When registering VTL0 memory via MSHV_ADD_VTL0_MEMORY, the kernel
computes pgmap->vmemmap_shift as the number of trailing zeros in the
OR of start_pfn and last_pfn, intending to use the largest compound
page order both endpoints are aligned to.
However, this value is not clamped to MAX_FOLIO_ORDER, so a
sufficiently aligned range (e.g. physical range
[0x800000000000, 0x800080000000), corresponding to start_pfn=0x800000000
with 35 trailing zeros) can produce a shift larger than what
memremap_pages() accepts, triggering a WARN and returning -EINVAL:
WARNING: ... memremap_pages+0x512/0x650
requested folio size unsupported
The MAX_FOLIO_ORDER check was added by
commit 646b67d57589 ("mm/memremap: reject unreasonable folio/compound
page sizes in memremap_pages()").
Fix this by clamping vmemmap_shift to MAX_FOLIO_ORDER so we always
request the largest order the kernel supports, in those cases, rather
than an out-of-range value.
Also fix the error path to propagate the actual error code from
devm_memremap_pages() instead of hard-coding -EFAULT, which was
masking the real -EINVAL return.
Fixes: 7bfe3b8ea6e3 ("Drivers: hv: Introduce mshv_vtl driver")
Cc: [email protected]
Signed-off-by: Naman Jain <[email protected]>
---
Changes since v1:
https://lore.kernel.org/all/[email protected]/
Addressed Michael's comments:
* remove MAX_FOLIO_ORDER value related text in commit msg
* Change change summary to keep prefix "mshv_vtl:"
* Add comments regarding last_pfn to avoid confusion
* use min instead of min_t
---
drivers/hv/mshv_vtl_main.c | 12 +++++++++---
include/uapi/linux/mshv.h | 2 +-
2 files changed, 10 insertions(+), 4 deletions(-)
diff --git a/drivers/hv/mshv_vtl_main.c b/drivers/hv/mshv_vtl_main.c
index 5856975f32e1..c19400701467 100644
--- a/drivers/hv/mshv_vtl_main.c
+++ b/drivers/hv/mshv_vtl_main.c
@@ -386,7 +386,6 @@ static int mshv_vtl_ioctl_add_vtl0_mem(struct mshv_vtl
*vtl, void __user *arg)
if (copy_from_user(&vtl0_mem, arg, sizeof(vtl0_mem)))
return -EFAULT;
- /* vtl0_mem.last_pfn is excluded in the pagemap range for VTL0 as per
design */
if (vtl0_mem.last_pfn <= vtl0_mem.start_pfn) {
dev_err(vtl->module_dev, "range start pfn (%llx) > end pfn
(%llx)\n",
vtl0_mem.start_pfn, vtl0_mem.last_pfn);
@@ -397,6 +396,10 @@ static int mshv_vtl_ioctl_add_vtl0_mem(struct mshv_vtl
*vtl, void __user *arg)
if (!pgmap)
return -ENOMEM;
+ /*
+ * vtl0_mem.last_pfn is excluded in the pagemap range for VTL0 as per
design.
+ * last_pfn is not reserved or wasted, and reflects 'start_pfn + size'
of pagemap range.
+ */
pgmap->ranges[0].start = PFN_PHYS(vtl0_mem.start_pfn);
pgmap->ranges[0].end = PFN_PHYS(vtl0_mem.last_pfn) - 1;
pgmap->nr_range = 1;
@@ -405,8 +408,11 @@ static int mshv_vtl_ioctl_add_vtl0_mem(struct mshv_vtl
*vtl, void __user *arg)
/*
* Determine the highest page order that can be used for the given
memory range.
* This works best when the range is aligned; i.e. both the start and
the length.
+ * Clamp to MAX_FOLIO_ORDER to avoid a WARN in memremap_pages() when
the range
+ * alignment exceeds the maximum supported folio order for this kernel
config.
*/
- pgmap->vmemmap_shift = count_trailing_zeros(vtl0_mem.start_pfn |
vtl0_mem.last_pfn);
+ pgmap->vmemmap_shift = min(count_trailing_zeros(vtl0_mem.start_pfn |
vtl0_mem.last_pfn),
+ MAX_FOLIO_ORDER);
dev_dbg(vtl->module_dev,
"Add VTL0 memory: start: 0x%llx, end_pfn: 0x%llx, page order:
%lu\n",
vtl0_mem.start_pfn, vtl0_mem.last_pfn, pgmap->vmemmap_shift);
@@ -415,7 +421,7 @@ static int mshv_vtl_ioctl_add_vtl0_mem(struct mshv_vtl
*vtl, void __user *arg)
if (IS_ERR(addr)) {
dev_err(vtl->module_dev, "devm_memremap_pages error: %ld\n",
PTR_ERR(addr));
kfree(pgmap);
- return -EFAULT;
+ return PTR_ERR(addr);
}
/* Don't free pgmap, since it has to stick around until the memory
diff --git a/include/uapi/linux/mshv.h b/include/uapi/linux/mshv.h
index e0645a34b55b..32ff92b6342b 100644
--- a/include/uapi/linux/mshv.h
+++ b/include/uapi/linux/mshv.h
@@ -357,7 +357,7 @@ struct mshv_vtl_sint_post_msg {
struct mshv_vtl_ram_disposition {
__u64 start_pfn;
- __u64 last_pfn;
+ __u64 last_pfn; /* last_pfn is excluded from the range [start_pfn,
last_pfn) */
};
struct mshv_vtl_set_poll_file {
--
2.43.0
