fs/coredump: Enable dynamic configuration of max file note size

Introduce the capability to dynamically configure the maximum file
note size for ELF core dumps via sysctl.

Why is this being done?
We have observed that during a crash when there are more than 65k mmaps
in memory, the existing fixed limit on the size of the ELF notes section
becomes a bottleneck. The notes section quickly reaches its capacity,
leading to incomplete memory segment information in the resulting coredump.
This truncation compromises the utility of the coredumps, as crucial
information about the memory state at the time of the crash might be
omitted.

This enhancement removes the previous static limit of 4MB, allowing
system administrators to adjust the size based on system-specific
requirements or constraints.

Eg:
$ sysctl -a | grep core_file_note_size_limit
kernel.core_file_note_size_limit = 4194304

$ sysctl -n kernel.core_file_note_size_limit
4194304

$echo 519304 > /proc/sys/kernel/core_file_note_size_limit

$sysctl -n kernel.core_file_note_size_limit
519304

Attempting to write beyond the ceiling value of 16MB
$echo 17194304 > /proc/sys/kernel/core_file_note_size_limit
bash: echo: write error: Invalid argument

Signed-off-by: Vijay Nag <nagvijay@microsoft.com>
Signed-off-by: Allen Pais <apais@linux.microsoft.com>
Link: https://lore.kernel.org/r/20240506193700.7884-1-apais@linux.microsoft.com
Signed-off-by: Kees Cook <keescook@chromium.org>

2 files changed, 22 insertions, 2 deletions

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 7862962f7a85..b5a25ee49eea 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1567,7 +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:
  *
@@ -1595,8 +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.
diff --git a/fs/coredump.c b/fs/coredump.c
index be6403b4b14b..317065e3eb9b 100644
--- a/fs/coredump.c
+++ b/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)