Merge patch series "Svvptc extension to remove preventive sfence.vma"

Alexandre Ghiti <alexghiti@rivosinc.com> says:

In RISC-V, after a new mapping is established, a sfence.vma needs to be
emitted for different reasons:

- if the uarch caches invalid entries, we need to invalidate it otherwise
  we would trap on this invalid entry,
- if the uarch does not cache invalid entries, a reordered access could fail
  to see the new mapping and then trap (sfence.vma acts as a fence).

We can actually avoid emitting those (mostly) useless and costly sfence.vma
by handling the traps instead:

- for new kernel mappings: only vmalloc mappings need to be taken care of,
  other new mapping are rare and already emit the required sfence.vma if
  needed.
  That must be achieved very early in the exception path as explained in
  patch 3, and this also fixes our fragile way of dealing with vmalloc faults.

- for new user mappings: Svvptc makes update_mmu_cache() a no-op but we can
  take some gratuitous page faults (which are very unlikely though).

Patch 1 and 2 introduce Svvptc extension probing.

On our uarch that does not cache invalid entries and a 6.5 kernel, the
gains are measurable:

* Kernel boot:                  6%
* ltp - mmapstress01:           8%
* lmbench - lat_pagefault:      20%
* lmbench - lat_mmap:           5%

Here are the corresponding numbers of sfence.vma emitted:

* Ubuntu boot to login:
Before: ~630k sfence.vma
After:  ~200k sfence.vma

* ltp - mmapstress01
Before: ~45k
After:  ~6.3k

* lmbench - lat_pagefault
Before: ~665k
After:   832 (!)

* lmbench - lat_mmap
Before: ~546k
After:   718 (!)

Thanks to Ved and Matt Evans for triggering the discussion that led to
this patchset!

* b4-shazam-merge:
  riscv: Stop emitting preventive sfence.vma for new userspace mappings with Svvptc
  riscv: Stop emitting preventive sfence.vma for new vmalloc mappings
  dt-bindings: riscv: Add Svvptc ISA extension description
  riscv: Add ISA extension parsing for Svvptc

Link: https://lore.kernel.org/r/20240717060125.139416-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

9 files changed, 145 insertions, 1 deletions

diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index ce79c558a4c8..8de73f91bfa3 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -46,7 +46,23 @@ do {							\
 } while (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
 
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 5a0bd27fd11a..46d9de54179e 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -92,6 +92,7 @@
 #define RISCV_ISA_EXT_ZCF		83
 #define RISCV_ISA_EXT_ZCMOP		84
 #define RISCV_ISA_EXT_ZAWRS		85
+#define RISCV_ISA_EXT_SVVPTC		86
 
 #define RISCV_ISA_EXT_XLINUXENVCFG	127
 
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index ede2f921967c..e79f15293492 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -497,6 +497,9 @@ 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
@@ -506,6 +509,13 @@ 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)
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 5b09dc874151..ebe52f96da34 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -61,6 +61,13 @@ struct thread_info {
 	void			*scs_base;
 	void			*scs_sp;
 #endif
+#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
 };
 
 #ifdef CONFIG_SHADOW_CALL_STACK
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index b09ca5f944f7..e94180ba432f 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -36,6 +36,8 @@ 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);
@@ -43,6 +45,11 @@ void asm_offsets(void)
 #ifdef CONFIG_SHADOW_CALL_STACK
 	OFFSET(TASK_TI_SCS_SP, task_struct, thread_info.scs_sp);
 #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
 
 	OFFSET(TASK_TI_CPU_NUM, task_struct, thread_info.cpu);
 	OFFSET(TASK_THREAD_F0,  task_struct, thread.fstate.f[0]);
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index b427188b28fc..3a8eeaa9310c 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -381,6 +381,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL),
 	__RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT),
 	__RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT),
+	__RISCV_ISA_EXT_DATA(svvptc, RISCV_ISA_EXT_SVVPTC),
 };
 
 const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext);
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index ac2e908d4418..fc41472d512e 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -19,6 +19,79 @@
 
 	.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
@@ -30,6 +103,20 @@ SYM_CODE_START(handle_exception)
 
 .Lrestore_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
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 0e56725377a4..206bae58ed6c 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -37,6 +37,8 @@
 
 #include "../kernel/head.h"
 
+u64 new_vmalloc[NR_CPUS / sizeof(u64) + 1];
+
 struct kernel_mapping kernel_map __ro_after_init;
 EXPORT_SYMBOL(kernel_map);
 #ifdef CONFIG_XIP_KERNEL
diff --git a/arch/riscv/mm/pgtable.c b/arch/riscv/mm/pgtable.c
index 533ec9055fa0..4ae67324f992 100644
--- a/arch/riscv/mm/pgtable.c
+++ b/arch/riscv/mm/pgtable.c
@@ -9,6 +9,9 @@ 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, ptep, entry);
 	/*
@@ -16,6 +19,16 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 	 * 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, 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,