftests/resctrl/resctrl_val.c @@ -684,13 +684,16 @@ static void run_benchmark(int signum, siginfo_t *info, void *ucontext) /* * resctrl_val: execute benchmark and measure memory bandwidth on * the benchmark + * @test: test information structure * @uparams: user supplied parameters * @benchmark_cmd: benchmark command and its arguments * @param: parameters passed to resctrl_val() * * Return: 0 when the test was run, < 0 on error. */ -int resctrl_val(const struct user_params *uparams, const char * const *benchmark_cmd, +int resctrl_val(const struct resctrl_test *test, + const struct user_params *uparams, + const char * const *benchmark_cmd, struct resctrl_val_param *param) { char *resctrl_val = param->resctrl_val; @@ -826,7 +829,7 @@ int resctrl_val(const struct user_params *uparams, const char * const *benchmark /* Test runs until the callback setup() tells the test to stop. */ while (1) { - ret = param->setup(uparams, param); + ret = param->setup(test, uparams, param); if (ret == END_OF_TESTS) { ret = 0; break; diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index 140f65467ddb..fed6741edc5f 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -529,23 +529,17 @@ out: * @ctrlgrp: Name of the con_mon grp * @schemata: Schemata that should be updated to * @cpu_no: CPU number that the benchmark PID is binded to - * @resctrl_val: Resctrl feature (Eg: mbm, mba.. etc) + * @resource: Resctrl resource (Eg: MB, L3, L2, etc.) * - * Update schemata of a con_mon grp *only* if requested resctrl feature is + * Update schemata of a con_mon grp *only* if requested resctrl resource is * allocation type * * Return: 0 on success, < 0 on error. */ -int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val) +int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resource) { char controlgroup[1024], reason[128], schema[1024] = {}; - int resource_id, fd, schema_len = -1, ret = 0; - - if (strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) && - strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) && - strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR)) && - strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) - return -ENOENT; + int resource_id, fd, schema_len, ret = 0; if (!schemata) { ksft_print_msg("Skipping empty schemata update\n"); @@ -565,14 +559,8 @@ int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, char *resctrl_val) else sprintf(controlgroup, "%s/schemata", RESCTRL_PATH); - if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR)) || - !strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) - schema_len = snprintf(schema, sizeof(schema), "%s%d%c%s\n", - "L3:", resource_id, '=', schemata); - if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR)) || - !strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) - schema_len = snprintf(schema, sizeof(schema), "%s%d%c%s\n", - "MB:", resource_id, '=', schemata); + schema_len = snprintf(schema, sizeof(schema), "%s:%d=%s\n", + resource, resource_id, schemata); if (schema_len < 0 || schema_len >= sizeof(schema)) { snprintf(reason, sizeof(reason), "snprintf() failed with return value : %d", schema_len); -- cgit v1.2.3-70-g09d2 From e73dda7ffd858a58ddeb9c53603ae14f2af8927c Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:05:13 +0200 Subject: selftests/resctrl: Add helper to convert L2/3 to integer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit "L2"/"L3" conversion to integer is embedded into get_cache_size() which prevents reuse. Create a helper for the cache string to integer conversion to make it reusable. Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/resctrlfs.c | 28 ++++++++++++++++++++-------- 1 file changed, 20 insertions(+), 8 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index fed6741edc5f..eab928c46f98 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -94,6 +94,23 @@ int umount_resctrlfs(void) return 0; } +/* + * get_cache_level - Convert cache level from string to integer + * @cache_type: Cache level as string + * + * Return: cache level as integer or -1 if @cache_type is invalid. + */ +static int get_cache_level(const char *cache_type) +{ + if (!strcmp(cache_type, "L3")) + return 3; + if (!strcmp(cache_type, "L2")) + return 2; + + ksft_print_msg("Invalid cache level\n"); + return -1; +} + /* * get_resource_id - Get socket number/l3 id for a specified CPU * @cpu_no: CPU number @@ -144,14 +161,9 @@ int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size int length, i, cache_num; FILE *fp; - if (!strcmp(cache_type, "L3")) { - cache_num = 3; - } else if (!strcmp(cache_type, "L2")) { - cache_num = 2; - } else { - ksft_print_msg("Invalid cache level\n"); - return -1; - } + cache_num = get_cache_level(cache_type); + if (cache_num < 0) + return cache_num; sprintf(cache_path, "/sys/bus/cpu/devices/cpu%d/cache/index%d/size", cpu_no, cache_num); -- cgit v1.2.3-70-g09d2 From 6874f6ed92df1e95ff815692b6bf6aa98e4c925b Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:05:14 +0200 Subject: selftests/resctrl: Rename resource ID to domain ID MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Kernel-side calls the instances of a resource domains. Change the resource_id naming in the selftest code to domain_id to match the kernel side better. Suggested-by: Maciej Wieczór-Retman Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/resctrl.h | 2 +- tools/testing/selftests/resctrl/resctrl_val.c | 30 +++++++++++++-------------- tools/testing/selftests/resctrl/resctrlfs.c | 18 ++++++++-------- 3 files changed, 25 insertions(+), 25 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 97d16daf8190..d4eef20723fc 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -129,7 +129,7 @@ extern char llc_occup_path[1024]; int get_vendor(void); bool check_resctrlfs_support(void); int filter_dmesg(void); -int get_resource_id(int cpu_no, int *resource_id); +int get_domain_id(int cpu_no, int *domain_id); int mount_resctrlfs(void); int umount_resctrlfs(void); int validate_bw_report_request(char *bw_report); diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c index 16ad91ccbcd3..631e5f055694 100644 --- a/tools/testing/selftests/resctrl/resctrl_val.c +++ b/tools/testing/selftests/resctrl/resctrl_val.c @@ -387,20 +387,20 @@ static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc) return 0; } -void set_mbm_path(const char *ctrlgrp, const char *mongrp, int resource_id) +void set_mbm_path(const char *ctrlgrp, const char *mongrp, int domain_id) { if (ctrlgrp && mongrp) sprintf(mbm_total_path, CON_MON_MBM_LOCAL_BYTES_PATH, - RESCTRL_PATH, ctrlgrp, mongrp, resource_id); + RESCTRL_PATH, ctrlgrp, mongrp, domain_id); else if (!ctrlgrp && mongrp) sprintf(mbm_total_path, MON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH, - mongrp, resource_id); + mongrp, domain_id); else if (ctrlgrp && !mongrp) sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH, RESCTRL_PATH, - ctrlgrp, resource_id); + ctrlgrp, domain_id); else if (!ctrlgrp && !mongrp) sprintf(mbm_total_path, MBM_LOCAL_BYTES_PATH, RESCTRL_PATH, - resource_id); + domain_id); } /* @@ -413,23 +413,23 @@ void set_mbm_path(const char *ctrlgrp, const char *mongrp, int resource_id) static void initialize_mem_bw_resctrl(const char *ctrlgrp, const char *mongrp, int cpu_no, char *resctrl_val) { - int resource_id; + int domain_id; - if (get_resource_id(cpu_no, &resource_id) < 0) { - ksft_print_msg("Could not get resource_id\n"); + if (get_domain_id(cpu_no, &domain_id) < 0) { + ksft_print_msg("Could not get domain ID\n"); return; } if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) - set_mbm_path(ctrlgrp, mongrp, resource_id); + set_mbm_path(ctrlgrp, mongrp, domain_id); if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) { if (ctrlgrp) sprintf(mbm_total_path, CON_MBM_LOCAL_BYTES_PATH, - RESCTRL_PATH, ctrlgrp, resource_id); + RESCTRL_PATH, ctrlgrp, domain_id); else sprintf(mbm_total_path, MBM_LOCAL_BYTES_PATH, - RESCTRL_PATH, resource_id); + RESCTRL_PATH, domain_id); } } @@ -582,15 +582,15 @@ static void set_cmt_path(const char *ctrlgrp, const char *mongrp, char sock_num) static void initialize_llc_occu_resctrl(const char *ctrlgrp, const char *mongrp, int cpu_no, char *resctrl_val) { - int resource_id; + int domain_id; - if (get_resource_id(cpu_no, &resource_id) < 0) { - ksft_print_msg("Could not get resource_id\n"); + if (get_domain_id(cpu_no, &domain_id) < 0) { + ksft_print_msg("Could not get domain ID\n"); return; } if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) - set_cmt_path(ctrlgrp, mongrp, resource_id); + set_cmt_path(ctrlgrp, mongrp, domain_id); } static int measure_vals(const struct user_params *uparams, diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index eab928c46f98..f29dc65d8b30 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -112,13 +112,13 @@ static int get_cache_level(const char *cache_type) } /* - * get_resource_id - Get socket number/l3 id for a specified CPU + * get_domain_id - Get resctrl domain ID for a specified CPU * @cpu_no: CPU number - * @resource_id: Socket number or l3_id + * @domain_id: domain ID (cache ID; for MB, L3 cache ID) * * Return: >= 0 on success, < 0 on failure. */ -int get_resource_id(int cpu_no, int *resource_id) +int get_domain_id(int cpu_no, int *domain_id) { char phys_pkg_path[1024]; FILE *fp; @@ -136,8 +136,8 @@ int get_resource_id(int cpu_no, int *resource_id) return -1; } - if (fscanf(fp, "%d", resource_id) <= 0) { - ksft_perror("Could not get socket number or l3 id"); + if (fscanf(fp, "%d", domain_id) <= 0) { + ksft_perror("Could not get domain ID"); fclose(fp); return -1; @@ -551,7 +551,7 @@ out: int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resource) { char controlgroup[1024], reason[128], schema[1024] = {}; - int resource_id, fd, schema_len, ret = 0; + int domain_id, fd, schema_len, ret = 0; if (!schemata) { ksft_print_msg("Skipping empty schemata update\n"); @@ -559,8 +559,8 @@ int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resour return -1; } - if (get_resource_id(cpu_no, &resource_id) < 0) { - sprintf(reason, "Failed to get resource id"); + if (get_domain_id(cpu_no, &domain_id) < 0) { + sprintf(reason, "Failed to get domain ID"); ret = -1; goto out; @@ -572,7 +572,7 @@ int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resour sprintf(controlgroup, "%s/schemata", RESCTRL_PATH); schema_len = snprintf(schema, sizeof(schema), "%s:%d=%s\n", - resource, resource_id, schemata); + resource, domain_id, schemata); if (schema_len < 0 || schema_len >= sizeof(schema)) { snprintf(reason, sizeof(reason), "snprintf() failed with return value : %d", schema_len); -- cgit v1.2.3-70-g09d2 From 345e8abe4c355bc24bab3f4a5634122e55be8665 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 15 Dec 2023 17:05:15 +0200 Subject: selftests/resctrl: Get domain id from cache id MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Domain id is acquired differently depending on CPU. AMD tests use id from L3 cache, whereas CPUs from other vendors base the id on topology package id. In order to support L2 CAT test, this has to be generalized. The driver side code seems to get the domain ids from cache ids so the approach used by the AMD branch seems to match the kernel-side code. It will also work with L2 domain IDs as long as the cache level is generalized. Using the topology id was always fragile due to mismatch with the kernel-side way to acquire the domain id. It got incorrect domain id, e.g., when Cluster-on-Die (CoD) is enabled for CPU (but CoD is not well suited for resctrl in the first place so it has not been a big issue if tests don't work correctly with it). Taking all the above into account, generalize acquiring the domain id by taking it from the cache id and do not hard-code the cache level. Signed-off-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/resctrl.h | 2 +- tools/testing/selftests/resctrl/resctrl_val.c | 4 ++-- tools/testing/selftests/resctrl/resctrlfs.c | 27 ++++++++++++++++++--------- 3 files changed, 21 insertions(+), 12 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index d4eef20723fc..c52eaf46f24d 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -129,7 +129,7 @@ extern char llc_occup_path[1024]; int get_vendor(void); bool check_resctrlfs_support(void); int filter_dmesg(void); -int get_domain_id(int cpu_no, int *domain_id); +int get_domain_id(const char *resource, int cpu_no, int *domain_id); int mount_resctrlfs(void); int umount_resctrlfs(void); int validate_bw_report_request(char *bw_report); diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c index 631e5f055694..5a49f07a6c85 100644 --- a/tools/testing/selftests/resctrl/resctrl_val.c +++ b/tools/testing/selftests/resctrl/resctrl_val.c @@ -415,7 +415,7 @@ static void initialize_mem_bw_resctrl(const char *ctrlgrp, const char *mongrp, { int domain_id; - if (get_domain_id(cpu_no, &domain_id) < 0) { + if (get_domain_id("MB", cpu_no, &domain_id) < 0) { ksft_print_msg("Could not get domain ID\n"); return; } @@ -584,7 +584,7 @@ static void initialize_llc_occu_resctrl(const char *ctrlgrp, const char *mongrp, { int domain_id; - if (get_domain_id(cpu_no, &domain_id) < 0) { + if (get_domain_id("L3", cpu_no, &domain_id) < 0) { ksft_print_msg("Could not get domain ID\n"); return; } diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index f29dc65d8b30..5750662cce57 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -111,28 +111,37 @@ static int get_cache_level(const char *cache_type) return -1; } +static int get_resource_cache_level(const char *resource) +{ + /* "MB" use L3 (LLC) as resource */ + if (!strcmp(resource, "MB")) + return 3; + return get_cache_level(resource); +} + /* * get_domain_id - Get resctrl domain ID for a specified CPU + * @resource: resource name * @cpu_no: CPU number * @domain_id: domain ID (cache ID; for MB, L3 cache ID) * * Return: >= 0 on success, < 0 on failure. */ -int get_domain_id(int cpu_no, int *domain_id) +int get_domain_id(const char *resource, int cpu_no, int *domain_id) { char phys_pkg_path[1024]; + int cache_num; FILE *fp; - if (get_vendor() == ARCH_AMD) - sprintf(phys_pkg_path, "%s%d/cache/index3/id", - PHYS_ID_PATH, cpu_no); - else - sprintf(phys_pkg_path, "%s%d/topology/physical_package_id", - PHYS_ID_PATH, cpu_no); + cache_num = get_resource_cache_level(resource); + if (cache_num < 0) + return cache_num; + + sprintf(phys_pkg_path, "%s%d/cache/index%d/id", PHYS_ID_PATH, cpu_no, cache_num); fp = fopen(phys_pkg_path, "r"); if (!fp) { - ksft_perror("Failed to open physical_package_id"); + ksft_perror("Failed to open cache id file"); return -1; } @@ -559,7 +568,7 @@ int write_schemata(char *ctrlgrp, char *schemata, int cpu_no, const char *resour return -1; } - if (get_domain_id(cpu_no, &domain_id) < 0) { + if (get_domain_id(resource, cpu_no, &domain_id) < 0) { sprintf(reason, "Failed to get domain ID"); ret = -1; -- cgit v1.2.3-70-g09d2 From f17d8a87ecb557bc6c9770751c3f0aaf10edbb98 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 13 Feb 2024 19:06:02 +0000 Subject: selftests: fuxex: Report a unique test name per run of futex_requeue_pi The futex_requeue_pi test program is run a number of times with different options to provide multiple test cases. Currently every time it runs it reports the result with a consistent string, meaning that automated systems parsing the TAP output from a test run have difficulty in distinguishing which test is which. The parameters used for the test are already logged as part of the test output, let's use the same format to roll them into the test name that we use with KTAP so that automated systems can follow the results of the individual cases that get run. Signed-off-by: Mark Brown Acked-by: Davidlohr Bueso Acked-by: Thomas Gleixner Signed-off-by: Shuah Khan --- tools/testing/selftests/futex/functional/futex_requeue_pi.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi.c b/tools/testing/selftests/futex/functional/futex_requeue_pi.c index 1ee5518ee6b7..7f3ca5c78df1 100644 --- a/tools/testing/selftests/futex/functional/futex_requeue_pi.c +++ b/tools/testing/selftests/futex/functional/futex_requeue_pi.c @@ -17,6 +17,8 @@ * *****************************************************************************/ +#define _GNU_SOURCE + #include #include #include @@ -358,6 +360,7 @@ out: int main(int argc, char *argv[]) { + const char *test_name; int c, ret; while ((c = getopt(argc, argv, "bchlot:v:")) != -1) { @@ -397,6 +400,14 @@ int main(int argc, char *argv[]) "\tArguments: broadcast=%d locked=%d owner=%d timeout=%ldns\n", broadcast, locked, owner, timeout_ns); + ret = asprintf(&test_name, + "%s broadcast=%d locked=%d owner=%d timeout=%ldns", + TEST_NAME, broadcast, locked, owner, timeout_ns); + if (ret < 0) { + ksft_print_msg("Failed to generate test name\n"); + test_name = TEST_NAME; + } + /* * FIXME: unit_test is obsolete now that we parse options and the * various style of runs are done by run.sh - simplify the code and move @@ -404,6 +415,6 @@ int main(int argc, char *argv[]) */ ret = unit_test(broadcast, locked, owner, timeout_ns); - print_result(TEST_NAME, ret); + print_result(test_name, ret); return ret; } -- cgit v1.2.3-70-g09d2 From 1901ae3cc9f8cbe78c3cdeec18cd54246ff11ca8 Mon Sep 17 00:00:00 2001 From: Kousik Sanagavarapu Date: Mon, 29 Jan 2024 21:58:07 +0530 Subject: selftest/ftrace: fix typo in ftracetest script Fix a typo in ftracetest script which is run when running the kselftests for ftrace. s/faii/fail Signed-off-by: Kousik Sanagavarapu Acked-by: Masami Hiramatsu (Google) Signed-off-by: Shuah Khan --- tools/testing/selftests/ftrace/ftracetest | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index c778d4dcc17e..25d4e0fca385 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -504,7 +504,7 @@ prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w` if [ "$KTAP" = "1" ]; then echo -n "# Totals:" echo -n " pass:"`echo $PASSED_CASES | wc -w` - echo -n " faii:"`echo $FAILED_CASES | wc -w` + echo -n " fail:"`echo $FAILED_CASES | wc -w` echo -n " xfail:"`echo $XFAILED_CASES | wc -w` echo -n " xpass:0" echo -n " skip:"`echo $UNTESTED_CASES $UNSUPPORTED_CASES | wc -w` -- cgit v1.2.3-70-g09d2 From 8cbf22b3dcf0c89d1df1a8e106295b349607eb5b Mon Sep 17 00:00:00 2001 From: Ali Zahraee Date: Wed, 31 Jan 2024 14:33:06 +0100 Subject: selftests: ftrace: fix typo in test description The typo in the description shows up in test logs and output. This patch submission is part of my application to the Linux Foundation mentorship program: Linux kernel Bug Fixing Spring Unpaid 2024. Signed-off-by: Ali Zahraee Acked-by: Masami Hiramatsu (Google) Signed-off-by: Shuah Khan --- tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc b/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc index add7d5bf585d..c45094d1e1d2 100644 --- a/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc +++ b/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc @@ -1,6 +1,6 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 -# description: Test file and directory owership changes for eventfs +# description: Test file and directory ownership changes for eventfs original_group=`stat -c "%g" .` original_owner=`stat -c "%u" .` -- cgit v1.2.3-70-g09d2 From 7c079e909b21f8f6e5d8e501c037752ff302a15e Mon Sep 17 00:00:00 2001 From: Laura Nao Date: Tue, 2 Jan 2024 15:15:28 +0100 Subject: selftests: Move KTAP bash helpers to selftests common folder MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move bash helpers for outputting in KTAP format to the common selftests folder. This allows kselftests other than the dt one to source the file and make use of the helper functions. Define pass, fail and skip codes in the same file too. Signed-off-by: Laura Nao Reviewed-by: Nícolas F. R. A. Prado Tested-by: Nícolas F. R. A. Prado Acked-by: Rob Herring Signed-off-by: Shuah Khan --- tools/testing/selftests/Makefile | 1 + tools/testing/selftests/dt/Makefile | 2 +- tools/testing/selftests/dt/ktap_helpers.sh | 70 -------------------- .../testing/selftests/dt/test_unprobed_devices.sh | 6 +- tools/testing/selftests/kselftest/ktap_helpers.sh | 76 ++++++++++++++++++++++ 5 files changed, 79 insertions(+), 76 deletions(-) delete mode 100644 tools/testing/selftests/dt/ktap_helpers.sh create mode 100644 tools/testing/selftests/kselftest/ktap_helpers.sh (limited to 'tools') diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 15b6a111c3be..c5b4574045b3 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -236,6 +236,7 @@ ifdef INSTALL_PATH install -m 744 kselftest/module.sh $(INSTALL_PATH)/kselftest/ install -m 744 kselftest/runner.sh $(INSTALL_PATH)/kselftest/ install -m 744 kselftest/prefix.pl $(INSTALL_PATH)/kselftest/ + install -m 744 kselftest/ktap_helpers.sh $(INSTALL_PATH)/kselftest/ install -m 744 run_kselftest.sh $(INSTALL_PATH)/ rm -f $(TEST_LIST) @ret=1; \ diff --git a/tools/testing/selftests/dt/Makefile b/tools/testing/selftests/dt/Makefile index 62dc00ee4978..2d33ee9e9b71 100644 --- a/tools/testing/selftests/dt/Makefile +++ b/tools/testing/selftests/dt/Makefile @@ -4,7 +4,7 @@ ifneq ($(PY3),) TEST_PROGS := test_unprobed_devices.sh TEST_GEN_FILES := compatible_list -TEST_FILES := compatible_ignore_list ktap_helpers.sh +TEST_FILES := compatible_ignore_list include ../lib.mk diff --git a/tools/testing/selftests/dt/ktap_helpers.sh b/tools/testing/selftests/dt/ktap_helpers.sh deleted file mode 100644 index 8dfae51bb4e2..000000000000 --- a/tools/testing/selftests/dt/ktap_helpers.sh +++ /dev/null @@ -1,70 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# Copyright (c) 2023 Collabora Ltd -# -# Helpers for outputting in KTAP format -# -KTAP_TESTNO=1 -KTAP_CNT_PASS=0 -KTAP_CNT_FAIL=0 -KTAP_CNT_SKIP=0 - -ktap_print_header() { - echo "TAP version 13" -} - -ktap_set_plan() { - num_tests="$1" - - echo "1..$num_tests" -} - -ktap_skip_all() { - echo -n "1..0 # SKIP " - echo $@ -} - -__ktap_test() { - result="$1" - description="$2" - directive="$3" # optional - - local directive_str= - [[ ! -z "$directive" ]] && directive_str="# $directive" - - echo $result $KTAP_TESTNO $description $directive_str - - KTAP_TESTNO=$((KTAP_TESTNO+1)) -} - -ktap_test_pass() { - description="$1" - - result="ok" - __ktap_test "$result" "$description" - - KTAP_CNT_PASS=$((KTAP_CNT_PASS+1)) -} - -ktap_test_skip() { - description="$1" - - result="ok" - directive="SKIP" - __ktap_test "$result" "$description" "$directive" - - KTAP_CNT_SKIP=$((KTAP_CNT_SKIP+1)) -} - -ktap_test_fail() { - description="$1" - - result="not ok" - __ktap_test "$result" "$description" - - KTAP_CNT_FAIL=$((KTAP_CNT_FAIL+1)) -} - -ktap_print_totals() { - echo "# Totals: pass:$KTAP_CNT_PASS fail:$KTAP_CNT_FAIL xfail:0 xpass:0 skip:$KTAP_CNT_SKIP error:0" -} diff --git a/tools/testing/selftests/dt/test_unprobed_devices.sh b/tools/testing/selftests/dt/test_unprobed_devices.sh index b07af2a4c4de..f2307ee443a6 100755 --- a/tools/testing/selftests/dt/test_unprobed_devices.sh +++ b/tools/testing/selftests/dt/test_unprobed_devices.sh @@ -15,16 +15,12 @@ DIR="$(dirname $(readlink -f "$0"))" -source "${DIR}"/ktap_helpers.sh +source "${DIR}"/../kselftest/ktap_helpers.sh PDT=/proc/device-tree/ COMPAT_LIST="${DIR}"/compatible_list IGNORE_LIST="${DIR}"/compatible_ignore_list -KSFT_PASS=0 -KSFT_FAIL=1 -KSFT_SKIP=4 - ktap_print_header if [[ ! -d "${PDT}" ]]; then diff --git a/tools/testing/selftests/kselftest/ktap_helpers.sh b/tools/testing/selftests/kselftest/ktap_helpers.sh new file mode 100644 index 000000000000..dd79d96f3b5a --- /dev/null +++ b/tools/testing/selftests/kselftest/ktap_helpers.sh @@ -0,0 +1,76 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2023 Collabora Ltd +# +# Helpers for outputting in KTAP format +# +KTAP_TESTNO=1 +KTAP_CNT_PASS=0 +KTAP_CNT_FAIL=0 +KTAP_CNT_SKIP=0 + +KSFT_PASS=0 +KSFT_FAIL=1 +KSFT_XFAIL=2 +KSFT_XPASS=3 +KSFT_SKIP=4 + +ktap_print_header() { + echo "TAP version 13" +} + +ktap_set_plan() { + num_tests="$1" + + echo "1..$num_tests" +} + +ktap_skip_all() { + echo -n "1..0 # SKIP " + echo $@ +} + +__ktap_test() { + result="$1" + description="$2" + directive="$3" # optional + + local directive_str= + [[ ! -z "$directive" ]] && directive_str="# $directive" + + echo $result $KTAP_TESTNO $description $directive_str + + KTAP_TESTNO=$((KTAP_TESTNO+1)) +} + +ktap_test_pass() { + description="$1" + + result="ok" + __ktap_test "$result" "$description" + + KTAP_CNT_PASS=$((KTAP_CNT_PASS+1)) +} + +ktap_test_skip() { + description="$1" + + result="ok" + directive="SKIP" + __ktap_test "$result" "$description" "$directive" + + KTAP_CNT_SKIP=$((KTAP_CNT_SKIP+1)) +} + +ktap_test_fail() { + description="$1" + + result="not ok" + __ktap_test "$result" "$description" + + KTAP_CNT_FAIL=$((KTAP_CNT_FAIL+1)) +} + +ktap_print_totals() { + echo "# Totals: pass:$KTAP_CNT_PASS fail:$KTAP_CNT_FAIL xfail:0 xpass:0 skip:$KTAP_CNT_SKIP error:0" +} -- cgit v1.2.3-70-g09d2 From 6934eea2690b3c8a95224f2d1dacc2f13d3bf4ce Mon Sep 17 00:00:00 2001 From: "Nícolas F. R. A. Prado" Date: Wed, 31 Jan 2024 17:02:40 -0500 Subject: selftests: ktap_helpers: Add helper to print diagnostic messages MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Similar to the C counterpart, add a helper to print a diagnostic message. Signed-off-by: Nícolas F. R. A. Prado Signed-off-by: Shuah Khan --- tools/testing/selftests/kselftest/ktap_helpers.sh | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'tools') diff --git a/tools/testing/selftests/kselftest/ktap_helpers.sh b/tools/testing/selftests/kselftest/ktap_helpers.sh index dd79d96f3b5a..ecc1413c22cd 100644 --- a/tools/testing/selftests/kselftest/ktap_helpers.sh +++ b/tools/testing/selftests/kselftest/ktap_helpers.sh @@ -19,6 +19,11 @@ ktap_print_header() { echo "TAP version 13" } +ktap_print_msg() +{ + echo "#" $@ +} + ktap_set_plan() { num_tests="$1" -- cgit v1.2.3-70-g09d2 From d90b7c705c5d9b5cb6b71b8aaa773c031084056c Mon Sep 17 00:00:00 2001 From: "Nícolas F. R. A. Prado" Date: Wed, 31 Jan 2024 17:02:41 -0500 Subject: selftests: ktap_helpers: Add helper to pass/fail test based on exit code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Similar to the C counterpart, add a helper function that runs a command and passes or fails the test based on the result. Signed-off-by: Nícolas F. R. A. Prado Signed-off-by: Shuah Khan --- tools/testing/selftests/kselftest/ktap_helpers.sh | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'tools') diff --git a/tools/testing/selftests/kselftest/ktap_helpers.sh b/tools/testing/selftests/kselftest/ktap_helpers.sh index ecc1413c22cd..29107924f5c2 100644 --- a/tools/testing/selftests/kselftest/ktap_helpers.sh +++ b/tools/testing/selftests/kselftest/ktap_helpers.sh @@ -76,6 +76,17 @@ ktap_test_fail() { KTAP_CNT_FAIL=$((KTAP_CNT_FAIL+1)) } +ktap_test_result() { + description="$1" + shift + + if $@; then + ktap_test_pass "$description" + else + ktap_test_fail "$description" + fi +} + ktap_print_totals() { echo "# Totals: pass:$KTAP_CNT_PASS fail:$KTAP_CNT_FAIL xfail:0 xpass:0 skip:$KTAP_CNT_SKIP error:0" } -- cgit v1.2.3-70-g09d2 From d63fde98b8929da625cc36c2f1143e837c0e6d10 Mon Sep 17 00:00:00 2001 From: "Nícolas F. R. A. Prado" Date: Wed, 31 Jan 2024 17:02:42 -0500 Subject: selftests: ktap_helpers: Add a helper to abort the test MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Similar to the C counterpart, add a helper function to abort the remainder of the test. Signed-off-by: Nícolas F. R. A. Prado Signed-off-by: Shuah Khan --- tools/testing/selftests/kselftest/ktap_helpers.sh | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'tools') diff --git a/tools/testing/selftests/kselftest/ktap_helpers.sh b/tools/testing/selftests/kselftest/ktap_helpers.sh index 29107924f5c2..87f93c6900c5 100644 --- a/tools/testing/selftests/kselftest/ktap_helpers.sh +++ b/tools/testing/selftests/kselftest/ktap_helpers.sh @@ -87,6 +87,13 @@ ktap_test_result() { fi } +ktap_exit_fail_msg() { + echo "Bail out! " $@ + ktap_print_totals + + exit "$KSFT_FAIL" +} + ktap_print_totals() { echo "# Totals: pass:$KTAP_CNT_PASS fail:$KTAP_CNT_FAIL xfail:0 xpass:0 skip:$KTAP_CNT_SKIP error:0" } -- cgit v1.2.3-70-g09d2 From 2dd0b5a8fcc4f6fef307c79a3ff1d91d9595004d Mon Sep 17 00:00:00 2001 From: "Nícolas F. R. A. Prado" Date: Wed, 31 Jan 2024 17:02:43 -0500 Subject: selftests: ktap_helpers: Add a helper to finish the test MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Similar to the C counterpart, keep track of the number of test cases in the test plan and add a helper function to be called at the end of the test to print the results and exit with the corresponding exit code. Signed-off-by: Nícolas F. R. A. Prado Signed-off-by: Shuah Khan --- tools/testing/selftests/kselftest/ktap_helpers.sh | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/kselftest/ktap_helpers.sh b/tools/testing/selftests/kselftest/ktap_helpers.sh index 87f93c6900c5..f2fbb914e058 100644 --- a/tools/testing/selftests/kselftest/ktap_helpers.sh +++ b/tools/testing/selftests/kselftest/ktap_helpers.sh @@ -15,6 +15,8 @@ KSFT_XFAIL=2 KSFT_XPASS=3 KSFT_SKIP=4 +KSFT_NUM_TESTS=0 + ktap_print_header() { echo "TAP version 13" } @@ -25,9 +27,9 @@ ktap_print_msg() } ktap_set_plan() { - num_tests="$1" + KSFT_NUM_TESTS="$1" - echo "1..$num_tests" + echo "1..$KSFT_NUM_TESTS" } ktap_skip_all() { @@ -94,6 +96,16 @@ ktap_exit_fail_msg() { exit "$KSFT_FAIL" } +ktap_finished() { + ktap_print_totals + + if [ $(("$KTAP_CNT_PASS" + "$KTAP_CNT_SKIP")) -eq "$KSFT_NUM_TESTS" ]; then + exit "$KSFT_PASS" + else + exit "$KSFT_FAIL" + fi +} + ktap_print_totals() { echo "# Totals: pass:$KTAP_CNT_PASS fail:$KTAP_CNT_FAIL xfail:0 xpass:0 skip:$KTAP_CNT_SKIP error:0" } -- cgit v1.2.3-70-g09d2 From 4a679c5afca027d7f4668f51693f7cce589038f5 Mon Sep 17 00:00:00 2001 From: "Nícolas F. R. A. Prado" Date: Wed, 31 Jan 2024 17:48:01 -0500 Subject: selftests: Add test to verify power supply properties MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a kselftest that verifies power supply properties from sysfs and uevent. It checks whether they are present, readable and return valid values. This initial set of properties is not comprehensive, but rather the ones that I was able to validate locally. Co-developed-by: Sebastian Reichel Signed-off-by: Sebastian Reichel Signed-off-by: Nícolas F. R. A. Prado Signed-off-by: Shuah Khan --- MAINTAINERS | 1 + tools/testing/selftests/Makefile | 1 + tools/testing/selftests/power_supply/Makefile | 4 + tools/testing/selftests/power_supply/helpers.sh | 178 +++++++++++++++++++++ .../power_supply/test_power_supply_properties.sh | 114 +++++++++++++ 5 files changed, 298 insertions(+) create mode 100644 tools/testing/selftests/power_supply/Makefile create mode 100644 tools/testing/selftests/power_supply/helpers.sh create mode 100755 tools/testing/selftests/power_supply/test_power_supply_properties.sh (limited to 'tools') diff --git a/MAINTAINERS b/MAINTAINERS index ad5bec15bf0f..f8f620746934 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17524,6 +17524,7 @@ F: Documentation/devicetree/bindings/power/supply/ F: drivers/power/supply/ F: include/linux/power/ F: include/linux/power_supply.h +F: tools/testing/selftests/power_supply/ POWERNV OPERATOR PANEL LCD DISPLAY DRIVER M: Suraj Jitindar Singh diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index c5b4574045b3..7e5960cda08c 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -67,6 +67,7 @@ TARGETS += nsfs TARGETS += perf_events TARGETS += pidfd TARGETS += pid_namespace +TARGETS += power_supply TARGETS += powerpc TARGETS += prctl TARGETS += proc diff --git a/tools/testing/selftests/power_supply/Makefile b/tools/testing/selftests/power_supply/Makefile new file mode 100644 index 000000000000..44f0658d3d2e --- /dev/null +++ b/tools/testing/selftests/power_supply/Makefile @@ -0,0 +1,4 @@ +TEST_PROGS := test_power_supply_properties.sh +TEST_FILES := helpers.sh + +include ../lib.mk diff --git a/tools/testing/selftests/power_supply/helpers.sh b/tools/testing/selftests/power_supply/helpers.sh new file mode 100644 index 000000000000..1ec90d7c9108 --- /dev/null +++ b/tools/testing/selftests/power_supply/helpers.sh @@ -0,0 +1,178 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2022, 2024 Collabora Ltd +SYSFS_SUPPLIES=/sys/class/power_supply + +calc() { + awk "BEGIN { print $* }"; +} + +test_sysfs_prop() { + PROP="$1" + VALUE="$2" # optional + + PROP_PATH="$SYSFS_SUPPLIES"/"$DEVNAME"/"$PROP" + TEST_NAME="$DEVNAME".sysfs."$PROP" + + if [ -z "$VALUE" ]; then + ktap_test_result "$TEST_NAME" [ -f "$PROP_PATH" ] + else + ktap_test_result "$TEST_NAME" grep -q "$VALUE" "$PROP_PATH" + fi +} + +to_human_readable_unit() { + VALUE="$1" + UNIT="$2" + + case "$VALUE" in + *[!0-9]* ) return ;; # Not a number + esac + + if [ "$UNIT" = "uA" ]; then + new_unit="mA" + div=1000 + elif [ "$UNIT" = "uV" ]; then + new_unit="V" + div=1000000 + elif [ "$UNIT" = "uAh" ]; then + new_unit="Ah" + div=1000000 + elif [ "$UNIT" = "uW" ]; then + new_unit="mW" + div=1000 + elif [ "$UNIT" = "uWh" ]; then + new_unit="Wh" + div=1000000 + else + return + fi + + value_converted=$(calc "$VALUE"/"$div") + echo "$value_converted" "$new_unit" +} + +_check_sysfs_prop_available() { + PROP=$1 + + PROP_PATH="$SYSFS_SUPPLIES"/"$DEVNAME"/"$PROP" + TEST_NAME="$DEVNAME".sysfs."$PROP" + + if [ ! -e "$PROP_PATH" ] ; then + ktap_test_skip "$TEST_NAME" + return 1 + fi + + if ! cat "$PROP_PATH" >/dev/null; then + ktap_print_msg "Failed to read" + ktap_test_fail "$TEST_NAME" + return 1 + fi + + return 0 +} + +test_sysfs_prop_optional() { + PROP=$1 + UNIT=$2 # optional + + TEST_NAME="$DEVNAME".sysfs."$PROP" + + _check_sysfs_prop_available "$PROP" || return + DATA=$(cat "$SYSFS_SUPPLIES"/"$DEVNAME"/"$PROP") + + ktap_print_msg "Reported: '$DATA' $UNIT ($(to_human_readable_unit "$DATA" "$UNIT"))" + ktap_test_pass "$TEST_NAME" +} + +test_sysfs_prop_optional_range() { + PROP=$1 + MIN=$2 + MAX=$3 + UNIT=$4 # optional + + TEST_NAME="$DEVNAME".sysfs."$PROP" + + _check_sysfs_prop_available "$PROP" || return + DATA=$(cat "$SYSFS_SUPPLIES"/"$DEVNAME"/"$PROP") + + if [ "$DATA" -lt "$MIN" ] || [ "$DATA" -gt "$MAX" ]; then + ktap_print_msg "'$DATA' is out of range (min=$MIN, max=$MAX)" + ktap_test_fail "$TEST_NAME" + else + ktap_print_msg "Reported: '$DATA' $UNIT ($(to_human_readable_unit "$DATA" "$UNIT"))" + ktap_test_pass "$TEST_NAME" + fi +} + +test_sysfs_prop_optional_list() { + PROP=$1 + LIST=$2 + + TEST_NAME="$DEVNAME".sysfs."$PROP" + + _check_sysfs_prop_available "$PROP" || return + DATA=$(cat "$SYSFS_SUPPLIES"/"$DEVNAME"/"$PROP") + + valid=0 + + OLDIFS=$IFS + IFS="," + for item in $LIST; do + if [ "$DATA" = "$item" ]; then + valid=1 + break + fi + done + if [ "$valid" -eq 1 ]; then + ktap_print_msg "Reported: '$DATA'" + ktap_test_pass "$TEST_NAME" + else + ktap_print_msg "'$DATA' is not a valid value for this property" + ktap_test_fail "$TEST_NAME" + fi + IFS=$OLDIFS +} + +dump_file() { + FILE="$1" + while read -r line; do + ktap_print_msg "$line" + done < "$FILE" +} + +__test_uevent_prop() { + PROP="$1" + OPTIONAL="$2" + VALUE="$3" # optional + + UEVENT_PATH="$SYSFS_SUPPLIES"/"$DEVNAME"/uevent + TEST_NAME="$DEVNAME".uevent."$PROP" + + if ! grep -q "POWER_SUPPLY_$PROP=" "$UEVENT_PATH"; then + if [ "$OPTIONAL" -eq 1 ]; then + ktap_test_skip "$TEST_NAME" + else + ktap_print_msg "Missing property" + ktap_test_fail "$TEST_NAME" + fi + return + fi + + if ! grep -q "POWER_SUPPLY_$PROP=$VALUE" "$UEVENT_PATH"; then + ktap_print_msg "Invalid value for uevent property, dumping..." + dump_file "$UEVENT_PATH" + ktap_test_fail "$TEST_NAME" + else + ktap_test_pass "$TEST_NAME" + fi +} + +test_uevent_prop() { + __test_uevent_prop "$1" 0 "$2" +} + +test_uevent_prop_optional() { + __test_uevent_prop "$1" 1 "$2" +} diff --git a/tools/testing/selftests/power_supply/test_power_supply_properties.sh b/tools/testing/selftests/power_supply/test_power_supply_properties.sh new file mode 100755 index 000000000000..df272dfe1d2a --- /dev/null +++ b/tools/testing/selftests/power_supply/test_power_supply_properties.sh @@ -0,0 +1,114 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2022, 2024 Collabora Ltd +# +# This test validates the power supply uAPI: namely, the files in sysfs and +# lines in uevent that expose the power supply properties. +# +# By default all power supplies available are tested. Optionally the name of a +# power supply can be passed as a parameter to test only that one instead. +DIR="$(dirname "$(readlink -f "$0")")" + +. "${DIR}"/../kselftest/ktap_helpers.sh + +. "${DIR}"/helpers.sh + +count_tests() { + SUPPLIES=$1 + + # This needs to be updated every time a new test is added. + NUM_TESTS=33 + + total_tests=0 + + for i in $SUPPLIES; do + total_tests=$(("$total_tests" + "$NUM_TESTS")) + done + + echo "$total_tests" +} + +ktap_print_header + +SYSFS_SUPPLIES=/sys/class/power_supply/ + +if [ $# -eq 0 ]; then + supplies=$(ls "$SYSFS_SUPPLIES") +else + supplies=$1 +fi + +ktap_set_plan "$(count_tests "$supplies")" + +for DEVNAME in $supplies; do + ktap_print_msg Testing device "$DEVNAME" + + if [ ! -d "$SYSFS_SUPPLIES"/"$DEVNAME" ]; then + ktap_test_fail "$DEVNAME".exists + ktap_exit_fail_msg Device does not exist + fi + + ktap_test_pass "$DEVNAME".exists + + test_uevent_prop NAME "$DEVNAME" + + test_sysfs_prop type + SUPPLY_TYPE=$(cat "$SYSFS_SUPPLIES"/"$DEVNAME"/type) + # This fails on kernels < 5.8 (needs 2ad3d74e3c69f) + test_uevent_prop TYPE "$SUPPLY_TYPE" + + test_sysfs_prop_optional usb_type + + test_sysfs_prop_optional_range online 0 2 + test_sysfs_prop_optional_range present 0 1 + + test_sysfs_prop_optional_list status "Unknown","Charging","Discharging","Not charging","Full" + + # Capacity is reported as percentage, thus any value less than 0 and + # greater than 100 are not allowed. + test_sysfs_prop_optional_range capacity 0 100 "%" + + test_sysfs_prop_optional_list capacity_level "Unknown","Critical","Low","Normal","High","Full" + + test_sysfs_prop_optional model_name + test_sysfs_prop_optional manufacturer + test_sysfs_prop_optional serial_number + test_sysfs_prop_optional_list technology "Unknown","NiMH","Li-ion","Li-poly","LiFe","NiCd","LiMn" + + test_sysfs_prop_optional cycle_count + + test_sysfs_prop_optional_list scope "Unknown","System","Device" + + test_sysfs_prop_optional input_current_limit "uA" + test_sysfs_prop_optional input_voltage_limit "uV" + + # Technically the power-supply class does not limit reported values. + # E.g. one could expose an RTC backup-battery, which goes below 1.5V or + # an electric vehicle battery with over 300V. But most devices do not + # have a step-up capable regulator behind the battery and operate with + # voltages considered safe to touch, so we limit the allowed range to + # 1.8V-60V to catch drivers reporting incorrectly scaled values. E.g. a + # common mistake is reporting data in mV instead of µV. + test_sysfs_prop_optional_range voltage_now 1800000 60000000 "uV" + test_sysfs_prop_optional_range voltage_min 1800000 60000000 "uV" + test_sysfs_prop_optional_range voltage_max 1800000 60000000 "uV" + test_sysfs_prop_optional_range voltage_min_design 1800000 60000000 "uV" + test_sysfs_prop_optional_range voltage_max_design 1800000 60000000 "uV" + + # current based systems + test_sysfs_prop_optional current_now "uA" + test_sysfs_prop_optional current_max "uA" + test_sysfs_prop_optional charge_now "uAh" + test_sysfs_prop_optional charge_full "uAh" + test_sysfs_prop_optional charge_full_design "uAh" + + # power based systems + test_sysfs_prop_optional power_now "uW" + test_sysfs_prop_optional energy_now "uWh" + test_sysfs_prop_optional energy_full "uWh" + test_sysfs_prop_optional energy_full_design "uWh" + test_sysfs_prop_optional energy_full_design "uWh" +done + +ktap_finished -- cgit v1.2.3-70-g09d2 From c25db1d27abd78175d9802f52c1b75f3cf716f2c Mon Sep 17 00:00:00 2001 From: Javier Carrasco Date: Wed, 14 Feb 2024 01:03:31 +0100 Subject: selftests: uevent: add missing gitignore The 'uevent_filtering' test generates an object with the same name, but there is no .gitignore file in the directory to add the object as stated in the selftest documentation. Add the missing .gitignore file and include 'uevent_filtering'. Signed-off-by: Javier Carrasco Signed-off-by: Shuah Khan --- tools/testing/selftests/uevent/.gitignore | 1 + 1 file changed, 1 insertion(+) create mode 100644 tools/testing/selftests/uevent/.gitignore (limited to 'tools') diff --git a/tools/testing/selftests/uevent/.gitignore b/tools/testing/selftests/uevent/.gitignore new file mode 100644 index 000000000000..382afb74cd40 --- /dev/null +++ b/tools/testing/selftests/uevent/.gitignore @@ -0,0 +1 @@ +uevent_filtering -- cgit v1.2.3-70-g09d2 From 4b7b4291dee2fef9148563be3eeb0034cc3bf5df Mon Sep 17 00:00:00 2001 From: Javier Carrasco Date: Wed, 14 Feb 2024 01:03:32 +0100 Subject: selftests: thermal: intel: power_floor: add missing gitignore The 'power_floor' test generates an object with the same name, but there is no .gitignore file in the directory to add the object as stated in the selftest documentation. Add the missing .gitignore file and include 'power_floor'. Signed-off-by: Javier Carrasco Signed-off-by: Shuah Khan --- tools/testing/selftests/thermal/intel/power_floor/.gitignore | 1 + 1 file changed, 1 insertion(+) create mode 100644 tools/testing/selftests/thermal/intel/power_floor/.gitignore (limited to 'tools') diff --git a/tools/testing/selftests/thermal/intel/power_floor/.gitignore b/tools/testing/selftests/thermal/intel/power_floor/.gitignore new file mode 100644 index 000000000000..1b9a76406f18 --- /dev/null +++ b/tools/testing/selftests/thermal/intel/power_floor/.gitignore @@ -0,0 +1 @@ +power_floor_test -- cgit v1.2.3-70-g09d2 From 2851f57d2dabd76a79365b78fedc80d2ed3ac2d8 Mon Sep 17 00:00:00 2001 From: Javier Carrasco Date: Wed, 14 Feb 2024 01:03:33 +0100 Subject: selftests: thermal: intel: workload_hint: add missing gitignore The 'workload_hint_test' test generates an object with the same name, but there is no .gitignore file in the directory to add the object as stated in the selftest documentation. Add the missing .gitignore file and include 'workload_hint_test'. Signed-off-by: Javier Carrasco Signed-off-by: Shuah Khan --- tools/testing/selftests/thermal/intel/workload_hint/.gitignore | 1 + 1 file changed, 1 insertion(+) create mode 100644 tools/testing/selftests/thermal/intel/workload_hint/.gitignore (limited to 'tools') diff --git a/tools/testing/selftests/thermal/intel/workload_hint/.gitignore b/tools/testing/selftests/thermal/intel/workload_hint/.gitignore new file mode 100644 index 000000000000..d697b034a3a8 --- /dev/null +++ b/tools/testing/selftests/thermal/intel/workload_hint/.gitignore @@ -0,0 +1 @@ +workload_hint_test -- cgit v1.2.3-70-g09d2 From 5bc9dc068afe95e924136d57c1a385194282a919 Mon Sep 17 00:00:00 2001 From: Vincenzo Mezzela Date: Sun, 11 Feb 2024 12:18:18 +0100 Subject: selftest: ftrace: fix minor typo in log Resolves a spelling error in the test log, preventing potential confusion. Signed-off-by: Vincenzo Mezzela Acked-by: Steven Rostedt (Google) Signed-off-by: Shuah Khan --- tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc index 4562e13cb26b..717898894ef7 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc @@ -40,7 +40,7 @@ grep "id: \(unknown_\|sys_\)" events/raw_syscalls/sys_exit/hist > /dev/null || \ reset_trigger -echo "Test histgram with log2 modifier" +echo "Test histogram with log2 modifier" echo 'hist:keys=bytes_req.log2' > events/kmem/kmalloc/trigger for i in `seq 1 10` ; do ( echo "forked" > /dev/null); done -- cgit v1.2.3-70-g09d2 From 3425a2005b291b62b6f6deeeab1156839c41cf85 Mon Sep 17 00:00:00 2001 From: Naveen N Rao Date: Fri, 16 Feb 2024 15:26:26 +0530 Subject: selftests/ftrace: Add test to exercize function tracer across cpu hotplug Add a test to exercize cpu hotplug with the function tracer active to ensure that sensitive functions in idle path are excluded from being traced. This helps catch issues such as the one fixed by commit 4b3338aaa74d ("powerpc/ftrace: Fix stack teardown in ftrace_no_trace"). Signed-off-by: Naveen N Rao Acked-by: Masami Hiramatsu (Google) Acked-by: Steven Rostedt (Google) Signed-off-by: Shuah Khan --- .../selftests/ftrace/test.d/ftrace/func_hotplug.tc | 42 ++++++++++++++++++++++ 1 file changed, 42 insertions(+) create mode 100644 tools/testing/selftests/ftrace/test.d/ftrace/func_hotplug.tc (limited to 'tools') diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_hotplug.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_hotplug.tc new file mode 100644 index 000000000000..ccfbfde3d942 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_hotplug.tc @@ -0,0 +1,42 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0-or-later +# description: ftrace - function trace across cpu hotplug +# requires: function:tracer + +if ! which nproc ; then + nproc() { + ls -d /sys/devices/system/cpu/cpu[0-9]* | wc -l + } +fi + +NP=`nproc` + +if [ $NP -eq 1 ] ;then + echo "We cannot test cpu hotplug in UP environment" + exit_unresolved +fi + +# Find online cpu +for i in /sys/devices/system/cpu/cpu[1-9]*; do + if [ -f $i/online ] && [ "$(cat $i/online)" = "1" ]; then + cpu=$i + break + fi +done + +if [ -z "$cpu" ]; then + echo "We cannot test cpu hotplug with a single cpu online" + exit_unresolved +fi + +echo 0 > tracing_on +echo > trace + +: "Set $(basename $cpu) offline/online with function tracer enabled" +echo function > current_tracer +echo 1 > tracing_on +(echo 0 > $cpu/online) +(echo "forked"; sleep 1) +(echo 1 > $cpu/online) +echo 0 > tracing_on +echo nop > current_tracer -- cgit v1.2.3-70-g09d2 From 85506aca2eb4ea41223c91c5fe25125953c19b13 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Mon, 19 Feb 2024 16:08:02 -0800 Subject: selftests/mqueue: Set timeout to 180 seconds While mq_perf_tests runs with the default kselftest timeout limit, which is 45 seconds, the test takes about 60 seconds to complete on i3.metal AWS instances. Hence, the test always times out. Increase the timeout to 180 seconds. Fixes: 852c8cbf34d3 ("selftests/kselftest/runner.sh: Add 45 second timeout per test") Cc: # 5.4.x Signed-off-by: SeongJae Park Reviewed-by: Kees Cook Signed-off-by: Shuah Khan --- tools/testing/selftests/mqueue/setting | 1 + 1 file changed, 1 insertion(+) create mode 100644 tools/testing/selftests/mqueue/setting (limited to 'tools') diff --git a/tools/testing/selftests/mqueue/setting b/tools/testing/selftests/mqueue/setting new file mode 100644 index 000000000000..a953c96aa16e --- /dev/null +++ b/tools/testing/selftests/mqueue/setting @@ -0,0 +1 @@ +timeout=180 -- cgit v1.2.3-70-g09d2 From 6f1a214d446b2f2f9c8c4b96755a8f0316ba4436 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Tue, 20 Feb 2024 09:23:23 +0000 Subject: selftests: sched: Fix spelling mistake "hiearchy" -> "hierarchy" There is a spelling mistake in a printed message. Fix it. Signed-off-by: Colin Ian King Signed-off-by: Shuah Khan --- tools/testing/selftests/sched/cs_prctl_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/testing/selftests/sched/cs_prctl_test.c b/tools/testing/selftests/sched/cs_prctl_test.c index 7ba057154343..62fba7356af2 100644 --- a/tools/testing/selftests/sched/cs_prctl_test.c +++ b/tools/testing/selftests/sched/cs_prctl_test.c @@ -276,7 +276,7 @@ int main(int argc, char *argv[]) if (setpgid(0, 0) != 0) handle_error("process group"); - printf("\n## Create a thread/process/process group hiearchy\n"); + printf("\n## Create a thread/process/process group hierarchy\n"); create_processes(num_processes, num_threads, procs); need_cleanup = 1; disp_processes(num_processes, procs); -- cgit v1.2.3-70-g09d2 From 2ed08e4bc53298db3f87b528cd804cb0cce066a9 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Wed, 21 Feb 2024 14:08:59 +0800 Subject: clocksource: Scale the watchdog read retries automatically On a 8-socket server the TSC is wrongly marked as 'unstable' and disabled during boot time on about one out of 120 boot attempts: clocksource: timekeeping watchdog on CPU227: wd-tsc-wd excessive read-back delay of 153560ns vs. limit of 125000ns, wd-wd read-back delay only 11440ns, attempt 3, marking tsc unstable tsc: Marking TSC unstable due to clocksource watchdog TSC found unstable after boot, most likely due to broken BIOS. Use 'tsc=unstable'. sched_clock: Marking unstable (119294969739, 159204297)<-(125446229205, -5992055152) clocksource: Checking clocksource tsc synchronization from CPU 319 to CPUs 0,99,136,180,210,542,601,896. clocksource: Switched to clocksource hpet The reason is that for platform with a large number of CPUs, there are sporadic big or huge read latencies while reading the watchog/clocksource during boot or when system is under stress work load, and the frequency and maximum value of the latency goes up with the number of online CPUs. The cCurrent code already has logic to detect and filter such high latency case by reading the watchdog twice and checking the two deltas. Due to the randomness of the latency, there is a low probabilty that the first delta (latency) is big, but the second delta is small and looks valid. The watchdog code retries the readouts by default twice, which is not necessarily sufficient for systems with a large number of CPUs. There is a command line parameter 'max_cswd_read_retries' which allows to increase the number of retries, but that's not user friendly as it needs to be tweaked per system. As the number of required retries is proportional to the number of online CPUs, this parameter can be calculated at runtime. Scale and enlarge the number of retries according to the number of online CPUs and remove the command line parameter completely. [ tglx: Massaged change log and comments ] Signed-off-by: Feng Tang Signed-off-by: Thomas Gleixner Tested-by: Jin Wang Tested-by: Paul E. McKenney Reviewed-by: Waiman Long Reviewed-by: Paul E. McKenney Link: https://lore.kernel.org/r/20240221060859.1027450-1-feng.tang@intel.com --- Documentation/admin-guide/kernel-parameters.txt | 6 ------ include/linux/clocksource.h | 14 +++++++++++++- kernel/time/clocksource-wdtest.c | 13 +++++++------ kernel/time/clocksource.c | 10 ++++------ tools/testing/selftests/rcutorture/bin/torture.sh | 2 +- 5 files changed, 25 insertions(+), 20 deletions(-) (limited to 'tools') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 31b3a25680d0..763e96dcf8b1 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -679,12 +679,6 @@ loops can be debugged more effectively on production systems. - clocksource.max_cswd_read_retries= [KNL] - Number of clocksource_watchdog() retries due to - external delays before the clock will be marked - unstable. Defaults to two retries, that is, - three attempts to read the clock under test. - clocksource.verify_n_cpus= [KNL] Limit the number of CPUs checked for clocksources marked with CLOCK_SOURCE_VERIFY_PERCPU that diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 1d42d4b17327..0ad8b550bb4b 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -291,7 +291,19 @@ static inline void timer_probe(void) {} #define TIMER_ACPI_DECLARE(name, table_id, fn) \ ACPI_DECLARE_PROBE_ENTRY(timer, name, table_id, 0, NULL, 0, fn) -extern ulong max_cswd_read_retries; +static inline unsigned int clocksource_get_max_watchdog_retry(void) +{ + /* + * When system is in the boot phase or under heavy workload, there + * can be random big latencies during the clocksource/watchdog + * read, so allow retries to filter the noise latency. As the + * latency's frequency and maximum value goes up with the number of + * CPUs, scale the number of retries with the number of online + * CPUs. + */ + return (ilog2(num_online_cpus()) / 2) + 1; +} + void clocksource_verify_percpu(struct clocksource *cs); #endif /* _LINUX_CLOCKSOURCE_H */ diff --git a/kernel/time/clocksource-wdtest.c b/kernel/time/clocksource-wdtest.c index df922f49d171..d06185e054ea 100644 --- a/kernel/time/clocksource-wdtest.c +++ b/kernel/time/clocksource-wdtest.c @@ -104,8 +104,8 @@ static void wdtest_ktime_clocksource_reset(void) static int wdtest_func(void *arg) { unsigned long j1, j2; + int i, max_retries; char *s; - int i; schedule_timeout_uninterruptible(holdoff * HZ); @@ -139,18 +139,19 @@ static int wdtest_func(void *arg) WARN_ON_ONCE(time_before(j2, j1 + NSEC_PER_USEC)); /* Verify tsc-like stability with various numbers of errors injected. */ - for (i = 0; i <= max_cswd_read_retries + 1; i++) { - if (i <= 1 && i < max_cswd_read_retries) + max_retries = clocksource_get_max_watchdog_retry(); + for (i = 0; i <= max_retries + 1; i++) { + if (i <= 1 && i < max_retries) s = ""; - else if (i <= max_cswd_read_retries) + else if (i <= max_retries) s = ", expect message"; else s = ", expect clock skew"; - pr_info("--- Watchdog with %dx error injection, %lu retries%s.\n", i, max_cswd_read_retries, s); + pr_info("--- Watchdog with %dx error injection, %d retries%s.\n", i, max_retries, s); WRITE_ONCE(wdtest_ktime_read_ndelays, i); schedule_timeout_uninterruptible(2 * HZ); WARN_ON_ONCE(READ_ONCE(wdtest_ktime_read_ndelays)); - WARN_ON_ONCE((i <= max_cswd_read_retries) != + WARN_ON_ONCE((i <= max_retries) != !(clocksource_wdtest_ktime.flags & CLOCK_SOURCE_UNSTABLE)); wdtest_ktime_clocksource_reset(); } diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 4ef06651ad07..e5b260aa0e02 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -210,9 +210,6 @@ void clocksource_mark_unstable(struct clocksource *cs) spin_unlock_irqrestore(&watchdog_lock, flags); } -ulong max_cswd_read_retries = 2; -module_param(max_cswd_read_retries, ulong, 0644); -EXPORT_SYMBOL_GPL(max_cswd_read_retries); static int verify_n_cpus = 8; module_param(verify_n_cpus, int, 0644); @@ -224,11 +221,12 @@ enum wd_read_status { static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow) { - unsigned int nretries; + unsigned int nretries, max_retries; u64 wd_end, wd_end2, wd_delta; int64_t wd_delay, wd_seq_delay; - for (nretries = 0; nretries <= max_cswd_read_retries; nretries++) { + max_retries = clocksource_get_max_watchdog_retry(); + for (nretries = 0; nretries <= max_retries; nretries++) { local_irq_disable(); *wdnow = watchdog->read(watchdog); *csnow = cs->read(cs); @@ -240,7 +238,7 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, wd_delay = clocksource_cyc2ns(wd_delta, watchdog->mult, watchdog->shift); if (wd_delay <= WATCHDOG_MAX_SKEW) { - if (nretries > 1 || nretries >= max_cswd_read_retries) { + if (nretries > 1 || nretries >= max_retries) { pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n", smp_processor_id(), watchdog->name, nretries); } diff --git a/tools/testing/selftests/rcutorture/bin/torture.sh b/tools/testing/selftests/rcutorture/bin/torture.sh index d5a0d8a33c27..bbac5f4b03d0 100755 --- a/tools/testing/selftests/rcutorture/bin/torture.sh +++ b/tools/testing/selftests/rcutorture/bin/torture.sh @@ -567,7 +567,7 @@ then torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000 tsc=watchdog" torture_set "clocksourcewd-1" tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration 45s --configs TREE03 --kconfig "CONFIG_TEST_CLOCKSOURCE_WATCHDOG=y" --trust-make - torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000 clocksource.max_cswd_read_retries=1 tsc=watchdog" + torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000 tsc=watchdog" torture_set "clocksourcewd-2" tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration 45s --configs TREE03 --kconfig "CONFIG_TEST_CLOCKSOURCE_WATCHDOG=y" --trust-make # In case our work is already done... -- cgit v1.2.3-70-g09d2 From 427e1646f1ef6c714a5bade30ca0302edc5d46a0 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Thu, 22 Feb 2024 13:16:35 +0200 Subject: x86/insn: Remove superfluous checks from instruction decoding routines It's pointless checking if a particular part of an instruction is decoded before calling the routine responsible for decoding it as this check is duplicated in the routines itself. Streamline the code by removing the superfluous checks. No functional difference. Signed-off-by: Nikolay Borisov Signed-off-by: Ingo Molnar Cc: Josh Poimboeuf Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20240222111636.2214523-2-nik.borisov@suse.com --- arch/x86/lib/insn.c | 56 ++++++++++++++++++----------------------------- tools/arch/x86/lib/insn.c | 56 ++++++++++++++++++----------------------------- 2 files changed, 42 insertions(+), 70 deletions(-) (limited to 'tools') diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 55e371cc69fd..3946bdc75087 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -268,11 +268,9 @@ int insn_get_opcode(struct insn *insn) if (opcode->got) return 0; - if (!insn->prefixes.got) { - ret = insn_get_prefixes(insn); - if (ret) - return ret; - } + ret = insn_get_prefixes(insn); + if (ret) + return ret; /* Get first opcode */ op = get_next(insn_byte_t, insn); @@ -339,11 +337,9 @@ int insn_get_modrm(struct insn *insn) if (modrm->got) return 0; - if (!insn->opcode.got) { - ret = insn_get_opcode(insn); - if (ret) - return ret; - } + ret = insn_get_opcode(insn); + if (ret) + return ret; if (inat_has_modrm(insn->attr)) { mod = get_next(insn_byte_t, insn); @@ -386,11 +382,9 @@ int insn_rip_relative(struct insn *insn) if (!insn->x86_64) return 0; - if (!modrm->got) { - ret = insn_get_modrm(insn); - if (ret) - return 0; - } + ret = insn_get_modrm(insn); + if (ret) + return 0; /* * For rip-relative instructions, the mod field (top 2 bits) * is zero and the r/m field (bottom 3 bits) is 0x5. @@ -417,11 +411,9 @@ int insn_get_sib(struct insn *insn) if (insn->sib.got) return 0; - if (!insn->modrm.got) { - ret = insn_get_modrm(insn); - if (ret) - return ret; - } + ret = insn_get_modrm(insn); + if (ret) + return ret; if (insn->modrm.nbytes) { modrm = insn->modrm.bytes[0]; @@ -460,11 +452,9 @@ int insn_get_displacement(struct insn *insn) if (insn->displacement.got) return 0; - if (!insn->sib.got) { - ret = insn_get_sib(insn); - if (ret) - return ret; - } + ret = insn_get_sib(insn); + if (ret) + return ret; if (insn->modrm.nbytes) { /* @@ -628,11 +618,9 @@ int insn_get_immediate(struct insn *insn) if (insn->immediate.got) return 0; - if (!insn->displacement.got) { - ret = insn_get_displacement(insn); - if (ret) - return ret; - } + ret = insn_get_displacement(insn); + if (ret) + return ret; if (inat_has_moffset(insn->attr)) { if (!__get_moffset(insn)) @@ -703,11 +691,9 @@ int insn_get_length(struct insn *insn) if (insn->length) return 0; - if (!insn->immediate.got) { - ret = insn_get_immediate(insn); - if (ret) - return ret; - } + ret = insn_get_immediate(insn); + if (ret) + return ret; insn->length = (unsigned char)((unsigned long)insn->next_byte - (unsigned long)insn->kaddr); diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c index 8fd63a067308..5d81924478d9 100644 --- a/tools/arch/x86/lib/insn.c +++ b/tools/arch/x86/lib/insn.c @@ -268,11 +268,9 @@ int insn_get_opcode(struct insn *insn) if (opcode->got) return 0; - if (!insn->prefixes.got) { - ret = insn_get_prefixes(insn); - if (ret) - return ret; - } + ret = insn_get_prefixes(insn); + if (ret) + return ret; /* Get first opcode */ op = get_next(insn_byte_t, insn); @@ -339,11 +337,9 @@ int insn_get_modrm(struct insn *insn) if (modrm->got) return 0; - if (!insn->opcode.got) { - ret = insn_get_opcode(insn); - if (ret) - return ret; - } + ret = insn_get_opcode(insn); + if (ret) + return ret; if (inat_has_modrm(insn->attr)) { mod = get_next(insn_byte_t, insn); @@ -386,11 +382,9 @@ int insn_rip_relative(struct insn *insn) if (!insn->x86_64) return 0; - if (!modrm->got) { - ret = insn_get_modrm(insn); - if (ret) - return 0; - } + ret = insn_get_modrm(insn); + if (ret) + return 0; /* * For rip-relative instructions, the mod field (top 2 bits) * is zero and the r/m field (bottom 3 bits) is 0x5. @@ -417,11 +411,9 @@ int insn_get_sib(struct insn *insn) if (insn->sib.got) return 0; - if (!insn->modrm.got) { - ret = insn_get_modrm(insn); - if (ret) - return ret; - } + ret = insn_get_modrm(insn); + if (ret) + return ret; if (insn->modrm.nbytes) { modrm = insn->modrm.bytes[0]; @@ -460,11 +452,9 @@ int insn_get_displacement(struct insn *insn) if (insn->displacement.got) return 0; - if (!insn->sib.got) { - ret = insn_get_sib(insn); - if (ret) - return ret; - } + ret = insn_get_sib(insn); + if (ret) + return ret; if (insn->modrm.nbytes) { /* @@ -628,11 +618,9 @@ int insn_get_immediate(struct insn *insn) if (insn->immediate.got) return 0; - if (!insn->displacement.got) { - ret = insn_get_displacement(insn); - if (ret) - return ret; - } + ret = insn_get_displacement(insn); + if (ret) + return ret; if (inat_has_moffset(insn->attr)) { if (!__get_moffset(insn)) @@ -703,11 +691,9 @@ int insn_get_length(struct insn *insn) if (insn->length) return 0; - if (!insn->immediate.got) { - ret = insn_get_immediate(insn); - if (ret) - return ret; - } + ret = insn_get_immediate(insn); + if (ret) + return ret; insn->length = (unsigned char)((unsigned long)insn->next_byte - (unsigned long)insn->kaddr); -- cgit v1.2.3-70-g09d2 From 07a5d4bcbf8e70a430431991f185eb29e74ae533 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Thu, 22 Feb 2024 13:16:36 +0200 Subject: x86/insn: Directly assign x86_64 state in insn_init() No point in checking again as this was already done by the caller. Signed-off-by: Nikolay Borisov Signed-off-by: Ingo Molnar Cc: Josh Poimboeuf Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20240222111636.2214523-3-nik.borisov@suse.com --- arch/x86/lib/insn.c | 2 +- tools/arch/x86/lib/insn.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 3946bdc75087..1bb155a0955b 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -71,7 +71,7 @@ void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64) insn->kaddr = kaddr; insn->end_kaddr = kaddr + buf_len; insn->next_byte = kaddr; - insn->x86_64 = x86_64 ? 1 : 0; + insn->x86_64 = x86_64; insn->opnd_bytes = 4; if (x86_64) insn->addr_bytes = 8; diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c index 5d81924478d9..ada4b4a79dd4 100644 --- a/tools/arch/x86/lib/insn.c +++ b/tools/arch/x86/lib/insn.c @@ -71,7 +71,7 @@ void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64) insn->kaddr = kaddr; insn->end_kaddr = kaddr + buf_len; insn->next_byte = kaddr; - insn->x86_64 = x86_64 ? 1 : 0; + insn->x86_64 = x86_64; insn->opnd_bytes = 4; if (x86_64) insn->addr_bytes = 8; -- cgit v1.2.3-70-g09d2 From 63e5c5a10559077bb5f32edf783084e7164af9c3 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 22 Feb 2024 11:06:11 -0800 Subject: KVM: selftests: Create GUEST_MEMFD for relevant invalid flags testcases Actually create a GUEST_MEMFD instance and pass it to KVM when doing negative tests for KVM_SET_USER_MEMORY_REGION2 + KVM_MEM_GUEST_MEMFD. Without a valid GUEST_MEMFD file descriptor, KVM_SET_USER_MEMORY_REGION2 will always fail with -EINVAL, resulting in false passes for any and all tests of illegal combinations of KVM_MEM_GUEST_MEMFD and other flags. Fixes: 5d74316466f4 ("KVM: selftests: Add a memory region subtest to validate invalid flags") Link: https://lore.kernel.org/r/20240222190612.2942589-5-seanjc@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/set_memory_region_test.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index 40337f566eeb..9df4b61116bc 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -367,11 +367,15 @@ static void test_invalid_memory_region_flags(void) } if (supported_flags & KVM_MEM_GUEST_MEMFD) { + int guest_memfd = vm_create_guest_memfd(vm, MEM_REGION_SIZE, 0); + r = __vm_set_user_memory_region2(vm, 0, KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_GUEST_MEMFD, - 0, MEM_REGION_SIZE, NULL, 0, 0); + 0, MEM_REGION_SIZE, NULL, guest_memfd, 0); TEST_ASSERT(r && errno == EINVAL, "KVM_SET_USER_MEMORY_REGION2 should have failed, dirty logging private memory is unsupported"); + + close(guest_memfd); } } -- cgit v1.2.3-70-g09d2 From 2dfd2383034421101300a3b7325cf339a182d218 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 22 Feb 2024 11:06:12 -0800 Subject: KVM: selftests: Add a testcase to verify GUEST_MEMFD and READONLY are exclusive Extend set_memory_region_test's invalid flags subtest to verify that GUEST_MEMFD is incompatible with READONLY. GUEST_MEMFD doesn't currently support writes from userspace and KVM doesn't support emulated MMIO on private accesses, and so KVM is supposed to reject the GUEST_MEMFD+READONLY in order to avoid configuration that KVM can't support. Link: https://lore.kernel.org/r/20240222190612.2942589-6-seanjc@google.com Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/set_memory_region_test.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'tools') diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index 9df4b61116bc..06b43ed23580 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -375,6 +375,12 @@ static void test_invalid_memory_region_flags(void) TEST_ASSERT(r && errno == EINVAL, "KVM_SET_USER_MEMORY_REGION2 should have failed, dirty logging private memory is unsupported"); + r = __vm_set_user_memory_region2(vm, 0, + KVM_MEM_READONLY | KVM_MEM_GUEST_MEMFD, + 0, MEM_REGION_SIZE, NULL, guest_memfd, 0); + TEST_ASSERT(r && errno == EINVAL, + "KVM_SET_USER_MEMORY_REGION2 should have failed, read-only GUEST_MEMFD memslots are unsupported"); + close(guest_memfd); } } -- cgit v1.2.3-70-g09d2 From 5339792bd64bd1605d3d51f8e52e94dfc385959b Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Fri, 16 Feb 2024 09:34:56 +0100 Subject: selftests/resctrl: Add test groups and name L3 CAT test L3_CAT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To select test to run -t parameter can be used. However, -t cat currently maps to L3 CAT test which will be confusing after more CAT related tests will be added. Allow selecting tests as groups and call L3 CAT test "L3_CAT", "CAT" group will enable all CAT related tests. Signed-off-by: Ilpo Järvinen Signed-off-by: Maciej Wieczor-Retman Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cat_test.c | 3 ++- tools/testing/selftests/resctrl/resctrl.h | 3 +++ tools/testing/selftests/resctrl/resctrl_tests.c | 16 +++++++++++----- 3 files changed, 16 insertions(+), 6 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index 24af8310288a..39fc9303b8e8 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -295,7 +295,8 @@ out: } struct resctrl_test l3_cat_test = { - .name = "CAT", + .name = "L3_CAT", + .group = "CAT", .resource = "L3", .feature_check = test_resource_feature_check, .run_test = cat_run_test, diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index c52eaf46f24d..a1462029998e 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -65,6 +65,8 @@ struct user_params { /* * resctrl_test: resctrl test definition * @name: Test name + * @group: Test group - a common name for tests that share some characteristic + * (e.g., L3 CAT test belongs to the CAT group). Can be NULL * @resource: Resource to test (e.g., MB, L3, L2, etc.) * @vendor_specific: Bitmask for vendor-specific tests (can be 0 for universal tests) * @disabled: Test is disabled @@ -73,6 +75,7 @@ struct user_params { */ struct resctrl_test { const char *name; + const char *group; const char *resource; unsigned int vendor_specific; bool disabled; diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c index 75fc49ba3efb..3044179ee6e9 100644 --- a/tools/testing/selftests/resctrl/resctrl_tests.c +++ b/tools/testing/selftests/resctrl/resctrl_tests.c @@ -65,11 +65,15 @@ static void cmd_help(void) printf("usage: resctrl_tests [-h] [-t test list] [-n no_of_bits] [-b benchmark_cmd [option]...]\n"); printf("\t-b benchmark_cmd [option]...: run specified benchmark for MBM, MBA and CMT\n"); printf("\t default benchmark is builtin fill_buf\n"); - printf("\t-t test list: run tests specified in the test list, "); + printf("\t-t test list: run tests/groups specified by the list, "); printf("e.g. -t mbm,mba,cmt,cat\n"); - printf("\t\tSupported tests:\n"); - for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) - printf("\t\t\t%s\n", resctrl_tests[i]->name); + printf("\t\tSupported tests (group):\n"); + for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) { + if (resctrl_tests[i]->group) + printf("\t\t\t%s (%s)\n", resctrl_tests[i]->name, resctrl_tests[i]->group); + else + printf("\t\t\t%s\n", resctrl_tests[i]->name); + } printf("\t-n no_of_bits: run cache tests using specified no of bits in cache bit mask\n"); printf("\t-p cpu_no: specify CPU number to run the test. 1 is default\n"); printf("\t-h: help\n"); @@ -199,7 +203,9 @@ int main(int argc, char **argv) bool found = false; for (i = 0; i < ARRAY_SIZE(resctrl_tests); i++) { - if (!strcasecmp(token, resctrl_tests[i]->name)) { + if (!strcasecmp(token, resctrl_tests[i]->name) || + (resctrl_tests[i]->group && + !strcasecmp(token, resctrl_tests[i]->group))) { if (resctrl_tests[i]->disabled) tests++; resctrl_tests[i]->disabled = false; -- cgit v1.2.3-70-g09d2 From e331ac141f1df6d151d24e60ff16e93ec075509e Mon Sep 17 00:00:00 2001 From: Maciej Wieczor-Retman Date: Fri, 16 Feb 2024 09:35:15 +0100 Subject: selftests/resctrl: Add a helper for the non-contiguous test MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The CAT non-contiguous selftests have to read the file responsible for reporting support of non-contiguous CBMs in kernel (resctrl). Then the test compares if that information matches what is reported by CPUID output. Add a generic helper function to read an unsigned number from /sys/fs/resctrl/info//. Signed-off-by: Maciej Wieczor-Retman Reviewed-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/resctrl.h | 1 + tools/testing/selftests/resctrl/resctrlfs.c | 36 +++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index a1462029998e..5116ea082d03 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -162,6 +162,7 @@ unsigned int count_contiguous_bits(unsigned long val, unsigned int *start); int get_full_cbm(const char *cache_type, unsigned long *mask); int get_mask_no_shareable(const char *cache_type, unsigned long *mask); int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size); +int resource_info_unsigned_get(const char *resource, const char *filename, unsigned int *val); void ctrlc_handler(int signum, siginfo_t *info, void *ptr); int signal_handler_register(void); void signal_handler_unregister(void); diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index 5750662cce57..8a183c73bc23 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -249,6 +249,42 @@ static int get_bit_mask(const char *filename, unsigned long *mask) return 0; } +/* + * resource_info_unsigned_get - Read an unsigned value from + * /sys/fs/resctrl/info/@resource/@filename + * @resource: Resource name that matches directory name in + * /sys/fs/resctrl/info + * @filename: File in /sys/fs/resctrl/info/@resource + * @val: Contains read value on success. + * + * Return: = 0 on success, < 0 on failure. On success the read + * value is saved into @val. + */ +int resource_info_unsigned_get(const char *resource, const char *filename, + unsigned int *val) +{ + char file_path[PATH_MAX]; + FILE *fp; + + snprintf(file_path, sizeof(file_path), "%s/%s/%s", INFO_PATH, resource, + filename); + + fp = fopen(file_path, "r"); + if (!fp) { + ksft_print_msg("Error opening %s: %m\n", file_path); + return -1; + } + + if (fscanf(fp, "%u", val) <= 0) { + ksft_print_msg("Could not get contents of %s: %m\n", file_path); + fclose(fp); + return -1; + } + + fclose(fp); + return 0; +} + /* * create_bit_mask- Create bit mask from start, len pair * @start: LSB of the mask -- cgit v1.2.3-70-g09d2 From 00616416488868a8b98343863e5ac078506e44e8 Mon Sep 17 00:00:00 2001 From: Maciej Wieczor-Retman Date: Fri, 16 Feb 2024 09:35:28 +0100 Subject: selftests/resctrl: Split validate_resctrl_feature_request() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit validate_resctrl_feature_request() is used to test both if a resource is present in the info directory, and if a passed monitoring feature is present in the mon_features file. Refactor validate_resctrl_feature_request() into two smaller functions that each accomplish one check to give feature checking more granularity: - Resource directory presence in the /sys/fs/resctrl/info directory. - Feature name presence in the /sys/fs/resctrl/info//mon_features file. Signed-off-by: Maciej Wieczor-Retman Reviewed-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cmt_test.c | 2 +- tools/testing/selftests/resctrl/mba_test.c | 2 +- tools/testing/selftests/resctrl/mbm_test.c | 6 ++--- tools/testing/selftests/resctrl/resctrl.h | 3 ++- tools/testing/selftests/resctrl/resctrlfs.c | 35 ++++++++++++++++++++--------- 5 files changed, 31 insertions(+), 17 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c index dd5ca343c469..a81f91222a89 100644 --- a/tools/testing/selftests/resctrl/cmt_test.c +++ b/tools/testing/selftests/resctrl/cmt_test.c @@ -170,7 +170,7 @@ out: static bool cmt_feature_check(const struct resctrl_test *test) { return test_resource_feature_check(test) && - validate_resctrl_feature_request("L3_MON", "llc_occupancy"); + resctrl_mon_feature_exists("L3_MON", "llc_occupancy"); } struct resctrl_test cmt_test = { diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c index da256d2dbe5c..7946e32e85c8 100644 --- a/tools/testing/selftests/resctrl/mba_test.c +++ b/tools/testing/selftests/resctrl/mba_test.c @@ -171,7 +171,7 @@ out: static bool mba_feature_check(const struct resctrl_test *test) { return test_resource_feature_check(test) && - validate_resctrl_feature_request("L3_MON", "mbm_local_bytes"); + resctrl_mon_feature_exists("L3_MON", "mbm_local_bytes"); } struct resctrl_test mba_test = { diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c index 34879e7b71a0..d67ffa3ec63a 100644 --- a/tools/testing/selftests/resctrl/mbm_test.c +++ b/tools/testing/selftests/resctrl/mbm_test.c @@ -97,7 +97,7 @@ static int mbm_setup(const struct resctrl_test *test, return END_OF_TESTS; /* Set up shemata with 100% allocation on the first run. */ - if (p->num_of_runs == 0 && validate_resctrl_feature_request("MB", NULL)) + if (p->num_of_runs == 0 && resctrl_resource_exists("MB")) ret = write_schemata(p->ctrlgrp, "100", uparams->cpu, test->resource); p->num_of_runs++; @@ -140,8 +140,8 @@ out: static bool mbm_feature_check(const struct resctrl_test *test) { - return validate_resctrl_feature_request("L3_MON", "mbm_total_bytes") && - validate_resctrl_feature_request("L3_MON", "mbm_local_bytes"); + return resctrl_mon_feature_exists("L3_MON", "mbm_total_bytes") && + resctrl_mon_feature_exists("L3_MON", "mbm_local_bytes"); } struct resctrl_test mbm_test = { diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 5116ea082d03..6d99ed44ec60 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -136,7 +136,8 @@ int get_domain_id(const char *resource, int cpu_no, int *domain_id); int mount_resctrlfs(void); int umount_resctrlfs(void); int validate_bw_report_request(char *bw_report); -bool validate_resctrl_feature_request(const char *resource, const char *feature); +bool resctrl_resource_exists(const char *resource); +bool resctrl_mon_feature_exists(const char *resource, const char *feature); bool test_resource_feature_check(const struct resctrl_test *test); char *fgrep(FILE *inf, const char *str); int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity); diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index 8a183c73bc23..1273e55c4a9d 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -708,20 +708,16 @@ char *fgrep(FILE *inf, const char *str) } /* - * validate_resctrl_feature_request - Check if requested feature is valid. - * @resource: Required resource (e.g., MB, L3, L2, L3_MON, etc.) - * @feature: Required monitor feature (in mon_features file). Can only be - * set for L3_MON. Must be NULL for all other resources. + * resctrl_resource_exists - Check if a resource is supported. + * @resource: Resctrl resource (e.g., MB, L3, L2, L3_MON, etc.) * - * Return: True if the resource/feature is supported, else false. False is + * Return: True if the resource is supported, else false. False is * also returned if resctrl FS is not mounted. */ -bool validate_resctrl_feature_request(const char *resource, const char *feature) +bool resctrl_resource_exists(const char *resource) { char res_path[PATH_MAX]; struct stat statbuf; - char *res; - FILE *inf; int ret; if (!resource) @@ -736,8 +732,25 @@ bool validate_resctrl_feature_request(const char *resource, const char *feature) if (stat(res_path, &statbuf)) return false; - if (!feature) - return true; + return true; +} + +/* + * resctrl_mon_feature_exists - Check if requested monitoring feature is valid. + * @resource: Resource that uses the mon_features file. Currently only L3_MON + * is valid. + * @feature: Required monitor feature (in mon_features file). + * + * Return: True if the feature is supported, else false. + */ +bool resctrl_mon_feature_exists(const char *resource, const char *feature) +{ + char res_path[PATH_MAX]; + char *res; + FILE *inf; + + if (!feature || !resource) + return false; snprintf(res_path, sizeof(res_path), "%s/%s/mon_features", INFO_PATH, resource); inf = fopen(res_path, "r"); @@ -753,7 +766,7 @@ bool validate_resctrl_feature_request(const char *resource, const char *feature) bool test_resource_feature_check(const struct resctrl_test *test) { - return validate_resctrl_feature_request(test->resource, NULL); + return resctrl_resource_exists(test->resource); } int filter_dmesg(void) -- cgit v1.2.3-70-g09d2 From 74e76cbabd7f71f46afdf125dd4f6a54447d87e0 Mon Sep 17 00:00:00 2001 From: Maciej Wieczor-Retman Date: Fri, 16 Feb 2024 09:35:41 +0100 Subject: selftests/resctrl: Add resource_info_file_exists() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Feature checking done by resctrl_mon_feature_exists() covers features represented by the feature name presence inside the 'mon_features' file in /sys/fs/resctrl/info/L3_MON directory. There exists a different way to represent feature support and that is by the presence of 0 or 1 in a single file in the info/resource directory. In this case the filename represents what feature support is being indicated. Add a generic function to check file presence in the /sys/fs/resctrl/info/ directory. Signed-off-by: Maciej Wieczor-Retman Reviewed-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/resctrl.h | 1 + tools/testing/selftests/resctrl/resctrlfs.c | 25 +++++++++++++++++++++++++ 2 files changed, 26 insertions(+) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 6d99ed44ec60..f434a6543b4f 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -138,6 +138,7 @@ int umount_resctrlfs(void); int validate_bw_report_request(char *bw_report); bool resctrl_resource_exists(const char *resource); bool resctrl_mon_feature_exists(const char *resource, const char *feature); +bool resource_info_file_exists(const char *resource, const char *file); bool test_resource_feature_check(const struct resctrl_test *test); char *fgrep(FILE *inf, const char *str); int taskset_benchmark(pid_t bm_pid, int cpu_no, cpu_set_t *old_affinity); diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index 1273e55c4a9d..1cade75176eb 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -764,6 +764,31 @@ bool resctrl_mon_feature_exists(const char *resource, const char *feature) return !!res; } +/* + * resource_info_file_exists - Check if a file is present inside + * /sys/fs/resctrl/info/@resource. + * @resource: Required resource (Eg: MB, L3, L2, etc.) + * @file: Required file. + * + * Return: True if the /sys/fs/resctrl/info/@resource/@file exists, else false. + */ +bool resource_info_file_exists(const char *resource, const char *file) +{ + char res_path[PATH_MAX]; + struct stat statbuf; + + if (!file || !resource) + return false; + + snprintf(res_path, sizeof(res_path), "%s/%s/%s", INFO_PATH, resource, + file); + + if (stat(res_path, &statbuf)) + return false; + + return true; +} + bool test_resource_feature_check(const struct resctrl_test *test) { return resctrl_resource_exists(test->resource); -- cgit v1.2.3-70-g09d2 From ae638551ab64a216364a63c4ee5061f82702fde2 Mon Sep 17 00:00:00 2001 From: Maciej Wieczor-Retman Date: Fri, 16 Feb 2024 09:35:52 +0100 Subject: selftests/resctrl: Add non-contiguous CBMs CAT test MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add tests for both L2 and L3 CAT to verify the return values generated by writing non-contiguous CBMs don't contradict the reported non-contiguous support information. Use a logical XOR to confirm return value of write_schemata() and non-contiguous CBMs support information match. Signed-off-by: Maciej Wieczor-Retman Reviewed-by: Reinette Chatre Reviewed-by: Ilpo Järvinen Signed-off-by: Shuah Khan --- tools/testing/selftests/resctrl/cat_test.c | 89 +++++++++++++++++++++++++ tools/testing/selftests/resctrl/resctrl.h | 2 + tools/testing/selftests/resctrl/resctrl_tests.c | 2 + 3 files changed, 93 insertions(+) (limited to 'tools') diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index 39fc9303b8e8..4cb991be8e31 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -294,6 +294,79 @@ out: return ret; } +static int noncont_cat_run_test(const struct resctrl_test *test, + const struct user_params *uparams) +{ + unsigned long full_cache_mask, cont_mask, noncont_mask; + unsigned int eax, ebx, ecx, edx, sparse_masks; + int bit_center, ret; + char schemata[64]; + + /* Check to compare sparse_masks content to CPUID output. */ + ret = resource_info_unsigned_get(test->resource, "sparse_masks", &sparse_masks); + if (ret) + return ret; + + if (!strcmp(test->resource, "L3")) + __cpuid_count(0x10, 1, eax, ebx, ecx, edx); + else if (!strcmp(test->resource, "L2")) + __cpuid_count(0x10, 2, eax, ebx, ecx, edx); + else + return -EINVAL; + + if (sparse_masks != ((ecx >> 3) & 1)) { + ksft_print_msg("CPUID output doesn't match 'sparse_masks' file content!\n"); + return 1; + } + + /* Write checks initialization. */ + ret = get_full_cbm(test->resource, &full_cache_mask); + if (ret < 0) + return ret; + bit_center = count_bits(full_cache_mask) / 2; + + /* + * The bit_center needs to be at least 3 to properly calculate the CBM + * hole in the noncont_mask. If it's smaller return an error since the + * cache mask is too short and that shouldn't happen. + */ + if (bit_center < 3) + return -EINVAL; + cont_mask = full_cache_mask >> bit_center; + + /* Contiguous mask write check. */ + snprintf(schemata, sizeof(schemata), "%lx", cont_mask); + ret = write_schemata("", schemata, uparams->cpu, test->resource); + if (ret) { + ksft_print_msg("Write of contiguous CBM failed\n"); + return 1; + } + + /* + * Non-contiguous mask write check. CBM has a 0xf hole approximately in the middle. + * Output is compared with support information to catch any edge case errors. + */ + noncont_mask = ~(0xfUL << (bit_center - 2)) & full_cache_mask; + snprintf(schemata, sizeof(schemata), "%lx", noncont_mask); + ret = write_schemata("", schemata, uparams->cpu, test->resource); + if (ret && sparse_masks) + ksft_print_msg("Non-contiguous CBMs supported but write of non-contiguous CBM failed\n"); + else if (ret && !sparse_masks) + ksft_print_msg("Non-contiguous CBMs not supported and write of non-contiguous CBM failed as expected\n"); + else if (!ret && !sparse_masks) + ksft_print_msg("Non-contiguous CBMs not supported but write of non-contiguous CBM succeeded\n"); + + return !ret == !sparse_masks; +} + +static bool noncont_cat_feature_check(const struct resctrl_test *test) +{ + if (!resctrl_resource_exists(test->resource)) + return false; + + return resource_info_file_exists(test->resource, "sparse_masks"); +} + struct resctrl_test l3_cat_test = { .name = "L3_CAT", .group = "CAT", @@ -301,3 +374,19 @@ struct resctrl_test l3_cat_test = { .feature_check = test_resource_feature_check, .run_test = cat_run_test, }; + +struct resctrl_test l3_noncont_cat_test = { + .name = "L3_NONCONT_CAT", + .group = "CAT", + .resource = "L3", + .feature_check = noncont_cat_feature_check, + .run_test = noncont_cat_run_test, +}; + +struct resctrl_test l2_noncont_cat_test = { + .name = "L2_NONCONT_CAT", + .group = "CAT", + .resource = "L2", + .feature_check = noncont_cat_feature_check, + .run_test = noncont_cat_run_test, +}; diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index f434a6543b4f..2051bd135e0d 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -209,5 +209,7 @@ extern struct resctrl_test mbm_test; extern struct resctrl_test mba_test; extern struct resctrl_test cmt_test; extern struct resctrl_test l3_cat_test; +extern struct resctrl_test l3_noncont_cat_test; +extern struct resctrl_test l2_noncont_cat_test; #endif /* RESCTRL_H */ diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c index 3044179ee6e9..f3dc1b9696e7 100644 --- a/tools/testing/selftests/resctrl/resctrl_tests.c +++ b/tools/testing/selftests/resctrl/resctrl_tests.c @@ -19,6 +19,8 @@ static struct resctrl_test *resctrl_tests[] = { &mba_test, &cmt_test, &l3_cat_test, + &l3_noncont_cat_test, + &l2_noncont_cat_test, }; static int detect_vendor(void) -- cgit v1.2.3-70-g09d2 From 1a825e4cdf457b7aef7ebbc2f1206654f5beb150 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 21 Feb 2024 15:12:11 -0800 Subject: selftests: net: veth: test syncing GRO and XDP state while device is down MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Test that we keep GRO flag in sync when XDP is disabled while the device is closed. Signed-off-by: Jakub Kicinski Reviewed-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller --- tools/testing/selftests/net/veth.sh | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'tools') diff --git a/tools/testing/selftests/net/veth.sh b/tools/testing/selftests/net/veth.sh index 27574bbf2d63..5ae85def0739 100755 --- a/tools/testing/selftests/net/veth.sh +++ b/tools/testing/selftests/net/veth.sh @@ -246,6 +246,20 @@ ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on chk_gro " - aggregation with TSO off" 1 cleanup +create_ns +ip -n $NS_DST link set dev veth$DST up +ip -n $NS_DST link set dev veth$DST xdp object ${BPF_FILE} section xdp +chk_gro_flag "gro vs xdp while down - gro flag on" $DST on +ip -n $NS_DST link set dev veth$DST down +chk_gro_flag " - after down" $DST on +ip -n $NS_DST link set dev veth$DST xdp off +chk_gro_flag " - after xdp off" $DST off +ip -n $NS_DST link set dev veth$DST up +chk_gro_flag " - after up" $DST off +ip -n $NS_SRC link set dev veth$SRC xdp object ${BPF_FILE} section xdp +chk_gro_flag " - after peer xdp" $DST off +cleanup + create_ns chk_channels "default channels" $DST 1 1 -- cgit v1.2.3-70-g09d2 From 7092dbee23282b6fcf1313fc64e2b92649ee16e8 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 23 Feb 2024 17:14:12 +0100 Subject: selftests: mptcp: rm subflow with v4/v4mapped addr Now both a v4 address and a v4-mapped address are supported when destroying a userspace pm subflow, this patch adds a second subflow to "userspace pm add & remove address" test, and two subflows could be removed two different ways, one with the v4mapped and one with v4. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/387 Fixes: 48d73f609dcc ("selftests: mptcp: update userspace pm addr tests") Cc: stable@vger.kernel.org Signed-off-by: Geliang Tang Reviewed-by: Mat Martineau Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://lore.kernel.org/r/20240223-upstream-net-20240223-misc-fixes-v1-2-162e87e48497@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 28 ++++++++++++++----------- tools/testing/selftests/net/mptcp/mptcp_lib.sh | 4 ++-- 2 files changed, 18 insertions(+), 14 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index c07386e21e0a..e68b1bc2c2e4 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -3333,16 +3333,17 @@ userspace_pm_rm_sf() { local evts=$evts_ns1 local t=${3:-1} - local ip=4 + local ip local tk da dp sp local cnt [ "$1" == "$ns2" ] && evts=$evts_ns2 - if mptcp_lib_is_v6 $2; then ip=6; fi + [ -n "$(mptcp_lib_evts_get_info "saddr4" "$evts" $t)" ] && ip=4 + [ -n "$(mptcp_lib_evts_get_info "saddr6" "$evts" $t)" ] && ip=6 tk=$(mptcp_lib_evts_get_info token "$evts") - da=$(mptcp_lib_evts_get_info "daddr$ip" "$evts" $t) - dp=$(mptcp_lib_evts_get_info dport "$evts" $t) - sp=$(mptcp_lib_evts_get_info sport "$evts" $t) + da=$(mptcp_lib_evts_get_info "daddr$ip" "$evts" $t $2) + dp=$(mptcp_lib_evts_get_info dport "$evts" $t $2) + sp=$(mptcp_lib_evts_get_info sport "$evts" $t $2) cnt=$(rm_sf_count ${1}) ip netns exec $1 ./pm_nl_ctl dsf lip $2 lport $sp \ @@ -3429,20 +3430,23 @@ userspace_tests() if reset_with_events "userspace pm add & remove address" && continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 - pm_nl_set_limits $ns2 1 1 + pm_nl_set_limits $ns2 2 2 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & local tests_pid=$! wait_mpj $ns1 userspace_pm_add_addr $ns1 10.0.2.1 10 - chk_join_nr 1 1 1 - chk_add_nr 1 1 - chk_mptcp_info subflows 1 subflows 1 - chk_subflows_total 2 2 - chk_mptcp_info add_addr_signal 1 add_addr_accepted 1 + userspace_pm_add_addr $ns1 10.0.3.1 20 + chk_join_nr 2 2 2 + chk_add_nr 2 2 + chk_mptcp_info subflows 2 subflows 2 + chk_subflows_total 3 3 + chk_mptcp_info add_addr_signal 2 add_addr_accepted 2 userspace_pm_rm_addr $ns1 10 userspace_pm_rm_sf $ns1 "::ffff:10.0.2.1" $SUB_ESTABLISHED - chk_rm_nr 1 1 invert + userspace_pm_rm_addr $ns1 20 + userspace_pm_rm_sf $ns1 10.0.3.1 $SUB_ESTABLISHED + chk_rm_nr 2 2 invert chk_mptcp_info subflows 0 subflows 0 chk_subflows_total 1 1 kill_events_pids diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 3a2abae5993e..3777d66fc56d 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -213,9 +213,9 @@ mptcp_lib_get_info_value() { grep "${2}" | sed -n 's/.*\('"${1}"':\)\([0-9a-f:.]*\).*$/\2/p;q' } -# $1: info name ; $2: evts_ns ; $3: event type +# $1: info name ; $2: evts_ns ; [$3: event type; [$4: addr]] mptcp_lib_evts_get_info() { - mptcp_lib_get_info_value "${1}" "^type:${3:-1}," < "${2}" + grep "${4:-}" "${2}" | mptcp_lib_get_info_value "${1}" "^type:${3:-1}," } # $1: PID -- cgit v1.2.3-70-g09d2 From 9480f388a2ef54fba911d9325372abd69a328601 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 23 Feb 2024 17:14:17 +0100 Subject: selftests: mptcp: join: add ss mptcp support check Commands 'ss -M' are used in script mptcp_join.sh to display only MPTCP sockets. So it must be checked if ss tool supports MPTCP in this script. Fixes: e274f7154008 ("selftests: mptcp: add subflow limits test-cases") Cc: stable@vger.kernel.org Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://lore.kernel.org/r/20240223-upstream-net-20240223-misc-fixes-v1-7-162e87e48497@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/mptcp_join.sh | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'tools') diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index e68b1bc2c2e4..e4581b0dfb96 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -161,6 +161,11 @@ check_tools() exit $ksft_skip fi + if ! ss -h | grep -q MPTCP; then + echo "SKIP: ss tool does not support MPTCP" + exit $ksft_skip + fi + # Use the legacy version if available to support old kernel versions if iptables-legacy -V &> /dev/null; then iptables="iptables-legacy" -- cgit v1.2.3-70-g09d2 From b4b51d36bbaa3ddb93b3e1ca3a1ef0aa629d6521 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 23 Feb 2024 17:14:20 +0100 Subject: selftests: mptcp: explicitly trigger the listener diag code-path The mptcp diag interface already experienced a few locking bugs that lockdep and appropriate coverage have detected in advance. Let's add a test-case triggering the relevant code path, to prevent similar issues in the future. Be careful to cope with very slow environments. Note that we don't need an explicit timeout on the mptcp_connect subprocess to cope with eventual bug/hang-up as the final cleanup terminating the child processes will take care of that. Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20240223-upstream-net-20240223-misc-fixes-v1-10-162e87e48497@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/diag.sh | 30 +++++++++++++++++++++++++++++- 1 file changed, 29 insertions(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 0a58ebb8b04c..f300f4e1eb59 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -20,7 +20,7 @@ flush_pids() ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGUSR1 &>/dev/null - for _ in $(seq 10); do + for _ in $(seq $((timeout_poll * 10))); do [ -z "$(ip netns pids "${ns}")" ] && break sleep 0.1 done @@ -91,6 +91,15 @@ chk_msk_nr() __chk_msk_nr "grep -c token:" "$@" } +chk_listener_nr() +{ + local expected=$1 + local msg="$2" + + __chk_nr "ss -inmlHMON $ns | wc -l" "$expected" "$msg - mptcp" 0 + __chk_nr "ss -inmlHtON $ns | wc -l" "$expected" "$msg - subflows" +} + wait_msk_nr() { local condition="grep -c token:" @@ -289,5 +298,24 @@ flush_pids chk_msk_inuse 0 "many->0" chk_msk_cestab 0 "many->0" +chk_listener_nr 0 "no listener sockets" +NR_SERVERS=100 +for I in $(seq 1 $NR_SERVERS); do + ip netns exec $ns ./mptcp_connect -p $((I + 20001)) \ + -t ${timeout_poll} -l 0.0.0.0 >/dev/null 2>&1 & +done + +for I in $(seq 1 $NR_SERVERS); do + mptcp_lib_wait_local_port_listen $ns $((I + 20001)) +done + +chk_listener_nr $NR_SERVERS "many listener sockets" + +# graceful termination +for I in $(seq 1 $NR_SERVERS); do + echo a | ip netns exec $ns ./mptcp_connect -p $((I + 20001)) 127.0.0.1 >/dev/null 2>&1 & +done +flush_pids + mptcp_lib_result_print_all_tap exit $ret -- cgit v1.2.3-70-g09d2 From ee8bd4a428a9c538e08aa5bc797fca19d577f667 Mon Sep 17 00:00:00 2001 From: Mickaël Salaün Date: Thu, 18 Jan 2024 16:14:22 +0100 Subject: kunit: tool: Print UML command MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit As for the Qemu command, print the command used to run tests with UML. Cc: Brendan Higgins Cc: David Gow Signed-off-by: Mickaël Salaün Reviewed-by: David Gow Signed-off-by: Shuah Khan --- tools/testing/kunit/kunit_kernel.py | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 0b6488efed47..7254c110ff23 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -146,6 +146,7 @@ class LinuxSourceTreeOperationsUml(LinuxSourceTreeOperations): """Runs the Linux UML binary. Must be named 'linux'.""" linux_bin = os.path.join(build_dir, 'linux') params.extend(['mem=1G', 'console=tty', 'kunit_shutdown=halt']) + print('Running tests with:\n$', linux_bin, ' '.join(shlex.quote(arg) for arg in params)) return subprocess.Popen([linux_bin] + params, stdin=subprocess.PIPE, stdout=subprocess.PIPE, -- cgit v1.2.3-70-g09d2 From 8ab37b0d98cfe7463cb75a62156ebad9a47d3417 Mon Sep 17 00:00:00 2001 From: Marcos Paulo de Souza Date: Wed, 21 Feb 2024 14:17:03 -0300 Subject: selftests: livepatch: Add initial .gitignore Ignore the binary used to test livepatching a syscall. Signed-off-by: Marcos Paulo de Souza Signed-off-by: Shuah Khan --- tools/testing/selftests/livepatch/.gitignore | 1 + 1 file changed, 1 insertion(+) create mode 100644 tools/testing/selftests/livepatch/.gitignore (limited to 'tools') diff --git a/tools/testing/selftests/livepatch/.gitignore b/tools/testing/selftests/livepatch/.gitignore new file mode 100644 index 000000000000..f1e9c2a20e99 --- /dev/null +++ b/tools/testing/selftests/livepatch/.gitignore @@ -0,0 +1 @@ +test_klp-call_getpid -- cgit v1.2.3-70-g09d2 From 54ee3526796f56c249124686a33e1cc05f76ea21 Mon Sep 17 00:00:00 2001 From: Marcos Paulo de Souza Date: Wed, 21 Feb 2024 14:17:04 -0300 Subject: selftests: livepatch: Avoid running the tests if kernel-devel is missing By checking if KDIR is a valid directory we can safely skip the tests if kernel-devel isn't installed (default value of KDIR), or if KDIR variable passed doesn't exists. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202402191417.XULH88Ct-lkp@intel.com/ Signed-off-by: Marcos Paulo de Souza Signed-off-by: Shuah Khan --- tools/testing/selftests/livepatch/functions.sh | 13 +++++++++++++ tools/testing/selftests/livepatch/test_modules/Makefile | 6 ++++++ 2 files changed, 19 insertions(+) (limited to 'tools') diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh index e60cf09491a6..f0ed148d3c51 100644 --- a/tools/testing/selftests/livepatch/functions.sh +++ b/tools/testing/selftests/livepatch/functions.sh @@ -34,6 +34,18 @@ function is_root() { fi } +# Check if we can compile the modules before loading them +function has_kdir() { + if [ -z "$KDIR" ]; then + KDIR="/lib/modules/$(uname -r)/build" + fi + + if [ ! -d "$KDIR" ]; then + echo "skip all tests: KDIR ($KDIR) not available to compile modules." + exit $ksft_skip + fi +} + # die(msg) - game over, man # msg - dying words function die() { @@ -108,6 +120,7 @@ function cleanup() { # the ftrace_enabled sysctl. function setup_config() { is_root + has_kdir push_config set_dynamic_debug set_ftrace_enabled 1 diff --git a/tools/testing/selftests/livepatch/test_modules/Makefile b/tools/testing/selftests/livepatch/test_modules/Makefile index f5e880269bff..e6e638c4bcba 100644 --- a/tools/testing/selftests/livepatch/test_modules/Makefile +++ b/tools/testing/selftests/livepatch/test_modules/Makefile @@ -13,8 +13,14 @@ obj-m += test_klp_atomic_replace.o \ test_klp_shadow_vars.o \ test_klp_syscall.o +# Ensure that KDIR exists, otherwise skip the compilation modules: +ifneq ("$(wildcard $(KDIR))", "") $(Q)$(MAKE) -C $(KDIR) modules KBUILD_EXTMOD=$(TESTMODS_DIR) +endif +# Ensure that KDIR exists, otherwise skip the clean target clean: +ifneq ("$(wildcard $(KDIR))", "") $(Q)$(MAKE) -C $(KDIR) clean KBUILD_EXTMOD=$(TESTMODS_DIR) +endif -- cgit v1.2.3-70-g09d2 From 539cd3f4da3fdbe7dc353634e004e4b0e725c35a Mon Sep 17 00:00:00 2001 From: Marcos Paulo de Souza Date: Wed, 21 Feb 2024 14:17:05 -0300 Subject: selftests: lib.mk: Do not process TEST_GEN_MODS_DIR The directory itself doesn't need have path handling, since it's only to mean where is the directory that contains modules to be built. Signed-off-by: Marcos Paulo de Souza Signed-off-by: Shuah Khan --- tools/testing/selftests/lib.mk | 3 --- 1 file changed, 3 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 0d8b7db92715..286ce0ee102b 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -54,12 +54,9 @@ endif # TEST_PROGS are for test shell scripts. # TEST_CUSTOM_PROGS and TEST_PROGS will be run by common run_tests # and install targets. Common clean doesn't touch them. -# TEST_GEN_MODS_DIR is used to specify a directory with modules to be built -# before the test executes. These modules are cleaned on the clean target as well. TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) -TEST_GEN_MODS_DIR := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_MODS_DIR)) all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) \ $(if $(TEST_GEN_MODS_DIR),gen_mods_dir) -- cgit v1.2.3-70-g09d2 From 6523cf516c55db164f8f73306027b1caebb5628e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 26 Feb 2024 15:21:48 +0100 Subject: selftests: netfilter: add bridge conntrack + multicast test case Add test case for multicast packet confirm race. Without preceding patch, this should result in: WARNING: CPU: 0 PID: 38 at net/netfilter/nf_conntrack_core.c:1198 __nf_conntrack_confirm+0x3ed/0x5f0 Workqueue: events_unbound macvlan_process_broadcast RIP: 0010:__nf_conntrack_confirm+0x3ed/0x5f0 ? __nf_conntrack_confirm+0x3ed/0x5f0 nf_confirm+0x2ad/0x2d0 nf_hook_slow+0x36/0xd0 ip_local_deliver+0xce/0x110 __netif_receive_skb_one_core+0x4f/0x70 process_backlog+0x8c/0x130 [..] Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/Makefile | 3 +- .../selftests/netfilter/bridge_netfilter.sh | 188 +++++++++++++++++++++ 2 files changed, 190 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/netfilter/bridge_netfilter.sh (limited to 'tools') diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index db27153eb4a0..936c3085bb83 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -7,7 +7,8 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ nft_queue.sh nft_meta.sh nf_nat_edemux.sh \ ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \ conntrack_vrf.sh nft_synproxy.sh rpath.sh nft_audit.sh \ - conntrack_sctp_collision.sh xt_string.sh + conntrack_sctp_collision.sh xt_string.sh \ + bridge_netfilter.sh HOSTPKG_CONFIG := pkg-config diff --git a/tools/testing/selftests/netfilter/bridge_netfilter.sh b/tools/testing/selftests/netfilter/bridge_netfilter.sh new file mode 100644 index 000000000000..659b3ab02c8b --- /dev/null +++ b/tools/testing/selftests/netfilter/bridge_netfilter.sh @@ -0,0 +1,188 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test bridge netfilter + conntrack, a combination that doesn't really work, +# with multicast/broadcast packets racing for hash table insertion. + +# eth0 br0 eth0 +# setup is: ns1 <->,ns0 <-> ns3 +# ns2 <-' `'-> ns4 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +sfx=$(mktemp -u "XXXXXXXX") +ns0="ns0-$sfx" +ns1="ns1-$sfx" +ns2="ns2-$sfx" +ns3="ns3-$sfx" +ns4="ns4-$sfx" + +ebtables -V > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ebtables" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +for i in $(seq 0 4); do + eval ip netns add \$ns$i +done + +cleanup() { + for i in $(seq 0 4); do eval ip netns del \$ns$i;done +} + +trap cleanup EXIT + +do_ping() +{ + fromns="$1" + dstip="$2" + + ip netns exec $fromns ping -c 1 -q $dstip > /dev/null + if [ $? -ne 0 ]; then + echo "ERROR: ping from $fromns to $dstip" + ip netns exec ${ns0} nft list ruleset + ret=1 + fi +} + +bcast_ping() +{ + fromns="$1" + dstip="$2" + + for i in $(seq 1 1000); do + ip netns exec $fromns ping -q -f -b -c 1 -q $dstip > /dev/null 2>&1 + if [ $? -ne 0 ]; then + echo "ERROR: ping -b from $fromns to $dstip" + ip netns exec ${ns0} nft list ruleset + fi + done +} + +ip link add veth1 netns ${ns0} type veth peer name eth0 netns ${ns1} +if [ $? -ne 0 ]; then + echo "SKIP: Can't create veth device" + exit $ksft_skip +fi + +ip link add veth2 netns ${ns0} type veth peer name eth0 netns $ns2 +ip link add veth3 netns ${ns0} type veth peer name eth0 netns $ns3 +ip link add veth4 netns ${ns0} type veth peer name eth0 netns $ns4 + +ip -net ${ns0} link set lo up + +for i in $(seq 1 4); do + ip -net ${ns0} link set veth$i up +done + +ip -net ${ns0} link add br0 type bridge stp_state 0 forward_delay 0 nf_call_iptables 1 nf_call_ip6tables 1 nf_call_arptables 1 +if [ $? -ne 0 ]; then + echo "SKIP: Can't create bridge br0" + exit $ksft_skip +fi + +# make veth0,1,2 part of bridge. +for i in $(seq 1 3); do + ip -net ${ns0} link set veth$i master br0 +done + +# add a macvlan on top of the bridge. +MACVLAN_ADDR=ba:f3:13:37:42:23 +ip -net ${ns0} link add link br0 name macvlan0 type macvlan mode private +ip -net ${ns0} link set macvlan0 address ${MACVLAN_ADDR} +ip -net ${ns0} link set macvlan0 up +ip -net ${ns0} addr add 10.23.0.1/24 dev macvlan0 + +# add a macvlan on top of veth4. +MACVLAN_ADDR=ba:f3:13:37:42:24 +ip -net ${ns0} link add link veth4 name macvlan4 type macvlan mode vepa +ip -net ${ns0} link set macvlan4 address ${MACVLAN_ADDR} +ip -net ${ns0} link set macvlan4 up + +# make the macvlan part of the bridge. +# veth4 is not a bridge port, only the macvlan on top of it. +ip -net ${ns0} link set macvlan4 master br0 + +ip -net ${ns0} link set br0 up +ip -net ${ns0} addr add 10.0.0.1/24 dev br0 +ip netns exec ${ns0} sysctl -q net.bridge.bridge-nf-call-iptables=1 +ret=$? +if [ $ret -ne 0 ] ; then + echo "SKIP: bridge netfilter not available" + ret=$ksft_skip +fi + +# for testing, so namespaces will reply to ping -b probes. +ip netns exec ${ns0} sysctl -q net.ipv4.icmp_echo_ignore_broadcasts=0 + +# enable conntrack in ns0 and drop broadcast packets in forward to +# avoid them from getting confirmed in the postrouting hook before +# the cloned skb is passed up the stack. +ip netns exec ${ns0} nft -f - < Date: Mon, 26 Feb 2024 13:40:18 -0800 Subject: tools: ynl: fix handling of multiple mcast groups We never increment the group number iterator, so all groups get recorded into index 0 of the mcast_groups[] array. As a result YNL can only handle using the last group. For example using the "netdev" sample on kernel with page pool commands results in: $ ./samples/netdev YNL: Multicast group 'mgmt' not found Most families have only one multicast group, so this hasn't been noticed. Plus perhaps developers usually test the last group which would have worked. Fixes: 86878f14d71a ("tools: ynl: user space helpers") Reviewed-by: Donald Hunter Acked-by: Nicolas Dichtel Link: https://lore.kernel.org/r/20240226214019.1255242-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- tools/net/ynl/lib/ynl.c | 1 + 1 file changed, 1 insertion(+) (limited to 'tools') diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c index 6e6d474c8366..45e49671ae87 100644 --- a/tools/net/ynl/lib/ynl.c +++ b/tools/net/ynl/lib/ynl.c @@ -523,6 +523,7 @@ ynl_get_family_info_mcast(struct ynl_sock *ys, const struct nlattr *mcasts) ys->mcast_groups[i].name[GENL_NAMSIZ - 1] = 0; } } + i++; } return 0; -- cgit v1.2.3-70-g09d2 From 380cb2f4df78433f64847cbc655fad2650e4769c Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Fri, 1 Mar 2024 21:10:35 +1100 Subject: selftests/powerpc: Fix fpu_signal failures My recent commit e5d00aaac651 ("selftests/powerpc: Check all FPRs in fpu_preempt") inadvertently broke the fpu_signal test. It needs to take into account that fpu_preempt now loads 32 FPRs, so enlarge darray. Also use the newly added randomise_darray() to properly randomise darray. Finally the checking done in signal_fpu_sig() needs to skip checking f30/f31, because they are used as scratch registers in check_all_fprs(), called by preempt_fpu(), and so could hold other values when the signal is taken. Fixes: e5d00aaac651 ("selftests/powerpc: Check all FPRs in fpu_preempt") Reported-by: Spoorthy Depends-on: 2ba107f6795d ("selftests/powerpc: Generate better bit patterns for FPU tests") Signed-off-by: Michael Ellerman Link: https://msgid.link/20240301101035.1230024-1-mpe@ellerman.id.au --- tools/testing/selftests/powerpc/math/fpu_signal.c | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/powerpc/math/fpu_signal.c b/tools/testing/selftests/powerpc/math/fpu_signal.c index 7b1addd50420..8a64f63e37ce 100644 --- a/tools/testing/selftests/powerpc/math/fpu_signal.c +++ b/tools/testing/selftests/powerpc/math/fpu_signal.c @@ -18,6 +18,7 @@ #include #include "utils.h" +#include "fpu.h" /* Number of times each thread should receive the signal */ #define ITERATIONS 10 @@ -27,9 +28,7 @@ */ #define THREAD_FACTOR 8 -__thread double darray[] = {0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0, - 1.1, 1.2, 1.3, 1.4, 1.5, 1.6, 1.7, 1.8, 1.9, 2.0, - 2.1}; +__thread double darray[32]; bool bad_context; int threads_starting; @@ -43,9 +42,9 @@ void signal_fpu_sig(int sig, siginfo_t *info, void *context) ucontext_t *uc = context; mcontext_t *mc = &uc->uc_mcontext; - /* Only the non volatiles were loaded up */ - for (i = 14; i < 32; i++) { - if (mc->fp_regs[i] != darray[i - 14]) { + // Don't check f30/f31, they're used as scratches in check_all_fprs() + for (i = 0; i < 30; i++) { + if (mc->fp_regs[i] != darray[i]) { bad_context = true; break; } @@ -54,7 +53,6 @@ void signal_fpu_sig(int sig, siginfo_t *info, void *context) void *signal_fpu_c(void *p) { - int i; long rc; struct sigaction act; act.sa_sigaction = signal_fpu_sig; @@ -64,9 +62,7 @@ void *signal_fpu_c(void *p) return p; srand(pthread_self()); - for (i = 0; i < 21; i++) - darray[i] = rand(); - + randomise_darray(darray, ARRAY_SIZE(darray)); rc = preempt_fpu(darray, &threads_starting, &running); return (void *) rc; -- cgit v1.2.3-70-g09d2 From 45bcc0346561daa3f59e19a753cc7f3e08e8dff1 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 1 Mar 2024 18:11:22 +0100 Subject: selftests: mptcp: diag: return KSFT_FAIL not test_cnt The test counter 'test_cnt' should not be returned in diag.sh, e.g. what if only the 4th test fail? Will do 'exit 4' which is 'exit ${KSFT_SKIP}', the whole test will be marked as skipped instead of 'failed'! So we should do ret=${KSFT_FAIL} instead. Fixes: df62f2ec3df6 ("selftests/mptcp: add diag interface tests") Cc: stable@vger.kernel.org Fixes: 42fb6cddec3b ("selftests: mptcp: more stable diag tests") Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: David S. Miller --- tools/testing/selftests/net/mptcp/diag.sh | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index f300f4e1eb59..18d37d4695c1 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -69,7 +69,7 @@ __chk_nr() else echo "[ fail ] expected $expected found $nr" mptcp_lib_result_fail "${msg}" - ret=$test_cnt + ret=${KSFT_FAIL} fi else echo "[ ok ]" @@ -124,11 +124,11 @@ wait_msk_nr() if [ $i -ge $timeout ]; then echo "[ fail ] timeout while expecting $expected max $max last $nr" mptcp_lib_result_fail "${msg} # timeout" - ret=$test_cnt + ret=${KSFT_FAIL} elif [ $nr != $expected ]; then echo "[ fail ] expected $expected found $nr" mptcp_lib_result_fail "${msg} # unexpected result" - ret=$test_cnt + ret=${KSFT_FAIL} else echo "[ ok ]" mptcp_lib_result_pass "${msg}" -- cgit v1.2.3-70-g09d2 From f05d2283d11187675569d3a0286dbaf45d8eb70c Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 1 Mar 2024 18:11:23 +0100 Subject: selftests: mptcp: diag: avoid extra waiting When creating a lot of listener sockets, it is enough to wait only for the last one, like we are doing before in diag.sh for other subtests. If we do a check for each listener sockets, each time listing all available sockets, it can take a very long time in very slow environments, at the point we can reach some timeout. When using the debug kconfig, the waiting time switches from more than 8 sec to 0.1 sec on my side. In slow/busy environments, and with a poll timeout set to 30 ms, the waiting time could go up to ~100 sec because the listener socket would timeout and stop, while the script would still be checking one by one if all sockets are ready. The result is that after having waited for everything to be ready, all sockets have been stopped due to a timeout, and it is too late for the script to check how many there were. While at it, also removed ss options we don't need: we only need the filtering options, to count how many listener sockets have been created. We don't need to ask ss to display internal TCP information, and the memory if the output is dropped by the 'wc -l' command anyway. Fixes: b4b51d36bbaa ("selftests: mptcp: explicitly trigger the listener diag code-path") Reported-by: Jakub Kicinski Closes: https://lore.kernel.org/r/20240301063754.2ecefecf@kernel.org Signed-off-by: Matthieu Baerts (NGI0) Signed-off-by: David S. Miller --- tools/testing/selftests/net/mptcp/diag.sh | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 18d37d4695c1..75fc95675e2d 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -96,8 +96,8 @@ chk_listener_nr() local expected=$1 local msg="$2" - __chk_nr "ss -inmlHMON $ns | wc -l" "$expected" "$msg - mptcp" 0 - __chk_nr "ss -inmlHtON $ns | wc -l" "$expected" "$msg - subflows" + __chk_nr "ss -nlHMON $ns | wc -l" "$expected" "$msg - mptcp" 0 + __chk_nr "ss -nlHtON $ns | wc -l" "$expected" "$msg - subflows" } wait_msk_nr() @@ -304,10 +304,7 @@ for I in $(seq 1 $NR_SERVERS); do ip netns exec $ns ./mptcp_connect -p $((I + 20001)) \ -t ${timeout_poll} -l 0.0.0.0 >/dev/null 2>&1 & done - -for I in $(seq 1 $NR_SERVERS); do - mptcp_lib_wait_local_port_listen $ns $((I + 20001)) -done +mptcp_lib_wait_local_port_listen $ns $((NR_SERVERS + 20001)) chk_listener_nr $NR_SERVERS "many listener sockets" -- cgit v1.2.3-70-g09d2 From 5d94da7ff00ef45737a64d947e7ff45aca972782 Mon Sep 17 00:00:00 2001 From: Laura Nao Date: Thu, 29 Feb 2024 16:52:35 +0100 Subject: kselftest: Add basic test for probing the rust sample modules Add new basic kselftest that checks if the available rust sample modules can be added and removed correctly. Signed-off-by: Laura Nao Reviewed-by: Sergio Gonzalez Collado Reviewed-by: Muhammad Usama Anjum Signed-off-by: Shuah Khan --- MAINTAINERS | 1 + tools/testing/selftests/Makefile | 1 + tools/testing/selftests/rust/Makefile | 4 +++ tools/testing/selftests/rust/config | 5 +++ tools/testing/selftests/rust/test_probe_samples.sh | 41 ++++++++++++++++++++++ 5 files changed, 52 insertions(+) create mode 100644 tools/testing/selftests/rust/Makefile create mode 100644 tools/testing/selftests/rust/config create mode 100755 tools/testing/selftests/rust/test_probe_samples.sh (limited to 'tools') diff --git a/MAINTAINERS b/MAINTAINERS index f8f620746934..4eda22ec74dd 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -19095,6 +19095,7 @@ F: Documentation/rust/ F: rust/ F: samples/rust/ F: scripts/*rust* +F: tools/testing/selftests/rust/ K: \b(?i:rust)\b RXRPC SOCKETS (AF_RXRPC) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 7e5960cda08c..cd9ae576bfde 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -79,6 +79,7 @@ TARGETS += riscv TARGETS += rlimits TARGETS += rseq TARGETS += rtc +TARGETS += rust TARGETS += seccomp TARGETS += sgx TARGETS += sigaltstack diff --git a/tools/testing/selftests/rust/Makefile b/tools/testing/selftests/rust/Makefile new file mode 100644 index 000000000000..fce1584d3bc0 --- /dev/null +++ b/tools/testing/selftests/rust/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +TEST_PROGS += test_probe_samples.sh + +include ../lib.mk diff --git a/tools/testing/selftests/rust/config b/tools/testing/selftests/rust/config new file mode 100644 index 000000000000..b4002acd40bc --- /dev/null +++ b/tools/testing/selftests/rust/config @@ -0,0 +1,5 @@ +CONFIG_RUST=y +CONFIG_SAMPLES=y +CONFIG_SAMPLES_RUST=y +CONFIG_SAMPLE_RUST_MINIMAL=m +CONFIG_SAMPLE_RUST_PRINT=m \ No newline at end of file diff --git a/tools/testing/selftests/rust/test_probe_samples.sh b/tools/testing/selftests/rust/test_probe_samples.sh new file mode 100755 index 000000000000..ad0397e4986f --- /dev/null +++ b/tools/testing/selftests/rust/test_probe_samples.sh @@ -0,0 +1,41 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2023 Collabora Ltd +# +# This script tests whether the rust sample modules can +# be added and removed correctly. +# +DIR="$(dirname "$(readlink -f "$0")")" + +KTAP_HELPERS="${DIR}/../kselftest/ktap_helpers.sh" +if [ -e "$KTAP_HELPERS" ]; then + source "$KTAP_HELPERS" +else + echo "$KTAP_HELPERS file not found [SKIP]" + exit 4 +fi + +rust_sample_modules=("rust_minimal" "rust_print") + +ktap_print_header + +for sample in "${rust_sample_modules[@]}"; do + if ! /sbin/modprobe -n -q "$sample"; then + ktap_skip_all "module $sample is not found in /lib/modules/$(uname -r)" + exit "$KSFT_SKIP" + fi +done + +ktap_set_plan "${#rust_sample_modules[@]}" + +for sample in "${rust_sample_modules[@]}"; do + if /sbin/modprobe -q "$sample"; then + /sbin/modprobe -q -r "$sample" + ktap_test_pass "$sample" + else + ktap_test_fail "$sample" + fi +done + +ktap_finished -- cgit v1.2.3-70-g09d2 From 5c2bc5e2f81d3344095ae241032dde20a4ea2b48 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Thu, 22 Feb 2024 17:41:21 +0200 Subject: selftests/bpf: test case for callback_depth states pruning logic The test case was minimized from mailing list discussion [0]. It is equivalent to the following C program: struct iter_limit_bug_ctx { __u64 a; __u64 b; __u64 c; }; static __naked void iter_limit_bug_cb(void) { switch (bpf_get_prandom_u32()) { case 1: ctx->a = 42; break; case 2: ctx->b = 42; break; default: ctx->c = 42; break; } } int iter_limit_bug(struct __sk_buff *skb) { struct iter_limit_bug_ctx ctx = { 7, 7, 7 }; bpf_loop(2, iter_limit_bug_cb, &ctx, 0); if (ctx.a == 42 && ctx.b == 42 && ctx.c == 7) asm volatile("r1 /= 0;":::"r1"); return 0; } The main idea is that each loop iteration changes one of the state variables in a non-deterministic manner. Hence it is premature to prune the states that have two iterations left comparing them to states with one iteration left. E.g. {{7,7,7}, callback_depth=0} can reach state {42,42,7}, while {{7,7,7}, callback_depth=1} can't. [0] https://lore.kernel.org/bpf/9b251840-7cb8-4d17-bd23-1fc8071d8eef@linux.dev/ Acked-by: Yonghong Song Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20240222154121.6991-3-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov --- .../bpf/progs/verifier_iterating_callbacks.c | 70 ++++++++++++++++++++++ 1 file changed, 70 insertions(+) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c index 5905e036e0ea..a955a6358206 100644 --- a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c +++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c @@ -239,4 +239,74 @@ int bpf_loop_iter_limit_nested(void *unused) return 1000 * a + b + c; } +struct iter_limit_bug_ctx { + __u64 a; + __u64 b; + __u64 c; +}; + +static __naked void iter_limit_bug_cb(void) +{ + /* This is the same as C code below, but written + * in assembly to control which branches are fall-through. + * + * switch (bpf_get_prandom_u32()) { + * case 1: ctx->a = 42; break; + * case 2: ctx->b = 42; break; + * default: ctx->c = 42; break; + * } + */ + asm volatile ( + "r9 = r2;" + "call %[bpf_get_prandom_u32];" + "r1 = r0;" + "r2 = 42;" + "r0 = 0;" + "if r1 == 0x1 goto 1f;" + "if r1 == 0x2 goto 2f;" + "*(u64 *)(r9 + 16) = r2;" + "exit;" + "1: *(u64 *)(r9 + 0) = r2;" + "exit;" + "2: *(u64 *)(r9 + 8) = r2;" + "exit;" + : + : __imm(bpf_get_prandom_u32) + : __clobber_all + ); +} + +SEC("tc") +__failure +__flag(BPF_F_TEST_STATE_FREQ) +int iter_limit_bug(struct __sk_buff *skb) +{ + struct iter_limit_bug_ctx ctx = { 7, 7, 7 }; + + bpf_loop(2, iter_limit_bug_cb, &ctx, 0); + + /* This is the same as C code below, + * written in assembly to guarantee checks order. + * + * if (ctx.a == 42 && ctx.b == 42 && ctx.c == 7) + * asm volatile("r1 /= 0;":::"r1"); + */ + asm volatile ( + "r1 = *(u64 *)%[ctx_a];" + "if r1 != 42 goto 1f;" + "r1 = *(u64 *)%[ctx_b];" + "if r1 != 42 goto 1f;" + "r1 = *(u64 *)%[ctx_c];" + "if r1 != 7 goto 1f;" + "r1 /= 0;" + "1:" + : + : [ctx_a]"m"(ctx.a), + [ctx_b]"m"(ctx.b), + [ctx_c]"m"(ctx.c) + : "r1" + ); + return 0; +} + char _license[] SEC("license") = "GPL"; -- cgit v1.2.3-70-g09d2 From 0bfc0336e1348883fdab4689f0c8c56458f36dd8 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 5 Mar 2024 10:08:29 +0100 Subject: selftests/bpf: Fix up xdp bonding test wrt feature flags MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Adjust the XDP feature flags for the bond device when no bond slave devices are attached. After 9b0ed890ac2a ("bonding: do not report NETDEV_XDP_ACT_XSK_ZEROCOPY"), the empty bond device must report 0 as flags instead of NETDEV_XDP_ACT_MASK. # ./vmtest.sh -- ./test_progs -t xdp_bond [...] [ 3.983311] bond1 (unregistering): (slave veth1_1): Releasing backup interface [ 3.995434] bond1 (unregistering): Released all slaves [ 4.022311] bond2: (slave veth2_1): Releasing backup interface #507/1 xdp_bonding/xdp_bonding_attach:OK #507/2 xdp_bonding/xdp_bonding_nested:OK #507/3 xdp_bonding/xdp_bonding_features:OK #507/4 xdp_bonding/xdp_bonding_roundrobin:OK #507/5 xdp_bonding/xdp_bonding_activebackup:OK #507/6 xdp_bonding/xdp_bonding_xor_layer2:OK #507/7 xdp_bonding/xdp_bonding_xor_layer23:OK #507/8 xdp_bonding/xdp_bonding_xor_layer34:OK #507/9 xdp_bonding/xdp_bonding_redirect_multi:OK #507 xdp_bonding:OK Summary: 1/9 PASSED, 0 SKIPPED, 0 FAILED [ 4.185255] bond2 (unregistering): Released all slaves [...] Fixes: 9b0ed890ac2a ("bonding: do not report NETDEV_XDP_ACT_XSK_ZEROCOPY") Signed-off-by: Daniel Borkmann Reviewed-by: Toke Høiland-Jørgensen Message-ID: <20240305090829.17131-2-daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/prog_tests/xdp_bonding.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c index c3b45745cbcc..6d8b54124cb3 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c @@ -511,7 +511,7 @@ static void test_xdp_bonding_features(struct skeletons *skeletons) if (!ASSERT_OK(err, "bond bpf_xdp_query")) goto out; - if (!ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK, + if (!ASSERT_EQ(query_opts.feature_flags, 0, "bond query_opts.feature_flags")) goto out; @@ -601,7 +601,7 @@ static void test_xdp_bonding_features(struct skeletons *skeletons) if (!ASSERT_OK(err, "bond bpf_xdp_query")) goto out; - ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK, + ASSERT_EQ(query_opts.feature_flags, 0, "bond query_opts.feature_flags"); out: bpf_link__destroy(link); -- cgit v1.2.3-70-g09d2