Skip to contentSkip to conversation

kexec: Move vmcoreinfo out of the kernel's .bss section

PATCH Superseded Xunlei Pang 6 participants 18 messages Apr 20, 2017 – Apr 27, 2017

Subsystems (9)
x86 PowerPC s390 Driver core +5 more subsystems

v4 of 5 Superseded Latest is v5 →

lore
Share & tools
lore
#0 lore raw

PATCH v4 1/3 kexec: Move vmcoreinfo out of the kernel's .bss section

As Eric said,
"what we need to do is move the variable vmcoreinfo_note out of the kernel's .bss section. And modify the code to regenerate and keep this information in something like the control page.

Definitely something like this needs a page all to itself, and ideally far away from any other kernel data structures. I clearly was not watching closely the data someone decided to keep this silly thing in the kernel's .bss section."

This patch allocates extra pages for these vmcoreinfo_XXX variables, one advantage is that it enhances some safety of vmcoreinfo, because vmcoreinfo now is kept far away from other kernel data structures.

---
v3->v4:
-Rebased on the latest linux-next
-Handle S390 vmcoreinfo_note properly
-Handle the newly-added xen/mmu_pv.c

 arch/ia64/kernel/machine_kexec.c |  5 -----
 arch/s390/kernel/machine_kexec.c |  1 +
 arch/s390/kernel/setup.c         |  6 ------
 arch/x86/kernel/crash.c          |  2 +-
 arch/x86/xen/mmu_pv.c            |  4 ++--
 include/linux/crash_core.h       |  2 +-
 kernel/crash_core.c              | 27 +++++++++++++++++++++++----
 kernel/ksysfs.c                  |  2 +-
 8 files changed, 29 insertions(+), 20 deletions(-)
arch/ia64/kernel/machine_kexec.c +0 -5
index 599507b..c14815d 100644
@@ -163,8 +163,3 @@ void arch_crash_save_vmcoreinfo(void)
 #endif
 }
 
-phys_addr_t paddr_vmcoreinfo_note(void)
-{
-	return ia64_tpa((unsigned long)(char *)&vmcoreinfo_note);
-}
-
arch/s390/kernel/machine_kexec.c +1 -0
index 49a6bd4..3d0b14a 100644
@@ -246,6 +246,7 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_SYMBOL(lowcore_ptr);
 	VMCOREINFO_SYMBOL(high_memory);
 	VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
+	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
 }
 
 void machine_shutdown(void)
arch/s390/kernel/setup.c +0 -6
index 3ae756c..3d1d808 100644
@@ -496,11 +496,6 @@ static void __init setup_memory_end(void)
 	pr_notice("The maximum memory size is %luMB\n", memory_end >> 20);
 }
 
-static void __init setup_vmcoreinfo(void)
-{
-	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
-}
-
 #ifdef CONFIG_CRASH_DUMP
 
 /*
@@ -939,7 +934,6 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	setup_resources();
-	setup_vmcoreinfo();
 	setup_lowcore();
 	smp_fill_possible_mask();
 	cpu_detect_mhz_feature();
arch/x86/kernel/crash.c +1 -1
index 22217ec..44404e2 100644
@@ -457,7 +457,7 @@ static int prepare_elf64_headers(struct crash_elf_data *ced,
 	bufp += sizeof(Elf64_Phdr);
 	phdr->p_type = PT_NOTE;
 	phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
-	phdr->p_filesz = phdr->p_memsz = sizeof(vmcoreinfo_note);
+	phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE;
 	(ehdr->e_phnum)++;
 
 #ifdef CONFIG_X86_64
arch/x86/xen/mmu_pv.c +2 -2
index 9d9ae66..35543fa 100644
@@ -2723,8 +2723,8 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 phys_addr_t paddr_vmcoreinfo_note(void)
 {
 	if (xen_pv_domain())
-		return virt_to_machine(&vmcoreinfo_note).maddr;
+		return virt_to_machine(vmcoreinfo_note).maddr;
 	else
-		return __pa_symbol(&vmcoreinfo_note);
+		return __pa(vmcoreinfo_note);
 }
 #endif /* CONFIG_KEXEC_CORE */
include/linux/crash_core.h +1 -1
index eb71a70..ba283a2 100644
@@ -53,7 +53,7 @@
 #define VMCOREINFO_PHYS_BASE(value) \
 	vmcoreinfo_append_str("PHYS_BASE=%lx\n", (unsigned long)value)
 
-extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
+extern u32 *vmcoreinfo_note;
 extern size_t vmcoreinfo_size;
 extern size_t vmcoreinfo_max_size;
 
kernel/crash_core.c +23 -4
index fcbd568..0321f04 100644
@@ -14,10 +14,10 @@
 #include <asm/sections.h>
 
 /* vmcoreinfo stuff */
-static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
-u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
+static unsigned char *vmcoreinfo_data;
 size_t vmcoreinfo_size;
-size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
+size_t vmcoreinfo_max_size = VMCOREINFO_BYTES;
+u32 *vmcoreinfo_note;
 
 /*
  * parsing the "crashkernel" commandline
@@ -326,6 +326,9 @@ static void update_vmcoreinfo_note(void)
 
 void crash_save_vmcoreinfo(void)
 {
+	if (!vmcoreinfo_note)
+		return;
+
 	vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
 	update_vmcoreinfo_note();
 }
@@ -356,11 +359,27 @@ void __weak arch_crash_save_vmcoreinfo(void)
 
 phys_addr_t __weak paddr_vmcoreinfo_note(void)
 {
-	return __pa_symbol((unsigned long)(char *)&vmcoreinfo_note);
+	return __pa(vmcoreinfo_note);
 }
 
 static int __init crash_save_vmcoreinfo_init(void)
 {
+	/* One page should be enough for VMCOREINFO_BYTES under all archs */
+	vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL);
+	if (!vmcoreinfo_data) {
+		pr_warn("Memory allocation for vmcoreinfo_data failed\n");
+		return -ENOMEM;
+	}
+
+	vmcoreinfo_note = alloc_pages_exact(VMCOREINFO_NOTE_SIZE,
+						GFP_KERNEL | __GFP_ZERO);
+	if (!vmcoreinfo_note) {
+		free_page((unsigned long)vmcoreinfo_data);
+		vmcoreinfo_data = NULL;
+		pr_warn("Memory allocation for vmcoreinfo_note failed\n");
+		return -ENOMEM;
+	}
+
 	VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
 	VMCOREINFO_PAGESIZE(PAGE_SIZE);
 
kernel/ksysfs.c +1 -1
index 23cd706..c40a4e5 100644
@@ -134,7 +134,7 @@ static ssize_t vmcoreinfo_show(struct kobject *kobj,
 {
 	phys_addr_t vmcore_base = paddr_vmcoreinfo_note();
 	return sprintf(buf, "%pa %x\n", &vmcore_base,
-		       (unsigned int)sizeof(vmcoreinfo_note));
+			(unsigned int)VMCOREINFO_NOTE_SIZE);
 }
 KERNEL_ATTR_RO(vmcoreinfo);
 
Signature · 1 line
1.8.3.1
#1 lore raw

PATCH v4 2/3 powerpc/fadump: Use the correct VMCOREINFO_NOTE_SIZE for phdr

vmcoreinfo_max_size stands for the vmcoreinfo_data, the correct one we should use is vmcoreinfo_note whose total size is VMCOREINFO_NOTE_SIZE.

Like explained in commit 77019967f06b ("kdump: fix exported size of vmcoreinfo note"), it should not affect the actual function, but we better fix it, also this change should be safe and backward compatible.

After this, we can get rid of variable vmcoreinfo_max_size, let's use the corresponding macros directly, fewer variables means more safety for vmcoreinfo operation.

Cc Mahesh Salgaonkar <[email protected]>
Cc Hari Bathini <[email protected]>

---
v3->v4:
-Rebased on the latest linux-next

 arch/powerpc/kernel/fadump.c | 3 +--
 include/linux/crash_core.h   | 1 -
 kernel/crash_core.c          | 3 +--
 3 files changed, 2 insertions(+), 5 deletions(-)
arch/powerpc/kernel/fadump.c +1 -2
index 466569e..7bd6cd0 100644
@@ -893,8 +893,7 @@ static int fadump_create_elfcore_headers(char *bufp)
 
 	phdr->p_paddr	= fadump_relocate(paddr_vmcoreinfo_note());
 	phdr->p_offset	= phdr->p_paddr;
-	phdr->p_memsz	= vmcoreinfo_max_size;
-	phdr->p_filesz	= vmcoreinfo_max_size;
+	phdr->p_memsz	= phdr->p_filesz = VMCOREINFO_NOTE_SIZE;
 
 	/* Increment number of program headers. */
 	(elf->e_phnum)++;
include/linux/crash_core.h +0 -1
index ba283a2..7d6bc7b 100644
@@ -55,7 +55,6 @@
 
 extern u32 *vmcoreinfo_note;
 extern size_t vmcoreinfo_size;
-extern size_t vmcoreinfo_max_size;
 
 Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
 			  void *data, size_t data_len);
kernel/crash_core.c +1 -2
index 0321f04..43cdb00 100644
@@ -16,7 +16,6 @@
 /* vmcoreinfo stuff */
 static unsigned char *vmcoreinfo_data;
 size_t vmcoreinfo_size;
-size_t vmcoreinfo_max_size = VMCOREINFO_BYTES;
 u32 *vmcoreinfo_note;
 
 /*
@@ -343,7 +342,7 @@ void vmcoreinfo_append_str(const char *fmt, ...)
 	r = vscnprintf(buf, sizeof(buf), fmt, args);
 	va_end(args);
 
-	r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
+	r = min(r, VMCOREINFO_BYTES - vmcoreinfo_size);
 
 	memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);
 
Signature · 1 line
1.8.3.1
#2 lore raw

Re: [PATCH v4 2/3] powerpc/fadump: Use the correct VMCOREINFO_NOTE_SIZE for phdr

Cc "Michael Holzheu"

Quoted 72 lines · Xunlei Pang

vmcoreinfo_max_size stands for the vmcoreinfo_data, the correct one we should use is vmcoreinfo_note whose total size is VMCOREINFO_NOTE_SIZE.

Like explained in commit 77019967f06b ("kdump: fix exported size of vmcoreinfo note"), it should not affect the actual function, but we better fix it, also this change should be safe and backward compatible.

After this, we can get rid of variable vmcoreinfo_max_size, let's use the corresponding macros directly, fewer variables means more safety for vmcoreinfo operation.

Cc Mahesh Salgaonkar <[email protected]>
Cc Hari Bathini <[email protected]>

---
v3->v4:

(quoted diff) +0 -1
-Rebased on the latest linux-next
 
 arch/powerpc/kernel/fadump.c | 3 +--
 include/linux/crash_core.h   | 1 -
 kernel/crash_core.c          | 3 +--
 3 files changed, 2 insertions(+), 5 deletions(-)
arch/powerpc/kernel/fadump.c +1 -2
index 466569e..7bd6cd0 100644
@@ -893,8 +893,7 @@ static int fadump_create_elfcore_headers(char *bufp)
 
 	phdr->p_paddr	= fadump_relocate(paddr_vmcoreinfo_note());
 	phdr->p_offset	= phdr->p_paddr;
-	phdr->p_memsz	= vmcoreinfo_max_size;
-	phdr->p_filesz	= vmcoreinfo_max_size;
+	phdr->p_memsz	= phdr->p_filesz = VMCOREINFO_NOTE_SIZE;
 
 	/* Increment number of program headers. */
 	(elf->e_phnum)++;
include/linux/crash_core.h +0 -1
index ba283a2..7d6bc7b 100644
@@ -55,7 +55,6 @@
 
 extern u32 *vmcoreinfo_note;
 extern size_t vmcoreinfo_size;
-extern size_t vmcoreinfo_max_size;
 
 Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
 			  void *data, size_t data_len);
kernel/crash_core.c +1 -2
index 0321f04..43cdb00 100644
@@ -16,7 +16,6 @@
 /* vmcoreinfo stuff */
 static unsigned char *vmcoreinfo_data;
 size_t vmcoreinfo_size;
-size_t vmcoreinfo_max_size = VMCOREINFO_BYTES;
 u32 *vmcoreinfo_note;
 
 /*
@@ -343,7 +342,7 @@ void vmcoreinfo_append_str(const char *fmt, ...)
 	r = vscnprintf(buf, sizeof(buf), fmt, args);
 	va_end(args);
 
-	r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
+	r = min(r, VMCOREINFO_BYTES - vmcoreinfo_size);
 
 	memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);
 
Reviewed-by on v4 2/3
#3 lore raw

Re: [PATCH v4 2/3] powerpc/fadump: Use the correct VMCOREINFO_NOTE_SIZE for phdr

In reply to Xunlei Pang

Ccing ppc list

Quoted 80 lines · Xunlei Pang

vmcoreinfo_max_size stands for the vmcoreinfo_data, the correct one we should use is vmcoreinfo_note whose total size is VMCOREINFO_NOTE_SIZE.

Like explained in commit 77019967f06b ("kdump: fix exported size of vmcoreinfo note"), it should not affect the actual function, but we better fix it, also this change should be safe and backward compatible.

After this, we can get rid of variable vmcoreinfo_max_size, let's use the corresponding macros directly, fewer variables means more safety for vmcoreinfo operation.

Cc Mahesh Salgaonkar <[email protected]>
Cc Hari Bathini <[email protected]>

---
v3->v4:

(quoted diff) +0 -1
-Rebased on the latest linux-next
 
 arch/powerpc/kernel/fadump.c | 3 +--
 include/linux/crash_core.h   | 1 -
 kernel/crash_core.c          | 3 +--
 3 files changed, 2 insertions(+), 5 deletions(-)
arch/powerpc/kernel/fadump.c +1 -2
index 466569e..7bd6cd0 100644
@@ -893,8 +893,7 @@ static int fadump_create_elfcore_headers(char *bufp)
 
 	phdr->p_paddr	= fadump_relocate(paddr_vmcoreinfo_note());
 	phdr->p_offset	= phdr->p_paddr;
-	phdr->p_memsz	= vmcoreinfo_max_size;
-	phdr->p_filesz	= vmcoreinfo_max_size;
+	phdr->p_memsz	= phdr->p_filesz = VMCOREINFO_NOTE_SIZE;
 
 	/* Increment number of program headers. */
 	(elf->e_phnum)++;
include/linux/crash_core.h +0 -1
index ba283a2..7d6bc7b 100644
@@ -55,7 +55,6 @@
 
 extern u32 *vmcoreinfo_note;
 extern size_t vmcoreinfo_size;
-extern size_t vmcoreinfo_max_size;
 
 Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
 			  void *data, size_t data_len);
kernel/crash_core.c +1 -2
index 0321f04..43cdb00 100644
@@ -16,7 +16,6 @@
 /* vmcoreinfo stuff */
 static unsigned char *vmcoreinfo_data;
 size_t vmcoreinfo_size;
-size_t vmcoreinfo_max_size = VMCOREINFO_BYTES;
 u32 *vmcoreinfo_note;
 
 /*
@@ -343,7 +342,7 @@ void vmcoreinfo_append_str(const char *fmt, ...)
 	r = vscnprintf(buf, sizeof(buf), fmt, args);
 	va_end(args);
 
-	r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
+	r = min(r, VMCOREINFO_BYTES - vmcoreinfo_size);
 
 	memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);
 
Signature · 7 lines
1.8.3.1


_______________________________________________
kexec mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/kexec

Thanks
Dave

#4 lore raw

Re: [PATCH v4 2/3] powerpc/fadump: Use the correct VMCOREINFO_NOTE_SIZE for phdr

Quoted 18 lines · Dave Young

Ccing ppc list

Quoted 16 lines · Xunlei Pang

vmcoreinfo_max_size stands for the vmcoreinfo_data, the correct one we should use is vmcoreinfo_note whose total size is VMCOREINFO_NOTE_SIZE.

Like explained in commit 77019967f06b ("kdump: fix exported size of vmcoreinfo note"), it should not affect the actual function, but we better fix it, also this change should be safe and backward compatible.

After this, we can get rid of variable vmcoreinfo_max_size, let's use the corresponding macros directly, fewer variables means more safety for vmcoreinfo operation.

Cc Mahesh Salgaonkar <[email protected]>
Cc Hari Bathini <[email protected]>

Thanks,
-Mahesh.

Quoted 70 lines
Quoted 64 lines

---
v3->v4:

(quoted diff) +0 -1
-Rebased on the latest linux-next
 
 arch/powerpc/kernel/fadump.c | 3 +--
 include/linux/crash_core.h   | 1 -
 kernel/crash_core.c          | 3 +--
 3 files changed, 2 insertions(+), 5 deletions(-)
arch/powerpc/kernel/fadump.c +1 -2
index 466569e..7bd6cd0 100644
@@ -893,8 +893,7 @@ static int fadump_create_elfcore_headers(char *bufp)
 
 	phdr->p_paddr	= fadump_relocate(paddr_vmcoreinfo_note());
 	phdr->p_offset	= phdr->p_paddr;
-	phdr->p_memsz	= vmcoreinfo_max_size;
-	phdr->p_filesz	= vmcoreinfo_max_size;
+	phdr->p_memsz	= phdr->p_filesz = VMCOREINFO_NOTE_SIZE;
 
 	/* Increment number of program headers. */
 	(elf->e_phnum)++;
include/linux/crash_core.h +0 -1
index ba283a2..7d6bc7b 100644
@@ -55,7 +55,6 @@
 
 extern u32 *vmcoreinfo_note;
 extern size_t vmcoreinfo_size;
-extern size_t vmcoreinfo_max_size;
 
 Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
 			  void *data, size_t data_len);
kernel/crash_core.c +1 -2
index 0321f04..43cdb00 100644
@@ -16,7 +16,6 @@
 /* vmcoreinfo stuff */
 static unsigned char *vmcoreinfo_data;
 size_t vmcoreinfo_size;
-size_t vmcoreinfo_max_size = VMCOREINFO_BYTES;
 u32 *vmcoreinfo_note;
 
 /*
@@ -343,7 +342,7 @@ void vmcoreinfo_append_str(const char *fmt, ...)
 	r = vscnprintf(buf, sizeof(buf), fmt, args);
 	va_end(args);
 
-	r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
+	r = min(r, VMCOREINFO_BYTES - vmcoreinfo_size);
 
 	memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);
 
Signature · 7 lines
1.8.3.1


_______________________________________________
kexec mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/kexec

Thanks
Dave

#5 lore raw

PATCH v4 3/3 kdump: Protect vmcoreinfo data under the crash memory

In reply to Xunlei Pang

Currently vmcoreinfo data is updated at boot time subsys_initcall(), it has the risk of being modified by some wrong code during system is running.

As a result, vmcore dumped may contain the wrong vmcoreinfo. Later on, when using "crash", "makedumpfile", etc utility to parse this vmcore, we probably will get "Segmentation fault" or other unexpected errors.

E.g. 1) wrong code overwrites vmcoreinfo_data; 2) further crashes the system; 3) trigger kdump, then we obviously will fail to recognize the crash context correctly due to the corrupted vmcoreinfo.

Now except for vmcoreinfo, all the crash data is well protected(including the cpu note which is fully updated in the crash path, thus its correctness is guaranteed). Given that vmcoreinfo data is a large chunk prepared for kdump, we better protect it as well.

To solve this, we relocate and copy vmcoreinfo_data to the crash memory when kdump is loading via kexec syscalls. Because the whole crash memory will be protected by existing arch_kexec_protect_crashkres() mechanism, we naturally protect vmcoreinfo_data from write(even read) access under kernel direct mapping after kdump is loaded.

Since kdump is usually loaded at the very early stage after boot, we can trust the correctness of the vmcoreinfo data copied.

On the other hand, we still need to operate the vmcoreinfo safe copy when crash happens to generate vmcoreinfo_note again, we rely on vmap() to map out a new kernel virtual address and update to use this new one instead in the following crash_save_vmcoreinfo().

BTW, we do not touch vmcoreinfo_note, because it will be fully updated using the protected vmcoreinfo_data after crash which is surely correct just like the cpu crash note.

Cc Michael Holzheu <[email protected]>

---
v3->v4:
-Rebased on the latest linux-next
-Copy vmcoreinfo after machine_kexec_prepare()

 include/linux/crash_core.h |  2 +-
 include/linux/kexec.h      |  2 ++
 kernel/crash_core.c        | 17 ++++++++++++++++-
 kernel/kexec.c             |  8 ++++++++
 kernel/kexec_core.c        | 39 +++++++++++++++++++++++++++++++++++++++
 kernel/kexec_file.c        |  8 ++++++++
 6 files changed, 74 insertions(+), 2 deletions(-)
include/linux/crash_core.h +1 -1
index 7d6bc7b..5469adb 100644
@@ -23,6 +23,7 @@
 
 typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4];
 
+void crash_update_vmcoreinfo_safecopy(void *ptr);
 void crash_save_vmcoreinfo(void);
 void arch_crash_save_vmcoreinfo(void);
 __printf(1, 2)
@@ -54,7 +55,6 @@
 	vmcoreinfo_append_str("PHYS_BASE=%lx\n", (unsigned long)value)
 
 extern u32 *vmcoreinfo_note;
-extern size_t vmcoreinfo_size;
 
 Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
 			  void *data, size_t data_len);
include/linux/kexec.h +2 -0
index c9481eb..3ea8275 100644
@@ -181,6 +181,7 @@ struct kimage {
 	unsigned long start;
 	struct page *control_code_page;
 	struct page *swap_page;
+	void *vmcoreinfo_data_copy; /* locates in the crash memory */
 
 	unsigned long nr_segments;
 	struct kexec_segment segment[KEXEC_SEGMENT_MAX];
@@ -250,6 +251,7 @@ extern void *kexec_purgatory_get_symbol_addr(struct kimage *image,
 int kexec_should_crash(struct task_struct *);
 int kexec_crash_loaded(void);
 void crash_save_cpu(struct pt_regs *regs, int cpu);
+extern int kimage_crash_copy_vmcoreinfo(struct kimage *image);
 
 extern struct kimage *kexec_image;
 extern struct kimage *kexec_crash_image;
kernel/crash_core.c +16 -1
index 43cdb00..a29e9ad 100644
@@ -15,9 +15,12 @@
 
 /* vmcoreinfo stuff */
 static unsigned char *vmcoreinfo_data;
-size_t vmcoreinfo_size;
+static size_t vmcoreinfo_size;
 u32 *vmcoreinfo_note;
 
+/* trusted vmcoreinfo, e.g. we can make a copy in the crash memory */
+static unsigned char *vmcoreinfo_data_safecopy;
+
 /*
  * parsing the "crashkernel" commandline
  *
@@ -323,11 +326,23 @@ static void update_vmcoreinfo_note(void)
 	final_note(buf);
 }
 
+void crash_update_vmcoreinfo_safecopy(void *ptr)
+{
+	if (ptr)
+		memcpy(ptr, vmcoreinfo_data, vmcoreinfo_size);
+
+	vmcoreinfo_data_safecopy = ptr;
+}
+
 void crash_save_vmcoreinfo(void)
 {
 	if (!vmcoreinfo_note)
 		return;
 
+	/* Use the safe copy to generate vmcoreinfo note if have */
+	if (vmcoreinfo_data_safecopy)
+		vmcoreinfo_data = vmcoreinfo_data_safecopy;
+
 	vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
 	update_vmcoreinfo_note();
 }
kernel/kexec.c +8 -0
index 980936a..e62ec4d 100644
@@ -144,6 +144,14 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments,
 	if (ret)
 		goto out;
 
+	/*
+	 * Some architecture(like S390) may touch the crash memory before
+	 * machine_kexec_prepare(), we must copy vmcoreinfo data after it.
+	 */
+	ret = kimage_crash_copy_vmcoreinfo(image);
+	if (ret)
+		goto out;
+
 	for (i = 0; i < nr_segments; i++) {
 		ret = kimage_load_segment(image, &image->segment[i]);
 		if (ret)
kernel/kexec_core.c +39 -0
index ae1a3ba..bac1b4f 100644
@@ -481,6 +481,40 @@ struct page *kimage_alloc_control_pages(struct kimage *image,
 	return pages;
 }
 
+int kimage_crash_copy_vmcoreinfo(struct kimage *image)
+{
+	struct page *vmcoreinfo_page;
+	void *safecopy;
+
+	if (image->type != KEXEC_TYPE_CRASH)
+		return 0;
+
+	/*
+	 * For kdump, allocate one vmcoreinfo safe copy from the
+	 * crash memory. as we have arch_kexec_protect_crashkres()
+	 * after kexec syscall, we naturally protect it from write
+	 * (even read) access under kernel direct mapping. But on
+	 * the other hand, we still need to operate it when crash
+	 * happens to generate vmcoreinfo note, hereby we rely on
+	 * vmap for this purpose.
+	 */
+	vmcoreinfo_page = kimage_alloc_control_pages(image, 0);
+	if (!vmcoreinfo_page) {
+		pr_warn("Could not allocate vmcoreinfo buffer\n");
+		return -ENOMEM;
+	}
+	safecopy = vmap(&vmcoreinfo_page, 1, VM_MAP, PAGE_KERNEL);
+	if (!safecopy) {
+		pr_warn("Could not vmap vmcoreinfo buffer\n");
+		return -ENOMEM;
+	}
+
+	image->vmcoreinfo_data_copy = safecopy;
+	crash_update_vmcoreinfo_safecopy(safecopy);
+
+	return 0;
+}
+
 static int kimage_add_entry(struct kimage *image, kimage_entry_t entry)
 {
 	if (*image->entry != 0)
@@ -598,6 +632,11 @@ void kimage_free(struct kimage *image)
 	if (image->file_mode)
 		kimage_file_post_load_cleanup(image);
 
+	if (image->vmcoreinfo_data_copy) {
+		crash_update_vmcoreinfo_safecopy(NULL);
+		vunmap(image->vmcoreinfo_data_copy);
+	}
+
 	kfree(image);
 }
 
kernel/kexec_file.c +8 -0
index b118735..f78f719 100644
@@ -304,6 +304,14 @@ void kimage_file_post_load_cleanup(struct kimage *image)
 	if (ret)
 		goto out;
 
+	/*
+	 * Some architecture(like S390) may touch the crash memory before
+	 * machine_kexec_prepare(), we must copy vmcoreinfo data after it.
+	 */
+	ret = kimage_crash_copy_vmcoreinfo(image);
+	if (ret)
+		goto out;
+
 	ret = kexec_calculate_store_digests(image);
 	if (ret)
 		goto out;
Signature · 1 line
1.8.3.1
#6 lore raw

Re: [PATCH v4 3/3] kdump: Protect vmcoreinfo data under the crash memory

Quoted 95 lines · Xunlei Pang

Currently vmcoreinfo data is updated at boot time subsys_initcall(), it has the risk of being modified by some wrong code during system is running.

As a result, vmcore dumped may contain the wrong vmcoreinfo. Later on, when using "crash", "makedumpfile", etc utility to parse this vmcore, we probably will get "Segmentation fault" or other unexpected errors.

E.g. 1) wrong code overwrites vmcoreinfo_data; 2) further crashes the system; 3) trigger kdump, then we obviously will fail to recognize the crash context correctly due to the corrupted vmcoreinfo.

Now except for vmcoreinfo, all the crash data is well protected(including the cpu note which is fully updated in the crash path, thus its correctness is guaranteed). Given that vmcoreinfo data is a large chunk prepared for kdump, we better protect it as well.

To solve this, we relocate and copy vmcoreinfo_data to the crash memory when kdump is loading via kexec syscalls. Because the whole crash memory will be protected by existing arch_kexec_protect_crashkres() mechanism, we naturally protect vmcoreinfo_data from write(even read) access under kernel direct mapping after kdump is loaded.

Since kdump is usually loaded at the very early stage after boot, we can trust the correctness of the vmcoreinfo data copied.

On the other hand, we still need to operate the vmcoreinfo safe copy when crash happens to generate vmcoreinfo_note again, we rely on vmap() to map out a new kernel virtual address and update to use this new one instead in the following crash_save_vmcoreinfo().

BTW, we do not touch vmcoreinfo_note, because it will be fully updated using the protected vmcoreinfo_data after crash which is surely correct just like the cpu crash note.

Cc Michael Holzheu <[email protected]>

---
v3->v4:

(quoted diff) +0 -2
-Rebased on the latest linux-next
-Copy vmcoreinfo after machine_kexec_prepare()
 
 include/linux/crash_core.h |  2 +-
 include/linux/kexec.h      |  2 ++
 kernel/crash_core.c        | 17 ++++++++++++++++-
 kernel/kexec.c             |  8 ++++++++
 kernel/kexec_core.c        | 39 +++++++++++++++++++++++++++++++++++++++
 kernel/kexec_file.c        |  8 ++++++++
 6 files changed, 74 insertions(+), 2 deletions(-)
include/linux/crash_core.h +1 -1
index 7d6bc7b..5469adb 100644
@@ -23,6 +23,7 @@
 
 typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4];
 
+void crash_update_vmcoreinfo_safecopy(void *ptr);
 void crash_save_vmcoreinfo(void);
 void arch_crash_save_vmcoreinfo(void);
 __printf(1, 2)
@@ -54,7 +55,6 @@
 	vmcoreinfo_append_str("PHYS_BASE=%lx\n", (unsigned long)value)
 
 extern u32 *vmcoreinfo_note;
-extern size_t vmcoreinfo_size;
 
 Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
 			  void *data, size_t data_len);
include/linux/kexec.h +2 -0
index c9481eb..3ea8275 100644
@@ -181,6 +181,7 @@ struct kimage {
 	unsigned long start;
 	struct page *control_code_page;
 	struct page *swap_page;
+	void *vmcoreinfo_data_copy; /* locates in the crash memory */
 
 	unsigned long nr_segments;
 	struct kexec_segment segment[KEXEC_SEGMENT_MAX];
@@ -250,6 +251,7 @@ extern void *kexec_purgatory_get_symbol_addr(struct kimage *image,
 int kexec_should_crash(struct task_struct *);
 int kexec_crash_loaded(void);
 void crash_save_cpu(struct pt_regs *regs, int cpu);
+extern int kimage_crash_copy_vmcoreinfo(struct kimage *image);
 
 extern struct kimage *kexec_image;
 extern struct kimage *kexec_crash_image;
kernel/crash_core.c +0 -0
index 43cdb00..a29e9ad 100644

kernel/crash_core.c line 21

Quoted 8 lines
kernel/crash_core.c +2 -1
@@ -15,9 +15,12 @@
 
 /* vmcoreinfo stuff */
 static unsigned char *vmcoreinfo_data;
-size_t vmcoreinfo_size;
+static size_t vmcoreinfo_size;
 u32 *vmcoreinfo_note;
 
+/* trusted vmcoreinfo, e.g. we can make a copy in the crash memory */

May make it clearer like:
/* Trusted vmcoreinfo copy in the kdump reserved memory */

Quoted 94 lines
kernel/crash_core.c +14 -0
+static unsigned char *vmcoreinfo_data_safecopy;
+
 /*
  * parsing the "crashkernel" commandline
  *
@@ -323,11 +326,23 @@ static void update_vmcoreinfo_note(void)
 	final_note(buf);
 }
 
+void crash_update_vmcoreinfo_safecopy(void *ptr)
+{
+	if (ptr)
+		memcpy(ptr, vmcoreinfo_data, vmcoreinfo_size);
+
+	vmcoreinfo_data_safecopy = ptr;
+}
+
 void crash_save_vmcoreinfo(void)
 {
 	if (!vmcoreinfo_note)
 		return;
 
+	/* Use the safe copy to generate vmcoreinfo note if have */
+	if (vmcoreinfo_data_safecopy)
+		vmcoreinfo_data = vmcoreinfo_data_safecopy;
+
 	vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
 	update_vmcoreinfo_note();
 }
kernel/kexec.c +8 -0
index 980936a..e62ec4d 100644
@@ -144,6 +144,14 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments,
 	if (ret)
 		goto out;
 
+	/*
+	 * Some architecture(like S390) may touch the crash memory before
+	 * machine_kexec_prepare(), we must copy vmcoreinfo data after it.
+	 */
+	ret = kimage_crash_copy_vmcoreinfo(image);
+	if (ret)
+		goto out;
+
 	for (i = 0; i < nr_segments; i++) {
 		ret = kimage_load_segment(image, &image->segment[i]);
 		if (ret)
kernel/kexec_core.c +34 -0
index ae1a3ba..bac1b4f 100644
@@ -481,6 +481,40 @@ struct page *kimage_alloc_control_pages(struct kimage *image,
 	return pages;
 }
 
+int kimage_crash_copy_vmcoreinfo(struct kimage *image)
+{
+	struct page *vmcoreinfo_page;
+	void *safecopy;
+
+	if (image->type != KEXEC_TYPE_CRASH)
+		return 0;
+
+	/*
+	 * For kdump, allocate one vmcoreinfo safe copy from the
+	 * crash memory. as we have arch_kexec_protect_crashkres()
+	 * after kexec syscall, we naturally protect it from write
+	 * (even read) access under kernel direct mapping. But on
+	 * the other hand, we still need to operate it when crash
+	 * happens to generate vmcoreinfo note, hereby we rely on
+	 * vmap for this purpose.
+	 */
+	vmcoreinfo_page = kimage_alloc_control_pages(image, 0);
+	if (!vmcoreinfo_page) {
+		pr_warn("Could not allocate vmcoreinfo buffer\n");
+		return -ENOMEM;
+	}
+	safecopy = vmap(&vmcoreinfo_page, 1, VM_MAP, PAGE_KERNEL);
+	if (!safecopy) {
+		pr_warn("Could not vmap vmcoreinfo buffer\n");
+		return -ENOMEM;
+	}
+
+	image->vmcoreinfo_data_copy = safecopy;
+	crash_update_vmcoreinfo_safecopy(safecopy);
+
+	return 0;
+}
+
 static int kimage_add_entry(struct kimage *image, kimage_entry_t entry)
 {
 	if (*image->entry != 0)

kernel/kexec_core.c void kimage_free(struct kimage *image) · line 639

Quoted 8 lines
kernel/kexec_core.c +5 -0
@@ -598,6 +632,11 @@ void kimage_free(struct kimage *image)
 	if (image->file_mode)
 		kimage_file_post_load_cleanup(image);
 
+	if (image->vmcoreinfo_data_copy) {
+		crash_update_vmcoreinfo_safecopy(NULL);
+		vunmap(image->vmcoreinfo_data_copy);
+	}
+

Should move above chunk before the freeing of the actual page?

Quoted 30 lines
kernel/kexec_core.c +0 -0
 	kfree(image);
 }
 
kernel/kexec_file.c +8 -0
index b118735..f78f719 100644
@@ -304,6 +304,14 @@ void kimage_file_post_load_cleanup(struct kimage *image)
 	if (ret)
 		goto out;
 
+	/*
+	 * Some architecture(like S390) may touch the crash memory before
+	 * machine_kexec_prepare(), we must copy vmcoreinfo data after it.
+	 */
+	ret = kimage_crash_copy_vmcoreinfo(image);
+	if (ret)
+		goto out;
+
 	ret = kexec_calculate_store_digests(image);
 	if (ret)
 		goto out;
Signature · 7 lines
1.8.3.1


_______________________________________________
kexec mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/kexec

Thanks
Dave

#7 lore raw

Re: [PATCH v4 3/3] kdump: Protect vmcoreinfo data under the crash memory

Quoted 103 lines · Dave Young
Quoted 102 lines · Xunlei Pang

Currently vmcoreinfo data is updated at boot time subsys_initcall(), it has the risk of being modified by some wrong code during system is running.

As a result, vmcore dumped may contain the wrong vmcoreinfo. Later on, when using "crash", "makedumpfile", etc utility to parse this vmcore, we probably will get "Segmentation fault" or other unexpected errors.

E.g. 1) wrong code overwrites vmcoreinfo_data; 2) further crashes the system; 3) trigger kdump, then we obviously will fail to recognize the crash context correctly due to the corrupted vmcoreinfo.

Now except for vmcoreinfo, all the crash data is well protected(including the cpu note which is fully updated in the crash path, thus its correctness is guaranteed). Given that vmcoreinfo data is a large chunk prepared for kdump, we better protect it as well.

To solve this, we relocate and copy vmcoreinfo_data to the crash memory when kdump is loading via kexec syscalls. Because the whole crash memory will be protected by existing arch_kexec_protect_crashkres() mechanism, we naturally protect vmcoreinfo_data from write(even read) access under kernel direct mapping after kdump is loaded.

Since kdump is usually loaded at the very early stage after boot, we can trust the correctness of the vmcoreinfo data copied.

On the other hand, we still need to operate the vmcoreinfo safe copy when crash happens to generate vmcoreinfo_note again, we rely on vmap() to map out a new kernel virtual address and update to use this new one instead in the following crash_save_vmcoreinfo().

BTW, we do not touch vmcoreinfo_note, because it will be fully updated using the protected vmcoreinfo_data after crash which is surely correct just like the cpu crash note.

Cc Michael Holzheu <[email protected]>

---
v3->v4:

(quoted diff) +0 -2
-Rebased on the latest linux-next
-Copy vmcoreinfo after machine_kexec_prepare()
 
 include/linux/crash_core.h |  2 +-
 include/linux/kexec.h      |  2 ++
 kernel/crash_core.c        | 17 ++++++++++++++++-
 kernel/kexec.c             |  8 ++++++++
 kernel/kexec_core.c        | 39 +++++++++++++++++++++++++++++++++++++++
 kernel/kexec_file.c        |  8 ++++++++
 6 files changed, 74 insertions(+), 2 deletions(-)
include/linux/crash_core.h +1 -1
index 7d6bc7b..5469adb 100644
@@ -23,6 +23,7 @@
 
 typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4];
 
+void crash_update_vmcoreinfo_safecopy(void *ptr);
 void crash_save_vmcoreinfo(void);
 void arch_crash_save_vmcoreinfo(void);
 __printf(1, 2)
@@ -54,7 +55,6 @@
 	vmcoreinfo_append_str("PHYS_BASE=%lx\n", (unsigned long)value)
 
 extern u32 *vmcoreinfo_note;
-extern size_t vmcoreinfo_size;
 
 Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
 			  void *data, size_t data_len);
include/linux/kexec.h +2 -0
index c9481eb..3ea8275 100644
@@ -181,6 +181,7 @@ struct kimage {
 	unsigned long start;
 	struct page *control_code_page;
 	struct page *swap_page;
+	void *vmcoreinfo_data_copy; /* locates in the crash memory */
 
 	unsigned long nr_segments;
 	struct kexec_segment segment[KEXEC_SEGMENT_MAX];
@@ -250,6 +251,7 @@ extern void *kexec_purgatory_get_symbol_addr(struct kimage *image,
 int kexec_should_crash(struct task_struct *);
 int kexec_crash_loaded(void);
 void crash_save_cpu(struct pt_regs *regs, int cpu);
+extern int kimage_crash_copy_vmcoreinfo(struct kimage *image);
 
 extern struct kimage *kexec_image;
 extern struct kimage *kexec_crash_image;
kernel/crash_core.c +1 -1
index 43cdb00..a29e9ad 100644
@@ -15,9 +15,12 @@
 
 /* vmcoreinfo stuff */
 static unsigned char *vmcoreinfo_data;
-size_t vmcoreinfo_size;
+static size_t vmcoreinfo_size;
 u32 *vmcoreinfo_note;
 
Quoted 3 lines

kernel/crash_core.c line 21

Quoted 1 line
kernel/crash_core.c +1 -0
+/* trusted vmcoreinfo, e.g. we can make a copy in the crash memory */

May make it clearer like:
/* Trusted vmcoreinfo copy in the kdump reserved memory */

My thought is that it is in crash_core.c now which should be independent of kexec/kdump, so I used "e.g. ..." just like one use case.

Quoted 98 lines
Quoted 98 lines
kernel/crash_core.c +14 -0
+static unsigned char *vmcoreinfo_data_safecopy;
+
 /*
  * parsing the "crashkernel" commandline
  *
@@ -323,11 +326,23 @@ static void update_vmcoreinfo_note(void)
 	final_note(buf);
 }
 
+void crash_update_vmcoreinfo_safecopy(void *ptr)
+{
+	if (ptr)
+		memcpy(ptr, vmcoreinfo_data, vmcoreinfo_size);
+
+	vmcoreinfo_data_safecopy = ptr;
+}
+
 void crash_save_vmcoreinfo(void)
 {
 	if (!vmcoreinfo_note)
 		return;
 
+	/* Use the safe copy to generate vmcoreinfo note if have */
+	if (vmcoreinfo_data_safecopy)
+		vmcoreinfo_data = vmcoreinfo_data_safecopy;
+
 	vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
 	update_vmcoreinfo_note();
 }
kernel/kexec.c +8 -0
index 980936a..e62ec4d 100644
@@ -144,6 +144,14 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments,
 	if (ret)
 		goto out;
 
+	/*
+	 * Some architecture(like S390) may touch the crash memory before
+	 * machine_kexec_prepare(), we must copy vmcoreinfo data after it.
+	 */
+	ret = kimage_crash_copy_vmcoreinfo(image);
+	if (ret)
+		goto out;
+
 	for (i = 0; i < nr_segments; i++) {
 		ret = kimage_load_segment(image, &image->segment[i]);
 		if (ret)
kernel/kexec_core.c +34 -0
index ae1a3ba..bac1b4f 100644
@@ -481,6 +481,40 @@ struct page *kimage_alloc_control_pages(struct kimage *image,
 	return pages;
 }
 
+int kimage_crash_copy_vmcoreinfo(struct kimage *image)
+{
+	struct page *vmcoreinfo_page;
+	void *safecopy;
+
+	if (image->type != KEXEC_TYPE_CRASH)
+		return 0;
+
+	/*
+	 * For kdump, allocate one vmcoreinfo safe copy from the
+	 * crash memory. as we have arch_kexec_protect_crashkres()
+	 * after kexec syscall, we naturally protect it from write
+	 * (even read) access under kernel direct mapping. But on
+	 * the other hand, we still need to operate it when crash
+	 * happens to generate vmcoreinfo note, hereby we rely on
+	 * vmap for this purpose.
+	 */
+	vmcoreinfo_page = kimage_alloc_control_pages(image, 0);
+	if (!vmcoreinfo_page) {
+		pr_warn("Could not allocate vmcoreinfo buffer\n");
+		return -ENOMEM;
+	}
+	safecopy = vmap(&vmcoreinfo_page, 1, VM_MAP, PAGE_KERNEL);
+	if (!safecopy) {
+		pr_warn("Could not vmap vmcoreinfo buffer\n");
+		return -ENOMEM;
+	}
+
+	image->vmcoreinfo_data_copy = safecopy;
+	crash_update_vmcoreinfo_safecopy(safecopy);
+
+	return 0;
+}
+
 static int kimage_add_entry(struct kimage *image, kimage_entry_t entry)
 {
 	if (*image->entry != 0)
@@ -598,6 +632,11 @@ void kimage_free(struct kimage *image)
 	if (image->file_mode)
 		kimage_file_post_load_cleanup(image);
 
Quoted 6 lines

kernel/kexec_core.c void kimage_free(struct kimage *image) · line 639

Quoted 5 lines
kernel/kexec_core.c +5 -0
+	if (image->vmcoreinfo_data_copy) {
+		crash_update_vmcoreinfo_safecopy(NULL);
+		vunmap(image->vmcoreinfo_data_copy);
+	}
+

Should move above chunk before the freeing of the actual page?

It should be fine, because it is allocated from the reserved memory, it doesn't need to be freed. Anyway I can move it above to avoid confusion. Thanks!

Regards,
Xunlei

Quoted 34 lines
Quoted 31 lines
kernel/kexec_core.c +0 -0
 	kfree(image);
 }
 
kernel/kexec_file.c +8 -0
index b118735..f78f719 100644
@@ -304,6 +304,14 @@ void kimage_file_post_load_cleanup(struct kimage *image)
 	if (ret)
 		goto out;
 
+	/*
+	 * Some architecture(like S390) may touch the crash memory before
+	 * machine_kexec_prepare(), we must copy vmcoreinfo data after it.
+	 */
+	ret = kimage_crash_copy_vmcoreinfo(image);
+	if (ret)
+		goto out;
+
 	ret = kexec_calculate_store_digests(image);
 	if (ret)
 		goto out;
Signature · 7 lines
1.8.3.1


_______________________________________________
kexec mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/kexec

Thanks
Dave

Quoted 4 lines

_______________________________________________
kexec mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/kexec

_______________________________________________
kexec mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/kexec

#8 lore raw

Re: [PATCH v4 3/3] kdump: Protect vmcoreinfo data under the crash memory

[snip]

Quoted 11 lines
Quoted 11 lines
Quoted 11 lines

index 43cdb00..a29e9ad 100644

kernel/crash_core.c +1 -1
@@ -15,9 +15,12 @@
 
 /* vmcoreinfo stuff */
 static unsigned char *vmcoreinfo_data;
-size_t vmcoreinfo_size;
+static size_t vmcoreinfo_size;
 u32 *vmcoreinfo_note;
 
Quoted 6 lines
Quoted 3 lines

kernel/crash_core.c line 21

Quoted 1 line
kernel/crash_core.c +1 -0
+/* trusted vmcoreinfo, e.g. we can make a copy in the crash memory */

May make it clearer like:
/* Trusted vmcoreinfo copy in the kdump reserved memory */

My thought is that it is in crash_core.c now which should be independent of kexec/kdump, so I used "e.g. ..." just like one use case.

Ok, then it is fine.

[snip]

Quoted 14 lines
Quoted 7 lines
Quoted 7 lines
kernel/crash_core.c +0 -0
 static int kimage_add_entry(struct kimage *image, kimage_entry_t entry)
 {
 	if (*image->entry != 0)
@@ -598,6 +632,11 @@ void kimage_free(struct kimage *image)
 	if (image->file_mode)
 		kimage_file_post_load_cleanup(image);
 
Quoted 6 lines

kernel/crash_core.c void kimage_free(struct kimage *image) · line 639

Quoted 5 lines
kernel/crash_core.c +5 -0
+	if (image->vmcoreinfo_data_copy) {
+		crash_update_vmcoreinfo_safecopy(NULL);
+		vunmap(image->vmcoreinfo_data_copy);
+	}
+

Should move above chunk before the freeing of the actual page?

Quoted 3 lines

It should be fine, because it is allocated from the reserved memory, it doesn't need to be freed. Anyway I can move it above to avoid confusion. Thanks!

Yes, it looks better, thanks for explanation.

Thanks
Dave

maintainer
#9 lore raw
In reply to Xunlei Pang
Quoted 10 lines · Xunlei Pang

As Eric said,
"what we need to do is move the variable vmcoreinfo_note out of the kernel's .bss section. And modify the code to regenerate and keep this information in something like the control page.

Definitely something like this needs a page all to itself, and ideally far away from any other kernel data structures. I clearly was not watching closely the data someone decided to keep this silly thing in the kernel's .bss section."

Quoted 8 lines

This patch allocates extra pages for these vmcoreinfo_XXX variables, one advantage is that it enhances some safety of vmcoreinfo, because vmcoreinfo now is kept far away from other kernel data structures.

Xen parts: Reviewed-by: Juergen Gross <[email protected]>

Juergen

Tested-by on v4 1/3
#10 lore raw
In reply to Xunlei Pang

Am Thu, 20 Apr 2017 19:39:32 +0800
schrieb Xunlei Pang <[email protected]>:

Quoted 10 lines

As Eric said,
"what we need to do is move the variable vmcoreinfo_note out of the kernel's .bss section. And modify the code to regenerate and keep this information in something like the control page.

Definitely something like this needs a page all to itself, and ideally far away from any other kernel data structures. I clearly was not watching closely the data someone decided to keep this silly thing in the kernel's .bss section."

Quoted 8 lines

This patch allocates extra pages for these vmcoreinfo_XXX variables, one advantage is that it enhances some safety of vmcoreinfo, because vmcoreinfo now is kept far away from other kernel data structures.

Now s390 seems to work with the patches. I tested kdump and zfcpdump.

Quoted 176 lines

---
v3->v4:

(quoted diff) +0 -3
-Rebased on the latest linux-next
-Handle S390 vmcoreinfo_note properly
-Handle the newly-added xen/mmu_pv.c
 
 arch/ia64/kernel/machine_kexec.c |  5 -----
 arch/s390/kernel/machine_kexec.c |  1 +
 arch/s390/kernel/setup.c         |  6 ------
 arch/x86/kernel/crash.c          |  2 +-
 arch/x86/xen/mmu_pv.c            |  4 ++--
 include/linux/crash_core.h       |  2 +-
 kernel/crash_core.c              | 27 +++++++++++++++++++++++----
 kernel/ksysfs.c                  |  2 +-
 8 files changed, 29 insertions(+), 20 deletions(-)
arch/ia64/kernel/machine_kexec.c +0 -5
index 599507b..c14815d 100644
@@ -163,8 +163,3 @@ void arch_crash_save_vmcoreinfo(void)
 #endif
 }
 
-phys_addr_t paddr_vmcoreinfo_note(void)
-{
-	return ia64_tpa((unsigned long)(char *)&vmcoreinfo_note);
-}
-
arch/s390/kernel/machine_kexec.c +1 -0
index 49a6bd4..3d0b14a 100644
@@ -246,6 +246,7 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_SYMBOL(lowcore_ptr);
 	VMCOREINFO_SYMBOL(high_memory);
 	VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
+	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
 }
 
 void machine_shutdown(void)
arch/s390/kernel/setup.c +0 -6
index 3ae756c..3d1d808 100644
@@ -496,11 +496,6 @@ static void __init setup_memory_end(void)
 	pr_notice("The maximum memory size is %luMB\n", memory_end >> 20);
 }
 
-static void __init setup_vmcoreinfo(void)
-{
-	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
-}
-
 #ifdef CONFIG_CRASH_DUMP
 
 /*
@@ -939,7 +934,6 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	setup_resources();
-	setup_vmcoreinfo();
 	setup_lowcore();
 	smp_fill_possible_mask();
 	cpu_detect_mhz_feature();
arch/x86/kernel/crash.c +1 -1
index 22217ec..44404e2 100644
@@ -457,7 +457,7 @@ static int prepare_elf64_headers(struct crash_elf_data *ced,
 	bufp += sizeof(Elf64_Phdr);
 	phdr->p_type = PT_NOTE;
 	phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
-	phdr->p_filesz = phdr->p_memsz = sizeof(vmcoreinfo_note);
+	phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE;
 	(ehdr->e_phnum)++;
 
 #ifdef CONFIG_X86_64
arch/x86/xen/mmu_pv.c +2 -2
index 9d9ae66..35543fa 100644
@@ -2723,8 +2723,8 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 phys_addr_t paddr_vmcoreinfo_note(void)
 {
 	if (xen_pv_domain())
-		return virt_to_machine(&vmcoreinfo_note).maddr;
+		return virt_to_machine(vmcoreinfo_note).maddr;
 	else
-		return __pa_symbol(&vmcoreinfo_note);
+		return __pa(vmcoreinfo_note);
 }
 #endif /* CONFIG_KEXEC_CORE */
include/linux/crash_core.h +1 -1
index eb71a70..ba283a2 100644
@@ -53,7 +53,7 @@
 #define VMCOREINFO_PHYS_BASE(value) \
 	vmcoreinfo_append_str("PHYS_BASE=%lx\n", (unsigned long)value)
 
-extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
+extern u32 *vmcoreinfo_note;
 extern size_t vmcoreinfo_size;
 extern size_t vmcoreinfo_max_size;
 
kernel/crash_core.c +23 -4
index fcbd568..0321f04 100644
@@ -14,10 +14,10 @@
 #include <asm/sections.h>
 
 /* vmcoreinfo stuff */
-static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
-u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
+static unsigned char *vmcoreinfo_data;
 size_t vmcoreinfo_size;
-size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
+size_t vmcoreinfo_max_size = VMCOREINFO_BYTES;
+u32 *vmcoreinfo_note;
 
 /*
  * parsing the "crashkernel" commandline
@@ -326,6 +326,9 @@ static void update_vmcoreinfo_note(void)
 
 void crash_save_vmcoreinfo(void)
 {
+	if (!vmcoreinfo_note)
+		return;
+
 	vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
 	update_vmcoreinfo_note();
 }
@@ -356,11 +359,27 @@ void __weak arch_crash_save_vmcoreinfo(void)
 
 phys_addr_t __weak paddr_vmcoreinfo_note(void)
 {
-	return __pa_symbol((unsigned long)(char *)&vmcoreinfo_note);
+	return __pa(vmcoreinfo_note);
 }
 
 static int __init crash_save_vmcoreinfo_init(void)
 {
+	/* One page should be enough for VMCOREINFO_BYTES under all archs */
+	vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL);
+	if (!vmcoreinfo_data) {
+		pr_warn("Memory allocation for vmcoreinfo_data failed\n");
+		return -ENOMEM;
+	}
+
+	vmcoreinfo_note = alloc_pages_exact(VMCOREINFO_NOTE_SIZE,
+						GFP_KERNEL | __GFP_ZERO);
+	if (!vmcoreinfo_note) {
+		free_page((unsigned long)vmcoreinfo_data);
+		vmcoreinfo_data = NULL;
+		pr_warn("Memory allocation for vmcoreinfo_note failed\n");
+		return -ENOMEM;
+	}
+
 	VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
 	VMCOREINFO_PAGESIZE(PAGE_SIZE);
 
kernel/ksysfs.c +1 -1
index 23cd706..c40a4e5 100644
@@ -134,7 +134,7 @@ static ssize_t vmcoreinfo_show(struct kobject *kobj,
 {
 	phys_addr_t vmcore_base = paddr_vmcoreinfo_note();
 	return sprintf(buf, "%pa %x\n", &vmcore_base,
-		       (unsigned int)sizeof(vmcoreinfo_note));
+			(unsigned int)VMCOREINFO_NOTE_SIZE);
 }
 KERNEL_ATTR_RO(vmcoreinfo);
 
#11 lore raw
In reply to Xunlei Pang

Add ia64i list, and s390 list although Michael has tested it

Quoted 153 lines · Xunlei Pang

As Eric said,
"what we need to do is move the variable vmcoreinfo_note out of the kernel's .bss section. And modify the code to regenerate and keep this information in something like the control page.

Definitely something like this needs a page all to itself, and ideally far away from any other kernel data structures. I clearly was not watching closely the data someone decided to keep this silly thing in the kernel's .bss section."

This patch allocates extra pages for these vmcoreinfo_XXX variables, one advantage is that it enhances some safety of vmcoreinfo, because vmcoreinfo now is kept far away from other kernel data structures.

---
v3->v4:

(quoted diff) +0 -3
-Rebased on the latest linux-next
-Handle S390 vmcoreinfo_note properly
-Handle the newly-added xen/mmu_pv.c
 
 arch/ia64/kernel/machine_kexec.c |  5 -----
 arch/s390/kernel/machine_kexec.c |  1 +
 arch/s390/kernel/setup.c         |  6 ------
 arch/x86/kernel/crash.c          |  2 +-
 arch/x86/xen/mmu_pv.c            |  4 ++--
 include/linux/crash_core.h       |  2 +-
 kernel/crash_core.c              | 27 +++++++++++++++++++++++----
 kernel/ksysfs.c                  |  2 +-
 8 files changed, 29 insertions(+), 20 deletions(-)
arch/ia64/kernel/machine_kexec.c +0 -5
index 599507b..c14815d 100644
@@ -163,8 +163,3 @@ void arch_crash_save_vmcoreinfo(void)
 #endif
 }
 
-phys_addr_t paddr_vmcoreinfo_note(void)
-{
-	return ia64_tpa((unsigned long)(char *)&vmcoreinfo_note);
-}
-
arch/s390/kernel/machine_kexec.c +1 -0
index 49a6bd4..3d0b14a 100644
@@ -246,6 +246,7 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_SYMBOL(lowcore_ptr);
 	VMCOREINFO_SYMBOL(high_memory);
 	VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
+	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
 }
 
 void machine_shutdown(void)
arch/s390/kernel/setup.c +0 -6
index 3ae756c..3d1d808 100644
@@ -496,11 +496,6 @@ static void __init setup_memory_end(void)
 	pr_notice("The maximum memory size is %luMB\n", memory_end >> 20);
 }
 
-static void __init setup_vmcoreinfo(void)
-{
-	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
-}
-
 #ifdef CONFIG_CRASH_DUMP
 
 /*
@@ -939,7 +934,6 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	setup_resources();
-	setup_vmcoreinfo();
 	setup_lowcore();
 	smp_fill_possible_mask();
 	cpu_detect_mhz_feature();
arch/x86/kernel/crash.c +1 -1
index 22217ec..44404e2 100644
@@ -457,7 +457,7 @@ static int prepare_elf64_headers(struct crash_elf_data *ced,
 	bufp += sizeof(Elf64_Phdr);
 	phdr->p_type = PT_NOTE;
 	phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
-	phdr->p_filesz = phdr->p_memsz = sizeof(vmcoreinfo_note);
+	phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE;
 	(ehdr->e_phnum)++;
 
 #ifdef CONFIG_X86_64
arch/x86/xen/mmu_pv.c +2 -2
index 9d9ae66..35543fa 100644
@@ -2723,8 +2723,8 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 phys_addr_t paddr_vmcoreinfo_note(void)
 {
 	if (xen_pv_domain())
-		return virt_to_machine(&vmcoreinfo_note).maddr;
+		return virt_to_machine(vmcoreinfo_note).maddr;
 	else
-		return __pa_symbol(&vmcoreinfo_note);
+		return __pa(vmcoreinfo_note);
 }
 #endif /* CONFIG_KEXEC_CORE */
include/linux/crash_core.h +1 -1
index eb71a70..ba283a2 100644
@@ -53,7 +53,7 @@
 #define VMCOREINFO_PHYS_BASE(value) \
 	vmcoreinfo_append_str("PHYS_BASE=%lx\n", (unsigned long)value)
 
-extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
+extern u32 *vmcoreinfo_note;
 extern size_t vmcoreinfo_size;
 extern size_t vmcoreinfo_max_size;
 
kernel/crash_core.c +6 -3
index fcbd568..0321f04 100644
@@ -14,10 +14,10 @@
 #include <asm/sections.h>
 
 /* vmcoreinfo stuff */
-static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
-u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
+static unsigned char *vmcoreinfo_data;
 size_t vmcoreinfo_size;
-size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
+size_t vmcoreinfo_max_size = VMCOREINFO_BYTES;
+u32 *vmcoreinfo_note;
 
 /*
  * parsing the "crashkernel" commandline
@@ -326,6 +326,9 @@ static void update_vmcoreinfo_note(void)
 
 void crash_save_vmcoreinfo(void)
 {
+	if (!vmcoreinfo_note)
+		return;
+
 	vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
 	update_vmcoreinfo_note();
 }

kernel/crash_core.c void __weak arch_crash_save_vmcoreinfo(void) · line 367

Quoted 10 lines
kernel/crash_core.c +2 -1
@@ -356,11 +359,27 @@ void __weak arch_crash_save_vmcoreinfo(void)
 
 phys_addr_t __weak paddr_vmcoreinfo_note(void)
 {
-	return __pa_symbol((unsigned long)(char *)&vmcoreinfo_note);
+	return __pa(vmcoreinfo_note);
 }
 
 static int __init crash_save_vmcoreinfo_init(void)
 {
+	/* One page should be enough for VMCOREINFO_BYTES under all archs */

Can we add a comment in the VMCOREINFO_BYTES header file about the one page assumption?

Or just define the VMCOREINFO_BYTES as PAGE_SIZE instead of 4096

Quoted 39 lines
kernel/crash_core.c +15 -0
+	vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL);
+	if (!vmcoreinfo_data) {
+		pr_warn("Memory allocation for vmcoreinfo_data failed\n");
+		return -ENOMEM;
+	}
+
+	vmcoreinfo_note = alloc_pages_exact(VMCOREINFO_NOTE_SIZE,
+						GFP_KERNEL | __GFP_ZERO);
+	if (!vmcoreinfo_note) {
+		free_page((unsigned long)vmcoreinfo_data);
+		vmcoreinfo_data = NULL;
+		pr_warn("Memory allocation for vmcoreinfo_note failed\n");
+		return -ENOMEM;
+	}
+
 	VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
 	VMCOREINFO_PAGESIZE(PAGE_SIZE);
 
kernel/ksysfs.c +1 -1
index 23cd706..c40a4e5 100644
@@ -134,7 +134,7 @@ static ssize_t vmcoreinfo_show(struct kobject *kobj,
 {
 	phys_addr_t vmcore_base = paddr_vmcoreinfo_note();
 	return sprintf(buf, "%pa %x\n", &vmcore_base,
-		       (unsigned int)sizeof(vmcoreinfo_note));
+			(unsigned int)VMCOREINFO_NOTE_SIZE);
 }
 KERNEL_ATTR_RO(vmcoreinfo);
 
Signature · 7 lines
1.8.3.1


_______________________________________________
kexec mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/kexec

Thanks
Dave

#12 lore raw
Quoted 163 lines · Dave Young

Add ia64i list, and s390 list although Michael has tested it

Quoted 160 lines · Xunlei Pang

As Eric said,
"what we need to do is move the variable vmcoreinfo_note out of the kernel's .bss section. And modify the code to regenerate and keep this information in something like the control page.

Definitely something like this needs a page all to itself, and ideally far away from any other kernel data structures. I clearly was not watching closely the data someone decided to keep this silly thing in the kernel's .bss section."

This patch allocates extra pages for these vmcoreinfo_XXX variables, one advantage is that it enhances some safety of vmcoreinfo, because vmcoreinfo now is kept far away from other kernel data structures.

---
v3->v4:

(quoted diff) +0 -3
-Rebased on the latest linux-next
-Handle S390 vmcoreinfo_note properly
-Handle the newly-added xen/mmu_pv.c
 
 arch/ia64/kernel/machine_kexec.c |  5 -----
 arch/s390/kernel/machine_kexec.c |  1 +
 arch/s390/kernel/setup.c         |  6 ------
 arch/x86/kernel/crash.c          |  2 +-
 arch/x86/xen/mmu_pv.c            |  4 ++--
 include/linux/crash_core.h       |  2 +-
 kernel/crash_core.c              | 27 +++++++++++++++++++++++----
 kernel/ksysfs.c                  |  2 +-
 8 files changed, 29 insertions(+), 20 deletions(-)
arch/ia64/kernel/machine_kexec.c +0 -5
index 599507b..c14815d 100644
@@ -163,8 +163,3 @@ void arch_crash_save_vmcoreinfo(void)
 #endif
 }
 
-phys_addr_t paddr_vmcoreinfo_note(void)
-{
-	return ia64_tpa((unsigned long)(char *)&vmcoreinfo_note);
-}
-
arch/s390/kernel/machine_kexec.c +1 -0
index 49a6bd4..3d0b14a 100644
@@ -246,6 +246,7 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_SYMBOL(lowcore_ptr);
 	VMCOREINFO_SYMBOL(high_memory);
 	VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
+	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
 }
 
 void machine_shutdown(void)
arch/s390/kernel/setup.c +0 -6
index 3ae756c..3d1d808 100644
@@ -496,11 +496,6 @@ static void __init setup_memory_end(void)
 	pr_notice("The maximum memory size is %luMB\n", memory_end >> 20);
 }
 
-static void __init setup_vmcoreinfo(void)
-{
-	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
-}
-
 #ifdef CONFIG_CRASH_DUMP
 
 /*
@@ -939,7 +934,6 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	setup_resources();
-	setup_vmcoreinfo();
 	setup_lowcore();
 	smp_fill_possible_mask();
 	cpu_detect_mhz_feature();
arch/x86/kernel/crash.c +1 -1
index 22217ec..44404e2 100644
@@ -457,7 +457,7 @@ static int prepare_elf64_headers(struct crash_elf_data *ced,
 	bufp += sizeof(Elf64_Phdr);
 	phdr->p_type = PT_NOTE;
 	phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
-	phdr->p_filesz = phdr->p_memsz = sizeof(vmcoreinfo_note);
+	phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE;
 	(ehdr->e_phnum)++;
 
 #ifdef CONFIG_X86_64
arch/x86/xen/mmu_pv.c +2 -2
index 9d9ae66..35543fa 100644
@@ -2723,8 +2723,8 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 phys_addr_t paddr_vmcoreinfo_note(void)
 {
 	if (xen_pv_domain())
-		return virt_to_machine(&vmcoreinfo_note).maddr;
+		return virt_to_machine(vmcoreinfo_note).maddr;
 	else
-		return __pa_symbol(&vmcoreinfo_note);
+		return __pa(vmcoreinfo_note);
 }
 #endif /* CONFIG_KEXEC_CORE */
include/linux/crash_core.h +1 -1
index eb71a70..ba283a2 100644
@@ -53,7 +53,7 @@
 #define VMCOREINFO_PHYS_BASE(value) \
 	vmcoreinfo_append_str("PHYS_BASE=%lx\n", (unsigned long)value)
 
-extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
+extern u32 *vmcoreinfo_note;
 extern size_t vmcoreinfo_size;
 extern size_t vmcoreinfo_max_size;
 
kernel/crash_core.c +7 -4
index fcbd568..0321f04 100644
@@ -14,10 +14,10 @@
 #include <asm/sections.h>
 
 /* vmcoreinfo stuff */
-static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
-u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
+static unsigned char *vmcoreinfo_data;
 size_t vmcoreinfo_size;
-size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
+size_t vmcoreinfo_max_size = VMCOREINFO_BYTES;
+u32 *vmcoreinfo_note;
 
 /*
  * parsing the "crashkernel" commandline
@@ -326,6 +326,9 @@ static void update_vmcoreinfo_note(void)
 
 void crash_save_vmcoreinfo(void)
 {
+	if (!vmcoreinfo_note)
+		return;
+
 	vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
 	update_vmcoreinfo_note();
 }
@@ -356,11 +359,27 @@ void __weak arch_crash_save_vmcoreinfo(void)
 
 phys_addr_t __weak paddr_vmcoreinfo_note(void)
 {
-	return __pa_symbol((unsigned long)(char *)&vmcoreinfo_note);
+	return __pa(vmcoreinfo_note);
 }
 
Quoted 7 lines

kernel/crash_core.c void __weak arch_crash_save_vmcoreinfo(void) · line 367

Quoted 3 lines
kernel/crash_core.c +1 -0
 static int __init crash_save_vmcoreinfo_init(void)
 {
+	/* One page should be enough for VMCOREINFO_BYTES under all archs */

Can we add a comment in the VMCOREINFO_BYTES header file about the one page assumption?

Or just define the VMCOREINFO_BYTES as PAGE_SIZE instead of 4096

Yes, I considered this before, but VMCOREINFO_BYTES is also used by VMCOREINFO_NOTE_SIZE definition which is exported to sysfs, also some platform has larger page size(64KB), so I didn't touch this 4096 value.

I think I should use kmalloc() to allocate both of them, then move this comment to Patch3 kimage_crash_copy_vmcoreinfo().

Regards,
Xunlei

Quoted 43 lines
Quoted 40 lines
kernel/crash_core.c +15 -0
+	vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL);
+	if (!vmcoreinfo_data) {
+		pr_warn("Memory allocation for vmcoreinfo_data failed\n");
+		return -ENOMEM;
+	}
+
+	vmcoreinfo_note = alloc_pages_exact(VMCOREINFO_NOTE_SIZE,
+						GFP_KERNEL | __GFP_ZERO);
+	if (!vmcoreinfo_note) {
+		free_page((unsigned long)vmcoreinfo_data);
+		vmcoreinfo_data = NULL;
+		pr_warn("Memory allocation for vmcoreinfo_note failed\n");
+		return -ENOMEM;
+	}
+
 	VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
 	VMCOREINFO_PAGESIZE(PAGE_SIZE);
 
kernel/ksysfs.c +1 -1
index 23cd706..c40a4e5 100644
@@ -134,7 +134,7 @@ static ssize_t vmcoreinfo_show(struct kobject *kobj,
 {
 	phys_addr_t vmcore_base = paddr_vmcoreinfo_note();
 	return sprintf(buf, "%pa %x\n", &vmcore_base,
-		       (unsigned int)sizeof(vmcoreinfo_note));
+			(unsigned int)VMCOREINFO_NOTE_SIZE);
 }
 KERNEL_ATTR_RO(vmcoreinfo);
 
Signature · 7 lines
1.8.3.1


_______________________________________________
kexec mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/kexec

Thanks
Dave

Quoted 4 lines

_______________________________________________
kexec mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/kexec

_______________________________________________
kexec mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/kexec

#13 lore raw
Quoted 170 lines · Xunlei Pang
Quoted 169 lines · Dave Young

Add ia64i list, and s390 list although Michael has tested it

Quoted 153 lines · Xunlei Pang

As Eric said,
"what we need to do is move the variable vmcoreinfo_note out of the kernel's .bss section. And modify the code to regenerate and keep this information in something like the control page.

Definitely something like this needs a page all to itself, and ideally far away from any other kernel data structures. I clearly was not watching closely the data someone decided to keep this silly thing in the kernel's .bss section."

This patch allocates extra pages for these vmcoreinfo_XXX variables, one advantage is that it enhances some safety of vmcoreinfo, because vmcoreinfo now is kept far away from other kernel data structures.

---
v3->v4:

(quoted diff) +0 -3
-Rebased on the latest linux-next
-Handle S390 vmcoreinfo_note properly
-Handle the newly-added xen/mmu_pv.c
 
 arch/ia64/kernel/machine_kexec.c |  5 -----
 arch/s390/kernel/machine_kexec.c |  1 +
 arch/s390/kernel/setup.c         |  6 ------
 arch/x86/kernel/crash.c          |  2 +-
 arch/x86/xen/mmu_pv.c            |  4 ++--
 include/linux/crash_core.h       |  2 +-
 kernel/crash_core.c              | 27 +++++++++++++++++++++++----
 kernel/ksysfs.c                  |  2 +-
 8 files changed, 29 insertions(+), 20 deletions(-)
arch/ia64/kernel/machine_kexec.c +0 -5
index 599507b..c14815d 100644
@@ -163,8 +163,3 @@ void arch_crash_save_vmcoreinfo(void)
 #endif
 }
 
-phys_addr_t paddr_vmcoreinfo_note(void)
-{
-	return ia64_tpa((unsigned long)(char *)&vmcoreinfo_note);
-}
-
arch/s390/kernel/machine_kexec.c +1 -0
index 49a6bd4..3d0b14a 100644
@@ -246,6 +246,7 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_SYMBOL(lowcore_ptr);
 	VMCOREINFO_SYMBOL(high_memory);
 	VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
+	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
 }
 
 void machine_shutdown(void)
arch/s390/kernel/setup.c +0 -6
index 3ae756c..3d1d808 100644
@@ -496,11 +496,6 @@ static void __init setup_memory_end(void)
 	pr_notice("The maximum memory size is %luMB\n", memory_end >> 20);
 }
 
-static void __init setup_vmcoreinfo(void)
-{
-	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
-}
-
 #ifdef CONFIG_CRASH_DUMP
 
 /*
@@ -939,7 +934,6 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	setup_resources();
-	setup_vmcoreinfo();
 	setup_lowcore();
 	smp_fill_possible_mask();
 	cpu_detect_mhz_feature();
arch/x86/kernel/crash.c +1 -1
index 22217ec..44404e2 100644
@@ -457,7 +457,7 @@ static int prepare_elf64_headers(struct crash_elf_data *ced,
 	bufp += sizeof(Elf64_Phdr);
 	phdr->p_type = PT_NOTE;
 	phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
-	phdr->p_filesz = phdr->p_memsz = sizeof(vmcoreinfo_note);
+	phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE;
 	(ehdr->e_phnum)++;
 
 #ifdef CONFIG_X86_64
arch/x86/xen/mmu_pv.c +2 -2
index 9d9ae66..35543fa 100644
@@ -2723,8 +2723,8 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
 phys_addr_t paddr_vmcoreinfo_note(void)
 {
 	if (xen_pv_domain())
-		return virt_to_machine(&vmcoreinfo_note).maddr;
+		return virt_to_machine(vmcoreinfo_note).maddr;
 	else
-		return __pa_symbol(&vmcoreinfo_note);
+		return __pa(vmcoreinfo_note);
 }
 #endif /* CONFIG_KEXEC_CORE */
include/linux/crash_core.h +1 -1
index eb71a70..ba283a2 100644
@@ -53,7 +53,7 @@
 #define VMCOREINFO_PHYS_BASE(value) \
 	vmcoreinfo_append_str("PHYS_BASE=%lx\n", (unsigned long)value)
 
-extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
+extern u32 *vmcoreinfo_note;
 extern size_t vmcoreinfo_size;
 extern size_t vmcoreinfo_max_size;
 
kernel/crash_core.c +6 -3
index fcbd568..0321f04 100644
@@ -14,10 +14,10 @@
 #include <asm/sections.h>
 
 /* vmcoreinfo stuff */
-static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
-u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
+static unsigned char *vmcoreinfo_data;
 size_t vmcoreinfo_size;
-size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
+size_t vmcoreinfo_max_size = VMCOREINFO_BYTES;
+u32 *vmcoreinfo_note;
 
 /*
  * parsing the "crashkernel" commandline
@@ -326,6 +326,9 @@ static void update_vmcoreinfo_note(void)
 
 void crash_save_vmcoreinfo(void)
 {
+	if (!vmcoreinfo_note)
+		return;
+
 	vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
 	update_vmcoreinfo_note();
 }

kernel/crash_core.c void __weak arch_crash_save_vmcoreinfo(void) · line 367

Quoted 10 lines
kernel/crash_core.c +2 -1
@@ -356,11 +359,27 @@ void __weak arch_crash_save_vmcoreinfo(void)
 
 phys_addr_t __weak paddr_vmcoreinfo_note(void)
 {
-	return __pa_symbol((unsigned long)(char *)&vmcoreinfo_note);
+	return __pa(vmcoreinfo_note);
 }
 
 static int __init crash_save_vmcoreinfo_init(void)
 {
+	/* One page should be enough for VMCOREINFO_BYTES under all archs */

Can we add a comment in the VMCOREINFO_BYTES header file about the one page assumption?

Quoted 7 lines
Quoted 1 line

Or just define the VMCOREINFO_BYTES as PAGE_SIZE instead of 4096

Yes, I considered this before, but VMCOREINFO_BYTES is also used by VMCOREINFO_NOTE_SIZE definition which is exported to sysfs, also some platform has larger page size(64KB), so I didn't touch this 4096 value.

I think I should use kmalloc() to allocate both of them, then move this comment to Patch3 kimage_crash_copy_vmcoreinfo().

But on the other hand, using a separate page for them seems safer compared with using frequently-used slab, what's your opinion?

Regards,
Xunlei

Quoted 51 lines

Regards,
Xunlei

Quoted 47 lines
Quoted 40 lines
kernel/crash_core.c +15 -0
+	vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL);
+	if (!vmcoreinfo_data) {
+		pr_warn("Memory allocation for vmcoreinfo_data failed\n");
+		return -ENOMEM;
+	}
+
+	vmcoreinfo_note = alloc_pages_exact(VMCOREINFO_NOTE_SIZE,
+						GFP_KERNEL | __GFP_ZERO);
+	if (!vmcoreinfo_note) {
+		free_page((unsigned long)vmcoreinfo_data);
+		vmcoreinfo_data = NULL;
+		pr_warn("Memory allocation for vmcoreinfo_note failed\n");
+		return -ENOMEM;
+	}
+
 	VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
 	VMCOREINFO_PAGESIZE(PAGE_SIZE);
 
kernel/ksysfs.c +1 -1
index 23cd706..c40a4e5 100644
@@ -134,7 +134,7 @@ static ssize_t vmcoreinfo_show(struct kobject *kobj,
 {
 	phys_addr_t vmcore_base = paddr_vmcoreinfo_note();
 	return sprintf(buf, "%pa %x\n", &vmcore_base,
-		       (unsigned int)sizeof(vmcoreinfo_note));
+			(unsigned int)VMCOREINFO_NOTE_SIZE);
 }
 KERNEL_ATTR_RO(vmcoreinfo);
 
Signature · 7 lines
1.8.3.1


_______________________________________________
kexec mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/kexec

Thanks
Dave

_______________________________________________
kexec mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/kexec

#14 lore raw

[snip]

Quoted 12 lines
Quoted 12 lines
Quoted 8 lines

kernel/crash_core.c void __weak arch_crash_save_vmcoreinfo(void) · line 367

Quoted 4 lines

static int __init crash_save_vmcoreinfo_init(void) {

kernel/crash_core.c +1 -0
+	/* One page should be enough for VMCOREINFO_BYTES under all archs */

Can we add a comment in the VMCOREINFO_BYTES header file about the one page assumption?

Or just define the VMCOREINFO_BYTES as PAGE_SIZE instead of 4096

Yes, I considered this before, but VMCOREINFO_BYTES is also used by VMCOREINFO_NOTE_SIZE definition which is exported to sysfs, also some platform has larger page size(64KB), so I didn't touch this 4096 value.

Quoted 5 lines
Quoted 2 lines

I think I should use kmalloc() to allocate both of them, then move this comment to Patch3 kimage_crash_copy_vmcoreinfo().

But on the other hand, using a separate page for them seems safer compared with using frequently-used slab, what's your opinion?

I feel current page based way is better.

For 64k page the vmcore note size will increase it seems fine. Do you have concern in mind?

Thanks

#15 lore raw
Quoted 13 lines · Dave Young

[snip]

Quoted 12 lines
Quoted 12 lines
Quoted 8 lines

kernel/crash_core.c void __weak arch_crash_save_vmcoreinfo(void) · line 367

Quoted 4 lines

static int __init crash_save_vmcoreinfo_init(void) {

kernel/crash_core.c +1 -0
+	/* One page should be enough for VMCOREINFO_BYTES under all archs */

Can we add a comment in the VMCOREINFO_BYTES header file about the one page assumption?

Or just define the VMCOREINFO_BYTES as PAGE_SIZE instead of 4096

Yes, I considered this before, but VMCOREINFO_BYTES is also used by VMCOREINFO_NOTE_SIZE definition which is exported to sysfs, also some platform has larger page size(64KB), so I didn't touch this 4096 value.

Quoted 8 lines
Quoted 4 lines
Quoted 2 lines

I think I should use kmalloc() to allocate both of them, then move this comment to Patch3 kimage_crash_copy_vmcoreinfo().

But on the other hand, using a separate page for them seems safer compared with using frequently-used slab, what's your opinion?

I feel current page based way is better.

For 64k page the vmcore note size will increase it seems fine. Do you have concern in mind?

Since tools are supposed to acquire vmcoreinfo note size from sysfs, it should be safe to do so, except that there is some waste in memory for larger PAGE_SIZE.

Regards,
Xunlei

#16 lore raw

Hi Xunlei,

Quoted 18 lines · Xunlei Pang
Quoted 17 lines · Dave Young

[snip]

Quoted 16 lines
Quoted 7 lines
Quoted 7 lines

kernel/crash_core.c void __weak arch_crash_save_vmcoreinfo(void) · line 367

Quoted 4 lines

static int __init crash_save_vmcoreinfo_init(void) {

kernel/crash_core.c +1 -0
+	/* One page should be enough for VMCOREINFO_BYTES under all archs */

Can we add a comment in the VMCOREINFO_BYTES header file about the one page assumption?

Quoted 7 lines
Quoted 1 line

Or just define the VMCOREINFO_BYTES as PAGE_SIZE instead of 4096

Yes, I considered this before, but VMCOREINFO_BYTES is also used by VMCOREINFO_NOTE_SIZE definition which is exported to sysfs, also some platform has larger page size(64KB), so I didn't touch this 4096 value.

I think I should use kmalloc() to allocate both of them, then move this comment to Patch3 kimage_crash_copy_vmcoreinfo().

But on the other hand, using a separate page for them seems safer compared with using frequently-used slab, what's your opinion?

Quoted 7 lines
Quoted 4 lines

I feel current page based way is better.

For 64k page the vmcore note size will increase it seems fine. Do you have concern in mind?

Since tools are supposed to acquire vmcoreinfo note size from sysfs, it should be safe to do so, except that there is some waste in memory for larger PAGE_SIZE.

Either way is fine to me, I think it is up to your implementation, if choose page alloc then modify the macro with PAGE_SIZE looks better.

Thanks
Dave

#17 lore raw
Quoted 21 lines · Dave Young

Hi Xunlei,

Quoted 18 lines · Xunlei Pang
Quoted 17 lines · Dave Young

[snip]

Quoted 16 lines
Quoted 7 lines
Quoted 7 lines

Review

Quoted 4 lines

static int __init crash_save_vmcoreinfo_init(void) {

(quoted diff) +1 -0
+	/* One page should be enough for VMCOREINFO_BYTES under all archs */

Can we add a comment in the VMCOREINFO_BYTES header file about the one page assumption?

Quoted 7 lines
Quoted 1 line

Or just define the VMCOREINFO_BYTES as PAGE_SIZE instead of 4096

Yes, I considered this before, but VMCOREINFO_BYTES is also used by VMCOREINFO_NOTE_SIZE definition which is exported to sysfs, also some platform has larger page size(64KB), so I didn't touch this 4096 value.

I think I should use kmalloc() to allocate both of them, then move this comment to Patch3 kimage_crash_copy_vmcoreinfo().

But on the other hand, using a separate page for them seems safer compared with using frequently-used slab, what's your opinion?

Quoted 8 lines
Quoted 6 lines
Quoted 4 lines

I feel current page based way is better.

For 64k page the vmcore note size will increase it seems fine. Do you have concern in mind?

Since tools are supposed to acquire vmcoreinfo note size from sysfs, it should be safe to do so, except that there is some waste in memory for larger PAGE_SIZE.

Either way is fine to me, I think it is up to your implementation, if choose page alloc then modify the macro with PAGE_SIZE looks better.

OK, I will use PAGE_SIZE then, thanks for your comments.

Quoted 8 lines

Thanks
Dave

_______________________________________________
kexec mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/kexec