Add Grace virtualization support to 6.14 HWE, (upstream vEVENTQ + HW QUEUE and OOT vEGM

Documentation/userspace-api/iommufd.rst

@@ -63,6 +63,13 @@ Following IOMMUFD objects are exposed to userspace:
   space usually has mappings from guest-level I/O virtual addresses to guest-
   level physical addresses.
 
+- IOMMUFD_FAULT, representing a software queue for an HWPT reporting IO page
+  faults using the IOMMU HW's PRI (Page Request Interface). This queue object
+  provides user space an FD to poll the page fault events and also to respond
+  to those events. A FAULT object must be created first to get a fault_id that
+  could be then used to allocate a fault-enabled HWPT via the IOMMU_HWPT_ALLOC
+  command by setting the IOMMU_HWPT_FAULT_ID_VALID bit in its flags field.
+
 - IOMMUFD_OBJ_VIOMMU, representing a slice of the physical IOMMU instance,
   passed to or shared with a VM. It may be some HW-accelerated virtualization
   features and some SW resources used by the VM. For examples:
@@ -109,6 +116,25 @@ Following IOMMUFD objects are exposed to userspace:
   vIOMMU, which is a separate ioctl call from attaching the same device to an
   HWPT_PAGING that the vIOMMU holds.
 
+- IOMMUFD_OBJ_VEVENTQ, representing a software queue for a vIOMMU to report its
+  events such as translation faults occurred to a nested stage-1 (excluding I/O
+  page faults that should go through IOMMUFD_OBJ_FAULT) and HW-specific events.
+  This queue object provides user space an FD to poll/read the vIOMMU events. A
+  vIOMMU object must be created first to get its viommu_id, which could be then
+  used to allocate a vEVENTQ. Each vIOMMU can support multiple types of vEVENTS,
+  but is confined to one vEVENTQ per vEVENTQ type.
+
+- IOMMUFD_OBJ_HW_QUEUE, representing a hardware accelerated queue, as a subset
+  of IOMMU's virtualization features, for the IOMMU HW to directly read or write
+  the virtual queue memory owned by a guest OS. This HW-acceleration feature can
+  allow VM to work with the IOMMU HW directly without a VM Exit, so as to reduce
+  overhead from the hypercalls. Along with the HW QUEUE object, iommufd provides
+  user space an mmap interface for VMM to mmap a physical MMIO region from the
+  host physical address space to the guest physical address space, allowing the
+  guest OS to directly control the allocated HW QUEUE. Thus, when allocating a
+  HW QUEUE, the VMM must request a pair of mmap info (offset/length) and pass in
+  exactly to an mmap syscall via its offset and length arguments.
+
 All user-visible objects are destroyed via the IOMMU_DESTROY uAPI.
 
 The diagrams below show relationships between user-visible objects and kernel
@@ -251,8 +277,11 @@ User visible objects are backed by following datastructures:
 - iommufd_device for IOMMUFD_OBJ_DEVICE.
 - iommufd_hwpt_paging for IOMMUFD_OBJ_HWPT_PAGING.
 - iommufd_hwpt_nested for IOMMUFD_OBJ_HWPT_NESTED.
+- iommufd_fault for IOMMUFD_OBJ_FAULT.
 - iommufd_viommu for IOMMUFD_OBJ_VIOMMU.
 - iommufd_vdevice for IOMMUFD_OBJ_VDEVICE.
+- iommufd_veventq for IOMMUFD_OBJ_VEVENTQ.
+- iommufd_hw_queue for IOMMUFD_OBJ_HW_QUEUE.
 
 Several terminologies when looking at these datastructures:
 

arch/arm64/configs/defconfig

@@ -1762,3 +1762,12 @@ CONFIG_CORESIGHT_STM=m
 CONFIG_CORESIGHT_CPU_DEBUG=m
 CONFIG_CORESIGHT_CTI=m
 CONFIG_MEMTEST=y
+CONFIG_NVGRACE_GPU_VFIO_PCI=m
+CONFIG_NVGRACE_EGM=m
+CONFIG_VFIO_DEVICE_CDEV=y
+# CONFIG_VFIO_CONTAINER is not set
+CONFIG_FAULT_INJECTION=y
+CONFIG_IOMMUFD_DRIVER=y
+CONFIG_IOMMUFD=y
+CONFIG_IOMMUFD_TEST=y
+CONFIG_IOMMUFD_VFIO_CONTAINER=y

arch/arm64/kvm/mmu.c

@@ -1472,6 +1472,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	bool s2_force_noncacheable = false, vfio_allow_any_uc = false;
 	unsigned long mmu_seq;
 	phys_addr_t ipa = fault_ipa;
+	unsigned long mt;
 	struct kvm *kvm = vcpu->kvm;
 	struct vm_area_struct *vma;
 	short vma_shift;
@@ -1593,6 +1594,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		vma_pagesize = min(vma_pagesize, (long)max_map_size);
 	}
 
+	mt = FIELD_GET(PTE_ATTRINDX_MASK, pgprot_val(vma->vm_page_prot));
+
 	/*
 	 * Both the canonical IPA and fault IPA must be hugepage-aligned to
 	 * ensure we find the right PFN and lay down the mapping in the right
@@ -1676,7 +1679,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		writable = false;
 	}
 
-	if (exec_fault && s2_force_noncacheable)
+	if (exec_fault && s2_force_noncacheable && mt != MT_NORMAL)
 		return -ENOEXEC;
 
 	/*

arch/um/kernel/um_arch.c

@@ -440,25 +440,24 @@ void __init arch_cpu_finalize_init(void)
 	os_check_bugs();
 }
 
-void apply_seal_endbr(s32 *start, s32 *end, struct module *mod)
+void apply_seal_endbr(s32 *start, s32 *end)
 {
 }
 
-void apply_retpolines(s32 *start, s32 *end, struct module *mod)
+void apply_retpolines(s32 *start, s32 *end)
 {
 }
 
-void apply_returns(s32 *start, s32 *end, struct module *mod)
+void apply_returns(s32 *start, s32 *end)
 {
 }
 
 void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
-		   s32 *start_cfi, s32 *end_cfi, struct module *mod)
+		   s32 *start_cfi, s32 *end_cfi)
 {
 }
 
-void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
-			struct module *mod)
+void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
 {
 }
 

arch/x86/entry/vdso/vma.c

@@ -48,8 +48,7 @@ int __init init_vdso_image(const struct vdso_image *image)
 
 	apply_alternatives((struct alt_instr *)(image->data + image->alt),
 			   (struct alt_instr *)(image->data + image->alt +
-						image->alt_len),
-			   NULL);
+						image->alt_len));
 
 	return 0;
 }

arch/x86/events/core.c

@@ -2845,7 +2845,7 @@ static bool is_uprobe_at_func_entry(struct pt_regs *regs)
 		return true;
 
 	/* endbr64 (64-bit only) */
-	if (user_64bit_mode(regs) && is_endbr(*(u32 *)auprobe->insn))
+	if (user_64bit_mode(regs) && is_endbr((u32 *)auprobe->insn))
 		return true;
 
 	return false;

arch/x86/include/asm/alternative.h

@@ -87,16 +87,16 @@ extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
  * instructions were patched in already:
  */
 extern int alternatives_patched;
-struct module;
 
 extern void alternative_instructions(void);
-extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
-			       struct module *mod);
-extern void apply_retpolines(s32 *start, s32 *end, struct module *mod);
-extern void apply_returns(s32 *start, s32 *end, struct module *mod);
-extern void apply_seal_endbr(s32 *start, s32 *end, struct module *mod);
+extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+extern void apply_retpolines(s32 *start, s32 *end);
+extern void apply_returns(s32 *start, s32 *end);
+extern void apply_seal_endbr(s32 *start, s32 *end);
 extern void apply_fineibt(s32 *start_retpoline, s32 *end_retpoine,
-			  s32 *start_cfi, s32 *end_cfi, struct module *mod);
+			  s32 *start_cfi, s32 *end_cfi);
+
+struct module;
 
 struct callthunk_sites {
 	s32				*call_start, *call_end;

arch/x86/include/asm/ftrace.h

@@ -36,21 +36,9 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 
 static inline unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip)
 {
-#ifdef CONFIG_X86_KERNEL_IBT
-	u32 instr;
-
-	/* We want to be extra safe in case entry ip is on the page edge,
-	 * but otherwise we need to avoid get_kernel_nofault()'s overhead.
-	 */
-	if ((fentry_ip & ~PAGE_MASK) < ENDBR_INSN_SIZE) {
-		if (get_kernel_nofault(instr, (u32 *)(fentry_ip - ENDBR_INSN_SIZE)))
-			return fentry_ip;
-	} else {
-		instr = *(u32 *)(fentry_ip - ENDBR_INSN_SIZE);
-	}
-	if (is_endbr(instr))
+	if (is_endbr((void*)(fentry_ip - ENDBR_INSN_SIZE)))
 		fentry_ip -= ENDBR_INSN_SIZE;
-#endif
+
 	return fentry_ip;
 }
 #define ftrace_get_symaddr(fentry_ip)	arch_ftrace_get_symaddr(fentry_ip)

arch/x86/include/asm/ibt.h

@@ -65,7 +65,7 @@ static inline __attribute_const__ u32 gen_endbr_poison(void)
 	return 0x001f0f66; /* osp nopl (%rax) */
 }
 
-static inline bool is_endbr(u32 val)
+static inline bool __is_endbr(u32 val)
 {
 	if (val == gen_endbr_poison())
 		return true;
@@ -74,6 +74,7 @@ static inline bool is_endbr(u32 val)
 	return val == gen_endbr();
 }
 
+extern __noendbr bool is_endbr(u32 *val);
 extern __noendbr u64 ibt_save(bool disable);
 extern __noendbr void ibt_restore(u64 save);
 
@@ -98,7 +99,7 @@ extern __noendbr void ibt_restore(u64 save);
 
 #define __noendbr
 
-static inline bool is_endbr(u32 val) { return false; }
+static inline bool is_endbr(u32 *val) { return false; }
 
 static inline u64 ibt_save(bool disable) { return 0; }
 static inline void ibt_restore(u64 save) { }