Merge tag 'execve-6.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux

Pull execve updates from Kees Cook:

 - Provide knob to change (previously fixed) coredump NOTES size
   (Allen Pais)

 - Add sched_prepare_exec tracepoint (Marco Elver)

 - Make /proc/$pid/auxv work under binfmt_elf_fdpic (Max Filippov)

 - Convert ARCH_HAVE_EXTRA_ELF_NOTES to proper Kconfig (Vignesh
   Balasubramanian)

 - Leave a gap between .bss and brk

* tag 'execve-6.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
  fs/coredump: Enable dynamic configuration of max file note size
  binfmt_elf_fdpic: fix /proc/<pid>/auxv
  binfmt_elf: Leave a gap between .bss and brk
  Replace macro "ARCH_HAVE_EXTRA_ELF_NOTES" with kconfig
  tracing: Add sched_prepare_exec tracepoint

arch/Kconfig

@@ -510,6 +510,15 @@ config MMU_LAZY_TLB_SHOOTDOWN
 config ARCH_HAVE_NMI_SAFE_CMPXCHG
 	bool
 
+config ARCH_HAVE_EXTRA_ELF_NOTES
+	bool
+	help
+	  An architecture should select this in order to enable adding an
+	  arch-specific ELF note section to core files. It must provide two
+	  functions: elf_coredump_extra_notes_size() and
+	  elf_coredump_extra_notes_write() which are invoked by the ELF core
+	  dumper.
+
 config ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
 	bool
 

arch/powerpc/Kconfig

@@ -156,6 +156,7 @@ config PPC
 	select ARCH_HAS_UACCESS_FLUSHCACHE
 	select ARCH_HAS_UBSAN
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
+	select ARCH_HAVE_EXTRA_ELF_NOTES        if SPU_BASE
 	select ARCH_KEEP_MEMBLOCK
 	select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE	if PPC_RADIX_MMU
 	select ARCH_MIGHT_HAVE_PC_PARPORT

arch/powerpc/include/asm/elf.h

@@ -127,8 +127,6 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 /* Notes used in ET_CORE. Note name is "SPU/<fd>/<filename>". */
 #define NT_SPU		1
 
-#define ARCH_HAVE_EXTRA_ELF_NOTES
-
 #endif /* CONFIG_SPU_BASE */
 
 #ifdef CONFIG_PPC64

fs/binfmt_elf.c

@@ -1262,6 +1262,9 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		if (IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) &&
 		    elf_ex->e_type == ET_DYN && !interpreter) {
 			mm->brk = mm->start_brk = ELF_ET_DYN_BASE;
+		} else {
+			/* Otherwise leave a gap between .bss and brk. */
+			mm->brk = mm->start_brk = mm->brk + PAGE_SIZE;
 		}
 
 		mm->brk = mm->start_brk = arch_randomize_brk(mm);
@@ -1564,7 +1567,6 @@ static void fill_siginfo_note(struct memelfnote *note, user_siginfo_t *csigdata,
 	fill_note(note, "CORE", NT_SIGINFO, sizeof(*csigdata), csigdata);
 }
 
-#define MAX_FILE_NOTE_SIZE (4*1024*1024)
 /*
  * Format of NT_FILE note:
  *
@@ -1592,8 +1594,12 @@ static int fill_files_note(struct memelfnote *note, struct coredump_params *cprm
 
 	names_ofs = (2 + 3 * count) * sizeof(data[0]);
  alloc:
-	if (size >= MAX_FILE_NOTE_SIZE) /* paranoia check */
+	/* paranoia check */
+	if (size >= core_file_note_size_limit) {
+		pr_warn_once("coredump Note size too large: %u (does kernel.core_file_note_size_limit sysctl need adjustment?\n",
+			      size);
 		return -EINVAL;
+	}
 	size = round_up(size, PAGE_SIZE);
 	/*
 	 * "size" can be 0 here legitimately.

fs/binfmt_elf_fdpic.c

@@ -505,8 +505,9 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
 	char *k_platform, *k_base_platform;
 	char __user *u_platform, *u_base_platform, *p;
 	int loop;
-	int nr;	/* reset for each csp adjustment */
 	unsigned long flags = 0;
+	int ei_index;
+	elf_addr_t *elf_info;
 
 #ifdef CONFIG_MMU
 	/* In some cases (e.g. Hyper-Threading), we want to avoid L1 evictions
@@ -601,44 +602,24 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
 	csp -= sp & 15UL;
 	sp -= sp & 15UL;
 
-	/* put the ELF interpreter info on the stack */
-#define NEW_AUX_ENT(id, val)						\
-	do {								\
-		struct { unsigned long _id, _val; } __user *ent, v;	\
-									\
-		ent = (void __user *) csp;				\
-		v._id = (id);						\
-		v._val = (val);						\
-		if (copy_to_user(ent + nr, &v, sizeof(v)))		\
-			return -EFAULT;					\
-		nr++;							\
+	/* Create the ELF interpreter info */
+	elf_info = (elf_addr_t *)mm->saved_auxv;
+	/* update AT_VECTOR_SIZE_BASE if the number of NEW_AUX_ENT() changes */
+#define NEW_AUX_ENT(id, val) \
+	do { \
+		*elf_info++ = id; \
+		*elf_info++ = val; \
 	} while (0)
 
-	nr = 0;
-	csp -= 2 * sizeof(unsigned long);
-	NEW_AUX_ENT(AT_NULL, 0);
-	if (k_platform) {
-		nr = 0;
-		csp -= 2 * sizeof(unsigned long);
-		NEW_AUX_ENT(AT_PLATFORM,
-			    (elf_addr_t) (unsigned long) u_platform);
-	}
-
-	if (k_base_platform) {
-		nr = 0;
-		csp -= 2 * sizeof(unsigned long);
-		NEW_AUX_ENT(AT_BASE_PLATFORM,
-			    (elf_addr_t) (unsigned long) u_base_platform);
-	}
-
-	if (bprm->have_execfd) {
-		nr = 0;
-		csp -= 2 * sizeof(unsigned long);
-		NEW_AUX_ENT(AT_EXECFD, bprm->execfd);
-	}
-
-	nr = 0;
-	csp -= DLINFO_ITEMS * 2 * sizeof(unsigned long);
+#ifdef ARCH_DLINFO
+	/*
+	 * ARCH_DLINFO must come first so PPC can do its special alignment of
+	 * AUXV.
+	 * update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT() in
+	 * ARCH_DLINFO changes
+	 */
+	ARCH_DLINFO;
+#endif
 	NEW_AUX_ENT(AT_HWCAP,	ELF_HWCAP);
 #ifdef ELF_HWCAP2
 	NEW_AUX_ENT(AT_HWCAP2,	ELF_HWCAP2);
@@ -659,17 +640,29 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
 	NEW_AUX_ENT(AT_EGID,	(elf_addr_t) from_kgid_munged(cred->user_ns, cred->egid));
 	NEW_AUX_ENT(AT_SECURE,	bprm->secureexec);
 	NEW_AUX_ENT(AT_EXECFN,	bprm->exec);
+	if (k_platform)
+		NEW_AUX_ENT(AT_PLATFORM,
+			    (elf_addr_t)(unsigned long)u_platform);
+	if (k_base_platform)
+		NEW_AUX_ENT(AT_BASE_PLATFORM,
+			    (elf_addr_t)(unsigned long)u_base_platform);
+	if (bprm->have_execfd)
+		NEW_AUX_ENT(AT_EXECFD, bprm->execfd);
+#undef NEW_AUX_ENT
+	/* AT_NULL is zero; clear the rest too */
+	memset(elf_info, 0, (char *)mm->saved_auxv +
+	       sizeof(mm->saved_auxv) - (char *)elf_info);
 
-#ifdef ARCH_DLINFO
-	nr = 0;
-	csp -= AT_VECTOR_SIZE_ARCH * 2 * sizeof(unsigned long);
+	/* And advance past the AT_NULL entry.  */
+	elf_info += 2;
 
-	/* ARCH_DLINFO must come last so platform specific code can enforce
-	 * special alignment requirements on the AUXV if necessary (eg. PPC).
-	 */
-	ARCH_DLINFO;
-#endif
-#undef NEW_AUX_ENT
+	ei_index = elf_info - (elf_addr_t *)mm->saved_auxv;
+	csp -= ei_index * sizeof(elf_addr_t);
+
+	/* Put the elf_info on the stack in the right place.  */
+	if (copy_to_user((void __user *)csp, mm->saved_auxv,
+			 ei_index * sizeof(elf_addr_t)))
+		return -EFAULT;
 
 	/* allocate room for argv[] and envv[] */
 	csp -= (bprm->envc + 1) * sizeof(elf_caddr_t);

fs/coredump.c

@@ -56,10 +56,15 @@
 static bool dump_vma_snapshot(struct coredump_params *cprm);
 static void free_vma_snapshot(struct coredump_params *cprm);
 
+#define CORE_FILE_NOTE_SIZE_DEFAULT (4*1024*1024)
+/* Define a reasonable max cap */
+#define CORE_FILE_NOTE_SIZE_MAX (16*1024*1024)
+
 static int core_uses_pid;
 static unsigned int core_pipe_limit;
 static char core_pattern[CORENAME_MAX_SIZE] = "core";
 static int core_name_size = CORENAME_MAX_SIZE;
+unsigned int core_file_note_size_limit = CORE_FILE_NOTE_SIZE_DEFAULT;
 
 struct core_name {
 	char *corename;
@@ -998,6 +1003,9 @@ static int proc_dostring_coredump(struct ctl_table *table, int write,
 	return error;
 }
 
+static const unsigned int core_file_note_size_min = CORE_FILE_NOTE_SIZE_DEFAULT;
+static const unsigned int core_file_note_size_max = CORE_FILE_NOTE_SIZE_MAX;
+
 static struct ctl_table coredump_sysctls[] = {
 	{
 		.procname	= "core_uses_pid",
@@ -1020,6 +1028,15 @@ static struct ctl_table coredump_sysctls[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname       = "core_file_note_size_limit",
+		.data           = &core_file_note_size_limit,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler	= proc_douintvec_minmax,
+		.extra1		= (unsigned int *)&core_file_note_size_min,
+		.extra2		= (unsigned int *)&core_file_note_size_max,
+	},
 };
 
 static int __init init_fs_coredump_sysctls(void)

fs/exec.c

@@ -1267,6 +1267,14 @@ int begin_new_exec(struct linux_binprm * bprm)
 	if (retval)
 		return retval;
 
+	/*
+	 * This tracepoint marks the point before flushing the old exec where
+	 * the current task is still unchanged, but errors are fatal (point of
+	 * no return). The later "sched_process_exec" tracepoint is called after
+	 * the current task has successfully switched to the new exec.
+	 */
+	trace_sched_prepare_exec(current, bprm);
+
 	/*
 	 * Ensure all future errors are fatal.
 	 */

include/linux/coredump.h

@@ -30,6 +30,8 @@ struct coredump_params {
 	struct core_vma_metadata *vma_meta;
 };
 
+extern unsigned int core_file_note_size_limit;
+
 /*
  * These are the only things you should do on a core-file: use only these
  * functions to write out all the necessary info.

include/linux/elf.h

@@ -65,7 +65,7 @@ extern Elf64_Dyn _DYNAMIC [];
 struct file;
 struct coredump_params;
 
-#ifndef ARCH_HAVE_EXTRA_ELF_NOTES
+#ifndef CONFIG_ARCH_HAVE_EXTRA_ELF_NOTES
 static inline int elf_coredump_extra_notes_size(void) { return 0; }
 static inline int elf_coredump_extra_notes_write(struct coredump_params *cprm) { return 0; }
 #else

include/trace/events/sched.h

@@ -420,6 +420,41 @@ TRACE_EVENT(sched_process_exec,
 		  __entry->pid, __entry->old_pid)
 );
 
+/**
+ * sched_prepare_exec - called before setting up new exec
+ * @task:	pointer to the current task
+ * @bprm:	pointer to linux_binprm used for new exec
+ *
+ * Called before flushing the old exec, where @task is still unchanged, but at
+ * the point of no return during switching to the new exec. At the point it is
+ * called the exec will either succeed, or on failure terminate the task. Also
+ * see the "sched_process_exec" tracepoint, which is called right after @task
+ * has successfully switched to the new exec.
+ */
+TRACE_EVENT(sched_prepare_exec,
+
+	TP_PROTO(struct task_struct *task, struct linux_binprm *bprm),
+
+	TP_ARGS(task, bprm),
+
+	TP_STRUCT__entry(
+		__string(	interp,		bprm->interp	)
+		__string(	filename,	bprm->filename	)
+		__field(	pid_t,		pid		)
+		__string(	comm,		task->comm	)
+	),
+
+	TP_fast_assign(
+		__assign_str(interp, bprm->interp);
+		__assign_str(filename, bprm->filename);
+		__entry->pid = task->pid;
+		__assign_str(comm, task->comm);
+	),
+
+	TP_printk("interp=%s filename=%s pid=%d comm=%s",
+		  __get_str(interp), __get_str(filename),
+		  __entry->pid, __get_str(comm))
+);
 
 #ifdef CONFIG_SCHEDSTATS
 #define DEFINE_EVENT_SCHEDSTAT DEFINE_EVENT