[RFC PATCH] RISC-V: KVM: Add minimal guest_memfd support

[Bingyu.Xian]

Add minimal guest_memfd support for RISC-V KVM, following the same
pattern as x86 and arm64.

1. Select KVM_GUEST_MEMFD in Kconfig
2. In kvm_riscv_mmu_map(), check kvm_slot_has_gmem() early, before
   taking mmap_read_lock(). For gmem memslots, resolve the PFN via
   kvm_gmem_get_pfn(), then acquire kvm->mmu_lock and jump to G-stage
   mapping, bypassing vma_lookup()/__kvm_faultin_pfn(). The gmem PFN
   is resolved before mmap_read_lock() so the mmu_lock taken for the
   mapping is never held while waiting for mmap_lock, which would
   deadlock against mmu_notifier invalidation (mmu_lock -> mmap_lock).
3. Skip kvm_release_faultin_page() for gmem pages; their lifetime is
   managed by the gmem inode and invalidation notifiers.

Verified: defconfig + CONFIG_KVM_GUEST_MEMFD=y compiles cleanly.

Assisted-by: YuanSheng: deepseek-v4-pro
Co-developed-by: Quan Zhou <zhouquan at iscas.ac.cn>
Signed-off-by: Quan Zhou <zhouquan at iscas.ac.cn>
Signed-off-by: Bingyu Xian <shanbeeyoo at gmail.com>
---
 arch/riscv/kvm/Kconfig |  1 +
 arch/riscv/kvm/mmu.c   | 17 ++++++++++++++++-
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
index ec2cee0a39e0..77121100579f 100644
--- a/arch/riscv/kvm/Kconfig
+++ b/arch/riscv/kvm/Kconfig
@@ -29,6 +29,7 @@ config KVM
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_GENERIC_HARDWARE_ENABLING
 	select KVM_MMIO
+	select KVM_GUEST_MEMFD
 	select VIRT_XFER_TO_GUEST_WORK
 	select SCHED_INFO
 	select GUEST_PERF_EVENTS if PERF_EVENTS
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index d2a06a54be17..a9d61d0366e2 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -557,6 +557,19 @@ int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 	/* Setup initial state of output mapping */
 	memset(out_map, 0, sizeof(*out_map));
 
+	if (kvm_slot_has_gmem(memslot)) {
+		int max_order;
+
+		ret = kvm_gmem_get_pfn(kvm, memslot, gfn, &hfn, &page, &max_order);
+		if (ret)
+			return ret;
+
+		vma_pagesize = PAGE_SIZE;
+		writable = true;
+		write_lock(&kvm->mmu_lock);
+		goto map_gstage;
+	}
+
 	if (is_write && logging &&
 	    kvm_riscv_mmu_dirty_log_write_fault_fast(kvm, memslot, gpa, out_map))
 		return 0;
@@ -643,6 +656,7 @@ int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 	if (!logging && !is_hugetlb && vma_pagesize == PAGE_SIZE)
 		vma_pagesize = transparent_hugepage_adjust(kvm, memslot, hva, &hfn, &gpa);
 
+map_gstage:
 	if (writable) {
 		mark_page_dirty_in_slot(kvm, memslot, gfn);
 		ret = kvm_riscv_gstage_map_page(&gstage, pcache, gpa, hfn << PAGE_SHIFT,
@@ -658,7 +672,8 @@ int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 		kvm_err("Failed to map in G-stage\n");
 
 out_unlock:
-	kvm_release_faultin_page(kvm, page, ret, writable);
+	if (!kvm_slot_has_gmem(memslot))
+		kvm_release_faultin_page(kvm, page, ret, writable);
 	write_unlock(&kvm->mmu_lock);
 	return ret;
 }
-- 
2.54.0