scsi: sas: Skip opt_sectors when DMA reports no real optimization hint

sas_host_setup() unconditionally sets shost->opt_sectors from
dma_opt_mapping_size().

When the IOMMU is disabled or in passthrough mode and no DMA ops provide
an opt_mapping_size callback, dma_opt_mapping_size() returns
min(dma_max_mapping_size(), SIZE_MAX) which equals
dma_max_mapping_size() — a hard upper bound, not an optimization hint.

On a Dell PowerEdge R750 with mpt3sas (Broadcom SAS3816, FW 33.15.00.00)
and intel_iommu=off the following values are observed:

  dma_opt_mapping_size()  = dma_max_mapping_size() (no real hint)
  shost->max_sectors      = 32767
  opt_sectors             = min(32767, huge >> 9) = 32767
  optimal_io_size         = 32767 << 9 = 16776704
                          → round_down(16776704, 4096) = 16773120

The SAS disk (SAMSUNG MZILT800HBHQ0D3) does not report an Optimal
Transfer Length in VPD page B0, so sdkp->opt_xfer_blocks remains 0.

sd_revalidate_disk() then uses min_not_zero(0, opt_sectors) =
opt_sectors, propagating the bogus value into the block device's
optimal_io_size (visible as OPT-IO = 16773120 in lsblk --topology).

mkfs.xfs picks up optimal_io_size and minimum_io_size and computes:

  swidth = 16773120 / 4096 = 4095
  sunit  = 8192 / 4096     = 2

Since 4095 % 2 != 0, XFS rejects the geometry:

  SB stripe unit sanity check failed

This makes it impossible to create XFS filesystems (e.g. for
/var/lib/docker) during system bootstrap.

Fix this by introducing a sas_dma_setup_opt_sectors() helper that sets
opt_sectors only when dma_opt_mapping_size() is strictly less than
dma_max_mapping_size(), indicating a genuine DMA optimization
constraint.

The helper computes min(opt_sectors, max_sectors) first, then rounds
down to a power of two so that filesystem geometry calculations always
produce clean results.

When the two DMA values are equal, no backend provided a real hint, so
opt_sectors stays at 0 ("no preference").

[mkp: implemented hch's suggestion]

Fixes: 4cbfca5f7750 ("scsi: scsi_transport_sas: cap shost opt_sectors according to DMA optimal limit")
Cc: stable@vger.kernel.org
Reviewed-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: Ionut Nechita <ionut.nechita@windriver.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://patch.msgid.link/20260519135238.373784-2-ionut.nechita@windriver.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index d8f2377b017fe415a75bde9478aaba9a934c8432..d689b9ed08a6c4949b666bcaf1bf43bb598ac9de 100644 (file)
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -27,6 +27,7 @@
 #include <linux/module.h>
 #include <linux/jiffies.h>
 #include <linux/err.h>
+#include <linux/log2.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/blkdev.h>
@@ -220,12 +221,45 @@ static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy)
  * SAS host attributes
  */
 
+/*
+ * Set shost->opt_sectors from the DMA optimal mapping size, but only
+ * when dma_opt_mapping_size() is strictly less than dma_max_mapping_size(),
+ * indicating a genuine optimization hint from an IOMMU or DMA backend.
+ * When the two are equal (e.g. IOMMU disabled / passthrough), no real
+ * hint exists, so leave opt_sectors at 0 to avoid bogus optimal_io_size
+ * values that break filesystem geometry (e.g. mkfs.xfs stripe alignment).
+ */
+static void sas_dma_setup_opt_sectors(struct Scsi_Host *shost)
+{
+       struct device *dma_dev = shost->dma_dev;
+       size_t opt = dma_opt_mapping_size(dma_dev);
+       size_t max = dma_max_mapping_size(dma_dev);
+       unsigned int opt_sectors;
+
+       /* opt >= max means no real hint was provided by the DMA layer */
+       if (opt >= max)
+               return;
+
+       /* Clamp to max_sectors to avoid overflow in sector arithmetic */
+       opt_sectors = min_t(unsigned int, opt >> SECTOR_SHIFT,
+                           shost->max_sectors);
+
+       /* Guard against zero before rounddown_pow_of_two() */
+       if (!opt_sectors)
+               return;
+
+       /*
+        * Round down to power-of-two so filesystem geometry calculations
+        * (e.g. XFS stripe width/unit) always produce clean divisors.
+        */
+       shost->opt_sectors = rounddown_pow_of_two(opt_sectors);
+}
+
 static int sas_host_setup(struct transport_container *tc, struct device *dev,
                          struct device *cdev)
 {
        struct Scsi_Host *shost = dev_to_shost(dev);
        struct sas_host_attrs *sas_host = to_sas_host_attrs(shost);
-       struct device *dma_dev = shost->dma_dev;
 
        INIT_LIST_HEAD(&sas_host->rphy_list);
        mutex_init(&sas_host->lock);
@@ -237,10 +271,7 @@ static int sas_host_setup(struct transport_container *tc, struct device *dev,
                dev_printk(KERN_ERR, dev, "fail to a bsg device %d\n",
                           shost->host_no);
 
-       if (dma_dev->dma_mask) {
-               shost->opt_sectors = min_t(unsigned int, shost->max_sectors,
-                               dma_opt_mapping_size(dma_dev) >> SECTOR_SHIFT);
-       }
+       sas_dma_setup_opt_sectors(shost);
 
        return 0;
 }