linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Omar Sandoval <osandov@osandov.com>
To: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	Andrew Morton <akpm@linux-foundation.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>,
	Eric Biederman <ebiederm@xmission.com>,
	James Morse <james.morse@arm.com>,
	Bhupesh Sharma <bhsharma@redhat.com>,
	kernel-team@fb.com
Subject: [PATCH v3 6/8] proc/kcore: clean up ELF header generation
Date: Wed, 18 Jul 2018 15:58:46 -0700	[thread overview]
Message-ID: <19c92cbad0e11f6103ff3274b2e7a7e51a1eb74b.1531953780.git.osandov@fb.com> (raw)
In-Reply-To: <cover.1531953780.git.osandov@fb.com>

From: Omar Sandoval <osandov@fb.com>

Currently, the ELF file header, program headers, and note segment are
allocated all at once, in some icky code dating back to 2.3. Programs
tend to read the file header, then the program headers, then the note
segment, all separately, so this is a waste of effort. It's cleaner and
more efficient to handle the three separately.

Signed-off-by: Omar Sandoval <osandov@fb.com>
---
 fs/proc/kcore.c | 350 +++++++++++++++++++-----------------------------
 1 file changed, 141 insertions(+), 209 deletions(-)

diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index e317ac890871..e2ca58d49938 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -49,15 +49,6 @@ static struct proc_dir_entry *proc_root_kcore;
 #define	kc_offset_to_vaddr(o) ((o) + PAGE_OFFSET)
 #endif
 
-/* An ELF note in memory */
-struct memelfnote
-{
-	const char *name;
-	int type;
-	unsigned int datasz;
-	void *data;
-};
-
 static LIST_HEAD(kclist_head);
 static DECLARE_RWSEM(kclist_lock);
 static int kcore_need_update = 1;
@@ -73,7 +64,8 @@ void __init kclist_add(struct kcore_list *new, void *addr, size_t size,
 	list_add_tail(&new->list, &kclist_head);
 }
 
-static size_t get_kcore_size(int *nphdr, size_t *elf_buflen)
+static size_t get_kcore_size(int *nphdr, size_t *phdrs_len, size_t *notes_len,
+			     size_t *data_offset)
 {
 	size_t try, size;
 	struct kcore_list *m;
@@ -87,15 +79,15 @@ static size_t get_kcore_size(int *nphdr, size_t *elf_buflen)
 			size = try;
 		*nphdr = *nphdr + 1;
 	}
-	*elf_buflen =	sizeof(struct elfhdr) + 
-			(*nphdr + 2)*sizeof(struct elf_phdr) + 
-			3 * ((sizeof(struct elf_note)) +
-			     roundup(sizeof(CORE_STR), 4)) +
-			roundup(sizeof(struct elf_prstatus), 4) +
-			roundup(sizeof(struct elf_prpsinfo), 4) +
-			roundup(arch_task_struct_size, 4);
-	*elf_buflen = PAGE_ALIGN(*elf_buflen);
-	return size + *elf_buflen;
+
+	*phdrs_len = *nphdr * sizeof(struct elf_phdr);
+	*notes_len = (3 * (sizeof(struct elf_note) + ALIGN(sizeof(CORE_STR), 4)) +
+		      ALIGN(sizeof(struct elf_prstatus), 4) +
+		      ALIGN(sizeof(struct elf_prpsinfo), 4) +
+		      ALIGN(arch_task_struct_size, 4));
+	*data_offset = PAGE_ALIGN(sizeof(struct elfhdr) + *phdrs_len +
+				  *notes_len);
+	return *data_offset + size;
 }
 
 #ifdef CONFIG_HIGHMEM
@@ -241,7 +233,7 @@ static int kcore_update_ram(void)
 	LIST_HEAD(list);
 	LIST_HEAD(garbage);
 	int nphdr;
-	size_t size;
+	size_t phdrs_len, notes_len, data_offset;
 	struct kcore_list *tmp, *pos;
 	int ret = 0;
 
@@ -263,7 +255,8 @@ static int kcore_update_ram(void)
 	}
 	list_splice_tail(&list, &kclist_head);
 
-	proc_root_kcore->size = get_kcore_size(&nphdr, &size);
+	proc_root_kcore->size = get_kcore_size(&nphdr, &phdrs_len, &notes_len,
+					       &data_offset);
 
 out:
 	up_write(&kclist_lock);
@@ -274,228 +267,168 @@ static int kcore_update_ram(void)
 	return ret;
 }
 
-/*****************************************************************************/
-/*
- * determine size of ELF note
- */
-static int notesize(struct memelfnote *en)
+static void append_kcore_note(char *notes, size_t *i, const char *name,
+			      unsigned int type, const void *desc,
+			      size_t descsz)
 {
-	int sz;
-
-	sz = sizeof(struct elf_note);
-	sz += roundup((strlen(en->name) + 1), 4);
-	sz += roundup(en->datasz, 4);
-
-	return sz;
-} /* end notesize() */
-
-/*****************************************************************************/
-/*
- * store a note in the header buffer
- */
-static char *storenote(struct memelfnote *men, char *bufp)
-{
-	struct elf_note en;
-
-#define DUMP_WRITE(addr,nr) do { memcpy(bufp,addr,nr); bufp += nr; } while(0)
-
-	en.n_namesz = strlen(men->name) + 1;
-	en.n_descsz = men->datasz;
-	en.n_type = men->type;
-
-	DUMP_WRITE(&en, sizeof(en));
-	DUMP_WRITE(men->name, en.n_namesz);
-
-	/* XXX - cast from long long to long to avoid need for libgcc.a */
-	bufp = (char*) roundup((unsigned long)bufp,4);
-	DUMP_WRITE(men->data, men->datasz);
-	bufp = (char*) roundup((unsigned long)bufp,4);
-
-#undef DUMP_WRITE
-
-	return bufp;
-} /* end storenote() */
-
-/*
- * store an ELF coredump header in the supplied buffer
- * nphdr is the number of elf_phdr to insert
- */
-static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff)
-{
-	struct elf_prstatus prstatus;	/* NT_PRSTATUS */
-	struct elf_prpsinfo prpsinfo;	/* NT_PRPSINFO */
-	struct elf_phdr *nhdr, *phdr;
-	struct elfhdr *elf;
-	struct memelfnote notes[3];
-	off_t offset = 0;
-	struct kcore_list *m;
-
-	/* setup ELF header */
-	elf = (struct elfhdr *) bufp;
-	bufp += sizeof(struct elfhdr);
-	offset += sizeof(struct elfhdr);
-	memcpy(elf->e_ident, ELFMAG, SELFMAG);
-	elf->e_ident[EI_CLASS]	= ELF_CLASS;
-	elf->e_ident[EI_DATA]	= ELF_DATA;
-	elf->e_ident[EI_VERSION]= EV_CURRENT;
-	elf->e_ident[EI_OSABI] = ELF_OSABI;
-	memset(elf->e_ident+EI_PAD, 0, EI_NIDENT-EI_PAD);
-	elf->e_type	= ET_CORE;
-	elf->e_machine	= ELF_ARCH;
-	elf->e_version	= EV_CURRENT;
-	elf->e_entry	= 0;
-	elf->e_phoff	= sizeof(struct elfhdr);
-	elf->e_shoff	= 0;
-	elf->e_flags	= ELF_CORE_EFLAGS;
-	elf->e_ehsize	= sizeof(struct elfhdr);
-	elf->e_phentsize= sizeof(struct elf_phdr);
-	elf->e_phnum	= nphdr;
-	elf->e_shentsize= 0;
-	elf->e_shnum	= 0;
-	elf->e_shstrndx	= 0;
-
-	/* setup ELF PT_NOTE program header */
-	nhdr = (struct elf_phdr *) bufp;
-	bufp += sizeof(struct elf_phdr);
-	offset += sizeof(struct elf_phdr);
-	nhdr->p_type	= PT_NOTE;
-	nhdr->p_offset	= 0;
-	nhdr->p_vaddr	= 0;
-	nhdr->p_paddr	= 0;
-	nhdr->p_filesz	= 0;
-	nhdr->p_memsz	= 0;
-	nhdr->p_flags	= 0;
-	nhdr->p_align	= 0;
-
-	/* setup ELF PT_LOAD program header for every area */
-	list_for_each_entry(m, &kclist_head, list) {
-		phdr = (struct elf_phdr *) bufp;
-		bufp += sizeof(struct elf_phdr);
-		offset += sizeof(struct elf_phdr);
-
-		phdr->p_type	= PT_LOAD;
-		phdr->p_flags	= PF_R|PF_W|PF_X;
-		phdr->p_offset	= kc_vaddr_to_offset(m->addr) + dataoff;
-		phdr->p_vaddr	= (size_t)m->addr;
-		if (m->type == KCORE_RAM)
-			phdr->p_paddr	= __pa(m->addr);
-		else if (m->type == KCORE_TEXT)
-			phdr->p_paddr	= __pa_symbol(m->addr);
-		else
-			phdr->p_paddr	= (elf_addr_t)-1;
-		phdr->p_filesz	= phdr->p_memsz	= m->size;
-		phdr->p_align	= PAGE_SIZE;
-	}
-
-	/*
-	 * Set up the notes in similar form to SVR4 core dumps made
-	 * with info from their /proc.
-	 */
-	nhdr->p_offset	= offset;
-
-	/* set up the process status */
-	notes[0].name = CORE_STR;
-	notes[0].type = NT_PRSTATUS;
-	notes[0].datasz = sizeof(struct elf_prstatus);
-	notes[0].data = &prstatus;
-
-	memset(&prstatus, 0, sizeof(struct elf_prstatus));
-
-	nhdr->p_filesz	= notesize(&notes[0]);
-	bufp = storenote(&notes[0], bufp);
-
-	/* set up the process info */
-	notes[1].name	= CORE_STR;
-	notes[1].type	= NT_PRPSINFO;
-	notes[1].datasz	= sizeof(struct elf_prpsinfo);
-	notes[1].data	= &prpsinfo;
-
-	memset(&prpsinfo, 0, sizeof(struct elf_prpsinfo));
-	prpsinfo.pr_state	= 0;
-	prpsinfo.pr_sname	= 'R';
-	prpsinfo.pr_zomb	= 0;
-
-	strcpy(prpsinfo.pr_fname, "vmlinux");
-	strlcpy(prpsinfo.pr_psargs, saved_command_line, sizeof(prpsinfo.pr_psargs));
-
-	nhdr->p_filesz	+= notesize(&notes[1]);
-	bufp = storenote(&notes[1], bufp);
-
-	/* set up the task structure */
-	notes[2].name	= CORE_STR;
-	notes[2].type	= NT_TASKSTRUCT;
-	notes[2].datasz	= arch_task_struct_size;
-	notes[2].data	= current;
-
-	nhdr->p_filesz	+= notesize(&notes[2]);
-	bufp = storenote(&notes[2], bufp);
-
-} /* end elf_kcore_store_hdr() */
+	struct elf_note *note = (struct elf_note *)&notes[*i];
+
+	note->n_namesz = strlen(name) + 1;
+	note->n_descsz = descsz;
+	note->n_type = type;
+	*i += sizeof(*note);
+	memcpy(&notes[*i], name, note->n_namesz);
+	*i = ALIGN(*i + note->n_namesz, 4);
+	memcpy(&notes[*i], desc, descsz);
+	*i = ALIGN(*i + descsz, 4);
+}
 
-/*****************************************************************************/
-/*
- * read from the ELF header and then kernel memory
- */
 static ssize_t
 read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 {
 	char *buf = file->private_data;
-	size_t size, tsz;
-	size_t elf_buflen;
+	size_t phdrs_offset, notes_offset, data_offset;
+	size_t phdrs_len, notes_len;
+	struct kcore_list *m;
+	size_t tsz;
 	int nphdr;
 	unsigned long start;
 	size_t orig_buflen = buflen;
 	int ret = 0;
 
 	down_read(&kclist_lock);
-	size = get_kcore_size(&nphdr, &elf_buflen);
 
-	if (buflen == 0 || *fpos >= size)
-		goto out;
+	get_kcore_size(&nphdr, &phdrs_len, &notes_len, &data_offset);
+	phdrs_offset = sizeof(struct elfhdr);
+	notes_offset = phdrs_offset + phdrs_len;
+
+	/* ELF file header. */
+	if (buflen && *fpos < sizeof(struct elfhdr)) {
+		struct elfhdr ehdr = {
+			.e_ident = {
+				[EI_MAG0] = ELFMAG0,
+				[EI_MAG1] = ELFMAG1,
+				[EI_MAG2] = ELFMAG2,
+				[EI_MAG3] = ELFMAG3,
+				[EI_CLASS] = ELF_CLASS,
+				[EI_DATA] = ELF_DATA,
+				[EI_VERSION] = EV_CURRENT,
+				[EI_OSABI] = ELF_OSABI,
+			},
+			.e_type = ET_CORE,
+			.e_machine = ELF_ARCH,
+			.e_version = EV_CURRENT,
+			.e_phoff = sizeof(struct elfhdr),
+			.e_flags = ELF_CORE_EFLAGS,
+			.e_ehsize = sizeof(struct elfhdr),
+			.e_phentsize = sizeof(struct elf_phdr),
+			.e_phnum = nphdr,
+		};
+
+		tsz = min_t(size_t, buflen, sizeof(struct elfhdr) - *fpos);
+		if (copy_to_user(buffer, (char *)&ehdr + *fpos, tsz)) {
+			ret = -EFAULT;
+			goto out;
+		}
 
-	/* trim buflen to not go beyond EOF */
-	if (buflen > size - *fpos)
-		buflen = size - *fpos;
+		buffer += tsz;
+		buflen -= tsz;
+		*fpos += tsz;
+	}
 
-	/* construct an ELF core header if we'll need some of it */
-	if (*fpos < elf_buflen) {
-		char * elf_buf;
+	/* ELF program headers. */
+	if (buflen && *fpos < phdrs_offset + phdrs_len) {
+		struct elf_phdr *phdrs, *phdr;
 
-		tsz = elf_buflen - *fpos;
-		if (buflen < tsz)
-			tsz = buflen;
-		elf_buf = kzalloc(elf_buflen, GFP_KERNEL);
-		if (!elf_buf) {
+		phdrs = kzalloc(phdrs_len, GFP_KERNEL);
+		if (!phdrs) {
 			ret = -ENOMEM;
 			goto out;
 		}
-		elf_kcore_store_hdr(elf_buf, nphdr, elf_buflen);
-		if (copy_to_user(buffer, elf_buf + *fpos, tsz)) {
-			kfree(elf_buf);
+
+		phdrs[0].p_type = PT_NOTE;
+		phdrs[0].p_offset = notes_offset;
+		phdrs[0].p_filesz = notes_len;
+
+		phdr = &phdrs[1];
+		list_for_each_entry(m, &kclist_head, list) {
+			phdr->p_type = PT_LOAD;
+			phdr->p_flags = PF_R | PF_W | PF_X;
+			phdr->p_offset = kc_vaddr_to_offset(m->addr) + data_offset;
+			phdr->p_vaddr = (size_t)m->addr;
+			if (m->type == KCORE_RAM)
+				phdr->p_paddr = __pa(m->addr);
+			else if (m->type == KCORE_TEXT)
+				phdr->p_paddr = __pa_symbol(m->addr);
+			else
+				phdr->p_paddr = (elf_addr_t)-1;
+			phdr->p_filesz = phdr->p_memsz = m->size;
+			phdr->p_align = PAGE_SIZE;
+			phdr++;
+		}
+
+		tsz = min_t(size_t, buflen, phdrs_offset + phdrs_len - *fpos);
+		if (copy_to_user(buffer, (char *)phdrs + *fpos - phdrs_offset,
+				 tsz)) {
+			kfree(phdrs);
 			ret = -EFAULT;
 			goto out;
 		}
-		kfree(elf_buf);
+		kfree(phdrs);
+
+		buffer += tsz;
 		buflen -= tsz;
 		*fpos += tsz;
-		buffer += tsz;
+	}
+
+	/* ELF note segment. */
+	if (buflen && *fpos < notes_offset + notes_len) {
+		struct elf_prstatus prstatus = {};
+		struct elf_prpsinfo prpsinfo = {
+			.pr_sname = 'R',
+			.pr_fname = "vmlinux",
+		};
+		char *notes;
+		size_t i = 0;
+
+		strlcpy(prpsinfo.pr_psargs, saved_command_line,
+			sizeof(prpsinfo.pr_psargs));
+
+		notes = kzalloc(notes_len, GFP_KERNEL);
+		if (!notes) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		append_kcore_note(notes, &i, CORE_STR, NT_PRSTATUS, &prstatus,
+				  sizeof(prstatus));
+		append_kcore_note(notes, &i, CORE_STR, NT_PRPSINFO, &prpsinfo,
+				  sizeof(prpsinfo));
+		append_kcore_note(notes, &i, CORE_STR, NT_TASKSTRUCT, current,
+				  arch_task_struct_size);
 
-		/* leave now if filled buffer already */
-		if (buflen == 0)
+		tsz = min_t(size_t, buflen, notes_offset + notes_len - *fpos);
+		if (copy_to_user(buffer, notes + *fpos - notes_offset, tsz)) {
+			kfree(notes);
+			ret = -EFAULT;
 			goto out;
+		}
+		kfree(notes);
+
+		buffer += tsz;
+		buflen -= tsz;
+		*fpos += tsz;
 	}
 
 	/*
 	 * Check to see if our file offset matches with any of
 	 * the addresses in the elf_phdr on our list.
 	 */
-	start = kc_offset_to_vaddr(*fpos - elf_buflen);
+	start = kc_offset_to_vaddr(*fpos - data_offset);
 	if ((tsz = (PAGE_SIZE - (start & ~PAGE_MASK))) > buflen)
 		tsz = buflen;
-		
-	while (buflen) {
-		struct kcore_list *m;
 
+	while (buflen) {
 		list_for_each_entry(m, &kclist_head, list) {
 			if (start >= m->addr && start < (m->addr+m->size))
 				break;
@@ -557,7 +490,6 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 	return orig_buflen - buflen;
 }
 
-
 static int open_kcore(struct inode *inode, struct file *filp)
 {
 	if (!capable(CAP_SYS_RAWIO))
-- 
2.18.0


  parent reply	other threads:[~2018-07-18 22:59 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-07-18 22:58 [PATCH v3 0/8] /proc/kcore improvements Omar Sandoval
2018-07-18 22:58 ` [PATCH v3 1/8] proc/kcore: don't grab lock for kclist_add() Omar Sandoval
2018-07-18 22:58 ` [PATCH v3 2/8] proc/kcore: don't grab lock for memory hotplug notifier Omar Sandoval
2018-07-18 22:58 ` [PATCH v3 3/8] proc/kcore: replace kclist_lock rwlock with rwsem Omar Sandoval
2018-07-18 22:58 ` [PATCH v3 4/8] proc/kcore: fix memory hotplug vs multiple opens race Omar Sandoval
2018-07-18 22:58 ` [PATCH v3 5/8] proc/kcore: hold lock during read Omar Sandoval
2018-07-24 15:11   ` Tetsuo Handa
2018-07-25 23:34     ` Omar Sandoval
2018-07-18 22:58 ` Omar Sandoval [this message]
2018-07-18 22:58 ` [PATCH v3 7/8] proc/kcore: optimize multiple page reads Omar Sandoval
2018-08-28 10:59   ` KASAN error in " Dominique Martinet
2018-08-29  4:04     ` [PATCH] proc/kcore: fix invalid memory access in multi-page read optimization Dominique Martinet
2018-09-04 18:03       ` Omar Sandoval
2018-09-04 22:24         ` Dominique Martinet
2018-09-04 22:35       ` [PATCH v2] " Dominique Martinet
2018-09-04 22:38         ` [PATCH v3] " Dominique Martinet
2018-09-04 22:41           ` Omar Sandoval
2018-09-05 19:56             ` Bhupesh Sharma
2018-09-05 20:57           ` Andrew Morton
2018-09-05 22:00             ` Dominique Martinet
2018-07-18 22:58 ` [PATCH v3 8/8] proc/kcore: add vmcoreinfo note to /proc/kcore Omar Sandoval

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=19c92cbad0e11f6103ff3274b2e7a7e51a1eb74b.1531953780.git.osandov@fb.com \
    --to=osandov@osandov.com \
    --cc=adobriyan@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=bhsharma@redhat.com \
    --cc=ebiederm@xmission.com \
    --cc=james.morse@arm.com \
    --cc=kernel-team@fb.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).