From: Joel Granados <joel.granados@kernel.org>
To: Kees Cook <kees@kernel.org>, Shuah Khan <shuah@kernel.org>,
linux-mm@kvack.org
Cc: Jianlin Shi <shijianlin11@foxmail.com>,
akpm@linux-foundation.org, vbabka@kernel.org,
hannes@cmpxchg.org, surenb@google.com, mhocko@suse.com,
jackmanb@google.com, ziy@nvidia.com,
linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-kselftest@vger.kernel.org,
Joel Granados <joel.granados@kernel.org>
Subject: [PATCH 1/4] sysctl: Split data conversion and file position handling
Date: Thu, 13 Aug 2026 14:18:37 +0200 [thread overview]
Message-ID: <20260813-lklm-partial_ctlvec-v1-1-df9e51c13704@kernel.org> (raw)
In-Reply-To: <20260813-lklm-partial_ctlvec-v1-0-df9e51c13704@kernel.org>
Apply the conversions to the data in a new helper function
(apply_conv_on_vec) while file position handling and argument validation
stay in the original function. Rename function to prov_vec (from
do_proc_vec). This is a prep commit to isolate the logic that needs to
change to prevent partial sysctl vector writes. No functional change
intended
Signed-off-by: Joel Granados <joel.granados@kernel.org>
---
kernel/sysctl.c | 202 ++++++++++++++++++++++++++++++++------------------------
1 file changed, 117 insertions(+), 85 deletions(-)
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index f7b75985d5420a522a316d1fade40dc7fbe60455..ed0e5101949c2fa56e33d543c65175d0ab579fc7 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -595,7 +595,7 @@ static int do_proc_int_conv_minmax(bool *negp, unsigned long *u_ptr, int *k_ptr,
static const char proc_wspace_sep[] = { ' ', '\t', '\n' };
/*
- * Element type processed by do_proc_vec(). The tag selects the element size
+ * Element type processed by proc_vec(). The tag selects the element size
* and signedness, and it selects which member of union proc_vec_conv is live.
*/
enum proc_vec_type {
@@ -605,7 +605,7 @@ enum proc_vec_type {
};
/*
- * Converter passed to do_proc_vec(). Only the member matching the
+ * Converter passed to proc_vec(). Only the member matching the
* enum proc_vec_type tag is ever read, so every dispatch stays fully typed and
* no void * converter pointer is needed.
*/
@@ -637,101 +637,133 @@ static int proc_vec_conv(enum proc_vec_type type, union proc_vec_conv conv,
return -EINVAL;
}
-/*
- * Read/write a vector of @type elements. The element size and signedness are
- * derived from @type, so a single runtime function replaces the per-type
- * variants. table->data is walked as raw bytes (@i) advanced by @size; the
- * converter performs the actual typed load/store.
+/**
+ * apply_conv_on_vec - Apply converter function on data vector
+ *
+ * Element signedness is derived from @data_type. table->data is walked
+ * as raw bytes (@data) advanced by @data_size; the converter performs
+ * the actual typed load/store. Sets buf_left_final to the number of
+ * bytes that where left outstanding after conversion. Can be > 0.
+ *
+ * Returns 0 on success. Non-zero on error.
*/
-static int do_proc_vec(const struct ctl_table *table, int dir,
- void *buffer, size_t *lenp, loff_t *ppos,
- enum proc_vec_type type, union proc_vec_conv conv)
+static int apply_conv_on_vec(const union proc_vec_conv conv,
+ const struct ctl_table *table,
+ const enum proc_vec_type data_type,
+ const size_t data_size, const int conv_dir,
+ const size_t buf_nbyte, void *buf,
+ size_t *buf_left_final)
{
- int vleft, first = 1, err = 0;
- size_t left, size;
- bool is_unsigned;
- char *i, *p;
+ int vec_left, first = 1, err = 0;
+ size_t buf_left;
+ char *data, *p;
+ bool is_unsigned = data_type == PROC_VEC_UINT || data_type == PROC_VEC_ULONG;
- switch (type) {
- case PROC_VEC_INT:
- size = sizeof(int);
- is_unsigned = false;
- break;
- case PROC_VEC_UINT:
- size = sizeof(uint);
- is_unsigned = true;
- break;
- case PROC_VEC_ULONG:
- size = sizeof(ulong);
- is_unsigned = true;
- break;
- default:
- return -EINVAL;
- }
-
- if (!table->data || !table->maxlen || !*lenp ||
- (*ppos && SYSCTL_KERN_TO_USER(dir))) {
- *lenp = 0;
- return 0;
- }
-
- i = table->data;
- vleft = table->maxlen / size;
- left = *lenp;
-
- /* uint arrays are not supported, *Do not* add support for them. */
- if (type == PROC_VEC_UINT && vleft != 1)
- return -EINVAL;
-
- if (SYSCTL_USER_TO_KERN(dir)) {
- if (proc_first_pos_non_zero_ignore(ppos, table))
- goto out;
+ data = table->data;
+ vec_left = table->maxlen / data_size;
+ buf_left = buf_nbyte;
- if (left > PAGE_SIZE - 1)
- left = PAGE_SIZE - 1;
- p = buffer;
+ if (SYSCTL_USER_TO_KERN(conv_dir)) {
+ if (buf_left > PAGE_SIZE - 1)
+ buf_left = PAGE_SIZE - 1;
+ p = buf;
}
- for (; left && vleft--; i += size, first = 0) {
+ for (; buf_left && vec_left--; data += data_size, first = 0) {
unsigned long lval;
bool neg = false;
- if (SYSCTL_USER_TO_KERN(dir)) {
- proc_skip_spaces(&p, &left);
+ if (SYSCTL_USER_TO_KERN(conv_dir)) {
+ proc_skip_spaces(&p, &buf_left);
- if (!left)
+ if (!buf_left)
break;
- err = proc_get_long(&p, &left, &lval, &neg,
+ err = proc_get_long(&p, &buf_left, &lval, &neg,
proc_wspace_sep,
sizeof(proc_wspace_sep), NULL);
if (!err && neg && is_unsigned)
err = -EINVAL;
if (err)
break;
- if (proc_vec_conv(type, conv, &neg, &lval, i, dir, table)) {
+ if (proc_vec_conv(data_type, conv, &neg, &lval, data, conv_dir, table)) {
err = -EINVAL;
break;
}
} else {
- if (proc_vec_conv(type, conv, &neg, &lval, i, dir, table)) {
+ if (proc_vec_conv(data_type, conv, &neg, &lval, data, conv_dir, table)) {
err = -EINVAL;
break;
}
if (!first)
- proc_put_char(&buffer, &left, '\t');
- proc_put_long(&buffer, &left, lval, neg);
+ proc_put_char(&buf, &buf_left, '\t');
+ proc_put_long(&buf, &buf_left, lval, neg);
}
}
- if (SYSCTL_KERN_TO_USER(dir) && !first && left && !err)
- proc_put_char(&buffer, &left, '\n');
- if (SYSCTL_USER_TO_KERN(dir) && !err && left)
- proc_skip_spaces(&p, &left);
- if (SYSCTL_USER_TO_KERN(dir) && first)
+ if (SYSCTL_KERN_TO_USER(conv_dir) && !first && buf_left && !err)
+ proc_put_char(&buf, &buf_left, '\n');
+ if (SYSCTL_USER_TO_KERN(conv_dir) && !err && buf_left)
+ proc_skip_spaces(&p, &buf_left);
+ if (SYSCTL_USER_TO_KERN(conv_dir) && first)
return err ? : -EINVAL;
- *lenp -= left;
+ *buf_left_final = buf_left;
+
+ return err;
+}
+
+/* Read/write a vector of @type elements. */
+static int proc_vec(const struct ctl_table *table, int dir, void *buffer,
+ size_t *lenp, loff_t *ppos, enum proc_vec_type type,
+ union proc_vec_conv conv)
+{
+ int err = 0;
+ size_t data_size, left_nbyte = SIZE_MAX;
+
+ switch (type) {
+ case PROC_VEC_INT:
+ data_size = sizeof(int);
+ break;
+ case PROC_VEC_UINT:
+ data_size = sizeof(uint);
+ break;
+ case PROC_VEC_ULONG:
+ data_size = sizeof(ulong);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (!table->data || !table->maxlen || !*lenp ||
+ (*ppos && SYSCTL_KERN_TO_USER(dir))) {
+ *lenp = 0;
+ return 0;
+ }
+
+ /* uint arrays are not supported, *Do not* add support for them. */
+ if (type == PROC_VEC_UINT && (table->maxlen / data_size) != 1)
+ return -EINVAL;
+
+ if (SYSCTL_USER_TO_KERN(dir)) {
+ if (proc_first_pos_non_zero_ignore(ppos, table))
+ goto out;
+ }
+
+ err = apply_conv_on_vec(conv, table, type, data_size, dir, *lenp, buffer,
+ &left_nbyte);
+
+ /*
+ * An unchanged left_nbyte signals a write with no parsed element; which
+ * is an error. Using SIZE_MAX to detect this error is possible because:
+ * 1. lenp is bounded by KMALLOC_MAX_SIZE in proc_sys_call_handler
+ * 2. lenp could never be SIZE_MAX as it is a "ridiculous" (exabyte) allocation.
+ */
+ if (left_nbyte == SIZE_MAX)
+ return err;
+
+ *lenp -= left_nbyte;
out:
*ppos += *lenp;
+
return err;
}
@@ -760,8 +792,8 @@ int proc_douintvec_conv(const struct ctl_table *table, int dir, void *buffer,
if (!conv)
conv = do_proc_uint_conv;
- return do_proc_vec(table, dir, buffer, lenp, ppos, PROC_VEC_UINT,
- (union proc_vec_conv){ .uint_conv = conv });
+ return proc_vec(table, dir, buffer, lenp, ppos, PROC_VEC_UINT,
+ (union proc_vec_conv){ .uint_conv = conv });
}
/**
@@ -820,8 +852,8 @@ int proc_dobool(const struct ctl_table *table, int dir, void *buffer,
int proc_dointvec(const struct ctl_table *table, int dir, void *buffer,
size_t *lenp, loff_t *ppos)
{
- return do_proc_vec(table, dir, buffer, lenp, ppos, PROC_VEC_INT,
- (union proc_vec_conv){ .int_conv = do_proc_int_conv });
+ return proc_vec(table, dir, buffer, lenp, ppos, PROC_VEC_INT,
+ (union proc_vec_conv){ .int_conv = do_proc_int_conv });
}
/**
@@ -840,8 +872,8 @@ int proc_dointvec(const struct ctl_table *table, int dir, void *buffer,
int proc_douintvec(const struct ctl_table *table, int dir, void *buffer,
size_t *lenp, loff_t *ppos)
{
- return do_proc_vec(table, dir, buffer, lenp, ppos, PROC_VEC_UINT,
- (union proc_vec_conv){ .uint_conv = do_proc_uint_conv });
+ return proc_vec(table, dir, buffer, lenp, ppos, PROC_VEC_UINT,
+ (union proc_vec_conv){ .uint_conv = do_proc_uint_conv });
}
/**
@@ -864,8 +896,8 @@ int proc_douintvec(const struct ctl_table *table, int dir, void *buffer,
int proc_dointvec_minmax(const struct ctl_table *table, int dir,
void *buffer, size_t *lenp, loff_t *ppos)
{
- return do_proc_vec(table, dir, buffer, lenp, ppos, PROC_VEC_INT,
- (union proc_vec_conv){ .int_conv = do_proc_int_conv_minmax });
+ return proc_vec(table, dir, buffer, lenp, ppos, PROC_VEC_INT,
+ (union proc_vec_conv){ .int_conv = do_proc_int_conv_minmax });
}
/**
@@ -891,8 +923,8 @@ int proc_dointvec_minmax(const struct ctl_table *table, int dir,
int proc_douintvec_minmax(const struct ctl_table *table, int dir,
void *buffer, size_t *lenp, loff_t *ppos)
{
- return do_proc_vec(table, dir, buffer, lenp, ppos, PROC_VEC_UINT,
- (union proc_vec_conv){ .uint_conv = do_proc_uint_conv_minmax });
+ return proc_vec(table, dir, buffer, lenp, ppos, PROC_VEC_UINT,
+ (union proc_vec_conv){ .uint_conv = do_proc_uint_conv_minmax });
}
/**
@@ -935,8 +967,8 @@ int proc_dou8vec_minmax(const struct ctl_table *table, int dir,
tmp.extra2 = (unsigned int *) &max;
val = READ_ONCE(*data);
- res = do_proc_vec(&tmp, dir, buffer, lenp, ppos, PROC_VEC_UINT,
- (union proc_vec_conv){ .uint_conv = do_proc_uint_conv_minmax });
+ res = proc_vec(&tmp, dir, buffer, lenp, ppos, PROC_VEC_UINT,
+ (union proc_vec_conv){ .uint_conv = do_proc_uint_conv_minmax });
if (res)
return res;
if (SYSCTL_USER_TO_KERN(dir))
@@ -1066,8 +1098,8 @@ int proc_doulongvec_conv(const struct ctl_table *table, int dir,
int (*conv)(bool *negp, ulong *u_ptr, ulong *k_ptr,
int dir, const struct ctl_table *table))
{
- return do_proc_vec(table, dir, buffer, lenp, ppos, PROC_VEC_ULONG,
- (union proc_vec_conv){ .ulong_conv = conv });
+ return proc_vec(table, dir, buffer, lenp, ppos, PROC_VEC_ULONG,
+ (union proc_vec_conv){ .ulong_conv = conv });
}
/**
@@ -1087,10 +1119,10 @@ int proc_doulongvec_conv(const struct ctl_table *table, int dir,
* Returns: %0 on success.
*/
int proc_doulongvec_minmax(const struct ctl_table *table, int dir,
- void *buffer, size_t *lenp, loff_t *ppos)
+ void *buffer, size_t *lenp, loff_t *ppos)
{
- return do_proc_vec(table, dir, buffer, lenp, ppos, PROC_VEC_ULONG,
- (union proc_vec_conv){ .ulong_conv = do_proc_ulong_conv });
+ return proc_vec(table, dir, buffer, lenp, ppos, PROC_VEC_ULONG,
+ (union proc_vec_conv){ .ulong_conv = do_proc_ulong_conv });
}
/**
@@ -1114,8 +1146,8 @@ int proc_dointvec_conv(const struct ctl_table *table, int dir, void *buffer,
{
if (!conv)
conv = do_proc_int_conv;
- return do_proc_vec(table, dir, buffer, lenp, ppos, PROC_VEC_INT,
- (union proc_vec_conv){ .int_conv = conv });
+ return proc_vec(table, dir, buffer, lenp, ppos, PROC_VEC_INT,
+ (union proc_vec_conv){ .int_conv = conv });
}
/**
--
2.50.1
next prev parent reply other threads:[~2026-08-13 12:19 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-13 12:18 [PATCH 0/4] sysctl: Disallow partial updates of miss-formatted sysctl vectors Joel Granados
2026-08-13 12:18 ` Joel Granados [this message]
2026-08-13 12:18 ` [PATCH 2/4] sysctl: Reject uint arrays before calling the general proc_vec Joel Granados
2026-08-13 12:18 ` [PATCH 3/4] sysctl: Disallow partial updates for erroneous sysctl vectors Joel Granados
2026-08-13 12:18 ` [PATCH 4/4] sysctl: Add 0013 to test partially updated vectors Joel Granados
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=20260813-lklm-partial_ctlvec-v1-1-df9e51c13704@kernel.org \
--to=joel.granados@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=jackmanb@google.com \
--cc=kees@kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@suse.com \
--cc=shijianlin11@foxmail.com \
--cc=shuah@kernel.org \
--cc=surenb@google.com \
--cc=vbabka@kernel.org \
--cc=ziy@nvidia.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.