[PATCH] Use VMCOREINTO inside '/proc/kcore' if available

[Bhupesh Sharma <bhsharma@redhat.com>]

Commit 94c97db3fe859ca14d7b38b0ae9ee0ffb83689d2 (arm64: Get
'info->page_offset' from PT_LOAD segments to support KASLR boot cases)
added a method to determine 'info->page_offset' from PT_LOAD segments
for arm64 platforms.

In this commit we hardcoded the NOT_PADDR_ARM64 macro as
0x0000000010a80000UL which was a valid value on qualcomm-amberwing
boards.

However, I was testing this change on several other arm64 boards
like apm-mustang, huawei-taishan and hp-moonshot and saw that
this value can vary on the basic of the "Kernel code" memory
range placement.

To fix the same, this patchset uses a new approach. Since kernel
version 4.19-rc5 (Commit
23c85094fe1895caefdd19ef624ee687ec5f4507 ["proc/kcore: add vmcoreinfo
note to /proc/kcore"]), '/proc/kcore' contains a new
PT_NOTE which carries the VMCOREINFO information.

If the same is available, we can use it for makedumpfile
'show_mem_usage()' and other functionality. This is especially useful
for architectures like arm64 as we can get kernel symbols like
'VA_BITS' and 'kimage_voffset' from the '/proc/kcore' itself and use it
to calculate 'info->page_offset' when we make a call to
'get_page_offset()'.

This VMCOREINFO note provides us a standard interface which can be
leveraged while debugging live (or primary) kernel with makedumpfile
(and other user-space tools), especially to derive the machine specific
details (for e.g. VA_BITS, PHYS_OFFSET and kimage_voffset for arm64
arch).

I also verified the makedumpfile functionality in crash kernel with this
patchset. Here are some details of the tests I ran:

Testing:
--------
1. Architectures tested:
   a) arm64 :- huawei-taishan, apm-mustang and qualcomm-amberwing boards.
   b) x86_64 :- Dell optiplex workstation.
      (NOTE that x86_64 makedumpfile --mem-usage use-case is currently
      broken with upstream kernel, but I have debugged the root-cause
      and will separately send a patch to fix the same).

2. Use-cases tested:
   a) Primary kernel ->
      [] --mem-usage:
         # makedumpfile -f --mem-usage /proc/kcore

      [] filtering use-case:
         # makedumpfile --split -d 31 -x vmlinux --config scrub.conf vmcore dumpfile_{1,2,3}

      [] dumpfile creation:
         # makedumpfile -d 31 -x vmlinux vmcore dumpfile

   b) Crash kernel ->
      [] dumpfile creation:
         # makedumpfile -l --message-level 31 -d 31 /proc/vmcore dump

3. Kernel versions tested:
   a) Kernel version 4.19-rc5 and above on both arm64 and x86_64.
   b) Fedora 28 on x86_64.
   c) Kernel version 4.14 on arm64.

Fixes: 94c97db3fe859ca14d7b38b0ae9ee0ffb83689d2 "arm64: Get 'info->page_offset' from PT_LOAD segments to support KASLR boot cases"
Cc: Kazuhito Hagio <k-hagio@ab.jp.nec.com>
Signed-off-by: Bhupesh Sharma <bhsharma@redhat.com>
---
 arch/arm64.c   | 114 +++++++++++++++++++++++++++++++++++++++++++--------------
 makedumpfile.c |  67 ++++++++++++++++++++++++++++++---
 makedumpfile.h |   2 +-
 3 files changed, 149 insertions(+), 34 deletions(-)

diff --git a/arch/arm64.c b/arch/arm64.c
index 362609668ea2..d695eff628f0 100644
--- a/arch/arm64.c
+++ b/arch/arm64.c
@@ -53,6 +53,7 @@ static unsigned long kimage_voffset;
 #define PAGE_OFFSET_42 ((0xffffffffffffffffUL) << 42)
 #define PAGE_OFFSET_47 ((0xffffffffffffffffUL) << 47)
 #define PAGE_OFFSET_48 ((0xffffffffffffffffUL) << 48)
+#define __PAGE_OFFSET(x) ((0xffffffffffffffffUL) << (x - 1))
 
 #define pgd_val(x)		((x).pgd)
 #define pud_val(x)		(pgd_val((x).pgd))
@@ -311,45 +312,104 @@ get_versiondep_info_arm64(void)
 	unsigned long long virt_start;
 	ulong _stext;
 
-	_stext = get_stext_symbol();
-	if (!_stext) {
-		ERRMSG("Can't get the symbol of _stext.\n");
-		return FALSE;
-	}
+	/* Calculate 'VA_BITS'. */
 
-	/* Derive va_bits as per arch/arm64/Kconfig */
-	if ((_stext & PAGE_OFFSET_36) == PAGE_OFFSET_36) {
-		va_bits = 36;
-	} else if ((_stext & PAGE_OFFSET_39) == PAGE_OFFSET_39) {
-		va_bits = 39;
-	} else if ((_stext & PAGE_OFFSET_42) == PAGE_OFFSET_42) {
-		va_bits = 42;
-	} else if ((_stext & PAGE_OFFSET_47) == PAGE_OFFSET_47) {
-		va_bits = 47;
-	} else if ((_stext & PAGE_OFFSET_48) == PAGE_OFFSET_48) {
-		va_bits = 48;
+	/* Since kernel version 4.19, '/proc/kcore' contains a new
+	 * PT_NOTE which carries the VMCOREINFO information.
+	 *
+	 * If the same is available, use it as it already contains the
+	 * value of 'VA_BITS' on the machine.
+	 *
+	 * Otherwise, we can read the '_stext' symbol and determine the
+	 * 'VA_BITS' value from the same as well.
+	 */
+	if (info->flag_kcore_contains_vmcoreinfo &&
+	    (NUMBER(VA_BITS) != NOT_FOUND_NUMBER)) {
+		va_bits = NUMBER(VA_BITS);
 	} else {
-		ERRMSG("Cannot find a proper _stext for calculating VA_BITS\n");
-		return FALSE;
+		_stext = get_stext_symbol();
+		if (!_stext) {
+			ERRMSG("Can't get the symbol of _stext.\n");
+			return FALSE;
+		}
+
+		/* Derive va_bits as per arch/arm64/Kconfig */
+		if ((_stext & PAGE_OFFSET_36) == PAGE_OFFSET_36) {
+			va_bits = 36;
+		} else if ((_stext & PAGE_OFFSET_39) == PAGE_OFFSET_39) {
+			va_bits = 39;
+		} else if ((_stext & PAGE_OFFSET_42) == PAGE_OFFSET_42) {
+			va_bits = 42;
+		} else if ((_stext & PAGE_OFFSET_47) == PAGE_OFFSET_47) {
+			va_bits = 47;
+		} else if ((_stext & PAGE_OFFSET_48) == PAGE_OFFSET_48) {
+			va_bits = 48;
+		} else {
+			ERRMSG("Cannot find a proper _stext for calculating VA_BITS\n");
+			return FALSE;
+		}
+	}
+
+	/* Calculate 'info->page_offset'. */
+
+	/* Since kernel version 4.19, '/proc/kcore' contains a new
+	 * PT_NOTE which carries the VMCOREINFO information.
+	 *
+	 * If the same is available, use it as it already contains the
+	 * value of 'kimage_voffset' on the machine.
+	 */
+	if (info->flag_kcore_contains_vmcoreinfo &&
+	    (NUMBER(kimage_voffset) != NOT_FOUND_NUMBER)) {
+		kimage_voffset = NUMBER(kimage_voffset);
 	}
 
+	/* First, lets try and calculate the 'info->page_offset' value
+	 * from PT_LOAD segments, if they are available.
+	 */
 	if (get_num_pt_loads()) {
 		for (i = 0;
 		    get_pt_load(i, &phys_start, NULL, &virt_start, NULL);
 		    i++) {
-			if (virt_start != NOT_KV_ADDR
-			    && virt_start < __START_KERNEL_map
-			    && phys_start != NOT_PADDR
-			    && phys_start != NOT_PADDR_ARM64) {
-				info->page_offset = virt_start - phys_start;
-				DEBUG_MSG("info->page_offset: %lx, VA_BITS: %d\n",
-						info->page_offset, va_bits);
-				return TRUE;
+			/* On systems where we have a valid 'kimage_voffset'
+			 * available by now, we should give preference to the same
+			 * while calculating 'info->page_offset'.
+			 *
+			 * Otherwise, we can ensure that we consider
+			 * only those PT_LOAD segments whose 'virt_start'
+			 * is greater than the PAGE_OFFSET value (as defined
+			 * in 'arch/arm64/include/asm/memory.h').
+			 */
+			if (!kimage_voffset) {
+				if (virt_start != NOT_KV_ADDR &&
+				   virt_start > __PAGE_OFFSET(va_bits) &&
+				   phys_start != NOT_PADDR) {
+					info->page_offset = virt_start - phys_start;
+					DEBUG_MSG("info->page_offset: %lx, VA_BITS: %d\n",
+							info->page_offset, va_bits);
+					return TRUE;
+				}
+			} else {
+				if (virt_start != NOT_KV_ADDR &&
+				   phys_start != NOT_PADDR &&
+				   (virt_start - phys_start) != kimage_voffset) {
+					info->page_offset = virt_start - phys_start;
+					DEBUG_MSG("info->page_offset: %lx, VA_BITS: %d\n",
+							info->page_offset, va_bits);
+					return TRUE;
+				}
 			}
 		}
 	}
 
-	info->page_offset = (0xffffffffffffffffUL) << (va_bits - 1);
+	/* Fallback to hard-coded value (equal to PAGE_OFFSET macro
+	 * defined in 'arch/arm64/include/asm/memory.h'), as the last
+	 * resort.
+	 *
+	 * Note that this will not be a valid value on KASLR enabled
+	 * kernels as the start address of linear range is also
+	 * randomized for KASLR boot cases.
+	 */
+	info->page_offset = __PAGE_OFFSET(va_bits);
 	DEBUG_MSG("page_offset=%lx, va_bits=%d\n", info->page_offset,
 			va_bits);
 
diff --git a/makedumpfile.c b/makedumpfile.c
index 3ccdaaeda0c5..59967f95e0d3 100644
--- a/makedumpfile.c
+++ b/makedumpfile.c
@@ -1302,6 +1302,20 @@ error:
 	return FALSE;
 }
 
+static int
+check_kcore_contains_vmcoreinfo(int fd, char *name)
+{
+	if (!get_elf_info(fd, name))
+		return FALSE;
+
+	if (!has_vmcoreinfo())
+		return FALSE;
+
+	DEBUG_MSG("VMCOREINFO PT_NOTE found in %s\n", name);
+
+	return TRUE;
+}
+
 int
 open_dump_memory(void)
 {
@@ -1314,6 +1328,23 @@ open_dump_memory(void)
 	}
 	info->fd_memory = fd;
 
+	/* Since kernel version 4.19, '/proc/kcore' contains a new
+	 * PT_NOTE which carries the VMCOREINFO information.
+	 *
+	 * If the same is available, use it for makedumpfile
+	 * show_mem_usage() cases.
+	 */
+	if (info->flag_mem_usage &&
+	    !(strcmp(info->name_memory, "/proc/kcore")) &&
+	    (info->kernel_version >= KERNEL_VERSION(4, 19, 0))){
+		status = check_kcore_contains_vmcoreinfo(fd,
+						info->name_memory);
+		if (status == TRUE) {
+			info->flag_kcore_contains_vmcoreinfo = TRUE;
+			return TRUE;
+		}
+	}
+
 	status = check_kdump_compressed(info->name_memory);
 	if (status == TRUE) {
 		info->flag_refiltering = TRUE;
@@ -11195,6 +11226,8 @@ static int get_sys_kernel_vmcoreinfo(uint64_t *addr, uint64_t *len)
 
 int show_mem_usage(void)
 {
+	off_t offset;
+	unsigned long size;
 	uint64_t vmcoreinfo_addr, vmcoreinfo_len;
 	struct cycle cycle = {0};
 
@@ -11208,17 +11241,39 @@ int show_mem_usage(void)
 	if (!open_files_for_creating_dumpfile())
 		return FALSE;
 
-	if (!get_elf_loads(info->fd_memory, info->name_memory))
-		return FALSE;
+	/* Since kernel version 4.19, '/proc/kcore' contains a new
+	 * PT_NOTE which carries the VMCOREINFO information.
+	 *
+	 * If the same is available, use it for makedumpfile
+	 * show_mem_usage(). This is especially useful for architectures
+	 * like arm64 as we can get symbols like 'VA_BITS' and
+	 * 'kimage_voffset' before we call get_page_offset().
+	 */
+
+	if (!info->flag_kcore_contains_vmcoreinfo) {
+		if (!get_elf_loads(info->fd_memory, info->name_memory))
+			return FALSE;
+	} else {
+		if (has_vmcoreinfo()) {
+			get_vmcoreinfo(&offset, &size);
+			if (!read_vmcoreinfo_from_vmcore(offset, size, FALSE))
+				return FALSE;
+		}
+	}
 
 	if (!get_page_offset())
 		return FALSE;
 
-	if (!get_sys_kernel_vmcoreinfo(&vmcoreinfo_addr, &vmcoreinfo_len))
-		return FALSE;
+	/* If flag_kcore_contains_vmcoreinfo is TRUE when we are here,
+	 * we don't need to read the vmcoreinfo again.
+	 */
+	if (!info->flag_kcore_contains_vmcoreinfo)
+		if (!get_sys_kernel_vmcoreinfo(&vmcoreinfo_addr, &vmcoreinfo_len))
+			return FALSE;
 
-	if (!set_kcore_vmcoreinfo(vmcoreinfo_addr, vmcoreinfo_len))
-		return FALSE;
+	if (!info->flag_kcore_contains_vmcoreinfo)
+		if (!set_kcore_vmcoreinfo(vmcoreinfo_addr, vmcoreinfo_len))
+			return FALSE;
 
 	if (!initial())
 		return FALSE;
diff --git a/makedumpfile.h b/makedumpfile.h
index d1fcd87e85f5..3ae683774fe5 100644
--- a/makedumpfile.h
+++ b/makedumpfile.h
@@ -544,7 +544,6 @@ unsigned long get_kvbase_arm64(void);
 #define KVBASE			get_kvbase_arm64()
 
 #define __START_KERNEL_map	(0xffffffff80000000UL)
-#define NOT_PADDR_ARM64		(0x0000000010a80000UL)
 
 #endif /* aarch64 */
 
@@ -1307,6 +1306,7 @@ struct DumpInfo {
 	int		flag_vmemmap;        /* kernel supports vmemmap address space */
 	int		flag_excludevm;      /* -e - excluding unused vmemmap pages */
 	int		flag_use_count;      /* _refcount is named _count in struct page */
+	int		flag_kcore_contains_vmcoreinfo;    /* '/proc/kcore' contains a VMCOREINFO PT_NOTE */
 	unsigned long	vaddr_for_vtop;      /* virtual address for debugging */
 	long		page_size;           /* size of page */
 	long		page_shift;
-- 
2.7.4


_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec