[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20230612210712.683175-2-eric.devolder@oracle.com>
Date: Mon, 12 Jun 2023 17:07:05 -0400
From: Eric DeVolder <eric.devolder@...cle.com>
To: linux-kernel@...r.kernel.org, david@...hat.com, osalvador@...e.de,
corbet@....net, tglx@...utronix.de, mingo@...hat.com, bp@...en8.de,
dave.hansen@...ux.intel.com, x86@...nel.org, bhe@...hat.com,
ebiederm@...ssion.com, kexec@...ts.infradead.org
Cc: hpa@...or.com, gregkh@...uxfoundation.org, rafael@...nel.org,
vgoyal@...hat.com, dyoung@...hat.com, lf32.dev@...il.com,
akpm@...ux-foundation.org, naveen.n.rao@...ux.vnet.ibm.com,
zohar@...ux.ibm.com, bhelgaas@...gle.com, vbabka@...e.cz,
tiwai@...e.de, seanjc@...gle.com, linux@...ssschuh.net,
vschneid@...hat.com, linux-mm@...ck.org, linux-doc@...r.kernel.org,
sourabhjain@...ux.ibm.com, konrad.wilk@...cle.com,
boris.ostrovsky@...cle.com, eric.devolder@...cle.com
Subject: [PATCH v23 1/8] crash: move a few code bits to setup support of crash hotplug
The crash hotplug support leans on the work for the kexec_file_load()
syscall. To also support the kexec_load() syscall, a few bits of code
need to be move outside of CONFIG_KEXEC_FILE. As such, these bits are
moved out of kexec_file.c and into a common location crash_core.c.
No functionality change intended.
Signed-off-by: Eric DeVolder <eric.devolder@...cle.com>
Reviewed-by: Sourabh Jain <sourabhjain@...ux.ibm.com>
Acked-by: Hari Bathini <hbathini@...ux.ibm.com>
Acked-by: Baoquan He <bhe@...hat.com>
---
include/linux/kexec.h | 30 +++----
kernel/crash_core.c | 182 ++++++++++++++++++++++++++++++++++++++++++
kernel/kexec_file.c | 181 -----------------------------------------
3 files changed, 197 insertions(+), 196 deletions(-)
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 22b5cd24f581..811a90e09698 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -105,6 +105,21 @@ struct compat_kexec_segment {
};
#endif
+/* Alignment required for elf header segment */
+#define ELF_CORE_HEADER_ALIGN 4096
+
+struct crash_mem {
+ unsigned int max_nr_ranges;
+ unsigned int nr_ranges;
+ struct range ranges[];
+};
+
+extern int crash_exclude_mem_range(struct crash_mem *mem,
+ unsigned long long mstart,
+ unsigned long long mend);
+extern int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
+ void **addr, unsigned long *sz);
+
#ifdef CONFIG_KEXEC_FILE
struct purgatory_info {
/*
@@ -230,21 +245,6 @@ static inline int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf)
}
#endif
-/* Alignment required for elf header segment */
-#define ELF_CORE_HEADER_ALIGN 4096
-
-struct crash_mem {
- unsigned int max_nr_ranges;
- unsigned int nr_ranges;
- struct range ranges[];
-};
-
-extern int crash_exclude_mem_range(struct crash_mem *mem,
- unsigned long long mstart,
- unsigned long long mend);
-extern int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
- void **addr, unsigned long *sz);
-
#ifndef arch_kexec_apply_relocations_add
/*
* arch_kexec_apply_relocations_add - apply relocations of type RELA
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 90ce1dfd591c..b7c30b748a16 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -10,6 +10,7 @@
#include <linux/utsname.h>
#include <linux/vmalloc.h>
#include <linux/sizes.h>
+#include <linux/kexec.h>
#include <asm/page.h>
#include <asm/sections.h>
@@ -314,6 +315,187 @@ static int __init parse_crashkernel_dummy(char *arg)
}
early_param("crashkernel", parse_crashkernel_dummy);
+int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
+ void **addr, unsigned long *sz)
+{
+ Elf64_Ehdr *ehdr;
+ Elf64_Phdr *phdr;
+ unsigned long nr_cpus = num_possible_cpus(), nr_phdr, elf_sz;
+ unsigned char *buf;
+ unsigned int cpu, i;
+ unsigned long long notes_addr;
+ unsigned long mstart, mend;
+
+ /* extra phdr for vmcoreinfo ELF note */
+ nr_phdr = nr_cpus + 1;
+ nr_phdr += mem->nr_ranges;
+
+ /*
+ * kexec-tools creates an extra PT_LOAD phdr for kernel text mapping
+ * area (for example, ffffffff80000000 - ffffffffa0000000 on x86_64).
+ * I think this is required by tools like gdb. So same physical
+ * memory will be mapped in two ELF headers. One will contain kernel
+ * text virtual addresses and other will have __va(physical) addresses.
+ */
+
+ nr_phdr++;
+ elf_sz = sizeof(Elf64_Ehdr) + nr_phdr * sizeof(Elf64_Phdr);
+ elf_sz = ALIGN(elf_sz, ELF_CORE_HEADER_ALIGN);
+
+ buf = vzalloc(elf_sz);
+ if (!buf)
+ return -ENOMEM;
+
+ ehdr = (Elf64_Ehdr *)buf;
+ phdr = (Elf64_Phdr *)(ehdr + 1);
+ memcpy(ehdr->e_ident, ELFMAG, SELFMAG);
+ ehdr->e_ident[EI_CLASS] = ELFCLASS64;
+ ehdr->e_ident[EI_DATA] = ELFDATA2LSB;
+ ehdr->e_ident[EI_VERSION] = EV_CURRENT;
+ ehdr->e_ident[EI_OSABI] = ELF_OSABI;
+ memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD);
+ ehdr->e_type = ET_CORE;
+ ehdr->e_machine = ELF_ARCH;
+ ehdr->e_version = EV_CURRENT;
+ ehdr->e_phoff = sizeof(Elf64_Ehdr);
+ ehdr->e_ehsize = sizeof(Elf64_Ehdr);
+ ehdr->e_phentsize = sizeof(Elf64_Phdr);
+
+ /* Prepare one phdr of type PT_NOTE for each present CPU */
+ for_each_present_cpu(cpu) {
+ phdr->p_type = PT_NOTE;
+ notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu));
+ phdr->p_offset = phdr->p_paddr = notes_addr;
+ phdr->p_filesz = phdr->p_memsz = sizeof(note_buf_t);
+ (ehdr->e_phnum)++;
+ phdr++;
+ }
+
+ /* Prepare one PT_NOTE header for vmcoreinfo */
+ phdr->p_type = PT_NOTE;
+ phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
+ phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE;
+ (ehdr->e_phnum)++;
+ phdr++;
+
+ /* Prepare PT_LOAD type program header for kernel text region */
+ if (need_kernel_map) {
+ phdr->p_type = PT_LOAD;
+ phdr->p_flags = PF_R|PF_W|PF_X;
+ phdr->p_vaddr = (unsigned long) _text;
+ phdr->p_filesz = phdr->p_memsz = _end - _text;
+ phdr->p_offset = phdr->p_paddr = __pa_symbol(_text);
+ ehdr->e_phnum++;
+ phdr++;
+ }
+
+ /* Go through all the ranges in mem->ranges[] and prepare phdr */
+ for (i = 0; i < mem->nr_ranges; i++) {
+ mstart = mem->ranges[i].start;
+ mend = mem->ranges[i].end;
+
+ phdr->p_type = PT_LOAD;
+ phdr->p_flags = PF_R|PF_W|PF_X;
+ phdr->p_offset = mstart;
+
+ phdr->p_paddr = mstart;
+ phdr->p_vaddr = (unsigned long) __va(mstart);
+ phdr->p_filesz = phdr->p_memsz = mend - mstart + 1;
+ phdr->p_align = 0;
+ ehdr->e_phnum++;
+ pr_debug("Crash PT_LOAD ELF header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
+ phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz,
+ ehdr->e_phnum, phdr->p_offset);
+ phdr++;
+ }
+
+ *addr = buf;
+ *sz = elf_sz;
+ return 0;
+}
+
+int crash_exclude_mem_range(struct crash_mem *mem,
+ unsigned long long mstart, unsigned long long mend)
+{
+ int i, j;
+ unsigned long long start, end, p_start, p_end;
+ struct range temp_range = {0, 0};
+
+ for (i = 0; i < mem->nr_ranges; i++) {
+ start = mem->ranges[i].start;
+ end = mem->ranges[i].end;
+ p_start = mstart;
+ p_end = mend;
+
+ if (mstart > end || mend < start)
+ continue;
+
+ /* Truncate any area outside of range */
+ if (mstart < start)
+ p_start = start;
+ if (mend > end)
+ p_end = end;
+
+ /* Found completely overlapping range */
+ if (p_start == start && p_end == end) {
+ mem->ranges[i].start = 0;
+ mem->ranges[i].end = 0;
+ if (i < mem->nr_ranges - 1) {
+ /* Shift rest of the ranges to left */
+ for (j = i; j < mem->nr_ranges - 1; j++) {
+ mem->ranges[j].start =
+ mem->ranges[j+1].start;
+ mem->ranges[j].end =
+ mem->ranges[j+1].end;
+ }
+
+ /*
+ * Continue to check if there are another overlapping ranges
+ * from the current position because of shifting the above
+ * mem ranges.
+ */
+ i--;
+ mem->nr_ranges--;
+ continue;
+ }
+ mem->nr_ranges--;
+ return 0;
+ }
+
+ if (p_start > start && p_end < end) {
+ /* Split original range */
+ mem->ranges[i].end = p_start - 1;
+ temp_range.start = p_end + 1;
+ temp_range.end = end;
+ } else if (p_start != start)
+ mem->ranges[i].end = p_start - 1;
+ else
+ mem->ranges[i].start = p_end + 1;
+ break;
+ }
+
+ /* If a split happened, add the split to array */
+ if (!temp_range.end)
+ return 0;
+
+ /* Split happened */
+ if (i == mem->max_nr_ranges - 1)
+ return -ENOMEM;
+
+ /* Location where new range should go */
+ j = i + 1;
+ if (j < mem->nr_ranges) {
+ /* Move over all ranges one slot towards the end */
+ for (i = mem->nr_ranges - 1; i >= j; i--)
+ mem->ranges[i + 1] = mem->ranges[i];
+ }
+
+ mem->ranges[j].start = temp_range.start;
+ mem->ranges[j].end = temp_range.end;
+ mem->nr_ranges++;
+ return 0;
+}
+
Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
void *data, size_t data_len)
{
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index f989f5f1933b..f8b1797b3ec9 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -1138,184 +1138,3 @@ int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name,
return 0;
}
#endif /* CONFIG_ARCH_HAS_KEXEC_PURGATORY */
-
-int crash_exclude_mem_range(struct crash_mem *mem,
- unsigned long long mstart, unsigned long long mend)
-{
- int i, j;
- unsigned long long start, end, p_start, p_end;
- struct range temp_range = {0, 0};
-
- for (i = 0; i < mem->nr_ranges; i++) {
- start = mem->ranges[i].start;
- end = mem->ranges[i].end;
- p_start = mstart;
- p_end = mend;
-
- if (mstart > end || mend < start)
- continue;
-
- /* Truncate any area outside of range */
- if (mstart < start)
- p_start = start;
- if (mend > end)
- p_end = end;
-
- /* Found completely overlapping range */
- if (p_start == start && p_end == end) {
- mem->ranges[i].start = 0;
- mem->ranges[i].end = 0;
- if (i < mem->nr_ranges - 1) {
- /* Shift rest of the ranges to left */
- for (j = i; j < mem->nr_ranges - 1; j++) {
- mem->ranges[j].start =
- mem->ranges[j+1].start;
- mem->ranges[j].end =
- mem->ranges[j+1].end;
- }
-
- /*
- * Continue to check if there are another overlapping ranges
- * from the current position because of shifting the above
- * mem ranges.
- */
- i--;
- mem->nr_ranges--;
- continue;
- }
- mem->nr_ranges--;
- return 0;
- }
-
- if (p_start > start && p_end < end) {
- /* Split original range */
- mem->ranges[i].end = p_start - 1;
- temp_range.start = p_end + 1;
- temp_range.end = end;
- } else if (p_start != start)
- mem->ranges[i].end = p_start - 1;
- else
- mem->ranges[i].start = p_end + 1;
- break;
- }
-
- /* If a split happened, add the split to array */
- if (!temp_range.end)
- return 0;
-
- /* Split happened */
- if (i == mem->max_nr_ranges - 1)
- return -ENOMEM;
-
- /* Location where new range should go */
- j = i + 1;
- if (j < mem->nr_ranges) {
- /* Move over all ranges one slot towards the end */
- for (i = mem->nr_ranges - 1; i >= j; i--)
- mem->ranges[i + 1] = mem->ranges[i];
- }
-
- mem->ranges[j].start = temp_range.start;
- mem->ranges[j].end = temp_range.end;
- mem->nr_ranges++;
- return 0;
-}
-
-int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
- void **addr, unsigned long *sz)
-{
- Elf64_Ehdr *ehdr;
- Elf64_Phdr *phdr;
- unsigned long nr_cpus = num_possible_cpus(), nr_phdr, elf_sz;
- unsigned char *buf;
- unsigned int cpu, i;
- unsigned long long notes_addr;
- unsigned long mstart, mend;
-
- /* extra phdr for vmcoreinfo ELF note */
- nr_phdr = nr_cpus + 1;
- nr_phdr += mem->nr_ranges;
-
- /*
- * kexec-tools creates an extra PT_LOAD phdr for kernel text mapping
- * area (for example, ffffffff80000000 - ffffffffa0000000 on x86_64).
- * I think this is required by tools like gdb. So same physical
- * memory will be mapped in two ELF headers. One will contain kernel
- * text virtual addresses and other will have __va(physical) addresses.
- */
-
- nr_phdr++;
- elf_sz = sizeof(Elf64_Ehdr) + nr_phdr * sizeof(Elf64_Phdr);
- elf_sz = ALIGN(elf_sz, ELF_CORE_HEADER_ALIGN);
-
- buf = vzalloc(elf_sz);
- if (!buf)
- return -ENOMEM;
-
- ehdr = (Elf64_Ehdr *)buf;
- phdr = (Elf64_Phdr *)(ehdr + 1);
- memcpy(ehdr->e_ident, ELFMAG, SELFMAG);
- ehdr->e_ident[EI_CLASS] = ELFCLASS64;
- ehdr->e_ident[EI_DATA] = ELFDATA2LSB;
- ehdr->e_ident[EI_VERSION] = EV_CURRENT;
- ehdr->e_ident[EI_OSABI] = ELF_OSABI;
- memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD);
- ehdr->e_type = ET_CORE;
- ehdr->e_machine = ELF_ARCH;
- ehdr->e_version = EV_CURRENT;
- ehdr->e_phoff = sizeof(Elf64_Ehdr);
- ehdr->e_ehsize = sizeof(Elf64_Ehdr);
- ehdr->e_phentsize = sizeof(Elf64_Phdr);
-
- /* Prepare one phdr of type PT_NOTE for each present CPU */
- for_each_present_cpu(cpu) {
- phdr->p_type = PT_NOTE;
- notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu));
- phdr->p_offset = phdr->p_paddr = notes_addr;
- phdr->p_filesz = phdr->p_memsz = sizeof(note_buf_t);
- (ehdr->e_phnum)++;
- phdr++;
- }
-
- /* Prepare one PT_NOTE header for vmcoreinfo */
- phdr->p_type = PT_NOTE;
- phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
- phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE;
- (ehdr->e_phnum)++;
- phdr++;
-
- /* Prepare PT_LOAD type program header for kernel text region */
- if (need_kernel_map) {
- phdr->p_type = PT_LOAD;
- phdr->p_flags = PF_R|PF_W|PF_X;
- phdr->p_vaddr = (unsigned long) _text;
- phdr->p_filesz = phdr->p_memsz = _end - _text;
- phdr->p_offset = phdr->p_paddr = __pa_symbol(_text);
- ehdr->e_phnum++;
- phdr++;
- }
-
- /* Go through all the ranges in mem->ranges[] and prepare phdr */
- for (i = 0; i < mem->nr_ranges; i++) {
- mstart = mem->ranges[i].start;
- mend = mem->ranges[i].end;
-
- phdr->p_type = PT_LOAD;
- phdr->p_flags = PF_R|PF_W|PF_X;
- phdr->p_offset = mstart;
-
- phdr->p_paddr = mstart;
- phdr->p_vaddr = (unsigned long) __va(mstart);
- phdr->p_filesz = phdr->p_memsz = mend - mstart + 1;
- phdr->p_align = 0;
- ehdr->e_phnum++;
- pr_debug("Crash PT_LOAD ELF header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
- phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz,
- ehdr->e_phnum, phdr->p_offset);
- phdr++;
- }
-
- *addr = buf;
- *sz = elf_sz;
- return 0;
-}
--
2.31.1
Powered by blists - more mailing lists