Message-Id: <20230814214446.6659-2-eric.devolder@oracle.com>
Date:   Mon, 14 Aug 2023 17:44:39 -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 v28 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.

In addition, struct crash_mem and crash_notes were moved to new
locales so that PROC_KCORE, which sets CRASH_CORE alone, builds
correctly.

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/crash_core.h |  20 ++++
 include/linux/kexec.h      |  15 ---
 kernel/crash_core.c        | 218 +++++++++++++++++++++++++++++++++++++
 kernel/kexec_core.c        |  37 -------
 kernel/kexec_file.c        | 181 ------------------------------
 5 files changed, 238 insertions(+), 233 deletions(-)

diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
index de62a722431e..1e48b1d96404 100644
--- a/include/linux/crash_core.h
+++ b/include/linux/crash_core.h
@@ -28,6 +28,8 @@
 				     VMCOREINFO_BYTES)
 
 typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4];
+/* Per cpu memory for storing cpu states in case of system crash. */
+extern note_buf_t __percpu *crash_notes;
 
 void crash_update_vmcoreinfo_safecopy(void *ptr);
 void crash_save_vmcoreinfo(void);
@@ -84,4 +86,22 @@ int parse_crashkernel_high(char *cmdline, unsigned long long system_ram,
 int parse_crashkernel_low(char *cmdline, unsigned long long system_ram,
 		unsigned long long *crash_size, unsigned long long *crash_base);
 
+/* 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);
+
+struct kimage;
+struct kexec_segment;
+
 #endif /* LINUX_CRASH_CORE_H */
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 22b5cd24f581..fb4350db33ff 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -230,21 +230,6 @@ 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..336083fba623 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>
@@ -18,6 +19,9 @@
 
 #include "kallsyms_internal.h"
 
+/* Per cpu memory for storing cpu states in case of system crash. */
+note_buf_t __percpu *crash_notes;
+
 /* vmcoreinfo stuff */
 unsigned char *vmcoreinfo_data;
 size_t vmcoreinfo_size;
@@ -314,6 +318,187 @@ 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)
 {
@@ -515,3 +700,36 @@ static int __init crash_save_vmcoreinfo_init(void)
 }
 
 subsys_initcall(crash_save_vmcoreinfo_init);
+
+static int __init crash_notes_memory_init(void)
+{
+	/* Allocate memory for saving cpu registers. */
+	size_t size, align;
+
+	/*
+	 * crash_notes could be allocated across 2 vmalloc pages when percpu
+	 * is vmalloc based . vmalloc doesn't guarantee 2 continuous vmalloc
+	 * pages are also on 2 continuous physical pages. In this case the
+	 * 2nd part of crash_notes in 2nd page could be lost since only the
+	 * starting address and size of crash_notes are exported through sysfs.
+	 * Here round up the size of crash_notes to the nearest power of two
+	 * and pass it to __alloc_percpu as align value. This can make sure
+	 * crash_notes is allocated inside one physical page.
+	 */
+	size = sizeof(note_buf_t);
+	align = min(roundup_pow_of_two(sizeof(note_buf_t)), PAGE_SIZE);
+
+	/*
+	 * Break compile if size is bigger than PAGE_SIZE since crash_notes
+	 * definitely will be in 2 pages with that.
+	 */
+	BUILD_BUG_ON(size > PAGE_SIZE);
+
+	crash_notes = __alloc_percpu(size, align);
+	if (!crash_notes) {
+		pr_warn("Memory allocation for saving cpu register states failed\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+subsys_initcall(crash_notes_memory_init);
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index e2f2574d8b74..4ff564bbd8d8 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -49,9 +49,6 @@
 
 atomic_t __kexec_lock = ATOMIC_INIT(0);
 
-/* Per cpu memory for storing cpu states in case of system crash. */
-note_buf_t __percpu *crash_notes;
-
 /* Flag to indicate we are going to kexec a new kernel */
 bool kexec_in_progress = false;
 
@@ -1218,40 +1215,6 @@ void crash_save_cpu(struct pt_regs *regs, int cpu)
 	final_note(buf);
 }
 
-static int __init crash_notes_memory_init(void)
-{
-	/* Allocate memory for saving cpu registers. */
-	size_t size, align;
-
-	/*
-	 * crash_notes could be allocated across 2 vmalloc pages when percpu
-	 * is vmalloc based . vmalloc doesn't guarantee 2 continuous vmalloc
-	 * pages are also on 2 continuous physical pages. In this case the
-	 * 2nd part of crash_notes in 2nd page could be lost since only the
-	 * starting address and size of crash_notes are exported through sysfs.
-	 * Here round up the size of crash_notes to the nearest power of two
-	 * and pass it to __alloc_percpu as align value. This can make sure
-	 * crash_notes is allocated inside one physical page.
-	 */
-	size = sizeof(note_buf_t);
-	align = min(roundup_pow_of_two(sizeof(note_buf_t)), PAGE_SIZE);
-
-	/*
-	 * Break compile if size is bigger than PAGE_SIZE since crash_notes
-	 * definitely will be in 2 pages with that.
-	 */
-	BUILD_BUG_ON(size > PAGE_SIZE);
-
-	crash_notes = __alloc_percpu(size, align);
-	if (!crash_notes) {
-		pr_warn("Memory allocation for saving cpu register states failed\n");
-		return -ENOMEM;
-	}
-	return 0;
-}
-subsys_initcall(crash_notes_memory_init);
-
-
 /*
  * Move into place and start executing a preloaded standalone
  * executable.  If nothing was preloaded return an error.
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index dd115571f8fc..453b7a513540 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -1151,184 +1151,3 @@ int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name,
 	return 0;
 }
 #endif /* CONFIG_ARCH_SUPPORTS_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