Resguardo inicial

linux-7.2.3/arch/riscv/mm/Makefile

@@ -0,0 +1,35 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+CFLAGS_init.o := -mcmodel=medany
+ifdef CONFIG_RELOCATABLE
+CFLAGS_init.o += -fno-pie
+endif
+
+ifdef CONFIG_FTRACE
+CFLAGS_REMOVE_init.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_cacheflush.o = $(CC_FLAGS_FTRACE)
+endif
+
+KCOV_INSTRUMENT_init.o := n
+
+obj-y += init.o
+obj-$(CONFIG_MMU) += extable.o fault.o pageattr.o pgtable.o tlbflush.o
+obj-y += cacheflush.o
+obj-y += context.o
+obj-y += pmem.o
+
+obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
+obj-$(CONFIG_PTDUMP) += ptdump.o
+obj-$(CONFIG_KASAN)   += kasan_init.o
+
+ifdef CONFIG_KASAN
+KASAN_SANITIZE_kasan_init.o := n
+KASAN_SANITIZE_init.o := n
+ifdef CONFIG_DEBUG_VIRTUAL
+KASAN_SANITIZE_physaddr.o := n
+endif
+endif
+
+obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o
+obj-$(CONFIG_RISCV_DMA_NONCOHERENT) += dma-noncoherent.o
+obj-$(CONFIG_RISCV_NONSTANDARD_CACHE_OPS) += cache-ops.o

linux-7.2.3/arch/riscv/mm/cache-ops.c

@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#include <asm/dma-noncoherent.h>
+
+struct riscv_nonstd_cache_ops noncoherent_cache_ops __ro_after_init;
+
+void
+riscv_noncoherent_register_cache_ops(const struct riscv_nonstd_cache_ops *ops)
+{
+	if (!ops)
+		return;
+	noncoherent_cache_ops = *ops;
+}
+EXPORT_SYMBOL_GPL(riscv_noncoherent_register_cache_ops);

linux-7.2.3/arch/riscv/mm/cacheflush.c

@@ -0,0 +1,289 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/acpi.h>
+#include <linux/of.h>
+#include <linux/prctl.h>
+#include <asm/acpi.h>
+#include <asm/cacheflush.h>
+
+#ifdef CONFIG_SMP
+
+#include <asm/sbi.h>
+
+static void ipi_remote_fence_i(void *info)
+{
+	return local_flush_icache_all();
+}
+
+void flush_icache_all(void)
+{
+	local_flush_icache_all();
+
+	if (num_online_cpus() < 2)
+		return;
+
+	/*
+	 * Make sure all previous writes to the D$ are ordered before making
+	 * the IPI. The RISC-V spec states that a hart must execute a data fence
+	 * before triggering a remote fence.i in order to make the modification
+	 * visible for remote harts.
+	 *
+	 * IPIs on RISC-V are triggered by MMIO writes to either CLINT or
+	 * S-IMSIC, so the fence ensures previous data writes "happen before"
+	 * the MMIO.
+	 */
+	RISCV_FENCE(w, o);
+
+	if (riscv_use_sbi_for_rfence())
+		sbi_remote_fence_i(NULL);
+	else
+		on_each_cpu(ipi_remote_fence_i, NULL, 1);
+}
+EXPORT_SYMBOL(flush_icache_all);
+
+/*
+ * Performs an icache flush for the given MM context.  RISC-V has no direct
+ * mechanism for instruction cache shoot downs, so instead we send an IPI that
+ * informs the remote harts they need to flush their local instruction caches.
+ * To avoid pathologically slow behavior in a common case (a bunch of
+ * single-hart processes on a many-hart machine, ie 'make -j') we avoid the
+ * IPIs for harts that are not currently executing a MM context and instead
+ * schedule a deferred local instruction cache flush to be performed before
+ * execution resumes on each hart.
+ */
+void flush_icache_mm(struct mm_struct *mm, bool local)
+{
+	unsigned int cpu;
+	cpumask_t others, *mask;
+
+	preempt_disable();
+
+	/* Mark every hart's icache as needing a flush for this MM. */
+	mask = &mm->context.icache_stale_mask;
+	cpumask_setall(mask);
+	/* Flush this hart's I$ now, and mark it as flushed. */
+	cpu = smp_processor_id();
+	cpumask_clear_cpu(cpu, mask);
+	local_flush_icache_all();
+
+	/*
+	 * Flush the I$ of other harts concurrently executing, and mark them as
+	 * flushed.
+	 */
+	cpumask_andnot(&others, mm_cpumask(mm), cpumask_of(cpu));
+	local |= cpumask_empty(&others);
+	if (mm == current->active_mm && local) {
+		/*
+		 * It's assumed that at least one strongly ordered operation is
+		 * performed on this hart between setting a hart's cpumask bit
+		 * and scheduling this MM context on that hart.  Sending an SBI
+		 * remote message will do this, but in the case where no
+		 * messages are sent we still need to order this hart's writes
+		 * with flush_icache_deferred().
+		 */
+		smp_mb();
+	} else if (riscv_use_sbi_for_rfence()) {
+		sbi_remote_fence_i(&others);
+	} else {
+		on_each_cpu_mask(&others, ipi_remote_fence_i, NULL, 1);
+	}
+
+	preempt_enable();
+}
+
+#endif /* CONFIG_SMP */
+
+#ifdef CONFIG_MMU
+void flush_icache_pte(struct mm_struct *mm, pte_t pte)
+{
+	struct folio *folio = page_folio(pte_page(pte));
+
+	if (!test_bit(PG_dcache_clean, &folio->flags.f)) {
+		flush_icache_mm(mm, false);
+		set_bit(PG_dcache_clean, &folio->flags.f);
+	}
+}
+#endif /* CONFIG_MMU */
+
+unsigned int riscv_cbom_block_size;
+EXPORT_SYMBOL_GPL(riscv_cbom_block_size);
+
+unsigned int riscv_cboz_block_size;
+EXPORT_SYMBOL_GPL(riscv_cboz_block_size);
+
+unsigned int riscv_cbop_block_size;
+EXPORT_SYMBOL_GPL(riscv_cbop_block_size);
+
+static void __init cbo_get_block_size(struct device_node *node,
+				      const char *name, u32 *block_size,
+				      unsigned long *first_hartid)
+{
+	unsigned long hartid;
+	u32 val;
+
+	if (riscv_of_processor_hartid(node, &hartid))
+		return;
+
+	if (of_property_read_u32(node, name, &val))
+		return;
+
+	if (!*block_size) {
+		*block_size = val;
+		*first_hartid = hartid;
+	} else if (*block_size != val) {
+		pr_warn("%s mismatched between harts %lu and %lu\n",
+			name, *first_hartid, hartid);
+	}
+}
+
+void __init riscv_init_cbo_blocksizes(void)
+{
+	unsigned long cbom_hartid, cboz_hartid, cbop_hartid;
+	u32 cbom_block_size = 0, cboz_block_size = 0, cbop_block_size = 0;
+	struct device_node *node;
+	struct acpi_table_header *rhct;
+	acpi_status status;
+
+	if (acpi_disabled) {
+		for_each_of_cpu_node(node) {
+			/* set block-size for cbom and/or cboz extension if available */
+			cbo_get_block_size(node, "riscv,cbom-block-size",
+					   &cbom_block_size, &cbom_hartid);
+			cbo_get_block_size(node, "riscv,cboz-block-size",
+					   &cboz_block_size, &cboz_hartid);
+			cbo_get_block_size(node, "riscv,cbop-block-size",
+					   &cbop_block_size, &cbop_hartid);
+		}
+	} else {
+		status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct);
+		if (ACPI_FAILURE(status))
+			return;
+
+		acpi_get_cbo_block_size(rhct, &cbom_block_size, &cboz_block_size, &cbop_block_size);
+		acpi_put_table((struct acpi_table_header *)rhct);
+	}
+
+	if (cbom_block_size)
+		riscv_cbom_block_size = cbom_block_size;
+
+	if (cboz_block_size)
+		riscv_cboz_block_size = cboz_block_size;
+
+	if (cbop_block_size)
+		riscv_cbop_block_size = cbop_block_size;
+}
+
+#ifdef CONFIG_SMP
+static void set_icache_stale_mask(void)
+{
+	int cpu = get_cpu();
+	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(cpu, mask);
+
+	cpumask_setall(mask);
+	__assign_cpu(cpu, mask, stale_cpu);
+	put_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:
+			set_icache_stale_mask();
+			current->mm->context.force_icache_flush = false;
+			break;
+		case PR_RISCV_SCOPE_PER_THREAD:
+			set_icache_stale_mask();
+			current->thread.force_icache_flush = false;
+			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
+}

linux-7.2.3/arch/riscv/mm/context.c

@@ -0,0 +1,338 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/bitops.h>
+#include <linux/cpumask.h>
+#include <linux/mm.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/static_key.h>
+#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 num_asids;
+
+static atomic_long_t current_version;
+
+static DEFINE_RAW_SPINLOCK(context_lock);
+static cpumask_t context_tlb_flush_pending;
+static unsigned long *context_asid_map;
+
+static DEFINE_PER_CPU(atomic_long_t, active_context);
+static DEFINE_PER_CPU(unsigned long, reserved_context);
+
+static bool check_update_reserved_context(unsigned long cntx,
+					  unsigned long newcntx)
+{
+	int cpu;
+	bool hit = false;
+
+	/*
+	 * Iterate over the set of reserved CONTEXT looking for a match.
+	 * If we find one, then we can update our mm to use new CONTEXT
+	 * (i.e. the same CONTEXT in the current_version) but we can't
+	 * exit the loop early, since we need to ensure that all copies
+	 * of the old CONTEXT are updated to reflect the mm. Failure to do
+	 * so could result in us missing the reserved CONTEXT in a future
+	 * version.
+	 */
+	for_each_possible_cpu(cpu) {
+		if (per_cpu(reserved_context, cpu) == cntx) {
+			hit = true;
+			per_cpu(reserved_context, cpu) = newcntx;
+		}
+	}
+
+	return hit;
+}
+
+static void __flush_context(void)
+{
+	int i;
+	unsigned long cntx;
+
+	/* Must be called with context_lock held */
+	lockdep_assert_held(&context_lock);
+
+	/* Update the list of reserved ASIDs and the ASID bitmap. */
+	bitmap_zero(context_asid_map, num_asids);
+
+	/* Mark already active ASIDs as used */
+	for_each_possible_cpu(i) {
+		cntx = atomic_long_xchg_relaxed(&per_cpu(active_context, i), 0);
+		/*
+		 * If this CPU has already been through a rollover, but
+		 * hasn't run another task in the meantime, we must preserve
+		 * its reserved CONTEXT, as this is the only trace we have of
+		 * the process it is still running.
+		 */
+		if (cntx == 0)
+			cntx = per_cpu(reserved_context, i);
+
+		__set_bit(cntx2asid(cntx), context_asid_map);
+		per_cpu(reserved_context, i) = cntx;
+	}
+
+	/* Mark ASID #0 as used because it is used at boot-time */
+	__set_bit(0, context_asid_map);
+
+	/* Queue a TLB invalidation for each CPU on next context-switch */
+	cpumask_setall(&context_tlb_flush_pending);
+}
+
+static unsigned long __new_context(struct mm_struct *mm)
+{
+	static u32 cur_idx = 1;
+	unsigned long cntx = atomic_long_read(&mm->context.id);
+	unsigned long asid, ver = atomic_long_read(&current_version);
+
+	/* Must be called with context_lock held */
+	lockdep_assert_held(&context_lock);
+
+	if (cntx != 0) {
+		unsigned long newcntx = ver | cntx2asid(cntx);
+
+		/*
+		 * If our current CONTEXT was active during a rollover, we
+		 * can continue to use it and this was just a false alarm.
+		 */
+		if (check_update_reserved_context(cntx, newcntx))
+			return newcntx;
+
+		/*
+		 * We had a valid CONTEXT in a previous life, so try to
+		 * re-use it if possible.
+		 */
+		if (!__test_and_set_bit(cntx2asid(cntx), context_asid_map))
+			return newcntx;
+	}
+
+	/*
+	 * Allocate a free ASID. If we can't find one then increment
+	 * current_version and flush all ASIDs.
+	 */
+	asid = find_next_zero_bit(context_asid_map, num_asids, cur_idx);
+	if (asid != num_asids)
+		goto set_asid;
+
+	/* We're out of ASIDs, so increment current_version */
+	ver = atomic_long_add_return_relaxed(BIT(SATP_ASID_BITS), &current_version);
+
+	/* Flush everything  */
+	__flush_context();
+
+	/* We have more ASIDs than CPUs, so this will always succeed */
+	asid = find_next_zero_bit(context_asid_map, num_asids, 1);
+
+set_asid:
+	__set_bit(asid, context_asid_map);
+	cur_idx = asid;
+	return asid | ver;
+}
+
+static void set_mm_asid(struct mm_struct *mm, unsigned int cpu)
+{
+	unsigned long flags;
+	bool need_flush_tlb = false;
+	unsigned long cntx, old_active_cntx;
+
+	cntx = atomic_long_read(&mm->context.id);
+
+	/*
+	 * If our active_context is non-zero and the context matches the
+	 * current_version, then we update the active_context entry with a
+	 * relaxed cmpxchg.
+	 *
+	 * Following is how we handle racing with a concurrent rollover:
+	 *
+	 * - We get a zero back from the cmpxchg and end up waiting on the
+	 *   lock. Taking the lock synchronises with the rollover and so
+	 *   we are forced to see the updated version.
+	 *
+	 * - We get a valid context back from the cmpxchg then we continue
+	 *   using old ASID because __flush_context() would have marked ASID
+	 *   of active_context as used and next context switch we will
+	 *   allocate new context.
+	 */
+	old_active_cntx = atomic_long_read(&per_cpu(active_context, cpu));
+	if (old_active_cntx &&
+	    (cntx2version(cntx) == atomic_long_read(&current_version)) &&
+	    atomic_long_cmpxchg_relaxed(&per_cpu(active_context, cpu),
+					old_active_cntx, cntx))
+		goto switch_mm_fast;
+
+	raw_spin_lock_irqsave(&context_lock, flags);
+
+	/* Check that our ASID belongs to the current_version. */
+	cntx = atomic_long_read(&mm->context.id);
+	if (cntx2version(cntx) != atomic_long_read(&current_version)) {
+		cntx = __new_context(mm);
+		atomic_long_set(&mm->context.id, cntx);
+	}
+
+	if (cpumask_test_and_clear_cpu(cpu, &context_tlb_flush_pending))
+		need_flush_tlb = true;
+
+	atomic_long_set(&per_cpu(active_context, cpu), cntx);
+
+	raw_spin_unlock_irqrestore(&context_lock, flags);
+
+switch_mm_fast:
+	csr_write(CSR_SATP, virt_to_pfn(mm->pgd) |
+		  (cntx2asid(cntx) << SATP_ASID_SHIFT) |
+		  satp_mode);
+
+	if (need_flush_tlb)
+		local_flush_tlb_all();
+}
+
+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_asid(0);
+}
+
+static inline void set_mm(struct mm_struct *prev,
+			  struct mm_struct *next, unsigned int cpu)
+{
+	/*
+	 * The mm_cpumask indicates which harts' TLBs contain the virtual
+	 * address mapping of the mm. Compared to noasid, using asid
+	 * can't guarantee that stale TLB entries are invalidated because
+	 * the asid mechanism wouldn't flush TLB for every switch_mm for
+	 * performance. So when using asid, keep all CPUs footmarks in
+	 * cpumask() until mm reset.
+	 */
+	cpumask_set_cpu(cpu, mm_cpumask(next));
+	if (static_branch_unlikely(&use_asid_allocator)) {
+		set_mm_asid(next, cpu);
+	} else {
+		cpumask_clear_cpu(cpu, mm_cpumask(prev));
+		set_mm_noasid(next);
+	}
+}
+
+static int __init asids_init(void)
+{
+	unsigned long asid_bits, old;
+
+	/* Figure-out number of ASID bits in HW */
+	old = csr_read(CSR_SATP);
+	asid_bits = old | (SATP_ASID_MASK << SATP_ASID_SHIFT);
+	csr_write(CSR_SATP, asid_bits);
+	asid_bits = (csr_read(CSR_SATP) >> SATP_ASID_SHIFT)  & SATP_ASID_MASK;
+	asid_bits = fls_long(asid_bits);
+	csr_write(CSR_SATP, old);
+
+	/*
+	 * In the process of determining number of ASID bits (above)
+	 * we polluted the TLB of current HART so let's do TLB flushed
+	 * to remove unwanted TLB enteries.
+	 */
+	local_flush_tlb_all();
+
+	/* Pre-compute ASID details */
+	if (asid_bits) {
+		num_asids = 1 << asid_bits;
+	}
+
+	/*
+	 * Use ASID allocator only if number of HW ASIDs are
+	 * at-least twice more than CPUs
+	 */
+	if (num_asids > (2 * num_possible_cpus())) {
+		atomic_long_set(&current_version, BIT(SATP_ASID_BITS));
+
+		context_asid_map = bitmap_zalloc(num_asids, GFP_KERNEL);
+		if (!context_asid_map)
+			panic("Failed to allocate bitmap for %lu ASIDs\n",
+			      num_asids);
+
+		__set_bit(0, context_asid_map);
+
+		static_branch_enable(&use_asid_allocator);
+
+		pr_info("ASID allocator using %lu bits (%lu entries)\n",
+			asid_bits, num_asids);
+	} else {
+		pr_info("ASID allocator disabled (%lu bits)\n", asid_bits);
+	}
+
+	return 0;
+}
+early_initcall(asids_init);
+#else
+static inline void set_mm(struct mm_struct *prev,
+			  struct mm_struct *next, unsigned int cpu)
+{
+	/* Nothing to do here when there is no MMU */
+}
+#endif
+
+/*
+ * When necessary, performs a deferred icache flush for the given MM context,
+ * on the local CPU.  RISC-V has no direct mechanism for instruction cache
+ * shoot downs, so instead we send an IPI that informs the remote harts they
+ * need to flush their local instruction caches.  To avoid pathologically slow
+ * behavior in a common case (a bunch of single-hart processes on a many-hart
+ * machine, ie 'make -j') we avoid the IPIs for harts that are not currently
+ * executing a MM context and instead schedule a deferred local instruction
+ * cache flush to be performed before execution resumes on each hart.  This
+ * actually performs that local instruction cache flush, which implicitly only
+ * refers to the current hart.
+ *
+ * The "cpu" argument must be the current local CPU number.
+ */
+static inline void flush_icache_deferred(struct mm_struct *mm, unsigned int cpu,
+					 struct task_struct *task)
+{
+#ifdef CONFIG_SMP
+	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();
+
+		/*
+		 * 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
+}
+
+void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+	struct task_struct *task)
+{
+	unsigned int cpu;
+
+	if (unlikely(prev == next))
+		return;
+
+	membarrier_arch_switch_mm(prev, next, task);
+
+	/*
+	 * Mark the current MM context as inactive, and the next as
+	 * active.  This is at least used by the icache flushing
+	 * routines in order to determine who should be flushed.
+	 */
+	cpu = smp_processor_id();
+
+	set_mm(prev, next, cpu);
+
+	flush_icache_deferred(next, cpu, task);
+}

linux-7.2.3/arch/riscv/mm/dma-noncoherent.c

@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * RISC-V specific functions to support DMA for non-coherent devices
+ *
+ * Copyright (c) 2021 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/dma-direct.h>
+#include <linux/dma-map-ops.h>
+#include <linux/mm.h>
+#include <asm/cacheflush.h>
+#include <asm/dma-noncoherent.h>
+
+static bool noncoherent_supported __ro_after_init;
+int dma_cache_alignment __ro_after_init = ARCH_DMA_MINALIGN;
+EXPORT_SYMBOL_GPL(dma_cache_alignment);
+
+static inline void arch_dma_cache_wback(phys_addr_t paddr, size_t size)
+{
+	void *vaddr = phys_to_virt(paddr);
+
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (unlikely(noncoherent_cache_ops.wback)) {
+		noncoherent_cache_ops.wback(paddr, size);
+		return;
+	}
+#endif
+	ALT_CMO_OP(CLEAN, vaddr, size, riscv_cbom_block_size);
+}
+
+static inline void arch_dma_cache_inv(phys_addr_t paddr, size_t size)
+{
+	void *vaddr = phys_to_virt(paddr);
+
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (unlikely(noncoherent_cache_ops.inv)) {
+		noncoherent_cache_ops.inv(paddr, size);
+		return;
+	}
+#endif
+
+	ALT_CMO_OP(INVAL, vaddr, size, riscv_cbom_block_size);
+}
+
+static inline void arch_dma_cache_wback_inv(phys_addr_t paddr, size_t size)
+{
+	void *vaddr = phys_to_virt(paddr);
+
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (unlikely(noncoherent_cache_ops.wback_inv)) {
+		noncoherent_cache_ops.wback_inv(paddr, size);
+		return;
+	}
+#endif
+
+	ALT_CMO_OP(FLUSH, vaddr, size, riscv_cbom_block_size);
+}
+
+static inline bool arch_sync_dma_clean_before_fromdevice(void)
+{
+	return true;
+}
+
+static inline bool arch_sync_dma_cpu_needs_post_dma_flush(void)
+{
+	return true;
+}
+
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+			      enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		arch_dma_cache_wback(paddr, size);
+		break;
+
+	case DMA_FROM_DEVICE:
+		if (!arch_sync_dma_clean_before_fromdevice()) {
+			arch_dma_cache_inv(paddr, size);
+			break;
+		}
+		fallthrough;
+
+	case DMA_BIDIRECTIONAL:
+		/* Skip the invalidate here if it's done later */
+		if (IS_ENABLED(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) &&
+		    arch_sync_dma_cpu_needs_post_dma_flush())
+			arch_dma_cache_wback(paddr, size);
+		else
+			arch_dma_cache_wback_inv(paddr, size);
+		break;
+
+	default:
+		break;
+	}
+}
+
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+			   enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		break;
+
+	case DMA_FROM_DEVICE:
+	case DMA_BIDIRECTIONAL:
+		/* FROM_DEVICE invalidate needed if speculative CPU prefetch only */
+		if (arch_sync_dma_cpu_needs_post_dma_flush())
+			arch_dma_cache_inv(paddr, size);
+		break;
+
+	default:
+		break;
+	}
+}
+
+void arch_dma_prep_coherent(struct page *page, size_t size)
+{
+	void *flush_addr = page_address(page);
+
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (unlikely(noncoherent_cache_ops.wback_inv)) {
+		noncoherent_cache_ops.wback_inv(page_to_phys(page), size);
+		return;
+	}
+#endif
+
+	ALT_CMO_OP(FLUSH, flush_addr, size, riscv_cbom_block_size);
+}
+
+void arch_setup_dma_ops(struct device *dev, bool coherent)
+{
+	WARN_TAINT(!coherent && riscv_cbom_block_size > ARCH_DMA_MINALIGN,
+		   TAINT_CPU_OUT_OF_SPEC,
+		   "%s %s: ARCH_DMA_MINALIGN smaller than riscv,cbom-block-size (%d < %d)",
+		   dev_driver_string(dev), dev_name(dev),
+		   ARCH_DMA_MINALIGN, riscv_cbom_block_size);
+
+	WARN_TAINT(!coherent && !noncoherent_supported, TAINT_CPU_OUT_OF_SPEC,
+		   "%s %s: device non-coherent but no non-coherent operations supported",
+		   dev_driver_string(dev), dev_name(dev));
+
+	dev_assign_dma_coherent(dev, coherent);
+}
+
+void riscv_noncoherent_supported(void)
+{
+	WARN(!riscv_cbom_block_size,
+	     "Non-coherent DMA support enabled without a block size\n");
+	noncoherent_supported = true;
+}
+
+void __init riscv_set_dma_cache_alignment(void)
+{
+	if (!noncoherent_supported)
+		dma_cache_alignment = 1;
+}

linux-7.2.3/arch/riscv/mm/extable.c

@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ *  Lennox Wu <lennox.wu@sunplusct.com>
+ *  Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2013 Regents of the University of California
+ */
+
+
+#include <linux/bitfield.h>
+#include <linux/extable.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <asm/asm-extable.h>
+#include <asm/ptrace.h>
+
+static inline unsigned long
+get_ex_fixup(const struct exception_table_entry *ex)
+{
+	return ((unsigned long)&ex->fixup + ex->fixup);
+}
+
+static bool ex_handler_fixup(const struct exception_table_entry *ex,
+			     struct pt_regs *regs)
+{
+	regs->epc = get_ex_fixup(ex);
+	return true;
+}
+
+static inline unsigned long regs_get_gpr(struct pt_regs *regs, unsigned int offset)
+{
+	if (unlikely(!offset || offset > MAX_REG_OFFSET))
+		return 0;
+
+	return *(unsigned long *)((unsigned long)regs + offset);
+}
+
+static inline void regs_set_gpr(struct pt_regs *regs, unsigned int offset,
+				unsigned long val)
+{
+	if (unlikely(offset > MAX_REG_OFFSET))
+		return;
+
+	if (offset)
+		*(unsigned long *)((unsigned long)regs + offset) = val;
+}
+
+static bool ex_handler_uaccess_err_zero(const struct exception_table_entry *ex,
+					struct pt_regs *regs)
+{
+	int reg_err = FIELD_GET(EX_DATA_REG_ERR, ex->data);
+	int reg_zero = FIELD_GET(EX_DATA_REG_ZERO, ex->data);
+
+	regs_set_gpr(regs, reg_err * sizeof(unsigned long), -EFAULT);
+	regs_set_gpr(regs, reg_zero * sizeof(unsigned long), 0);
+
+	regs->epc = get_ex_fixup(ex);
+	return true;
+}
+
+static bool
+ex_handler_load_unaligned_zeropad(const struct exception_table_entry *ex,
+				  struct pt_regs *regs)
+{
+	int reg_data = FIELD_GET(EX_DATA_REG_DATA, ex->data);
+	int reg_addr = FIELD_GET(EX_DATA_REG_ADDR, ex->data);
+	unsigned long data, addr, offset;
+
+	addr = regs_get_gpr(regs, reg_addr * sizeof(unsigned long));
+
+	offset = addr & 0x7UL;
+	addr &= ~0x7UL;
+
+	data = *(unsigned long *)addr >> (offset * 8);
+
+	regs_set_gpr(regs, reg_data * sizeof(unsigned long), data);
+
+	regs->epc = get_ex_fixup(ex);
+	return true;
+}
+
+bool fixup_exception(struct pt_regs *regs)
+{
+	const struct exception_table_entry *ex;
+
+	ex = search_exception_tables(regs->epc);
+	if (!ex)
+		return false;
+
+	switch (ex->type) {
+	case EX_TYPE_FIXUP:
+		return ex_handler_fixup(ex, regs);
+	case EX_TYPE_BPF:
+		return ex_handler_bpf(ex, regs);
+	case EX_TYPE_UACCESS_ERR_ZERO:
+		return ex_handler_uaccess_err_zero(ex, regs);
+	case EX_TYPE_LOAD_UNALIGNED_ZEROPAD:
+		return ex_handler_load_unaligned_zeropad(ex, regs);
+	}
+
+	BUG();
+}

linux-7.2.3/arch/riscv/mm/fault.c

@@ -0,0 +1,443 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ *  Lennox Wu <lennox.wu@sunplusct.com>
+ *  Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2012 Regents of the University of California
+ */
+
+
+#include <linux/mm.h>
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/perf_event.h>
+#include <linux/signal.h>
+#include <linux/uaccess.h>
+#include <linux/kprobes.h>
+#include <linux/kfence.h>
+#include <linux/entry-common.h>
+
+#include <asm/ptrace.h>
+#include <asm/tlbflush.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/exceptions.h>
+
+#include "../kernel/head.h"
+
+static void show_pte(unsigned long addr)
+{
+	pgd_t *pgdp, pgd;
+	p4d_t *p4dp, p4d;
+	pud_t *pudp, pud;
+	pmd_t *pmdp, pmd;
+	pte_t *ptep, pte;
+	struct mm_struct *mm = current->mm;
+
+	if (!mm)
+		mm = &init_mm;
+
+	pr_alert("Current %s pgtable: %luK pagesize, %d-bit VAs, pgdp=0x%016llx\n",
+		 current->comm, PAGE_SIZE / SZ_1K, VA_BITS,
+		 mm == &init_mm ? (u64)__pa_symbol(mm->pgd) : virt_to_phys(mm->pgd));
+
+	pgdp = pgd_offset(mm, addr);
+	pgd = pgdp_get(pgdp);
+	pr_alert("[%016lx] pgd=%016lx", addr, pgd_val(pgd));
+	if (pgd_none(pgd) || pgd_bad(pgd) || pgd_leaf(pgd))
+		goto out;
+
+	p4dp = p4d_offset(pgdp, addr);
+	p4d = p4dp_get(p4dp);
+	pr_cont(", p4d=%016lx", p4d_val(p4d));
+	if (p4d_none(p4d) || p4d_bad(p4d) || p4d_leaf(p4d))
+		goto out;
+
+	pudp = pud_offset(p4dp, addr);
+	pud = pudp_get(pudp);
+	pr_cont(", pud=%016lx", pud_val(pud));
+	if (pud_none(pud) || pud_bad(pud) || pud_leaf(pud))
+		goto out;
+
+	pmdp = pmd_offset(pudp, addr);
+	pmd = pmdp_get(pmdp);
+	pr_cont(", pmd=%016lx", pmd_val(pmd));
+	if (pmd_none(pmd) || pmd_bad(pmd) || pmd_leaf(pmd))
+		goto out;
+
+	ptep = pte_offset_map(pmdp, addr);
+	if (!ptep)
+		goto out;
+
+	pte = ptep_get(ptep);
+	pr_cont(", pte=%016lx", pte_val(pte));
+	pte_unmap(ptep);
+out:
+	pr_cont("\n");
+}
+
+static void die_kernel_fault(const char *msg, unsigned long addr,
+		struct pt_regs *regs)
+{
+	bust_spinlocks(1);
+
+	pr_alert("Unable to handle kernel %s at virtual address " REG_FMT "\n", msg,
+		addr);
+
+	bust_spinlocks(0);
+	show_pte(addr);
+	die(regs, "Oops");
+	make_task_dead(SIGKILL);
+}
+
+static inline void no_context(struct pt_regs *regs, unsigned long addr)
+{
+	const char *msg;
+
+	/* Are we prepared to handle this kernel fault? */
+	if (fixup_exception(regs))
+		return;
+
+	/*
+	 * Oops. The kernel tried to access some bad page. We'll have to
+	 * terminate things with extreme prejudice.
+	 */
+	if (addr < PAGE_SIZE)
+		msg = "NULL pointer dereference";
+	else {
+		if (kfence_handle_page_fault(addr, regs->cause == EXC_STORE_PAGE_FAULT, regs))
+			return;
+
+		msg = "paging request";
+	}
+
+	die_kernel_fault(msg, addr, regs);
+}
+
+static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_fault_t fault)
+{
+	if (!user_mode(regs)) {
+		no_context(regs, addr);
+		return;
+	}
+
+	if (fault & VM_FAULT_OOM) {
+		/*
+		 * 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).
+		 */
+		pagefault_out_of_memory();
+		return;
+	} else if (fault & (VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) {
+		/* Kernel mode? Handle exceptions or die */
+		do_trap(regs, SIGBUS, BUS_ADRERR, addr);
+		return;
+	} else if (fault & VM_FAULT_SIGSEGV) {
+		do_trap(regs, SIGSEGV, SEGV_MAPERR, addr);
+		return;
+	}
+
+	BUG();
+}
+
+static inline void
+bad_area_nosemaphore(struct pt_regs *regs, int code, unsigned long addr)
+{
+	/*
+	 * Something tried to access memory that isn't in our memory map.
+	 * Fix it, but check if it's kernel or user first.
+	 */
+	/* User mode accesses just cause a SIGSEGV */
+	if (user_mode(regs)) {
+		do_trap(regs, SIGSEGV, code, addr);
+		return;
+	}
+
+	no_context(regs, addr);
+}
+
+static inline void
+bad_area(struct pt_regs *regs, struct mm_struct *mm, int code,
+	 unsigned long addr)
+{
+	mmap_read_unlock(mm);
+
+	bad_area_nosemaphore(regs, code, addr);
+}
+
+static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long addr)
+{
+	pgd_t *pgd, *pgd_k;
+	pud_t *pud_k;
+	p4d_t *p4d_k;
+	pmd_t *pmd_k;
+	pte_t *pte_k;
+	int index;
+	unsigned long pfn;
+
+	/* User mode accesses just cause a SIGSEGV */
+	if (user_mode(regs))
+		return do_trap(regs, SIGSEGV, code, addr);
+
+	/*
+	 * Synchronize this task's top level page-table
+	 * with the 'reference' page table.
+	 *
+	 * Do _not_ use "tsk->active_mm->pgd" here.
+	 * We might be inside an interrupt in the middle
+	 * of a task switch.
+	 */
+	index = pgd_index(addr);
+	pfn = csr_read(CSR_SATP) & SATP_PPN;
+	pgd = (pgd_t *)pfn_to_virt(pfn) + index;
+	pgd_k = init_mm.pgd + index;
+
+	if (!pgd_present(pgdp_get(pgd_k))) {
+		no_context(regs, addr);
+		return;
+	}
+	set_pgd(pgd, pgdp_get(pgd_k));
+
+	p4d_k = p4d_offset(pgd_k, addr);
+	if (!p4d_present(p4dp_get(p4d_k))) {
+		no_context(regs, addr);
+		return;
+	}
+
+	pud_k = pud_offset(p4d_k, addr);
+	if (!pud_present(pudp_get(pud_k))) {
+		no_context(regs, addr);
+		return;
+	}
+	if (pud_leaf(pudp_get(pud_k)))
+		goto flush_tlb;
+
+	/*
+	 * Since the vmalloc area is global, it is unnecessary
+	 * to copy individual PTEs
+	 */
+	pmd_k = pmd_offset(pud_k, addr);
+	if (!pmd_present(pmdp_get(pmd_k))) {
+		no_context(regs, addr);
+		return;
+	}
+	if (pmd_leaf(pmdp_get(pmd_k)))
+		goto flush_tlb;
+
+	/*
+	 * Make sure the actual PTE exists as well to
+	 * catch kernel vmalloc-area accesses to non-mapped
+	 * addresses. If we don't do this, this will just
+	 * silently loop forever.
+	 */
+	pte_k = pte_offset_kernel(pmd_k, addr);
+	if (!pte_present(ptep_get(pte_k))) {
+		no_context(regs, addr);
+		return;
+	}
+
+	/*
+	 * The kernel assumes that TLBs don't cache invalid
+	 * entries, but in RISC-V, SFENCE.VMA specifies an
+	 * ordering constraint, not a cache flush; it is
+	 * necessary even after writing invalid entries.
+	 */
+flush_tlb:
+	local_flush_tlb_page(addr);
+}
+
+static inline bool access_error(unsigned long cause, struct vm_area_struct *vma)
+{
+	switch (cause) {
+	case EXC_INST_PAGE_FAULT:
+		if (!(vma->vm_flags & VM_EXEC)) {
+			return true;
+		}
+		break;
+	case EXC_LOAD_PAGE_FAULT:
+		/* Write implies read */
+		if (!(vma->vm_flags & (VM_READ | VM_WRITE))) {
+			return true;
+		}
+		break;
+	case EXC_STORE_PAGE_FAULT:
+		if (!(vma->vm_flags & VM_WRITE)) {
+			return true;
+		}
+		break;
+	default:
+		panic("%s: unhandled cause %lu", __func__, cause);
+	}
+	return false;
+}
+
+/*
+ * This routine handles page faults.  It determines the address and the
+ * problem, and then passes it off to one of the appropriate routines.
+ */
+void handle_page_fault(struct pt_regs *regs)
+{
+	struct task_struct *tsk;
+	struct vm_area_struct *vma;
+	struct mm_struct *mm;
+	unsigned long addr, cause;
+	unsigned int flags = FAULT_FLAG_DEFAULT;
+	int code = SEGV_MAPERR;
+	vm_fault_t fault;
+
+	cause = regs->cause;
+	addr = regs->badaddr;
+
+	tsk = current;
+	mm = tsk->mm;
+
+	if (kprobe_page_fault(regs, cause))
+		return;
+
+	if (user_mode(regs))
+		trace_page_fault_user(addr, regs, cause);
+	else
+		trace_page_fault_kernel(addr, regs, cause);
+
+	/*
+	 * Fault-in kernel-space virtual memory on-demand.
+	 * The 'reference' page table is init_mm.pgd.
+	 *
+	 * NOTE! We MUST NOT take any locks for this case. We may
+	 * be in an interrupt or a critical region, and should
+	 * only copy the information from the master page table,
+	 * nothing more.
+	 */
+	if ((!IS_ENABLED(CONFIG_MMU) || !IS_ENABLED(CONFIG_64BIT)) &&
+	    unlikely(addr >= VMALLOC_START && addr < VMALLOC_END)) {
+		vmalloc_fault(regs, code, addr);
+		return;
+	}
+
+	/* Enable interrupts if they were enabled in the parent context. */
+	if (!regs_irqs_disabled(regs))
+		local_irq_enable();
+
+	/*
+	 * If we're in an interrupt, have no user context, or are running
+	 * in an atomic region, then we must not take the fault.
+	 */
+	if (unlikely(faulthandler_disabled() || !mm)) {
+		tsk->thread.bad_cause = cause;
+		no_context(regs, addr);
+		return;
+	}
+
+	if (user_mode(regs))
+		flags |= FAULT_FLAG_USER;
+
+	if (!user_mode(regs) && addr < TASK_SIZE && unlikely(!(regs->status & SR_SUM))) {
+		if (fixup_exception(regs))
+			return;
+
+		die_kernel_fault("access to user memory without uaccess routines", addr, regs);
+	}
+
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
+
+	if (cause == EXC_STORE_PAGE_FAULT)
+		flags |= FAULT_FLAG_WRITE;
+	else if (cause == EXC_INST_PAGE_FAULT)
+		flags |= FAULT_FLAG_INSTRUCTION;
+	if (!(flags & FAULT_FLAG_USER))
+		goto lock_mmap;
+
+	vma = lock_vma_under_rcu(mm, addr);
+	if (!vma)
+		goto lock_mmap;
+
+	if (unlikely(access_error(cause, vma))) {
+		vma_end_read(vma);
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+		tsk->thread.bad_cause = cause;
+		bad_area_nosemaphore(regs, SEGV_ACCERR, addr);
+		return;
+	}
+
+	fault = handle_mm_fault(vma, addr, flags | FAULT_FLAG_VMA_LOCK, regs);
+	if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
+		vma_end_read(vma);
+
+	if (!(fault & VM_FAULT_RETRY)) {
+		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
+		goto done;
+	}
+	count_vm_vma_lock_event(VMA_LOCK_RETRY);
+	if (fault & VM_FAULT_MAJOR)
+		flags |= FAULT_FLAG_TRIED;
+
+	if (fault_signal_pending(fault, regs)) {
+		if (!user_mode(regs))
+			no_context(regs, addr);
+		return;
+	}
+lock_mmap:
+
+retry:
+	vma = lock_mm_and_find_vma(mm, addr, regs);
+	if (unlikely(!vma)) {
+		tsk->thread.bad_cause = cause;
+		bad_area_nosemaphore(regs, code, addr);
+		return;
+	}
+
+	/*
+	 * Ok, we have a good vm_area for this memory access, so
+	 * we can handle it.
+	 */
+	code = SEGV_ACCERR;
+
+	if (unlikely(access_error(cause, vma))) {
+		tsk->thread.bad_cause = cause;
+		bad_area(regs, mm, code, addr);
+		return;
+	}
+
+	/*
+	 * If for any reason at all we could not handle the fault,
+	 * make sure we exit gracefully rather than endlessly redo
+	 * the fault.
+	 */
+	fault = handle_mm_fault(vma, addr, flags, regs);
+
+	/*
+	 * If we need to retry but a fatal signal is pending, handle the
+	 * signal first. We do not need to release the mmap_lock because it
+	 * would already be released in __lock_page_or_retry in mm/filemap.c.
+	 */
+	if (fault_signal_pending(fault, regs)) {
+		if (!user_mode(regs))
+			no_context(regs, addr);
+		return;
+	}
+
+	/* The fault is fully completed (including releasing mmap lock) */
+	if (fault & VM_FAULT_COMPLETED)
+		return;
+
+	if (unlikely(fault & VM_FAULT_RETRY)) {
+		flags |= FAULT_FLAG_TRIED;
+
+		/*
+		 * No need to mmap_read_unlock(mm) as we would
+		 * have already released it in __lock_page_or_retry
+		 * in mm/filemap.c.
+		 */
+		goto retry;
+	}
+
+	mmap_read_unlock(mm);
+
+done:
+	if (unlikely(fault & VM_FAULT_ERROR)) {
+		tsk->thread.bad_cause = cause;
+		mm_fault_error(regs, addr, fault);
+		return;
+	}
+	return;
+}

linux-7.2.3/arch/riscv/mm/hugetlbpage.c

@@ -0,0 +1,457 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/hugetlb.h>
+#include <linux/err.h>
+
+#ifdef CONFIG_RISCV_ISA_SVNAPOT
+pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+	unsigned long pte_num;
+	int i;
+	pte_t orig_pte = ptep_get(ptep);
+
+	if (!pte_present(orig_pte) || !pte_napot(orig_pte))
+		return orig_pte;
+
+	pte_num = napot_pte_num(napot_cont_order(orig_pte));
+
+	for (i = 0; i < pte_num; i++, ptep++) {
+		pte_t pte = ptep_get(ptep);
+
+		if (pte_dirty(pte))
+			orig_pte = pte_mkdirty(orig_pte);
+
+		if (pte_young(pte))
+			orig_pte = pte_mkyoung(orig_pte);
+	}
+
+	return orig_pte;
+}
+
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+		      struct vm_area_struct *vma,
+		      unsigned long addr,
+		      unsigned long sz)
+{
+	unsigned long order;
+	pte_t *pte = NULL;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset(mm, addr);
+	p4d = p4d_alloc(mm, pgd, addr);
+	if (!p4d)
+		return NULL;
+
+	pud = pud_alloc(mm, p4d, addr);
+	if (!pud)
+		return NULL;
+
+	if (sz == PUD_SIZE) {
+		pte = (pte_t *)pud;
+		goto out;
+	}
+
+	if (sz == PMD_SIZE) {
+		if (want_pmd_share(vma, addr) && pud_none(pudp_get(pud)))
+			pte = huge_pmd_share(mm, vma, addr, pud);
+		else
+			pte = (pte_t *)pmd_alloc(mm, pud, addr);
+		goto out;
+	}
+
+	pmd = pmd_alloc(mm, pud, addr);
+	if (!pmd)
+		return NULL;
+
+	for_each_napot_order(order) {
+		if (napot_cont_size(order) == sz) {
+			pte = pte_alloc_huge(mm, pmd, addr & napot_cont_mask(order));
+			break;
+		}
+	}
+
+out:
+	if (pte) {
+		pte_t pteval = ptep_get_lockless(pte);
+
+		WARN_ON_ONCE(pte_present(pteval) && !pte_huge(pteval));
+	}
+	return pte;
+}
+
+pte_t *huge_pte_offset(struct mm_struct *mm,
+		       unsigned long addr,
+		       unsigned long sz)
+{
+	unsigned long order;
+	pte_t *pte = NULL;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset(mm, addr);
+	if (!pgd_present(pgdp_get(pgd)))
+		return NULL;
+
+	p4d = p4d_offset(pgd, addr);
+	if (!p4d_present(p4dp_get(p4d)))
+		return NULL;
+
+	pud = pud_offset(p4d, addr);
+	if (sz == PUD_SIZE)
+		/* must be pud huge, non-present or none */
+		return (pte_t *)pud;
+
+	if (!pud_present(pudp_get(pud)))
+		return NULL;
+
+	pmd = pmd_offset(pud, addr);
+	if (sz == PMD_SIZE)
+		/* must be pmd huge, non-present or none */
+		return (pte_t *)pmd;
+
+	if (!pmd_present(pmdp_get(pmd)))
+		return NULL;
+
+	for_each_napot_order(order) {
+		if (napot_cont_size(order) == sz) {
+			pte = pte_offset_huge(pmd, addr & napot_cont_mask(order));
+			break;
+		}
+	}
+	return pte;
+}
+
+unsigned long hugetlb_mask_last_page(struct hstate *h)
+{
+	unsigned long hp_size = huge_page_size(h);
+
+	switch (hp_size) {
+#ifndef __PAGETABLE_PMD_FOLDED
+	case PUD_SIZE:
+		return P4D_SIZE - PUD_SIZE;
+#endif
+	case PMD_SIZE:
+		return PUD_SIZE - PMD_SIZE;
+	case napot_cont_size(NAPOT_CONT64KB_ORDER):
+		return PMD_SIZE - napot_cont_size(NAPOT_CONT64KB_ORDER);
+	default:
+		break;
+	}
+
+	return 0UL;
+}
+
+static pte_t get_clear_contig(struct mm_struct *mm,
+			      unsigned long addr,
+			      pte_t *ptep,
+			      unsigned long ncontig)
+{
+	pte_t pte, tmp_pte;
+	bool present;
+
+	pte = ptep_get_and_clear(mm, addr, ptep);
+	present = pte_present(pte);
+	while (--ncontig) {
+		ptep++;
+		addr += PAGE_SIZE;
+		tmp_pte = ptep_get_and_clear(mm, addr, ptep);
+		if (present) {
+			if (pte_dirty(tmp_pte))
+				pte = pte_mkdirty(pte);
+			if (pte_young(tmp_pte))
+				pte = pte_mkyoung(pte);
+		}
+	}
+	return pte;
+}
+
+static pte_t get_clear_contig_flush(struct mm_struct *mm,
+				    unsigned long addr,
+				    pte_t *ptep,
+				    unsigned long pte_num)
+{
+	pte_t orig_pte = get_clear_contig(mm, addr, ptep, pte_num);
+	struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
+	bool valid = !pte_none(orig_pte);
+
+	if (valid)
+		flush_tlb_range(&vma, addr, addr + (PAGE_SIZE * pte_num));
+
+	return orig_pte;
+}
+
+pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
+{
+	unsigned long order;
+
+	for_each_napot_order(order) {
+		if (shift == napot_cont_shift(order)) {
+			entry = pte_mknapot(entry, order);
+			break;
+		}
+	}
+	if (order == NAPOT_ORDER_MAX)
+		entry = pte_mkhuge(entry);
+
+	return entry;
+}
+
+static void clear_flush(struct mm_struct *mm,
+			unsigned long addr,
+			pte_t *ptep,
+			unsigned long pgsize,
+			unsigned long ncontig)
+{
+	struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
+	unsigned long i, saddr = addr;
+
+	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+		ptep_get_and_clear(mm, addr, ptep);
+
+	flush_tlb_range(&vma, saddr, addr);
+}
+
+static int num_contig_ptes_from_size(unsigned long sz, size_t *pgsize)
+{
+	unsigned long hugepage_shift;
+
+	if (sz >= PGDIR_SIZE)
+		hugepage_shift = PGDIR_SHIFT;
+	else if (sz >= P4D_SIZE)
+		hugepage_shift = P4D_SHIFT;
+	else if (sz >= PUD_SIZE)
+		hugepage_shift = PUD_SHIFT;
+	else if (sz >= PMD_SIZE)
+		hugepage_shift = PMD_SHIFT;
+	else
+		hugepage_shift = PAGE_SHIFT;
+
+	*pgsize = 1 << hugepage_shift;
+
+	return sz >> hugepage_shift;
+}
+
+/*
+ * When dealing with NAPOT mappings, the privileged specification indicates that
+ * "if an update needs to be made, the OS generally should first mark all of the
+ * PTEs invalid, then issue SFENCE.VMA instruction(s) covering all 4 KiB regions
+ * within the range, [...] then update the PTE(s), as described in Section
+ * 4.2.1.". That's the equivalent of the Break-Before-Make approach used by
+ * arm64.
+ */
+void set_huge_pte_at(struct mm_struct *mm,
+		     unsigned long addr,
+		     pte_t *ptep,
+		     pte_t pte,
+		     unsigned long sz)
+{
+	size_t pgsize;
+	int i, pte_num;
+
+	pte_num = num_contig_ptes_from_size(sz, &pgsize);
+
+	if (!pte_present(pte)) {
+		for (i = 0; i < pte_num; i++, ptep++, addr += pgsize)
+			set_ptes(mm, addr, ptep, pte, 1);
+		return;
+	}
+
+	if (!pte_napot(pte)) {
+		set_ptes(mm, addr, ptep, pte, 1);
+		return;
+	}
+
+	clear_flush(mm, addr, ptep, pgsize, pte_num);
+
+	for (i = 0; i < pte_num; i++, ptep++, addr += pgsize)
+		set_pte_at(mm, addr, ptep, pte);
+}
+
+int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+			       unsigned long addr,
+			       pte_t *ptep,
+			       pte_t pte,
+			       int dirty)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long order;
+	pte_t orig_pte;
+	int i, pte_num;
+
+	if (!pte_napot(pte))
+		return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+
+	order = napot_cont_order(pte);
+	pte_num = napot_pte_num(order);
+	ptep = huge_pte_offset(mm, addr, napot_cont_size(order));
+	orig_pte = get_clear_contig_flush(mm, addr, ptep, pte_num);
+
+	if (pte_dirty(orig_pte))
+		pte = pte_mkdirty(pte);
+
+	if (pte_young(orig_pte))
+		pte = pte_mkyoung(pte);
+
+	for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++)
+		set_pte_at(mm, addr, ptep, pte);
+
+	return true;
+}
+
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+			      unsigned long addr,
+			      pte_t *ptep, unsigned long sz)
+{
+	size_t pgsize;
+	pte_t orig_pte = ptep_get(ptep);
+	int pte_num;
+
+	if (!pte_napot(orig_pte))
+		return ptep_get_and_clear(mm, addr, ptep);
+
+	pte_num = num_contig_ptes_from_size(sz, &pgsize);
+
+	return get_clear_contig(mm, addr, ptep, pte_num);
+}
+
+void huge_ptep_set_wrprotect(struct mm_struct *mm,
+			     unsigned long addr,
+			     pte_t *ptep)
+{
+	pte_t pte = ptep_get(ptep);
+	unsigned long order;
+	pte_t orig_pte;
+	int i, pte_num;
+
+	if (!pte_napot(pte)) {
+		ptep_set_wrprotect(mm, addr, ptep);
+		return;
+	}
+
+	order = napot_cont_order(pte);
+	pte_num = napot_pte_num(order);
+	ptep = huge_pte_offset(mm, addr, napot_cont_size(order));
+	orig_pte = get_clear_contig_flush(mm, addr, ptep, pte_num);
+
+	orig_pte = pte_wrprotect(orig_pte);
+
+	for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++)
+		set_pte_at(mm, addr, ptep, orig_pte);
+}
+
+pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
+			    unsigned long addr,
+			    pte_t *ptep)
+{
+	pte_t pte = ptep_get(ptep);
+	int pte_num;
+
+	if (!pte_napot(pte))
+		return ptep_clear_flush(vma, addr, ptep);
+
+	pte_num = napot_pte_num(napot_cont_order(pte));
+
+	return get_clear_contig_flush(vma->vm_mm, addr, ptep, pte_num);
+}
+
+void huge_pte_clear(struct mm_struct *mm,
+		    unsigned long addr,
+		    pte_t *ptep,
+		    unsigned long sz)
+{
+	size_t pgsize;
+	pte_t pte = ptep_get(ptep);
+	int i, pte_num;
+
+	if (!pte_napot(pte)) {
+		pte_clear(mm, addr, ptep);
+		return;
+	}
+
+	pte_num = num_contig_ptes_from_size(sz, &pgsize);
+
+	for (i = 0; i < pte_num; i++, addr += pgsize, ptep++)
+		pte_clear(mm, addr, ptep);
+}
+
+static bool is_napot_size(unsigned long size)
+{
+	unsigned long order;
+
+	if (!has_svnapot())
+		return false;
+
+	for_each_napot_order(order) {
+		if (size == napot_cont_size(order))
+			return true;
+	}
+	return false;
+}
+
+static __init int napot_hugetlbpages_init(void)
+{
+	if (has_svnapot()) {
+		unsigned long order;
+
+		for_each_napot_order(order)
+			hugetlb_add_hstate(order);
+	}
+	return 0;
+}
+arch_initcall(napot_hugetlbpages_init);
+
+#else
+
+static bool is_napot_size(unsigned long size)
+{
+	return false;
+}
+
+#endif /*CONFIG_RISCV_ISA_SVNAPOT*/
+
+static bool __hugetlb_valid_size(unsigned long size)
+{
+	if (size == HPAGE_SIZE)
+		return true;
+	else if (IS_ENABLED(CONFIG_64BIT) && size == PUD_SIZE)
+		return true;
+	else if (is_napot_size(size))
+		return true;
+	else
+		return false;
+}
+
+bool __init arch_hugetlb_valid_size(unsigned long size)
+{
+	return __hugetlb_valid_size(size);
+}
+
+#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+bool arch_hugetlb_migration_supported(struct hstate *h)
+{
+	return __hugetlb_valid_size(huge_page_size(h));
+}
+#endif
+
+#ifdef CONFIG_CONTIG_ALLOC
+static __init int gigantic_pages_init(void)
+{
+	/* With CONTIG_ALLOC, we can allocate gigantic pages at runtime */
+	if (IS_ENABLED(CONFIG_64BIT))
+		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
+	return 0;
+}
+arch_initcall(gigantic_pages_init);
+#endif
+
+unsigned int __init arch_hugetlb_cma_order(void)
+{
+	if (IS_ENABLED(CONFIG_64BIT))
+		return PUD_SHIFT - PAGE_SHIFT;
+
+	return 0;
+}

linux-7.2.3/arch/riscv/mm/kasan_init.c

@@ -0,0 +1,537 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019 Andes Technology Corporation
+
+#include <linux/pfn.h>
+#include <linux/init_task.h>
+#include <linux/kasan.h>
+#include <linux/kernel.h>
+#include <linux/memblock.h>
+#include <linux/pgtable.h>
+#include <asm/tlbflush.h>
+#include <asm/fixmap.h>
+#include <asm/pgalloc.h>
+
+/*
+ * Kasan shadow region must lie at a fixed address across sv39, sv48 and sv57
+ * which is right before the kernel.
+ *
+ * For sv39, the region is aligned on PGDIR_SIZE so we only need to populate
+ * the page global directory with kasan_early_shadow_pmd.
+ *
+ * For sv48 and sv57, the region start is aligned on PGDIR_SIZE whereas the end
+ * region is not and then we have to go down to the PUD level.
+ */
+
+static pgd_t tmp_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
+static p4d_t tmp_p4d[PTRS_PER_P4D] __page_aligned_bss;
+static pud_t tmp_pud[PTRS_PER_PUD] __page_aligned_bss;
+
+static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned long end)
+{
+	phys_addr_t phys_addr;
+	pte_t *ptep, *p;
+
+	if (pmd_none(pmdp_get(pmd))) {
+		p = memblock_alloc_or_panic(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE);
+		set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(p)), PAGE_TABLE));
+	}
+
+	ptep = pte_offset_kernel(pmd, vaddr);
+
+	do {
+		if (pte_none(ptep_get(ptep))) {
+			phys_addr = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
+			set_pte(ptep, pfn_pte(PFN_DOWN(phys_addr), PAGE_KERNEL));
+			memset(__va(phys_addr), KASAN_SHADOW_INIT, PAGE_SIZE);
+		}
+	} while (ptep++, vaddr += PAGE_SIZE, vaddr != end);
+}
+
+static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned long end)
+{
+	phys_addr_t phys_addr;
+	pmd_t *pmdp, *p;
+	unsigned long next;
+
+	if (pud_none(pudp_get(pud))) {
+		p = memblock_alloc_or_panic(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE);
+		set_pud(pud, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE));
+	}
+
+	pmdp = pmd_offset(pud, vaddr);
+
+	do {
+		next = pmd_addr_end(vaddr, end);
+
+		if (pmd_none(pmdp_get(pmdp)) && IS_ALIGNED(vaddr, PMD_SIZE) &&
+		    (next - vaddr) >= PMD_SIZE) {
+			phys_addr = memblock_phys_alloc(PMD_SIZE, PMD_SIZE);
+			if (phys_addr) {
+				set_pmd(pmdp, pfn_pmd(PFN_DOWN(phys_addr), PAGE_KERNEL));
+				memset(__va(phys_addr), KASAN_SHADOW_INIT, PMD_SIZE);
+				continue;
+			}
+		}
+
+		kasan_populate_pte(pmdp, vaddr, next);
+	} while (pmdp++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_populate_pud(p4d_t *p4d,
+				      unsigned long vaddr, unsigned long end)
+{
+	phys_addr_t phys_addr;
+	pud_t *pudp, *p;
+	unsigned long next;
+
+	if (p4d_none(p4dp_get(p4d))) {
+		p = memblock_alloc_or_panic(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE);
+		set_p4d(p4d, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE));
+	}
+
+	pudp = pud_offset(p4d, vaddr);
+
+	do {
+		next = pud_addr_end(vaddr, end);
+
+		if (pud_none(pudp_get(pudp)) && IS_ALIGNED(vaddr, PUD_SIZE) &&
+		    (next - vaddr) >= PUD_SIZE) {
+			phys_addr = memblock_phys_alloc(PUD_SIZE, PUD_SIZE);
+			if (phys_addr) {
+				set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_KERNEL));
+				memset(__va(phys_addr), KASAN_SHADOW_INIT, PUD_SIZE);
+				continue;
+			}
+		}
+
+		kasan_populate_pmd(pudp, vaddr, next);
+	} while (pudp++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_populate_p4d(pgd_t *pgd,
+				      unsigned long vaddr, unsigned long end)
+{
+	phys_addr_t phys_addr;
+	p4d_t *p4dp, *p;
+	unsigned long next;
+
+	if (pgd_none(pgdp_get(pgd))) {
+		p = memblock_alloc_or_panic(PTRS_PER_P4D * sizeof(p4d_t), PAGE_SIZE);
+		set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE));
+	}
+
+	p4dp = p4d_offset(pgd, vaddr);
+
+	do {
+		next = p4d_addr_end(vaddr, end);
+
+		if (p4d_none(p4dp_get(p4dp)) && IS_ALIGNED(vaddr, P4D_SIZE) &&
+		    (next - vaddr) >= P4D_SIZE) {
+			phys_addr = memblock_phys_alloc(P4D_SIZE, P4D_SIZE);
+			if (phys_addr) {
+				set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_KERNEL));
+				memset(__va(phys_addr), KASAN_SHADOW_INIT, P4D_SIZE);
+				continue;
+			}
+		}
+
+		kasan_populate_pud(p4dp, vaddr, next);
+	} while (p4dp++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_populate_pgd(pgd_t *pgdp,
+				      unsigned long vaddr, unsigned long end)
+{
+	phys_addr_t phys_addr;
+	unsigned long next;
+
+	do {
+		next = pgd_addr_end(vaddr, end);
+
+		if (pgd_none(pgdp_get(pgdp)) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
+		    (next - vaddr) >= PGDIR_SIZE) {
+			phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE);
+			if (phys_addr) {
+				set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_KERNEL));
+				memset(__va(phys_addr), KASAN_SHADOW_INIT, PGDIR_SIZE);
+				continue;
+			}
+		}
+
+		kasan_populate_p4d(pgdp, vaddr, next);
+	} while (pgdp++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_early_clear_pud(p4d_t *p4dp,
+					 unsigned long vaddr, unsigned long end)
+{
+	pud_t *pudp, *base_pud;
+	unsigned long next;
+
+	if (!pgtable_l4_enabled) {
+		pudp = (pud_t *)p4dp;
+	} else {
+		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(p4dp_get(p4dp))));
+		pudp = base_pud + pud_index(vaddr);
+	}
+
+	do {
+		next = pud_addr_end(vaddr, end);
+
+		if (IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE) {
+			pud_clear(pudp);
+			continue;
+		}
+
+		BUG();
+	} while (pudp++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_early_clear_p4d(pgd_t *pgdp,
+					 unsigned long vaddr, unsigned long end)
+{
+	p4d_t *p4dp, *base_p4d;
+	unsigned long next;
+
+	if (!pgtable_l5_enabled) {
+		p4dp = (p4d_t *)pgdp;
+	} else {
+		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(pgdp_get(pgdp))));
+		p4dp = base_p4d + p4d_index(vaddr);
+	}
+
+	do {
+		next = p4d_addr_end(vaddr, end);
+
+		if (pgtable_l4_enabled && IS_ALIGNED(vaddr, P4D_SIZE) &&
+		    (next - vaddr) >= P4D_SIZE) {
+			p4d_clear(p4dp);
+			continue;
+		}
+
+		kasan_early_clear_pud(p4dp, vaddr, next);
+	} while (p4dp++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_early_clear_pgd(pgd_t *pgdp,
+					 unsigned long vaddr, unsigned long end)
+{
+	unsigned long next;
+
+	do {
+		next = pgd_addr_end(vaddr, end);
+
+		if (pgtable_l5_enabled && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
+		    (next - vaddr) >= PGDIR_SIZE) {
+			pgd_clear(pgdp);
+			continue;
+		}
+
+		kasan_early_clear_p4d(pgdp, vaddr, next);
+	} while (pgdp++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_early_populate_pud(p4d_t *p4dp,
+					    unsigned long vaddr,
+					    unsigned long end)
+{
+	pud_t *pudp, *base_pud;
+	phys_addr_t phys_addr;
+	unsigned long next;
+
+	if (!pgtable_l4_enabled) {
+		pudp = (pud_t *)p4dp;
+	} else {
+		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(p4dp_get(p4dp))));
+		pudp = base_pud + pud_index(vaddr);
+	}
+
+	do {
+		next = pud_addr_end(vaddr, end);
+
+		if (pud_none(pudp_get(pudp)) && IS_ALIGNED(vaddr, PUD_SIZE) &&
+		    (next - vaddr) >= PUD_SIZE) {
+			phys_addr = __pa((uintptr_t)kasan_early_shadow_pmd);
+			set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_TABLE));
+			continue;
+		}
+
+		BUG();
+	} while (pudp++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_early_populate_p4d(pgd_t *pgdp,
+					    unsigned long vaddr,
+					    unsigned long end)
+{
+	p4d_t *p4dp, *base_p4d;
+	phys_addr_t phys_addr;
+	unsigned long next;
+
+	/*
+	 * We can't use pgd_page_vaddr here as it would return a linear
+	 * mapping address but it is not mapped yet, but when populating
+	 * early_pg_dir, we need the physical address and when populating
+	 * swapper_pg_dir, we need the kernel virtual address so use
+	 * pt_ops facility.
+	 * Note that this test is then completely equivalent to
+	 * p4dp = p4d_offset(pgdp, vaddr)
+	 */
+	if (!pgtable_l5_enabled) {
+		p4dp = (p4d_t *)pgdp;
+	} else {
+		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(pgdp_get(pgdp))));
+		p4dp = base_p4d + p4d_index(vaddr);
+	}
+
+	do {
+		next = p4d_addr_end(vaddr, end);
+
+		if (p4d_none(p4dp_get(p4dp)) && IS_ALIGNED(vaddr, P4D_SIZE) &&
+		    (next - vaddr) >= P4D_SIZE) {
+			phys_addr = __pa((uintptr_t)kasan_early_shadow_pud);
+			set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_TABLE));
+			continue;
+		}
+
+		kasan_early_populate_pud(p4dp, vaddr, next);
+	} while (p4dp++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_early_populate_pgd(pgd_t *pgdp,
+					    unsigned long vaddr,
+					    unsigned long end)
+{
+	phys_addr_t phys_addr;
+	unsigned long next;
+
+	do {
+		next = pgd_addr_end(vaddr, end);
+
+		if (pgd_none(pgdp_get(pgdp)) && IS_ALIGNED(vaddr, PGDIR_SIZE) &&
+		    (next - vaddr) >= PGDIR_SIZE) {
+			phys_addr = __pa((uintptr_t)kasan_early_shadow_p4d);
+			set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_TABLE));
+			continue;
+		}
+
+		kasan_early_populate_p4d(pgdp, vaddr, next);
+	} while (pgdp++, vaddr = next, vaddr != end);
+}
+
+asmlinkage void __init kasan_early_init(void)
+{
+	uintptr_t i;
+
+	BUILD_BUG_ON(KASAN_SHADOW_OFFSET !=
+		KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT)));
+
+	for (i = 0; i < PTRS_PER_PTE; ++i)
+		set_pte(kasan_early_shadow_pte + i,
+			pfn_pte(virt_to_pfn(kasan_early_shadow_page), PAGE_KERNEL));
+
+	for (i = 0; i < PTRS_PER_PMD; ++i)
+		set_pmd(kasan_early_shadow_pmd + i,
+			pfn_pmd(PFN_DOWN
+				(__pa((uintptr_t)kasan_early_shadow_pte)),
+				PAGE_TABLE));
+
+	if (pgtable_l4_enabled) {
+		for (i = 0; i < PTRS_PER_PUD; ++i)
+			set_pud(kasan_early_shadow_pud + i,
+				pfn_pud(PFN_DOWN
+					(__pa(((uintptr_t)kasan_early_shadow_pmd))),
+					PAGE_TABLE));
+	}
+
+	if (pgtable_l5_enabled) {
+		for (i = 0; i < PTRS_PER_P4D; ++i)
+			set_p4d(kasan_early_shadow_p4d + i,
+				pfn_p4d(PFN_DOWN
+					(__pa(((uintptr_t)kasan_early_shadow_pud))),
+					PAGE_TABLE));
+	}
+
+	kasan_early_populate_pgd(early_pg_dir + pgd_index(KASAN_SHADOW_START),
+				 KASAN_SHADOW_START, KASAN_SHADOW_END);
+
+	local_flush_tlb_all();
+}
+
+void __init kasan_swapper_init(void)
+{
+	kasan_early_populate_pgd(pgd_offset_k(KASAN_SHADOW_START),
+				 KASAN_SHADOW_START, KASAN_SHADOW_END);
+
+	local_flush_tlb_all();
+}
+
+static void __init kasan_populate(void *start, void *end)
+{
+	unsigned long vaddr = (unsigned long)start & PAGE_MASK;
+	unsigned long vend = PAGE_ALIGN((unsigned long)end);
+
+	kasan_populate_pgd(pgd_offset_k(vaddr), vaddr, vend);
+}
+
+static void __init kasan_shallow_populate_pud(p4d_t *p4d,
+					      unsigned long vaddr, unsigned long end)
+{
+	unsigned long next;
+	void *p;
+	pud_t *pud_k = pud_offset(p4d, vaddr);
+
+	do {
+		next = pud_addr_end(vaddr, end);
+
+		if (pud_none(pudp_get(pud_k))) {
+			p = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
+			set_pud(pud_k, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE));
+			continue;
+		}
+
+		BUG();
+	} while (pud_k++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_shallow_populate_p4d(pgd_t *pgd,
+					      unsigned long vaddr, unsigned long end)
+{
+	unsigned long next;
+	void *p;
+	p4d_t *p4d_k = p4d_offset(pgd, vaddr);
+
+	do {
+		next = p4d_addr_end(vaddr, end);
+
+		if (p4d_none(p4dp_get(p4d_k))) {
+			p = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
+			set_p4d(p4d_k, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE));
+			continue;
+		}
+
+		kasan_shallow_populate_pud(p4d_k, vaddr, end);
+	} while (p4d_k++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_shallow_populate_pgd(unsigned long vaddr, unsigned long end)
+{
+	unsigned long next;
+	void *p;
+	pgd_t *pgd_k = pgd_offset_k(vaddr);
+
+	do {
+		next = pgd_addr_end(vaddr, end);
+
+		if (pgd_none(pgdp_get(pgd_k))) {
+			p = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
+			set_pgd(pgd_k, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE));
+			continue;
+		}
+
+		kasan_shallow_populate_p4d(pgd_k, vaddr, next);
+	} while (pgd_k++, vaddr = next, vaddr != end);
+}
+
+static void __init kasan_shallow_populate(void *start, void *end)
+{
+	unsigned long vaddr = (unsigned long)start & PAGE_MASK;
+	unsigned long vend = PAGE_ALIGN((unsigned long)end);
+
+	kasan_shallow_populate_pgd(vaddr, vend);
+}
+
+#ifdef CONFIG_KASAN_VMALLOC
+void __init kasan_populate_early_vm_area_shadow(void *start, unsigned long size)
+{
+	kasan_populate(kasan_mem_to_shadow(start),
+		       kasan_mem_to_shadow(start + size));
+}
+#endif
+
+static void __init create_tmp_mapping(void)
+{
+	void *ptr;
+	p4d_t *base_p4d;
+
+	/*
+	 * We need to clean the early mapping: this is hard to achieve "in-place",
+	 * so install a temporary mapping like arm64 and x86 do.
+	 */
+	memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(pgd_t) * PTRS_PER_PGD);
+
+	/* Copy the last p4d since it is shared with the kernel mapping. */
+	if (pgtable_l5_enabled) {
+		ptr = (p4d_t *)pgd_page_vaddr(pgdp_get(pgd_offset_k(KASAN_SHADOW_END)));
+		memcpy(tmp_p4d, ptr, sizeof(p4d_t) * PTRS_PER_P4D);
+		set_pgd(&tmp_pg_dir[pgd_index(KASAN_SHADOW_END)],
+			pfn_pgd(PFN_DOWN(__pa(tmp_p4d)), PAGE_TABLE));
+		base_p4d = tmp_p4d;
+	} else {
+		base_p4d = (p4d_t *)tmp_pg_dir;
+	}
+
+	/* Copy the last pud since it is shared with the kernel mapping. */
+	if (pgtable_l4_enabled) {
+		ptr = (pud_t *)p4d_page_vaddr(p4dp_get(base_p4d + p4d_index(KASAN_SHADOW_END)));
+		memcpy(tmp_pud, ptr, sizeof(pud_t) * PTRS_PER_PUD);
+		set_p4d(&base_p4d[p4d_index(KASAN_SHADOW_END)],
+			pfn_p4d(PFN_DOWN(__pa(tmp_pud)), PAGE_TABLE));
+	}
+}
+
+void __init kasan_init(void)
+{
+	phys_addr_t p_start, p_end;
+	u64 i;
+
+	create_tmp_mapping();
+	csr_write(CSR_SATP, PFN_DOWN(__pa(tmp_pg_dir)) | satp_mode);
+
+	kasan_early_clear_pgd(pgd_offset_k(KASAN_SHADOW_START),
+			      KASAN_SHADOW_START, KASAN_SHADOW_END);
+
+	kasan_populate_early_shadow((void *)kasan_mem_to_shadow((void *)FIXADDR_START),
+				    (void *)kasan_mem_to_shadow((void *)VMALLOC_START));
+
+	if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
+		kasan_shallow_populate(
+			(void *)kasan_mem_to_shadow((void *)VMALLOC_START),
+			(void *)kasan_mem_to_shadow((void *)VMALLOC_END));
+		/* Shallow populate modules and BPF which are vmalloc-allocated */
+		kasan_shallow_populate(
+			(void *)kasan_mem_to_shadow((void *)MODULES_VADDR),
+			(void *)kasan_mem_to_shadow((void *)MODULES_END));
+	} else {
+		kasan_populate_early_shadow((void *)kasan_mem_to_shadow((void *)VMALLOC_START),
+					    (void *)kasan_mem_to_shadow((void *)VMALLOC_END));
+	}
+
+	/* Populate the linear mapping */
+	for_each_mem_range(i, &p_start, &p_end) {
+		void *start = (void *)__va(p_start);
+		void *end = (void *)__va(p_end);
+
+		if (start >= end)
+			break;
+
+		kasan_populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end));
+	}
+
+	/* Populate kernel */
+	kasan_populate(kasan_mem_to_shadow((const void *)MODULES_END),
+		       kasan_mem_to_shadow((const void *)MODULES_VADDR + SZ_2G));
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		set_pte(&kasan_early_shadow_pte[i],
+			mk_pte(virt_to_page(kasan_early_shadow_page),
+			       __pgprot(_PAGE_PRESENT | _PAGE_READ |
+					_PAGE_ACCESSED)));
+
+	memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE);
+	init_task.kasan_depth = 0;
+
+	csr_write(CSR_SATP, PFN_DOWN(__pa(swapper_pg_dir)) | satp_mode);
+	local_flush_tlb_all();
+	kasan_init_generic();
+}

linux-7.2.3/arch/riscv/mm/pageattr.c

@@ -0,0 +1,470 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2019 SiFive
+ */
+
+#include <linux/pagewalk.h>
+#include <linux/pgtable.h>
+#include <linux/vmalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/bitops.h>
+#include <asm/set_memory.h>
+
+struct pageattr_masks {
+	pgprot_t set_mask;
+	pgprot_t clear_mask;
+};
+
+static unsigned long set_pageattr_masks(unsigned long val, struct mm_walk *walk)
+{
+	struct pageattr_masks *masks = walk->private;
+	unsigned long new_val = val;
+
+	new_val &= ~(pgprot_val(masks->clear_mask));
+	new_val |= (pgprot_val(masks->set_mask));
+
+	return new_val;
+}
+
+static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	p4d_t val = p4dp_get(p4d);
+
+	if (p4d_leaf(val)) {
+		val = __p4d(set_pageattr_masks(p4d_val(val), walk));
+		set_p4d(p4d, val);
+	}
+
+	return 0;
+}
+
+static int pageattr_pud_entry(pud_t *pud, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	pud_t val = pudp_get(pud);
+
+	if (pud_leaf(val)) {
+		val = __pud(set_pageattr_masks(pud_val(val), walk));
+		set_pud(pud, val);
+	}
+
+	return 0;
+}
+
+static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	pmd_t val = pmdp_get(pmd);
+
+	if (pmd_leaf(val)) {
+		val = __pmd(set_pageattr_masks(pmd_val(val), walk));
+		set_pmd(pmd, val);
+	}
+
+	return 0;
+}
+
+static int pageattr_pte_entry(pte_t *pte, unsigned long addr,
+			      unsigned long next, struct mm_walk *walk)
+{
+	pte_t val = ptep_get(pte);
+
+	val = __pte(set_pageattr_masks(pte_val(val), walk));
+	set_pte(pte, val);
+
+	return 0;
+}
+
+static int pageattr_pte_hole(unsigned long addr, unsigned long next,
+			     int depth, struct mm_walk *walk)
+{
+	/* Nothing to do here */
+	return 0;
+}
+
+static const struct mm_walk_ops pageattr_ops = {
+	.p4d_entry = pageattr_p4d_entry,
+	.pud_entry = pageattr_pud_entry,
+	.pmd_entry = pageattr_pmd_entry,
+	.pte_entry = pageattr_pte_entry,
+	.pte_hole = pageattr_pte_hole,
+	.walk_lock = PGWALK_RDLOCK,
+};
+
+#ifdef CONFIG_64BIT
+static int __split_linear_mapping_pmd(pud_t *pudp,
+				      unsigned long vaddr, unsigned long end)
+{
+	pmd_t *pmdp;
+	unsigned long next;
+
+	pmdp = pmd_offset(pudp, vaddr);
+
+	do {
+		next = pmd_addr_end(vaddr, end);
+
+		if (next - vaddr >= PMD_SIZE &&
+		    vaddr <= (vaddr & PMD_MASK) && end >= next)
+			continue;
+
+		if (pmd_leaf(pmdp_get(pmdp))) {
+			struct page *pte_page;
+			unsigned long pfn = _pmd_pfn(pmdp_get(pmdp));
+			pgprot_t prot = __pgprot(pmd_val(pmdp_get(pmdp)) & ~_PAGE_PFN_MASK);
+			pte_t *ptep_new;
+			int i;
+
+			pte_page = alloc_page(GFP_KERNEL);
+			if (!pte_page)
+				return -ENOMEM;
+
+			ptep_new = (pte_t *)page_address(pte_page);
+			for (i = 0; i < PTRS_PER_PTE; ++i, ++ptep_new)
+				set_pte(ptep_new, pfn_pte(pfn + i, prot));
+
+			smp_wmb();
+
+			set_pmd(pmdp, pfn_pmd(page_to_pfn(pte_page), PAGE_TABLE));
+		}
+	} while (pmdp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int __split_linear_mapping_pud(p4d_t *p4dp,
+				      unsigned long vaddr, unsigned long end)
+{
+	pud_t *pudp;
+	unsigned long next;
+	int ret;
+
+	pudp = pud_offset(p4dp, vaddr);
+
+	do {
+		next = pud_addr_end(vaddr, end);
+
+		if (next - vaddr >= PUD_SIZE &&
+		    vaddr <= (vaddr & PUD_MASK) && end >= next)
+			continue;
+
+		if (pud_leaf(pudp_get(pudp))) {
+			struct page *pmd_page;
+			unsigned long pfn = _pud_pfn(pudp_get(pudp));
+			pgprot_t prot = __pgprot(pud_val(pudp_get(pudp)) & ~_PAGE_PFN_MASK);
+			pmd_t *pmdp_new;
+			int i;
+
+			pmd_page = alloc_page(GFP_KERNEL);
+			if (!pmd_page)
+				return -ENOMEM;
+
+			pmdp_new = (pmd_t *)page_address(pmd_page);
+			for (i = 0; i < PTRS_PER_PMD; ++i, ++pmdp_new)
+				set_pmd(pmdp_new,
+					pfn_pmd(pfn + ((i * PMD_SIZE) >> PAGE_SHIFT), prot));
+
+			smp_wmb();
+
+			set_pud(pudp, pfn_pud(page_to_pfn(pmd_page), PAGE_TABLE));
+		}
+
+		ret = __split_linear_mapping_pmd(pudp, vaddr, next);
+		if (ret)
+			return ret;
+	} while (pudp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int __split_linear_mapping_p4d(pgd_t *pgdp,
+				      unsigned long vaddr, unsigned long end)
+{
+	p4d_t *p4dp;
+	unsigned long next;
+	int ret;
+
+	p4dp = p4d_offset(pgdp, vaddr);
+
+	do {
+		next = p4d_addr_end(vaddr, end);
+
+		/*
+		 * If [vaddr; end] contains [vaddr & P4D_MASK; next], we don't
+		 * need to split, we'll change the protections on the whole P4D.
+		 */
+		if (next - vaddr >= P4D_SIZE &&
+		    vaddr <= (vaddr & P4D_MASK) && end >= next)
+			continue;
+
+		if (p4d_leaf(p4dp_get(p4dp))) {
+			struct page *pud_page;
+			unsigned long pfn = _p4d_pfn(p4dp_get(p4dp));
+			pgprot_t prot = __pgprot(p4d_val(p4dp_get(p4dp)) & ~_PAGE_PFN_MASK);
+			pud_t *pudp_new;
+			int i;
+
+			pud_page = alloc_page(GFP_KERNEL);
+			if (!pud_page)
+				return -ENOMEM;
+
+			/*
+			 * Fill the pud level with leaf puds that have the same
+			 * protections as the leaf p4d.
+			 */
+			pudp_new = (pud_t *)page_address(pud_page);
+			for (i = 0; i < PTRS_PER_PUD; ++i, ++pudp_new)
+				set_pud(pudp_new,
+					pfn_pud(pfn + ((i * PUD_SIZE) >> PAGE_SHIFT), prot));
+
+			/*
+			 * Make sure the pud filling is not reordered with the
+			 * p4d store which could result in seeing a partially
+			 * filled pud level.
+			 */
+			smp_wmb();
+
+			set_p4d(p4dp, pfn_p4d(page_to_pfn(pud_page), PAGE_TABLE));
+		}
+
+		ret = __split_linear_mapping_pud(p4dp, vaddr, next);
+		if (ret)
+			return ret;
+	} while (p4dp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int __split_linear_mapping_pgd(pgd_t *pgdp,
+				      unsigned long vaddr,
+				      unsigned long end)
+{
+	unsigned long next;
+	int ret;
+
+	do {
+		next = pgd_addr_end(vaddr, end);
+		/* We never use PGD mappings for the linear mapping */
+		ret = __split_linear_mapping_p4d(pgdp, vaddr, next);
+		if (ret)
+			return ret;
+	} while (pgdp++, vaddr = next, vaddr != end);
+
+	return 0;
+}
+
+static int split_linear_mapping(unsigned long start, unsigned long end)
+{
+	return __split_linear_mapping_pgd(pgd_offset_k(start), start, end);
+}
+#endif	/* CONFIG_64BIT */
+
+static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
+			pgprot_t clear_mask)
+{
+	int ret;
+	unsigned long start = addr;
+	unsigned long end = start + PAGE_SIZE * numpages;
+	unsigned long __maybe_unused lm_start;
+	unsigned long __maybe_unused lm_end;
+	struct pageattr_masks masks = {
+		.set_mask = set_mask,
+		.clear_mask = clear_mask
+	};
+
+	if (!numpages)
+		return 0;
+
+	mmap_write_lock(&init_mm);
+
+#ifdef CONFIG_64BIT
+	/*
+	 * We are about to change the permissions of a kernel mapping, we must
+	 * apply the same changes to its linear mapping alias, which may imply
+	 * splitting a huge mapping.
+	 */
+
+	if (is_vmalloc_or_module_addr((void *)start)) {
+		struct vm_struct *area = NULL;
+		int i, page_start;
+
+		area = find_vm_area((void *)start);
+		page_start = (start - (unsigned long)area->addr) >> PAGE_SHIFT;
+
+		for (i = page_start; i < page_start + numpages; ++i) {
+			lm_start = (unsigned long)page_address(area->pages[i]);
+			lm_end = lm_start + PAGE_SIZE;
+
+			ret = split_linear_mapping(lm_start, lm_end);
+			if (ret)
+				goto unlock;
+
+			ret = walk_kernel_page_table_range(lm_start, lm_end,
+						    &pageattr_ops, NULL, &masks);
+			if (ret)
+				goto unlock;
+		}
+	} else if (is_kernel_mapping(start) || is_linear_mapping(start)) {
+		if (is_kernel_mapping(start)) {
+			lm_start = (unsigned long)lm_alias(start);
+			lm_end = (unsigned long)lm_alias(end);
+		} else {
+			lm_start = start;
+			lm_end = end;
+		}
+
+		ret = split_linear_mapping(lm_start, lm_end);
+		if (ret)
+			goto unlock;
+
+		ret = walk_kernel_page_table_range(lm_start, lm_end,
+					    &pageattr_ops, NULL, &masks);
+		if (ret)
+			goto unlock;
+	}
+
+	ret =  walk_kernel_page_table_range(start, end, &pageattr_ops, NULL,
+				     &masks);
+
+unlock:
+	mmap_write_unlock(&init_mm);
+
+	/*
+	 * We can't use flush_tlb_kernel_range() here as we may have split a
+	 * hugepage that is larger than that, so let's flush everything.
+	 */
+	flush_tlb_all();
+#else
+	ret =  walk_kernel_page_table_range(start, end, &pageattr_ops, NULL,
+				     &masks);
+
+	mmap_write_unlock(&init_mm);
+
+	flush_tlb_kernel_range(start, end);
+#endif
+
+	return ret;
+}
+
+int set_memory_rw_nx(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, __pgprot(_PAGE_READ | _PAGE_WRITE),
+			    __pgprot(_PAGE_EXEC));
+}
+
+int set_memory_ro(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, __pgprot(_PAGE_READ),
+			    __pgprot(_PAGE_WRITE));
+}
+
+int set_memory_rw(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, __pgprot(_PAGE_READ | _PAGE_WRITE),
+			    __pgprot(0));
+}
+
+int set_memory_x(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, __pgprot(_PAGE_EXEC), __pgprot(0));
+}
+
+int set_memory_nx(unsigned long addr, int numpages)
+{
+	return __set_memory(addr, numpages, __pgprot(0), __pgprot(_PAGE_EXEC));
+}
+
+int set_direct_map_invalid_noflush(struct page *page)
+{
+	return __set_memory((unsigned long)page_address(page), 1,
+			    __pgprot(0), __pgprot(_PAGE_PRESENT));
+}
+
+int set_direct_map_default_noflush(struct page *page)
+{
+	return __set_memory((unsigned long)page_address(page), 1,
+			    PAGE_KERNEL, __pgprot(_PAGE_EXEC));
+}
+
+int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid)
+{
+	pgprot_t set, clear;
+
+	if (valid) {
+		set = PAGE_KERNEL;
+		clear = __pgprot(_PAGE_EXEC);
+	} else {
+		set = __pgprot(0);
+		clear = __pgprot(_PAGE_PRESENT);
+	}
+
+	return __set_memory((unsigned long)page_address(page), nr, set, clear);
+}
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+static int debug_pagealloc_set_page(pte_t *pte, unsigned long addr, void *data)
+{
+	int enable = *(int *)data;
+
+	unsigned long val = pte_val(ptep_get(pte));
+
+	if (enable)
+		val |= _PAGE_PRESENT;
+	else
+		val &= ~_PAGE_PRESENT;
+
+	set_pte(pte, __pte(val));
+
+	return 0;
+}
+
+void __kernel_map_pages(struct page *page, int numpages, int enable)
+{
+	if (!debug_pagealloc_enabled())
+		return;
+
+	unsigned long start = (unsigned long)page_address(page);
+	unsigned long size = PAGE_SIZE * numpages;
+
+	apply_to_existing_page_range(&init_mm, start, size, debug_pagealloc_set_page, &enable);
+
+	flush_tlb_kernel_range(start, start + size);
+}
+#endif
+
+bool kernel_page_present(struct page *page)
+{
+	unsigned long addr = (unsigned long)page_address(page);
+	pgd_t *pgd;
+	pud_t *pud;
+	p4d_t *p4d;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pgd = pgd_offset_k(addr);
+	if (!pgd_present(pgdp_get(pgd)))
+		return false;
+	if (pgd_leaf(pgdp_get(pgd)))
+		return true;
+
+	p4d = p4d_offset(pgd, addr);
+	if (!p4d_present(p4dp_get(p4d)))
+		return false;
+	if (p4d_leaf(p4dp_get(p4d)))
+		return true;
+
+	pud = pud_offset(p4d, addr);
+	if (!pud_present(pudp_get(pud)))
+		return false;
+	if (pud_leaf(pudp_get(pud)))
+		return true;
+
+	pmd = pmd_offset(pud, addr);
+	if (!pmd_present(pmdp_get(pmd)))
+		return false;
+	if (pmd_leaf(pmdp_get(pmd)))
+		return true;
+
+	pte = pte_offset_kernel(pmd, addr);
+	return pte_present(ptep_get(pte));
+}

linux-7.2.3/arch/riscv/mm/pgtable.c

@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <asm/pgalloc.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/pgtable.h>
+
+int ptep_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pte_t *ptep,
+			  pte_t entry, int dirty)
+{
+	if (riscv_has_extension_unlikely(RISCV_ISA_EXT_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;
+	}
+
+	if (!pte_same(ptep_get(ptep), entry))
+		__set_pte_at(vma->vm_mm, ptep, entry);
+	/*
+	 * update_mmu_cache will unconditionally execute, handling both
+	 * the case that the PTE changed and the spurious fault case.
+	 */
+	return true;
+}
+
+bool ptep_test_and_clear_young(struct vm_area_struct *vma,
+		unsigned long address, pte_t *ptep)
+{
+	if (!pte_young(ptep_get(ptep)))
+		return false;
+	return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep));
+}
+EXPORT_SYMBOL_GPL(ptep_test_and_clear_young);
+
+#ifdef CONFIG_64BIT
+pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+{
+	if (pgtable_l4_enabled)
+		return p4d_pgtable(p4dp_get(p4d)) + pud_index(address);
+
+	return (pud_t *)p4d;
+}
+EXPORT_SYMBOL_GPL(pud_offset);
+
+p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+{
+	if (pgtable_l5_enabled)
+		return pgd_pgtable(pgdp_get(pgd)) + p4d_index(address);
+
+	return (p4d_t *)pgd;
+}
+EXPORT_SYMBOL_GPL(p4d_offset);
+#endif
+
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
+{
+	return 0;
+}
+
+void p4d_clear_huge(p4d_t *p4d)
+{
+}
+
+int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot)
+{
+	pud_t new_pud = pfn_pud(__phys_to_pfn(phys), prot);
+
+	set_pud(pud, new_pud);
+	return 1;
+}
+
+int pud_clear_huge(pud_t *pud)
+{
+	if (!pud_leaf(pudp_get(pud)))
+		return 0;
+	pud_clear(pud);
+	return 1;
+}
+
+int pud_free_pmd_page(pud_t *pud, unsigned long addr)
+{
+	pmd_t *pmd = pud_pgtable(pudp_get(pud));
+	int i;
+
+	pud_clear(pud);
+
+	flush_tlb_kernel_range(addr, addr + PUD_SIZE);
+
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		if (!pmd_none(pmd[i])) {
+			pte_t *pte = (pte_t *)pmd_page_vaddr(pmd[i]);
+
+			pte_free_kernel(NULL, pte);
+		}
+	}
+
+	pmd_free(NULL, pmd);
+
+	return 1;
+}
+
+int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot)
+{
+	pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), prot);
+
+	set_pmd(pmd, new_pmd);
+	return 1;
+}
+
+int pmd_clear_huge(pmd_t *pmd)
+{
+	if (!pmd_leaf(pmdp_get(pmd)))
+		return 0;
+	pmd_clear(pmd);
+	return 1;
+}
+
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
+{
+	pte_t *pte = (pte_t *)pmd_page_vaddr(pmdp_get(pmd));
+
+	pmd_clear(pmd);
+
+	flush_tlb_kernel_range(addr, addr + PMD_SIZE);
+	pte_free_kernel(NULL, pte);
+	return 1;
+}
+
+#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
+					unsigned long address, pmd_t *pmdp)
+{
+	pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
+
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+	VM_BUG_ON(pmd_trans_huge(pmdp_get(pmdp)));
+	/*
+	 * When leaf PTE entries (regular pages) are collapsed into a leaf
+	 * PMD entry (huge page), a valid non-leaf PTE is converted into a
+	 * valid leaf PTE at the level 1 page table.  Since the sfence.vma
+	 * forms that specify an address only apply to leaf PTEs, we need a
+	 * global flush here.  collapse_huge_page() assumes these flushes are
+	 * eager, so just do the fence here.
+	 */
+	flush_tlb_mm(vma->vm_mm);
+	return pmd;
+}
+
+pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address,
+		      pud_t *pudp)
+{
+	VM_WARN_ON_ONCE(!pud_present(*pudp));
+	pud_t old = pudp_establish(vma, address, pudp, pud_mkinvalid(*pudp));
+
+	flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE);
+	return old;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_SHADOW_STACK)
+		return pte_mkwrite_shstk(pte);
+
+	return pte_mkwrite_novma(pte);
+}
+
+pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_SHADOW_STACK)
+		return pmd_mkwrite_shstk(pmd);
+
+	return pmd_mkwrite_novma(pmd);
+}

linux-7.2.3/arch/riscv/mm/physaddr.c

@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/types.h>
+#include <linux/mmdebug.h>
+#include <linux/mm.h>
+#include <asm/page.h>
+#include <asm/sections.h>
+
+phys_addr_t __virt_to_phys(unsigned long x)
+{
+	/*
+	 * Boundary checking against the kernel linear mapping space.
+	 */
+	WARN(!is_linear_mapping(x) && !is_kernel_mapping(x),
+	     "virt_to_phys used for non-linear address: %p (%pS)\n",
+	     (void *)x, (void *)x);
+
+	return __va_to_pa_nodebug(x);
+}
+EXPORT_SYMBOL(__virt_to_phys);
+
+phys_addr_t __phys_addr_symbol(unsigned long x)
+{
+	unsigned long kernel_start = kernel_map.virt_addr;
+	unsigned long kernel_end = kernel_start + kernel_map.size;
+
+	/*
+	 * Boundary checking against the kernel image mapping.
+	 * __pa_symbol should only be used on kernel symbol addresses.
+	 */
+	VIRTUAL_BUG_ON(x < kernel_start || x > kernel_end);
+
+	return __va_to_pa_nodebug(x);
+}
+EXPORT_SYMBOL(__phys_addr_symbol);
+
+phys_addr_t linear_mapping_va_to_pa(unsigned long x)
+{
+	BUG_ON(!kernel_map.va_pa_offset);
+
+	return ((unsigned long)(x) - kernel_map.va_pa_offset);
+}
+EXPORT_SYMBOL(linear_mapping_va_to_pa);
+
+void *linear_mapping_pa_to_va(unsigned long x)
+{
+	BUG_ON(!kernel_map.va_pa_offset);
+
+	return ((void *)((unsigned long)(x) + kernel_map.va_pa_offset));
+}
+EXPORT_SYMBOL(linear_mapping_pa_to_va);

linux-7.2.3/arch/riscv/mm/pmem.c

@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022 Ventana Micro Systems Inc.
+ */
+
+#include <linux/export.h>
+#include <linux/libnvdimm.h>
+
+#include <asm/cacheflush.h>
+#include <asm/dma-noncoherent.h>
+
+void arch_wb_cache_pmem(void *addr, size_t size)
+{
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (unlikely(noncoherent_cache_ops.wback)) {
+		noncoherent_cache_ops.wback(virt_to_phys(addr), size);
+		return;
+	}
+#endif
+	ALT_CMO_OP(CLEAN, addr, size, riscv_cbom_block_size);
+}
+EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
+
+void arch_invalidate_pmem(void *addr, size_t size)
+{
+#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
+	if (unlikely(noncoherent_cache_ops.inv)) {
+		noncoherent_cache_ops.inv(virt_to_phys(addr), size);
+		return;
+	}
+#endif
+	ALT_CMO_OP(INVAL, addr, size, riscv_cbom_block_size);
+}
+EXPORT_SYMBOL_GPL(arch_invalidate_pmem);

linux-7.2.3/arch/riscv/mm/ptdump.c

@@ -0,0 +1,467 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2019 SiFive
+ */
+
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/string.h>
+#include <linux/ptdump.h>
+
+#include <linux/pgtable.h>
+#include <asm/kasan.h>
+
+#define pt_dump_seq_printf(m, fmt, args...)	\
+({						\
+	if (m)					\
+		seq_printf(m, fmt, ##args);	\
+})
+
+#define pt_dump_seq_puts(m, fmt)	\
+({					\
+	if (m)				\
+		seq_puts(m, fmt);	\
+})
+
+/*
+ * The page dumper groups page table entries of the same type into a single
+ * description. It uses pg_state to track the range information while
+ * iterating over the pte entries. When the continuity is broken it then
+ * dumps out a description of the range.
+ */
+struct pg_state {
+	struct ptdump_state ptdump;
+	struct seq_file *seq;
+	const struct addr_marker *marker;
+	unsigned long start_address;
+	unsigned long start_pa;
+	unsigned long last_pa;
+	int level;
+	u64 current_prot;
+	bool check_wx;
+	unsigned long wx_pages;
+};
+
+/* Address marker */
+struct addr_marker {
+	unsigned long start_address;
+	const char *name;
+};
+
+/* Private information for debugfs */
+struct ptd_mm_info {
+	struct mm_struct		*mm;
+	const struct addr_marker	*markers;
+	unsigned long base_addr;
+	unsigned long end;
+};
+
+enum address_markers_idx {
+	FIXMAP_START_NR,
+	FIXMAP_END_NR,
+	PCI_IO_START_NR,
+	PCI_IO_END_NR,
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	VMEMMAP_START_NR,
+	VMEMMAP_END_NR,
+#endif
+	VMALLOC_START_NR,
+	VMALLOC_END_NR,
+	PAGE_OFFSET_NR,
+#ifdef CONFIG_KASAN
+	KASAN_SHADOW_START_NR,
+	KASAN_SHADOW_END_NR,
+#endif
+#ifdef CONFIG_64BIT
+	MODULES_MAPPING_NR,
+	KERNEL_MAPPING_NR,
+#endif
+	END_OF_SPACE_NR
+};
+
+static struct addr_marker address_markers[] = {
+	{0, "Fixmap start"},
+	{0, "Fixmap end"},
+	{0, "PCI I/O start"},
+	{0, "PCI I/O end"},
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	{0, "vmemmap start"},
+	{0, "vmemmap end"},
+#endif
+	{0, "vmalloc() area"},
+	{0, "vmalloc() end"},
+	{0, "Linear mapping"},
+#ifdef CONFIG_KASAN
+	{0, "Kasan shadow start"},
+	{0, "Kasan shadow end"},
+#endif
+#ifdef CONFIG_64BIT
+	{0, "Modules/BPF mapping"},
+	{0, "Kernel mapping"},
+#endif
+	{-1, NULL},
+};
+
+static struct ptd_mm_info kernel_ptd_info = {
+	.mm		= &init_mm,
+	.markers	= address_markers,
+	.base_addr	= 0,
+	.end		= ULONG_MAX,
+};
+
+#ifdef CONFIG_EFI
+static struct addr_marker efi_addr_markers[] = {
+		{ 0,		"UEFI runtime start" },
+		{ SZ_1G,	"UEFI runtime end" },
+		{ -1,		NULL }
+};
+
+static struct ptd_mm_info efi_ptd_info = {
+	.mm		= &efi_mm,
+	.markers	= efi_addr_markers,
+	.base_addr	= 0,
+	.end		= SZ_2G,
+};
+#endif
+
+/* Page Table Entry */
+struct prot_bits {
+	u64 mask;
+	const char *set;
+	const char *clear;
+};
+
+static const struct prot_bits pte_bits[] = {
+	{
+#ifdef CONFIG_64BIT
+		.mask = _PAGE_NAPOT,
+		.set = "N",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_MTMASK_SVPBMT,
+		.set = "MT(%s)",
+		.clear = "  ..  ",
+	}, {
+#endif
+		.mask = _PAGE_SOFT,
+		.set = "RSW(%d)",
+		.clear = "  ..  ",
+	}, {
+		.mask = _PAGE_DIRTY,
+		.set = "D",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_ACCESSED,
+		.set = "A",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_GLOBAL,
+		.set = "G",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_USER,
+		.set = "U",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_EXEC,
+		.set = "X",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_WRITE,
+		.set = "W",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_READ,
+		.set = "R",
+		.clear = ".",
+	}, {
+		.mask = _PAGE_PRESENT,
+		.set = "V",
+		.clear = ".",
+	}
+};
+
+/* Page Level */
+struct pg_level {
+	const char *name;
+	u64 mask;
+};
+
+static struct pg_level pg_level[] = {
+	{ /* pgd */
+		.name = "PGD",
+	}, { /* p4d */
+		.name = (CONFIG_PGTABLE_LEVELS > 4) ? "P4D" : "PGD",
+	}, { /* pud */
+		.name = (CONFIG_PGTABLE_LEVELS > 3) ? "PUD" : "PGD",
+	}, { /* pmd */
+		.name = (CONFIG_PGTABLE_LEVELS > 2) ? "PMD" : "PGD",
+	}, { /* pte */
+		.name = "PTE",
+	},
+};
+
+static void dump_prot(struct pg_state *st)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(pte_bits); i++) {
+		char s[7];
+		unsigned long val;
+
+		val = st->current_prot & pte_bits[i].mask;
+		if (val) {
+			if (pte_bits[i].mask == _PAGE_SOFT)
+				snprintf(s, sizeof(s), pte_bits[i].set, val >> 8);
+#ifdef CONFIG_64BIT
+			else if (pte_bits[i].mask == _PAGE_MTMASK_SVPBMT) {
+				if (val == _PAGE_NOCACHE_SVPBMT)
+					snprintf(s, sizeof(s), pte_bits[i].set, "NC");
+				else if (val == _PAGE_IO_SVPBMT)
+					snprintf(s, sizeof(s), pte_bits[i].set, "IO");
+				else
+					snprintf(s, sizeof(s), pte_bits[i].set, "??");
+			}
+#endif
+			else
+				strscpy(s, pte_bits[i].set);
+		} else {
+			strscpy(s, pte_bits[i].clear);
+		}
+
+		pt_dump_seq_printf(st->seq, " %s", s);
+	}
+}
+
+#ifdef CONFIG_64BIT
+#define ADDR_FORMAT	"0x%016lx"
+#else
+#define ADDR_FORMAT	"0x%08lx"
+#endif
+static void dump_addr(struct pg_state *st, unsigned long addr)
+{
+	static const char units[] = "KMGTPE";
+	const char *unit = units;
+	unsigned long delta;
+
+	pt_dump_seq_printf(st->seq, ADDR_FORMAT "-" ADDR_FORMAT "   ",
+			   st->start_address, addr);
+
+	pt_dump_seq_printf(st->seq, " " ADDR_FORMAT " ", st->start_pa);
+	delta = (addr - st->start_address) >> 10;
+
+	while (!(delta & 1023) && unit[1]) {
+		delta >>= 10;
+		unit++;
+	}
+
+	pt_dump_seq_printf(st->seq, "%9lu%c %s", delta, *unit,
+			   pg_level[st->level].name);
+}
+
+static void note_prot_wx(struct pg_state *st, unsigned long addr)
+{
+	if (!st->check_wx)
+		return;
+
+	if ((st->current_prot & (_PAGE_WRITE | _PAGE_EXEC)) !=
+	    (_PAGE_WRITE | _PAGE_EXEC))
+		return;
+
+	WARN_ONCE(1, "riscv/mm: Found insecure W+X mapping at address %p/%pS\n",
+		  (void *)st->start_address, (void *)st->start_address);
+
+	st->wx_pages += (addr - st->start_address) / PAGE_SIZE;
+}
+
+static void note_page(struct ptdump_state *pt_st, unsigned long addr,
+		      int level, u64 val)
+{
+	struct pg_state *st = container_of(pt_st, struct pg_state, ptdump);
+	u64 pa = PFN_PHYS(pte_pfn(__pte(val)));
+	u64 prot = 0;
+
+	if (level >= 0)
+		prot = val & pg_level[level].mask;
+
+	if (st->level == -1) {
+		st->level = level;
+		st->current_prot = prot;
+		st->start_address = addr;
+		st->start_pa = pa;
+		st->last_pa = pa;
+		pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+	} else if (prot != st->current_prot ||
+		   level != st->level || addr >= st->marker[1].start_address) {
+		if (st->current_prot) {
+			note_prot_wx(st, addr);
+			dump_addr(st, addr);
+			dump_prot(st);
+			pt_dump_seq_puts(st->seq, "\n");
+		}
+
+		while (addr >= st->marker[1].start_address) {
+			st->marker++;
+			pt_dump_seq_printf(st->seq, "---[ %s ]---\n",
+					   st->marker->name);
+		}
+
+		st->start_address = addr;
+		st->start_pa = pa;
+		st->last_pa = pa;
+		st->current_prot = prot;
+		st->level = level;
+	} else {
+		st->last_pa = pa;
+	}
+}
+
+static void note_page_pte(struct ptdump_state *pt_st, unsigned long addr, pte_t pte)
+{
+	note_page(pt_st, addr, 4, pte_val(pte));
+}
+
+static void note_page_pmd(struct ptdump_state *pt_st, unsigned long addr, pmd_t pmd)
+{
+	note_page(pt_st, addr, 3, pmd_val(pmd));
+}
+
+static void note_page_pud(struct ptdump_state *pt_st, unsigned long addr, pud_t pud)
+{
+	note_page(pt_st, addr, 2, pud_val(pud));
+}
+
+static void note_page_p4d(struct ptdump_state *pt_st, unsigned long addr, p4d_t p4d)
+{
+	note_page(pt_st, addr, 1, p4d_val(p4d));
+}
+
+static void note_page_pgd(struct ptdump_state *pt_st, unsigned long addr, pgd_t pgd)
+{
+	note_page(pt_st, addr, 0, pgd_val(pgd));
+}
+
+static void note_page_flush(struct ptdump_state *pt_st)
+{
+	pte_t pte_zero = {0};
+
+	note_page(pt_st, 0, -1, pte_val(pte_zero));
+}
+
+static void ptdump_walk(struct seq_file *s, struct ptd_mm_info *pinfo)
+{
+	struct pg_state st = {
+		.seq = s,
+		.marker = pinfo->markers,
+		.level = -1,
+		.ptdump = {
+			.note_page_pte = note_page_pte,
+			.note_page_pmd = note_page_pmd,
+			.note_page_pud = note_page_pud,
+			.note_page_p4d = note_page_p4d,
+			.note_page_pgd = note_page_pgd,
+			.note_page_flush = note_page_flush,
+			.range = (struct ptdump_range[]) {
+				{pinfo->base_addr, pinfo->end},
+				{0, 0}
+			}
+		}
+	};
+
+	ptdump_walk_pgd(&st.ptdump, pinfo->mm, NULL);
+}
+
+bool ptdump_check_wx(void)
+{
+	struct pg_state st = {
+		.seq = NULL,
+		.marker = (struct addr_marker[]) {
+			{0, NULL},
+			{-1, NULL},
+		},
+		.level = -1,
+		.check_wx = true,
+		.ptdump = {
+			.note_page_pte = note_page_pte,
+			.note_page_pmd = note_page_pmd,
+			.note_page_pud = note_page_pud,
+			.note_page_p4d = note_page_p4d,
+			.note_page_pgd = note_page_pgd,
+			.note_page_flush = note_page_flush,
+			.range = (struct ptdump_range[]) {
+				{KERN_VIRT_START, ULONG_MAX},
+				{0, 0}
+			}
+		}
+	};
+
+	ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
+
+	if (st.wx_pages) {
+		pr_warn("Checked W+X mappings: failed, %lu W+X pages found\n",
+			st.wx_pages);
+
+		return false;
+	} else {
+		pr_info("Checked W+X mappings: passed, no W+X pages found\n");
+
+		return true;
+	}
+}
+
+static int ptdump_show(struct seq_file *m, void *v)
+{
+	ptdump_walk(m, m->private);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(ptdump);
+
+static int __init ptdump_init(void)
+{
+	unsigned int i, j;
+
+	address_markers[FIXMAP_START_NR].start_address = FIXADDR_START;
+	address_markers[FIXMAP_END_NR].start_address = FIXADDR_TOP;
+	address_markers[PCI_IO_START_NR].start_address = PCI_IO_START;
+	address_markers[PCI_IO_END_NR].start_address = PCI_IO_END;
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	address_markers[VMEMMAP_START_NR].start_address = VMEMMAP_START;
+	address_markers[VMEMMAP_END_NR].start_address = VMEMMAP_END;
+#endif
+	address_markers[VMALLOC_START_NR].start_address = VMALLOC_START;
+	address_markers[VMALLOC_END_NR].start_address = VMALLOC_END;
+	address_markers[PAGE_OFFSET_NR].start_address = PAGE_OFFSET;
+#ifdef CONFIG_KASAN
+	address_markers[KASAN_SHADOW_START_NR].start_address = KASAN_SHADOW_START;
+	address_markers[KASAN_SHADOW_END_NR].start_address = KASAN_SHADOW_END;
+#endif
+#ifdef CONFIG_64BIT
+	address_markers[MODULES_MAPPING_NR].start_address = MODULES_VADDR;
+	address_markers[KERNEL_MAPPING_NR].start_address = kernel_map.virt_addr;
+#endif
+
+	kernel_ptd_info.base_addr = KERN_VIRT_START;
+
+	pg_level[1].name = pgtable_l5_enabled ? "P4D" : "PGD";
+	pg_level[2].name = pgtable_l4_enabled ? "PUD" : "PGD";
+
+	for (i = 0; i < ARRAY_SIZE(pg_level); i++)
+		for (j = 0; j < ARRAY_SIZE(pte_bits); j++)
+			pg_level[i].mask |= pte_bits[j].mask;
+
+	debugfs_create_file("kernel_page_tables", 0400, NULL, &kernel_ptd_info,
+			    &ptdump_fops);
+#ifdef CONFIG_EFI
+	if (efi_enabled(EFI_RUNTIME_SERVICES))
+		debugfs_create_file("efi_page_tables", 0400, NULL, &efi_ptd_info,
+				    &ptdump_fops);
+#endif
+
+	return 0;
+}
+
+device_initcall(ptdump_init);

linux-7.2.3/arch/riscv/mm/tlbflush.c

@@ -0,0 +1,242 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/sched.h>
+#include <linux/hugetlb.h>
+#include <linux/mmu_notifier.h>
+#include <asm/sbi.h>
+#include <asm/mmu_context.h>
+#include <asm/cpufeature.h>
+
+#define has_svinval()	riscv_has_extension_unlikely(RISCV_ISA_EXT_SVINVAL)
+
+static inline void local_sfence_inval_ir(void)
+{
+	asm volatile(SFENCE_INVAL_IR() ::: "memory");
+}
+
+static inline void local_sfence_w_inval(void)
+{
+	asm volatile(SFENCE_W_INVAL() ::: "memory");
+}
+
+static inline void local_sinval_vma(unsigned long vma, unsigned long asid)
+{
+	if (asid != FLUSH_TLB_NO_ASID)
+		asm volatile(SINVAL_VMA(%0, %1) : : "r" (vma), "r" (asid) : "memory");
+	else
+		asm volatile(SINVAL_VMA(%0, zero) : : "r" (vma) : "memory");
+}
+
+/*
+ * Flush entire TLB if number of entries to be flushed is greater
+ * than the threshold below.
+ */
+unsigned long tlb_flush_all_threshold __read_mostly = 64;
+
+static void local_flush_tlb_range_threshold_asid(unsigned long start,
+						 unsigned long size,
+						 unsigned long stride,
+						 unsigned long asid)
+{
+	unsigned long nr_ptes_in_range = DIV_ROUND_UP(size, stride);
+	int i;
+
+	if (nr_ptes_in_range > tlb_flush_all_threshold) {
+		local_flush_tlb_all_asid(asid);
+		return;
+	}
+
+	if (has_svinval()) {
+		local_sfence_w_inval();
+		for (i = 0; i < nr_ptes_in_range; ++i) {
+			local_sinval_vma(start, asid);
+			start += stride;
+		}
+		local_sfence_inval_ir();
+		return;
+	}
+
+	for (i = 0; i < nr_ptes_in_range; ++i) {
+		local_flush_tlb_page_asid(start, asid);
+		start += stride;
+	}
+}
+
+static inline void local_flush_tlb_range_asid(unsigned long start,
+		unsigned long size, unsigned long stride, unsigned long asid)
+{
+	if (size <= stride)
+		local_flush_tlb_page_asid(start, asid);
+	else if (size == FLUSH_TLB_MAX_SIZE)
+		local_flush_tlb_all_asid(asid);
+	else
+		local_flush_tlb_range_threshold_asid(start, size, stride, asid);
+}
+
+/* Flush a range of kernel pages without broadcasting */
+void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	local_flush_tlb_range_asid(start, end - start, PAGE_SIZE, FLUSH_TLB_NO_ASID);
+}
+
+static void __ipi_flush_tlb_all(void *info)
+{
+	local_flush_tlb_all();
+}
+
+void flush_tlb_all(void)
+{
+	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 {
+	unsigned long asid;
+	unsigned long start;
+	unsigned long size;
+	unsigned long stride;
+};
+
+static void __ipi_flush_tlb_range_asid(void *info)
+{
+	struct flush_tlb_range_data *d = info;
+
+	local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid);
+}
+
+static inline unsigned long get_mm_asid(struct mm_struct *mm)
+{
+	return mm ? cntx2asid(atomic_long_read(&mm->context.id)) : FLUSH_TLB_NO_ASID;
+}
+
+static void __flush_tlb_range(struct mm_struct *mm,
+			      const struct cpumask *cmask,
+			      unsigned long start, unsigned long size,
+			      unsigned long stride)
+{
+	unsigned long asid = get_mm_asid(mm);
+	unsigned int cpu;
+
+	if (cpumask_empty(cmask))
+		return;
+
+	cpu = get_cpu();
+
+	/* 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 {
+		struct flush_tlb_range_data ftd;
+
+		ftd.asid = asid;
+		ftd.start = start;
+		ftd.size = size;
+		ftd.stride = stride;
+		on_each_cpu_mask(cmask, __ipi_flush_tlb_range_asid, &ftd, 1);
+	}
+
+	put_cpu();
+
+	if (mm)
+		mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, start + size);
+}
+
+void flush_tlb_mm(struct mm_struct *mm)
+{
+	__flush_tlb_range(mm, mm_cpumask(mm), 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
+}
+
+void flush_tlb_mm_range(struct mm_struct *mm,
+			unsigned long start, unsigned long end,
+			unsigned int page_size)
+{
+	__flush_tlb_range(mm, mm_cpumask(mm), start, end - start, page_size);
+}
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
+{
+	__flush_tlb_range(vma->vm_mm, mm_cpumask(vma->vm_mm),
+			  addr, PAGE_SIZE, PAGE_SIZE);
+}
+
+void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+		     unsigned long end)
+{
+	unsigned long stride_size;
+
+	if (!is_vm_hugetlb_page(vma)) {
+		stride_size = PAGE_SIZE;
+	} else {
+		stride_size = huge_page_size(hstate_vma(vma));
+
+		/*
+		 * As stated in the privileged specification, every PTE in a
+		 * NAPOT region must be invalidated, so reset the stride in that
+		 * case.
+		 */
+		if (has_svnapot()) {
+			if (stride_size >= PGDIR_SIZE)
+				stride_size = PGDIR_SIZE;
+			else if (stride_size >= P4D_SIZE)
+				stride_size = P4D_SIZE;
+			else if (stride_size >= PUD_SIZE)
+				stride_size = PUD_SIZE;
+			else if (stride_size >= PMD_SIZE)
+				stride_size = PMD_SIZE;
+			else
+				stride_size = PAGE_SIZE;
+		}
+	}
+
+	__flush_tlb_range(vma->vm_mm, mm_cpumask(vma->vm_mm),
+			  start, end - start, stride_size);
+}
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	__flush_tlb_range(NULL, cpu_online_mask,
+			  start, end - start, PAGE_SIZE);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
+			unsigned long end)
+{
+	__flush_tlb_range(vma->vm_mm, mm_cpumask(vma->vm_mm),
+			  start, end - start, PMD_SIZE);
+}
+
+void flush_pud_tlb_range(struct vm_area_struct *vma, unsigned long start,
+			 unsigned long end)
+{
+	__flush_tlb_range(vma->vm_mm, mm_cpumask(vma->vm_mm),
+			  start, end - start, PUD_SIZE);
+}
+#endif
+
+bool arch_tlbbatch_should_defer(struct mm_struct *mm)
+{
+	return true;
+}
+
+void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
+		struct mm_struct *mm, unsigned long start, unsigned long end)
+{
+	cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
+	mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end);
+}
+
+void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
+{
+	__flush_tlb_range(NULL, &batch->cpumask,
+			  0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE);
+	cpumask_clear(&batch->cpumask);
+}