diff options
Diffstat (limited to 'fs/proc')
| -rw-r--r-- | fs/proc/Kconfig | 15 | ||||
| -rw-r--r-- | fs/proc/array.c | 35 | ||||
| -rw-r--r-- | fs/proc/base.c | 270 | ||||
| -rw-r--r-- | fs/proc/fd.c | 2 | ||||
| -rw-r--r-- | fs/proc/internal.h | 4 | ||||
| -rw-r--r-- | fs/proc/page.c | 2 | ||||
| -rw-r--r-- | fs/proc/task_mmu.c | 39 | ||||
| -rw-r--r-- | fs/proc/vmcore.c | 386 |
8 files changed, 550 insertions, 203 deletions
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index 1ade1206bb89..0eaeb41453f5 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -43,6 +43,21 @@ config PROC_VMCORE help Exports the dump image of crashed kernel in ELF format. +config PROC_VMCORE_DEVICE_DUMP + bool "Device Hardware/Firmware Log Collection" + depends on PROC_VMCORE + default n + help + After kernel panic, device drivers can collect the device + specific snapshot of their hardware or firmware before the + underlying devices are initialized in crash recovery kernel. + Note that the device driver must be present in the crash + recovery kernel's initramfs to collect its underlying device + snapshot. + + If you say Y here, the collected device dumps will be added + as ELF notes to /proc/vmcore. + config PROC_SYSCTL bool "Sysctl support (/proc/sys)" if EXPERT depends on PROC_FS diff --git a/fs/proc/array.c b/fs/proc/array.c index e6d7f41b6684..0ceb3b6b37e7 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -96,22 +96,29 @@ #include <asm/processor.h> #include "internal.h" -static inline void task_name(struct seq_file *m, struct task_struct *p) +void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape) { char *buf; size_t size; - char tcomm[sizeof(p->comm)]; + char tcomm[64]; int ret; - get_task_comm(tcomm, p); - - seq_puts(m, "Name:\t"); + if (p->flags & PF_WQ_WORKER) + wq_worker_comm(tcomm, sizeof(tcomm), p); + else + __get_task_comm(tcomm, sizeof(tcomm), p); size = seq_get_buf(m, &buf); - ret = string_escape_str(tcomm, buf, size, ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\"); - seq_commit(m, ret < size ? ret : -1); + if (escape) { + ret = string_escape_str(tcomm, buf, size, + ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\"); + if (ret >= size) + ret = -1; + } else { + ret = strscpy(buf, tcomm, size); + } - seq_putc(m, '\n'); + seq_commit(m, ret); } /* @@ -261,7 +268,7 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p) unsigned long flags; sigset_t pending, shpending, blocked, ignored, caught; int num_threads = 0; - unsigned long qsize = 0; + unsigned int qsize = 0; unsigned long qlim = 0; sigemptyset(&pending); @@ -390,7 +397,10 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, { struct mm_struct *mm = get_task_mm(task); - task_name(m, task); + seq_puts(m, "Name:\t"); + proc_task_name(m, task, true); + seq_putc(m, '\n'); + task_state(m, ns, pid, task); if (mm) { @@ -425,7 +435,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, u64 cutime, cstime, utime, stime; u64 cgtime, gtime; unsigned long rsslim = 0; - char tcomm[sizeof(task->comm)]; unsigned long flags; state = *get_task_state(task); @@ -452,8 +461,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, } } - get_task_comm(tcomm, task); - sigemptyset(&sigign); sigemptyset(&sigcatch); cutime = cstime = utime = stime = 0; @@ -520,7 +527,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, seq_put_decimal_ull(m, "", pid_nr_ns(pid, ns)); seq_puts(m, " ("); - seq_puts(m, tcomm); + proc_task_name(m, task, false); seq_puts(m, ") "); seq_putc(m, state); seq_put_decimal_ll(m, " ", ppid); diff --git a/fs/proc/base.c b/fs/proc/base.c index 33ed1746927a..4aa9ce5df02f 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -205,171 +205,129 @@ static int proc_root_link(struct dentry *dentry, struct path *path) return result; } -static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, - size_t _count, loff_t *pos) +static ssize_t get_mm_cmdline(struct mm_struct *mm, char __user *buf, + size_t count, loff_t *ppos) { - struct task_struct *tsk; - struct mm_struct *mm; - char *page; - unsigned long count = _count; unsigned long arg_start, arg_end, env_start, env_end; - unsigned long len1, len2, len; - unsigned long p; - char c; - ssize_t rv; - - BUG_ON(*pos < 0); + unsigned long pos, len; + char *page; - tsk = get_proc_task(file_inode(file)); - if (!tsk) - return -ESRCH; - mm = get_task_mm(tsk); - put_task_struct(tsk); - if (!mm) - return 0; /* Check if process spawned far enough to have cmdline. */ - if (!mm->env_end) { - rv = 0; - goto out_mmput; - } - - page = (char *)__get_free_page(GFP_KERNEL); - if (!page) { - rv = -ENOMEM; - goto out_mmput; - } + if (!mm->env_end) + return 0; - down_read(&mm->mmap_sem); + spin_lock(&mm->arg_lock); arg_start = mm->arg_start; arg_end = mm->arg_end; env_start = mm->env_start; env_end = mm->env_end; - up_read(&mm->mmap_sem); - - BUG_ON(arg_start > arg_end); - BUG_ON(env_start > env_end); + spin_unlock(&mm->arg_lock); - len1 = arg_end - arg_start; - len2 = env_end - env_start; + if (arg_start >= arg_end) + return 0; - /* Empty ARGV. */ - if (len1 == 0) { - rv = 0; - goto out_free_page; - } /* - * Inherently racy -- command line shares address space - * with code and data. + * We have traditionally allowed the user to re-write + * the argument strings and overflow the end result + * into the environment section. But only do that if + * the environment area is contiguous to the arguments. */ - rv = access_remote_vm(mm, arg_end - 1, &c, 1, FOLL_ANON); - if (rv <= 0) - goto out_free_page; - - rv = 0; - - if (c == '\0') { - /* Command line (set of strings) occupies whole ARGV. */ - if (len1 <= *pos) - goto out_free_page; - - p = arg_start + *pos; - len = len1 - *pos; - while (count > 0 && len > 0) { - unsigned int _count; - int nr_read; - - _count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON); - if (nr_read < 0) - rv = nr_read; - if (nr_read <= 0) - goto out_free_page; - - if (copy_to_user(buf, page, nr_read)) { - rv = -EFAULT; - goto out_free_page; - } + if (env_start != arg_end || env_start >= env_end) + env_start = env_end = arg_end; - p += nr_read; - len -= nr_read; - buf += nr_read; - count -= nr_read; - rv += nr_read; - } - } else { - /* - * Command line (1 string) occupies ARGV and - * extends into ENVP. - */ - struct { - unsigned long p; - unsigned long len; - } cmdline[2] = { - { .p = arg_start, .len = len1 }, - { .p = env_start, .len = len2 }, - }; - loff_t pos1 = *pos; - unsigned int i; + /* We're not going to care if "*ppos" has high bits set */ + pos = arg_start + *ppos; + + /* .. but we do check the result is in the proper range */ + if (pos < arg_start || pos >= env_end) + return 0; + + /* .. and we never go past env_end */ + if (env_end - pos < count) + count = env_end - pos; + + page = (char *)__get_free_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + + len = 0; + while (count) { + int got; + size_t size = min_t(size_t, PAGE_SIZE, count); + + got = access_remote_vm(mm, pos, page, size, FOLL_ANON); + if (got <= 0) + break; + + /* Don't walk past a NUL character once you hit arg_end */ + if (pos + got >= arg_end) { + int n = 0; - i = 0; - while (i < 2 && pos1 >= cmdline[i].len) { - pos1 -= cmdline[i].len; - i++; + /* + * If we started before 'arg_end' but ended up + * at or after it, we start the NUL character + * check at arg_end-1 (where we expect the normal + * EOF to be). + * + * NOTE! This is smaller than 'got', because + * pos + got >= arg_end + */ + if (pos < arg_end) + n = arg_end - pos - 1; + + /* Cut off at first NUL after 'n' */ + got = n + strnlen(page+n, got-n); + if (!got) + break; } - while (i < 2) { - p = cmdline[i].p + pos1; - len = cmdline[i].len - pos1; - while (count > 0 && len > 0) { - unsigned int _count, l; - int nr_read; - bool final; - - _count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON); - if (nr_read < 0) - rv = nr_read; - if (nr_read <= 0) - goto out_free_page; - - /* - * Command line can be shorter than whole ARGV - * even if last "marker" byte says it is not. - */ - final = false; - l = strnlen(page, nr_read); - if (l < nr_read) { - nr_read = l; - final = true; - } - - if (copy_to_user(buf, page, nr_read)) { - rv = -EFAULT; - goto out_free_page; - } - - p += nr_read; - len -= nr_read; - buf += nr_read; - count -= nr_read; - rv += nr_read; - - if (final) - goto out_free_page; - } - /* Only first chunk can be read partially. */ - pos1 = 0; - i++; + got -= copy_to_user(buf, page, got); + if (unlikely(!got)) { + if (!len) + len = -EFAULT; + break; } + pos += got; + buf += got; + len += got; + count -= got; } -out_free_page: free_page((unsigned long)page); -out_mmput: + return len; +} + +static ssize_t get_task_cmdline(struct task_struct *tsk, char __user *buf, + size_t count, loff_t *pos) +{ + struct mm_struct *mm; + ssize_t ret; + + mm = get_task_mm(tsk); + if (!mm) + return 0; + + ret = get_mm_cmdline(mm, buf, count, pos); mmput(mm); - if (rv > 0) - *pos += rv; - return rv; + return ret; +} + +static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, + size_t count, loff_t *pos) +{ + struct task_struct *tsk; + ssize_t ret; + + BUG_ON(*pos < 0); + + tsk = get_proc_task(file_inode(file)); + if (!tsk) + return -ESRCH; + ret = get_task_cmdline(tsk, buf, count, pos); + put_task_struct(tsk); + if (ret > 0) + *pos += ret; + return ret; } static const struct file_operations proc_pid_cmdline_ops = { @@ -430,7 +388,6 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, struct stack_trace trace; unsigned long *entries; int err; - int i; entries = kmalloc(MAX_STACK_TRACE_DEPTH * sizeof(*entries), GFP_KERNEL); if (!entries) @@ -443,6 +400,8 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, err = lock_trace(task); if (!err) { + unsigned int i; + save_stack_trace_tsk(task, &trace); for (i = 0; i < trace.nr_entries; i++) { @@ -927,10 +886,10 @@ static ssize_t environ_read(struct file *file, char __user *buf, if (!mmget_not_zero(mm)) goto free; - down_read(&mm->mmap_sem); + spin_lock(&mm->arg_lock); env_start = mm->env_start; env_end = mm->env_end; - up_read(&mm->mmap_sem); + spin_unlock(&mm->arg_lock); while (count > 0) { size_t this_len, max_len; @@ -1563,9 +1522,8 @@ static int comm_show(struct seq_file *m, void *v) if (!p) return -ESRCH; - task_lock(p); - seq_printf(m, "%s\n", p->comm); - task_unlock(p); + proc_task_name(m, p, false); + seq_putc(m, '\n'); put_task_struct(p); @@ -1785,9 +1743,9 @@ int pid_getattr(const struct path *path, struct kstat *stat, generic_fillattr(inode, stat); - rcu_read_lock(); stat->uid = GLOBAL_ROOT_UID; stat->gid = GLOBAL_ROOT_GID; + rcu_read_lock(); task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) { if (!has_pid_permissions(pid, task, HIDEPID_INVISIBLE)) { @@ -1876,7 +1834,7 @@ const struct dentry_operations pid_dentry_operations = * by stat. */ bool proc_fill_cache(struct file *file, struct dir_context *ctx, - const char *name, int len, + const char *name, unsigned int len, instantiate_t instantiate, struct task_struct *task, const void *ptr) { struct dentry *child, *dir = file->f_path.dentry; @@ -1895,19 +1853,19 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx, struct dentry *res; res = instantiate(child, task, ptr); d_lookup_done(child); - if (IS_ERR(res)) - goto end_instantiate; if (unlikely(res)) { dput(child); child = res; + if (IS_ERR(child)) + goto end_instantiate; } } } inode = d_inode(child); ino = inode->i_ino; type = inode->i_mode >> 12; -end_instantiate: dput(child); +end_instantiate: return dir_emit(ctx, name, len, ino, type); } @@ -3252,7 +3210,7 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx) iter.task; iter.tgid += 1, iter = next_tgid(ns, iter)) { char name[10 + 1]; - int len; + unsigned int len; cond_resched(); if (!has_pid_permissions(ns, iter.task, HIDEPID_INVISIBLE)) @@ -3579,7 +3537,7 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx) task; task = next_tid(task), ctx->pos++) { char name[10 + 1]; - int len; + unsigned int len; tid = task_pid_nr_ns(task, ns); len = snprintf(name, sizeof(name), "%u", tid); if (!proc_fill_cache(file, ctx, name, len, diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 05b9893e9a22..81882a13212d 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -248,7 +248,7 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx, struct file *f; struct fd_data data; char name[10 + 1]; - int len; + unsigned int len; f = fcheck_files(files, fd); if (!f) diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 43c70c9e6b62..50cb22a08c2f 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -136,6 +136,8 @@ unsigned name_to_int(const struct qstr *qstr); */ extern const struct file_operations proc_tid_children_operations; +extern void proc_task_name(struct seq_file *m, struct task_struct *p, + bool escape); extern int proc_tid_stat(struct seq_file *, struct pid_namespace *, struct pid *, struct task_struct *); extern int proc_tgid_stat(struct seq_file *, struct pid_namespace *, @@ -161,7 +163,7 @@ extern loff_t mem_lseek(struct file *, loff_t, int); /* Lookups */ typedef struct dentry *instantiate_t(struct dentry *, struct task_struct *, const void *); -extern bool proc_fill_cache(struct file *, struct dir_context *, const char *, int, +bool proc_fill_cache(struct file *, struct dir_context *, const char *, unsigned int, instantiate_t, struct task_struct *, const void *); /* diff --git a/fs/proc/page.c b/fs/proc/page.c index 1491918a33c3..792c78a49174 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -154,6 +154,8 @@ u64 stable_page_flags(struct page *page) if (PageBalloon(page)) u |= 1 << KPF_BALLOON; + if (PageTable(page)) + u |= 1 << KPF_PGTABLE; if (page_is_idle(page)) u |= 1 << KPF_IDLE; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index a20c6e495bb2..597969db9e90 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -18,6 +18,7 @@ #include <linux/page_idle.h> #include <linux/shmem_fs.h> #include <linux/uaccess.h> +#include <linux/pkeys.h> #include <asm/elf.h> #include <asm/tlb.h> @@ -673,13 +674,16 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_MERGEABLE)] = "mg", [ilog2(VM_UFFD_MISSING)]= "um", [ilog2(VM_UFFD_WP)] = "uw", -#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS +#ifdef CONFIG_ARCH_HAS_PKEYS /* These come out via ProtectionKey: */ [ilog2(VM_PKEY_BIT0)] = "", [ilog2(VM_PKEY_BIT1)] = "", [ilog2(VM_PKEY_BIT2)] = "", [ilog2(VM_PKEY_BIT3)] = "", +#if VM_PKEY_BIT4 + [ilog2(VM_PKEY_BIT4)] = "", #endif +#endif /* CONFIG_ARCH_HAS_PKEYS */ }; size_t i; @@ -727,10 +731,6 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, } #endif /* HUGETLB_PAGE */ -void __weak arch_show_smap(struct seq_file *m, struct vm_area_struct *vma) -{ -} - #define SEQ_PUT_DEC(str, val) \ seq_put_decimal_ull_width(m, str, (val) >> 10, 8) static int show_smap(struct seq_file *m, void *v, int is_pid) @@ -835,7 +835,8 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) seq_puts(m, " kB\n"); } if (!rollup_mode) { - arch_show_smap(m, vma); + if (arch_pkeys_enabled()) + seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma)); show_smap_vma_flags(m, vma); } m_cache_vma(m, vma); @@ -1258,8 +1259,9 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, if (pte_swp_soft_dirty(pte)) flags |= PM_SOFT_DIRTY; entry = pte_to_swp_entry(pte); - frame = swp_type(entry) | - (swp_offset(entry) << MAX_SWAPFILES_SHIFT); + if (pm->show_pfn) + frame = swp_type(entry) | + (swp_offset(entry) << MAX_SWAPFILES_SHIFT); flags |= PM_SWAP; if (is_migration_entry(entry)) page = migration_entry_to_page(entry); @@ -1310,11 +1312,14 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION else if (is_swap_pmd(pmd)) { swp_entry_t entry = pmd_to_swp_entry(pmd); - unsigned long offset = swp_offset(entry); + unsigned long offset; - offset += (addr & ~PMD_MASK) >> PAGE_SHIFT; - frame = swp_type(entry) | - (offset << MAX_SWAPFILES_SHIFT); + if (pm->show_pfn) { + offset = swp_offset(entry) + + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + frame = swp_type(entry) | + (offset << MAX_SWAPFILES_SHIFT); + } flags |= PM_SWAP; if (pmd_swp_soft_dirty(pmd)) flags |= PM_SOFT_DIRTY; @@ -1332,10 +1337,12 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, err = add_to_pagemap(addr, &pme, pm); if (err) break; - if (pm->show_pfn && (flags & PM_PRESENT)) - frame++; - else if (flags & PM_SWAP) - frame += (1 << MAX_SWAPFILES_SHIFT); + if (pm->show_pfn) { + if (flags & PM_PRESENT) + frame++; + else if (flags & PM_SWAP) + frame += (1 << MAX_SWAPFILES_SHIFT); + } } spin_unlock(ptl); return err; diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index a45f0af22a60..cfb6674331fd 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -20,6 +20,7 @@ #include <linux/init.h> #include <linux/crash_dump.h> #include <linux/list.h> +#include <linux/mutex.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> #include <linux/uaccess.h> @@ -38,12 +39,23 @@ static size_t elfcorebuf_sz_orig; static char *elfnotes_buf; static size_t elfnotes_sz; +/* Size of all notes minus the device dump notes */ +static size_t elfnotes_orig_sz; /* Total size of vmcore file. */ static u64 vmcore_size; static struct proc_dir_entry *proc_vmcore; +#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP +/* Device Dump list and mutex to synchronize access to list */ +static LIST_HEAD(vmcoredd_list); +static DEFINE_MUTEX(vmcoredd_mutex); +#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ + +/* Device Dump Size */ +static size_t vmcoredd_orig_sz; + /* * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error * The called function has to take care of module refcounting. @@ -178,6 +190,77 @@ static int copy_to(void *target, void *src, size_t size, int userbuf) return 0; } +#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP +static int vmcoredd_copy_dumps(void *dst, u64 start, size_t size, int userbuf) +{ + struct vmcoredd_node *dump; + u64 offset = 0; + int ret = 0; + size_t tsz; + char *buf; + + mutex_lock(&vmcoredd_mutex); + list_for_each_entry(dump, &vmcoredd_list, list) { + if (start < offset + dump->size) { + tsz = min(offset + (u64)dump->size - start, (u64)size); + buf = dump->buf + start - offset; + if (copy_to(dst, buf, tsz, userbuf)) { + ret = -EFAULT; + goto out_unlock; + } + + size -= tsz; + start += tsz; + dst += tsz; + + /* Leave now if buffer filled already */ + if (!size) + goto out_unlock; + } + offset += dump->size; + } + +out_unlock: + mutex_unlock(&vmcoredd_mutex); + return ret; +} + +static int vmcoredd_mmap_dumps(struct vm_area_struct *vma, unsigned long dst, + u64 start, size_t size) +{ + struct vmcoredd_node *dump; + u64 offset = 0; + int ret = 0; + size_t tsz; + char *buf; + + mutex_lock(&vmcoredd_mutex); + list_for_each_entry(dump, &vmcoredd_list, list) { + if (start < offset + dump->size) { + tsz = min(offset + (u64)dump->size - start, (u64)size); + buf = dump->buf + start - offset; + if (remap_vmalloc_range_partial(vma, dst, buf, tsz)) { + ret = -EFAULT; + goto out_unlock; + } + + size -= tsz; + start += tsz; + dst += tsz; + + /* Leave now if buffer filled already */ + if (!size) + goto out_unlock; + } + offset += dump->size; + } + +out_unlock: + mutex_unlock(&vmcoredd_mutex); + return ret; +} +#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ + /* Read from the ELF header and then the crash dump. On error, negative value is * returned otherwise number of bytes read are returned. */ @@ -215,10 +298,41 @@ static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos, if (*fpos < elfcorebuf_sz + elfnotes_sz) { void *kaddr; + /* We add device dumps before other elf notes because the + * other elf notes may not fill the elf notes buffer + * completely and we will end up with zero-filled data + * between the elf notes and the device dumps. Tools will + * then try to decode this zero-filled data as valid notes + * and we don't want that. Hence, adding device dumps before + * the other elf notes ensure that zero-filled data can be + * avoided. + */ +#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP + /* Read device dumps */ + if (*fpos < elfcorebuf_sz + vmcoredd_orig_sz) { + tsz = min(elfcorebuf_sz + vmcoredd_orig_sz - + (size_t)*fpos, buflen); + start = *fpos - elfcorebuf_sz; + if (vmcoredd_copy_dumps(buffer, start, tsz, userbuf)) + return -EFAULT; + + buflen -= tsz; + *fpos += tsz; + buffer += tsz; + acc += tsz; + + /* leave now if filled buffer already */ + if (!buflen) + return acc; + } +#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ + + /* Read remaining elf notes */ tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, buflen); - kaddr = elfnotes_buf + *fpos - elfcorebuf_sz; + kaddr = elfnotes_buf + *fpos - elfcorebuf_sz - vmcoredd_orig_sz; if (copy_to(buffer, kaddr, tsz, userbuf)) return -EFAULT; + buflen -= tsz; *fpos += tsz; buffer += tsz; @@ -302,10 +416,8 @@ static const struct vm_operations_struct vmcore_mmap_ops = { }; /** - * alloc_elfnotes_buf - allocate buffer for ELF note segment in - * vmalloc memory - * - * @notes_sz: size of buffer + * vmcore_alloc_buf - allocate buffer in vmalloc memory + * @sizez: size of buffer * * If CONFIG_MMU is defined, use vmalloc_user() to allow users to mmap * the buffer to user-space by means of remap_vmalloc_range(). @@ -313,12 +425,12 @@ static const struct vm_operations_struct vmcore_mmap_ops = { * If CONFIG_MMU is not defined, use vzalloc() since mmap_vmcore() is * disabled and there's no need to allow users to mmap the buffer. */ -static inline char *alloc_elfnotes_buf(size_t notes_sz) +static inline char *vmcore_alloc_buf(size_t size) { #ifdef CONFIG_MMU - return vmalloc_user(notes_sz); + return vmalloc_user(size); #else - return vzalloc(notes_sz); + return vzalloc(size); #endif } @@ -446,11 +558,46 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) if (start < elfcorebuf_sz + elfnotes_sz) { void *kaddr; + /* We add device dumps before other elf notes because the + * other elf notes may not fill the elf notes buffer + * completely and we will end up with zero-filled data + * between the elf notes and the device dumps. Tools will + * then try to decode this zero-filled data as valid notes + * and we don't want that. Hence, adding device dumps before + * the other elf notes ensure that zero-filled data can be + * avoided. This also ensures that the device dumps and + * other elf notes can be properly mmaped at page aligned + * address. + */ +#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP + /* Read device dumps */ + if (start < elfcorebuf_sz + vmcoredd_orig_sz) { + u64 start_off; + + tsz = min(elfcorebuf_sz + vmcoredd_orig_sz - + (size_t)start, size); + start_off = start - elfcorebuf_sz; + if (vmcoredd_mmap_dumps(vma, vma->vm_start + len, + start_off, tsz)) + goto fail; + + size -= tsz; + start += tsz; + len += tsz; + + /* leave now if filled buffer already */ + if (!size) + return 0; + } +#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ + + /* Read remaining elf notes */ tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)start, size); - kaddr = elfnotes_buf + start - elfcorebuf_sz; + kaddr = elfnotes_buf + start - elfcorebuf_sz - vmcoredd_orig_sz; if (remap_vmalloc_range_partial(vma, vma->vm_start + len, kaddr, tsz)) goto fail; + size -= tsz; start += tsz; len += tsz; @@ -502,8 +649,8 @@ static struct vmcore* __init get_new_element(void) return kzalloc(sizeof(struct vmcore), GFP_KERNEL); } -static u64 __init get_vmcore_size(size_t elfsz, size_t elfnotesegsz, - struct list_head *vc_list) +static u64 get_vmcore_size(size_t elfsz, size_t elfnotesegsz, + struct list_head *vc_list) { u64 size; struct vmcore *m; @@ -665,7 +812,7 @@ static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz, return rc; *notes_sz = roundup(phdr_sz, PAGE_SIZE); - *notes_buf = alloc_elfnotes_buf(*notes_sz); + *notes_buf = vmcore_alloc_buf(*notes_sz); if (!*notes_buf) return -ENOMEM; @@ -698,6 +845,11 @@ static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz, /* Modify e_phnum to reflect merged headers. */ ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1; + /* Store the size of all notes. We need this to update the note + * header when the device dumps will be added. + */ + elfnotes_orig_sz = phdr.p_memsz; + return 0; } @@ -851,7 +1003,7 @@ static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz, return rc; *notes_sz = roundup(phdr_sz, PAGE_SIZE); - *notes_buf = alloc_elfnotes_buf(*notes_sz); + *notes_buf = vmcore_alloc_buf(*notes_sz); if (!*notes_buf) return -ENOMEM; @@ -884,6 +1036,11 @@ static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz, /* Modify e_phnum to reflect merged headers. */ ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1; + /* Store the size of all notes. We need this to update the note + * header when the device dumps will be added. + */ + elfnotes_orig_sz = phdr.p_memsz; + return 0; } @@ -976,8 +1133,8 @@ static int __init process_ptload_program_headers_elf32(char *elfptr, } /* Sets offset fields of vmcore elements. */ -static void __init set_vmcore_list_offsets(size_t elfsz, size_t elfnotes_sz, - struct list_head *vc_list) +static void set_vmcore_list_offsets(size_t elfsz, size_t elfnotes_sz, + struct list_head *vc_list) { loff_t vmcore_off; struct vmcore *m; @@ -1145,6 +1302,202 @@ static int __init parse_crash_elf_headers(void) return 0; } +#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP +/** + * vmcoredd_write_header - Write vmcore device dump header at the + * beginning of the dump's buffer. + * @buf: Output buffer where the note is written + * @data: Dump info + * @size: Size of the dump + * + * Fills beginning of the dump's buffer with vmcore device dump header. + */ +static void vmcoredd_write_header(void *buf, struct vmcoredd_data *data, + u32 size) +{ + struct vmcoredd_header *vdd_hdr = (struct vmcoredd_header *)buf; + + vdd_hdr->n_namesz = sizeof(vdd_hdr->name); + vdd_hdr->n_descsz = size + sizeof(vdd_hdr->dump_name); + vdd_hdr->n_type = NT_VMCOREDD; + + strncpy((char *)vdd_hdr->name, VMCOREDD_NOTE_NAME, + sizeof(vdd_hdr->name)); + memcpy(vdd_hdr->dump_name, data->dump_name, sizeof(vdd_hdr->dump_name)); +} + +/** + * vmcoredd_update_program_headers - Update all Elf program headers + * @elfptr: Pointer to elf header + * @elfnotesz: Size of elf notes aligned to page size + * @vmcoreddsz: Size of device dumps to be added to elf note header + * + * Determine type of Elf header (Elf64 or Elf32) and update the elf note size. + * Also update the offsets of all the program headers after the elf note header. + */ +static void vmcoredd_update_program_headers(char *elfptr, size_t elfnotesz, + size_t vmcoreddsz) +{ + unsigned char *e_ident = (unsigned char *)elfptr; + u64 start, end, size; + loff_t vmcore_off; + u32 i; + + vmcore_off = elfcorebuf_sz + elfnotesz; + + if (e_ident[EI_CLASS] == ELFCLASS64) { + Elf64_Ehdr *ehdr = (Elf64_Ehdr *)elfptr; + Elf64_Phdr *phdr = (Elf64_Phdr *)(elfptr + sizeof(Elf64_Ehdr)); + + /* Update all program headers */ + for (i = 0; i < ehdr->e_phnum; i++, phdr++) { + if (phdr->p_type == PT_NOTE) { + /* Update note size */ + phdr->p_memsz = elfnotes_orig_sz + vmcoreddsz; + phdr->p_filesz = phdr->p_memsz; + continue; + } + + start = rounddown(phdr->p_offset, PAGE_SIZE); + end = roundup(phdr->p_offset + phdr->p_memsz, + PAGE_SIZE); + size = end - start; + phdr->p_offset = vmcore_off + (phdr->p_offset - start); + vmcore_off += size; + } + } else { + Elf32_Ehdr *ehdr = (Elf32_Ehdr *)elfptr; + Elf32_Phdr *phdr = (Elf32_Phdr *)(elfptr + sizeof(Elf32_Ehdr)); + + /* Update all program headers */ + for (i = 0; i < ehdr->e_phnum; i++, phdr++) { + if (phdr->p_type == PT_NOTE) { + /* Update note size */ + phdr->p_memsz = elfnotes_orig_sz + vmcoreddsz; + phdr->p_filesz = phdr->p_memsz; + continue; + } + + start = rounddown(phdr->p_offset, PAGE_SIZE); + end = roundup(phdr->p_offset + phdr->p_memsz, + PAGE_SIZE); + size = end - start; + phdr->p_offset = vmcore_off + (phdr->p_offset - start); + vmcore_off += size; + } + } +} + +/** + * vmcoredd_update_size - Update the total size of the device dumps and update + * Elf header + * @dump_size: Size of the current device dump to be added to total size + * + * Update the total size of all the device dumps and update the Elf program + * headers. Calculate the new offsets for the vmcore list and update the + * total vmcore size. + */ +static void vmcoredd_update_size(size_t dump_size) +{ + vmcoredd_orig_sz += dump_size; + elfnotes_sz = roundup(elfnotes_orig_sz, PAGE_SIZE) + vmcoredd_orig_sz; + vmcoredd_update_program_headers(elfcorebuf, elfnotes_sz, + vmcoredd_orig_sz); + + /* Update vmcore list offsets */ + set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list); + + vmcore_size = get_vmcore_size(elfcorebuf_sz, elfnotes_sz, + &vmcore_list); + proc_vmcore->size = vmcore_size; +} + +/** + * vmcore_add_device_dump - Add a buffer containing device dump to vmcore + * @data: dump info. + * + * Allocate a buffer and invoke the calling driver's dump collect routine. + * Write Elf note at the beginning of the buffer to indicate vmcore device + * dump and add the dump to global list. + */ +int vmcore_add_device_dump(struct vmcoredd_data *data) +{ + struct vmcoredd_node *dump; + void *buf = NULL; + size_t data_size; + int ret; + + if (!data || !strlen(data->dump_name) || + !data->vmcoredd_callback || !data->size) + return -EINVAL; + + dump = vzalloc(sizeof(*dump)); + if (!dump) { + ret = -ENOMEM; + goto out_err; + } + + /* Keep size of the buffer page aligned so that it can be mmaped */ + data_size = roundup(sizeof(struct vmcoredd_header) + data->size, + PAGE_SIZE); + + /* Allocate buffer for driver's to write their dumps */ + buf = vmcore_alloc_buf(data_size); + if (!buf) { + ret = -ENOMEM; + goto out_err; + } + + vmcoredd_write_header(buf, data, data_size - + sizeof(struct vmcoredd_header)); + + /* Invoke the driver's dump collection routing */ + ret = data->vmcoredd_callback(data, buf + + sizeof(struct vmcoredd_header)); + if (ret) + goto out_err; + + dump->buf = buf; + dump->size = data_size; + + /* Add the dump to driver sysfs list */ + mutex_lock(&vmcoredd_mutex); + list_add_tail(&dump->list, &vmcoredd_list); + mutex_unlock(&vmcoredd_mutex); + + vmcoredd_update_size(data_size); + return 0; + +out_err: + if (buf) + vfree(buf); + + if (dump) + vfree(dump); + + return ret; +} +EXPORT_SYMBOL(vmcore_add_device_dump); +#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ + +/* Free all dumps in vmcore device dump list */ +static void vmcore_free_device_dumps(void) +{ +#ifdef CONFIG_PROC_VMCORE_DEVICE_DUMP + mutex_lock(&vmcoredd_mutex); + while (!list_empty(&vmcoredd_list)) { + struct vmcoredd_node *dump; + + dump = list_first_entry(&vmcoredd_list, struct vmcoredd_node, + list); + list_del(&dump->list); + vfree(dump->buf); + vfree(dump); + } + mutex_unlock(&vmcoredd_mutex); +#endif /* CONFIG_PROC_VMCORE_DEVICE_DUMP */ +} + /* Init function for vmcore module. */ static int __init vmcore_init(void) { @@ -1192,4 +1545,7 @@ void vmcore_cleanup(void) kfree(m); } free_elfcorebuf(); + + /* clear vmcore device dump list */ + vmcore_free_device_dumps(); } |
