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.
Unified · Split
| @@ -386,7 +386,6 @@ static int mshv_vtl_ioctl_add_vtl0_mem(struct mshv_vtl *vtl, void __user *arg) · 385 unmodified lines | ||
| 386 | 386 | |
| 387 | 387 | if (copy_from_user(&vtl0_mem, arg, sizeof(vtl0_mem))) |
| 388 | 388 | return -EFAULT; |
| 389 | − /* vtl0_mem.last_pfn is excluded in the pagemap range for VTL0 as per design */ | |
| 390 | 389 | if (vtl0_mem.last_pfn <= vtl0_mem.start_pfn) { |
| 391 | 390 | dev_err(vtl->module_dev, "range start pfn (%llx) > end pfn (%llx)\n", |
| 392 | 391 | 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) · 4 unmodified lines | ||
| 397 | 396 | if (!pgmap) |
| 398 | 397 | return -ENOMEM; |
| 399 | 398 | |
| 399 | + /* | |
| 400 | + * vtl0_mem.last_pfn is excluded in the pagemap range for VTL0 as per design. | |
| 401 | + * last_pfn is not reserved or wasted, and reflects 'start_pfn + size' of pagemap range. | |
| 402 | + */ | |
| 400 | 403 | pgmap->ranges[0].start = PFN_PHYS(vtl0_mem.start_pfn); |
| 401 | 404 | pgmap->ranges[0].end = PFN_PHYS(vtl0_mem.last_pfn) - 1; |
| 402 | 405 | pgmap->nr_range = 1; |
| @@ -405,8 +408,11 @@ static int mshv_vtl_ioctl_add_vtl0_mem(struct mshv_vtl *vtl, void __user *arg) · 2 unmodified lines | ||
| 405 | 408 | /* |
| 406 | 409 | * Determine the highest page order that can be used for the given memory range. |
| 407 | 410 | * This works best when the range is aligned; i.e. both the start and the length. |
| 411 | + * Clamp to MAX_FOLIO_ORDER to avoid a WARN in memremap_pages() when the range | |
| 412 | + * alignment exceeds the maximum supported folio order for this kernel config. | |
| 408 | 413 | */ |
| 409 | − pgmap->vmemmap_shift = count_trailing_zeros(vtl0_mem.start_pfn | vtl0_mem.last_pfn); | |
| 414 | + pgmap->vmemmap_shift = min(count_trailing_zeros(vtl0_mem.start_pfn | vtl0_mem.last_pfn), | |
| 415 | + MAX_FOLIO_ORDER); | |
| 410 | 416 | dev_dbg(vtl->module_dev, |
| 411 | 417 | "Add VTL0 memory: start: 0x%llx, end_pfn: 0x%llx, page order: %lu\n", |
| 412 | 418 | 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) · 2 unmodified lines | ||
| 415 | 421 | if (IS_ERR(addr)) { |
| 416 | 422 | dev_err(vtl->module_dev, "devm_memremap_pages error: %ld\n", PTR_ERR(addr)); |
| 417 | 423 | kfree(pgmap); |
| 418 | − return -EFAULT; | |
| 424 | + return PTR_ERR(addr); | |
| 419 | 425 | } |
| 420 | 426 | |
| 421 | 427 | /* Don't free pgmap, since it has to stick around until the memory |
| @@ -357,7 +357,7 @@ struct mshv_vtl_sint_post_msg { · 356 unmodified lines | ||
| 357 | 357 | |
| 358 | 358 | struct mshv_vtl_ram_disposition { |
| 359 | 359 | __u64 start_pfn; |
| 360 | − __u64 last_pfn; | |
| 360 | + __u64 last_pfn; /* last_pfn is excluded from the range [start_pfn, last_pfn) */ | |
| 361 | 361 | }; |
| 362 | 362 | |
| 363 | 363 | struct mshv_vtl_set_poll_file { |