lkml.org 
[lkml]   [2002]   [Dec]   [16]   [last100]   RSS Feed
Views: [more markup]  [less markup]  [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Frommgross <>
SubjectRe: Multithreaded coredump patch where?
DateMon, 16 Dec 2002 13:21:20 -0800
I haven't rebased the patches I posted back in June for a while now.

Attached is the patch I posted for the 2.4.18 vanilla kernel.  Its a bit 
controversial, but it seems to work for a number of folks.  Let me know if 
you have any troubles re-basing it.

I don't know if there is any plan to back port Ingo's version of this feature 
to 2.4.x

--mgross



On Monday 16 December 2002 09:28 am, Roberto Fichera wrote:
> Does anyone point me where can I download a stable
> multithread coredump patch for the 2.4.19/20 kernel ?
>
> Thanks in advance,
>
> Roberto Fichera.
>
>
> ______________________________________
> E-mail protetta dal servizio antivirus di IsolaWeb Agency & ISP
> http://wwww.isolaweb.it
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/
diff -urN -X dontdiff linux-2.4.18/arch/i386/kernel/i387.c linux2418.tcore/arch/i386/kernel/i387.c
--- linux-2.4.18/arch/i386/kernel/i387.c	Fri Feb 23 13:09:08 2001
+++ linux2418.tcore/arch/i386/kernel/i387.c	Thu Jun 13 10:00:48 2002
@@ -520,3 +520,44 @@
 
 	return fpvalid;
 }
+
+int dump_task_fpu( struct task_struct *tsk, struct user_i387_struct *fpu )
+{
+	int fpvalid;
+
+	fpvalid = tsk->used_math;
+	if ( fpvalid ) {
+		if (tsk == current) unlazy_fpu( tsk );
+		if ( cpu_has_fxsr ) {
+			copy_fpu_fxsave( tsk, fpu );
+		} else {
+			copy_fpu_fsave( tsk, fpu );
+		}
+	}
+
+	return fpvalid;
+}
+
+int dump_task_extended_fpu( struct task_struct *tsk, struct user_fxsr_struct *fpu )
+{
+	int fpvalid;
+	
+	fpvalid = tsk->used_math && cpu_has_fxsr;
+	if ( fpvalid ) {
+		if (tsk == current) unlazy_fpu( tsk );
+		memcpy( fpu, &tsk->thread.i387.fxsave,
+		sizeof(struct user_fxsr_struct) );
+	}
+	
+	return fpvalid;
+}
+
+
+#ifdef CONFIG_SMP
+void dump_smp_unlazy_fpu(void)
+{
+	unlazy_fpu(current);
+	return;
+}
+#endif
+
diff -urN -X dontdiff linux-2.4.18/arch/i386/kernel/process.c linux2418.tcore/arch/i386/kernel/process.c
--- linux-2.4.18/arch/i386/kernel/process.c	Mon Feb 25 14:37:53 2002
+++ linux2418.tcore/arch/i386/kernel/process.c	Thu Jun 13 10:00:48 2002
@@ -644,6 +644,24 @@
 
 	dump->u_fpvalid = dump_fpu (regs, &dump->i387);
 }
+/* 
+ * Capture the user space registers if the task is not running (in user space)
+ */
+#include <linux/elfcore.h>
+int dump_task_regs(struct task_struct *tsk,  elf_gregset_t *regs)
+{
+	struct pt_regs ptregs;
+	
+	ptregs = *(struct pt_regs *)((unsigned long)tsk + THREAD_SIZE - sizeof(struct pt_regs));
+	ptregs.xcs &= 0xffff;
+	ptregs.xds &= 0xffff;
+	ptregs.xes &= 0xffff;
+	ptregs.xss &= 0xffff;
+
+	elf_core_copy_regs(regs, &ptregs);
+
+	return 1;
+}
 
 /*
  * This special macro can be used to load a debugging register
diff -urN -X dontdiff linux-2.4.18/arch/ia64/kernel/process.c linux2418.tcore/arch/ia64/kernel/process.c
--- linux-2.4.18/arch/ia64/kernel/process.c	Fri Nov  9 17:26:17 2001
+++ linux2418.tcore/arch/ia64/kernel/process.c	Thu Jun 13 10:00:48 2002
@@ -298,6 +298,31 @@
 void
 do_copy_regs (struct unw_frame_info *info, void *arg)
 {
+	do_copy_task_regs(current, info, arg);
+}
+
+void
+do_dump_fpu (struct unw_frame_info *info, void *arg)
+{
+	do_dump_task_fpu(current, info, arg);
+}
+
+void
+ia64_elf_core_copy_regs (struct pt_regs *pt, elf_gregset_t dst)
+{
+	unw_init_running(do_copy_regs, dst);
+}
+
+int
+dump_fpu (struct pt_regs *pt, elf_fpregset_t dst)
+{
+	unw_init_running(do_dump_fpu, dst);
+	return 1;	/* f0-f31 are always valid so we always return 1 */
+}
+
+static void
+do_copy_task_regs (struct task_struct *task, struct unw_frame_info *info, void *arg)
+{
 	unsigned long mask, sp, nat_bits = 0, ip, ar_rnat, urbs_end, cfm;
 	elf_greg_t *dst = arg;
 	struct pt_regs *pt;
@@ -312,12 +337,12 @@
 	unw_get_sp(info, &sp);
 	pt = (struct pt_regs *) (sp + 16);
 
-	urbs_end = ia64_get_user_rbs_end(current, pt, &cfm);
+	urbs_end = ia64_get_user_rbs_end(task, pt, &cfm);
 
-	if (ia64_sync_user_rbs(current, info->sw, pt->ar_bspstore, urbs_end) < 0)
+	if (ia64_sync_user_rbs(task, info->sw, pt->ar_bspstore, urbs_end) < 0)
 		return;
 
-	ia64_peek(current, info->sw, urbs_end, (long) ia64_rse_rnat_addr((long *) urbs_end),
+	ia64_peek(task, info->sw, urbs_end, (long) ia64_rse_rnat_addr((long *) urbs_end),
 		  &ar_rnat);
 
 	/*
@@ -366,7 +391,7 @@
 }
 
 void
-do_dump_fpu (struct unw_frame_info *info, void *arg)
+do_dump_task_fpu (struct task_struct *task, struct unw_frame_info *info, void *arg)
 {
 	elf_fpreg_t *dst = arg;
 	int i;
@@ -381,22 +406,41 @@
 	for (i = 2; i < 32; ++i)
 		unw_get_fr(info, i, dst + i);
 
-	ia64_flush_fph(current);
-	if ((current->thread.flags & IA64_THREAD_FPH_VALID) != 0)
-		memcpy(dst + 32, current->thread.fph, 96*16);
+	ia64_flush_fph(task);
+	if ((task->thread.flags & IA64_THREAD_FPH_VALID) != 0)
+		memcpy(dst + 32, task->thread.fph, 96*16);
 }
 
-void
-ia64_elf_core_copy_regs (struct pt_regs *pt, elf_gregset_t dst)
+int dump_task_regs(struct task_struct *task, elf_gregset_t *regs)
 {
-	unw_init_running(do_copy_regs, dst);
+	struct unw_frame_info tcore_info;
+
+	if(current == task) {
+		unw_init_running(do_copy_regs, regs);
+	}
+	else {
+		memset(&tcore_info, 0, sizeof(tcore_info));	
+		unw_init_from_blocked_task(&tcore_info, task);
+		do_copy_task_regs(task, &tcore_info, regs);
+	}
+
+	return 1;
 }
 
-int
-dump_fpu (struct pt_regs *pt, elf_fpregset_t dst)
+int dump_task_fpu (struct task_struct *task, elf_fpregset_t *dst)
 {
-	unw_init_running(do_dump_fpu, dst);
-	return 1;	/* f0-f31 are always valid so we always return 1 */
+	struct unw_frame_info tcore_info;
+
+	if(current == task) {
+		unw_init_running(do_dump_fpu, dst);
+	}
+	else {
+		memset(&tcore_info, 0, sizeof(tcore_info));	
+		unw_init_from_blocked_task(&tcore_info, task);
+		do_dump_task_fpu(task, &tcore_info, dst);
+	}
+
+	return 1; 
 }
 
 asmlinkage long
Binary files linux-2.4.18/core and linux2418.tcore/core differ
diff -urN -X dontdiff linux-2.4.18/fs/binfmt_elf.c linux2418.tcore/fs/binfmt_elf.c
--- linux-2.4.18/fs/binfmt_elf.c	Mon Feb 25 14:38:08 2002
+++ linux2418.tcore/fs/binfmt_elf.c	Tue Jun 18 10:00:13 2002
@@ -30,6 +30,7 @@
 #include <linux/elfcore.h>
 #include <linux/init.h>
 #include <linux/highuid.h>
+#include <linux/smp.h>
 #include <linux/smp_lock.h>
 #include <linux/compiler.h>
 #include <linux/highmem.h>
@@ -952,7 +953,7 @@
 /* #define DEBUG */
 
 #ifdef DEBUG
-static void dump_regs(const char *str, elf_greg_t *r)
+static void dump_regs(const char *str, elf_gregset_t *r)
 {
 	int i;
 	static const char *regs[] = { "ebx", "ecx", "edx", "esi", "edi", "ebp",
@@ -1000,6 +1001,156 @@
 #define DUMP_SEEK(off)	\
 	if (!dump_seek(file, (off))) \
 		goto end_coredump;
+
+static inline void fill_elf_header(struct elfhdr *elf, int segs)
+{
+	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;
+	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 = 0;
+	elf->e_ehsize = sizeof(struct elfhdr);
+	elf->e_phentsize = sizeof(struct elf_phdr);
+	elf->e_phnum = segs;
+	elf->e_shentsize = 0;
+	elf->e_shnum = 0;
+	elf->e_shstrndx = 0;
+	return;
+}
+
+static inline void fill_elf_note_phdr(struct elf_phdr *phdr, int sz, off_t offset)
+{
+	phdr->p_type = PT_NOTE;
+	phdr->p_offset = offset;
+	phdr->p_vaddr = 0;
+	phdr->p_paddr = 0;
+	phdr->p_filesz = sz;
+	phdr->p_memsz = 0;
+	phdr->p_flags = 0;
+	phdr->p_align = 0;
+	return;
+}
+
+static inline void fill_note(struct memelfnote *note, const char *name, int type, 
+		unsigned int sz, void *data)
+{
+	note->name = name;
+	note->type = type;
+	note->datasz = sz;
+	note->data = data;
+	return;
+}
+
+/*
+ * fill up all the fields in prstatus from the given task struct, except registers
+ * which need to be filled up seperately.
+ */
+static inline void fill_prstatus(struct elf_prstatus *prstatus, struct task_struct *p, long signr) 
+{
+	prstatus->pr_info.si_signo = prstatus->pr_cursig = signr;
+	prstatus->pr_sigpend = p->pending.signal.sig[0];
+	prstatus->pr_sighold = p->blocked.sig[0];
+	prstatus->pr_pid = p->pid;
+	prstatus->pr_ppid = p->p_pptr->pid;
+	prstatus->pr_pgrp = p->pgrp;
+	prstatus->pr_sid = p->session;
+	prstatus->pr_utime.tv_sec = CT_TO_SECS(p->times.tms_utime);
+	prstatus->pr_utime.tv_usec = CT_TO_USECS(p->times.tms_utime);
+	prstatus->pr_stime.tv_sec = CT_TO_SECS(p->times.tms_stime);
+	prstatus->pr_stime.tv_usec = CT_TO_USECS(p->times.tms_stime);
+	prstatus->pr_cutime.tv_sec = CT_TO_SECS(p->times.tms_cutime);
+	prstatus->pr_cutime.tv_usec = CT_TO_USECS(p->times.tms_cutime);
+	prstatus->pr_cstime.tv_sec = CT_TO_SECS(p->times.tms_cstime);
+	prstatus->pr_cstime.tv_usec = CT_TO_USECS(p->times.tms_cstime);
+	return;
+}
+
+static inline void fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p)
+{
+	int i;
+	
+	psinfo->pr_pid = p->pid;
+	psinfo->pr_ppid = p->p_pptr->pid;
+	psinfo->pr_pgrp = p->pgrp;
+	psinfo->pr_sid = p->session;
+
+	i = p->state ? ffz(~p->state) + 1 : 0;
+	psinfo->pr_state = i;
+	psinfo->pr_sname = (i < 0 || i > 5) ? '.' : "RSDZTD"[i];
+	psinfo->pr_zomb = psinfo->pr_sname == 'Z';
+	psinfo->pr_nice =  p->nice;
+	psinfo->pr_flag = p->flags;
+	psinfo->pr_uid = NEW_TO_OLD_UID(p->uid);
+	psinfo->pr_gid = NEW_TO_OLD_GID(p->gid);
+	strncpy(psinfo->pr_fname, p->comm, sizeof(psinfo->pr_fname));
+	return;
+}
+
+/* Here is the structure in which status of each thread is captured. */
+struct elf_thread_status
+{
+	struct list_head list;
+	struct elf_prstatus prstatus;	/* NT_PRSTATUS */
+	elf_fpregset_t fpu;		/* NT_PRFPREG */
+#ifdef ELF_CORE_COPY_XFPREGS
+	elf_fpxregset_t xfpu;		/* NT_PRXFPREG */
+#endif
+	struct memelfnote notes[3];
+	int num_notes;
+};
+
+/*
+ * In order to add the specific thread information for the elf file format,
+ * we need to keep a linked list of every threads pr_status and then
+ * create a single section for them in the final core file.
+ */
+static int elf_dump_thread_status(long signr, struct task_struct * p, struct list_head * thread_list)
+{
+
+	struct elf_thread_status *t;
+	int sz = 0;
+
+	t = kmalloc(sizeof(*t), GFP_KERNEL);
+	if (!t) {
+		printk(KERN_WARNING "Cannot allocate memory for thread status.\n");
+		return 0;
+	}
+
+	INIT_LIST_HEAD(&t->list);
+	t->num_notes = 0;
+
+	fill_prstatus(&t->prstatus, p, signr);
+	elf_core_copy_task_regs(p, &t->prstatus.pr_reg);	
+	
+	fill_note(&t->notes[0], "CORE", NT_PRSTATUS, sizeof(t->prstatus), &(t->prstatus));
+	t->num_notes++;
+	sz += notesize(&t->notes[0]);
+
+	if ((t->prstatus.pr_fpvalid = elf_core_copy_task_fpregs(p, &t->fpu))) {
+		fill_note(&t->notes[1], "CORE", NT_PRFPREG, sizeof(t->fpu), &(t->fpu));
+		t->num_notes++;
+		sz += notesize(&t->notes[1]);
+	}
+
+#ifdef ELF_CORE_COPY_XFPREGS
+	if (elf_core_copy_task_xfpregs(p, &t->xfpu)) {
+		fill_note(&t->notes[2], "LINUX", NT_PRXFPREG, sizeof(t->xfpu), &(t->xfpu));
+		t->num_notes++;
+		sz += notesize(&t->notes[2]);
+	}
+#endif	
+	list_add(&t->list, thread_list);
+	return sz;
+}
+
 /*
  * Actual dumper
  *
@@ -1018,12 +1169,23 @@
 	struct elfhdr elf;
 	off_t offset = 0, dataoff;
 	unsigned long limit = current->rlim[RLIMIT_CORE].rlim_cur;
-	int numnote = 4;
-	struct memelfnote notes[4];
+	int numnote = 5;
+	struct memelfnote notes[5];
 	struct elf_prstatus prstatus;	/* NT_PRSTATUS */
-	elf_fpregset_t fpu;		/* NT_PRFPREG */
 	struct elf_prpsinfo psinfo;	/* NT_PRPSINFO */
+ 	struct task_struct *p;
+ 	LIST_HEAD(thread_list);
+ 	struct list_head *t;
+	elf_fpregset_t fpu;
+#ifdef ELF_CORE_COPY_XFPREGS
+	elf_fpxregset_t xfpu;
+#endif
+	int thread_status_size = 0;
+	
 
+	/* First pause all related threaded processes */
+	tcore_suspend_threads();
+	
 	/* first copy the parameters from user space */
 	memset(&psinfo, 0, sizeof(psinfo));
 	{
@@ -1041,51 +1203,50 @@
 
 	}
 
-	memset(&prstatus, 0, sizeof(prstatus));
-	/*
-	 * This transfers the registers from regs into the standard
-	 * coredump arrangement, whatever that is.
-	 */
-#ifdef ELF_CORE_COPY_REGS
-	ELF_CORE_COPY_REGS(prstatus.pr_reg, regs)
-#else
-	if (sizeof(elf_gregset_t) != sizeof(struct pt_regs))
-	{
-		printk("sizeof(elf_gregset_t) (%ld) != sizeof(struct pt_regs) (%ld)\n",
-			(long)sizeof(elf_gregset_t), (long)sizeof(struct pt_regs));
+	 /* capture the status of all other threads */
+	if (signr) {
+		read_lock(&tasklist_lock);
+		for_each_task(p)
+			if (current->mm == p->mm && current != p) {
+				int sz = elf_dump_thread_status(signr, p, &thread_list);
+				if (!sz) {
+					read_unlock(&tasklist_lock);
+					goto cleanup;
+				}
+				else
+					thread_status_size += sz;
+			}
+		read_unlock(&tasklist_lock);
 	}
-	else
-		*(struct pt_regs *)&prstatus.pr_reg = *regs;
-#endif
 
-	/* now stop all vm operations */
-	down_write(&current->mm->mmap_sem);
-	segs = current->mm->map_count;
+	/* now capture current's thread state */
+	memset(&prstatus, 0, sizeof(prstatus));
+	fill_prstatus(&prstatus, current, signr);
+	elf_core_copy_regs(&prstatus.pr_reg, regs);
+	
+	/* We no longer stop all vm operations */
+  
+	/* This because those proceses that could possibly 
+	 * change map_count or the mmap / vma pages are now suspended.
+	 *
+	 * Only ptrace can touch these memory address, but it cannot change
+	 * the map_count or the pages.  So no possibility of crashing exists while dumping
+	 * the mm->vm_next areas to the core file.
+	 *
+	 * Grabbing mmap_sem in this function is risky WRT the use of suspend_threads.
+	 * Although no locks ups have been induced, if one of the suspended threads was 
+	 * in line for the current->mmap_sem and if gets it while on the Phantom runque,
+	 * then we would dead lock in this function if we continue to attempt to down_write
+	 * in this function.
+	 */
+  	segs = current->mm->map_count;
 
 #ifdef DEBUG
 	printk("elf_core_dump: %d segs %lu limit\n", segs, limit);
 #endif
 
 	/* Set up header */
-	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;
-	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(elf);
-	elf.e_shoff = 0;
-	elf.e_flags = 0;
-	elf.e_ehsize = sizeof(elf);
-	elf.e_phentsize = sizeof(struct elf_phdr);
-	elf.e_phnum = segs+1;		/* Include notes */
-	elf.e_shentsize = 0;
-	elf.e_shnum = 0;
-	elf.e_shstrndx = 0;
+	fill_elf_header(&elf, segs+1); /* including notes section*/
 
 	fs = get_fs();
 	set_fs(KERNEL_DS);
@@ -1102,64 +1263,34 @@
 	 * with info from their /proc.
 	 */
 
-	notes[0].name = "CORE";
-	notes[0].type = NT_PRSTATUS;
-	notes[0].datasz = sizeof(prstatus);
-	notes[0].data = &prstatus;
-	prstatus.pr_info.si_signo = prstatus.pr_cursig = signr;
-	prstatus.pr_sigpend = current->pending.signal.sig[0];
-	prstatus.pr_sighold = current->blocked.sig[0];
-	psinfo.pr_pid = prstatus.pr_pid = current->pid;
-	psinfo.pr_ppid = prstatus.pr_ppid = current->p_pptr->pid;
-	psinfo.pr_pgrp = prstatus.pr_pgrp = current->pgrp;
-	psinfo.pr_sid = prstatus.pr_sid = current->session;
-	prstatus.pr_utime.tv_sec = CT_TO_SECS(current->times.tms_utime);
-	prstatus.pr_utime.tv_usec = CT_TO_USECS(current->times.tms_utime);
-	prstatus.pr_stime.tv_sec = CT_TO_SECS(current->times.tms_stime);
-	prstatus.pr_stime.tv_usec = CT_TO_USECS(current->times.tms_stime);
-	prstatus.pr_cutime.tv_sec = CT_TO_SECS(current->times.tms_cutime);
-	prstatus.pr_cutime.tv_usec = CT_TO_USECS(current->times.tms_cutime);
-	prstatus.pr_cstime.tv_sec = CT_TO_SECS(current->times.tms_cstime);
-	prstatus.pr_cstime.tv_usec = CT_TO_USECS(current->times.tms_cstime);
-
 #ifdef DEBUG
 	dump_regs("Passed in regs", (elf_greg_t *)regs);
 	dump_regs("prstatus regs", (elf_greg_t *)&prstatus.pr_reg);
 #endif
 
-	notes[1].name = "CORE";
-	notes[1].type = NT_PRPSINFO;
-	notes[1].datasz = sizeof(psinfo);
-	notes[1].data = &psinfo;
-	i = current->state ? ffz(~current->state) + 1 : 0;
-	psinfo.pr_state = i;
-	psinfo.pr_sname = (i < 0 || i > 5) ? '.' : "RSDZTD"[i];
-	psinfo.pr_zomb = psinfo.pr_sname == 'Z';
-	psinfo.pr_nice = current->nice;
-	psinfo.pr_flag = current->flags;
-	psinfo.pr_uid = NEW_TO_OLD_UID(current->uid);
-	psinfo.pr_gid = NEW_TO_OLD_GID(current->gid);
-	strncpy(psinfo.pr_fname, current->comm, sizeof(psinfo.pr_fname));
-
-	notes[2].name = "CORE";
-	notes[2].type = NT_TASKSTRUCT;
-	notes[2].datasz = sizeof(*current);
-	notes[2].data = current;
-
-	/* Try to dump the FPU. */
-	prstatus.pr_fpvalid = dump_fpu (regs, &fpu);
-	if (!prstatus.pr_fpvalid)
-	{
-		numnote--;
-	}
-	else
-	{
-		notes[3].name = "CORE";
-		notes[3].type = NT_PRFPREG;
-		notes[3].datasz = sizeof(fpu);
-		notes[3].data = &fpu;
-	}
+	fill_note(&notes[0], "CORE", NT_PRSTATUS, sizeof(prstatus), &prstatus);
 	
+	fill_psinfo(&psinfo, current);
+	fill_note(&notes[1], "CORE", NT_PRPSINFO, sizeof(psinfo), &psinfo);
+	
+	fill_note(&notes[2], "CORE", NT_TASKSTRUCT, sizeof(*current), current);
+  
+  	/* Try to dump the FPU. */
+	if ((prstatus.pr_fpvalid = elf_core_copy_task_fpregs(current, &fpu))) {
+		fill_note(&notes[3], "CORE", NT_PRFPREG, sizeof(fpu), &fpu);
+	} else {
+		--numnote;
+ 	}
+#ifdef ELF_CORE_COPY_XFPREGS
+	if (elf_core_copy_task_xfpregs(current, &xfpu)) {
+		fill_note(&notes[4], "LINUX", NT_PRXFPREG, sizeof(xfpu), &xfpu);
+	} else {
+		--numnote;
+	}
+#else
+	numnote --;
+#endif	
+  
 	/* Write notes phdr entry */
 	{
 		struct elf_phdr phdr;
@@ -1167,17 +1298,11 @@
 
 		for(i = 0; i < numnote; i++)
 			sz += notesize(&notes[i]);
+		
+		sz += thread_status_size;
 
-		phdr.p_type = PT_NOTE;
-		phdr.p_offset = offset;
-		phdr.p_vaddr = 0;
-		phdr.p_paddr = 0;
-		phdr.p_filesz = sz;
-		phdr.p_memsz = 0;
-		phdr.p_flags = 0;
-		phdr.p_align = 0;
-
-		offset += phdr.p_filesz;
+		fill_elf_note_phdr(&phdr, sz, offset);
+		offset += sz;
 		DUMP_WRITE(&phdr, sizeof(phdr));
 	}
 
@@ -1206,10 +1331,19 @@
 		DUMP_WRITE(&phdr, sizeof(phdr));
 	}
 
+ 	/* write out the notes section */
 	for(i = 0; i < numnote; i++)
 		if (!writenote(&notes[i], file))
 			goto end_coredump;
 
+	/* write out the thread status notes section */
+	list_for_each(t, &thread_list) {
+		struct elf_thread_status *tmp = list_entry(t, struct elf_thread_status, list);
+		for (i = 0; i < tmp->num_notes; i++)
+			if (!writenote(&tmp->notes[i], file))
+				goto end_coredump;
+	}
+ 
 	DUMP_SEEK(dataoff);
 
 	for(vma = current->mm->mmap; vma != NULL; vma = vma->vm_next) {
@@ -1253,11 +1387,21 @@
 		       (off_t) file->f_pos, offset);
 	}
 
- end_coredump:
+end_coredump:
 	set_fs(fs);
-	up_write(&current->mm->mmap_sem);
+
+cleanup:
+	while(!list_empty(&thread_list)) {
+		struct list_head *tmp = thread_list.next;
+		list_del(tmp);
+		kfree(list_entry(tmp, struct elf_thread_status, list));
+	}
+
+	tcore_resume_threads();
+
 	return has_dumped;
 }
+
 #endif		/* USE_ELF_CORE_DUMP */
 
 static int __init init_elf_binfmt(void)
diff -urN -X dontdiff linux-2.4.18/include/asm-i386/elf.h linux2418.tcore/include/asm-i386/elf.h
--- linux-2.4.18/include/asm-i386/elf.h	Thu Nov 22 14:48:29 2001
+++ linux2418.tcore/include/asm-i386/elf.h	Thu Jun 13 11:19:11 2002
@@ -99,6 +99,21 @@
 
 #ifdef __KERNEL__
 #define SET_PERSONALITY(ex, ibcs2) set_personality((ibcs2)?PER_SVR4:PER_LINUX)
+
+
+extern int dump_task_regs (struct task_struct *, elf_gregset_t *);
+extern int dump_task_fpu (struct task_struct *, elf_fpregset_t *);
+extern int dump_task_extended_fpu (struct task_struct *, struct user_fxsr_struct *);
+
+#define ELF_CORE_COPY_TASK_REGS(tsk, elf_regs) dump_task_regs(tsk, elf_regs)
+#define ELF_CORE_COPY_FPREGS(tsk, elf_fpregs) dump_task_fpu(tsk, elf_fpregs)
+#define ELF_CORE_COPY_XFPREGS(tsk, elf_xfpregs) dump_task_extended_fpu(tsk, elf_xfpregs)
+
+#ifdef CONFIG_SMP
+extern void dump_smp_unlazy_fpu(void);
+#define ELF_CORE_SYNC dump_smp_unlazy_fpu
+#endif
+
 #endif
 
 #endif
diff -urN -X dontdiff linux-2.4.18/include/asm-ia64/elf.h linux2418.tcore/include/asm-ia64/elf.h
--- linux-2.4.18/include/asm-ia64/elf.h	Tue Jul 11 18:43:45 2000
+++ linux2418.tcore/include/asm-ia64/elf.h	Thu Jun 13 10:00:48 2002
@@ -62,12 +62,16 @@
 #define ELF_NGREG	128	/* we really need just 72 but let's leave some headroom... */
 #define ELF_NFPREG	128	/* f0 and f1 could be omitted, but so what... */
 
+typedef unsigned long elf_fpxregset_t;
+
 typedef unsigned long elf_greg_t;
 typedef elf_greg_t elf_gregset_t[ELF_NGREG];
 
 typedef struct ia64_fpreg elf_fpreg_t;
 typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
 
+
+
 struct pt_regs;	/* forward declaration... */
 extern void ia64_elf_core_copy_regs (struct pt_regs *src, elf_gregset_t dst);
 #define ELF_CORE_COPY_REGS(_dest,_regs)	ia64_elf_core_copy_regs(_regs, _dest);
@@ -83,6 +87,12 @@
 
 #ifdef __KERNEL__
 #define SET_PERSONALITY(ex, ibcs2) set_personality((ibcs2)?PER_SVR4:PER_LINUX)
+extern int dump_task_regs(struct task_struct *, elf_gregset_t *);
+extern int dump_task_fpu (struct task_struct *, elf_fpregset_t *);
+
+#define ELF_CORE_COPY_TASK_REGS(tsk, elf_gregs) dump_task_regs(tsk, elf_gregs)
+#define ELF_CORE_COPY_FPREGS(tsk, elf_fpregs) dump_task_fpu(tsk, elf_fpregs)
+
 #endif
 
 #endif /* _ASM_IA64_ELF_H */
diff -urN -X dontdiff linux-2.4.18/include/linux/elf.h linux2418.tcore/include/linux/elf.h
--- linux-2.4.18/include/linux/elf.h	Thu Nov 22 14:48:29 2001
+++ linux2418.tcore/include/linux/elf.h	Thu Jun 13 11:20:43 2002
@@ -576,6 +576,9 @@
 #define NT_PRPSINFO	3
 #define NT_TASKSTRUCT	4
 #define NT_PRFPXREG	20
+#define NT_PRXFPREG     0x46e62b7f	/* note name must be "LINUX" as per GDB */
+					/* from gdb5.1/include/elf/common.h */
+
 
 /* Note header in a PT_NOTE section */
 typedef struct elf32_note {
@@ -606,6 +609,5 @@
 #define elf_note	elf64_note
 
 #endif
-
 
 #endif /* _LINUX_ELF_H */
diff -urN -X dontdiff linux-2.4.18/include/linux/elfcore.h linux2418.tcore/include/linux/elfcore.h
--- linux-2.4.18/include/linux/elfcore.h	Thu Nov 22 14:49:02 2001
+++ linux2418.tcore/include/linux/elfcore.h	Thu Jun 13 11:19:11 2002
@@ -86,4 +86,66 @@
 #define PRARGSZ ELF_PRARGSZ 
 #endif
 
+#ifdef __KERNEL__
+static inline void elf_core_copy_regs(elf_gregset_t *elfregs, struct pt_regs *regs)
+{
+#ifdef ELF_CORE_COPY_REGS
+	ELF_CORE_COPY_REGS((*elfregs), regs)
+#else
+	if (sizeof(elf_gregset_t) != sizeof(struct pt_regs)) {
+		printk("sizeof(elf_gregset_t) (%ld) != sizeof(struct pt_regs) (%ld)\n",
+			(long)sizeof(elf_gregset_t), (long)sizeof(struct pt_regs));
+	} else
+		*(struct pt_regs *)elfregs = *regs;
+#endif
+}
+
+static inline int elf_core_copy_task_regs(struct task_struct *t, elf_gregset_t* elfregs)
+{
+#ifdef ELF_CORE_COPY_TASK_REGS
+	
+	return ELF_CORE_COPY_TASK_REGS(t, elfregs);
+#endif
+	return 0;
+}
+
+extern int dump_fpu (struct pt_regs *, elf_fpregset_t *);
+
+static inline int elf_core_copy_task_fpregs(struct task_struct *t, elf_fpregset_t *fpu)
+{
+#ifdef ELF_CORE_COPY_FPREGS
+	return ELF_CORE_COPY_FPREGS(t, fpu);
+#else
+	return dump_fpu(NULL, fpu);
+#endif
+}
+
+#ifdef ELF_CORE_COPY_XFPREGS
+static inline int elf_core_copy_task_xfpregs(struct task_struct *t, elf_fpxregset_t *xfpu)
+{
+	return ELF_CORE_COPY_XFPREGS(t, xfpu);
+}
+#endif
+
+#ifdef CONFIG_SMP
+/*
+ * trivial function used for SMP CPU synchronization.
+ * It doesn't do anything.
+ */
+static void tcore_do_nothing(void *var)
+{
+
+#ifdef ELF_CORE_SYNC
+	ELF_CORE_SYNC();
+#endif
+
+	return;
+}
+
+#endif
+
+
+#endif /* __KERNEL__ */
+
+
 #endif /* _LINUX_ELFCORE_H */
diff -urN -X dontdiff linux-2.4.18/include/linux/sched.h linux2418.tcore/include/linux/sched.h
--- linux-2.4.18/include/linux/sched.h	Fri Dec 21 12:42:03 2001
+++ linux2418.tcore/include/linux/sched.h	Thu Jun 13 11:19:11 2002
@@ -132,6 +132,14 @@
 
 #include <linux/spinlock.h>
 
+
+/* functions for pausing and resumming functions 
+ * common mm's without using signals.  These are used
+ * by the multithreaded elf core dump code in binfmt_elf.c*/
+extern void tcore_suspend_threads( void );
+extern void tcore_resume_threads( void );
+
+
 /*
  * This serializes "schedule()" and also protects
  * the run-queue from deletions/modifications (but
diff -urN -X dontdiff linux-2.4.18/kernel/sched.c linux2418.tcore/kernel/sched.c
--- linux-2.4.18/kernel/sched.c	Fri Dec 21 12:42:04 2001
+++ linux2418.tcore/kernel/sched.c	Thu Jun 13 10:00:48 2002
@@ -33,6 +33,8 @@
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
 
+#include <linux/elfcore.h>
+
 extern void timer_bh(void);
 extern void tqueue_bh(void);
 extern void immediate_bh(void);
@@ -121,7 +123,7 @@
 #else
 
 #define idle_task(cpu) (&init_task)
-#define can_schedule(p,cpu) (1)
+#define can_schedule(p,cpu) ((p)->cpus_allowed & (1 << cpu))
 
 #endif
 
@@ -851,6 +853,108 @@
 }
 
 void scheduling_functions_end_here(void) { }
+  
+/*
+ * needed for accurate core dumps of multi-threaded applications.
+ * see binfmt_elf.c for more information.
+ */
+static void reschedule_other_cpus(void)
+{
+#ifdef CONFIG_SMP
+	int i, cpu;
+	struct task_struct *p;
+
+	for(i=0; i< smp_num_cpus; i++) {
+		cpu = cpu_logical_map(i);
+		p = cpu_curr(cpu);
+		if (p->processor != smp_processor_id()) {
+			p->need_resched = 1;
+			smp_send_reschedule(p->processor);
+		}
+ 	}
+#endif	
+	return;
+}
+
+/* functions for pausing and resumming functions with out using signals */
+void tcore_suspend_threads(void)
+{
+	struct task_struct *p;
+
+//
+// grab all the rq_locks.
+// current is the process dumping core
+//  
+
+	down_write(&current->mm->mmap_sem);
+	// avoid potential race on >2 way SMP if 3 or more thread procs
+	// dump core at the same time.
+	
+
+	/*
+	 * brute force method uses the runqueue_lock contention.  Grab this lock, and
+	 * force a schedule call on all the other CPU's to get them spinning.
+	 * spin_lock_prefetch(&runqueue_lock) <-- is this needed?
+	 */
+	read_lock(&tasklist_lock);
+	spin_lock_irq(&runqueue_lock);
+
+	task_lock(current);
+	current->cpus_allowed = 1UL << current->processor;
+	// prevent migraion of dumping process making life complicated.
+	task_unlock(current);
+			
+	reschedule_other_cpus();
+	// this is an optional IPI, but it makes for the most accurate core files possible.
+		
+	for_each_task(p)
+		if (current->mm == p->mm && current != p) {
+			task_lock(p);
+			p->cpus_allowed = 0UL;
+			task_unlock(p);
+			/* 
+			 * forces yeild and keeps waking process from getting scheduled
+			 * in. This will result in these processes getting swapped out and
+			 * not swapped in by the scheduler if they have been sleeping.
+			 */
+		}
+		
+	spin_unlock_irq(&runqueue_lock);
+	
+	/* let them all run again.. */
+	read_unlock(&tasklist_lock);
+
+	up_write(&current->mm->mmap_sem);
+	
+#ifdef CONFIG_SMP
+	/* 
+	 * now we syncronize on all the CPU's to make sure
+	 * none of the other thread processes are running in 
+	 * and any lazy fpu register data has been captured 
+	 * from user space before we proceed.
+	 */
+	smp_call_function(tcore_do_nothing, NULL, 1,1);
+#endif
+	
+return;
+}
+
+void tcore_resume_threads(void)
+{
+	struct task_struct *p;
+
+	read_lock(&tasklist_lock);
+	for_each_task(p)
+		if (current->mm == p->mm && current != p){ 
+			task_lock(p);
+			p->cpus_allowed = 1UL << current->processor;
+			task_unlock(p);
+		}
+	read_unlock(&tasklist_lock);
+
+	return;
+}
+
 
 #ifndef __alpha__
 
\
 
 \ /
  Last update: 2005-03-22 12:31    [W:0.464 / U:0.050 seconds]
©2003-2008 Jasper Spaans