The patch titled Subject: vmcore: reference e_phoff member explicitly to get position of program header table has been added to the -mm tree. Its filename is vmcore-reference-e_phoff-member-explicitly-to-get-position-of-program-header-table.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: HATAYAMA Daisuke <d.hatayama@xxxxxxxxxxxxxx> Subject: vmcore: reference e_phoff member explicitly to get position of program header table Currently, read to /proc/vmcore is done by read_oldmem() that uses ioremap/iounmap per a single page. For example, if memory is 1GB, ioremap/iounmap is called (1GB / 4KB)-times, that is, 262144 times. This causes big performance degradation. In particular, the current main user of this mmap() is makedumpfile, which not only reads memory from /proc/vmcore but also does other processing like filtering, compression and IO work. Update of page table and the following TLB flush makes such processing much slow; though I have yet to make patch for makedumpfile and yet to confirm how it's improved. To address the issue, this patch implements mmap() on /proc/vmcore to improve read performance. My simple benchmark shows the improvement from 200 [MiB/sec] to over 50.0 [GiB/sec]. This patch: Currently, the code assumes that position of program header table is next to ELF header. But future change can break the assumption on kexec-tools and the 1st kernel. To avoid worst case, reference e_phoff member explicitly to get position of program header table in file-offset. Signed-off-by: Zhang Yanfei <zhangyanfei@xxxxxxxxxxxxxx> Signed-off-by: HATAYAMA Daisuke <d.hatayama@xxxxxxxxxxxxxx> Cc: Vivek Goyal <vgoyal@xxxxxxxxxx> Cc: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- fs/proc/vmcore.c | 56 ++++++++++++++++++++++++++++----------------- 1 file changed, 36 insertions(+), 20 deletions(-) diff -puN fs/proc/vmcore.c~vmcore-reference-e_phoff-member-explicitly-to-get-position-of-program-header-table fs/proc/vmcore.c --- a/fs/proc/vmcore.c~vmcore-reference-e_phoff-member-explicitly-to-get-position-of-program-header-table +++ a/fs/proc/vmcore.c @@ -221,8 +221,8 @@ static u64 __init get_vmcore_size_elf64( Elf64_Phdr *phdr_ptr; ehdr_ptr = (Elf64_Ehdr *)elfptr; - phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); - size = sizeof(Elf64_Ehdr) + ((ehdr_ptr->e_phnum) * sizeof(Elf64_Phdr)); + phdr_ptr = (Elf64_Phdr*)(elfptr + ehdr_ptr->e_phoff); + size = ehdr_ptr->e_phoff + ((ehdr_ptr->e_phnum) * sizeof(Elf64_Phdr)); for (i = 0; i < ehdr_ptr->e_phnum; i++) { size += phdr_ptr->p_memsz; phdr_ptr++; @@ -238,8 +238,8 @@ static u64 __init get_vmcore_size_elf32( Elf32_Phdr *phdr_ptr; ehdr_ptr = (Elf32_Ehdr *)elfptr; - phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr)); - size = sizeof(Elf32_Ehdr) + ((ehdr_ptr->e_phnum) * sizeof(Elf32_Phdr)); + phdr_ptr = (Elf32_Phdr*)(elfptr + ehdr_ptr->e_phoff); + size = ehdr_ptr->e_phoff + ((ehdr_ptr->e_phnum) * sizeof(Elf32_Phdr)); for (i = 0; i < ehdr_ptr->e_phnum; i++) { size += phdr_ptr->p_memsz; phdr_ptr++; @@ -259,7 +259,7 @@ static int __init merge_note_headers_elf u64 phdr_sz = 0, note_off; ehdr_ptr = (Elf64_Ehdr *)elfptr; - phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); + phdr_ptr = (Elf64_Phdr*)(elfptr + ehdr_ptr->e_phoff); for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { int j; void *notes_section; @@ -305,7 +305,7 @@ static int __init merge_note_headers_elf /* Prepare merged PT_NOTE program header. */ phdr.p_type = PT_NOTE; phdr.p_flags = 0; - note_off = sizeof(Elf64_Ehdr) + + note_off = ehdr_ptr->e_phoff + (ehdr_ptr->e_phnum - nr_ptnote +1) * sizeof(Elf64_Phdr); phdr.p_offset = note_off; phdr.p_vaddr = phdr.p_paddr = 0; @@ -313,14 +313,14 @@ static int __init merge_note_headers_elf phdr.p_align = 0; /* Add merged PT_NOTE program header*/ - tmp = elfptr + sizeof(Elf64_Ehdr); + tmp = elfptr + ehdr_ptr->e_phoff; memcpy(tmp, &phdr, sizeof(phdr)); tmp += sizeof(phdr); /* Remove unwanted PT_NOTE program headers. */ i = (nr_ptnote - 1) * sizeof(Elf64_Phdr); *elfsz = *elfsz - i; - memmove(tmp, tmp+i, ((*elfsz)-sizeof(Elf64_Ehdr)-sizeof(Elf64_Phdr))); + memmove(tmp, tmp+i, ((*elfsz)-ehdr_ptr->e_phoff-sizeof(Elf64_Phdr))); /* Modify e_phnum to reflect merged headers. */ ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1; @@ -340,7 +340,7 @@ static int __init merge_note_headers_elf u64 phdr_sz = 0, note_off; ehdr_ptr = (Elf32_Ehdr *)elfptr; - phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr)); + phdr_ptr = (Elf32_Phdr*)(elfptr + ehdr_ptr->e_phoff); for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) { int j; void *notes_section; @@ -386,7 +386,7 @@ static int __init merge_note_headers_elf /* Prepare merged PT_NOTE program header. */ phdr.p_type = PT_NOTE; phdr.p_flags = 0; - note_off = sizeof(Elf32_Ehdr) + + note_off = ehdr_ptr->e_phoff + (ehdr_ptr->e_phnum - nr_ptnote +1) * sizeof(Elf32_Phdr); phdr.p_offset = note_off; phdr.p_vaddr = phdr.p_paddr = 0; @@ -394,14 +394,14 @@ static int __init merge_note_headers_elf phdr.p_align = 0; /* Add merged PT_NOTE program header*/ - tmp = elfptr + sizeof(Elf32_Ehdr); + tmp = elfptr + ehdr_ptr->e_phoff; memcpy(tmp, &phdr, sizeof(phdr)); tmp += sizeof(phdr); /* Remove unwanted PT_NOTE program headers. */ i = (nr_ptnote - 1) * sizeof(Elf32_Phdr); *elfsz = *elfsz - i; - memmove(tmp, tmp+i, ((*elfsz)-sizeof(Elf32_Ehdr)-sizeof(Elf32_Phdr))); + memmove(tmp, tmp+i, ((*elfsz)-ehdr_ptr->e_phoff-sizeof(Elf32_Phdr))); /* Modify e_phnum to reflect merged headers. */ ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1; @@ -422,10 +422,10 @@ static int __init process_ptload_program struct vmcore *new; ehdr_ptr = (Elf64_Ehdr *)elfptr; - phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); /* PT_NOTE hdr */ + phdr_ptr = (Elf64_Phdr*)(elfptr + ehdr_ptr->e_phoff); /* PT_NOTE hdr */ /* First program header is PT_NOTE header. */ - vmcore_off = sizeof(Elf64_Ehdr) + + vmcore_off = ehdr_ptr->e_phoff + (ehdr_ptr->e_phnum) * sizeof(Elf64_Phdr) + phdr_ptr->p_memsz; /* Note sections */ @@ -459,10 +459,10 @@ static int __init process_ptload_program struct vmcore *new; ehdr_ptr = (Elf32_Ehdr *)elfptr; - phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr)); /* PT_NOTE hdr */ + phdr_ptr = (Elf32_Phdr*)(elfptr + ehdr_ptr->e_phoff); /* PT_NOTE hdr */ /* First program header is PT_NOTE header. */ - vmcore_off = sizeof(Elf32_Ehdr) + + vmcore_off = ehdr_ptr->e_phoff + (ehdr_ptr->e_phnum) * sizeof(Elf32_Phdr) + phdr_ptr->p_memsz; /* Note sections */ @@ -496,7 +496,7 @@ static void __init set_vmcore_list_offse ehdr_ptr = (Elf64_Ehdr *)elfptr; /* Skip Elf header and program headers. */ - vmcore_off = sizeof(Elf64_Ehdr) + + vmcore_off = ehdr_ptr->e_phoff + (ehdr_ptr->e_phnum) * sizeof(Elf64_Phdr); list_for_each_entry(m, vc_list, list) { @@ -516,7 +516,7 @@ static void __init set_vmcore_list_offse ehdr_ptr = (Elf32_Ehdr *)elfptr; /* Skip Elf header and program headers. */ - vmcore_off = sizeof(Elf32_Ehdr) + + vmcore_off = ehdr_ptr->e_phoff + (ehdr_ptr->e_phnum) * sizeof(Elf32_Phdr); list_for_each_entry(m, vc_list, list) { @@ -558,11 +558,19 @@ static int __init parse_crash_elf64_head if (!elfcorebuf) return -ENOMEM; addr = elfcorehdr_addr; - rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz, &addr, 0); + rc = read_from_oldmem(elfcorebuf, sizeof(Elf64_Ehdr), &addr, 0); if (rc < 0) { kfree(elfcorebuf); return rc; } + addr = elfcorehdr_addr + ehdr.e_phoff; + rc = read_from_oldmem(elfcorebuf + sizeof(Elf64_Ehdr), + ehdr.e_phnum * sizeof(Elf64_Phdr), &addr, 0); + if (rc < 0) { + kfree(elfcorebuf); + return rc; + } + ((Elf64_Ehdr *)elfcorebuf)->e_phoff = sizeof(Elf64_Ehdr); /* Merge all PT_NOTE headers into one. */ rc = merge_note_headers_elf64(elfcorebuf, &elfcorebuf_sz, &vmcore_list); @@ -613,11 +621,19 @@ static int __init parse_crash_elf32_head if (!elfcorebuf) return -ENOMEM; addr = elfcorehdr_addr; - rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz, &addr, 0); + rc = read_from_oldmem(elfcorebuf, sizeof(Elf32_Ehdr), &addr, 0); + if (rc < 0) { + kfree(elfcorebuf); + return rc; + } + addr = elfcorehdr_addr + ehdr.e_phoff; + rc = read_from_oldmem(elfcorebuf + sizeof(Elf32_Ehdr), + ehdr.e_phnum * sizeof(Elf32_Phdr), &addr, 0); if (rc < 0) { kfree(elfcorebuf); return rc; } + ((Elf32_Ehdr *)elfcorebuf)->e_phoff = sizeof(Elf32_Ehdr); /* Merge all PT_NOTE headers into one. */ rc = merge_note_headers_elf32(elfcorebuf, &elfcorebuf_sz, &vmcore_list); _ Patches currently in -mm which might be from d.hatayama@xxxxxxxxxxxxxx are vmcore-reference-e_phoff-member-explicitly-to-get-position-of-program-header-table.patch vmcore-clean-up-by-removing-unnecessary-variable.patch vmcore-rearrange-program-headers-without-assuming-consequtive-pt_note-entries.patch vmcore-sysfs-export-elf-note-segment-size-instead-of-vmcoreinfo-data-size.patch vmcore-allocate-buffer-for-elf-headers-on-page-size-alignment.patch vmcore-round-up-buffer-size-of-elf-headers-by-page_size.patch vmcore-procfs-introduce-a-flag-to-distinguish-objects-copied-in-2nd-kernel.patch vmcore-copy-non-page-size-aligned-head-and-tail-pages-in-2nd-kernel.patch vmcore-modify-vmcore-clean-up-function-to-free-buffer-on-2nd-kernel.patch vmcore-clean-up-read_vmcore.patch vmcore-read-buffers-for-vmcore-objects-copied-from-old-memory.patch vmcore-allocate-per-cpu-crash_notes-objects-on-page-size-boundary.patch kexec-allocate-vmcoreinfo-note-buffer-on-page-size-boundary.patch kexec-elf-introduce-nt_vmcore_debuginfo-note-type.patch elf-introduce-nt_vmcore_pad-type.patch kexec-fill-note-buffers-by-nt_vmcore_pad-notes-in-page-size-boundary.patch vmcore-check-nt_vmcore_pad-as-a-mark-indicating-the-end-of-elf-note-buffer.patch vmcore-check-if-vmcore-objects-satify-mmaps-page-size-boundary-requirement.patch vmcore-round-up-offset-of-vmcore-object-in-page-size-boundary.patch vmcore-count-holes-generated-by-round-up-operation-for-vmcore-size.patch vmcore-introduce-mmap_vmcore.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html