Merge tag 'riscv-for-linus-6.10-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:

 - Add byte/half-word compare-and-exchange, emulated via LR/SC loops

 - Support for Rust

 - Support for Zihintpause in hwprobe

 - Add PR_RISCV_SET_ICACHE_FLUSH_CTX prctl()

 - Support lockless lockrefs

* tag 'riscv-for-linus-6.10-mw1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (42 commits)
  riscv: defconfig: Enable CONFIG_CLK_SOPHGO_CV1800
  riscv: select ARCH_HAS_FAST_MULTIPLIER
  riscv: mm: still create swiotlb buffer for kmalloc() bouncing if required
  riscv: Annotate pgtable_l{4,5}_enabled with __ro_after_init
  riscv: Remove redundant CONFIG_64BIT from pgtable_l{4,5}_enabled
  riscv: mm: Always use an ASID to flush mm contexts
  riscv: mm: Preserve global TLB entries when switching contexts
  riscv: mm: Make asid_bits a local variable
  riscv: mm: Use a fixed layout for the MM context ID
  riscv: mm: Introduce cntx2asid/cntx2version helper macros
  riscv: Avoid TLB flush loops when affected by SiFive CIP-1200
  riscv: Apply SiFive CIP-1200 workaround to single-ASID sfence.vma
  riscv: mm: Combine the SMP and UP TLB flush code
  riscv: Only send remote fences when some other CPU is online
  riscv: mm: Broadcast kernel TLB flushes only when needed
  riscv: Use IPIs for remote cache/TLB flushes by default
  riscv: Factor out page table TLB synchronization
  riscv: Flush the instruction cache during SMP bringup
  riscv: hwprobe: export Zihintpause ISA extension
  riscv: misaligned: remove CONFIG_RISCV_M_MODE specific code
  ...

5 files changed, 177 insertions, 85 deletions

diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
index 2c869f8026a8..cbe4d775ef56 100644
--- a/arch/riscv/mm/Makefile
+++ b/arch/riscv/mm/Makefile
@@ -13,14 +13,11 @@ endif
 KCOV_INSTRUMENT_init.o := n
 
 obj-y += init.o
-obj-$(CONFIG_MMU) += extable.o fault.o pageattr.o pgtable.o
+obj-$(CONFIG_MMU) += extable.o fault.o pageattr.o pgtable.o tlbflush.o
 obj-y += cacheflush.o
 obj-y += context.o
 obj-y += pmem.o
 
-ifeq ($(CONFIG_MMU),y)
-obj-$(CONFIG_SMP) += tlbflush.o
-endif
 obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
 obj-$(CONFIG_PTDUMP_CORE) += ptdump.o
 obj-$(CONFIG_KASAN)   += kasan_init.o
diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
index bc61ee5975e4..a03c994eed3b 100644
--- a/arch/riscv/mm/cacheflush.c
+++ b/arch/riscv/mm/cacheflush.c
@@ -5,6 +5,7 @@
 
 #include <linux/acpi.h>
 #include <linux/of.h>
+#include <linux/prctl.h>
 #include <asm/acpi.h>
 #include <asm/cacheflush.h>
 
@@ -21,7 +22,9 @@ void flush_icache_all(void)
 {
 	local_flush_icache_all();
 
-	if (IS_ENABLED(CONFIG_RISCV_SBI) && !riscv_use_ipi_for_rfence())
+	if (num_online_cpus() < 2)
+		return;
+	else if (riscv_use_sbi_for_rfence())
 		sbi_remote_fence_i(NULL);
 	else
 		on_each_cpu(ipi_remote_fence_i, NULL, 1);
@@ -69,8 +72,7 @@ void flush_icache_mm(struct mm_struct *mm, bool local)
 		 * with flush_icache_deferred().
 		 */
 		smp_mb();
-	} else if (IS_ENABLED(CONFIG_RISCV_SBI) &&
-		   !riscv_use_ipi_for_rfence()) {
+	} else if (riscv_use_sbi_for_rfence()) {
 		sbi_remote_fence_i(&others);
 	} else {
 		on_each_cpu_mask(&others, ipi_remote_fence_i, NULL, 1);
@@ -152,3 +154,115 @@ void __init riscv_init_cbo_blocksizes(void)
 	if (cboz_block_size)
 		riscv_cboz_block_size = cboz_block_size;
 }
+
+#ifdef CONFIG_SMP
+static void set_icache_stale_mask(void)
+{
+	cpumask_t *mask;
+	bool stale_cpu;
+
+	/*
+	 * Mark every other hart's icache as needing a flush for
+	 * this MM. Maintain the previous value of the current
+	 * cpu to handle the case when this function is called
+	 * concurrently on different harts.
+	 */
+	mask = &current->mm->context.icache_stale_mask;
+	stale_cpu = cpumask_test_cpu(smp_processor_id(), mask);
+
+	cpumask_setall(mask);
+	cpumask_assign_cpu(smp_processor_id(), mask, stale_cpu);
+}
+#endif
+
+/**
+ * riscv_set_icache_flush_ctx() - Enable/disable icache flushing instructions in
+ * userspace.
+ * @ctx: Set the type of icache flushing instructions permitted/prohibited in
+ *	 userspace. Supported values described below.
+ *
+ * Supported values for ctx:
+ *
+ * * %PR_RISCV_CTX_SW_FENCEI_ON: Allow fence.i in user space.
+ *
+ * * %PR_RISCV_CTX_SW_FENCEI_OFF: Disallow fence.i in user space. All threads in
+ *   a process will be affected when ``scope == PR_RISCV_SCOPE_PER_PROCESS``.
+ *   Therefore, caution must be taken; use this flag only when you can guarantee
+ *   that no thread in the process will emit fence.i from this point onward.
+ *
+ * @scope: Set scope of where icache flushing instructions are allowed to be
+ *	   emitted. Supported values described below.
+ *
+ * Supported values for scope:
+ *
+ * * %PR_RISCV_SCOPE_PER_PROCESS: Ensure the icache of any thread in this process
+ *                               is coherent with instruction storage upon
+ *                               migration.
+ *
+ * * %PR_RISCV_SCOPE_PER_THREAD: Ensure the icache of the current thread is
+ *                              coherent with instruction storage upon
+ *                              migration.
+ *
+ * When ``scope == PR_RISCV_SCOPE_PER_PROCESS``, all threads in the process are
+ * permitted to emit icache flushing instructions. Whenever any thread in the
+ * process is migrated, the corresponding hart's icache will be guaranteed to be
+ * consistent with instruction storage. This does not enforce any guarantees
+ * outside of migration. If a thread modifies an instruction that another thread
+ * may attempt to execute, the other thread must still emit an icache flushing
+ * instruction before attempting to execute the potentially modified
+ * instruction. This must be performed by the user-space program.
+ *
+ * In per-thread context (eg. ``scope == PR_RISCV_SCOPE_PER_THREAD``) only the
+ * thread calling this function is permitted to emit icache flushing
+ * instructions. When the thread is migrated, the corresponding hart's icache
+ * will be guaranteed to be consistent with instruction storage.
+ *
+ * On kernels configured without SMP, this function is a nop as migrations
+ * across harts will not occur.
+ */
+int riscv_set_icache_flush_ctx(unsigned long ctx, unsigned long scope)
+{
+#ifdef CONFIG_SMP
+	switch (ctx) {
+	case PR_RISCV_CTX_SW_FENCEI_ON:
+		switch (scope) {
+		case PR_RISCV_SCOPE_PER_PROCESS:
+			current->mm->context.force_icache_flush = true;
+			break;
+		case PR_RISCV_SCOPE_PER_THREAD:
+			current->thread.force_icache_flush = true;
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	case PR_RISCV_CTX_SW_FENCEI_OFF:
+		switch (scope) {
+		case PR_RISCV_SCOPE_PER_PROCESS:
+			current->mm->context.force_icache_flush = false;
+
+			set_icache_stale_mask();
+			break;
+		case PR_RISCV_SCOPE_PER_THREAD:
+			current->thread.force_icache_flush = false;
+
+			set_icache_stale_mask();
+			break;
+		default:
+			return -EINVAL;
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+#else
+	switch (ctx) {
+	case PR_RISCV_CTX_SW_FENCEI_ON:
+	case PR_RISCV_CTX_SW_FENCEI_OFF:
+		return 0;
+	default:
+		return -EINVAL;
+	}
+#endif
+}
diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
index ba8eb3944687..4abe3de23225 100644
--- a/arch/riscv/mm/context.c
+++ b/arch/riscv/mm/context.c
@@ -15,14 +15,13 @@
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
+#include <asm/switch_to.h>
 
 #ifdef CONFIG_MMU
 
 DEFINE_STATIC_KEY_FALSE(use_asid_allocator);
 
-static unsigned long asid_bits;
 static unsigned long num_asids;
-unsigned long asid_mask;
 
 static atomic_long_t current_version;
 
@@ -81,7 +80,7 @@ static void __flush_context(void)
 		if (cntx == 0)
 			cntx = per_cpu(reserved_context, i);
 
-		__set_bit(cntx & asid_mask, context_asid_map);
+		__set_bit(cntx2asid(cntx), context_asid_map);
 		per_cpu(reserved_context, i) = cntx;
 	}
 
@@ -102,7 +101,7 @@ static unsigned long __new_context(struct mm_struct *mm)
 	lockdep_assert_held(&context_lock);
 
 	if (cntx != 0) {
-		unsigned long newcntx = ver | (cntx & asid_mask);
+		unsigned long newcntx = ver | cntx2asid(cntx);
 
 		/*
 		 * If our current CONTEXT was active during a rollover, we
@@ -115,7 +114,7 @@ static unsigned long __new_context(struct mm_struct *mm)
 		 * We had a valid CONTEXT in a previous life, so try to
 		 * re-use it if possible.
 		 */
-		if (!__test_and_set_bit(cntx & asid_mask, context_asid_map))
+		if (!__test_and_set_bit(cntx2asid(cntx), context_asid_map))
 			return newcntx;
 	}
 
@@ -128,7 +127,7 @@ static unsigned long __new_context(struct mm_struct *mm)
 		goto set_asid;
 
 	/* We're out of ASIDs, so increment current_version */
-	ver = atomic_long_add_return_relaxed(num_asids, &current_version);
+	ver = atomic_long_add_return_relaxed(BIT(SATP_ASID_BITS), &current_version);
 
 	/* Flush everything  */
 	__flush_context();
@@ -168,7 +167,7 @@ static void set_mm_asid(struct mm_struct *mm, unsigned int cpu)
 	 */
 	old_active_cntx = atomic_long_read(&per_cpu(active_context, cpu));
 	if (old_active_cntx &&
-	    ((cntx & ~asid_mask) == atomic_long_read(&current_version)) &&
+	    (cntx2version(cntx) == atomic_long_read(&current_version)) &&
 	    atomic_long_cmpxchg_relaxed(&per_cpu(active_context, cpu),
 					old_active_cntx, cntx))
 		goto switch_mm_fast;
@@ -177,7 +176,7 @@ static void set_mm_asid(struct mm_struct *mm, unsigned int cpu)
 
 	/* Check that our ASID belongs to the current_version. */
 	cntx = atomic_long_read(&mm->context.id);
-	if ((cntx & ~asid_mask) != atomic_long_read(&current_version)) {
+	if (cntx2version(cntx) != atomic_long_read(&current_version)) {
 		cntx = __new_context(mm);
 		atomic_long_set(&mm->context.id, cntx);
 	}
@@ -191,7 +190,7 @@ static void set_mm_asid(struct mm_struct *mm, unsigned int cpu)
 
 switch_mm_fast:
 	csr_write(CSR_SATP, virt_to_pfn(mm->pgd) |
-		  ((cntx & asid_mask) << SATP_ASID_SHIFT) |
+		  (cntx2asid(cntx) << SATP_ASID_SHIFT) |
 		  satp_mode);
 
 	if (need_flush_tlb)
@@ -202,7 +201,7 @@ static void set_mm_noasid(struct mm_struct *mm)
 {
 	/* Switch the page table and blindly nuke entire local TLB */
 	csr_write(CSR_SATP, virt_to_pfn(mm->pgd) | satp_mode);
-	local_flush_tlb_all();
+	local_flush_tlb_all_asid(0);
 }
 
 static inline void set_mm(struct mm_struct *prev,
@@ -227,7 +226,7 @@ static inline void set_mm(struct mm_struct *prev,
 
 static int __init asids_init(void)
 {
-	unsigned long old;
+	unsigned long asid_bits, old;
 
 	/* Figure-out number of ASID bits in HW */
 	old = csr_read(CSR_SATP);
@@ -247,7 +246,6 @@ static int __init asids_init(void)
 	/* Pre-compute ASID details */
 	if (asid_bits) {
 		num_asids = 1 << asid_bits;
-		asid_mask = num_asids - 1;
 	}
 
 	/*
@@ -255,7 +253,7 @@ static int __init asids_init(void)
 	 * at-least twice more than CPUs
 	 */
 	if (num_asids > (2 * num_possible_cpus())) {
-		atomic_long_set(&current_version, num_asids);
+		atomic_long_set(&current_version, BIT(SATP_ASID_BITS));
 
 		context_asid_map = bitmap_zalloc(num_asids, GFP_KERNEL);
 		if (!context_asid_map)
@@ -297,21 +295,23 @@ static inline void set_mm(struct mm_struct *prev,
  *
  * The "cpu" argument must be the current local CPU number.
  */
-static inline void flush_icache_deferred(struct mm_struct *mm, unsigned int cpu)
+static inline void flush_icache_deferred(struct mm_struct *mm, unsigned int cpu,
+					 struct task_struct *task)
 {
 #ifdef CONFIG_SMP
-	cpumask_t *mask = &mm->context.icache_stale_mask;
-
-	if (cpumask_test_cpu(cpu, mask)) {
-		cpumask_clear_cpu(cpu, mask);
+	if (cpumask_test_and_clear_cpu(cpu, &mm->context.icache_stale_mask)) {
 		/*
 		 * Ensure the remote hart's writes are visible to this hart.
 		 * This pairs with a barrier in flush_icache_mm.
 		 */
 		smp_mb();
-		local_flush_icache_all();
-	}
 
+		/*
+		 * If cache will be flushed in switch_to, no need to flush here.
+		 */
+		if (!(task && switch_to_should_flush_icache(task)))
+			local_flush_icache_all();
+	}
 #endif
 }
 
@@ -334,5 +334,5 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 
 	set_mm(prev, next, cpu);
 
-	flush_icache_deferred(next, cpu);
+	flush_icache_deferred(next, cpu, task);
 }
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 9940171c79f0..7e12925fc660 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -50,8 +50,8 @@ u64 satp_mode __ro_after_init = SATP_MODE_32;
 EXPORT_SYMBOL(satp_mode);
 
 #ifdef CONFIG_64BIT
-bool pgtable_l4_enabled = IS_ENABLED(CONFIG_64BIT) && !IS_ENABLED(CONFIG_XIP_KERNEL);
-bool pgtable_l5_enabled = IS_ENABLED(CONFIG_64BIT) && !IS_ENABLED(CONFIG_XIP_KERNEL);
+bool pgtable_l4_enabled __ro_after_init = !IS_ENABLED(CONFIG_XIP_KERNEL);
+bool pgtable_l5_enabled __ro_after_init = !IS_ENABLED(CONFIG_XIP_KERNEL);
 EXPORT_SYMBOL(pgtable_l4_enabled);
 EXPORT_SYMBOL(pgtable_l5_enabled);
 #endif
@@ -162,11 +162,25 @@ static void print_vm_layout(void) { }
 
 void __init mem_init(void)
 {
+	bool swiotlb = max_pfn > PFN_DOWN(dma32_phys_limit);
 #ifdef CONFIG_FLATMEM
 	BUG_ON(!mem_map);
 #endif /* CONFIG_FLATMEM */
 
-	swiotlb_init(max_pfn > PFN_DOWN(dma32_phys_limit), SWIOTLB_VERBOSE);
+	if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb &&
+	    dma_cache_alignment != 1) {
+		/*
+		 * If no bouncing needed for ZONE_DMA, allocate 1MB swiotlb
+		 * buffer per 1GB of RAM for kmalloc() bouncing on
+		 * non-coherent platforms.
+		 */
+		unsigned long size =
+			DIV_ROUND_UP(memblock_phys_mem_size(), 1024);
+		swiotlb_adjust_size(min(swiotlb_size_or_default(), size));
+		swiotlb = true;
+	}
+
+	swiotlb_init(swiotlb, SWIOTLB_VERBOSE);
 	memblock_free_all();
 
 	print_vm_layout();
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 07d743f87b3f..9b6e86ce3867 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -7,34 +7,11 @@
 #include <asm/sbi.h>
 #include <asm/mmu_context.h>
 
-static inline void local_flush_tlb_all_asid(unsigned long asid)
-{
-	if (asid != FLUSH_TLB_NO_ASID)
-		__asm__ __volatile__ ("sfence.vma x0, %0"
-				:
-				: "r" (asid)
-				: "memory");
-	else
-		local_flush_tlb_all();
-}
-
-static inline void local_flush_tlb_page_asid(unsigned long addr,
-		unsigned long asid)
-{
-	if (asid != FLUSH_TLB_NO_ASID)
-		__asm__ __volatile__ ("sfence.vma %0, %1"
-				:
-				: "r" (addr), "r" (asid)
-				: "memory");
-	else
-		local_flush_tlb_page(addr);
-}
-
 /*
  * Flush entire TLB if number of entries to be flushed is greater
  * than the threshold below.
  */
-static unsigned long tlb_flush_all_threshold __read_mostly = 64;
+unsigned long tlb_flush_all_threshold __read_mostly = 64;
 
 static void local_flush_tlb_range_threshold_asid(unsigned long start,
 						 unsigned long size,
@@ -79,10 +56,12 @@ static void __ipi_flush_tlb_all(void *info)
 
 void flush_tlb_all(void)
 {
-	if (riscv_use_ipi_for_rfence())
-		on_each_cpu(__ipi_flush_tlb_all, NULL, 1);
-	else
+	if (num_online_cpus() < 2)
+		local_flush_tlb_all();
+	else if (riscv_use_sbi_for_rfence())
 		sbi_remote_sfence_vma_asid(NULL, 0, FLUSH_TLB_MAX_SIZE, FLUSH_TLB_NO_ASID);
+	else
+		on_each_cpu(__ipi_flush_tlb_all, NULL, 1);
 }
 
 struct flush_tlb_range_data {
@@ -103,46 +82,34 @@ static void __flush_tlb_range(const struct cpumask *cmask, unsigned long asid,
 			      unsigned long start, unsigned long size,
 			      unsigned long stride)
 {
-	struct flush_tlb_range_data ftd;
-	bool broadcast;
+	unsigned int cpu;
 
 	if (cpumask_empty(cmask))
 		return;
 
-	if (cmask != cpu_online_mask) {
-		unsigned int cpuid;
+	cpu = get_cpu();
 
-		cpuid = get_cpu();
-		/* check if the tlbflush needs to be sent to other CPUs */
-		broadcast = cpumask_any_but(cmask, cpuid) < nr_cpu_ids;
+	/* Check if the TLB flush needs to be sent to other CPUs. */
+	if (cpumask_any_but(cmask, cpu) >= nr_cpu_ids) {
+		local_flush_tlb_range_asid(start, size, stride, asid);
+	} else if (riscv_use_sbi_for_rfence()) {
+		sbi_remote_sfence_vma_asid(cmask, start, size, asid);
 	} else {
-		broadcast = true;
-	}
+		struct flush_tlb_range_data ftd;
 
-	if (broadcast) {
-		if (riscv_use_ipi_for_rfence()) {
-			ftd.asid = asid;
-			ftd.start = start;
-			ftd.size = size;
-			ftd.stride = stride;
-			on_each_cpu_mask(cmask,
-					 __ipi_flush_tlb_range_asid,
-					 &ftd, 1);
-		} else
-			sbi_remote_sfence_vma_asid(cmask,
-						   start, size, asid);
-	} else {
-		local_flush_tlb_range_asid(start, size, stride, asid);
+		ftd.asid = asid;
+		ftd.start = start;
+		ftd.size = size;
+		ftd.stride = stride;
+		on_each_cpu_mask(cmask, __ipi_flush_tlb_range_asid, &ftd, 1);
 	}
 
-	if (cmask != cpu_online_mask)
-		put_cpu();
+	put_cpu();
 }
 
 static inline unsigned long get_mm_asid(struct mm_struct *mm)
 {
-	return static_branch_unlikely(&use_asid_allocator) ?
-			atomic_long_read(&mm->context.id) & asid_mask : FLUSH_TLB_NO_ASID;
+	return cntx2asid(atomic_long_read(&mm->context.id));
 }
 
 void flush_tlb_mm(struct mm_struct *mm)