Backport subject : 'Svvptc extension to remove preventive sfence.vma'

arch/riscv/include/asm/cacheflush.h

@@ -43,7 +43,23 @@ static inline void flush_dcache_page(struct page *page)
 	flush_icache_mm(vma->vm_mm, 0)
 
 #ifdef CONFIG_64BIT
-#define flush_cache_vmap(start, end)		flush_tlb_kernel_range(start, end)
+extern u64 new_vmalloc[NR_CPUS / sizeof(u64) + 1];
+extern char _end[];
+#define flush_cache_vmap flush_cache_vmap
+static inline void flush_cache_vmap(unsigned long start, unsigned long end)
+{
+	if (is_vmalloc_or_module_addr((void *)start)) {
+		int i;
+
+		/*
+		 * We don't care if concurrently a cpu resets this value since
+		 * the only place this can happen is in handle_exception() where
+		 * an sfence.vma is emitted.
+		 */
+		for (i = 0; i < ARRAY_SIZE(new_vmalloc); ++i)
+			new_vmalloc[i] = -1ULL;
+	}
+}
 #define flush_cache_vmap_early(start, end)	local_flush_tlb_kernel_range(start, end)
 #endif
 

arch/riscv/include/asm/pgtable.h

@@ -493,6 +493,9 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
 		struct vm_area_struct *vma, unsigned long address,
 		pte_t *ptep, unsigned int nr)
 {
+	asm goto(ALTERNATIVE("nop", "j %l[svvptc]", 0, RISCV_ISA_EXT_SVVPTC, 1)
+		 : : : : svvptc);
+
 	/*
 	 * The kernel assumes that TLBs don't cache invalid entries, but
 	 * in RISC-V, SFENCE.VMA specifies an ordering constraint, not a
@@ -502,12 +505,23 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
 	 */
 	while (nr--)
 		local_flush_tlb_page(address + nr * PAGE_SIZE);
+
+svvptc:;
+	/*
+	 * Svvptc guarantees that the new valid pte will be visible within
+	 * a bounded timeframe, so when the uarch does not cache invalid
+	 * entries, we don't have to do anything.
+	 */
 }
 #define update_mmu_cache(vma, addr, ptep) \
 	update_mmu_cache_range(NULL, vma, addr, ptep, 1)
 
 #define __HAVE_ARCH_UPDATE_MMU_TLB
-#define update_mmu_tlb update_mmu_cache
+static inline void update_mmu_tlb(struct vm_area_struct *vma,
+				  unsigned long address, pte_t *ptep)
+{
+	flush_tlb_range(vma, address, address + PAGE_SIZE);
+}
 
 static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
 		unsigned long address, pmd_t *pmdp)

arch/riscv/include/asm/thread_info.h

@@ -61,6 +61,13 @@ struct thread_info {
 	long			user_sp;	/* User stack pointer */
 	int			cpu;
 	unsigned long		syscall_work;	/* SYSCALL_WORK_ flags */
+#ifdef CONFIG_64BIT
+	/*
+	 * Used in handle_exception() to save a0, a1 and a2 before knowing if we
+	 * can access the kernel stack.
+	 */
+	unsigned long		a0, a1, a2;
+#endif
 };
 
 /*

arch/riscv/kernel/asm-offsets.c

@@ -32,6 +32,8 @@ void asm_offsets(void)
 	OFFSET(TASK_THREAD_S9, task_struct, thread.s[9]);
 	OFFSET(TASK_THREAD_S10, task_struct, thread.s[10]);
 	OFFSET(TASK_THREAD_S11, task_struct, thread.s[11]);
+
+	OFFSET(TASK_TI_CPU, task_struct, thread_info.cpu);
 	OFFSET(TASK_TI_FLAGS, task_struct, thread_info.flags);
 	OFFSET(TASK_TI_PREEMPT_COUNT, task_struct, thread_info.preempt_count);
 	OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp);
@@ -74,6 +76,11 @@ void asm_offsets(void)
 #ifdef CONFIG_STACKPROTECTOR
 	OFFSET(TSK_STACK_CANARY, task_struct, stack_canary);
 #endif
+#ifdef CONFIG_64BIT
+	OFFSET(TASK_TI_A0, task_struct, thread_info.a0);
+	OFFSET(TASK_TI_A1, task_struct, thread_info.a1);
+	OFFSET(TASK_TI_A2, task_struct, thread_info.a2);
+#endif
 
 	DEFINE(PT_SIZE, sizeof(struct pt_regs));
 	OFFSET(PT_EPC, pt_regs, epc);

arch/riscv/kernel/entry.S

@@ -18,6 +18,79 @@
 
 	.section .irqentry.text, "ax"
 
+.macro new_vmalloc_check
+	REG_S 	a0, TASK_TI_A0(tp)
+	csrr 	a0, CSR_CAUSE
+	/* Exclude IRQs */
+	blt  	a0, zero, _new_vmalloc_restore_context_a0
+
+	REG_S 	a1, TASK_TI_A1(tp)
+	/* Only check new_vmalloc if we are in page/protection fault */
+	li   	a1, EXC_LOAD_PAGE_FAULT
+	beq  	a0, a1, _new_vmalloc_kernel_address
+	li   	a1, EXC_STORE_PAGE_FAULT
+	beq  	a0, a1, _new_vmalloc_kernel_address
+	li   	a1, EXC_INST_PAGE_FAULT
+	bne  	a0, a1, _new_vmalloc_restore_context_a1
+
+_new_vmalloc_kernel_address:
+	/* Is it a kernel address? */
+	csrr 	a0, CSR_TVAL
+	bge 	a0, zero, _new_vmalloc_restore_context_a1
+
+	/* Check if a new vmalloc mapping appeared that could explain the trap */
+	REG_S	a2, TASK_TI_A2(tp)
+	/*
+	 * Computes:
+	 * a0 = &new_vmalloc[BIT_WORD(cpu)]
+	 * a1 = BIT_MASK(cpu)
+	 */
+	REG_L 	a2, TASK_TI_CPU(tp)
+	/*
+	 * Compute the new_vmalloc element position:
+	 * (cpu / 64) * 8 = (cpu >> 6) << 3
+	 */
+	srli	a1, a2, 6
+	slli	a1, a1, 3
+	la	a0, new_vmalloc
+	add	a0, a0, a1
+	/*
+	 * Compute the bit position in the new_vmalloc element:
+	 * bit_pos = cpu % 64 = cpu - (cpu / 64) * 64 = cpu - (cpu >> 6) << 6
+	 * 	   = cpu - ((cpu >> 6) << 3) << 3
+	 */
+	slli	a1, a1, 3
+	sub	a1, a2, a1
+	/* Compute the "get mask": 1 << bit_pos */
+	li	a2, 1
+	sll	a1, a2, a1
+
+	/* Check the value of new_vmalloc for this cpu */
+	REG_L	a2, 0(a0)
+	and	a2, a2, a1
+	beq	a2, zero, _new_vmalloc_restore_context
+
+	/* Atomically reset the current cpu bit in new_vmalloc */
+	amoxor.d	a0, a1, (a0)
+
+	/* Only emit a sfence.vma if the uarch caches invalid entries */
+	ALTERNATIVE("sfence.vma", "nop", 0, RISCV_ISA_EXT_SVVPTC, 1)
+
+	REG_L	a0, TASK_TI_A0(tp)
+	REG_L	a1, TASK_TI_A1(tp)
+	REG_L	a2, TASK_TI_A2(tp)
+	csrw	CSR_SCRATCH, x0
+	sret
+
+_new_vmalloc_restore_context:
+	REG_L 	a2, TASK_TI_A2(tp)
+_new_vmalloc_restore_context_a1:
+	REG_L 	a1, TASK_TI_A1(tp)
+_new_vmalloc_restore_context_a0:
+	REG_L	a0, TASK_TI_A0(tp)
+.endm
+
+
 SYM_CODE_START(handle_exception)
 	/*
 	 * If coming from userspace, preserve the user thread pointer and load
@@ -29,6 +102,20 @@ SYM_CODE_START(handle_exception)
 
 _restore_kernel_tpsp:
 	csrr tp, CSR_SCRATCH
+
+#ifdef CONFIG_64BIT
+	/*
+	 * The RISC-V kernel does not eagerly emit a sfence.vma after each
+	 * new vmalloc mapping, which may result in exceptions:
+	 * - if the uarch caches invalid entries, the new mapping would not be
+	 *   observed by the page table walker and an invalidation is needed.
+	 * - if the uarch does not cache invalid entries, a reordered access
+	 *   could "miss" the new mapping and traps: in that case, we only need
+	 *   to retry the access, no sfence.vma is required.
+	 */
+	new_vmalloc_check
+#endif
+
 	REG_S sp, TASK_TI_KERNEL_SP(tp)
 
 #ifdef CONFIG_VMAP_STACK

arch/riscv/mm/init.c

@@ -42,6 +42,8 @@
 extern phys_addr_t __init_memblock find_max_low_addr(phys_addr_t limit);
 #endif
 
+u64 new_vmalloc[NR_CPUS / sizeof(u64) + 1];
+
 struct kernel_mapping kernel_map __ro_after_init;
 EXPORT_SYMBOL(kernel_map);
 #ifdef CONFIG_XIP_KERNEL

arch/riscv/mm/pgtable.c

@@ -9,13 +9,26 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 			  unsigned long address, pte_t *ptep,
 			  pte_t entry, int dirty)
 {
+	asm goto(ALTERNATIVE("nop", "j %l[svvptc]", 0, RISCV_ISA_EXT_SVVPTC, 1)
+		 : : : : svvptc);
+
 	if (!pte_same(ptep_get(ptep), entry))
 		__set_pte_at(vma->vm_mm, address, ptep, entry);
 	/*
 	 * update_mmu_cache will unconditionally execute, handling both
 	 * the case that the PTE changed and the spurious fault case.
 	 */
 	return true;
+
+svvptc:
+	if (!pte_same(ptep_get(ptep), entry)) {
+		__set_pte_at(vma->vm_mm, address, ptep, entry);
+		/* Here only not svadu is impacted */
+		flush_tlb_page(vma, address);
+		return true;
+	}
+
+	return false;
 }
 
 int ptep_test_and_clear_young(struct vm_area_struct *vma,