On 17.11.25 12:46, Mike Rapoport wrote:
From: "Mike Rapoport (Microsoft)" rppt@kernel.org
- Export handle_userfault() for KVM module so that fault() handler in guest_memfd would be able to notify userspace about page faults in its address space.
- Implement get_pagecache_folio() for guest_memfd.
- And finally, introduce UFFD_FEATURE_MINOR_GENERIC that will allow using userfaultfd minor mode with memory types other than shmem and hugetlb provided they are allowed to call handle_userfault() and implement get_pagecache_folio().
Signed-off-by: Mike Rapoport (Microsoft) rppt@kernel.org
fs/userfaultfd.c | 4 +++- include/uapi/linux/userfaultfd.h | 8 +++++++- virt/kvm/guest_memfd.c | 30 ++++++++++++++++++++++++++++++ 3 files changed, 40 insertions(+), 2 deletions(-)
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 54c6cc7fe9c6..964fa2662d5c 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -537,6 +537,7 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) out: return ret; } +EXPORT_SYMBOL_FOR_MODULES(handle_userfault, "kvm"); static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, struct userfaultfd_wait_queue *ewq) @@ -1978,7 +1979,8 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, uffdio_api.features = UFFD_API_FEATURES; #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR uffdio_api.features &=
~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM);
~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM |UFFD_FEATURE_MINOR_GENERIC);diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 2841e4ea8f2c..c5cbd4a5a26e 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -42,7 +42,8 @@ UFFD_FEATURE_WP_UNPOPULATED | \ UFFD_FEATURE_POISON | \ UFFD_FEATURE_WP_ASYNC | \
UFFD_FEATURE_MOVE)
UFFD_FEATURE_MOVE | \UFFD_FEATURE_MINOR_GENERIC)@@ -210,6 +211,10 @@ struct uffdio_api { * UFFD_FEATURE_MINOR_SHMEM indicates the same support as * UFFD_FEATURE_MINOR_HUGETLBFS, but for shmem-backed pages instead. *
* UFFD_FEATURE_MINOR_GENERIC indicates that minor faults can be* intercepted for file-backed memory in case subsystem backing this* memory supports it.*
- UFFD_FEATURE_EXACT_ADDRESS indicates that the exact address of page
- faults would be provided and the offset within the page would not be
- masked.
@@ -248,6 +253,7 @@ struct uffdio_api { #define UFFD_FEATURE_POISON (1<<14) #define UFFD_FEATURE_WP_ASYNC (1<<15) #define UFFD_FEATURE_MOVE (1<<16) +#define UFFD_FEATURE_MINOR_GENERIC (1<<17) __u64 features; __u64 ioctls; diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index fbca8c0972da..5e3c63307fdf 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -4,6 +4,7 @@ #include <linux/kvm_host.h> #include <linux/pagemap.h> #include <linux/anon_inodes.h> +#include <linux/userfaultfd_k.h> #include "kvm_mm.h" @@ -369,6 +370,12 @@ static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf) return vmf_error(err); }
- if (userfaultfd_minor(vmf->vma)) {
folio_unlock(folio);folio_put(folio);return handle_userfault(vmf, VM_UFFD_MINOR);- }
Staring at things like VM_FAULT_NEEDDSYNC, I'm wondering whether we could have a new return value from ->fault that would indicate that handle_userfault(vmf, VM_UFFD_MINOR) should be called.
Maybe some VM_FAULT_UFFD_MINOR or simply VM_FAULT_USERFAULTFD and we can just derive that it is VM_UFFD_MINOR.
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 4f66a3206a63c..2cf17da880f0e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1601,6 +1601,8 @@ typedef __bitwise unsigned int vm_fault_t; * fsync() to complete (for synchronous page faults * in DAX) * @VM_FAULT_COMPLETED: ->fault completed, meanwhile mmap lock released + * @VM_FAULT_USERFAULTFD: ->fault did not modify page tables and needs + * handle_userfault() to complete * @VM_FAULT_HINDEX_MASK: mask HINDEX value * */ @@ -1618,6 +1620,7 @@ enum vm_fault_reason { VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, VM_FAULT_COMPLETED = (__force vm_fault_t)0x004000, + VM_FAULT_USERFAULTFD = (__force vm_fault_t)0x006000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, };
@@ -1642,6 +1645,7 @@ enum vm_fault_reason { { VM_FAULT_FALLBACK, "FALLBACK" }, \ { VM_FAULT_DONE_COW, "DONE_COW" }, \ { VM_FAULT_NEEDDSYNC, "NEEDDSYNC" }, \ + { VM_FAULT_USERFAULTFD, "USERFAULTFD" },\ { VM_FAULT_COMPLETED, "COMPLETED" }
struct vm_special_mapping {
IIUC, we have exactly two invocations of ->fault(vmf) in memory.c where we would have to handle it IIUC. And the return value would never leave the core.
That way, we wouldn't have to export handle_userfault().
Just a thought ...