[PATCH RESEND v5 00/10] kexec-tools, x86: E820 memmap pass for kdump

[PATCH RESEND v5 00/10] kexec-tools, x86: E820 memmap pass for kdump

[WANG Chao]

Hi, all

(Sorry for this late update. I was occupied with something else)

This patchset enables passing memory map via E820 map on x86 platform instead
of memmap=exactmap. It's a better design and will solve the following problem
so far:

- kernel cmdline is limited resource and large machines tend to have many
    memory ranges that may excceed kernel cmdline limit size.
- kASLR doesn't work with memmap=exactmap, because kASLR happens early than
    user defined memmap=exactmap takes effect.

Unfortunately, saved_max_pfn still got its user out there (calgry pci, it looks
like the only one). So for backward compatibility, I'm introducing a new option
--pass-memmap-cmdline to force kexec-tools to pass memmap=exactmap, the old way.

This patchset contains massive updates from the previous one. I take some
suggestions from reviewers. I try to split the changes into smaller pieces and
keep the whole change as minimal as I can so it wouldn't be too harsh to review
the patch.

Any comment is appreciate!

v5->v4:
Dave:
 - separate add_setup_data() to another patch.
Vivek:
 - adding comments for setup_data.
 - store crash memory range info golobally in kexec_info.
me:
 -remove dbgprint_mem_range defination, Simon has merged the patch.

v3->v4:
Linn: check return value of malloc (use xmalloc).
me: fix dbgprintf_mem_range.

v2->v3:
Linn:
 - do not free sd (setup_data) buffer.
 - reuse code in setup_e820 and setup_e820_ext.

v1->v2:
Vivek:
 - Use function instead of macro for dbgprint_mem_range
 - Do not pass reserved memory range for kdump. It could addressed later
   separately.

WANG Chao (10):
  x86, cleanup: fix indent
  x86, cleanup: add extra arguments to add_memmap() and delete_memmap()
  x86, cleanup: add other types of memory range for 2nd kernel boot to
    memmap_p
  x86, cleanup: add_memmap() only do alignment check on RANGE_RAM
  x86, cleanup: use dbgprint_mem_range for memory range debugging
  x86, cleanup: increase CRASH_MAX_MEMMAP_NR up to
    CRASH_MAX_MEMORY_RANGES
  x86, cleanup: Store crash memory ranges kexec_info
  x86, cleanup: Add a funtion add_setup_data()
  x86: add --pass-memmap-cmdline option
  x86: Pass memory range via E820 for kdump

 kexec/arch/i386/crashdump-x86.c        |  79 +++++++--------
 kexec/arch/i386/crashdump-x86.h        |   2 +-
 kexec/arch/i386/include/arch/options.h |   2 +
 kexec/arch/i386/kexec-x86.c            |   4 +
 kexec/arch/i386/kexec-x86.h            |   1 +
 kexec/arch/i386/x86-linux-setup.c      | 175 ++++++++++++++++++++++-----------
 kexec/arch/i386/x86-linux-setup.h      |   1 +
 kexec/arch/x86_64/kexec-x86_64.c       |   5 +
 kexec/kexec.h                          |   2 +
 9 files changed, 171 insertions(+), 100 deletions(-)

-- 
1.8.5.3


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

[PATCH RESEND v5 01/10] x86, cleanup: fix indent

[WANG Chao]

Signed-off-by: WANG Chao <chaowang@redhat.com>
---
 kexec/arch/i386/crashdump-x86.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/kexec/arch/i386/crashdump-x86.c b/kexec/arch/i386/crashdump-x86.c
index 91872ab..72bce0b 100644
--- a/kexec/arch/i386/crashdump-x86.c
+++ b/kexec/arch/i386/crashdump-x86.c
@@ -509,11 +509,11 @@ static int add_memmap(struct memory_range *memmap_p, unsigned long long addr,
 		else if (addr > mend)
 			tidx = i+1;
 	}
-		/* Insert the memory region. */
-		for (j = nr_entries-1; j >= tidx; j--)
-			memmap_p[j+1] = memmap_p[j];
-		memmap_p[tidx].start = addr;
-		memmap_p[tidx].end = addr + size - 1;
+	/* Insert the memory region. */
+	for (j = nr_entries-1; j >= tidx; j--)
+		memmap_p[j+1] = memmap_p[j];
+	memmap_p[tidx].start = addr;
+	memmap_p[tidx].end = addr + size - 1;
 
 	dbgprintf("Memmap after adding segment\n");
 	for (i = 0; i < CRASH_MAX_MEMMAP_NR;  i++) {
-- 
1.8.5.3


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

[PATCH RESEND v5 02/10] x86, cleanup: add extra arguments to add_memmap() and delete_memmap()

[WANG Chao]

This change will be used later:

add_memmap(.., int *nr_memmap, .., int type);
delete_memmap(.., int *nr_memmap, ..);

Signed-off-by: WANG Chao <chaowang@redhat.com>
---
 kexec/arch/i386/crashdump-x86.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/kexec/arch/i386/crashdump-x86.c b/kexec/arch/i386/crashdump-x86.c
index 72bce0b..e695eaf 100644
--- a/kexec/arch/i386/crashdump-x86.c
+++ b/kexec/arch/i386/crashdump-x86.c
@@ -476,8 +476,8 @@ static int exclude_region(int *nr_ranges, uint64_t start, uint64_t end)
 
 /* Adds a segment from list of memory regions which new kernel can use to
  * boot. Segment start and end should be aligned to 1K boundary. */
-static int add_memmap(struct memory_range *memmap_p, unsigned long long addr,
-								size_t size)
+static int add_memmap(struct memory_range *memmap_p, int *nr_memmap_p,
+			unsigned long long addr, size_t size, int type)
 {
 	int i, j, nr_entries = 0, tidx = 0, align = 1024;
 	unsigned long long mstart, mend;
@@ -514,6 +514,8 @@ static int add_memmap(struct memory_range *memmap_p, unsigned long long addr,
 		memmap_p[j+1] = memmap_p[j];
 	memmap_p[tidx].start = addr;
 	memmap_p[tidx].end = addr + size - 1;
+	memmap_p[tidx].type = type;
+	*nr_memmap_p = nr_entries + 1;
 
 	dbgprintf("Memmap after adding segment\n");
 	for (i = 0; i < CRASH_MAX_MEMMAP_NR;  i++) {
@@ -530,8 +532,8 @@ static int add_memmap(struct memory_range *memmap_p, unsigned long long addr,
 
 /* Removes a segment from list of memory regions which new kernel can use to
  * boot. Segment start and end should be aligned to 1K boundary. */
-static int delete_memmap(struct memory_range *memmap_p, unsigned long long addr,
-								size_t size)
+static int delete_memmap(struct memory_range *memmap_p, int *nr_memmap_p,
+				unsigned long long addr, size_t size)
 {
 	int i, j, nr_entries = 0, tidx = -1, operation = 0, align = 1024;
 	unsigned long long mstart, mend;
@@ -593,12 +595,14 @@ static int delete_memmap(struct memory_range *memmap_p, unsigned long long addr,
 		for (j = nr_entries-1; j > tidx; j--)
 			memmap_p[j+1] = memmap_p[j];
 		memmap_p[tidx+1] = temp_region;
+		*nr_memmap_p = nr_entries + 1;
 	}
 	if ((operation == -1) && tidx >=0) {
 		/* Delete the exact match memory region. */
 		for (j = i+1; j < CRASH_MAX_MEMMAP_NR; j++)
 			memmap_p[j-1] = memmap_p[j];
 		memmap_p[j-1].start = memmap_p[j-1].end = 0;
+		*nr_memmap_p = nr_entries - 1;
 	}
 
 	dbgprintf("Memmap after deleting segment\n");
@@ -865,7 +869,7 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
 {
 	void *tmp;
 	unsigned long sz, bufsz, memsz, elfcorehdr;
-	int nr_ranges = 0, align = 1024, i;
+	int nr_ranges = 0, nr_memmap_p = 0, align = 1024, i;
 	struct memory_range *mem_range, *memmap_p;
 	struct crash_elf_info elf_info;
 	unsigned kexec_arch;
@@ -941,10 +945,10 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
 	sz = (sizeof(struct memory_range) * CRASH_MAX_MEMMAP_NR);
 	memmap_p = xmalloc(sz);
 	memset(memmap_p, 0, sz);
-	add_memmap(memmap_p, info->backup_src_start, info->backup_src_size);
+	add_memmap(memmap_p, &nr_memmap_p, info->backup_src_start, info->backup_src_size, RANGE_RAM);
 	for (i = 0; i < crash_reserved_mem_nr; i++) {
 		sz = crash_reserved_mem[i].end - crash_reserved_mem[i].start +1;
-		if (add_memmap(memmap_p, crash_reserved_mem[i].start, sz) < 0)
+		if (add_memmap(memmap_p, &nr_memmap_p, crash_reserved_mem[i].start, sz, RANGE_RAM) < 0)
 			return ENOCRASHKERNEL;
 	}
 
@@ -957,7 +961,7 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
 						0, max_addr, -1);
 		dbgprintf("Created backup segment at 0x%lx\n",
 			  info->backup_start);
-		if (delete_memmap(memmap_p, info->backup_start, sz) < 0)
+		if (delete_memmap(memmap_p, &nr_memmap_p, info->backup_start, sz) < 0)
 			return EFAILED;
 	}
 
@@ -993,7 +997,7 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
 	elfcorehdr = add_buffer(info, tmp, bufsz, memsz, align, min_base,
 							max_addr, -1);
 	dbgprintf("Created elf header segment at 0x%lx\n", elfcorehdr);
-	if (delete_memmap(memmap_p, elfcorehdr, memsz) < 0)
+	if (delete_memmap(memmap_p, &nr_memmap_p, elfcorehdr, memsz) < 0)
 		return -1;
 	cmdline_add_memmap(mod_cmdline, memmap_p);
 	if (!bzImage_support_efi_boot)
-- 
1.8.5.3


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

[PATCH RESEND v5 03/10] x86, cleanup: add other types of memory range for 2nd kernel boot to memmap_p

[WANG Chao]

Now memmap_p contains all the memory range for 2nd kernel boot.

Signed-off-by: WANG Chao <chaowang@redhat.com>
---
 kexec/arch/i386/crashdump-x86.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/kexec/arch/i386/crashdump-x86.c b/kexec/arch/i386/crashdump-x86.c
index e695eaf..43eb8f7 100644
--- a/kexec/arch/i386/crashdump-x86.c
+++ b/kexec/arch/i386/crashdump-x86.c
@@ -1006,12 +1006,15 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
 
 	/* Inform second kernel about the presence of ACPI tables. */
 	for (i = 0; i < CRASH_MAX_MEMORY_RANGES; i++) {
-		unsigned long start, end;
+		unsigned long start, end, size, type;
 		if ( !( mem_range[i].type == RANGE_ACPI
 			|| mem_range[i].type == RANGE_ACPI_NVS) )
 			continue;
 		start = mem_range[i].start;
 		end = mem_range[i].end;
+		type = mem_range[i].type;
+		size = end - start;
+		add_memmap(memmap_p, &nr_memmap_p, start, size, type);
 		cmdline_add_memmap_acpi(mod_cmdline, start, end);
 	}
 	return 0;
-- 
1.8.5.3


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

[PATCH RESEND v5 04/10] x86, cleanup: add_memmap() only do alignment check on RANGE_RAM

[WANG Chao]

Signed-off-by: WANG Chao <chaowang@redhat.com>
---
 kexec/arch/i386/crashdump-x86.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kexec/arch/i386/crashdump-x86.c b/kexec/arch/i386/crashdump-x86.c
index 43eb8f7..4072c10 100644
--- a/kexec/arch/i386/crashdump-x86.c
+++ b/kexec/arch/i386/crashdump-x86.c
@@ -482,8 +482,8 @@ static int add_memmap(struct memory_range *memmap_p, int *nr_memmap_p,
 	int i, j, nr_entries = 0, tidx = 0, align = 1024;
 	unsigned long long mstart, mend;
 
-	/* Do alignment check. */
-	if ((addr%align) || (size%align))
+	/* Do alignment check if it's RANGE_RAM */
+	if ((type == RANGE_RAM) && ((addr%align) || (size%align)))
 		return -1;
 
 	/* Make sure at least one entry in list is free. */
-- 
1.8.5.3


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

[PATCH RESEND v5 05/10] x86, cleanup: use dbgprint_mem_range for memory range debugging

[WANG Chao]

Signed-off-by: WANG Chao <chaowang@redhat.com>
---
 kexec/arch/i386/crashdump-x86.c | 26 +++-----------------------
 1 file changed, 3 insertions(+), 23 deletions(-)

diff --git a/kexec/arch/i386/crashdump-x86.c b/kexec/arch/i386/crashdump-x86.c
index 4072c10..2437c30 100644
--- a/kexec/arch/i386/crashdump-x86.c
+++ b/kexec/arch/i386/crashdump-x86.c
@@ -517,15 +517,7 @@ static int add_memmap(struct memory_range *memmap_p, int *nr_memmap_p,
 	memmap_p[tidx].type = type;
 	*nr_memmap_p = nr_entries + 1;
 
-	dbgprintf("Memmap after adding segment\n");
-	for (i = 0; i < CRASH_MAX_MEMMAP_NR;  i++) {
-		mstart = memmap_p[i].start;
-		mend = memmap_p[i].end;
-		if (mstart == 0 && mend == 0)
-			break;
-		dbgprintf("%016llx - %016llx\n",
-			mstart, mend);
-	}
+	dbgprint_mem_range("Memmap after adding segment", memmap_p, *nr_memmap_p);
 
 	return 0;
 }
@@ -605,16 +597,7 @@ static int delete_memmap(struct memory_range *memmap_p, int *nr_memmap_p,
 		*nr_memmap_p = nr_entries - 1;
 	}
 
-	dbgprintf("Memmap after deleting segment\n");
-	for (i = 0; i < CRASH_MAX_MEMMAP_NR;  i++) {
-		mstart = memmap_p[i].start;
-		mend = memmap_p[i].end;
-		if (mstart == 0 && mend == 0) {
-			break;
-		}
-		dbgprintf("%016llx - %016llx\n",
-			mstart, mend);
-	}
+	dbgprint_mem_range("Memmap after deleting segment", memmap_p, *nr_memmap_p);
 
 	return 0;
 }
@@ -913,10 +896,7 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
 
 	get_backup_area(info, mem_range, nr_ranges);
 
-	dbgprintf("CRASH MEMORY RANGES\n");
-
-	for(i = 0; i < nr_ranges; ++i)
-		dbgprintf("%016Lx-%016Lx\n", mem_range[i].start, mem_range[i].end);
+	dbgprint_mem_range("CRASH MEMORY RANGES", mem_range, nr_ranges);
 
 	/*
 	 * if the core type has not been set on command line, set it here
-- 
1.8.5.3


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

[PATCH RESEND v5 06/10] x86, cleanup: increase CRASH_MAX_MEMMAP_NR up to CRASH_MAX_MEMORY_RANGES

[WANG Chao]

CRASH_MAX_MEMMAP_NR now is defined (KEXEC_MAX_SEGMENTS + 2) which is way
lower than the memmap we can pass to 2nd kernel.

Signed-off-by: WANG Chao <chaowang@redhat.com>
---
 kexec/arch/i386/crashdump-x86.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kexec/arch/i386/crashdump-x86.h b/kexec/arch/i386/crashdump-x86.h
index b61cf0a..0edeb27 100644
--- a/kexec/arch/i386/crashdump-x86.h
+++ b/kexec/arch/i386/crashdump-x86.h
@@ -20,8 +20,8 @@ int load_crashdump_segments(struct kexec_info *info, char *mod_cmdline,
 /* Kernel text size */
 #define X86_64_KERNEL_TEXT_SIZE  (512UL*1024*1024)
 
-#define CRASH_MAX_MEMMAP_NR	(KEXEC_MAX_SEGMENTS + 1)
 #define CRASH_MAX_MEMORY_RANGES	(MAX_MEMORY_RANGES + 2)
+#define CRASH_MAX_MEMMAP_NR	CRASH_MAX_MEMORY_RANGES
 
 /* Backup Region, First 640K of System RAM. */
 #define BACKUP_SRC_START	0x00000000
-- 
1.8.5.3


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

[PATCH RESEND v5 07/10] x86, cleanup: Store crash memory ranges kexec_info

[WANG Chao]

Add two new members to kexec_info structure:

struct memory_range *crash_range
int nr_crash_ranges;

crash_range contains the memory ranges used to boot 2nd kernel.
nr_crash_ranges contains the count of the crash memory ranges.

Signed-off-by: WANG Chao <chaowang@redhat.com>
---
 kexec/arch/i386/crashdump-x86.c | 6 ++++++
 kexec/kexec.h                   | 2 ++
 2 files changed, 8 insertions(+)

diff --git a/kexec/arch/i386/crashdump-x86.c b/kexec/arch/i386/crashdump-x86.c
index 2437c30..2a6871d 100644
--- a/kexec/arch/i386/crashdump-x86.c
+++ b/kexec/arch/i386/crashdump-x86.c
@@ -997,6 +997,12 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
 		add_memmap(memmap_p, &nr_memmap_p, start, size, type);
 		cmdline_add_memmap_acpi(mod_cmdline, start, end);
 	}
+
+	/* Store 2nd kernel boot memory ranges for later reference in
+	 * x86-setup-linux.c: setup_linux_system_parameters() */
+	info->crash_range = memmap_p;
+	info->nr_crash_ranges = nr_memmap_p;
+
 	return 0;
 }
 
diff --git a/kexec/kexec.h b/kexec/kexec.h
index d69bba2..22d4a42 100644
--- a/kexec/kexec.h
+++ b/kexec/kexec.h
@@ -148,6 +148,8 @@ struct kexec_info {
 	int nr_segments;
 	struct memory_range *memory_range;
 	int memory_ranges;
+	struct memory_range *crash_range;
+	int nr_crash_ranges;
 	void *entry;
 	struct mem_ehdr rhdr;
 	unsigned long backup_start;
-- 
1.8.5.3


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

[PATCH RESEND v5 08/10] x86, cleanup: Add a funtion add_setup_data()

[WANG Chao]

add_setup_data() is used to add an instance to the single linked list
of setup_data structure.

Signed-off-by: WANG Chao <chaowang@redhat.com>
---
 kexec/arch/i386/x86-linux-setup.c | 26 ++++++++++++++++++++------
 1 file changed, 20 insertions(+), 6 deletions(-)

diff --git a/kexec/arch/i386/x86-linux-setup.c b/kexec/arch/i386/x86-linux-setup.c
index e04e45d..8ed36cc 100644
--- a/kexec/arch/i386/x86-linux-setup.c
+++ b/kexec/arch/i386/x86-linux-setup.c
@@ -603,6 +603,22 @@ struct efi_info {
 };
 
 /*
+ * Add another instance to single linked list of struct setup_data.
+ * Please refer to kernel Documentation/x86/boot.txt for more details
+ * about setup_data structure.
+ */
+static void add_setup_data(struct kexec_info *info,
+			   struct x86_linux_param_header *real_mode,
+			   struct setup_data *sd)
+{
+	int sdsize = sizeof(struct setup_data) + sd->len;
+
+	sd->next = real_mode->setup_data;
+	real_mode->setup_data = add_buffer(info, sd, sdsize, sdsize, getpagesize(),
+			    0x100000, ULONG_MAX, INT_MAX);
+}
+
+/*
  * setup_efi_data will collect below data and pass them to 2nd kernel.
  * 1) SMBIOS, fw_vendor, runtime, config_table, they are passed via x86
  *    setup_data.
@@ -611,11 +627,11 @@ struct efi_info {
 static int setup_efi_data(struct kexec_info *info,
 			  struct x86_linux_param_header *real_mode)
 {
-	int64_t setup_data_paddr, memmap_paddr;
+	int64_t memmap_paddr;
 	struct setup_data *sd;
 	struct efi_setup_data *esd;
 	struct efi_mem_descriptor *maps;
-	int nr_maps, size, sdsize, ret = 0;
+	int nr_maps, size, ret = 0;
 	struct efi_info *ei = (struct efi_info *)real_mode->efi_info;
 
 	ret = access("/sys/firmware/efi/systab", F_OK);
@@ -648,10 +664,8 @@ static int setup_efi_data(struct kexec_info *info,
 	sd->len = sizeof(*esd);
 	memcpy(sd->data, esd, sizeof(*esd));
 	free(esd);
-	sdsize = sd->len + sizeof(struct setup_data);
-	setup_data_paddr = add_buffer(info, sd, sdsize, sdsize, getpagesize(),
-					0x100000, ULONG_MAX, INT_MAX);
-	real_mode->setup_data = setup_data_paddr;
+
+	add_setup_data(info, real_mode, sd);
 
 	size = nr_maps * sizeof(struct efi_mem_descriptor);
 	memmap_paddr = add_buffer(info, maps, size, size, getpagesize(),
-- 
1.8.5.3


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

[PATCH RESEND v5 09/10] x86: add --pass-memmap-cmdline option

[WANG Chao]

--pass-memmap-cmdline is used for pass memmap=exactmap cmdline for 2nd
kernel. Later we will use this option to disable passing E820 memmap
method but use the old exactmap method.

Signed-off-by: WANG Chao <chaowang@redhat.com>
Tested-by: Linn Crosetto <linn@hp.com>
---
 kexec/arch/i386/include/arch/options.h | 2 ++
 kexec/arch/i386/kexec-x86.c            | 4 ++++
 kexec/arch/i386/kexec-x86.h            | 1 +
 kexec/arch/x86_64/kexec-x86_64.c       | 5 +++++
 4 files changed, 12 insertions(+)

diff --git a/kexec/arch/i386/include/arch/options.h b/kexec/arch/i386/include/arch/options.h
index aaac731..e5300b5 100644
--- a/kexec/arch/i386/include/arch/options.h
+++ b/kexec/arch/i386/include/arch/options.h
@@ -30,6 +30,7 @@
 #define OPT_VGA 		(OPT_ARCH_MAX+8)
 #define OPT_REAL_MODE		(OPT_ARCH_MAX+9)
 #define OPT_ENTRY_32BIT		(OPT_ARCH_MAX+10)
+#define OPT_PASS_MEMMAP_CMDLINE	(OPT_ARCH_MAX+11)
 
 /* Options relevant to the architecture (excluding loader-specific ones): */
 #define KEXEC_ARCH_OPTIONS \
@@ -41,6 +42,7 @@
 	{ "console-serial", 0, 0, OPT_CONSOLE_SERIAL }, \
 	{ "elf32-core-headers", 0, 0, OPT_ELF32_CORE }, \
 	{ "elf64-core-headers", 0, 0, OPT_ELF64_CORE }, \
+	{ "pass-memmap-cmdline", 0, 0, OPT_PASS_MEMMAP_CMDLINE }, \
 
 #define KEXEC_ARCH_OPT_STR KEXEC_OPT_STR ""
 
diff --git a/kexec/arch/i386/kexec-x86.c b/kexec/arch/i386/kexec-x86.c
index 014ecd5..0b58dff 100644
--- a/kexec/arch/i386/kexec-x86.c
+++ b/kexec/arch/i386/kexec-x86.c
@@ -54,6 +54,7 @@ void arch_usage(void)
 		"     --console-serial          Enable the serial console\n"
 		"     --elf32-core-headers      Prepare core headers in ELF32 format\n"
 		"     --elf64-core-headers      Prepare core headers in ELF64 format\n"
+		"     --pass--memmap-cmdline    Pass memory map via command line in kexec on panic case\n"
 		);
 }
 
@@ -64,6 +65,7 @@ struct arch_options_t arch_options = {
 	.console_vga = 0,
 	.console_serial = 0,
 	.core_header_type = CORE_TYPE_UNDEF,
+	.pass_memmap_cmdline = 0,
 };
 
 int arch_process_options(int argc, char **argv)
@@ -133,6 +135,8 @@ int arch_process_options(int argc, char **argv)
 		case OPT_ELF64_CORE:
 			arch_options.core_header_type = CORE_TYPE_ELF64;
 			break;
+		case OPT_PASS_MEMMAP_CMDLINE:
+			arch_options.pass_memmap_cmdline = 1;
 		}
 	}
 	/* Reset getopt for the next pass; called in other source modules */
diff --git a/kexec/arch/i386/kexec-x86.h b/kexec/arch/i386/kexec-x86.h
index 5aa2a46..e8c9188 100644
--- a/kexec/arch/i386/kexec-x86.h
+++ b/kexec/arch/i386/kexec-x86.h
@@ -50,6 +50,7 @@ struct arch_options_t {
 	uint8_t  	console_vga;
 	uint8_t  	console_serial;
 	enum coretype	core_header_type;
+	uint8_t  	pass_memmap_cmdline;
 };
 
 int multiboot_x86_probe(const char *buf, off_t len);
diff --git a/kexec/arch/x86_64/kexec-x86_64.c b/kexec/arch/x86_64/kexec-x86_64.c
index 5c23e01..f70851d 100644
--- a/kexec/arch/x86_64/kexec-x86_64.c
+++ b/kexec/arch/x86_64/kexec-x86_64.c
@@ -53,6 +53,7 @@ void arch_usage(void)
 		"     --serial-baud=<baud_rate> Specify the serial port baud rate\n"
 		"     --console-vga             Enable the vga console\n"
 		"     --console-serial          Enable the serial console\n"
+		"     --pass-memmap-cmdline     Pass memory map via command line in kexec on panic case\n"
 		);
 }
 
@@ -63,6 +64,7 @@ struct arch_options_t arch_options = {
 	.console_vga = 0,
 	.console_serial = 0,
 	.core_header_type = CORE_TYPE_ELF64,
+	.pass_memmap_cmdline = 0,
 };
 
 int arch_process_options(int argc, char **argv)
@@ -126,6 +128,9 @@ int arch_process_options(int argc, char **argv)
 			}
 			arch_options.serial_baud = value;
 			break;
+		case OPT_PASS_MEMMAP_CMDLINE:
+			arch_options.pass_memmap_cmdline = 1;
+			break;
 		}
 	}
 	/* Reset getopt for the next pass; called in other source modules */
-- 
1.8.5.3


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

[PATCH RESEND v5 10/10] x86: Pass memory range via E820 for kdump

[WANG Chao]

command line size is restricted by kernel, sometimes memmap=exactmap has
too many memory ranges to pass to cmdline. And also memmap=exactmap and
kASLR doesn't work together.

A better approach, to pass the memory ranges for crash kernel to boot
into, is filling the memory ranges into E820.

boot_params only got 128 slots for E820 map to fit in, when the number of
memory map exceeds 128, use setup_data to pass the rest as extended E820
memory map.

kexec boot could also benefit from setup_data in case E820 memory map
exceeds 128.

Now this new approach becomes default instead of memmap=exactmap.
saved_max_pfn users can specify --pass-memmap-cmdline to use the
exactmap approach.

Signed-off-by: WANG Chao <chaowang@redhat.com>
Tested-by: Linn Crosetto <linn@hp.com>
Reviewed-by: Linn Crosetto <linn@hp.com>
Signed-off-by: WANG Chao <chaowang@redhat.com>
---
 kexec/arch/i386/crashdump-x86.c   |   6 +-
 kexec/arch/i386/x86-linux-setup.c | 149 +++++++++++++++++++++++++-------------
 kexec/arch/i386/x86-linux-setup.h |   1 +
 3 files changed, 103 insertions(+), 53 deletions(-)

diff --git a/kexec/arch/i386/crashdump-x86.c b/kexec/arch/i386/crashdump-x86.c
index 2a6871d..2c0dbe3 100644
--- a/kexec/arch/i386/crashdump-x86.c
+++ b/kexec/arch/i386/crashdump-x86.c
@@ -979,7 +979,8 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
 	dbgprintf("Created elf header segment at 0x%lx\n", elfcorehdr);
 	if (delete_memmap(memmap_p, &nr_memmap_p, elfcorehdr, memsz) < 0)
 		return -1;
-	cmdline_add_memmap(mod_cmdline, memmap_p);
+	if (arch_options.pass_memmap_cmdline)
+		cmdline_add_memmap(mod_cmdline, memmap_p);
 	if (!bzImage_support_efi_boot)
 		cmdline_add_efi(mod_cmdline);
 	cmdline_add_elfcorehdr(mod_cmdline, elfcorehdr);
@@ -995,7 +996,8 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
 		type = mem_range[i].type;
 		size = end - start;
 		add_memmap(memmap_p, &nr_memmap_p, start, size, type);
-		cmdline_add_memmap_acpi(mod_cmdline, start, end);
+		if (arch_options.pass_memmap_cmdline)
+			cmdline_add_memmap_acpi(mod_cmdline, start, end);
 	}
 
 	/* Store 2nd kernel boot memory ranges for later reference in
diff --git a/kexec/arch/i386/x86-linux-setup.c b/kexec/arch/i386/x86-linux-setup.c
index 8ed36cc..2f9bb97 100644
--- a/kexec/arch/i386/x86-linux-setup.c
+++ b/kexec/arch/i386/x86-linux-setup.c
@@ -36,8 +36,6 @@
 #include "x86-linux-setup.h"
 #include "../../kexec/kexec-syscall.h"
 
-#define SETUP_EFI	4
-
 void init_linux_parameters(struct x86_linux_param_header *real_mode)
 {
 	/* Fill in the values that are usually provided by the kernel. */
@@ -502,6 +500,11 @@ struct efi_setup_data {
 struct setup_data {
 	uint64_t next;
 	uint32_t type;
+#define SETUP_NONE	0
+#define SETUP_E820_EXT	1
+#define SETUP_DTB	2
+#define SETUP_PCI	3
+#define SETUP_EFI	4
 	uint32_t len;
 	uint8_t data[0];
 } __attribute__((packed));
@@ -684,6 +687,98 @@ out:
 	return ret;
 }
 
+static void add_e820_map_from_mr(struct x86_linux_param_header *real_mode,
+			struct e820entry *e820, struct memory_range *range, int nr_range)
+{
+	int i;
+
+	for (i = 0; i < nr_range; i++) {
+		e820[i].addr = range[i].start;
+		e820[i].size = range[i].end - range[i].start;
+		switch (range[i].type) {
+			case RANGE_RAM:
+				e820[i].type = E820_RAM;
+				break;
+			case RANGE_ACPI:
+				e820[i].type = E820_ACPI;
+				break;
+			case RANGE_ACPI_NVS:
+				e820[i].type = E820_NVS;
+				break;
+			default:
+			case RANGE_RESERVED:
+				e820[i].type = E820_RESERVED;
+				break;
+		}
+		dbgprintf("%016lx-%016lx (%d)\n",
+				e820[i].addr,
+				e820[i].addr + e820[i].size - 1,
+				e820[i].type);
+
+		if (range[i].type != RANGE_RAM)
+			continue;
+		if ((range[i].start <= 0x100000) && range[i].end > 0x100000) {
+			unsigned long long mem_k = (range[i].end >> 10) - (0x100000 >> 10);
+			real_mode->ext_mem_k = mem_k;
+			real_mode->alt_mem_k = mem_k;
+			if (mem_k > 0xfc00) {
+				real_mode->ext_mem_k = 0xfc00; /* 64M */
+			}
+			if (mem_k > 0xffffffff) {
+				real_mode->alt_mem_k = 0xffffffff;
+			}
+		}
+	}
+}
+
+static void setup_e820_ext(struct kexec_info *info, struct x86_linux_param_header *real_mode,
+			   struct memory_range *range, int nr_range)
+{
+	struct setup_data *sd;
+	struct e820entry *e820;
+	int nr_range_ext;
+
+	nr_range_ext = nr_range - E820MAX;
+	sd = xmalloc(sizeof(struct setup_data) + nr_range_ext * sizeof(struct e820entry));
+	sd->next = 0;
+	sd->len = nr_range_ext * sizeof(struct e820entry);
+	sd->type = SETUP_E820_EXT;
+
+	e820 = (struct e820entry *) sd->data;
+	dbgprintf("Extended E820 via setup_data:\n");
+	add_e820_map_from_mr(real_mode, e820, range + E820MAX, nr_range_ext);
+	add_setup_data(info, real_mode, sd);
+}
+
+static void setup_e820(struct kexec_info *info, struct x86_linux_param_header *real_mode)
+{
+	struct memory_range *range;
+	int nr_range, nr_range_saved;
+
+
+	if (info->kexec_flags & KEXEC_ON_CRASH && !arch_options.pass_memmap_cmdline) {
+		range = info->crash_range;
+		nr_range = info->nr_crash_ranges;
+	} else {
+		range = info->memory_range;
+		nr_range = info->memory_ranges;
+	}
+
+	nr_range_saved = nr_range;
+	if (nr_range > E820MAX) {
+		nr_range = E820MAX;
+	}
+
+	real_mode->e820_map_nr = nr_range;
+	dbgprintf("E820 memmap:\n");
+	add_e820_map_from_mr(real_mode, real_mode->e820_map, range, nr_range);
+
+	if (nr_range_saved > E820MAX) {
+		dbgprintf("extra E820 memmap are passed via setup_data\n");
+		setup_e820_ext(info, real_mode, range, nr_range_saved);
+	}
+}
+
 static int
 get_efi_mem_desc_version(struct x86_linux_param_header *real_mode)
 {
@@ -725,10 +820,6 @@ out:
 void setup_linux_system_parameters(struct kexec_info *info,
 				   struct x86_linux_param_header *real_mode)
 {
-	/* Fill in information the BIOS would usually provide */
-	struct memory_range *range;
-	int i, ranges;
-
 	/* get subarch from running kernel */
 	setup_subarch(real_mode);
 	if (bzImage_support_efi_boot)
@@ -769,51 +860,7 @@ void setup_linux_system_parameters(struct kexec_info *info,
 	/* another safe default */
 	real_mode->aux_device_info = 0;
 
-	range = info->memory_range;
-	ranges = info->memory_ranges;
-	if (ranges > E820MAX) {
-		if (!(info->kexec_flags & KEXEC_ON_CRASH))
-			/*
-			 * this e820 not used for capture kernel, see
-			 * do_bzImage_load()
-			 */
-			fprintf(stderr,
-				"Too many memory ranges, truncating...\n");
-		ranges = E820MAX;
-	}
-	real_mode->e820_map_nr = ranges;
-	for(i = 0; i < ranges; i++) {
-		real_mode->e820_map[i].addr = range[i].start;
-		real_mode->e820_map[i].size = range[i].end - range[i].start;
-		switch (range[i].type) {
-		case RANGE_RAM:
-			real_mode->e820_map[i].type = E820_RAM; 
-			break;
-		case RANGE_ACPI:
-			real_mode->e820_map[i].type = E820_ACPI; 
-			break;
-		case RANGE_ACPI_NVS:
-			real_mode->e820_map[i].type = E820_NVS;
-			break;
-		default:
-		case RANGE_RESERVED:
-			real_mode->e820_map[i].type = E820_RESERVED; 
-			break;
-		}
-		if (range[i].type != RANGE_RAM)
-			continue;
-		if ((range[i].start <= 0x100000) && range[i].end > 0x100000) {
-			unsigned long long mem_k = (range[i].end >> 10) - (0x100000 >> 10);
-			real_mode->ext_mem_k = mem_k;
-			real_mode->alt_mem_k = mem_k;
-			if (mem_k > 0xfc00) {
-				real_mode->ext_mem_k = 0xfc00; /* 64M */
-			}
-			if (mem_k > 0xffffffff) {
-				real_mode->alt_mem_k = 0xffffffff;
-			}
-		}
-	}
+	setup_e820(info, real_mode);
 
 	/* fill the EDD information */
 	setup_edd_info(real_mode);
diff --git a/kexec/arch/i386/x86-linux-setup.h b/kexec/arch/i386/x86-linux-setup.h
index 6fb84b4..f5d23d3 100644
--- a/kexec/arch/i386/x86-linux-setup.h
+++ b/kexec/arch/i386/x86-linux-setup.h
@@ -30,5 +30,6 @@ void setup_linux_system_parameters(struct kexec_info *info,
 /* command line parameter may be appended by purgatory */
 #define PURGATORY_CMDLINE_SIZE 64
 extern int bzImage_support_efi_boot;
+extern struct arch_options_t arch_options;
 
 #endif /* X86_LINUX_SETUP_H */
-- 
1.8.5.3


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

Re: [PATCH RESEND v5 01/10] x86, cleanup: fix indent

[Simon Horman]

On Fri, Apr 11, 2014 at 10:23:22AM +0800, WANG Chao wrote:
> Signed-off-by: WANG Chao <chaowang@redhat.com>

Thanks, Applied.

> ---
>  kexec/arch/i386/crashdump-x86.c | 10 +++++-----
>  1 file changed, 5 insertions(+), 5 deletions(-)
> 
> diff --git a/kexec/arch/i386/crashdump-x86.c b/kexec/arch/i386/crashdump-x86.c
> index 91872ab..72bce0b 100644
> --- a/kexec/arch/i386/crashdump-x86.c
> +++ b/kexec/arch/i386/crashdump-x86.c
> @@ -509,11 +509,11 @@ static int add_memmap(struct memory_range *memmap_p, unsigned long long addr,
>  		else if (addr > mend)
>  			tidx = i+1;
>  	}
> -		/* Insert the memory region. */
> -		for (j = nr_entries-1; j >= tidx; j--)
> -			memmap_p[j+1] = memmap_p[j];
> -		memmap_p[tidx].start = addr;
> -		memmap_p[tidx].end = addr + size - 1;
> +	/* Insert the memory region. */
> +	for (j = nr_entries-1; j >= tidx; j--)
> +		memmap_p[j+1] = memmap_p[j];
> +	memmap_p[tidx].start = addr;
> +	memmap_p[tidx].end = addr + size - 1;
>  
>  	dbgprintf("Memmap after adding segment\n");
>  	for (i = 0; i < CRASH_MAX_MEMMAP_NR;  i++) {
> -- 
> 1.8.5.3
> 

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

Re: [PATCH RESEND v5 02/10] x86, cleanup: add extra arguments to add_memmap() and delete_memmap()

[Simon Horman]

On Fri, Apr 11, 2014 at 10:23:23AM +0800, WANG Chao wrote:
> This change will be used later:
> 
> add_memmap(.., int *nr_memmap, .., int type);
> delete_memmap(.., int *nr_memmap, ..);

Could you please include an explanation of the motivation for this
change in the change log (i.e. here).

> 
> Signed-off-by: WANG Chao <chaowang@redhat.com>
> ---
>  kexec/arch/i386/crashdump-x86.c | 22 +++++++++++++---------
>  1 file changed, 13 insertions(+), 9 deletions(-)
> 
> diff --git a/kexec/arch/i386/crashdump-x86.c b/kexec/arch/i386/crashdump-x86.c
> index 72bce0b..e695eaf 100644
> --- a/kexec/arch/i386/crashdump-x86.c
> +++ b/kexec/arch/i386/crashdump-x86.c
> @@ -476,8 +476,8 @@ static int exclude_region(int *nr_ranges, uint64_t start, uint64_t end)
>  
>  /* Adds a segment from list of memory regions which new kernel can use to
>   * boot. Segment start and end should be aligned to 1K boundary. */
> -static int add_memmap(struct memory_range *memmap_p, unsigned long long addr,
> -								size_t size)
> +static int add_memmap(struct memory_range *memmap_p, int *nr_memmap_p,
> +			unsigned long long addr, size_t size, int type)
>  {
>  	int i, j, nr_entries = 0, tidx = 0, align = 1024;
>  	unsigned long long mstart, mend;
> @@ -514,6 +514,8 @@ static int add_memmap(struct memory_range *memmap_p, unsigned long long addr,
>  		memmap_p[j+1] = memmap_p[j];
>  	memmap_p[tidx].start = addr;
>  	memmap_p[tidx].end = addr + size - 1;
> +	memmap_p[tidx].type = type;
> +	*nr_memmap_p = nr_entries + 1;
>  
>  	dbgprintf("Memmap after adding segment\n");
>  	for (i = 0; i < CRASH_MAX_MEMMAP_NR;  i++) {
> @@ -530,8 +532,8 @@ static int add_memmap(struct memory_range *memmap_p, unsigned long long addr,
>  
>  /* Removes a segment from list of memory regions which new kernel can use to
>   * boot. Segment start and end should be aligned to 1K boundary. */
> -static int delete_memmap(struct memory_range *memmap_p, unsigned long long addr,
> -								size_t size)
> +static int delete_memmap(struct memory_range *memmap_p, int *nr_memmap_p,
> +				unsigned long long addr, size_t size)
>  {
>  	int i, j, nr_entries = 0, tidx = -1, operation = 0, align = 1024;
>  	unsigned long long mstart, mend;
> @@ -593,12 +595,14 @@ static int delete_memmap(struct memory_range *memmap_p, unsigned long long addr,
>  		for (j = nr_entries-1; j > tidx; j--)
>  			memmap_p[j+1] = memmap_p[j];
>  		memmap_p[tidx+1] = temp_region;
> +		*nr_memmap_p = nr_entries + 1;
>  	}
>  	if ((operation == -1) && tidx >=0) {
>  		/* Delete the exact match memory region. */
>  		for (j = i+1; j < CRASH_MAX_MEMMAP_NR; j++)
>  			memmap_p[j-1] = memmap_p[j];
>  		memmap_p[j-1].start = memmap_p[j-1].end = 0;
> +		*nr_memmap_p = nr_entries - 1;
>  	}
>  
>  	dbgprintf("Memmap after deleting segment\n");
> @@ -865,7 +869,7 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
>  {
>  	void *tmp;
>  	unsigned long sz, bufsz, memsz, elfcorehdr;
> -	int nr_ranges = 0, align = 1024, i;
> +	int nr_ranges = 0, nr_memmap_p = 0, align = 1024, i;
>  	struct memory_range *mem_range, *memmap_p;
>  	struct crash_elf_info elf_info;
>  	unsigned kexec_arch;
> @@ -941,10 +945,10 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
>  	sz = (sizeof(struct memory_range) * CRASH_MAX_MEMMAP_NR);
>  	memmap_p = xmalloc(sz);
>  	memset(memmap_p, 0, sz);
> -	add_memmap(memmap_p, info->backup_src_start, info->backup_src_size);
> +	add_memmap(memmap_p, &nr_memmap_p, info->backup_src_start, info->backup_src_size, RANGE_RAM);
>  	for (i = 0; i < crash_reserved_mem_nr; i++) {
>  		sz = crash_reserved_mem[i].end - crash_reserved_mem[i].start +1;
> -		if (add_memmap(memmap_p, crash_reserved_mem[i].start, sz) < 0)
> +		if (add_memmap(memmap_p, &nr_memmap_p, crash_reserved_mem[i].start, sz, RANGE_RAM) < 0)
>  			return ENOCRASHKERNEL;
>  	}
>  
> @@ -957,7 +961,7 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
>  						0, max_addr, -1);
>  		dbgprintf("Created backup segment at 0x%lx\n",
>  			  info->backup_start);
> -		if (delete_memmap(memmap_p, info->backup_start, sz) < 0)
> +		if (delete_memmap(memmap_p, &nr_memmap_p, info->backup_start, sz) < 0)
>  			return EFAILED;
>  	}
>  
> @@ -993,7 +997,7 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
>  	elfcorehdr = add_buffer(info, tmp, bufsz, memsz, align, min_base,
>  							max_addr, -1);
>  	dbgprintf("Created elf header segment at 0x%lx\n", elfcorehdr);
> -	if (delete_memmap(memmap_p, elfcorehdr, memsz) < 0)
> +	if (delete_memmap(memmap_p, &nr_memmap_p, elfcorehdr, memsz) < 0)
>  		return -1;
>  	cmdline_add_memmap(mod_cmdline, memmap_p);
>  	if (!bzImage_support_efi_boot)
> -- 
> 1.8.5.3
> 

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

Re: [PATCH RESEND v5 03/10] x86, cleanup: add other types of memory range for 2nd kernel boot to memmap_p

[Simon Horman]

On Fri, Apr 11, 2014 at 10:23:24AM +0800, WANG Chao wrote:
> Now memmap_p contains all the memory range for 2nd kernel boot.

Could you please include a fuller explanation of what this patch
achieves and the motivation for it.

> 
> Signed-off-by: WANG Chao <chaowang@redhat.com>
> ---
>  kexec/arch/i386/crashdump-x86.c | 5 ++++-
>  1 file changed, 4 insertions(+), 1 deletion(-)
> 
> diff --git a/kexec/arch/i386/crashdump-x86.c b/kexec/arch/i386/crashdump-x86.c
> index e695eaf..43eb8f7 100644
> --- a/kexec/arch/i386/crashdump-x86.c
> +++ b/kexec/arch/i386/crashdump-x86.c
> @@ -1006,12 +1006,15 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
>  
>  	/* Inform second kernel about the presence of ACPI tables. */
>  	for (i = 0; i < CRASH_MAX_MEMORY_RANGES; i++) {
> -		unsigned long start, end;
> +		unsigned long start, end, size, type;
>  		if ( !( mem_range[i].type == RANGE_ACPI
>  			|| mem_range[i].type == RANGE_ACPI_NVS) )
>  			continue;
>  		start = mem_range[i].start;
>  		end = mem_range[i].end;
> +		type = mem_range[i].type;
> +		size = end - start;
> +		add_memmap(memmap_p, &nr_memmap_p, start, size, type);
>  		cmdline_add_memmap_acpi(mod_cmdline, start, end);
>  	}
>  	return 0;
> -- 
> 1.8.5.3
> 

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

Re: [PATCH RESEND v5 04/10] x86, cleanup: add_memmap() only do alignment check on RANGE_RAM

[Simon Horman]

Could you please explain why this is necessary.

Also, it seems to me that it would make sense to move this
patch so that is is immediately after patch 2 in the series.

On Fri, Apr 11, 2014 at 10:23:25AM +0800, WANG Chao wrote:
> Signed-off-by: WANG Chao <chaowang@redhat.com>
> ---
>  kexec/arch/i386/crashdump-x86.c | 4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
> 
> diff --git a/kexec/arch/i386/crashdump-x86.c b/kexec/arch/i386/crashdump-x86.c
> index 43eb8f7..4072c10 100644
> --- a/kexec/arch/i386/crashdump-x86.c
> +++ b/kexec/arch/i386/crashdump-x86.c
> @@ -482,8 +482,8 @@ static int add_memmap(struct memory_range *memmap_p, int *nr_memmap_p,
>  	int i, j, nr_entries = 0, tidx = 0, align = 1024;
>  	unsigned long long mstart, mend;
>  
> -	/* Do alignment check. */
> -	if ((addr%align) || (size%align))
> +	/* Do alignment check if it's RANGE_RAM */
> +	if ((type == RANGE_RAM) && ((addr%align) || (size%align)))
>  		return -1;
>  
>  	/* Make sure at least one entry in list is free. */
> -- 
> 1.8.5.3
> 

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

Re: [PATCH RESEND v5 08/10] x86, cleanup: Add a funtion add_setup_data()

[Simon Horman]

On Fri, Apr 11, 2014 at 10:23:29AM +0800, WANG Chao wrote:
> add_setup_data() is used to add an instance to the single linked list
> of setup_data structure.
> 
> Signed-off-by: WANG Chao <chaowang@redhat.com>

Thanks, applied.

> ---
>  kexec/arch/i386/x86-linux-setup.c | 26 ++++++++++++++++++++------
>  1 file changed, 20 insertions(+), 6 deletions(-)
> 
> diff --git a/kexec/arch/i386/x86-linux-setup.c b/kexec/arch/i386/x86-linux-setup.c
> index e04e45d..8ed36cc 100644
> --- a/kexec/arch/i386/x86-linux-setup.c
> +++ b/kexec/arch/i386/x86-linux-setup.c
> @@ -603,6 +603,22 @@ struct efi_info {
>  };
>  
>  /*
> + * Add another instance to single linked list of struct setup_data.
> + * Please refer to kernel Documentation/x86/boot.txt for more details
> + * about setup_data structure.
> + */
> +static void add_setup_data(struct kexec_info *info,
> +			   struct x86_linux_param_header *real_mode,
> +			   struct setup_data *sd)
> +{
> +	int sdsize = sizeof(struct setup_data) + sd->len;
> +
> +	sd->next = real_mode->setup_data;
> +	real_mode->setup_data = add_buffer(info, sd, sdsize, sdsize, getpagesize(),
> +			    0x100000, ULONG_MAX, INT_MAX);
> +}
> +
> +/*
>   * setup_efi_data will collect below data and pass them to 2nd kernel.
>   * 1) SMBIOS, fw_vendor, runtime, config_table, they are passed via x86
>   *    setup_data.
> @@ -611,11 +627,11 @@ struct efi_info {
>  static int setup_efi_data(struct kexec_info *info,
>  			  struct x86_linux_param_header *real_mode)
>  {
> -	int64_t setup_data_paddr, memmap_paddr;
> +	int64_t memmap_paddr;
>  	struct setup_data *sd;
>  	struct efi_setup_data *esd;
>  	struct efi_mem_descriptor *maps;
> -	int nr_maps, size, sdsize, ret = 0;
> +	int nr_maps, size, ret = 0;
>  	struct efi_info *ei = (struct efi_info *)real_mode->efi_info;
>  
>  	ret = access("/sys/firmware/efi/systab", F_OK);
> @@ -648,10 +664,8 @@ static int setup_efi_data(struct kexec_info *info,
>  	sd->len = sizeof(*esd);
>  	memcpy(sd->data, esd, sizeof(*esd));
>  	free(esd);
> -	sdsize = sd->len + sizeof(struct setup_data);
> -	setup_data_paddr = add_buffer(info, sd, sdsize, sdsize, getpagesize(),
> -					0x100000, ULONG_MAX, INT_MAX);
> -	real_mode->setup_data = setup_data_paddr;
> +
> +	add_setup_data(info, real_mode, sd);
>  
>  	size = nr_maps * sizeof(struct efi_mem_descriptor);
>  	memmap_paddr = add_buffer(info, maps, size, size, getpagesize(),
> -- 
> 1.8.5.3
> 

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

Re: [PATCH RESEND v5 04/10] x86, cleanup: add_memmap() only do alignment check on RANGE_RAM

[WANG Chao]

On 04/14/14 at 11:13am, Simon Horman wrote:
> Could you please explain why this is necessary.

add_memmap() will also add memory range with type RANGE_ACPI and
RANGE_ACPI_NVS (RANGE_RESERVED in the future) besides RANGE_RAM to
memmap_p.

Among these types of memory range, only RANGE_RAM needs to
be aligned with certain alignment. RANGE_ACPI, RANGE_ACPI_NVS and
RANGE_RESERVED doesn't have to be aligned.

I'll add above comment to the patch description.

> 
> Also, it seems to me that it would make sense to move this
> patch so that is is immediately after patch 2 in the series.

Will do.

> 
> On Fri, Apr 11, 2014 at 10:23:25AM +0800, WANG Chao wrote:
> > Signed-off-by: WANG Chao <chaowang@redhat.com>
> > ---
> >  kexec/arch/i386/crashdump-x86.c | 4 ++--
> >  1 file changed, 2 insertions(+), 2 deletions(-)
> > 
> > diff --git a/kexec/arch/i386/crashdump-x86.c b/kexec/arch/i386/crashdump-x86.c
> > index 43eb8f7..4072c10 100644
> > --- a/kexec/arch/i386/crashdump-x86.c
> > +++ b/kexec/arch/i386/crashdump-x86.c
> > @@ -482,8 +482,8 @@ static int add_memmap(struct memory_range *memmap_p, int *nr_memmap_p,
> >  	int i, j, nr_entries = 0, tidx = 0, align = 1024;
> >  	unsigned long long mstart, mend;
> >  
> > -	/* Do alignment check. */
> > -	if ((addr%align) || (size%align))
> > +	/* Do alignment check if it's RANGE_RAM */
> > +	if ((type == RANGE_RAM) && ((addr%align) || (size%align)))
> >  		return -1;
> >  
> >  	/* Make sure at least one entry in list is free. */
> > -- 
> > 1.8.5.3
> > 

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

Re: [PATCH RESEND v5 03/10] x86, cleanup: add other types of memory range for 2nd kernel boot to memmap_p

[WANG Chao]

On 04/14/14 at 11:12am, Simon Horman wrote:
> On Fri, Apr 11, 2014 at 10:23:24AM +0800, WANG Chao wrote:
> > Now memmap_p contains all the memory range for 2nd kernel boot.
> 
> Could you please include a fuller explanation of what this patch
> achieves and the motivation for it.

In load_crashdump_segments(), memmap_p used to contain RANGE_RAM memory
range for booting 2nd kernel. Now adding types of RANGE_ACPI and
RANGE_ACPI_NVS to memmap_p, so later we can pass all the types of memory
range to 2nd kernel. These all types of memory ranges are all stored in
memmap_p.

I'll add above comment to patch description.

Thanks
WANG Chao

> 
> > 
> > Signed-off-by: WANG Chao <chaowang@redhat.com>
> > ---
> >  kexec/arch/i386/crashdump-x86.c | 5 ++++-
> >  1 file changed, 4 insertions(+), 1 deletion(-)
> > 
> > diff --git a/kexec/arch/i386/crashdump-x86.c b/kexec/arch/i386/crashdump-x86.c
> > index e695eaf..43eb8f7 100644
> > --- a/kexec/arch/i386/crashdump-x86.c
> > +++ b/kexec/arch/i386/crashdump-x86.c
> > @@ -1006,12 +1006,15 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
> >  
> >  	/* Inform second kernel about the presence of ACPI tables. */
> >  	for (i = 0; i < CRASH_MAX_MEMORY_RANGES; i++) {
> > -		unsigned long start, end;
> > +		unsigned long start, end, size, type;
> >  		if ( !( mem_range[i].type == RANGE_ACPI
> >  			|| mem_range[i].type == RANGE_ACPI_NVS) )
> >  			continue;
> >  		start = mem_range[i].start;
> >  		end = mem_range[i].end;
> > +		type = mem_range[i].type;
> > +		size = end - start;
> > +		add_memmap(memmap_p, &nr_memmap_p, start, size, type);
> >  		cmdline_add_memmap_acpi(mod_cmdline, start, end);
> >  	}
> >  	return 0;
> > -- 
> > 1.8.5.3
> > 

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

Re: [PATCH RESEND v5 02/10] x86, cleanup: add extra arguments to add_memmap() and delete_memmap()

[WANG Chao]

On 04/14/14 at 11:11am, Simon Horman wrote:
> On Fri, Apr 11, 2014 at 10:23:23AM +0800, WANG Chao wrote:
> > This change will be used later:
> > 
> > add_memmap(.., int *nr_memmap, .., int type);
> > delete_memmap(.., int *nr_memmap, ..);
> 
> Could you please include an explanation of the motivation for this
> change in the change log (i.e. here).

memmap_p[] is statically allocated for a certain amount. It will be used
later when mapping these memory maps to e820 map.

It's convenient to keep track of the count of memmap_p (nr_memmap) in
add_memmap and delete_memmap, because the counting has already been
taken care of in these two functions.

The original add_memmap() can only add memory range of RANGE_RAM type.
For adding other types of memory range, add another argument for
indicating the type.

Thanks
WANG Chao

> 
> > 
> > Signed-off-by: WANG Chao <chaowang@redhat.com>
> > ---
> >  kexec/arch/i386/crashdump-x86.c | 22 +++++++++++++---------
> >  1 file changed, 13 insertions(+), 9 deletions(-)
> > 
> > diff --git a/kexec/arch/i386/crashdump-x86.c b/kexec/arch/i386/crashdump-x86.c
> > index 72bce0b..e695eaf 100644
> > --- a/kexec/arch/i386/crashdump-x86.c
> > +++ b/kexec/arch/i386/crashdump-x86.c
> > @@ -476,8 +476,8 @@ static int exclude_region(int *nr_ranges, uint64_t start, uint64_t end)
> >  
> >  /* Adds a segment from list of memory regions which new kernel can use to
> >   * boot. Segment start and end should be aligned to 1K boundary. */
> > -static int add_memmap(struct memory_range *memmap_p, unsigned long long addr,
> > -								size_t size)
> > +static int add_memmap(struct memory_range *memmap_p, int *nr_memmap_p,
> > +			unsigned long long addr, size_t size, int type)
> >  {
> >  	int i, j, nr_entries = 0, tidx = 0, align = 1024;
> >  	unsigned long long mstart, mend;
> > @@ -514,6 +514,8 @@ static int add_memmap(struct memory_range *memmap_p, unsigned long long addr,
> >  		memmap_p[j+1] = memmap_p[j];
> >  	memmap_p[tidx].start = addr;
> >  	memmap_p[tidx].end = addr + size - 1;
> > +	memmap_p[tidx].type = type;
> > +	*nr_memmap_p = nr_entries + 1;
> >  
> >  	dbgprintf("Memmap after adding segment\n");
> >  	for (i = 0; i < CRASH_MAX_MEMMAP_NR;  i++) {
> > @@ -530,8 +532,8 @@ static int add_memmap(struct memory_range *memmap_p, unsigned long long addr,
> >  
> >  /* Removes a segment from list of memory regions which new kernel can use to
> >   * boot. Segment start and end should be aligned to 1K boundary. */
> > -static int delete_memmap(struct memory_range *memmap_p, unsigned long long addr,
> > -								size_t size)
> > +static int delete_memmap(struct memory_range *memmap_p, int *nr_memmap_p,
> > +				unsigned long long addr, size_t size)
> >  {
> >  	int i, j, nr_entries = 0, tidx = -1, operation = 0, align = 1024;
> >  	unsigned long long mstart, mend;
> > @@ -593,12 +595,14 @@ static int delete_memmap(struct memory_range *memmap_p, unsigned long long addr,
> >  		for (j = nr_entries-1; j > tidx; j--)
> >  			memmap_p[j+1] = memmap_p[j];
> >  		memmap_p[tidx+1] = temp_region;
> > +		*nr_memmap_p = nr_entries + 1;
> >  	}
> >  	if ((operation == -1) && tidx >=0) {
> >  		/* Delete the exact match memory region. */
> >  		for (j = i+1; j < CRASH_MAX_MEMMAP_NR; j++)
> >  			memmap_p[j-1] = memmap_p[j];
> >  		memmap_p[j-1].start = memmap_p[j-1].end = 0;
> > +		*nr_memmap_p = nr_entries - 1;
> >  	}
> >  
> >  	dbgprintf("Memmap after deleting segment\n");
> > @@ -865,7 +869,7 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
> >  {
> >  	void *tmp;
> >  	unsigned long sz, bufsz, memsz, elfcorehdr;
> > -	int nr_ranges = 0, align = 1024, i;
> > +	int nr_ranges = 0, nr_memmap_p = 0, align = 1024, i;
> >  	struct memory_range *mem_range, *memmap_p;
> >  	struct crash_elf_info elf_info;
> >  	unsigned kexec_arch;
> > @@ -941,10 +945,10 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
> >  	sz = (sizeof(struct memory_range) * CRASH_MAX_MEMMAP_NR);
> >  	memmap_p = xmalloc(sz);
> >  	memset(memmap_p, 0, sz);
> > -	add_memmap(memmap_p, info->backup_src_start, info->backup_src_size);
> > +	add_memmap(memmap_p, &nr_memmap_p, info->backup_src_start, info->backup_src_size, RANGE_RAM);
> >  	for (i = 0; i < crash_reserved_mem_nr; i++) {
> >  		sz = crash_reserved_mem[i].end - crash_reserved_mem[i].start +1;
> > -		if (add_memmap(memmap_p, crash_reserved_mem[i].start, sz) < 0)
> > +		if (add_memmap(memmap_p, &nr_memmap_p, crash_reserved_mem[i].start, sz, RANGE_RAM) < 0)
> >  			return ENOCRASHKERNEL;
> >  	}
> >  
> > @@ -957,7 +961,7 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
> >  						0, max_addr, -1);
> >  		dbgprintf("Created backup segment at 0x%lx\n",
> >  			  info->backup_start);
> > -		if (delete_memmap(memmap_p, info->backup_start, sz) < 0)
> > +		if (delete_memmap(memmap_p, &nr_memmap_p, info->backup_start, sz) < 0)
> >  			return EFAILED;
> >  	}
> >  
> > @@ -993,7 +997,7 @@ int load_crashdump_segments(struct kexec_info *info, char* mod_cmdline,
> >  	elfcorehdr = add_buffer(info, tmp, bufsz, memsz, align, min_base,
> >  							max_addr, -1);
> >  	dbgprintf("Created elf header segment at 0x%lx\n", elfcorehdr);
> > -	if (delete_memmap(memmap_p, elfcorehdr, memsz) < 0)
> > +	if (delete_memmap(memmap_p, &nr_memmap_p, elfcorehdr, memsz) < 0)
> >  		return -1;
> >  	cmdline_add_memmap(mod_cmdline, memmap_p);
> >  	if (!bzImage_support_efi_boot)
> > -- 
> > 1.8.5.3
> > 

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