LoongArch: Add KFENCE (Kernel Electric-Fence) support

The LoongArch architecture is quite different from other architectures.
When the allocating of KFENCE itself is done, it is mapped to the direct
mapping configuration window [1] by default on LoongArch.  It means that
it is not possible to use the page table mapped mode which required by
the KFENCE system and therefore it should be remapped to the appropriate
region.

This patch adds architecture specific implementation details for KFENCE.
In particular, this implements the required interface in <asm/kfence.h>.

Tested this patch by running the testcases and all passed.

[1] https://loongson.github.io/LoongArch-Documentation/LoongArch-Vol1-EN.html#virtual-address-space-and-address-translation-mode

Signed-off-by: Enze Li <lienze@kylinos.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

Author: lienze

arch/loongarch/Kconfig

@@ -92,6 +92,7 @@ config LOONGARCH
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
+	select HAVE_ARCH_KFENCE
 	select HAVE_ARCH_KGDB if PERF_EVENTS
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
 	select HAVE_ARCH_SECCOMP_FILTER

arch/loongarch/include/asm/kfence.h

@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * KFENCE support for LoongArch.
+ *
+ * Author: Enze Li <lienze@kylinos.cn>
+ * Copyright (C) 2022-2023 KylinSoft Corporation.
+ */
+
+#ifndef _ASM_LOONGARCH_KFENCE_H
+#define _ASM_LOONGARCH_KFENCE_H
+
+#include <linux/kfence.h>
+#include <asm/pgtable.h>
+#include <asm/tlb.h>
+
+static inline bool arch_kfence_init_pool(void)
+{
+	int err;
+	char *kfence_pool = __kfence_pool;
+	struct vm_struct *area;
+
+	area = __get_vm_area_caller(KFENCE_POOL_SIZE, VM_IOREMAP,
+				    KFENCE_AREA_START, KFENCE_AREA_END,
+				    __builtin_return_address(0));
+	if (!area)
+		return false;
+
+	__kfence_pool = (char *)area->addr;
+	err = ioremap_page_range((unsigned long)__kfence_pool,
+				 (unsigned long)__kfence_pool + KFENCE_POOL_SIZE,
+				 virt_to_phys((void *)kfence_pool), PAGE_KERNEL);
+	if (err) {
+		free_vm_area(area);
+		__kfence_pool = kfence_pool;
+		return false;
+	}
+
+	return true;
+}
+
+/* Protect the given page and flush TLB. */
+static inline bool kfence_protect_page(unsigned long addr, bool protect)
+{
+	pte_t *pte = virt_to_kpte(addr);
+
+	if (WARN_ON(!pte) || pte_none(*pte))
+		return false;
+
+	if (protect)
+		set_pte(pte, __pte(pte_val(*pte) & ~(_PAGE_VALID | _PAGE_PRESENT)));
+	else
+		set_pte(pte, __pte(pte_val(*pte) | (_PAGE_VALID | _PAGE_PRESENT)));
+
+	preempt_disable();
+	local_flush_tlb_one(addr);
+	preempt_enable();
+
+	return true;
+}
+
+#endif /* _ASM_LOONGARCH_KFENCE_H */

arch/loongarch/include/asm/pgtable.h

@@ -82,14 +82,23 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #define MODULES_VADDR	(vm_map_base + PCI_IOSIZE + (2 * PAGE_SIZE))
 #define MODULES_END	(MODULES_VADDR + SZ_256M)
 
+#ifdef CONFIG_KFENCE
+#define KFENCE_AREA_SIZE	(((CONFIG_KFENCE_NUM_OBJECTS + 1) * 2 + 2) * PAGE_SIZE)
+#else
+#define KFENCE_AREA_SIZE	0
+#endif
+
 #define VMALLOC_START	MODULES_END
 #define VMALLOC_END	\
 	(vm_map_base +	\
-	 min(PTRS_PER_PGD * PTRS_PER_PUD * PTRS_PER_PMD * PTRS_PER_PTE * PAGE_SIZE, (1UL << cpu_vabits)) - PMD_SIZE - VMEMMAP_SIZE)
+	 min(PTRS_PER_PGD * PTRS_PER_PUD * PTRS_PER_PMD * PTRS_PER_PTE * PAGE_SIZE, (1UL << cpu_vabits)) - PMD_SIZE - VMEMMAP_SIZE - KFENCE_AREA_SIZE)
 
 #define vmemmap		((struct page *)((VMALLOC_END + PMD_SIZE) & PMD_MASK))
 #define VMEMMAP_END	((unsigned long)vmemmap + VMEMMAP_SIZE - 1)
 
+#define KFENCE_AREA_START	(VMEMMAP_END + 1)
+#define KFENCE_AREA_END		(KFENCE_AREA_START + KFENCE_AREA_SIZE - 1)
+
 #define pte_ERROR(e) \
 	pr_err("%s:%d: bad pte %016lx.\n", __FILE__, __LINE__, pte_val(e))
 #ifndef __PAGETABLE_PMD_FOLDED

arch/loongarch/mm/fault.c

@@ -23,21 +23,26 @@
 #include <linux/kprobes.h>
 #include <linux/perf_event.h>
 #include <linux/uaccess.h>
+#include <linux/kfence.h>
 
 #include <asm/branch.h>
 #include <asm/mmu_context.h>
 #include <asm/ptrace.h>
 
 int show_unhandled_signals = 1;
 
-static void __kprobes no_context(struct pt_regs *regs, unsigned long address)
+static void __kprobes no_context(struct pt_regs *regs,
+			unsigned long write, unsigned long address)
 {
 	const int field = sizeof(unsigned long) * 2;
 
 	/* Are we prepared to handle this kernel fault?	 */
 	if (fixup_exception(regs))
 		return;
 
+	if (kfence_handle_page_fault(address, write, regs))
+		return;
+
 	/*
 	 * Oops. The kernel tried to access some bad page. We'll have to
 	 * terminate things with extreme prejudice.
@@ -51,14 +56,15 @@ static void __kprobes no_context(struct pt_regs *regs, unsigned long address)
 	die("Oops", regs);
 }
 
-static void __kprobes do_out_of_memory(struct pt_regs *regs, unsigned long address)
+static void __kprobes do_out_of_memory(struct pt_regs *regs,
+			unsigned long write, unsigned long address)
 {
 	/*
 	 * We ran out of memory, call the OOM killer, and return the userspace
 	 * (which will retry the fault, or kill us if we got oom-killed).
 	 */
 	if (!user_mode(regs)) {
-		no_context(regs, address);
+		no_context(regs, write, address);
 		return;
 	}
 	pagefault_out_of_memory();
@@ -69,7 +75,7 @@ static void __kprobes do_sigbus(struct pt_regs *regs,
 {
 	/* Kernel mode? Handle exceptions or die */
 	if (!user_mode(regs)) {
-		no_context(regs, address);
+		no_context(regs, write, address);
 		return;
 	}
 
@@ -90,7 +96,7 @@ static void __kprobes do_sigsegv(struct pt_regs *regs,
 
 	/* Kernel mode? Handle exceptions or die */
 	if (!user_mode(regs)) {
-		no_context(regs, address);
+		no_context(regs, write, address);
 		return;
 	}
 
@@ -149,7 +155,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs,
 	 */
 	if (address & __UA_LIMIT) {
 		if (!user_mode(regs))
-			no_context(regs, address);
+			no_context(regs, write, address);
 		else
 			do_sigsegv(regs, write, address, si_code);
 		return;
@@ -211,7 +217,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs,
 
 	if (fault_signal_pending(fault, regs)) {
 		if (!user_mode(regs))
-			no_context(regs, address);
+			no_context(regs, write, address);
 		return;
 	}
 
@@ -232,7 +238,7 @@ static void __kprobes __do_page_fault(struct pt_regs *regs,
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		mmap_read_unlock(mm);
 		if (fault & VM_FAULT_OOM) {
-			do_out_of_memory(regs, address);
+			do_out_of_memory(regs, write, address);
 			return;
 		} else if (fault & VM_FAULT_SIGSEGV) {
 			do_sigsegv(regs, write, address, si_code);