At the outcome of this patch set, the crash_prepare_elf64_headers()
is utilized on both the kexec_file_load() and kexec_load() paths. As
such, need to move this function out of kexec_file.c and into a
common location crash_core.c.

No functionality change.

Signed-off-by: Eric DeVolder <eric.devolder@oracle.com>
Acked-by: Baoquan He <bhe@redhat.com>
---
 kernel/crash_core.c | 100 ++++++++++++++++++++++++++++++++++++++++++++
 kernel/kexec_file.c |  99 -------------------------------------------
 2 files changed, 100 insertions(+), 99 deletions(-)

diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index a0eb4d5cf557..46c160d14045 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 +315,105 @@ 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;
+}
+
 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 45637511e0de..f98d1742872b 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -1217,102 +1217,3 @@ int crash_exclude_mem_range(struct crash_mem *mem,
 	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

On 09/12/22 21:06, Eric DeVolder wrote:
> At the outcome of this patch set, the crash_prepare_elf64_headers()
> is utilized on both the kexec_file_load() and kexec_load() paths. As
> such, need to move this function out of kexec_file.c and into a
> common location crash_core.c.
>
> No functionality change.
>
> Signed-off-by: Eric DeVolder <eric.devolder@oracle.com>
> Acked-by: Baoquan He <bhe@redhat.com>
> ---
>   kernel/crash_core.c | 100 ++++++++++++++++++++++++++++++++++++++++++++
>   kernel/kexec_file.c |  99 -------------------------------------------
>   2 files changed, 100 insertions(+), 99 deletions(-)
>
> diff --git a/kernel/crash_core.c b/kernel/crash_core.c
> index a0eb4d5cf557..46c160d14045 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 +315,105 @@ 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);
Seems like above function is out of CONFIG_KEXEC_FILE but some of the
structure/attributes like crash_mem and ELF_CORE_HEADER_ALIGN are
still defined under CONFIG_KEXEC_FILE (look for include/linux/kexec.h).

This leads to kernel build issue when CONFIG_KEXEC_FILE is disabled.

Thanks,
Sourabh Jain

On 1/8/23 23:05, Sourabh Jain wrote:
> 
> On 09/12/22 21:06, Eric DeVolder wrote:
>> At the outcome of this patch set, the crash_prepare_elf64_headers()
>> is utilized on both the kexec_file_load() and kexec_load() paths. As
>> such, need to move this function out of kexec_file.c and into a
>> common location crash_core.c.
>>
>> No functionality change.
>>
>> Signed-off-by: Eric DeVolder <eric.devolder@oracle.com>
>> Acked-by: Baoquan He <bhe@redhat.com>
>> ---
>>   kernel/crash_core.c | 100 ++++++++++++++++++++++++++++++++++++++++++++
>>   kernel/kexec_file.c |  99 -------------------------------------------
>>   2 files changed, 100 insertions(+), 99 deletions(-)
>>
>> diff --git a/kernel/crash_core.c b/kernel/crash_core.c
>> index a0eb4d5cf557..46c160d14045 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 +315,105 @@ 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);
> Seems like above function is out of CONFIG_KEXEC_FILE but some of the
> structure/attributes like crash_mem and ELF_CORE_HEADER_ALIGN are
> still defined under CONFIG_KEXEC_FILE (look for include/linux/kexec.h).
> 
> This leads to kernel build issue when CONFIG_KEXEC_FILE is disabled.
> 
> Thanks,
> Sourabh Jain

After looking into this for a bit, to allow hotplug without kexec_file would require quite a bit of 
code movement. Why? Because hotplug is basically built on top of (part of) the infrastructure that 
was needed for kexec_file.

I'd be inclined to suggest that KEXEC_FILE be a required dependency for CRASH_HOTPLUG, ie:

  config CRASH_HOTPLUG
         bool "Update the crash elfcorehdr on system configuration changes"
         default n
-       depends on CRASH_DUMP && (HOTPLUG_CPU || MEMORY_HOTPLUG)
+       depends on CRASH_DUMP && KEXEC_FILE && (HOTPLUG_CPU || MEMORY_HOTPLUG)


If that isn't feasible, then it would appear quite a bit of surgery is needed to properly separate 
out the items hotplug needs from kexec_file.

Thoughts?
eric

On 12/01/23 22:53, Eric DeVolder wrote:
>
>
> On 1/8/23 23:05, Sourabh Jain wrote:
>>
>> On 09/12/22 21:06, Eric DeVolder wrote:
>>> At the outcome of this patch set, the crash_prepare_elf64_headers()
>>> is utilized on both the kexec_file_load() and kexec_load() paths. As
>>> such, need to move this function out of kexec_file.c and into a
>>> common location crash_core.c.
>>>
>>> No functionality change.
>>>
>>> Signed-off-by: Eric DeVolder <eric.devolder@oracle.com>
>>> Acked-by: Baoquan He <bhe@redhat.com>
>>> ---
>>>   kernel/crash_core.c | 100 
>>> ++++++++++++++++++++++++++++++++++++++++++++
>>>   kernel/kexec_file.c |  99 -------------------------------------------
>>>   2 files changed, 100 insertions(+), 99 deletions(-)
>>>
>>> diff --git a/kernel/crash_core.c b/kernel/crash_core.c
>>> index a0eb4d5cf557..46c160d14045 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 +315,105 @@ 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);
>> Seems like above function is out of CONFIG_KEXEC_FILE but some of the
>> structure/attributes like crash_mem and ELF_CORE_HEADER_ALIGN are
>> still defined under CONFIG_KEXEC_FILE (look for include/linux/kexec.h).
>>
>> This leads to kernel build issue when CONFIG_KEXEC_FILE is disabled.
>>
>> Thanks,
>> Sourabh Jain
>
> After looking into this for a bit, to allow hotplug without kexec_file 
> would require quite a bit of code movement. Why? Because hotplug is 
> basically built on top of (part of) the infrastructure that was needed 
> for kexec_file.
>
> I'd be inclined to suggest that KEXEC_FILE be a required dependency 
> for CRASH_HOTPLUG, ie:

Since kexec_load is deprecated I don't see any harm in doing that.

- Sourabh Jain

On 1/12/23 11:23, Eric DeVolder wrote:
> 
> 
> On 1/8/23 23:05, Sourabh Jain wrote:
>>
>> On 09/12/22 21:06, Eric DeVolder wrote:
>>> At the outcome of this patch set, the crash_prepare_elf64_headers()
>>> is utilized on both the kexec_file_load() and kexec_load() paths. As
>>> such, need to move this function out of kexec_file.c and into a
>>> common location crash_core.c.
>>>
>>> No functionality change.
>>>
>>> Signed-off-by: Eric DeVolder <eric.devolder@oracle.com>
>>> Acked-by: Baoquan He <bhe@redhat.com>
>>> ---
>>>   kernel/crash_core.c | 100 ++++++++++++++++++++++++++++++++++++++++++++
>>>   kernel/kexec_file.c |  99 -------------------------------------------
>>>   2 files changed, 100 insertions(+), 99 deletions(-)
>>>
>>> diff --git a/kernel/crash_core.c b/kernel/crash_core.c
>>> index a0eb4d5cf557..46c160d14045 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 +315,105 @@ 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);
>> Seems like above function is out of CONFIG_KEXEC_FILE but some of the
>> structure/attributes like crash_mem and ELF_CORE_HEADER_ALIGN are
>> still defined under CONFIG_KEXEC_FILE (look for include/linux/kexec.h).
>>
>> This leads to kernel build issue when CONFIG_KEXEC_FILE is disabled.
>>
>> Thanks,
>> Sourabh Jain
> 
> After looking into this for a bit, to allow hotplug without kexec_file would require quite a bit of 
> code movement. Why? Because hotplug is basically built on top of (part of) the infrastructure that 
> was needed for kexec_file.
> 
> I'd be inclined to suggest that KEXEC_FILE be a required dependency for CRASH_HOTPLUG, ie:
> 
>   config CRASH_HOTPLUG
>          bool "Update the crash elfcorehdr on system configuration changes"
>          default n
> -       depends on CRASH_DUMP && (HOTPLUG_CPU || MEMORY_HOTPLUG)
> +       depends on CRASH_DUMP && KEXEC_FILE && (HOTPLUG_CPU || MEMORY_HOTPLUG)
> 
> 
> If that isn't feasible, then it would appear quite a bit of surgery is needed to properly separate 
> out the items hotplug needs from kexec_file.
> 
> Thoughts?
> eric

I completed the changes necessary to move code around to allow this to work outside of KEXEC_FILE; 
in the end it wasn't too bad. I'll include these changes in the next version.
eric

Hi Eric,

On Thu, 12 Jan 2023 11:23:18 -0600
Eric DeVolder <eric.devolder@oracle.com> wrote:

>[...]
> After looking into this for a bit, to allow hotplug without kexec_file would require quite a bit of 
> code movement. Why? Because hotplug is basically built on top of (part of) the infrastructure that 
> was needed for kexec_file.
> 
> I'd be inclined to suggest that KEXEC_FILE be a required dependency for CRASH_HOTPLUG, ie:
> 
>   config CRASH_HOTPLUG
>          bool "Update the crash elfcorehdr on system configuration changes"
>          default n
> -       depends on CRASH_DUMP && (HOTPLUG_CPU || MEMORY_HOTPLUG)
> +       depends on CRASH_DUMP && KEXEC_FILE && (HOTPLUG_CPU || MEMORY_HOTPLUG)
> 
> 
> If that isn't feasible, then it would appear quite a bit of surgery is needed to properly separate 
> out the items hotplug needs from kexec_file.
> 
> Thoughts?

I would have thought that CPU hotplug can be handled in the kernel only
if the crash image was loaded by the kernel with kexec_file_load(2).
When the image is loaded with kexec_load(2), then all data structures
are prepared by the user-space utility kexec(8), and the kernel
generally has no idea how to handle them.

In short, I believe that by definition there must be this dependency of
CRASH_HOTPLUG on KEXEC_FILE.

Petr T

On 1/8/23 23:05, Sourabh Jain wrote:
> 
> On 09/12/22 21:06, Eric DeVolder wrote:
>> At the outcome of this patch set, the crash_prepare_elf64_headers()
>> is utilized on both the kexec_file_load() and kexec_load() paths. As
>> such, need to move this function out of kexec_file.c and into a
>> common location crash_core.c.
>>
>> No functionality change.
>>
>> Signed-off-by: Eric DeVolder <eric.devolder@oracle.com>
>> Acked-by: Baoquan He <bhe@redhat.com>
>> ---
>>   kernel/crash_core.c | 100 ++++++++++++++++++++++++++++++++++++++++++++
>>   kernel/kexec_file.c |  99 -------------------------------------------
>>   2 files changed, 100 insertions(+), 99 deletions(-)
>>
>> diff --git a/kernel/crash_core.c b/kernel/crash_core.c
>> index a0eb4d5cf557..46c160d14045 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 +315,105 @@ 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);
> Seems like above function is out of CONFIG_KEXEC_FILE but some of the
> structure/attributes like crash_mem and ELF_CORE_HEADER_ALIGN are
> still defined under CONFIG_KEXEC_FILE (look for include/linux/kexec.h).
> 
> This leads to kernel build issue when CONFIG_KEXEC_FILE is disabled.
> 
> Thanks,
> Sourabh Jain
Thanks Sourabh, I'll look into this further.
eric