[PATCH v4 0/9] s390/vfio_ccw fixes

[PATCH v4 0/9] s390/vfio_ccw fixes

[Eric Farman]

This series addresses some pre-existing issues found in the
s390 vfio_ccw (DASD passthrough) driver.

v1: https://lore.kernel.org/r/20260714232208.1683788-1-farman@linux.ibm.com/
v2: https://lore.kernel.org/r/20260720201931.976660-1-farman@linux.ibm.com/
v3: https://lore.kernel.org/r/20260723174751.1180334-1-farman@linux.ibm.com/
v3->v4:
 - [MR] Added r-b where provided (thank you!)
 - [MR] Make ccwchain_count unsigned
 - [MR] Reworked loop in ccwchain_calc_length()
 - [MR] Add boundary check before nospec clamp in async, crw, and schib regions
 - [MR] Add lockdep assertions where appropriate
 - [EF/MR] Add definitions of new fields in channel_program and vfio_ccw_private
 - [sashiko/MR] Fix calculation of DMA address between Format-1 and Format-2 IDA
 - [NEW][sashiko/EF] Defer cp_free() from fsm_notoper(), so it can be called
   while holding sch->lock, without needing to dance with private->cp_mutex

Eric Farman (9):
  s390/vfio_ccw: free all memory if cp_init() fails
  s390/vfio_ccw: limit the number of channel program segments
  s390/vfio_ccw: fix out of bounds check on CCW array
  s390/vfio_ccw: ensure first IDAW remains constant
  s390/vfio_ccw: calculate idal length based on idaw type
  s390/vfio_ccw: ensure index for read/write regions are within range
  s390/vfio_ccw: move cp cleanup out of not operational
  s390/vfio_ccw: implement a channel program mutex
  s390/vfio_ccw: implement a crw lock

 drivers/s390/cio/vfio_ccw_async.c   | 16 +++++
 drivers/s390/cio/vfio_ccw_chp.c     | 30 +++++++--
 drivers/s390/cio/vfio_ccw_cp.c      | 96 ++++++++++++++++++++++-------
 drivers/s390/cio/vfio_ccw_cp.h      | 10 +++
 drivers/s390/cio/vfio_ccw_drv.c     | 19 ++++++
 drivers/s390/cio/vfio_ccw_fsm.c     | 23 ++++---
 drivers/s390/cio/vfio_ccw_ops.c     | 21 +++++--
 drivers/s390/cio/vfio_ccw_private.h | 10 +++
 8 files changed, 184 insertions(+), 41 deletions(-)

-- 
2.53.0

[PATCH v4 1/9] s390/vfio_ccw: free all memory if cp_init() fails

[Eric Farman]

The routine cp_free() is called to unpin/free any memory once an I/O
is completed successfully, or if cp_prefetch() fails. But if cp_init()
fails, and cp->initialized is not enabled, the same routine cannot be
used to free all the memory.

An attempt to address this exists in ccwchain_handle_ccw(), where a
single call to ccwchain_free() is made for the currently-processed
CCW segment. But this will leak other segments (created as a result
of a Transfer in Channel) that had been allocated as part of the same
channel program.

Address this by performing the cleanup outside of the recursive
ccwchain_handle_ccw()/ccwchain_loop_tic() logic.

Fixes: 8b515be512a2 ("vfio-ccw: Fix memory leak and don't call cp_free in cp_init")
Cc: stable@vger.kernel.org
Reviewed-by: Farhan Ali<alifm@linux.ibm.com>
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Eric Farman <farman@linux.ibm.com>
---
 drivers/s390/cio/vfio_ccw_cp.c | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index 7561aa7d3e01..086d1b54bdb0 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -455,9 +455,6 @@ static int ccwchain_handle_ccw(dma32_t cda, struct channel_program *cp)
 	/* Loop for tics on this new chain. */
 	ret = ccwchain_loop_tic(chain, cp);
 
-	if (ret)
-		ccwchain_free(chain);
-
 	return ret;
 }
 
@@ -486,6 +483,23 @@ static int ccwchain_loop_tic(struct ccwchain *chain, struct channel_program *cp)
 	return 0;
 }
 
+static int ccwchain_build_ccws(dma32_t cda, struct channel_program *cp)
+{
+	struct ccwchain *chain, *temp;
+	int ret;
+
+	ret = ccwchain_handle_ccw(cda, cp);
+
+	if (ret) {
+		/* Cleanup if an error occurred */
+		list_for_each_entry_safe(chain, temp, &cp->ccwchain_list, next) {
+			ccwchain_free(chain);
+		}
+	}
+
+	return ret;
+}
+
 static int ccwchain_fetch_tic(struct ccw1 *ccw,
 			      struct channel_program *cp)
 {
@@ -735,7 +749,7 @@ int cp_init(struct channel_program *cp, union orb *orb)
 	memcpy(&cp->orb, orb, sizeof(*orb));
 
 	/* Build a ccwchain for the first CCW segment */
-	ret = ccwchain_handle_ccw(orb->cmd.cpa, cp);
+	ret = ccwchain_build_ccws(orb->cmd.cpa, cp);
 
 	if (!ret)
 		cp->initialized = true;
-- 
2.53.0

[PATCH v4 2/9] s390/vfio_ccw: limit the number of channel program segments

[Eric Farman]

The processing of channel programs, and the CCWs within them, is done
recursively. As such, there is an arbitrary (but not architectural)
limit to the number of CCWs that can exist in a single channel program.

The vfio-ccw logic breaks these channel programs into segments whenever
it encounters a Transfer-In-Channel (TIC) CCW, and the combined number
of segments count towards the global limit. Impose an equivalent limit
to the number of segments until such logic can be made non-recursive.

Fixes: 0a19e61e6d4c ("vfio: ccw: introduce channel program interfaces")
Cc: stable@vger.kernel.org
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Eric Farman <farman@linux.ibm.com>
---
 drivers/s390/cio/vfio_ccw_cp.c | 6 ++++++
 drivers/s390/cio/vfio_ccw_cp.h | 8 ++++++++
 2 files changed, 14 insertions(+)

diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index 086d1b54bdb0..1c2890d139c6 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -332,6 +332,7 @@ static struct ccwchain *ccwchain_alloc(struct channel_program *cp, int len)
 		goto out_err;
 
 	list_add_tail(&chain->next, &cp->ccwchain_list);
+	cp->ccwchain_count++;
 
 	return chain;
 
@@ -441,6 +442,10 @@ static int ccwchain_handle_ccw(dma32_t cda, struct channel_program *cp)
 	if (len < 0)
 		return len;
 
+	/* Limit number of chains in a single channel program */
+	if (cp->ccwchain_count >= CCWCHAIN_COUNT_MAX)
+		return -EINVAL;
+
 	/* Need alloc a new chain for this one. */
 	chain = ccwchain_alloc(cp, len);
 	if (!chain)
@@ -745,6 +750,7 @@ int cp_init(struct channel_program *cp, union orb *orb)
 			vdev->dev,
 			"Prefetching channel program even though prefetch not specified in ORB");
 
+	cp->ccwchain_count = 0;
 	INIT_LIST_HEAD(&cp->ccwchain_list);
 	memcpy(&cp->orb, orb, sizeof(*orb));
 
diff --git a/drivers/s390/cio/vfio_ccw_cp.h b/drivers/s390/cio/vfio_ccw_cp.h
index fc31eb699807..a9b1d8dbc6f6 100644
--- a/drivers/s390/cio/vfio_ccw_cp.h
+++ b/drivers/s390/cio/vfio_ccw_cp.h
@@ -23,11 +23,18 @@
  */
 #define CCWCHAIN_LEN_MAX	256
 
+/*
+ * Maximum number of chains
+ */
+#define CCWCHAIN_COUNT_MAX	16
+
 /**
  * struct channel_program - manage information for channel program
  * @ccwchain_list: list head of ccwchains
  * @orb: orb for the currently processed ssch request
  * @initialized: whether this instance is actually initialized
+ * @guest_cp: copy of guest channel program
+ * @ccwchain_count: number of channel program segments (linked by TIC)
  *
  * @ccwchain_list is the head of a ccwchain list, that contents the
  * translated result of the guest channel program that pointed out by
@@ -38,6 +45,7 @@ struct channel_program {
 	union orb orb;
 	bool initialized;
 	struct ccw1 *guest_cp;
+	unsigned int ccwchain_count;
 };
 
 int cp_init(struct channel_program *cp, union orb *orb);
-- 
2.53.0

[PATCH v4 3/9] s390/vfio_ccw: fix out of bounds check on CCW array

[Eric Farman]

The routine ccwchain_calc_length() counts the number of channel
command words (CCWs) that are chained together in a single channel
program, and rejects anything larger than CCWCHAIN_LEN_MAX (256) CCWs.

The loop itself is "do..while (count < 257)", and while the logic in
is_cpa_within_range() correctly adjusts between the 0-index array of
CCWs and the count of CCWs starting at 1, this means it would look
at a possible 257th CCW before ending the loop and (correctly)
returning an error.

Fix this by restructuring the loop to break as soon as 256 CCWs
(thus indexes 0-255) are examined, without looking at memory
outside the range.

Fixes: 0a19e61e6d4c ("vfio: ccw: introduce channel program interfaces")
Cc: stable@vger.kernel.org
Signed-off-by: Eric Farman <farman@linux.ibm.com>
---
 drivers/s390/cio/vfio_ccw_cp.c | 17 +++++------------
 1 file changed, 5 insertions(+), 12 deletions(-)

diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index 1c2890d139c6..af632f9d5453 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -377,11 +377,9 @@ static void ccwchain_cda_free(struct ccwchain *chain, int idx)
 static int ccwchain_calc_length(u64 iova, struct channel_program *cp)
 {
 	struct ccw1 *ccw = cp->guest_cp;
-	int cnt = 0;
-
-	do {
-		cnt++;
+	int cnt;
 
+	for (cnt = 1; cnt <= CCWCHAIN_LEN_MAX; cnt++, ccw++) {
 		/*
 		 * We want to keep counting if the current CCW has the
 		 * command-chaining flag enabled, or if it is a TIC CCW
@@ -391,15 +389,10 @@ static int ccwchain_calc_length(u64 iova, struct channel_program *cp)
 		 * after the TIC, depending on the results of its operation.
 		 */
 		if (!ccw_is_chain(ccw) && !is_tic_within_range(ccw, iova, cnt))
-			break;
-
-		ccw++;
-	} while (cnt < CCWCHAIN_LEN_MAX + 1);
-
-	if (cnt == CCWCHAIN_LEN_MAX + 1)
-		cnt = -EINVAL;
+			return cnt;
+	}
 
-	return cnt;
+	return -EINVAL;
 }
 
 static int tic_target_chain_exists(struct ccw1 *tic, struct channel_program *cp)
-- 
2.53.0

[PATCH v4 4/9] s390/vfio_ccw: ensure first IDAW remains constant

[Eric Farman]

The first IDAW in a list does not need to be on a 2K/4K boundary
like all others, and so is read separately to accurately calculate
the size of the buffer needed to read the full IDAL.

Verify that the address found in the first IDAW is unchanged between
reads, to ensure a consistent set of IDAWs being worked with.

Fixes: 01aa26c672c0 ("s390/cio: Combine direct and indirect CCW paths")
Cc: stable@vger.kernel.org
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Eric Farman <farman@linux.ibm.com>
---
 drivers/s390/cio/vfio_ccw_cp.c | 16 ++++++++++++++++
 drivers/s390/cio/vfio_ccw_cp.h |  2 ++
 2 files changed, 18 insertions(+)

diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index af632f9d5453..6275794751cb 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -523,6 +523,7 @@ static dma64_t *get_guest_idal(struct ccw1 *ccw, struct channel_program *cp, int
 		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
 	dma64_t *idaws;
 	dma32_t *idaws_f1;
+	u64 first_idaw;
 	int idal_len = idaw_nr * sizeof(*idaws);
 	int idaw_size = idal_is_2k(cp) ? PAGE_SIZE / 2 : PAGE_SIZE;
 	int idaw_mask = ~(idaw_size - 1);
@@ -539,6 +540,18 @@ static dma64_t *get_guest_idal(struct ccw1 *ccw, struct channel_program *cp, int
 			kfree(idaws);
 			return ERR_PTR(ret);
 		}
+
+		idaws_f1 = (dma32_t *)idaws;
+		if (cp->orb.cmd.c64)
+			first_idaw = dma64_to_u64(idaws[0]);
+		else
+			first_idaw = dma32_to_u32(idaws_f1[0]);
+
+		/* Unexpected mismatch from earlier read */
+		if (first_idaw != cp->guest_iova) {
+			kfree(idaws);
+			return ERR_PTR(-EINVAL);
+		}
 	} else {
 		/* Fabricate an IDAL based off CCW data address */
 		if (cp->orb.cmd.c64) {
@@ -604,6 +617,9 @@ static int ccw_count_idaws(struct ccw1 *ccw,
 		iova = dma32_to_u32(ccw->cda);
 	}
 
+	/* Save the read address for later */
+	cp->guest_iova = iova;
+
 	/* Format-1 IDAWs operate on 2K each */
 	if (!cp->orb.cmd.c64)
 		return idal_2k_nr_words((void *)iova, bytes);
diff --git a/drivers/s390/cio/vfio_ccw_cp.h b/drivers/s390/cio/vfio_ccw_cp.h
index a9b1d8dbc6f6..9af98ff12d67 100644
--- a/drivers/s390/cio/vfio_ccw_cp.h
+++ b/drivers/s390/cio/vfio_ccw_cp.h
@@ -35,6 +35,7 @@
  * @initialized: whether this instance is actually initialized
  * @guest_cp: copy of guest channel program
  * @ccwchain_count: number of channel program segments (linked by TIC)
+ * @guest_iova: first data address of a guest channel program
  *
  * @ccwchain_list is the head of a ccwchain list, that contents the
  * translated result of the guest channel program that pointed out by
@@ -46,6 +47,7 @@ struct channel_program {
 	bool initialized;
 	struct ccw1 *guest_cp;
 	unsigned int ccwchain_count;
+	u64 guest_iova;
 };
 
 int cp_init(struct channel_program *cp, union orb *orb);
-- 
2.53.0

[PATCH v4 5/9] s390/vfio_ccw: calculate idal length based on idaw type

[Eric Farman]

Sashiko pointed out that get_guest_idal() unconditionally calculates
the length of the IDAL presuming everything is a Format-2 IDAW.

The output of vfio-ccw is always Format-2, but the input can be either
Format-1 (31-bit addresses) or Format-2 (64-bit addresses). As a result,
the size of the guest IDAL may be incorrect and should be trimmed down.

Reported-by: sashiko-bot <sashiko-bot@kernel.org>
Link: https://lore.kernel.org/r/20260720203400.7328E1F000E9@smtp.kernel.org/
Fixes: 1b676fe3d9d3 ("vfio/ccw: handle a guest Format-1 IDAL")
Cc: stable@vger.kernel.org
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Signed-off-by: Eric Farman <farman@linux.ibm.com>
---
 drivers/s390/cio/vfio_ccw_cp.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index 6275794751cb..5ef082b8289a 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -233,6 +233,7 @@ static void convert_ccw0_to_ccw1(struct ccw1 *source, unsigned long len)
 }
 
 #define idal_is_2k(_cp) (!(_cp)->orb.cmd.c64 || (_cp)->orb.cmd.i2k)
+#define get_idaw_size(_cp) ((_cp)->orb.cmd.c64 ? sizeof(u64) : sizeof(u32))
 
 /*
  * Helpers to operate ccwchain.
@@ -524,7 +525,7 @@ static dma64_t *get_guest_idal(struct ccw1 *ccw, struct channel_program *cp, int
 	dma64_t *idaws;
 	dma32_t *idaws_f1;
 	u64 first_idaw;
-	int idal_len = idaw_nr * sizeof(*idaws);
+	int idal_len = idaw_nr * get_idaw_size(cp);
 	int idaw_size = idal_is_2k(cp) ? PAGE_SIZE / 2 : PAGE_SIZE;
 	int idaw_mask = ~(idaw_size - 1);
 	int i, ret;
@@ -593,7 +594,7 @@ static int ccw_count_idaws(struct ccw1 *ccw,
 	struct vfio_device *vdev =
 		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
 	u64 iova;
-	int size = cp->orb.cmd.c64 ? sizeof(u64) : sizeof(u32);
+	int size = get_idaw_size(cp);
 	int ret;
 	int bytes = 1;
 
-- 
2.53.0

[PATCH v4 6/9] s390/vfio_ccw: ensure index for read/write regions are within range

[Eric Farman]

The introduction of the capability chain rightly clamped the
region indexes to the range of the capabilities itself, but
neglected to do so for the existing read/write regions which
should also be enforced.

Fixes: db8e5d17ac03 ("vfio-ccw: add capabilities chain")
Cc: stable@vger.kernel.org
Cc: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Eric Farman <farman@linux.ibm.com>
---
 drivers/s390/cio/vfio_ccw_async.c | 16 ++++++++++++++++
 drivers/s390/cio/vfio_ccw_chp.c   | 15 +++++++++++++++
 drivers/s390/cio/vfio_ccw_ops.c   |  7 +++----
 3 files changed, 34 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/cio/vfio_ccw_async.c b/drivers/s390/cio/vfio_ccw_async.c
index 420d89ba7f83..4aff0b58fa5d 100644
--- a/drivers/s390/cio/vfio_ccw_async.c
+++ b/drivers/s390/cio/vfio_ccw_async.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/vfio.h>
+#include <linux/nospec.h>
 
 #include "vfio_ccw_private.h"
 
@@ -24,11 +25,20 @@ static ssize_t vfio_ccw_async_region_read(struct vfio_ccw_private *private,
 		return -EINVAL;
 
 	mutex_lock(&private->io_mutex);
+
+	if (i >= private->num_regions) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	i = array_index_nospec(i, private->num_regions);
 	region = private->region[i].data;
 	if (copy_to_user(buf, (void *)region + pos, count))
 		ret = -EFAULT;
 	else
 		ret = count;
+
+out_unlock:
 	mutex_unlock(&private->io_mutex);
 	return ret;
 }
@@ -48,6 +58,12 @@ static ssize_t vfio_ccw_async_region_write(struct vfio_ccw_private *private,
 	if (!mutex_trylock(&private->io_mutex))
 		return -EAGAIN;
 
+	if (i >= private->num_regions) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	i = array_index_nospec(i, private->num_regions);
 	region = private->region[i].data;
 	if (copy_from_user((void *)region + pos, buf, count)) {
 		ret = -EFAULT;
diff --git a/drivers/s390/cio/vfio_ccw_chp.c b/drivers/s390/cio/vfio_ccw_chp.c
index 38c176cf6295..f3015132d4b5 100644
--- a/drivers/s390/cio/vfio_ccw_chp.c
+++ b/drivers/s390/cio/vfio_ccw_chp.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/slab.h>
+#include <linux/nospec.h>
 #include <linux/vfio.h>
 #include "vfio_ccw_private.h"
 
@@ -26,6 +27,13 @@ static ssize_t vfio_ccw_schib_region_read(struct vfio_ccw_private *private,
 		return -EINVAL;
 
 	mutex_lock(&private->io_mutex);
+
+	if (i >= private->num_regions) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	i = array_index_nospec(i, private->num_regions);
 	region = private->region[i].data;
 
 	if (cio_update_schib(sch)) {
@@ -97,6 +105,12 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private,
 		list_del(&crw->next);
 
 	mutex_lock(&private->io_mutex);
+	if (i >= private->num_regions) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	i = array_index_nospec(i, private->num_regions);
 	region = private->region[i].data;
 
 	if (crw)
@@ -109,6 +123,7 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private,
 
 	region->crw = 0;
 
+out:
 	mutex_unlock(&private->io_mutex);
 
 	kfree(crw);
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index 45ec722d25ea..032a1cdf4df7 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -243,6 +243,7 @@ static ssize_t vfio_ccw_mdev_read(struct vfio_device *vdev,
 		return vfio_ccw_mdev_read_io_region(private, buf, count, ppos);
 	default:
 		index -= VFIO_CCW_NUM_REGIONS;
+		index = array_index_nospec(index, private->num_regions);
 		return private->region[index].ops->read(private, buf, count,
 							ppos);
 	}
@@ -295,6 +296,7 @@ static ssize_t vfio_ccw_mdev_write(struct vfio_device *vdev,
 		return vfio_ccw_mdev_write_io_region(private, buf, count, ppos);
 	default:
 		index -= VFIO_CCW_NUM_REGIONS;
+		index = array_index_nospec(index, private->num_regions);
 		return private->region[index].ops->write(private, buf, count,
 							 ppos);
 	}
@@ -338,11 +340,8 @@ static int vfio_ccw_mdev_ioctl_get_region_info(struct vfio_device *vdev,
 		    VFIO_CCW_NUM_REGIONS + private->num_regions)
 			return -EINVAL;
 
-		info->index = array_index_nospec(info->index,
-						 VFIO_CCW_NUM_REGIONS +
-						 private->num_regions);
-
 		i = info->index - VFIO_CCW_NUM_REGIONS;
+		i = array_index_nospec(i, private->num_regions);
 
 		info->offset = VFIO_CCW_INDEX_TO_OFFSET(info->index);
 		info->size = private->region[i].size;
-- 
2.53.0

[PATCH v4 7/9] s390/vfio_ccw: move cp cleanup out of not operational

[Eric Farman]

The fsm_notoper() routine is called when the device has been
lost, and is (by definition) no longer operational. Since this
can happen asynchronously from the normal behavior of the
driver, the cleanup may happen when holding other locks
in the calling sequence (notably, the cio subchannel lock).

Push the cleanup of the private->cp resources to a workqueue,
where it can be done out from under that lock sequence and
(soon) under its own serialization mechanism.

Fixes: 204b394a23ad ("vfio/ccw: Move FSM open/close to MDEV open/close")
Cc: stable@vger.kernel.org
Signed-off-by: Eric Farman <farman@linux.ibm.com>
---
 drivers/s390/cio/vfio_ccw_drv.c     | 9 +++++++++
 drivers/s390/cio/vfio_ccw_fsm.c     | 3 +--
 drivers/s390/cio/vfio_ccw_ops.c     | 1 +
 drivers/s390/cio/vfio_ccw_private.h | 3 +++
 4 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index 1a095085bc72..c197ad5ab580 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -125,6 +125,15 @@ void vfio_ccw_crw_todo(struct work_struct *work)
 		eventfd_signal(private->crw_trigger);
 }
 
+void vfio_ccw_notoper_todo(struct work_struct *work)
+{
+	struct vfio_ccw_private *private;
+
+	private = container_of(work, struct vfio_ccw_private, notoper_work);
+
+	cp_free(&private->cp);
+}
+
 /*
  * Css driver callbacks
  */
diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
index 4d7988ea47ef..4d47a3c7b9a0 100644
--- a/drivers/s390/cio/vfio_ccw_fsm.c
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -170,8 +170,7 @@ static void fsm_notoper(struct vfio_ccw_private *private,
 	css_sched_sch_todo(sch, SCH_TODO_UNREG);
 	private->state = VFIO_CCW_STATE_NOT_OPER;
 
-	/* This is usually handled during CLOSE event */
-	cp_free(&private->cp);
+	queue_work(vfio_ccw_work_q, &private->notoper_work);
 }
 
 /*
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index 032a1cdf4df7..6c74d596be9d 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -54,6 +54,7 @@ static int vfio_ccw_mdev_init_dev(struct vfio_device *vdev)
 	INIT_LIST_HEAD(&private->crw);
 	INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo);
 	INIT_WORK(&private->crw_work, vfio_ccw_crw_todo);
+	INIT_WORK(&private->notoper_work, vfio_ccw_notoper_todo);
 
 	private->cp.guest_cp = kzalloc_objs(struct ccw1, CCWCHAIN_LEN_MAX);
 	if (!private->cp.guest_cp)
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
index 0501d4bbcdbd..e2256402b089 100644
--- a/drivers/s390/cio/vfio_ccw_private.h
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -102,6 +102,7 @@ struct vfio_ccw_parent {
  * @req_trigger: eventfd ctx for signaling userspace to return device
  * @io_work: work for deferral process of I/O handling
  * @crw_work: work for deferral process of CRW handling
+ * @notoper_work: work for deferred processing in not-operational state
  */
 struct vfio_ccw_private {
 	struct vfio_device vdev;
@@ -125,11 +126,13 @@ struct vfio_ccw_private {
 	struct eventfd_ctx	*req_trigger;
 	struct work_struct	io_work;
 	struct work_struct	crw_work;
+	struct work_struct	notoper_work;
 } __aligned(8);
 
 int vfio_ccw_sch_quiesce(struct subchannel *sch);
 void vfio_ccw_sch_io_todo(struct work_struct *work);
 void vfio_ccw_crw_todo(struct work_struct *work);
+void vfio_ccw_notoper_todo(struct work_struct *work);
 
 extern struct mdev_driver vfio_ccw_mdev_driver;
 
-- 
2.53.0

[PATCH v4 8/9] s390/vfio_ccw: implement a channel program mutex

[Eric Farman]

The channel_program struct is manipulated without a serialization
mechanism to ensure consistent behavior. Take a broad stroke of
putting the entire structure behind a mutex, and ensure everything
that needs private->cp holds this mutex.

There are a couple where the cio layer's subchannel->lock performs
this role in this code, which isn't correct (it should only be used
when touching the actual subchannel, like cio_enable_subchannel()),
so adjust the locations where that spinlock is acquired/released
to correctly coexist with this new mutex.

Fixes: 0a19e61e6d4c ("vfio: ccw: introduce channel program interfaces")
Cc: stable@vger.kernel.org
Signed-off-by: Eric Farman <farman@linux.ibm.com>
---
 drivers/s390/cio/vfio_ccw_cp.c      | 30 +++++++++++++++++++++++++----
 drivers/s390/cio/vfio_ccw_drv.c     |  6 ++++++
 drivers/s390/cio/vfio_ccw_fsm.c     | 20 ++++++++++++-------
 drivers/s390/cio/vfio_ccw_ops.c     | 10 +++++++++-
 drivers/s390/cio/vfio_ccw_private.h |  3 +++
 5 files changed, 57 insertions(+), 12 deletions(-)

diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index 5ef082b8289a..ab66caff9894 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -738,12 +738,15 @@ static int ccwchain_fetch_one(struct ccw1 *ccw,
  */
 int cp_init(struct channel_program *cp, union orb *orb)
 {
-	struct vfio_device *vdev =
-		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
+	struct vfio_ccw_private *private =
+		container_of(cp, struct vfio_ccw_private, cp);
+	struct vfio_device *vdev = &private->vdev;
 	/* custom ratelimit used to avoid flood during guest IPL */
 	static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 1);
 	int ret;
 
+	lockdep_assert_held(&private->cp_mutex);
+
 	/* this is an error in the caller */
 	if (cp->initialized)
 		return -EBUSY;
@@ -784,11 +787,14 @@ int cp_init(struct channel_program *cp, union orb *orb)
  */
 void cp_free(struct channel_program *cp)
 {
-	struct vfio_device *vdev =
-		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
+	struct vfio_ccw_private *private =
+		container_of(cp, struct vfio_ccw_private, cp);
+	struct vfio_device *vdev = &private->vdev;
 	struct ccwchain *chain, *temp;
 	int i;
 
+	lockdep_assert_held(&private->cp_mutex);
+
 	if (!cp->initialized)
 		return;
 
@@ -841,11 +847,15 @@ void cp_free(struct channel_program *cp)
  */
 int cp_prefetch(struct channel_program *cp)
 {
+	struct vfio_ccw_private *private =
+		container_of(cp, struct vfio_ccw_private, cp);
 	struct ccwchain *chain;
 	struct ccw1 *ccw;
 	struct page_array *pa;
 	int len, idx, ret;
 
+	lockdep_assert_held(&private->cp_mutex);
+
 	/* this is an error in the caller */
 	if (!cp->initialized)
 		return -EINVAL;
@@ -883,10 +893,14 @@ int cp_prefetch(struct channel_program *cp)
  */
 union orb *cp_get_orb(struct channel_program *cp, struct subchannel *sch)
 {
+	struct vfio_ccw_private *private =
+		container_of(cp, struct vfio_ccw_private, cp);
 	union orb *orb;
 	struct ccwchain *chain;
 	struct ccw1 *cpa;
 
+	lockdep_assert_held(&private->cp_mutex);
+
 	/* this is an error in the caller */
 	if (!cp->initialized)
 		return NULL;
@@ -931,10 +945,14 @@ union orb *cp_get_orb(struct channel_program *cp, struct subchannel *sch)
  */
 void cp_update_scsw(struct channel_program *cp, union scsw *scsw)
 {
+	struct vfio_ccw_private *private =
+		container_of(cp, struct vfio_ccw_private, cp);
 	struct ccwchain *chain;
 	dma32_t cpa = scsw->cmd.cpa;
 	u32 ccw_head;
 
+	lockdep_assert_held(&private->cp_mutex);
+
 	if (!cp->initialized)
 		return;
 
@@ -977,9 +995,13 @@ void cp_update_scsw(struct channel_program *cp, union scsw *scsw)
  */
 bool cp_iova_pinned(struct channel_program *cp, u64 iova, u64 length)
 {
+	struct vfio_ccw_private *private =
+		container_of(cp, struct vfio_ccw_private, cp);
 	struct ccwchain *chain;
 	int i;
 
+	lockdep_assert_held(&private->cp_mutex);
+
 	if (!cp->initialized)
 		return false;
 
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index c197ad5ab580..4830f0dd9c3a 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -91,6 +91,8 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
 
 	is_final = !(scsw_actl(&irb->scsw) &
 		     (SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT));
+
+	mutex_lock(&private->cp_mutex);
 	if (scsw_is_solicited(&irb->scsw)) {
 		cp_update_scsw(&private->cp, &irb->scsw);
 		if (is_final && private->state == VFIO_CCW_STATE_CP_PENDING) {
@@ -98,6 +100,8 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
 			cp_is_finished = true;
 		}
 	}
+	mutex_unlock(&private->cp_mutex);
+
 	mutex_lock(&private->io_mutex);
 	memcpy(private->io_region->irb_area, irb, sizeof(*irb));
 	mutex_unlock(&private->io_mutex);
@@ -131,7 +135,9 @@ void vfio_ccw_notoper_todo(struct work_struct *work)
 
 	private = container_of(work, struct vfio_ccw_private, notoper_work);
 
+	mutex_lock(&private->cp_mutex);
 	cp_free(&private->cp);
+	mutex_unlock(&private->cp_mutex);
 }
 
 /*
diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
index 4d47a3c7b9a0..cefdfcb0cad7 100644
--- a/drivers/s390/cio/vfio_ccw_fsm.c
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -25,17 +25,15 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
 	unsigned long flags;
 	int ret;
 
-	spin_lock_irqsave(&sch->lock, flags);
-
 	orb = cp_get_orb(&private->cp, sch);
-	if (!orb) {
-		ret = -EIO;
-		goto out;
-	}
+	if (!orb)
+		return -EIO;
 
 	VFIO_CCW_TRACE_EVENT(5, "stIO");
 	VFIO_CCW_TRACE_EVENT(5, dev_name(&sch->dev));
 
+	spin_lock_irqsave(&sch->lock, flags);
+
 	/* Issue "Start Subchannel" */
 	ccode = ssch(sch->schid, orb);
 
@@ -71,7 +69,6 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
 	default:
 		ret = ccode;
 	}
-out:
 	spin_unlock_irqrestore(&sch->lock, flags);
 	return ret;
 }
@@ -251,6 +248,8 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 	private->state = VFIO_CCW_STATE_CP_PROCESSING;
 	memcpy(scsw, io_region->scsw_area, sizeof(*scsw));
 
+	mutex_lock(&private->cp_mutex);
+
 	if (scsw->cmd.fctl & SCSW_FCTL_START_FUNC) {
 		orb = (union orb *)io_region->orb_area;
 
@@ -299,6 +298,8 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 			cp_free(&private->cp);
 			goto err_out;
 		}
+
+		mutex_unlock(&private->cp_mutex);
 		return;
 	} else if (scsw->cmd.fctl & SCSW_FCTL_HALT_FUNC) {
 		VFIO_CCW_MSG_EVENT(2,
@@ -319,6 +320,7 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 	}
 
 err_out:
+	mutex_unlock(&private->cp_mutex);
 	private->state = VFIO_CCW_STATE_IDLE;
 	trace_vfio_ccw_fsm_io_request(scsw->cmd.fctl, schid,
 				      io_region->ret_code, errstr);
@@ -409,7 +411,11 @@ static void fsm_close(struct vfio_ccw_private *private,
 
 	private->state = VFIO_CCW_STATE_STANDBY;
 	spin_unlock_irq(&sch->lock);
+
+	mutex_lock(&private->cp_mutex);
 	cp_free(&private->cp);
+	mutex_unlock(&private->cp_mutex);
+
 	return;
 
 err_unlock:
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index 6c74d596be9d..9242a37677a0 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -38,8 +38,13 @@ static void vfio_ccw_dma_unmap(struct vfio_device *vdev, u64 iova, u64 length)
 		container_of(vdev, struct vfio_ccw_private, vdev);
 
 	/* Drivers MUST unpin pages in response to an invalidation. */
-	if (!cp_iova_pinned(&private->cp, iova, length))
+	mutex_lock(&private->cp_mutex);
+	if (!cp_iova_pinned(&private->cp, iova, length)) {
+		mutex_unlock(&private->cp_mutex);
 		return;
+	}
+
+	mutex_unlock(&private->cp_mutex);
 
 	vfio_ccw_mdev_reset(private);
 }
@@ -50,6 +55,7 @@ static int vfio_ccw_mdev_init_dev(struct vfio_device *vdev)
 		container_of(vdev, struct vfio_ccw_private, vdev);
 
 	mutex_init(&private->io_mutex);
+	mutex_init(&private->cp_mutex);
 	private->state = VFIO_CCW_STATE_STANDBY;
 	INIT_LIST_HEAD(&private->crw);
 	INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo);
@@ -91,6 +97,7 @@ static int vfio_ccw_mdev_init_dev(struct vfio_device *vdev)
 out_free_cp:
 	kfree(private->cp.guest_cp);
 out_free_private:
+	mutex_destroy(&private->cp_mutex);
 	mutex_destroy(&private->io_mutex);
 	return -ENOMEM;
 }
@@ -142,6 +149,7 @@ static void vfio_ccw_mdev_release_dev(struct vfio_device *vdev)
 	kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
 	kmem_cache_free(vfio_ccw_io_region, private->io_region);
 	kfree(private->cp.guest_cp);
+	mutex_destroy(&private->cp_mutex);
 	mutex_destroy(&private->io_mutex);
 }
 
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
index e2256402b089..b595fd81f370 100644
--- a/drivers/s390/cio/vfio_ccw_private.h
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -94,6 +94,7 @@ struct vfio_ccw_parent {
  * @schib_region: MMIO region for SCHIB information
  * @crw_region: MMIO region for getting channel report words
  * @num_regions: number of additional regions
+ * @cp_mutex: protect against concurrent update of CP resources
  * @cp: channel program for the current I/O operation
  * @irb: irb info received from interrupt
  * @scsw: scsw info
@@ -116,7 +117,9 @@ struct vfio_ccw_private {
 	struct ccw_crw_region	*crw_region;
 	int num_regions;
 
+	struct mutex		cp_mutex;
 	struct channel_program	cp;
+
 	struct irb		irb;
 	union scsw		scsw;
 	struct list_head	crw;
-- 
2.53.0

[PATCH v4 9/9] s390/vfio_ccw: implement a crw lock

[Eric Farman]

Unlike the channel_program struct, which covers synchronous I/O
submissions and asynchronous interrupts, the CRW region relies
exclusively on asynchronous events coming from hardware.

Implement a lock to manage the list of those payloads, to ensure
they are read cohesively.

Fixes: 3f02cb2fd9d2 ("vfio-ccw: Wire up the CRW irq and CRW region")
Cc: stable@vger.kernel.org
Cc: Farhan Ali <alifm@linux.ibm.com>
Signed-off-by: Eric Farman <farman@linux.ibm.com>
---
 drivers/s390/cio/vfio_ccw_chp.c     | 25 +++++++++++++++----------
 drivers/s390/cio/vfio_ccw_drv.c     |  4 ++++
 drivers/s390/cio/vfio_ccw_ops.c     |  3 +++
 drivers/s390/cio/vfio_ccw_private.h |  4 ++++
 4 files changed, 26 insertions(+), 10 deletions(-)

diff --git a/drivers/s390/cio/vfio_ccw_chp.c b/drivers/s390/cio/vfio_ccw_chp.c
index f3015132d4b5..313c541e83eb 100644
--- a/drivers/s390/cio/vfio_ccw_chp.c
+++ b/drivers/s390/cio/vfio_ccw_chp.c
@@ -98,12 +98,6 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private,
 	if (pos + count > sizeof(*region))
 		return -EINVAL;
 
-	crw = list_first_entry_or_null(&private->crw,
-				       struct vfio_ccw_crw, next);
-
-	if (crw)
-		list_del(&crw->next);
-
 	mutex_lock(&private->io_mutex);
 	if (i >= private->num_regions) {
 		ret = -EINVAL;
@@ -113,6 +107,16 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private,
 	i = array_index_nospec(i, private->num_regions);
 	region = private->region[i].data;
 
+	spin_lock(&private->crw_lock);
+	crw = list_first_entry_or_null(&private->crw,
+				       struct vfio_ccw_crw, next);
+
+	if (crw)
+		list_del(&crw->next);
+
+	/* Drop CRW lock while copying to userspace */
+	spin_unlock(&private->crw_lock);
+
 	if (crw)
 		memcpy(&region->crw, &crw->crw, sizeof(region->crw));
 
@@ -122,15 +126,16 @@ static ssize_t vfio_ccw_crw_region_read(struct vfio_ccw_private *private,
 		ret = count;
 
 	region->crw = 0;
-
-out:
-	mutex_unlock(&private->io_mutex);
-
 	kfree(crw);
 
 	/* Notify the guest if more CRWs are on our queue */
+	spin_lock(&private->crw_lock);
 	if (!list_empty(&private->crw) && private->crw_trigger)
 		eventfd_signal(private->crw_trigger);
+	spin_unlock(&private->crw_lock);
+
+out:
+	mutex_unlock(&private->io_mutex);
 
 	return ret;
 }
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index 4830f0dd9c3a..32f631d08620 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -125,8 +125,10 @@ void vfio_ccw_crw_todo(struct work_struct *work)
 
 	private = container_of(work, struct vfio_ccw_private, crw_work);
 
+	spin_lock(&private->crw_lock);
 	if (!list_empty(&private->crw) && private->crw_trigger)
 		eventfd_signal(private->crw_trigger);
+	spin_unlock(&private->crw_lock);
 }
 
 void vfio_ccw_notoper_todo(struct work_struct *work)
@@ -307,7 +309,9 @@ static void vfio_ccw_queue_crw(struct vfio_ccw_private *private,
 	crw->crw.erc = erc;
 	crw->crw.rsid = rsid;
 
+	spin_lock(&private->crw_lock);
 	list_add_tail(&crw->next, &private->crw);
+	spin_unlock(&private->crw_lock);
 	queue_work(vfio_ccw_work_q, &private->crw_work);
 }
 
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index 9242a37677a0..6735b5f4c07a 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -61,6 +61,7 @@ static int vfio_ccw_mdev_init_dev(struct vfio_device *vdev)
 	INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo);
 	INIT_WORK(&private->crw_work, vfio_ccw_crw_todo);
 	INIT_WORK(&private->notoper_work, vfio_ccw_notoper_todo);
+	spin_lock_init(&private->crw_lock);
 
 	private->cp.guest_cp = kzalloc_objs(struct ccw1, CCWCHAIN_LEN_MAX);
 	if (!private->cp.guest_cp)
@@ -139,10 +140,12 @@ static void vfio_ccw_mdev_release_dev(struct vfio_device *vdev)
 		container_of(vdev, struct vfio_ccw_private, vdev);
 	struct vfio_ccw_crw *crw, *temp;
 
+	spin_lock(&private->crw_lock);
 	list_for_each_entry_safe(crw, temp, &private->crw, next) {
 		list_del(&crw->next);
 		kfree(crw);
 	}
+	spin_unlock(&private->crw_lock);
 
 	kmem_cache_free(vfio_ccw_crw_region, private->crw_region);
 	kmem_cache_free(vfio_ccw_schib_region, private->schib_region);
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
index b595fd81f370..ffa8be7547fe 100644
--- a/drivers/s390/cio/vfio_ccw_private.h
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -98,6 +98,8 @@ struct vfio_ccw_parent {
  * @cp: channel program for the current I/O operation
  * @irb: irb info received from interrupt
  * @scsw: scsw info
+ * @crw_lock: serialization of CRW information
+ * @crw: list of Channel Report Word elements
  * @io_trigger: eventfd ctx for signaling userspace I/O results
  * @crw_trigger: eventfd ctx for signaling userspace CRW information
  * @req_trigger: eventfd ctx for signaling userspace to return device
@@ -122,6 +124,8 @@ struct vfio_ccw_private {
 
 	struct irb		irb;
 	union scsw		scsw;
+
+	spinlock_t		crw_lock;
 	struct list_head	crw;
 
 	struct eventfd_ctx	*io_trigger;
-- 
2.53.0

Re: [PATCH v4 3/9] s390/vfio_ccw: fix out of bounds check on CCW array

[sashiko-bot]

> The routine ccwchain_calc_length() counts the number of channel
> command words (CCWs) that are chained together in a single channel
> program, and rejects anything larger than CCWCHAIN_LEN_MAX (256) CCWs.
> 
> The loop itself is "do..while (count < 257)", and while the logic in
> is_cpa_within_range() correctly adjusts between the 0-index array of
> CCWs and the count of CCWs starting at 1, this means it would look
> at a possible 257th CCW before ending the loop and (correctly)
> returning an error.
> 
> Fix this by restructuring the loop to break as soon as 256 CCWs
> (thus indexes 0-255) are examined, without looking at memory
> outside the range.
> 
> Fixes: 0a19e61e6d4c ("vfio: ccw: introduce channel program interfaces")
> Cc: stable@vger.kernel.org
> Signed-off-by: Eric Farman <farman@linux.ibm.com>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260725152705.3958100-1-farman@linux.ibm.com?part=3

Re: [PATCH v4 5/9] s390/vfio_ccw: calculate idal length based on idaw type

[sashiko-bot]

> Sashiko pointed out that get_guest_idal() unconditionally calculates
> the length of the IDAL presuming everything is a Format-2 IDAW.
> 
> The output of vfio-ccw is always Format-2, but the input can be either
> Format-1 (31-bit addresses) or Format-2 (64-bit addresses). As a result,
> the size of the guest IDAL may be incorrect and should be trimmed down.
> 
> Reported-by: sashiko-bot <sashiko-bot@kernel.org>
> Link: https://lore.kernel.org/r/20260720203400.7328E1F000E9@smtp.kernel.org/
> Fixes: 1b676fe3d9d3 ("vfio/ccw: handle a guest Format-1 IDAL")
> Cc: stable@vger.kernel.org
> Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
> Signed-off-by: Eric Farman <farman@linux.ibm.com>

Sashiko has reviewed this patch and found no issues. It looks great!

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260725152705.3958100-1-farman@linux.ibm.com?part=5

Re: [PATCH v4 2/9] s390/vfio_ccw: limit the number of channel program segments

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:

Pre-existing issues:
- [High] The `ccwchain_calc_length` function can read out-of-bounds when evaluating a maximum-length CCW chain.
- [Medium] `vfio_dma_rw` unconditionally fetches exactly 2K bytes regardless of actual chain length.
--

--- Patch [2]: [PATCH v4 2/9] s390/vfio_ccw: limit the number of channel program segments ---
commit 329c62f260a235e5ffc6e09ecde7b4928c02051c
Author: Eric Farman <farman@linux.ibm.com>
Subject: s390/vfio_ccw: limit the number of channel program segments

This commit imposes a limit on the number of channel program segments
(linked by TIC) that can exist in a single channel program. It breaks
channel programs into segments when encountering a Transfer-In-Channel (TIC)
CCW and enforces a global limit on the number of segments to prevent unbounded
recursion.

[ ... ]
> diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
> index 086d1b54bdb05..1c2890d139c6b 100644
> --- a/drivers/s390/cio/vfio_ccw_cp.c
> +++ b/drivers/s390/cio/vfio_ccw_cp.c
[ ... ]
> @@ -441,6 +442,10 @@ static int ccwchain_handle_ccw(dma32_t cda, struct channel_program *cp)
>  	if (len < 0)
>  		return len;
>  
> +	/* Limit number of chains in a single channel program */
> +	if (cp->ccwchain_count >= CCWCHAIN_COUNT_MAX)
> +		return -EINVAL;
> +

[Severity: Medium]
This isn't a bug introduced by this patch, but does the unconditional read of
2K bytes in ccwchain_handle_ccw() cause valid short programs to fail?

Earlier in ccwchain_handle_ccw(), the code performs a hardcoded 2K read before
calculating the actual chain length:

ccwchain_handle_ccw() {
    ...
    ret = vfio_dma_rw(vdev, gcda, cp->guest_cp,
                      CCWCHAIN_LEN_MAX * sizeof(struct ccw1), false);
    if (ret)
        return ret;
    ...
}

If a guest submits a short channel program located near the end of a mapped
memory region, and the adjacent page is unmapped, vfio_dma_rw() will fail the
entire transaction instead of returning a partial read.

Could this lead to rejection of valid channel programs based on their memory
layout?

[Severity: High]
This is a pre-existing issue, but can the length calculation read out of
bounds?

In ccwchain_calc_length(), which is called just before the new limit check,
the code evaluates a maximum-length CCW chain:

ccwchain_calc_length() {
    ...
    if (!ccw_is_chain(ccw) && !is_tic_within_range(ccw, iova, cnt))
        break;
    ...
}

If a guest VM submits a channel program where the first 256 CCWs all have
the chain flag set, the loop increments the counter to 257. On the 257th
iteration, calling ccw_is_chain(ccw) reads the flags field from guest_cp[256],
which is one element past the end of the allocated CCWCHAIN_LEN_MAX array.

Can an unprivileged guest trigger an out-of-bounds read by providing a
specially crafted channel program?

>  	/* Need alloc a new chain for this one. */
>  	chain = ccwchain_alloc(cp, len);
>  	if (!chain)
[ ... ]

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260725152705.3958100-1-farman@linux.ibm.com?part=2

Re: [PATCH v4 7/9] s390/vfio_ccw: move cp cleanup out of not operational

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [High] The newly introduced `notoper_work` is queued asynchronously but never cancelled or flushed when the device is released, leading to a Use-After-Free.
- [High] The asynchronous execution of `cp_free()` in `vfio_ccw_notoper_todo()` runs without any locks, creating a critical race condition with concurrent callers.
--

--- Patch [7]: [PATCH v4 7/9] s390/vfio_ccw: move cp cleanup out of not operational ---
commit fa524c6f90fe876d05c7a596474d882a3c80e457
Author: Eric Farman <farman@linux.ibm.com>

s390/vfio_ccw: move cp cleanup out of not operational

This commit shifts the cleanup of channel program resources out of the
synchronous fsm_notoper state handler. It defers the cp_free operation
to a workqueue, avoiding potential lock contention with the cio subchannel
lock.

> diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
> index 1a095085bc728..c197ad5ab5805 100644
> --- a/drivers/s390/cio/vfio_ccw_drv.c
> +++ b/drivers/s390/cio/vfio_ccw_drv.c

[ ... ]

> @@ -125,6 +125,15 @@ void vfio_ccw_crw_todo(struct work_struct *work)
>  		eventfd_signal(private->crw_trigger);
>  }
>  
> +void vfio_ccw_notoper_todo(struct work_struct *work)
> +{
> +	struct vfio_ccw_private *private;
> +
> +	private = container_of(work, struct vfio_ccw_private, notoper_work);
> +
> +	cp_free(&private->cp);
> +}

[Severity: High]
Does this asynchronous execution of cp_free need some form of locking?

If userspace closes the device file at the same time this work executes,
fsm_close might call cp_free() concurrently. Since cp_free() checks and
clears cp->initialized non-atomically:

drivers/s390/cio/vfio_ccw_cp.c:cp_free() {
    if (!cp->initialized)
        return;
    cp->initialized = false;
    ...
}

Could both threads observe cp->initialized as true, leading to a
double-free of the chain structures? 

The commit message mentions this will be done "(soon) under its own
serialization mechanism", but should that be included in this patch to
prevent the race condition entirely?

> diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
> index 4d7988ea47ef0..4d47a3c7b9a06 100644
> --- a/drivers/s390/cio/vfio_ccw_fsm.c
> +++ b/drivers/s390/cio/vfio_ccw_fsm.c

[ ... ]

> @@ -170,8 +170,7 @@ static void fsm_notoper(struct vfio_ccw_private *private,
>  	css_sched_sch_todo(sch, SCH_TODO_UNREG);
>  	private->state = VFIO_CCW_STATE_NOT_OPER;
>  
> -	/* This is usually handled during CLOSE event */
> -	cp_free(&private->cp);
> +	queue_work(vfio_ccw_work_q, &private->notoper_work);
>  }

[Severity: High]
If this work is queued, but the device is subsequently removed and released
via vfio_ccw_mdev_release_dev(), will the work item still be pending?

Since vfio_ccw_mdev_release_dev() frees the private structure, is there a
risk of a use-after-free if the workqueue thread eventually executes
vfio_ccw_notoper_todo() and dereferences the freed private pointer?

Should cancel_work_sync(&private->notoper_work) or flush_work() be added to
the device teardown path to ensure the work is safely stopped before private
is freed?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260725152705.3958100-1-farman@linux.ibm.com?part=7

Re: [PATCH v4 1/9] s390/vfio_ccw: free all memory if cp_init() fails

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:

Pre-existing issues:
- [High] Unbounded recursion between `ccwchain_handle_ccw()` and `ccwchain_loop_tic()` can exhaust the host kernel stack.
- [High] An off-by-one error in `ccwchain_calc_length()` causes a heap out-of-bounds read past the end of the `cp->guest_cp` array.
--

--- Patch [1]: [PATCH v4 1/9] s390/vfio_ccw: free all memory if cp_init() fails ---
commit 8ee92e1dc4c9d7d0f67c0ba543dd404b37f81dcc
Author: Eric Farman <farman@linux.ibm.com>

s390/vfio_ccw: free all memory if cp_init() fails

This commit addresses a memory leak where CCW segments created as a result
of a Transfer in Channel would not be properly freed if cp_init() fails.
It moves the cleanup logic outside the recursive ccwchain_handle_ccw() and
ccwchain_loop_tic() loops.

> diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
> index 7561aa7d3e017..086d1b54bdb05 100644
> --- a/drivers/s390/cio/vfio_ccw_cp.c
> +++ b/drivers/s390/cio/vfio_ccw_cp.c
> @@ -455,9 +455,6 @@ static int ccwchain_handle_ccw(dma32_t cda, struct channel_program *cp)
>  	/* Loop for tics on this new chain. */
>  	ret = ccwchain_loop_tic(chain, cp);
>  

[Severity: High]
This isn't a bug introduced by this patch, but can this unbounded recursion
between ccwchain_handle_ccw() and ccwchain_loop_tic() exhaust the host kernel
stack?

If a guest constructs a channel program consisting of a long linear sequence
of TICs (Transfer in Channel), where each TIC points to a distinct, previously
unvisited address, could this lead to a kernel panic from stack overflow?

Since there is no limit on the recursion depth, ccwchain_handle_ccw() and
ccwchain_loop_tic() recursively call each other until the stack overflows:

ccwchain_handle_ccw() -> ccwchain_loop_tic() -> ccwchain_handle_ccw()

> -	if (ret)
> -		ccwchain_free(chain);
> -
>  	return ret;
>  }

[Severity: High]
This is a pre-existing issue, but does an off-by-one error in
ccwchain_calc_length() cause a heap out-of-bounds read past the end of the
cp->guest_cp array?

If the guest provides a CCW chain of exactly CCWCHAIN_LEN_MAX (256) elements,
with all elements having the chain flag set, the loop logic permits
evaluating the chain flag on the out-of-bounds index before realizing
the maximum limit is reached:

drivers/s390/cio/vfio_ccw_cp.c:ccwchain_calc_length() {
    ...
    } while (cnt < CCWCHAIN_LEN_MAX + 1);
    ...
}

Could this lead to a kernel Oops if it crosses a page boundary into an
unmapped page, or trigger KASAN panics?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260725152705.3958100-1-farman@linux.ibm.com?part=1

Re: [PATCH v4 6/9] s390/vfio_ccw: ensure index for read/write regions are within range

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [Critical] Missing `cancel_work_sync` allows `crw_work` to execute after the device is freed, leading to a Use-After-Free.
--

--- Patch [6]: [PATCH v4 6/9] s390/vfio_ccw: ensure index for read/write regions are within range ---
commit 9f53752835377d5ad4247b37c995e0a1051a888e
Author: Eric Farman <farman@linux.ibm.com>

s390/vfio_ccw: ensure index for read/write regions are within range

This commit adds bounds checking for read/write region indices that were
missed during the capability chain introduction. It also applies
array_index_nospec to prevent speculative execution issues.

> diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
> index 45ec722d25ea6..032a1cdf4df70 100644
> --- a/drivers/s390/cio/vfio_ccw_ops.c
> +++ b/drivers/s390/cio/vfio_ccw_ops.c

[ ... ]

[Severity: Critical]
This is a pre-existing issue, but while reviewing the changes in
vfio_ccw_ops.c, I noticed a potential use-after-free in the device
teardown sequence.

In vfio_ccw_mdev_release_dev(), the private structure is freed, but there
doesn't appear to be a call to cancel_work_sync(&private->crw_work):

drivers/s390/cio/vfio_ccw_ops.c:vfio_ccw_mdev_release_dev() {
	struct vfio_ccw_private *private =
		container_of(vdev, struct vfio_ccw_private, vdev);
	struct vfio_ccw_crw *crw, *temp;

	list_for_each_entry_safe(crw, temp, &private->crw, next) {
...

Concurrently, if a channel path event triggers vfio_ccw_chp_event() just
before the private pointer is cleared, it can queue the work:

drivers/s390/cio/vfio_ccw_drv.c:vfio_ccw_queue_crw() {
    ...
	list_add_tail(&crw->next, &private->crw);
	queue_work(vfio_ccw_work_q, &private->crw_work);
}

Could this race allow the pending crw_work (vfio_ccw_crw_todo) to execute
after the private structure has already been freed, leading to memory
corruption when it accesses private->crw or private->crw_trigger?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260725152705.3958100-1-farman@linux.ibm.com?part=6

Re: [PATCH v4 8/9] s390/vfio_ccw: implement a channel program mutex

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:

Pre-existing issues:
- [High] Pending asynchronous work items are not cancelled or flushed during device release, leading to a use-after-free and locking a destroyed mutex.
- [High] Unprotected update of `private->state` in `vfio_ccw_sch_io_todo()` causes a race condition that permanently bricks the device.
--

--- Patch [8]: [PATCH v4 8/9] s390/vfio_ccw: implement a channel program mutex ---
commit dd565d50b000e987452a43655c08441c643c355d
Author: Eric Farman <farman@linux.ibm.com>

s390/vfio_ccw: implement a channel program mutex

This patch introduces a cp_mutex to protect the channel_program struct
from concurrent manipulation. It updates various functions to acquire
this mutex instead of relying on the cio layer's subchannel lock.

> diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
> index c197ad5ab5805..4830f0dd9c3a3 100644
> --- a/drivers/s390/cio/vfio_ccw_drv.c
> +++ b/drivers/s390/cio/vfio_ccw_drv.c
> @@ -91,6 +91,8 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
>  
>  	is_final = !(scsw_actl(&irb->scsw) &
>  		     (SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT));
> +
> +	mutex_lock(&private->cp_mutex);
>  	if (scsw_is_solicited(&irb->scsw)) {
>  		cp_update_scsw(&private->cp, &irb->scsw);
>  		if (is_final && private->state == VFIO_CCW_STATE_CP_PENDING) {
> @@ -98,6 +100,8 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
>  			cp_is_finished = true;
>  		}
>  	}
> +	mutex_unlock(&private->cp_mutex);

[Severity: High]
This is a pre-existing issue, but does this unlocked state update in
vfio_ccw_sch_io_todo() cause a race condition with concurrent close
operations?

In vfio_ccw_sch_io_todo(), private->state = VFIO_CCW_STATE_IDLE is assigned
unconditionally outside of any locks shortly after this mutex_unlock. If a
user closes the device concurrently, fsm_close() disables the subchannel and
sets the state to VFIO_CCW_STATE_STANDBY.

If vfio_ccw_sch_io_todo() then overwrites this state with IDLE, a subsequent
device open will encounter fsm_notoper() because the state machine handles
OPEN in the IDLE state by transitioning to NOT_OPER, which bricks the device
until it is manually recreated.

> +
>  	mutex_lock(&private->io_mutex);
>  	memcpy(private->io_region->irb_area, irb, sizeof(*irb));
>  	mutex_unlock(&private->io_mutex);

[ ... ]

> diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
> index 6c74d596be9de..9242a37677a06 100644
> --- a/drivers/s390/cio/vfio_ccw_ops.c
> +++ b/drivers/s390/cio/vfio_ccw_ops.c

[ ... ]

> @@ -142,6 +149,7 @@ static void vfio_ccw_mdev_release_dev(struct vfio_device *vdev)
>  	kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
>  	kmem_cache_free(vfio_ccw_io_region, private->io_region);
>  	kfree(private->cp.guest_cp);
> +	mutex_destroy(&private->cp_mutex);
>  	mutex_destroy(&private->io_mutex);
>  }

[Severity: High]
This is a pre-existing issue, but could destroying these mutexes here cause
a use-after-free and crash if pending asynchronous work items are still
active?

If an I/O interrupt fires right before the device is released (for example,
during unbind) and cio_disable_subchannel() returns 0 because the subchannel
is idle, the workqueue flush in vfio_ccw_sch_quiesce() gets skipped.

vfio_ccw_mdev_release_dev() will then destroy cp_mutex and io_mutex, and
free the private structure without cancelling queued work like io_work or
notoper_work. When vfio_ccw_sch_io_todo() or vfio_ccw_notoper_todo()
subsequently runs, it accesses the freed private struct and attempts to lock
the destroyed cp_mutex.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260725152705.3958100-1-farman@linux.ibm.com?part=8

Re: [PATCH v4 4/9] s390/vfio_ccw: ensure first IDAW remains constant

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:

Pre-existing issues:
- [High] `get_guest_idal` reads past the end of the guest's IDAL buffer for format-1 IDALs, potentially causing spurious DMA faults.
- [High] Untranslated guest IDALs are passed to the host channel subsystem when data transfer is skipped, causing hardware Program Checks.
--

--- Patch [4]: [PATCH v4 4/9] s390/vfio_ccw: ensure first IDAW remains constant ---
commit ff6c62bce82b594d19f9d6e95c9229ea752d6614
Author: Eric Farman <farman@linux.ibm.com>

s390/vfio_ccw: ensure first IDAW remains constant

The first IDAW in a list does not need to be on a 2K/4K boundary like all
others, and so is read separately to accurately calculate the size of the
buffer needed to read the full IDAL. This commit validates that the address
found in the first IDAW is unchanged between reads.

> diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
> index af632f9d54535..6275794751cb4 100644
> --- a/drivers/s390/cio/vfio_ccw_cp.c
> +++ b/drivers/s390/cio/vfio_ccw_cp.c
> @@ -523,6 +523,7 @@ static dma64_t *get_guest_idal(struct ccw1 *ccw, struct channel_program *cp, int
>  		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
>  	dma64_t *idaws;
>  	dma32_t *idaws_f1;
> +	u64 first_idaw;
>  	int idal_len = idaw_nr * sizeof(*idaws);
        ^^^^

[Severity: High]
This is a pre-existing issue, but does get_guest_idal() read past the end of
the guest's IDAL buffer for format-1 IDALs?

It appears that idal_len is calculated using sizeof(*idaws), which is always 8
bytes (sizeof(dma64_t)), even when the guest uses 32-bit (format-1) IDAWs.

Later in get_guest_idal(), vfio_dma_rw() is called with this idal_len:

	if (ccw_is_idal(ccw)) {
		/* Copy IDAL from guest */
		ret = vfio_dma_rw(vdev, dma32_to_u32(ccw->cda), idaws, idal_len, false);

If a guest channel program uses Format-1 (32-bit) IDAWs, they are only 4 bytes
each. Calling vfio_dma_rw() with idaw_nr * 8 reads 100% past the end of the
guest's IDAL buffer.

If the guest's 32-bit IDAL ends near a page boundary and the adjacent page is
unmapped or restricted, this over-read could cross into unmapped guest memory
and fail, potentially spuriously rejecting a valid guest I/O request with a
DMA translation error.

>  	int idaw_size = idal_is_2k(cp) ? PAGE_SIZE / 2 : PAGE_SIZE;
>  	int idaw_mask = ~(idaw_size - 1);

[ ... ]

[Severity: High]
This is also a pre-existing issue, but does ccwchain_fetch_ccw() pass
untranslated guest IDALs to the host channel subsystem when data transfer is
skipped?

Looking at ccwchain_fetch_ccw(), if ccw_does_data_transfer(ccw) is false
(e.g., a READ CCW with the SKIP flag), pa->pa_nr is set to 0:

	if (ccw_does_data_transfer(ccw)) {
		ret = page_array_pin(pa, vdev, idal_is_2k(cp));
		if (ret < 0)
			goto out_unpin;
	} else {
		pa->pa_nr = 0;
	}

	ccw->cda = virt_to_dma32(idaws);
	ccw->flags |= CCW_FLAG_IDA;

	/* Populate the IDAL with pinned/translated addresses from page */
	page_array_idal_create_words(pa, idaws);

Consequently, page_array_idal_create_words() loops 0 times, leaving the idaws
buffer populated with raw guest IOVAs instead of valid host absolute addresses.

Since vfio-ccw forces orb.cmd.c64 = 1 (Format-2, 64-bit IDAWs) when issuing the
SSCH to the host channel subsystem, the hardware will fetch these untranslated
guest IOVAs. If the guest used 32-bit IDAWs, they are read as garbage 64-bit
pointers.

Will the hardware validate these invalid addresses during execution and trigger
a Channel Program Check, spuriously failing the guest's SKIP I/O request?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260725152705.3958100-1-farman@linux.ibm.com?part=4

Re: [PATCH v4 9/9] s390/vfio_ccw: implement a crw lock

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:

Pre-existing issues:
- [High] Missing cancellation of asynchronous work items (`crw_work`, `io_work`, `notoper_work`) during device release leads to a Use-After-Free of the `vfio_ccw_private` structure.
- [High] Unsynchronized modification of `crw_trigger` in the `SET_IRQS` ioctl causes a Time-of-Check to Time-of-Use (TOCTOU) race and Use-After-Free during eventfd signaling.
--

--- Patch [9]: [PATCH v4 9/9] s390/vfio_ccw: implement a crw lock ---
commit 5187e6c3172f066c510e9c2798199ac3a8915b42
Author: Eric Farman <farman@linux.ibm.com>

s390/vfio_ccw: implement a crw lock

Unlike the channel_program struct, which covers synchronous I/O
submissions and asynchronous interrupts, the CRW region relies
exclusively on asynchronous events coming from hardware. This patch
implements a lock to manage the list of those payloads to ensure
they are read cohesively.

> diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
> index 4830f0dd9c3a3..32f631d086205 100644
> --- a/drivers/s390/cio/vfio_ccw_drv.c
> +++ b/drivers/s390/cio/vfio_ccw_drv.c
> @@ -125,8 +125,10 @@ void vfio_ccw_crw_todo(struct work_struct *work)
>  
>  	private = container_of(work, struct vfio_ccw_private, crw_work);
>  
> +	spin_lock(&private->crw_lock);
>  	if (!list_empty(&private->crw) && private->crw_trigger)
>  		eventfd_signal(private->crw_trigger);
> +	spin_unlock(&private->crw_lock);
>  }

[Severity: High]
This isn't a bug introduced by this patch, but does checking
private->crw_trigger under crw_lock fully protect against a Use-After-Free
during eventfd signaling?

If a guest userspace process concurrently calls the VFIO_DEVICE_SET_IRQS ioctl
to change or unset the crw_trigger while crw_work is running, the writer path
modifies private->crw_trigger locklessly:

drivers/s390/cio/vfio_ccw_ops.c:vfio_ccw_mdev_set_irqs() {
    ...
    if (*ctx)
        eventfd_ctx_put(*ctx);
    *ctx = NULL;
    ...
}

If the ioctl thread frees the context right after vfio_ccw_crw_todo() reads it
but before calling eventfd_signal(), could the worker thread dereference a
freed pointer?

[ ... ]

> diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
> index 9242a37677a06..6735b5f4c07a2 100644
> --- a/drivers/s390/cio/vfio_ccw_ops.c
> +++ b/drivers/s390/cio/vfio_ccw_ops.c
[ ... ]
> @@ -139,10 +140,12 @@ static void vfio_ccw_mdev_release_dev(struct vfio_device *vdev)
>  		container_of(vdev, struct vfio_ccw_private, vdev);
>  	struct vfio_ccw_crw *crw, *temp;
>  
> +	spin_lock(&private->crw_lock);
>  	list_for_each_entry_safe(crw, temp, &private->crw, next) {
>  		list_del(&crw->next);
>  		kfree(crw);
>  	}
> +	spin_unlock(&private->crw_lock);
>  
>  	kmem_cache_free(vfio_ccw_crw_region, private->crw_region);
>  	kmem_cache_free(vfio_ccw_schib_region, private->schib_region);

[Severity: High]
This is a pre-existing issue, but does the device release function need to
cancel asynchronous work items before freeing the private structure?

If the administrator removes the mdev while an asynchronous hardware event is
queued, vfio_ccw_mdev_release_dev() will free private without canceling the
work items, such as crw_work, io_work, or notoper_work.

Could the queued work run and access the freed private pointer, like in
vfio_ccw_crw_todo():

    private = container_of(work, struct vfio_ccw_private, crw_work);
    
    spin_lock(&private->crw_lock);
    if (!list_empty(&private->crw) && private->crw_trigger)
        eventfd_signal(private->crw_trigger);

causing a Use-After-Free?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260725152705.3958100-1-farman@linux.ibm.com?part=9

Re: [PATCH v4 3/9] s390/vfio_ccw: fix out of bounds check on CCW array

[Matthew Rosato]

On 7/25/26 11:26 AM, Eric Farman wrote:
> The routine ccwchain_calc_length() counts the number of channel
> command words (CCWs) that are chained together in a single channel
> program, and rejects anything larger than CCWCHAIN_LEN_MAX (256) CCWs.
> 
> The loop itself is "do..while (count < 257)", and while the logic in
> is_cpa_within_range() correctly adjusts between the 0-index array of
> CCWs and the count of CCWs starting at 1, this means it would look
> at a possible 257th CCW before ending the loop and (correctly)
> returning an error.
> 
> Fix this by restructuring the loop to break as soon as 256 CCWs
> (thus indexes 0-255) are examined, without looking at memory
> outside the range.
> 
> Fixes: 0a19e61e6d4c ("vfio: ccw: introduce channel program interfaces")
> Cc: stable@vger.kernel.org
> Signed-off-by: Eric Farman <farman@linux.ibm.com>

Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>

> ---
>  drivers/s390/cio/vfio_ccw_cp.c | 17 +++++------------
>  1 file changed, 5 insertions(+), 12 deletions(-)
> 
> diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
> index 1c2890d139c6..af632f9d5453 100644
> --- a/drivers/s390/cio/vfio_ccw_cp.c
> +++ b/drivers/s390/cio/vfio_ccw_cp.c
> @@ -377,11 +377,9 @@ static void ccwchain_cda_free(struct ccwchain *chain, int idx)
>  static int ccwchain_calc_length(u64 iova, struct channel_program *cp)
>  {
>  	struct ccw1 *ccw = cp->guest_cp;
> -	int cnt = 0;
> -
> -	do {
> -		cnt++;
> +	int cnt;
>  
> +	for (cnt = 1; cnt <= CCWCHAIN_LEN_MAX; cnt++, ccw++) {
>  		/*
>  		 * We want to keep counting if the current CCW has the
>  		 * command-chaining flag enabled, or if it is a TIC CCW
> @@ -391,15 +389,10 @@ static int ccwchain_calc_length(u64 iova, struct channel_program *cp)
>  		 * after the TIC, depending on the results of its operation.
>  		 */
>  		if (!ccw_is_chain(ccw) && !is_tic_within_range(ccw, iova, cnt))
> -			break;
> -
> -		ccw++;
> -	} while (cnt < CCWCHAIN_LEN_MAX + 1);
> -
> -	if (cnt == CCWCHAIN_LEN_MAX + 1)
> -		cnt = -EINVAL;
> +			return cnt;
> +	}
>  
> -	return cnt;
> +	return -EINVAL;
>  }
>  
>  static int tic_target_chain_exists(struct ccw1 *tic, struct channel_program *cp)

Re: [PATCH v4 6/9] s390/vfio_ccw: ensure index for read/write regions are within range

[Matthew Rosato]

On 7/25/26 11:27 AM, Eric Farman wrote:
> The introduction of the capability chain rightly clamped the
> region indexes to the range of the capabilities itself, but
> neglected to do so for the existing read/write regions which
> should also be enforced.
> 
> Fixes: db8e5d17ac03 ("vfio-ccw: add capabilities chain")
> Cc: stable@vger.kernel.org
> Cc: Cornelia Huck <cohuck@redhat.com>
> Signed-off-by: Eric Farman <farman@linux.ibm.com>
> ---
>  drivers/s390/cio/vfio_ccw_async.c | 16 ++++++++++++++++
>  drivers/s390/cio/vfio_ccw_chp.c   | 15 +++++++++++++++
>  drivers/s390/cio/vfio_ccw_ops.c   |  7 +++----
>  3 files changed, 34 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/s390/cio/vfio_ccw_async.c b/drivers/s390/cio/vfio_ccw_async.c
> index 420d89ba7f83..4aff0b58fa5d 100644
> --- a/drivers/s390/cio/vfio_ccw_async.c
> +++ b/drivers/s390/cio/vfio_ccw_async.c
> @@ -8,6 +8,7 @@
>   */
>  
>  #include <linux/vfio.h>
> +#include <linux/nospec.h>
>  
>  #include "vfio_ccw_private.h"
>  
> @@ -24,11 +25,20 @@ static ssize_t vfio_ccw_async_region_read(struct vfio_ccw_private *private,
>  		return -EINVAL;
>  
>  	mutex_lock(&private->io_mutex);
> +
> +	if (i >= private->num_regions) {
> +		ret = -EINVAL;
> +		goto out_unlock;
> +	}
> +
> +	i = array_index_nospec(i, private->num_regions);

LGTM.

...

> diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
> index 45ec722d25ea..032a1cdf4df7 100644
> --- a/drivers/s390/cio/vfio_ccw_ops.c
> +++ b/drivers/s390/cio/vfio_ccw_ops.c
> @@ -243,6 +243,7 @@ static ssize_t vfio_ccw_mdev_read(struct vfio_device *vdev,
>  		return vfio_ccw_mdev_read_io_region(private, buf, count, ppos);
>  	default:
>  		index -= VFIO_CCW_NUM_REGIONS;
> +		index = array_index_nospec(index, private->num_regions);
>  		return private->region[index].ops->read(private, buf, count,
>  							ppos);
>  	}
> @@ -295,6 +296,7 @@ static ssize_t vfio_ccw_mdev_write(struct vfio_device *vdev,
>  		return vfio_ccw_mdev_write_io_region(private, buf, count, ppos);
>  	default:
>  		index -= VFIO_CCW_NUM_REGIONS;
> +		index = array_index_nospec(index, private->num_regions);
>  		return private->region[index].ops->write(private, buf, count,
>  							 ppos);
>  	}
> @@ -338,11 +340,8 @@ static int vfio_ccw_mdev_ioctl_get_region_info(struct vfio_device *vdev,
>  		    VFIO_CCW_NUM_REGIONS + private->num_regions)
>  			return -EINVAL;
>  
> -		info->index = array_index_nospec(info->index,
> -						 VFIO_CCW_NUM_REGIONS +
> -						 private->num_regions);
> -
>  		i = info->index - VFIO_CCW_NUM_REGIONS;
> +		i = array_index_nospec(i, private->num_regions);

...  These didn't at first, but then I realized that these functions in
vfio_ccw_ops.c each had pre-existing checks of index against
VFIO_CCW_NUM_REGIONS prior to this point.

Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>

Re: [PATCH v4 7/9] s390/vfio_ccw: move cp cleanup out of not operational

[Matthew Rosato]

On 7/25/26 11:27 AM, Eric Farman wrote:
> The fsm_notoper() routine is called when the device has been
> lost, and is (by definition) no longer operational. Since this
> can happen asynchronously from the normal behavior of the
> driver, the cleanup may happen when holding other locks
> in the calling sequence (notably, the cio subchannel lock).
> 
> Push the cleanup of the private->cp resources to a workqueue,
> where it can be done out from under that lock sequence and
> (soon) under its own serialization mechanism.
> 
> Fixes: 204b394a23ad ("vfio/ccw: Move FSM open/close to MDEV open/close")
> Cc: stable@vger.kernel.org
> Signed-off-by: Eric Farman <farman@linux.ibm.com>

Doesn't this need a cancel of the workqueue before the vfio_ccw_private
gets freed, maybe in vfio_ccw_mdev_release_dev()?
> ---
>  drivers/s390/cio/vfio_ccw_drv.c     | 9 +++++++++
>  drivers/s390/cio/vfio_ccw_fsm.c     | 3 +--
>  drivers/s390/cio/vfio_ccw_ops.c     | 1 +
>  drivers/s390/cio/vfio_ccw_private.h | 3 +++
>  4 files changed, 14 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
> index 1a095085bc72..c197ad5ab580 100644
> --- a/drivers/s390/cio/vfio_ccw_drv.c
> +++ b/drivers/s390/cio/vfio_ccw_drv.c
> @@ -125,6 +125,15 @@ void vfio_ccw_crw_todo(struct work_struct *work)
>  		eventfd_signal(private->crw_trigger);
>  }
>  
> +void vfio_ccw_notoper_todo(struct work_struct *work)
> +{
> +	struct vfio_ccw_private *private;
> +
> +	private = container_of(work, struct vfio_ccw_private, notoper_work);
> +
> +	cp_free(&private->cp);
> +}
> +
>  /*
>   * Css driver callbacks
>   */
> diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
> index 4d7988ea47ef..4d47a3c7b9a0 100644
> --- a/drivers/s390/cio/vfio_ccw_fsm.c
> +++ b/drivers/s390/cio/vfio_ccw_fsm.c
> @@ -170,8 +170,7 @@ static void fsm_notoper(struct vfio_ccw_private *private,
>  	css_sched_sch_todo(sch, SCH_TODO_UNREG);
>  	private->state = VFIO_CCW_STATE_NOT_OPER;
>  
> -	/* This is usually handled during CLOSE event */
> -	cp_free(&private->cp);
> +	queue_work(vfio_ccw_work_q, &private->notoper_work);
>  }
>  
>  /*
> diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
> index 032a1cdf4df7..6c74d596be9d 100644
> --- a/drivers/s390/cio/vfio_ccw_ops.c
> +++ b/drivers/s390/cio/vfio_ccw_ops.c
> @@ -54,6 +54,7 @@ static int vfio_ccw_mdev_init_dev(struct vfio_device *vdev)
>  	INIT_LIST_HEAD(&private->crw);
>  	INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo);
>  	INIT_WORK(&private->crw_work, vfio_ccw_crw_todo);
> +	INIT_WORK(&private->notoper_work, vfio_ccw_notoper_todo);
>  
>  	private->cp.guest_cp = kzalloc_objs(struct ccw1, CCWCHAIN_LEN_MAX);
>  	if (!private->cp.guest_cp)
> diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
> index 0501d4bbcdbd..e2256402b089 100644
> --- a/drivers/s390/cio/vfio_ccw_private.h
> +++ b/drivers/s390/cio/vfio_ccw_private.h
> @@ -102,6 +102,7 @@ struct vfio_ccw_parent {
>   * @req_trigger: eventfd ctx for signaling userspace to return device
>   * @io_work: work for deferral process of I/O handling
>   * @crw_work: work for deferral process of CRW handling
> + * @notoper_work: work for deferred processing in not-operational state
>   */
>  struct vfio_ccw_private {
>  	struct vfio_device vdev;
> @@ -125,11 +126,13 @@ struct vfio_ccw_private {
>  	struct eventfd_ctx	*req_trigger;
>  	struct work_struct	io_work;
>  	struct work_struct	crw_work;
> +	struct work_struct	notoper_work;
>  } __aligned(8);
>  
>  int vfio_ccw_sch_quiesce(struct subchannel *sch);
>  void vfio_ccw_sch_io_todo(struct work_struct *work);
>  void vfio_ccw_crw_todo(struct work_struct *work);
> +void vfio_ccw_notoper_todo(struct work_struct *work);
>  
>  extern struct mdev_driver vfio_ccw_mdev_driver;
>  

Re: [PATCH v4 9/9] s390/vfio_ccw: implement a crw lock

[Matthew Rosato]

On 7/25/26 11:27 AM, Eric Farman wrote:
> Unlike the channel_program struct, which covers synchronous I/O
> submissions and asynchronous interrupts, the CRW region relies
> exclusively on asynchronous events coming from hardware.
> 
> Implement a lock to manage the list of those payloads, to ensure
> they are read cohesively.
> 
> Fixes: 3f02cb2fd9d2 ("vfio-ccw: Wire up the CRW irq and CRW region")
> Cc: stable@vger.kernel.org
> Cc: Farhan Ali <alifm@linux.ibm.com>
> Signed-off-by: Eric Farman <farman@linux.ibm.com>

...

> --- a/drivers/s390/cio/vfio_ccw_private.h
> +++ b/drivers/s390/cio/vfio_ccw_private.h
> @@ -98,6 +98,8 @@ struct vfio_ccw_parent {
>   * @cp: channel program for the current I/O operation
>   * @irb: irb info received from interrupt
>   * @scsw: scsw info
> + * @crw_lock: serialization of CRW information

I would re-word this to say 'CRW list', to make it a bit more clear that
the lock does not protect crw_trigger at this time (as discussed in v3).

With that:

Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>


> + * @crw: list of Channel Report Word elements
>   * @io_trigger: eventfd ctx for signaling userspace I/O results
>   * @crw_trigger: eventfd ctx for signaling userspace CRW information
>   * @req_trigger: eventfd ctx for signaling userspace to return device
> @@ -122,6 +124,8 @@ struct vfio_ccw_private {
>  
>  	struct irb		irb;
>  	union scsw		scsw;
> +
> +	spinlock_t		crw_lock;
>  	struct list_head	crw;
>  
>  	struct eventfd_ctx	*io_trigger;

Re: [PATCH v4 8/9] s390/vfio_ccw: implement a channel program mutex

[Matthew Rosato]

On 7/25/26 11:27 AM, Eric Farman wrote:
> The channel_program struct is manipulated without a serialization
> mechanism to ensure consistent behavior. Take a broad stroke of
> putting the entire structure behind a mutex, and ensure everything
> that needs private->cp holds this mutex.
> 
> There are a couple where the cio layer's subchannel->lock performs
> this role in this code, which isn't correct (it should only be used
> when touching the actual subchannel, like cio_enable_subchannel()),
> so adjust the locations where that spinlock is acquired/released
> to correctly coexist with this new mutex.
> 
> Fixes: 0a19e61e6d4c ("vfio: ccw: introduce channel program interfaces")
> Cc: stable@vger.kernel.org
> Signed-off-by: Eric Farman <farman@linux.ibm.com>

Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>

> ---
>  drivers/s390/cio/vfio_ccw_cp.c      | 30 +++++++++++++++++++++++++----
>  drivers/s390/cio/vfio_ccw_drv.c     |  6 ++++++
>  drivers/s390/cio/vfio_ccw_fsm.c     | 20 ++++++++++++-------
>  drivers/s390/cio/vfio_ccw_ops.c     | 10 +++++++++-
>  drivers/s390/cio/vfio_ccw_private.h |  3 +++
>  5 files changed, 57 insertions(+), 12 deletions(-)
> 
> diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
> index 5ef082b8289a..ab66caff9894 100644
> --- a/drivers/s390/cio/vfio_ccw_cp.c
> +++ b/drivers/s390/cio/vfio_ccw_cp.c
> @@ -738,12 +738,15 @@ static int ccwchain_fetch_one(struct ccw1 *ccw,
>   */
>  int cp_init(struct channel_program *cp, union orb *orb)
>  {
> -	struct vfio_device *vdev =
> -		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
> +	struct vfio_ccw_private *private =
> +		container_of(cp, struct vfio_ccw_private, cp);
> +	struct vfio_device *vdev = &private->vdev;
>  	/* custom ratelimit used to avoid flood during guest IPL */
>  	static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 1);
>  	int ret;
>  
> +	lockdep_assert_held(&private->cp_mutex);
> +
>  	/* this is an error in the caller */
>  	if (cp->initialized)
>  		return -EBUSY;
> @@ -784,11 +787,14 @@ int cp_init(struct channel_program *cp, union orb *orb)
>   */
>  void cp_free(struct channel_program *cp)
>  {
> -	struct vfio_device *vdev =
> -		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
> +	struct vfio_ccw_private *private =
> +		container_of(cp, struct vfio_ccw_private, cp);
> +	struct vfio_device *vdev = &private->vdev;
>  	struct ccwchain *chain, *temp;
>  	int i;
>  
> +	lockdep_assert_held(&private->cp_mutex);
> +
>  	if (!cp->initialized)
>  		return;
>  
> @@ -841,11 +847,15 @@ void cp_free(struct channel_program *cp)
>   */
>  int cp_prefetch(struct channel_program *cp)
>  {
> +	struct vfio_ccw_private *private =
> +		container_of(cp, struct vfio_ccw_private, cp);
>  	struct ccwchain *chain;
>  	struct ccw1 *ccw;
>  	struct page_array *pa;
>  	int len, idx, ret;
>  
> +	lockdep_assert_held(&private->cp_mutex);
> +
>  	/* this is an error in the caller */
>  	if (!cp->initialized)
>  		return -EINVAL;
> @@ -883,10 +893,14 @@ int cp_prefetch(struct channel_program *cp)
>   */
>  union orb *cp_get_orb(struct channel_program *cp, struct subchannel *sch)
>  {
> +	struct vfio_ccw_private *private =
> +		container_of(cp, struct vfio_ccw_private, cp);
>  	union orb *orb;
>  	struct ccwchain *chain;
>  	struct ccw1 *cpa;
>  
> +	lockdep_assert_held(&private->cp_mutex);
> +
>  	/* this is an error in the caller */
>  	if (!cp->initialized)
>  		return NULL;
> @@ -931,10 +945,14 @@ union orb *cp_get_orb(struct channel_program *cp, struct subchannel *sch)
>   */
>  void cp_update_scsw(struct channel_program *cp, union scsw *scsw)
>  {
> +	struct vfio_ccw_private *private =
> +		container_of(cp, struct vfio_ccw_private, cp);
>  	struct ccwchain *chain;
>  	dma32_t cpa = scsw->cmd.cpa;
>  	u32 ccw_head;
>  
> +	lockdep_assert_held(&private->cp_mutex);
> +
>  	if (!cp->initialized)
>  		return;
>  
> @@ -977,9 +995,13 @@ void cp_update_scsw(struct channel_program *cp, union scsw *scsw)
>   */
>  bool cp_iova_pinned(struct channel_program *cp, u64 iova, u64 length)
>  {
> +	struct vfio_ccw_private *private =
> +		container_of(cp, struct vfio_ccw_private, cp);
>  	struct ccwchain *chain;
>  	int i;
>  
> +	lockdep_assert_held(&private->cp_mutex);
> +
>  	if (!cp->initialized)
>  		return false;
>  
> diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
> index c197ad5ab580..4830f0dd9c3a 100644
> --- a/drivers/s390/cio/vfio_ccw_drv.c
> +++ b/drivers/s390/cio/vfio_ccw_drv.c
> @@ -91,6 +91,8 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
>  
>  	is_final = !(scsw_actl(&irb->scsw) &
>  		     (SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT));
> +
> +	mutex_lock(&private->cp_mutex);
>  	if (scsw_is_solicited(&irb->scsw)) {
>  		cp_update_scsw(&private->cp, &irb->scsw);
>  		if (is_final && private->state == VFIO_CCW_STATE_CP_PENDING) {
> @@ -98,6 +100,8 @@ void vfio_ccw_sch_io_todo(struct work_struct *work)
>  			cp_is_finished = true;
>  		}
>  	}
> +	mutex_unlock(&private->cp_mutex);
> +
>  	mutex_lock(&private->io_mutex);
>  	memcpy(private->io_region->irb_area, irb, sizeof(*irb));
>  	mutex_unlock(&private->io_mutex);
> @@ -131,7 +135,9 @@ void vfio_ccw_notoper_todo(struct work_struct *work)
>  
>  	private = container_of(work, struct vfio_ccw_private, notoper_work);
>  
> +	mutex_lock(&private->cp_mutex);
>  	cp_free(&private->cp);
> +	mutex_unlock(&private->cp_mutex);
>  }
>  
>  /*
> diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
> index 4d47a3c7b9a0..cefdfcb0cad7 100644
> --- a/drivers/s390/cio/vfio_ccw_fsm.c
> +++ b/drivers/s390/cio/vfio_ccw_fsm.c
> @@ -25,17 +25,15 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
>  	unsigned long flags;
>  	int ret;
>  
> -	spin_lock_irqsave(&sch->lock, flags);
> -
>  	orb = cp_get_orb(&private->cp, sch);
> -	if (!orb) {
> -		ret = -EIO;
> -		goto out;
> -	}
> +	if (!orb)
> +		return -EIO;
>  
>  	VFIO_CCW_TRACE_EVENT(5, "stIO");
>  	VFIO_CCW_TRACE_EVENT(5, dev_name(&sch->dev));
>  
> +	spin_lock_irqsave(&sch->lock, flags);
> +
>  	/* Issue "Start Subchannel" */
>  	ccode = ssch(sch->schid, orb);
>  
> @@ -71,7 +69,6 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
>  	default:
>  		ret = ccode;
>  	}
> -out:
>  	spin_unlock_irqrestore(&sch->lock, flags);
>  	return ret;
>  }
> @@ -251,6 +248,8 @@ static void fsm_io_request(struct vfio_ccw_private *private,
>  	private->state = VFIO_CCW_STATE_CP_PROCESSING;
>  	memcpy(scsw, io_region->scsw_area, sizeof(*scsw));
>  
> +	mutex_lock(&private->cp_mutex);
> +
>  	if (scsw->cmd.fctl & SCSW_FCTL_START_FUNC) {
>  		orb = (union orb *)io_region->orb_area;
>  
> @@ -299,6 +298,8 @@ static void fsm_io_request(struct vfio_ccw_private *private,
>  			cp_free(&private->cp);
>  			goto err_out;
>  		}
> +
> +		mutex_unlock(&private->cp_mutex);
>  		return;
>  	} else if (scsw->cmd.fctl & SCSW_FCTL_HALT_FUNC) {
>  		VFIO_CCW_MSG_EVENT(2,
> @@ -319,6 +320,7 @@ static void fsm_io_request(struct vfio_ccw_private *private,
>  	}
>  
>  err_out:
> +	mutex_unlock(&private->cp_mutex);
>  	private->state = VFIO_CCW_STATE_IDLE;
>  	trace_vfio_ccw_fsm_io_request(scsw->cmd.fctl, schid,
>  				      io_region->ret_code, errstr);
> @@ -409,7 +411,11 @@ static void fsm_close(struct vfio_ccw_private *private,
>  
>  	private->state = VFIO_CCW_STATE_STANDBY;
>  	spin_unlock_irq(&sch->lock);
> +
> +	mutex_lock(&private->cp_mutex);
>  	cp_free(&private->cp);
> +	mutex_unlock(&private->cp_mutex);
> +
>  	return;
>  
>  err_unlock:
> diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
> index 6c74d596be9d..9242a37677a0 100644
> --- a/drivers/s390/cio/vfio_ccw_ops.c
> +++ b/drivers/s390/cio/vfio_ccw_ops.c
> @@ -38,8 +38,13 @@ static void vfio_ccw_dma_unmap(struct vfio_device *vdev, u64 iova, u64 length)
>  		container_of(vdev, struct vfio_ccw_private, vdev);
>  
>  	/* Drivers MUST unpin pages in response to an invalidation. */
> -	if (!cp_iova_pinned(&private->cp, iova, length))
> +	mutex_lock(&private->cp_mutex);
> +	if (!cp_iova_pinned(&private->cp, iova, length)) {
> +		mutex_unlock(&private->cp_mutex);
>  		return;
> +	}
> +
> +	mutex_unlock(&private->cp_mutex);
>  
>  	vfio_ccw_mdev_reset(private);
>  }
> @@ -50,6 +55,7 @@ static int vfio_ccw_mdev_init_dev(struct vfio_device *vdev)
>  		container_of(vdev, struct vfio_ccw_private, vdev);
>  
>  	mutex_init(&private->io_mutex);
> +	mutex_init(&private->cp_mutex);
>  	private->state = VFIO_CCW_STATE_STANDBY;
>  	INIT_LIST_HEAD(&private->crw);
>  	INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo);
> @@ -91,6 +97,7 @@ static int vfio_ccw_mdev_init_dev(struct vfio_device *vdev)
>  out_free_cp:
>  	kfree(private->cp.guest_cp);
>  out_free_private:
> +	mutex_destroy(&private->cp_mutex);
>  	mutex_destroy(&private->io_mutex);
>  	return -ENOMEM;
>  }
> @@ -142,6 +149,7 @@ static void vfio_ccw_mdev_release_dev(struct vfio_device *vdev)
>  	kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
>  	kmem_cache_free(vfio_ccw_io_region, private->io_region);
>  	kfree(private->cp.guest_cp);
> +	mutex_destroy(&private->cp_mutex);
>  	mutex_destroy(&private->io_mutex);
>  }
>  
> diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
> index e2256402b089..b595fd81f370 100644
> --- a/drivers/s390/cio/vfio_ccw_private.h
> +++ b/drivers/s390/cio/vfio_ccw_private.h
> @@ -94,6 +94,7 @@ struct vfio_ccw_parent {
>   * @schib_region: MMIO region for SCHIB information
>   * @crw_region: MMIO region for getting channel report words
>   * @num_regions: number of additional regions
> + * @cp_mutex: protect against concurrent update of CP resources
>   * @cp: channel program for the current I/O operation
>   * @irb: irb info received from interrupt
>   * @scsw: scsw info
> @@ -116,7 +117,9 @@ struct vfio_ccw_private {
>  	struct ccw_crw_region	*crw_region;
>  	int num_regions;
>  
> +	struct mutex		cp_mutex;
>  	struct channel_program	cp;
> +
>  	struct irb		irb;
>  	union scsw		scsw;
>  	struct list_head	crw;