[PATCH 1/7] scsi: sg and st: account the command buffer memory to memcg

[Tao Cui <cui.tao@linux.dev>]

From: Tao Cui <cuitao@kylinos.cn>

The sg data buffers are unaccounted: the per-fd reserved buffer, the
scatter-gather page array, and the order-0..N pages behind it, plus the
per-device tape buffer in st.  All of it is user controllable.  The
reserved size is capped only by the device max_sectors, SG_MAX_QUEUE
(16) commands can be in flight per fd, and the fd count is bounded by
RLIMIT_NOFILE.  Nothing is charged to the memcg of the process driving
it.  The September 2026 fixes in sg_build_indirect reshaped the element
sizing and left the accounting alone.

Mark these allocations __GFP_ACCOUNT so the driving process pays for
the memory it induces.

Signed-off-by: Tao Cui <cuitao@kylinos.cn>
---
 drivers/scsi/sg.c | 23 ++++++++++++++++++++---
 drivers/scsi/st.c |  7 ++++---
 2 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 6551f1284d44..9c1414479b21 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -911,6 +911,19 @@ static int put_compat_request_table(struct compat_sg_req_info __user *o,
 }
 #endif
 
+/*
+ * The sg passthrough of the blktrace ioctls has the same exposure as the
+ * block device path: holding the node is the only requirement today, and
+ * a created trace outlives the fd.  Must match the gate in
+ * blk_trace_ioctl().
+ */
+static bool sg_is_blktrace_cmd(unsigned int cmd)
+{
+	return cmd == BLKTRACESETUP || cmd == BLKTRACESETUP2 ||
+	       cmd == BLKTRACESTART || cmd == BLKTRACESTOP ||
+	       cmd == BLKTRACETEARDOWN;
+}
+
 static long
 sg_ioctl_common(struct file *filp, Sg_device *sdp, Sg_fd *sfp,
 		unsigned int cmd_in, void __user *p)
@@ -920,6 +933,9 @@ sg_ioctl_common(struct file *filp, Sg_device *sdp, Sg_fd *sfp,
 	Sg_request *srp;
 	unsigned long iflags;
 
+	if (sg_is_blktrace_cmd(cmd_in) && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
 	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
 				   "sg_ioctl: cmd=0x%x\n", (int) cmd_in));
 	read_only = (O_RDWR != (filp->f_flags & O_ACCMODE));
@@ -1829,7 +1845,7 @@ static int
 sg_build_sgat(Sg_scatter_hold * schp, const Sg_fd * sfp, int tablesize)
 {
 	int sg_bufflen = tablesize * sizeof(struct page *);
-	gfp_t gfp_flags = GFP_ATOMIC | __GFP_NOWARN;
+	gfp_t gfp_flags = GFP_ATOMIC | __GFP_NOWARN | __GFP_ACCOUNT;
 
 	schp->pages = kzalloc(sg_bufflen, gfp_flags);
 	if (!schp->pages)
@@ -1844,7 +1860,8 @@ sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size)
 	int ret_sz = 0, i, k, rem_sz, num, mx_sc_elems;
 	int sg_tablesize = sfp->parentdp->sg_tablesize;
 	int blk_size = buff_size, order;
-	gfp_t gfp_mask = GFP_ATOMIC | __GFP_COMP | __GFP_NOWARN | __GFP_ZERO;
+	gfp_t gfp_mask = GFP_ATOMIC | __GFP_COMP | __GFP_NOWARN |
+			 __GFP_ACCOUNT | __GFP_ZERO;
 
 	if (blk_size < 0)
 		return -EFAULT;
@@ -2134,7 +2151,7 @@ sg_add_sfp(Sg_device * sdp)
 	unsigned long iflags;
 	int bufflen;
 
-	sfp = kzalloc_obj(*sfp, GFP_ATOMIC | __GFP_NOWARN);
+	sfp = kzalloc_obj(*sfp, GFP_ATOMIC | __GFP_NOWARN | __GFP_ACCOUNT);
 	if (!sfp)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index e9d41e3cc2dd..b92633ab2757 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -4074,7 +4074,7 @@ static struct st_buffer *new_tape_buffer(int max_sg)
 {
 	struct st_buffer *tb;
 
-	tb = kzalloc_obj(struct st_buffer);
+	tb = kzalloc_obj(struct st_buffer, GFP_KERNEL_ACCOUNT);
 	if (!tb) {
 		printk(KERN_NOTICE "st: Can't allocate new tape buffer.\n");
 		return NULL;
@@ -4083,7 +4083,8 @@ static struct st_buffer *new_tape_buffer(int max_sg)
 	tb->use_sg = max_sg;
 	tb->buffer_size = 0;
 
-	tb->reserved_pages = kzalloc_objs(struct page *, max_sg);
+	tb->reserved_pages = kzalloc_objs(struct page *, max_sg,
+					  GFP_KERNEL_ACCOUNT);
 	if (!tb->reserved_pages) {
 		kfree(tb);
 		return NULL;
@@ -4109,7 +4110,7 @@ static int enlarge_buffer(struct st_buffer * STbuffer, int new_size)
 
 	max_segs = STbuffer->use_sg;
 
-	priority = GFP_KERNEL | __GFP_NOWARN;
+	priority = GFP_KERNEL | __GFP_NOWARN | __GFP_ACCOUNT;
 
 	if (STbuffer->cleared)
 		priority |= __GFP_ZERO;
-- 
2.43.0