kexec: fill note buffers by NT_VMCORE_PAD notes in page-size boundary

Fill both crash_notes and vmcoreinfo_note buffers by NT_VMCORE_PAD note
type to make them satisfy mmap()'s page-size boundary requirement.

So far, end of note segments has been marked by zero-filled elf header.
Instead, this patch writes NT_VMCORE_PAD note in the end of note segments
until the offset on page-size boundary.

Also, old kernel can treat the ELF segments created without null header
because it stops reading ELF segments if real size it reads reachs
p_memsz.

Signed-off-by: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h
index 694bcd6bd927bff60bf76ceede7a222877e02999..f33ec08ec8d3f4d46d066263e910b7264e02d699 100644 (file)
--- a/arch/s390/include/asm/kexec.h
+++ b/arch/s390/include/asm/kexec.h
@@ -41,8 +41,8 @@
 /*
  * Size for s390x ELF notes per CPU
  *
- * Seven notes plus zero note at the end: prstatus, fpregset, timer,
- * tod_cmp, tod_reg, control regs, and prefix
+ * Seven notes plus note with NT_VMCORE_PAD type at the end: prstatus,
+ * fpregset, timer, tod_cmp, tod_reg, control regs, and prefix
  */
 #define KEXEC_NOTE_BYTES \
        (ALIGN(sizeof(struct elf_note), 4) * 8 + \
@@ -53,7 +53,9 @@
         ALIGN(sizeof(u64), 4) + \
         ALIGN(sizeof(u32), 4) + \
         ALIGN(sizeof(u64) * 16, 4) + \
-        ALIGN(sizeof(u32), 4) \
+        ALIGN(sizeof(u32), 4) + \
+        KEXEC_CORE_NOTE_DESC_BYTES + \
+        VMCOREINFO_NOTE_NAME_BYTES \
        )
 
 /* Provide a dummy definition to avoid build failures. */

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 5113570f4b4e9a56327771492f7a9c546f064e4a..6592935f664962eb68430ff690c4064dcfa676b6 100644 (file)
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -47,14 +47,16 @@
 #define KEXEC_CORE_NOTE_NAME_BYTES ALIGN(sizeof(KEXEC_CORE_NOTE_NAME), 4)
 #define KEXEC_CORE_NOTE_DESC_BYTES ALIGN(sizeof(struct elf_prstatus), 4)
 /*
- * The per-cpu notes area is a list of notes terminated by a "NULL"
- * note header.  For kdump, the code in vmcore.c runs in the context
- * of the second kernel to combine them into one note.
+ * The per-cpu notes area is a list of notes terminated by a note
+ * header with NT_VMCORE_PAD type. For kdump, the code in vmcore.c
+ * runs in the context of the second kernel to combine them into one
+ * note.
  */
 #ifndef KEXEC_NOTE_BYTES
 #define KEXEC_NOTE_BYTES ( (KEXEC_NOTE_HEAD_BYTES * 2) +               \
                            KEXEC_CORE_NOTE_NAME_BYTES +                \
-                           KEXEC_CORE_NOTE_DESC_BYTES )
+                           KEXEC_CORE_NOTE_DESC_BYTES +                \
+                           VMCOREINFO_NOTE_NAME_BYTES)
 #endif
 
 /*
@@ -187,7 +189,7 @@ extern struct kimage *kexec_crash_image;
 #define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4)
 #define VMCOREINFO_NOTE_SIZE       ALIGN(KEXEC_NOTE_HEAD_BYTES*2       \
                                         +VMCOREINFO_BYTES              \
-                                        +VMCOREINFO_NOTE_NAME_BYTES,   \
+                                        +VMCOREINFO_NOTE_NAME_BYTES*2, \
                                         PAGE_SIZE)
 
 /* Location of a reserved region to hold the crash kernel.

diff --git a/kernel/kexec.c b/kernel/kexec.c
index 0ecef8ef2eefe986dc83e0b408520b61a6d086b6..02d19826282caee6262ed148ceef43482d9f2309 100644 (file)
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -40,6 +40,7 @@
 
 /* Per cpu memory for storing cpu states in case of system crash. */
 note_buf_t __percpu *crash_notes;
+static size_t crash_notes_size = ALIGN(sizeof(note_buf_t), PAGE_SIZE);
 
 /* vmcoreinfo stuff */
 static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
@@ -1166,6 +1167,7 @@ unlock:
        return ret;
 }
 
+/* If @data is NULL, fill @buf with 0 in @data_len bytes. */
 static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data,
                            size_t data_len)
 {
@@ -1178,26 +1180,36 @@ static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data,
        buf += (sizeof(note) + 3)/4;
        memcpy(buf, name, note.n_namesz);
        buf += (note.n_namesz + 3)/4;
-       memcpy(buf, data, note.n_descsz);
+       if (data)
+               memcpy(buf, data, note.n_descsz);
+       else
+               memset(buf, 0, note.n_descsz);
        buf += (note.n_descsz + 3)/4;
 
        return buf;
 }
 
-static void final_note(u32 *buf)
+static void final_note(u32 *buf, size_t buf_len, size_t data_len)
 {
-       struct elf_note note;
+       size_t used_bytes, pad_hdr_size;
 
-       note.n_namesz = 0;
-       note.n_descsz = 0;
-       note.n_type   = 0;
-       memcpy(buf, &note, sizeof(note));
+       pad_hdr_size = KEXEC_NOTE_HEAD_BYTES + VMCOREINFO_NOTE_NAME_BYTES;
+
+       /*
+        * keep space for ELF note header and "VMCOREINFO" name to
+        * terminate ELF segment by NT_VMCORE_PAD note.
+        */
+       BUG_ON(data_len + pad_hdr_size > buf_len);
+
+       used_bytes = data_len + pad_hdr_size;
+       append_elf_note(buf, VMCOREINFO_NOTE_NAME, NT_VMCORE_PAD, NULL,
+                       roundup(used_bytes, PAGE_SIZE) - used_bytes);
 }
 
 void crash_save_cpu(struct pt_regs *regs, int cpu)
 {
        struct elf_prstatus prstatus;
-       u32 *buf;
+       u32 *buf, *buf_end;
 
        if ((cpu < 0) || (cpu >= nr_cpu_ids))
                return;
@@ -1215,16 +1227,15 @@ void crash_save_cpu(struct pt_regs *regs, int cpu)
        memset(&prstatus, 0, sizeof(prstatus));
        prstatus.pr_pid = current->pid;
        elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
-       buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
-                             &prstatus, sizeof(prstatus));
-       final_note(buf);
+       buf_end = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
+                                 &prstatus, sizeof(prstatus));
+       final_note(buf_end, crash_notes_size, (buf_end - buf) * sizeof(u32));
 }
 
 static int __init crash_notes_memory_init(void)
 {
        /* Allocate memory for saving cpu registers. */
-       crash_notes = __alloc_percpu(roundup(sizeof(note_buf_t), PAGE_SIZE),
-                                    PAGE_SIZE);
+       crash_notes = __alloc_percpu(crash_notes_size, PAGE_SIZE);
        if (!crash_notes) {
                printk("Kexec: Memory allocation for saving cpu register"
                " states failed\n");
@@ -1423,13 +1434,14 @@ int __init parse_crashkernel_low(char *cmdline,
 
 static void update_vmcoreinfo_note(void)
 {
-       u32 *buf = vmcoreinfo_note;
+       u32 *buf = vmcoreinfo_note, *buf_end;
 
        if (!vmcoreinfo_size)
                return;
-       buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, NT_VMCORE_DEBUGINFO,
-                             vmcoreinfo_data, vmcoreinfo_size);
-       final_note(buf);
+       buf_end = append_elf_note(buf, VMCOREINFO_NOTE_NAME, NT_VMCORE_DEBUGINFO,
+                                 vmcoreinfo_data, vmcoreinfo_size);
+       final_note(buf_end, sizeof(vmcoreinfo_note),
+                  (buf_end - buf) * sizeof(u32));
 }
 
 void crash_save_vmcoreinfo(void)