diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/acct.c | 11 | ||||
-rw-r--r-- | kernel/bpf/task_iter.c | 10 | ||||
-rw-r--r-- | kernel/crash_core.c | 28 | ||||
-rw-r--r-- | kernel/debug/debug_core.c | 12 | ||||
-rw-r--r-- | kernel/events/core.c | 3 | ||||
-rw-r--r-- | kernel/events/uprobes.c | 9 | ||||
-rw-r--r-- | kernel/fork.c | 57 | ||||
-rw-r--r-- | kernel/kallsyms.c | 23 | ||||
-rw-r--r-- | kernel/kallsyms_internal.h | 30 | ||||
-rw-r--r-- | kernel/rcu/tree.c | 2 | ||||
-rw-r--r-- | kernel/resource.c | 19 | ||||
-rw-r--r-- | kernel/sched/fair.c | 10 |
12 files changed, 116 insertions, 98 deletions
diff --git a/kernel/acct.c b/kernel/acct.c index 13706356ec54..62200d799b9b 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -555,15 +555,14 @@ void acct_collect(long exitcode, int group_dead) unsigned long vsize = 0; if (group_dead && current->mm) { + struct mm_struct *mm = current->mm; + VMA_ITERATOR(vmi, mm, 0); struct vm_area_struct *vma; - mmap_read_lock(current->mm); - vma = current->mm->mmap; - while (vma) { + mmap_read_lock(mm); + for_each_vma(vmi, vma) vsize += vma->vm_end - vma->vm_start; - vma = vma->vm_next; - } - mmap_read_unlock(current->mm); + mmap_read_unlock(mm); } spin_lock_irq(¤t->sighand->siglock); diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index 8c921799def4..1c8debd42dc9 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -299,8 +299,8 @@ struct bpf_iter_seq_task_vma_info { }; enum bpf_task_vma_iter_find_op { - task_vma_iter_first_vma, /* use mm->mmap */ - task_vma_iter_next_vma, /* use curr_vma->vm_next */ + task_vma_iter_first_vma, /* use find_vma() with addr 0 */ + task_vma_iter_next_vma, /* use vma_next() with curr_vma */ task_vma_iter_find_vma, /* use find_vma() to find next vma */ }; @@ -400,10 +400,10 @@ again: switch (op) { case task_vma_iter_first_vma: - curr_vma = curr_task->mm->mmap; + curr_vma = find_vma(curr_task->mm, 0); break; case task_vma_iter_next_vma: - curr_vma = curr_vma->vm_next; + curr_vma = find_vma(curr_task->mm, curr_vma->vm_end); break; case task_vma_iter_find_vma: /* We dropped mmap_lock so it is necessary to use find_vma @@ -417,7 +417,7 @@ again: if (curr_vma && curr_vma->vm_start == info->prev_vm_start && curr_vma->vm_end == info->prev_vm_end) - curr_vma = curr_vma->vm_next; + curr_vma = find_vma(curr_task->mm, curr_vma->vm_end); break; } if (!curr_vma) { diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 71122e01623c..07b26df453a9 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -9,12 +9,15 @@ #include <linux/init.h> #include <linux/utsname.h> #include <linux/vmalloc.h> +#include <linux/sizes.h> #include <asm/page.h> #include <asm/sections.h> #include <crypto/sha1.h> +#include "kallsyms_internal.h" + /* vmcoreinfo stuff */ unsigned char *vmcoreinfo_data; size_t vmcoreinfo_size; @@ -43,6 +46,15 @@ static int __init parse_crashkernel_mem(char *cmdline, unsigned long long *crash_base) { char *cur = cmdline, *tmp; + unsigned long long total_mem = system_ram; + + /* + * Firmware sometimes reserves some memory regions for its own use, + * so the system memory size is less than the actual physical memory + * size. Work around this by rounding up the total size to 128M, + * which is enough for most test cases. + */ + total_mem = roundup(total_mem, SZ_128M); /* for each entry of the comma-separated list */ do { @@ -87,13 +99,13 @@ static int __init parse_crashkernel_mem(char *cmdline, return -EINVAL; } cur = tmp; - if (size >= system_ram) { + if (size >= total_mem) { pr_warn("crashkernel: invalid size\n"); return -EINVAL; } /* match ? */ - if (system_ram >= start && system_ram < end) { + if (total_mem >= start && total_mem < end) { *crash_size = size; break; } @@ -480,6 +492,18 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE); #endif +#ifdef CONFIG_KALLSYMS + VMCOREINFO_SYMBOL(kallsyms_names); + VMCOREINFO_SYMBOL(kallsyms_token_table); + VMCOREINFO_SYMBOL(kallsyms_token_index); +#ifdef CONFIG_KALLSYMS_BASE_RELATIVE + VMCOREINFO_SYMBOL(kallsyms_offsets); + VMCOREINFO_SYMBOL(kallsyms_relative_base); +#else + VMCOREINFO_SYMBOL(kallsyms_addresses); +#endif /* CONFIG_KALLSYMS_BASE_RELATIVE */ +#endif /* CONFIG_KALLSYMS */ + arch_crash_save_vmcoreinfo(); update_vmcoreinfo_note(); diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 7beceb447211..d5e9ccde3ab8 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -50,7 +50,6 @@ #include <linux/pid.h> #include <linux/smp.h> #include <linux/mm.h> -#include <linux/vmacache.h> #include <linux/rcupdate.h> #include <linux/irq.h> #include <linux/security.h> @@ -283,17 +282,6 @@ static void kgdb_flush_swbreak_addr(unsigned long addr) if (!CACHE_FLUSH_IS_SAFE) return; - if (current->mm) { - int i; - - for (i = 0; i < VMACACHE_SIZE; i++) { - if (!current->vmacache.vmas[i]) - continue; - flush_cache_range(current->vmacache.vmas[i], - addr, addr + BREAK_INSTR_SIZE); - } - } - /* Force flush instruction cache if it was outside the mm */ flush_icache_range(addr, addr + BREAK_INSTR_SIZE); } diff --git a/kernel/events/core.c b/kernel/events/core.c index 48bae58d240e..3f84bfc9e50a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10214,8 +10214,9 @@ static void perf_addr_filter_apply(struct perf_addr_filter *filter, struct perf_addr_filter_range *fr) { struct vm_area_struct *vma; + VMA_ITERATOR(vmi, mm, 0); - for (vma = mm->mmap; vma; vma = vma->vm_next) { + for_each_vma(vmi, vma) { if (!vma->vm_file) continue; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 2eaa327f8158..401bc2d24ce0 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -349,9 +349,10 @@ static bool valid_ref_ctr_vma(struct uprobe *uprobe, static struct vm_area_struct * find_ref_ctr_vma(struct uprobe *uprobe, struct mm_struct *mm) { + VMA_ITERATOR(vmi, mm, 0); struct vm_area_struct *tmp; - for (tmp = mm->mmap; tmp; tmp = tmp->vm_next) + for_each_vma(vmi, tmp) if (valid_ref_ctr_vma(uprobe, tmp)) return tmp; @@ -1231,11 +1232,12 @@ int uprobe_apply(struct inode *inode, loff_t offset, static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm) { + VMA_ITERATOR(vmi, mm, 0); struct vm_area_struct *vma; int err = 0; mmap_read_lock(mm); - for (vma = mm->mmap; vma; vma = vma->vm_next) { + for_each_vma(vmi, vma) { unsigned long vaddr; loff_t offset; @@ -1983,9 +1985,10 @@ bool uprobe_deny_signal(void) static void mmf_recalc_uprobes(struct mm_struct *mm) { + VMA_ITERATOR(vmi, mm, 0); struct vm_area_struct *vma; - for (vma = mm->mmap; vma; vma = vma->vm_next) { + for_each_vma(vmi, vma) { if (!valid_vma(vma, false)) continue; /* diff --git a/kernel/fork.c b/kernel/fork.c index 3ec068a68a30..23f0ba3affe5 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -43,7 +43,6 @@ #include <linux/fs.h> #include <linux/mm.h> #include <linux/mm_inline.h> -#include <linux/vmacache.h> #include <linux/nsproxy.h> #include <linux/capability.h> #include <linux/cpu.h> @@ -475,7 +474,6 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) */ *new = data_race(*orig); INIT_LIST_HEAD(&new->anon_vma_chain); - new->vm_next = new->vm_prev = NULL; dup_anon_vma_name(orig, new); } return new; @@ -580,10 +578,11 @@ static void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm) static __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { - struct vm_area_struct *mpnt, *tmp, *prev, **pprev; - struct rb_node **rb_link, *rb_parent; + struct vm_area_struct *mpnt, *tmp; int retval; - unsigned long charge; + unsigned long charge = 0; + MA_STATE(old_mas, &oldmm->mm_mt, 0, 0); + MA_STATE(mas, &mm->mm_mt, 0, 0); LIST_HEAD(uf); uprobe_start_dup_mmap(); @@ -606,16 +605,16 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, mm->exec_vm = oldmm->exec_vm; mm->stack_vm = oldmm->stack_vm; - rb_link = &mm->mm_rb.rb_node; - rb_parent = NULL; - pprev = &mm->mmap; retval = ksm_fork(mm, oldmm); if (retval) goto out; khugepaged_fork(mm, oldmm); - prev = NULL; - for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) { + retval = mas_expected_entries(&mas, oldmm->map_count); + if (retval) + goto out; + + mas_for_each(&old_mas, mpnt, ULONG_MAX) { struct file *file; if (mpnt->vm_flags & VM_DONTCOPY) { @@ -629,7 +628,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, */ if (fatal_signal_pending(current)) { retval = -EINTR; - goto out; + goto loop_out; } if (mpnt->vm_flags & VM_ACCOUNT) { unsigned long len = vma_pages(mpnt); @@ -682,17 +681,10 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, if (is_vm_hugetlb_page(tmp)) reset_vma_resv_huge_pages(tmp); - /* - * Link in the new vma and copy the page table entries. - */ - *pprev = tmp; - pprev = &tmp->vm_next; - tmp->vm_prev = prev; - prev = tmp; - - __vma_link_rb(mm, tmp, rb_link, rb_parent); - rb_link = &tmp->vm_rb.rb_right; - rb_parent = &tmp->vm_rb; + /* Link the vma into the MT */ + mas.index = tmp->vm_start; + mas.last = tmp->vm_end - 1; + mas_store(&mas, tmp); mm->map_count++; if (!(tmp->vm_flags & VM_WIPEONFORK)) @@ -702,10 +694,12 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, tmp->vm_ops->open(tmp); if (retval) - goto out; + goto loop_out; } /* a new mm has just been created */ retval = arch_dup_mmap(oldmm, mm); +loop_out: + mas_destroy(&mas); out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); @@ -721,7 +715,7 @@ fail_nomem_policy: fail_nomem: retval = -ENOMEM; vm_unacct_memory(charge); - goto out; + goto loop_out; } static inline int mm_alloc_pgd(struct mm_struct *mm) @@ -1109,9 +1103,8 @@ static void mm_init_uprobes_state(struct mm_struct *mm) static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, struct user_namespace *user_ns) { - mm->mmap = NULL; - mm->mm_rb = RB_ROOT; - mm->vmacache_seqnum = 0; + mt_init_flags(&mm->mm_mt, MM_MT_FLAGS); + mt_set_external_lock(&mm->mm_mt, &mm->mmap_lock); atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); seqcount_init(&mm->write_protect_seq); @@ -1284,13 +1277,16 @@ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) /* Forbid mm->exe_file change if old file still mapped. */ old_exe_file = get_mm_exe_file(mm); if (old_exe_file) { + VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); - for (vma = mm->mmap; vma && !ret; vma = vma->vm_next) { + for_each_vma(vmi, vma) { if (!vma->vm_file) continue; if (path_equal(&vma->vm_file->f_path, - &old_exe_file->f_path)) + &old_exe_file->f_path)) { ret = -EBUSY; + break; + } } mmap_read_unlock(mm); fput(old_exe_file); @@ -1566,9 +1562,6 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) if (!oldmm) return 0; - /* initialize the new vmacache entries */ - vmacache_flush(tsk); - if (clone_flags & CLONE_VM) { mmget(oldmm); mm = oldmm; diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 87e2b1638115..f55c63d9d39a 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -31,28 +31,7 @@ #include <linux/kernel.h> #include <linux/bsearch.h> -/* - * These will be re-linked against their real values - * during the second link stage. - */ -extern const unsigned long kallsyms_addresses[] __weak; -extern const int kallsyms_offsets[] __weak; -extern const u8 kallsyms_names[] __weak; - -/* - * Tell the compiler that the count isn't in the small data section if the arch - * has one (eg: FRV). - */ -extern const unsigned int kallsyms_num_syms -__section(".rodata") __attribute__((weak)); - -extern const unsigned long kallsyms_relative_base -__section(".rodata") __attribute__((weak)); - -extern const char kallsyms_token_table[] __weak; -extern const u16 kallsyms_token_index[] __weak; - -extern const unsigned int kallsyms_markers[] __weak; +#include "kallsyms_internal.h" /* * Expand a compressed symbol data into the resulting uncompressed string, diff --git a/kernel/kallsyms_internal.h b/kernel/kallsyms_internal.h new file mode 100644 index 000000000000..2d0c6f2f0243 --- /dev/null +++ b/kernel/kallsyms_internal.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef LINUX_KALLSYMS_INTERNAL_H_ +#define LINUX_KALLSYMS_INTERNAL_H_ + +#include <linux/types.h> + +/* + * These will be re-linked against their real values + * during the second link stage. + */ +extern const unsigned long kallsyms_addresses[] __weak; +extern const int kallsyms_offsets[] __weak; +extern const u8 kallsyms_names[] __weak; + +/* + * Tell the compiler that the count isn't in the small data section if the arch + * has one (eg: FRV). + */ +extern const unsigned int kallsyms_num_syms +__section(".rodata") __attribute__((weak)); + +extern const unsigned long kallsyms_relative_base +__section(".rodata") __attribute__((weak)); + +extern const char kallsyms_token_table[] __weak; +extern const u16 kallsyms_token_index[] __weak; + +extern const unsigned int kallsyms_markers[] __weak; + +#endif // LINUX_KALLSYMS_INTERNAL_H_ diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 89cb173a1a95..9e1b600e6925 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -4569,7 +4569,7 @@ static void __init kfree_rcu_batch_init(void) INIT_DELAYED_WORK(&krcp->page_cache_work, fill_page_cache_func); krcp->initialized = true; } - if (register_shrinker(&kfree_rcu_shrinker)) + if (register_shrinker(&kfree_rcu_shrinker, "rcu-kfree")) pr_err("Failed to register kfree_rcu() shrinker!\n"); } diff --git a/kernel/resource.c b/kernel/resource.c index 34eaee179689..ecf6b9a50adc 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -311,7 +311,7 @@ EXPORT_SYMBOL(release_resource); * * If a resource is found, returns 0 and @*res is overwritten with the part * of the resource that's within [@start..@end]; if none is found, returns - * -ENODEV. Returns -EINVAL for invalid parameters. + * -ENODEV. * * @start: start address of the resource searched for * @end: end address of same resource @@ -328,9 +328,6 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end, { struct resource *p; - if (!res) - return -EINVAL; - if (start >= end) return -EINVAL; @@ -356,7 +353,7 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end, break; } - if (p) { + if (p && res) { /* copy data */ *res = (struct resource) { .start = max(start, p->start), @@ -474,18 +471,18 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, return ret; } -static int __is_ram(unsigned long pfn, unsigned long nr_pages, void *arg) -{ - return 1; -} - /* * This generic page_is_ram() returns true if specified address is * registered as System RAM in iomem_resource list. */ int __weak page_is_ram(unsigned long pfn) { - return walk_system_ram_range(pfn, 1, NULL, __is_ram) == 1; + const resource_size_t pfn_res = PFN_PHYS(pfn); + + return find_next_iomem_res(pfn_res, + pfn_res + 1, + IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY, + IORES_DESC_NONE, NULL) == 0; } EXPORT_SYMBOL_GPL(page_is_ram); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 8bed75757e65..78795a997d9c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2768,6 +2768,7 @@ static void task_numa_work(struct callback_head *work) struct task_struct *p = current; struct mm_struct *mm = p->mm; u64 runtime = p->se.sum_exec_runtime; + MA_STATE(mas, &mm->mm_mt, 0, 0); struct vm_area_struct *vma; unsigned long start, end; unsigned long nr_pte_updates = 0; @@ -2824,13 +2825,16 @@ static void task_numa_work(struct callback_head *work) if (!mmap_read_trylock(mm)) return; - vma = find_vma(mm, start); + mas_set(&mas, start); + vma = mas_find(&mas, ULONG_MAX); if (!vma) { reset_ptenuma_scan(p); start = 0; - vma = mm->mmap; + mas_set(&mas, start); + vma = mas_find(&mas, ULONG_MAX); } - for (; vma; vma = vma->vm_next) { + + for (; vma; vma = mas_find(&mas, ULONG_MAX)) { if (!vma_migratable(vma) || !vma_policy_mof(vma) || is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) { continue; |