summaryrefslogtreecommitdiffstats
path: root/fs/proc
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/fd.c2
-rw-r--r--fs/proc/task_mmu.c50
-rw-r--r--fs/proc/vmcore.c154
3 files changed, 175 insertions, 31 deletions
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 0ff80f9b930..985ea881b5b 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -286,7 +286,7 @@ int proc_fd_permission(struct inode *inode, int mask)
int rv = generic_permission(inode, mask);
if (rv == 0)
return 0;
- if (task_pid(current) == proc_pid(inode))
+ if (task_tgid(current) == proc_pid(inode))
rv = 0;
return rv;
}
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 107d026f5d6..7366e9d63ce 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -740,6 +740,9 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
ptent = pte_file_clear_soft_dirty(ptent);
}
+ if (vma->vm_flags & VM_SOFTDIRTY)
+ vma->vm_flags &= ~VM_SOFTDIRTY;
+
set_pte_at(vma->vm_mm, addr, pte, ptent);
#endif
}
@@ -949,13 +952,15 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
if (is_migration_entry(entry))
page = migration_entry_to_page(entry);
} else {
- *pme = make_pme(PM_NOT_PRESENT(pm->v2));
+ if (vma->vm_flags & VM_SOFTDIRTY)
+ flags2 |= __PM_SOFT_DIRTY;
+ *pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
return;
}
if (page && !PageAnon(page))
flags |= PM_FILE;
- if (pte_soft_dirty(pte))
+ if ((vma->vm_flags & VM_SOFTDIRTY) || pte_soft_dirty(pte))
flags2 |= __PM_SOFT_DIRTY;
*pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, flags2) | flags);
@@ -974,7 +979,7 @@ static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *p
*pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset)
| PM_STATUS2(pm->v2, pmd_flags2) | PM_PRESENT);
else
- *pme = make_pme(PM_NOT_PRESENT(pm->v2));
+ *pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, pmd_flags2));
}
#else
static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
@@ -997,7 +1002,11 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
if (vma && pmd_trans_huge_lock(pmd, vma) == 1) {
int pmd_flags2;
- pmd_flags2 = (pmd_soft_dirty(*pmd) ? __PM_SOFT_DIRTY : 0);
+ if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(*pmd))
+ pmd_flags2 = __PM_SOFT_DIRTY;
+ else
+ pmd_flags2 = 0;
+
for (; addr != end; addr += PAGE_SIZE) {
unsigned long offset;
@@ -1015,12 +1024,17 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
if (pmd_trans_unstable(pmd))
return 0;
for (; addr != end; addr += PAGE_SIZE) {
+ int flags2;
/* check to see if we've left 'vma' behind
* and need a new, higher one */
if (vma && (addr >= vma->vm_end)) {
vma = find_vma(walk->mm, addr);
- pme = make_pme(PM_NOT_PRESENT(pm->v2));
+ if (vma && (vma->vm_flags & VM_SOFTDIRTY))
+ flags2 = __PM_SOFT_DIRTY;
+ else
+ flags2 = 0;
+ pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
}
/* check that 'vma' actually covers this address,
@@ -1044,13 +1058,15 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
#ifdef CONFIG_HUGETLB_PAGE
static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
- pte_t pte, int offset)
+ pte_t pte, int offset, int flags2)
{
if (pte_present(pte))
- *pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset)
- | PM_STATUS2(pm->v2, 0) | PM_PRESENT);
+ *pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset) |
+ PM_STATUS2(pm->v2, flags2) |
+ PM_PRESENT);
else
- *pme = make_pme(PM_NOT_PRESENT(pm->v2));
+ *pme = make_pme(PM_NOT_PRESENT(pm->v2) |
+ PM_STATUS2(pm->v2, flags2));
}
/* This function walks within one hugetlb entry in the single call */
@@ -1059,12 +1075,22 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
struct mm_walk *walk)
{
struct pagemapread *pm = walk->private;
+ struct vm_area_struct *vma;
int err = 0;
+ int flags2;
pagemap_entry_t pme;
+ vma = find_vma(walk->mm, addr);
+ WARN_ON_ONCE(!vma);
+
+ if (vma && (vma->vm_flags & VM_SOFTDIRTY))
+ flags2 = __PM_SOFT_DIRTY;
+ else
+ flags2 = 0;
+
for (; addr != end; addr += PAGE_SIZE) {
int offset = (addr & ~hmask) >> PAGE_SHIFT;
- huge_pte_to_pagemap_entry(&pme, pm, *pte, offset);
+ huge_pte_to_pagemap_entry(&pme, pm, *pte, offset, flags2);
err = add_to_pagemap(addr, &pme, pm);
if (err)
return err;
@@ -1376,8 +1402,10 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
walk.mm = mm;
pol = get_vma_policy(task, vma, vma->vm_start);
- mpol_to_str(buffer, sizeof(buffer), pol);
+ n = mpol_to_str(buffer, sizeof(buffer), pol);
mpol_cond_put(pol);
+ if (n < 0)
+ return n;
seq_printf(m, "%08lx %s", vma->vm_start, buffer);
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index a1a16eb97c7..9100d695988 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -21,6 +21,7 @@
#include <linux/crash_dump.h>
#include <linux/list.h>
#include <linux/vmalloc.h>
+#include <linux/pagemap.h>
#include <asm/uaccess.h>
#include <asm/io.h>
#include "internal.h"
@@ -123,11 +124,65 @@ static ssize_t read_from_oldmem(char *buf, size_t count,
return read;
}
+/*
+ * Architectures may override this function to allocate ELF header in 2nd kernel
+ */
+int __weak elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
+{
+ return 0;
+}
+
+/*
+ * Architectures may override this function to free header
+ */
+void __weak elfcorehdr_free(unsigned long long addr)
+{}
+
+/*
+ * Architectures may override this function to read from ELF header
+ */
+ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos)
+{
+ return read_from_oldmem(buf, count, ppos, 0);
+}
+
+/*
+ * Architectures may override this function to read from notes sections
+ */
+ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos)
+{
+ return read_from_oldmem(buf, count, ppos, 0);
+}
+
+/*
+ * Architectures may override this function to map oldmem
+ */
+int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
+ unsigned long from, unsigned long pfn,
+ unsigned long size, pgprot_t prot)
+{
+ return remap_pfn_range(vma, from, pfn, size, prot);
+}
+
+/*
+ * Copy to either kernel or user space
+ */
+static int copy_to(void *target, void *src, size_t size, int userbuf)
+{
+ if (userbuf) {
+ if (copy_to_user((char __user *) target, src, size))
+ return -EFAULT;
+ } else {
+ memcpy(target, src, size);
+ }
+ return 0;
+}
+
/* Read from the ELF header and then the crash dump. On error, negative value is
* returned otherwise number of bytes read are returned.
*/
-static ssize_t read_vmcore(struct file *file, char __user *buffer,
- size_t buflen, loff_t *fpos)
+static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos,
+ int userbuf)
{
ssize_t acc = 0, tmp;
size_t tsz;
@@ -144,7 +199,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
/* Read ELF core header */
if (*fpos < elfcorebuf_sz) {
tsz = min(elfcorebuf_sz - (size_t)*fpos, buflen);
- if (copy_to_user(buffer, elfcorebuf + *fpos, tsz))
+ if (copy_to(buffer, elfcorebuf + *fpos, tsz, userbuf))
return -EFAULT;
buflen -= tsz;
*fpos += tsz;
@@ -162,7 +217,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, buflen);
kaddr = elfnotes_buf + *fpos - elfcorebuf_sz;
- if (copy_to_user(buffer, kaddr, tsz))
+ if (copy_to(buffer, kaddr, tsz, userbuf))
return -EFAULT;
buflen -= tsz;
*fpos += tsz;
@@ -178,7 +233,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
if (*fpos < m->offset + m->size) {
tsz = min_t(size_t, m->offset + m->size - *fpos, buflen);
start = m->paddr + *fpos - m->offset;
- tmp = read_from_oldmem(buffer, tsz, &start, 1);
+ tmp = read_from_oldmem(buffer, tsz, &start, userbuf);
if (tmp < 0)
return tmp;
buflen -= tsz;
@@ -195,6 +250,55 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
return acc;
}
+static ssize_t read_vmcore(struct file *file, char __user *buffer,
+ size_t buflen, loff_t *fpos)
+{
+ return __read_vmcore((__force char *) buffer, buflen, fpos, 1);
+}
+
+/*
+ * The vmcore fault handler uses the page cache and fills data using the
+ * standard __vmcore_read() function.
+ *
+ * On s390 the fault handler is used for memory regions that can't be mapped
+ * directly with remap_pfn_range().
+ */
+static int mmap_vmcore_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+#ifdef CONFIG_S390
+ struct address_space *mapping = vma->vm_file->f_mapping;
+ pgoff_t index = vmf->pgoff;
+ struct page *page;
+ loff_t offset;
+ char *buf;
+ int rc;
+
+ page = find_or_create_page(mapping, index, GFP_KERNEL);
+ if (!page)
+ return VM_FAULT_OOM;
+ if (!PageUptodate(page)) {
+ offset = (loff_t) index << PAGE_CACHE_SHIFT;
+ buf = __va((page_to_pfn(page) << PAGE_SHIFT));
+ rc = __read_vmcore(buf, PAGE_SIZE, &offset, 0);
+ if (rc < 0) {
+ unlock_page(page);
+ page_cache_release(page);
+ return (rc == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS;
+ }
+ SetPageUptodate(page);
+ }
+ unlock_page(page);
+ vmf->page = page;
+ return 0;
+#else
+ return VM_FAULT_SIGBUS;
+#endif
+}
+
+static const struct vm_operations_struct vmcore_mmap_ops = {
+ .fault = mmap_vmcore_fault,
+};
+
/**
* alloc_elfnotes_buf - allocate buffer for ELF note segment in
* vmalloc memory
@@ -223,7 +327,7 @@ static inline char *alloc_elfnotes_buf(size_t notes_sz)
* regions in the 1st kernel pointed to by PT_LOAD entries) into
* virtually contiguous user-space in ELF layout.
*/
-#if defined(CONFIG_MMU) && !defined(CONFIG_S390)
+#ifdef CONFIG_MMU
static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
{
size_t size = vma->vm_end - vma->vm_start;
@@ -241,6 +345,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC);
vma->vm_flags |= VM_MIXEDMAP;
+ vma->vm_ops = &vmcore_mmap_ops;
len = 0;
@@ -282,9 +387,9 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
tsz = min_t(size_t, m->offset + m->size - start, size);
paddr = m->paddr + start - m->offset;
- if (remap_pfn_range(vma, vma->vm_start + len,
- paddr >> PAGE_SHIFT, tsz,
- vma->vm_page_prot))
+ if (remap_oldmem_pfn_range(vma, vma->vm_start + len,
+ paddr >> PAGE_SHIFT, tsz,
+ vma->vm_page_prot))
goto fail;
size -= tsz;
start += tsz;
@@ -357,7 +462,7 @@ static int __init update_note_header_size_elf64(const Elf64_Ehdr *ehdr_ptr)
notes_section = kmalloc(max_sz, GFP_KERNEL);
if (!notes_section)
return -ENOMEM;
- rc = read_from_oldmem(notes_section, max_sz, &offset, 0);
+ rc = elfcorehdr_read_notes(notes_section, max_sz, &offset);
if (rc < 0) {
kfree(notes_section);
return rc;
@@ -444,7 +549,8 @@ static int __init copy_notes_elf64(const Elf64_Ehdr *ehdr_ptr, char *notes_buf)
if (phdr_ptr->p_type != PT_NOTE)
continue;
offset = phdr_ptr->p_offset;
- rc = read_from_oldmem(notes_buf, phdr_ptr->p_memsz, &offset, 0);
+ rc = elfcorehdr_read_notes(notes_buf, phdr_ptr->p_memsz,
+ &offset);
if (rc < 0)
return rc;
notes_buf += phdr_ptr->p_memsz;
@@ -536,7 +642,7 @@ static int __init update_note_header_size_elf32(const Elf32_Ehdr *ehdr_ptr)
notes_section = kmalloc(max_sz, GFP_KERNEL);
if (!notes_section)
return -ENOMEM;
- rc = read_from_oldmem(notes_section, max_sz, &offset, 0);
+ rc = elfcorehdr_read_notes(notes_section, max_sz, &offset);
if (rc < 0) {
kfree(notes_section);
return rc;
@@ -623,7 +729,8 @@ static int __init copy_notes_elf32(const Elf32_Ehdr *ehdr_ptr, char *notes_buf)
if (phdr_ptr->p_type != PT_NOTE)
continue;
offset = phdr_ptr->p_offset;
- rc = read_from_oldmem(notes_buf, phdr_ptr->p_memsz, &offset, 0);
+ rc = elfcorehdr_read_notes(notes_buf, phdr_ptr->p_memsz,
+ &offset);
if (rc < 0)
return rc;
notes_buf += phdr_ptr->p_memsz;
@@ -810,7 +917,7 @@ static int __init parse_crash_elf64_headers(void)
addr = elfcorehdr_addr;
/* Read Elf header */
- rc = read_from_oldmem((char*)&ehdr, sizeof(Elf64_Ehdr), &addr, 0);
+ rc = elfcorehdr_read((char *)&ehdr, sizeof(Elf64_Ehdr), &addr);
if (rc < 0)
return rc;
@@ -837,7 +944,7 @@ static int __init parse_crash_elf64_headers(void)
if (!elfcorebuf)
return -ENOMEM;
addr = elfcorehdr_addr;
- rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz_orig, &addr, 0);
+ rc = elfcorehdr_read(elfcorebuf, elfcorebuf_sz_orig, &addr);
if (rc < 0)
goto fail;
@@ -866,7 +973,7 @@ static int __init parse_crash_elf32_headers(void)
addr = elfcorehdr_addr;
/* Read Elf header */
- rc = read_from_oldmem((char*)&ehdr, sizeof(Elf32_Ehdr), &addr, 0);
+ rc = elfcorehdr_read((char *)&ehdr, sizeof(Elf32_Ehdr), &addr);
if (rc < 0)
return rc;
@@ -892,7 +999,7 @@ static int __init parse_crash_elf32_headers(void)
if (!elfcorebuf)
return -ENOMEM;
addr = elfcorehdr_addr;
- rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz_orig, &addr, 0);
+ rc = elfcorehdr_read(elfcorebuf, elfcorebuf_sz_orig, &addr);
if (rc < 0)
goto fail;
@@ -919,7 +1026,7 @@ static int __init parse_crash_elf_headers(void)
int rc=0;
addr = elfcorehdr_addr;
- rc = read_from_oldmem(e_ident, EI_NIDENT, &addr, 0);
+ rc = elfcorehdr_read(e_ident, EI_NIDENT, &addr);
if (rc < 0)
return rc;
if (memcmp(e_ident, ELFMAG, SELFMAG) != 0) {
@@ -952,7 +1059,14 @@ static int __init vmcore_init(void)
{
int rc = 0;
- /* If elfcorehdr= has been passed in cmdline, then capture the dump.*/
+ /* Allow architectures to allocate ELF header in 2nd kernel */
+ rc = elfcorehdr_alloc(&elfcorehdr_addr, &elfcorehdr_size);
+ if (rc)
+ return rc;
+ /*
+ * If elfcorehdr= has been passed in cmdline or created in 2nd kernel,
+ * then capture the dump.
+ */
if (!(is_vmcore_usable()))
return rc;
rc = parse_crash_elf_headers();
@@ -960,6 +1074,8 @@ static int __init vmcore_init(void)
pr_warn("Kdump: vmcore not initialized\n");
return rc;
}
+ elfcorehdr_free(elfcorehdr_addr);
+ elfcorehdr_addr = ELFCORE_ADDR_ERR;
proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations);
if (proc_vmcore)
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-12 13:39:54 +0000