1 files changed, 324 insertions, 103 deletions

diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 39f8fd4438f..a3b9150e680 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -11,59 +11,262 @@
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
-#include <linux/crash_dump.h>
 #include <linux/bootmem.h>
 #include <linux/elf.h>
+#include <linux/memblock.h>
+#include <asm/os_info.h>
+#include <asm/elf.h>
 #include <asm/ipl.h>
+#include <asm/sclp.h>
 
 #define PTR_ADD(x, y) (((char *) (x)) + ((unsigned long) (y)))
 #define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y)))
 #define PTR_DIFF(x, y) ((unsigned long)(((char *) (x)) - ((unsigned long) (y))))
 
+static struct memblock_region oldmem_region;
+
+static struct memblock_type oldmem_type = {
+	.cnt = 1,
+	.max = 1,
+	.total_size = 0,
+	.regions = &oldmem_region,
+};
+
+#define for_each_dump_mem_range(i, nid, p_start, p_end, p_nid)		\
+	for (i = 0, __next_mem_range(&i, nid, &memblock.physmem,	\
+				     &oldmem_type, p_start,		\
+				     p_end, p_nid);			\
+	     i != (u64)ULLONG_MAX;					\
+	     __next_mem_range(&i, nid, &memblock.physmem,		\
+			      &oldmem_type,				\
+			      p_start, p_end, p_nid))
+
+struct dump_save_areas dump_save_areas;
+
 /*
- * Copy one page from "oldmem"
+ * Allocate and add a save area for a CPU
+ */
+struct save_area *dump_save_area_create(int cpu)
+{
+	struct save_area **save_areas, *save_area;
+
+	save_area = kmalloc(sizeof(*save_area), GFP_KERNEL);
+	if (!save_area)
+		return NULL;
+	if (cpu + 1 > dump_save_areas.count) {
+		dump_save_areas.count = cpu + 1;
+		save_areas = krealloc(dump_save_areas.areas,
+				      dump_save_areas.count * sizeof(void *),
+				      GFP_KERNEL | __GFP_ZERO);
+		if (!save_areas) {
+			kfree(save_area);
+			return NULL;
+		}
+		dump_save_areas.areas = save_areas;
+	}
+	dump_save_areas.areas[cpu] = save_area;
+	return save_area;
+}
+
+/*
+ * Return physical address for virtual address
+ */
+static inline void *load_real_addr(void *addr)
+{
+	unsigned long real_addr;
+
+	asm volatile(
+		   "	lra     %0,0(%1)\n"
+		   "	jz	0f\n"
+		   "	la	%0,0\n"
+		   "0:"
+		   : "=a" (real_addr) : "a" (addr) : "cc");
+	return (void *)real_addr;
+}
+
+/*
+ * Copy real to virtual or real memory
+ */
+static int copy_from_realmem(void *dest, void *src, size_t count)
+{
+	unsigned long size;
+
+	if (!count)
+		return 0;
+	if (!is_vmalloc_or_module_addr(dest))
+		return memcpy_real(dest, src, count);
+	do {
+		size = min(count, PAGE_SIZE - (__pa(dest) & ~PAGE_MASK));
+		if (memcpy_real(load_real_addr(dest), src, size))
+			return -EFAULT;
+		count -= size;
+		dest += size;
+		src += size;
+	} while (count);
+	return 0;
+}
+
+/*
+ * Pointer to ELF header in new kernel
+ */
+static void *elfcorehdr_newmem;
+
+/*
+ * Copy one page from zfcpdump "oldmem"
+ *
+ * For pages below HSA size memory from the HSA is copied. Otherwise
+ * real memory copy is used.
+ */
+static ssize_t copy_oldmem_page_zfcpdump(char *buf, size_t csize,
+					 unsigned long src, int userbuf)
+{
+	int rc;
+
+	if (src < sclp_get_hsa_size()) {
+		rc = memcpy_hsa(buf, src, csize, userbuf);
+	} else {
+		if (userbuf)
+			rc = copy_to_user_real((void __force __user *) buf,
+					       (void *) src, csize);
+		else
+			rc = memcpy_real(buf, (void *) src, csize);
+	}
+	return rc ? rc : csize;
+}
+
+/*
+ * Copy one page from kdump "oldmem"
  *
  * For the kdump reserved memory this functions performs a swap operation:
  *  - [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] is mapped to [0 - OLDMEM_SIZE].
  *  - [0 - OLDMEM_SIZE] is mapped to [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE]
  */
-ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
-			 size_t csize, unsigned long offset, int userbuf)
-{
-	unsigned long src;
+static ssize_t copy_oldmem_page_kdump(char *buf, size_t csize,
+				      unsigned long src, int userbuf)
 
-	if (!csize)
-		return 0;
+{
+	int rc;
 
-	src = (pfn << PAGE_SHIFT) + offset;
 	if (src < OLDMEM_SIZE)
 		src += OLDMEM_BASE;
 	else if (src > OLDMEM_BASE &&
 		 src < OLDMEM_BASE + OLDMEM_SIZE)
 		src -= OLDMEM_BASE;
 	if (userbuf)
-		copy_to_user_real((void __force __user *) buf, (void *) src,
-				  csize);
+		rc = copy_to_user_real((void __force __user *) buf,
+				       (void *) src, csize);
+	else
+		rc = copy_from_realmem(buf, (void *) src, csize);
+	return (rc == 0) ? rc : csize;
+}
+
+/*
+ * Copy one page from "oldmem"
+ */
+ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize,
+			 unsigned long offset, int userbuf)
+{
+	unsigned long src;
+
+	if (!csize)
+		return 0;
+	src = (pfn << PAGE_SHIFT) + offset;
+	if (OLDMEM_BASE)
+		return copy_oldmem_page_kdump(buf, csize, src, userbuf);
+	else
+		return copy_oldmem_page_zfcpdump(buf, csize, src, userbuf);
+}
+
+/*
+ * Remap "oldmem" for kdump
+ *
+ * For the kdump reserved memory this functions performs a swap operation:
+ * [0 - OLDMEM_SIZE] is mapped to [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE]
+ */
+static int remap_oldmem_pfn_range_kdump(struct vm_area_struct *vma,
+					unsigned long from, unsigned long pfn,
+					unsigned long size, pgprot_t prot)
+{
+	unsigned long size_old;
+	int rc;
+
+	if (pfn < OLDMEM_SIZE >> PAGE_SHIFT) {
+		size_old = min(size, OLDMEM_SIZE - (pfn << PAGE_SHIFT));
+		rc = remap_pfn_range(vma, from,
+				     pfn + (OLDMEM_BASE >> PAGE_SHIFT),
+				     size_old, prot);
+		if (rc || size == size_old)
+			return rc;
+		size -= size_old;
+		from += size_old;
+		pfn += size_old >> PAGE_SHIFT;
+	}
+	return remap_pfn_range(vma, from, pfn, size, prot);
+}
+
+/*
+ * Remap "oldmem" for zfcpdump
+ *
+ * We only map available memory above HSA size. Memory below HSA size
+ * is read on demand using the copy_oldmem_page() function.
+ */
+static int remap_oldmem_pfn_range_zfcpdump(struct vm_area_struct *vma,
+					   unsigned long from,
+					   unsigned long pfn,
+					   unsigned long size, pgprot_t prot)
+{
+	unsigned long hsa_end = sclp_get_hsa_size();
+	unsigned long size_hsa;
+
+	if (pfn < hsa_end >> PAGE_SHIFT) {
+		size_hsa = min(size, hsa_end - (pfn << PAGE_SHIFT));
+		if (size == size_hsa)
+			return 0;
+		size -= size_hsa;
+		from += size_hsa;
+		pfn += size_hsa >> PAGE_SHIFT;
+	}
+	return remap_pfn_range(vma, from, pfn, size, prot);
+}
+
+/*
+ * Remap "oldmem" for kdump or zfcpdump
+ */
+int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from,
+			   unsigned long pfn, unsigned long size, pgprot_t prot)
+{
+	if (OLDMEM_BASE)
+		return remap_oldmem_pfn_range_kdump(vma, from, pfn, size, prot);
 	else
-		memcpy_real(buf, (void *) src, csize);
-	return csize;
+		return remap_oldmem_pfn_range_zfcpdump(vma, from, pfn, size,
+						       prot);
 }
 
 /*
  * Copy memory from old kernel
  */
-static int copy_from_oldmem(void *dest, void *src, size_t count)
+int copy_from_oldmem(void *dest, void *src, size_t count)
 {
 	unsigned long copied = 0;
 	int rc;
 
-	if ((unsigned long) src < OLDMEM_SIZE) {
-		copied = min(count, OLDMEM_SIZE - (unsigned long) src);
-		rc = memcpy_real(dest, src + OLDMEM_BASE, copied);
-		if (rc)
-			return rc;
+	if (OLDMEM_BASE) {
+		if ((unsigned long) src < OLDMEM_SIZE) {
+			copied = min(count, OLDMEM_SIZE - (unsigned long) src);
+			rc = copy_from_realmem(dest, src + OLDMEM_BASE, copied);
+			if (rc)
+				return rc;
+		}
+	} else {
+		unsigned long hsa_end = sclp_get_hsa_size();
+		if ((unsigned long) src < hsa_end) {
+			copied = min(count, hsa_end - (unsigned long) src);
+			rc = memcpy_hsa(dest, (unsigned long) src, copied, 0);
+			if (rc)
+				return rc;
+		}
 	}
-	return memcpy_real(dest + copied, src + copied, count - copied);
+	return copy_from_realmem(dest + copied, src + copied, count - copied);
 }
 
 /*
@@ -80,19 +283,6 @@ static void *kzalloc_panic(int len)
 }
 
 /*
- * Get memory layout and create hole for oldmem
- */
-static struct mem_chunk *get_memory_layout(void)
-{
-	struct mem_chunk *chunk_array;
-
-	chunk_array = kzalloc_panic(MEMORY_CHUNKS * sizeof(struct mem_chunk));
-	detect_memory_layout(chunk_array);
-	create_mem_hole(chunk_array, OLDMEM_BASE, OLDMEM_SIZE, CHUNK_CRASHK);
-	return chunk_array;
-}
-
-/*
  * Initialize ELF note
  */
 static void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len,
@@ -225,28 +415,44 @@ static void *nt_prpsinfo(void *ptr)
 }
 
 /*
- * Initialize vmcoreinfo note (new kernel)
+ * Get vmcoreinfo using lowcore->vmcore_info (new kernel)
  */
-static void *nt_vmcoreinfo(void *ptr)
+static void *get_vmcoreinfo_old(unsigned long *size)
 {
 	char nt_name[11], *vmcoreinfo;
 	Elf64_Nhdr note;
 	void *addr;
 
 	if (copy_from_oldmem(&addr, &S390_lowcore.vmcore_info, sizeof(addr)))
-		return ptr;
+		return NULL;
 	memset(nt_name, 0, sizeof(nt_name));
 	if (copy_from_oldmem(&note, addr, sizeof(note)))
-		return ptr;
+		return NULL;
 	if (copy_from_oldmem(nt_name, addr + sizeof(note), sizeof(nt_name) - 1))
-		return ptr;
+		return NULL;
 	if (strcmp(nt_name, "VMCOREINFO") != 0)
-		return ptr;
-	vmcoreinfo = kzalloc_panic(note.n_descsz + 1);
+		return NULL;
+	vmcoreinfo = kzalloc_panic(note.n_descsz);
 	if (copy_from_oldmem(vmcoreinfo, addr + 24, note.n_descsz))
+		return NULL;
+	*size = note.n_descsz;
+	return vmcoreinfo;
+}
+
+/*
+ * Initialize vmcoreinfo note (new kernel)
+ */
+static void *nt_vmcoreinfo(void *ptr)
+{
+	unsigned long size;
+	void *vmcoreinfo;
+
+	vmcoreinfo = os_info_old_entry(OS_INFO_VMCOREINFO, &size);
+	if (!vmcoreinfo)
+		vmcoreinfo = get_vmcoreinfo_old(&size);
+	if (!vmcoreinfo)
 		return ptr;
-	vmcoreinfo[note.n_descsz + 1] = 0;
-	return nt_init(ptr, 0, vmcoreinfo, note.n_descsz, "VMCOREINFO");
+	return nt_init(ptr, 0, vmcoreinfo, size, "VMCOREINFO");
 }
 
 /*
@@ -277,8 +483,8 @@ static int get_cpu_cnt(void)
 {
 	int i, cpus = 0;
 
-	for (i = 0; zfcpdump_save_areas[i]; i++) {
-		if (zfcpdump_save_areas[i]->pref_reg == 0)
+	for (i = 0; i < dump_save_areas.count; i++) {
+		if (dump_save_areas.areas[i]->pref_reg == 0)
 			continue;
 		cpus++;
 	}
@@ -290,60 +496,33 @@ static int get_cpu_cnt(void)
  */
 static int get_mem_chunk_cnt(void)
 {
-	struct mem_chunk *chunk_array, *mem_chunk;
-	int i, cnt = 0;
+	int cnt = 0;
+	u64 idx;
 
-	chunk_array = get_memory_layout();
-	for (i = 0; i < MEMORY_CHUNKS; i++) {
-		mem_chunk = &chunk_array[i];
-		if (chunk_array[i].type != CHUNK_READ_WRITE &&
-		    chunk_array[i].type != CHUNK_READ_ONLY)
-			continue;
-		if (mem_chunk->size == 0)
-			continue;
+	for_each_dump_mem_range(idx, NUMA_NO_NODE, NULL, NULL, NULL)
 		cnt++;
-	}
-	kfree(chunk_array);
 	return cnt;
 }
 
 /*
- * Relocate pointer in order to allow vmcore code access the data
- */
-static inline unsigned long relocate(unsigned long addr)
-{
-	return OLDMEM_BASE + addr;
-}
-
-/*
  * Initialize ELF loads (new kernel)
  */
-static int loads_init(Elf64_Phdr *phdr, u64 loads_offset)
+static void loads_init(Elf64_Phdr *phdr, u64 loads_offset)
 {
-	struct mem_chunk *chunk_array, *mem_chunk;
-	int i;
+	phys_addr_t start, end;
+	u64 idx;
 
-	chunk_array = get_memory_layout();
-	for (i = 0; i < MEMORY_CHUNKS; i++) {
-		mem_chunk = &chunk_array[i];
-		if (mem_chunk->size == 0)
-			break;
-		if (chunk_array[i].type != CHUNK_READ_WRITE &&
-		    chunk_array[i].type != CHUNK_READ_ONLY)
-			continue;
-		else
-			phdr->p_filesz = mem_chunk->size;
+	for_each_dump_mem_range(idx, NUMA_NO_NODE, &start, &end, NULL) {
+		phdr->p_filesz = end - start;
 		phdr->p_type = PT_LOAD;
-		phdr->p_offset = mem_chunk->addr;
-		phdr->p_vaddr = mem_chunk->addr;
-		phdr->p_paddr = mem_chunk->addr;
-		phdr->p_memsz = mem_chunk->size;
+		phdr->p_offset = start;
+		phdr->p_vaddr = start;
+		phdr->p_paddr = start;
+		phdr->p_memsz = end - start;
 		phdr->p_flags = PF_R | PF_W | PF_X;
 		phdr->p_align = PAGE_SIZE;
 		phdr++;
 	}
-	kfree(chunk_array);
-	return i;
 }
 
 /*
@@ -357,8 +536,8 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset)
 
 	ptr = nt_prpsinfo(ptr);
 
-	for (i = 0; zfcpdump_save_areas[i]; i++) {
-		sa = zfcpdump_save_areas[i];
+	for (i = 0; i < dump_save_areas.count; i++) {
+		sa = dump_save_areas.areas[i];
 		if (sa->pref_reg == 0)
 			continue;
 		ptr = fill_cpu_elf_notes(ptr, sa);
@@ -366,7 +545,7 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset)
 	ptr = nt_vmcoreinfo(ptr);
 	memset(phdr, 0, sizeof(*phdr));
 	phdr->p_type = PT_NOTE;
-	phdr->p_offset = relocate(notes_offset);
+	phdr->p_offset = notes_offset;
 	phdr->p_filesz = (unsigned long) PTR_SUB(ptr, ptr_start);
 	phdr->p_memsz = phdr->p_filesz;
 	return ptr;
@@ -375,7 +554,7 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset)
 /*
  * Create ELF core header (new kernel)
  */
-static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz)
+int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
 {
 	Elf64_Phdr *phdr_notes, *phdr_loads;
 	int mem_chunk_cnt;
@@ -383,6 +562,23 @@ static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz)
 	u32 alloc_size;
 	u64 hdr_off;
 
+	/* If we are not in kdump or zfcpdump mode return */
+	if (!OLDMEM_BASE && ipl_info.type != IPL_TYPE_FCP_DUMP)
+		return 0;
+	/* If elfcorehdr= has been passed via cmdline, we use that one */
+	if (elfcorehdr_addr != ELFCORE_ADDR_MAX)
+		return 0;
+	/* If we cannot get HSA size for zfcpdump return error */
+	if (ipl_info.type == IPL_TYPE_FCP_DUMP && !sclp_get_hsa_size())
+		return -ENODEV;
+
+	/* For kdump, exclude previous crashkernel memory */
+	if (OLDMEM_BASE) {
+		oldmem_region.base = OLDMEM_BASE;
+		oldmem_region.size = OLDMEM_SIZE;
+		oldmem_type.total_size = OLDMEM_SIZE;
+	}
+
 	mem_chunk_cnt = get_mem_chunk_cnt();
 
 	alloc_size = 0x1000 + get_cpu_cnt() * 0x300 +
@@ -400,27 +596,52 @@ static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz)
 	ptr = notes_init(phdr_notes, ptr, ((unsigned long) hdr) + hdr_off);
 	/* Init loads */
 	hdr_off = PTR_DIFF(ptr, hdr);
-	loads_init(phdr_loads, ((unsigned long) hdr) + hdr_off);
-	*elfcorebuf_sz = hdr_off;
-	*elfcorebuf = (void *) relocate((unsigned long) hdr);
-	BUG_ON(*elfcorebuf_sz > alloc_size);
+	loads_init(phdr_loads, hdr_off);
+	*addr = (unsigned long long) hdr;
+	elfcorehdr_newmem = hdr;
+	*size = (unsigned long long) hdr_off;
+	BUG_ON(elfcorehdr_size > alloc_size);
+	return 0;
 }
 
 /*
- * Create kdump ELF core header in new kernel, if it has not been passed via
- * the "elfcorehdr" kernel parameter
+ * Free ELF core header (new kernel)
  */
-static int setup_kdump_elfcorehdr(void)
+void elfcorehdr_free(unsigned long long addr)
 {
-	size_t elfcorebuf_sz;
-	char *elfcorebuf;
+	if (!elfcorehdr_newmem)
+		return;
+	kfree((void *)(unsigned long)addr);
+}
 
-	if (!OLDMEM_BASE || is_kdump_kernel())
-		return -EINVAL;
-	s390_elf_corehdr_create(&elfcorebuf, &elfcorebuf_sz);
-	elfcorehdr_addr = (unsigned long long) elfcorebuf;
-	elfcorehdr_size = elfcorebuf_sz;
-	return 0;
+/*
+ * Read from ELF header
+ */
+ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos)
+{
+	void *src = (void *)(unsigned long)*ppos;
+
+	src = elfcorehdr_newmem ? src : src - OLDMEM_BASE;
+	memcpy(buf, src, count);
+	*ppos += count;
+	return count;
 }
 
-subsys_initcall(setup_kdump_elfcorehdr);
+/*
+ * Read from ELF notes data
+ */
+ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos)
+{
+	void *src = (void *)(unsigned long)*ppos;
+	int rc;
+
+	if (elfcorehdr_newmem) {
+		memcpy(buf, src, count);
+	} else {
+		rc = copy_from_oldmem(buf, src, count);
+		if (rc)
+			return rc;
+	}
+	*ppos += count;
+	return count;
+}