Merge tag 'riscv-for-linus-5.2-mw2' of git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux

Pull RISC-V updates from Palmer Dabbelt:
 "This contains an assortment of RISC-V related patches that I'd like to
  target for the 5.2 merge window. Most of the patches are cleanups, but
  there are a handful of user-visible changes:

   - The nosmp and nr_cpus command-line arguments are now supported,
     which work like normal.

   - The SBI console no longer installs itself as a preferred console,
     we rely on standard mechanisms (/chosen, command-line, hueristics)
     instead.

   - sfence_remove_sfence_vma{,_asid} now pass their arguments along to
     the SBI call.

   - Modules now support BUG().

   - A missing sfence.vma during boot has been added. This bug only
     manifests during boot.

   - The arch/riscv support for SiFive's L2 cache controller has been
     merged, which should un-block the EDAC framework work.

  I've only tested this on QEMU again, as I didn't have time to get
  things running on the Unleashed. The latest master from this morning
  merges in cleanly and passes the tests as well"

* tag 'riscv-for-linus-5.2-mw2' of git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux: (31 commits)
  riscv: fix locking violation in page fault handler
  RISC-V: sifive_l2_cache: Add L2 cache controller driver for SiFive SoCs
  RISC-V: Add DT documentation for SiFive L2 Cache Controller
  RISC-V: Avoid using invalid intermediate translations
  riscv: Support BUG() in kernel module
  riscv: Add the support for c.ebreak check in is_valid_bugaddr()
  riscv: support trap-based WARN()
  riscv: fix sbi_remote_sfence_vma{,_asid}.
  riscv: move switch_mm to its own file
  riscv: move flush_icache_{all,mm} to cacheflush.c
  tty: Don't force RISCV SBI console as preferred console
  RISC-V: Access CSRs using CSR numbers
  RISC-V: Add interrupt related SCAUSE defines in asm/csr.h
  RISC-V: Use tabs to align macro values in asm/csr.h
  RISC-V: Fix minor checkpatch issues.
  RISC-V: Support nr_cpus command line option.
  RISC-V: Implement nosmp commandline option.
  RISC-V: Add RISC-V specific arch_match_cpu_phys_id
  riscv: vdso: drop unnecessary cc-ldoption
  riscv: call pm_power_off from machine_halt / machine_power_off
  ...

5 files changed, 310 insertions, 6 deletions

diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
index b68aac701803..8db569141485 100644
--- a/arch/riscv/mm/Makefile
+++ b/arch/riscv/mm/Makefile
@@ -9,3 +9,5 @@ obj-y += fault.o
 obj-y += extable.o
 obj-y += ioremap.o
 obj-y += cacheflush.o
+obj-y += context.o
+obj-y += sifive_l2_cache.o
diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
index 498c0a0814fe..497b7d07af0c 100644
--- a/arch/riscv/mm/cacheflush.c
+++ b/arch/riscv/mm/cacheflush.c
@@ -14,6 +14,67 @@
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
 
+#ifdef CONFIG_SMP
+
+#include <asm/sbi.h>
+
+void flush_icache_all(void)
+{
+	sbi_remote_fence_i(NULL);
+}
+
+/*
+ * 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, hmask, *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) {
+		cpumask_clear(&hmask);
+		riscv_cpuid_to_hartid_mask(&others, &hmask);
+		sbi_remote_fence_i(hmask.bits);
+	} else {
+		/*
+		 * 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();
+	}
+
+	preempt_enable();
+}
+
+#endif /* CONFIG_SMP */
+
 void flush_icache_pte(pte_t pte)
 {
 	struct page *page = pte_page(pte);
diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
new file mode 100644
index 000000000000..89ceb3cbe218
--- /dev/null
+++ b/arch/riscv/mm/context.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2012 Regents of the University of California
+ * Copyright (C) 2017 SiFive
+ */
+
+#include <linux/mm.h>
+#include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
+
+/*
+ * 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.
+ */
+static inline void flush_icache_deferred(struct mm_struct *mm)
+{
+#ifdef CONFIG_SMP
+	unsigned int cpu = smp_processor_id();
+	cpumask_t *mask = &mm->context.icache_stale_mask;
+
+	if (cpumask_test_cpu(cpu, mask)) {
+		cpumask_clear_cpu(cpu, mask);
+		/*
+		 * Ensure the remote hart's writes are visible to this hart.
+		 * This pairs with a barrier in flush_icache_mm.
+		 */
+		smp_mb();
+		local_flush_icache_all();
+	}
+
+#endif
+}
+
+void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+	struct task_struct *task)
+{
+	unsigned int cpu;
+
+	if (unlikely(prev == next))
+		return;
+
+	/*
+	 * 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();
+
+	cpumask_clear_cpu(cpu, mm_cpumask(prev));
+	cpumask_set_cpu(cpu, mm_cpumask(next));
+
+	/*
+	 * Use the old spbtr name instead of using the current satp
+	 * name to support binutils 2.29 which doesn't know about the
+	 * privileged ISA 1.10 yet.
+	 */
+	csr_write(sptbr, virt_to_pfn(next->pgd) | SATP_MODE);
+	local_flush_tlb_all();
+
+	flush_icache_deferred(next);
+}
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 88401d5125bc..cec8be9e2d6a 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -229,8 +229,9 @@ vmalloc_fault:
 		pte_t *pte_k;
 		int index;
 
+		/* User mode accesses just cause a SIGSEGV */
 		if (user_mode(regs))
-			goto bad_area;
+			return do_trap(regs, SIGSEGV, code, addr, tsk);
 
 		/*
 		 * Synchronize this task's top level page-table
@@ -239,13 +240,9 @@ vmalloc_fault:
 		 * Do _not_ use "tsk->active_mm->pgd" here.
 		 * We might be inside an interrupt in the middle
 		 * of a task switch.
-		 *
-		 * Note: Use the old spbtr name instead of using the current
-		 * satp name to support binutils 2.29 which doesn't know about
-		 * the privileged ISA 1.10 yet.
 		 */
 		index = pgd_index(addr);
-		pgd = (pgd_t *)pfn_to_virt(csr_read(sptbr)) + index;
+		pgd = (pgd_t *)pfn_to_virt(csr_read(CSR_SATP)) + index;
 		pgd_k = init_mm.pgd + index;
 
 		if (!pgd_present(*pgd_k))
diff --git a/arch/riscv/mm/sifive_l2_cache.c b/arch/riscv/mm/sifive_l2_cache.c
new file mode 100644
index 000000000000..4eb64619b3f4
--- /dev/null
+++ b/arch/riscv/mm/sifive_l2_cache.c
@@ -0,0 +1,175 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * SiFive L2 cache controller Driver
+ *
+ * Copyright (C) 2018-2019 SiFive, Inc.
+ *
+ */
+#include <linux/debugfs.h>
+#include <linux/interrupt.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+#include <asm/sifive_l2_cache.h>
+
+#define SIFIVE_L2_DIRECCFIX_LOW 0x100
+#define SIFIVE_L2_DIRECCFIX_HIGH 0x104
+#define SIFIVE_L2_DIRECCFIX_COUNT 0x108
+
+#define SIFIVE_L2_DATECCFIX_LOW 0x140
+#define SIFIVE_L2_DATECCFIX_HIGH 0x144
+#define SIFIVE_L2_DATECCFIX_COUNT 0x148
+
+#define SIFIVE_L2_DATECCFAIL_LOW 0x160
+#define SIFIVE_L2_DATECCFAIL_HIGH 0x164
+#define SIFIVE_L2_DATECCFAIL_COUNT 0x168
+
+#define SIFIVE_L2_CONFIG 0x00
+#define SIFIVE_L2_WAYENABLE 0x08
+#define SIFIVE_L2_ECCINJECTERR 0x40
+
+#define SIFIVE_L2_MAX_ECCINTR 3
+
+static void __iomem *l2_base;
+static int g_irq[SIFIVE_L2_MAX_ECCINTR];
+
+enum {
+	DIR_CORR = 0,
+	DATA_CORR,
+	DATA_UNCORR,
+};
+
+#ifdef CONFIG_DEBUG_FS
+static struct dentry *sifive_test;
+
+static ssize_t l2_write(struct file *file, const char __user *data,
+			size_t count, loff_t *ppos)
+{
+	unsigned int val;
+
+	if (kstrtouint_from_user(data, count, 0, &val))
+		return -EINVAL;
+	if ((val >= 0 && val < 0xFF) || (val >= 0x10000 && val < 0x100FF))
+		writel(val, l2_base + SIFIVE_L2_ECCINJECTERR);
+	else
+		return -EINVAL;
+	return count;
+}
+
+static const struct file_operations l2_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.write = l2_write
+};
+
+static void setup_sifive_debug(void)
+{
+	sifive_test = debugfs_create_dir("sifive_l2_cache", NULL);
+
+	debugfs_create_file("sifive_debug_inject_error", 0200,
+			    sifive_test, NULL, &l2_fops);
+}
+#endif
+
+static void l2_config_read(void)
+{
+	u32 regval, val;
+
+	regval = readl(l2_base + SIFIVE_L2_CONFIG);
+	val = regval & 0xFF;
+	pr_info("L2CACHE: No. of Banks in the cache: %d\n", val);
+	val = (regval & 0xFF00) >> 8;
+	pr_info("L2CACHE: No. of ways per bank: %d\n", val);
+	val = (regval & 0xFF0000) >> 16;
+	pr_info("L2CACHE: Sets per bank: %llu\n", (uint64_t)1 << val);
+	val = (regval & 0xFF000000) >> 24;
+	pr_info("L2CACHE: Bytes per cache block: %llu\n", (uint64_t)1 << val);
+
+	regval = readl(l2_base + SIFIVE_L2_WAYENABLE);
+	pr_info("L2CACHE: Index of the largest way enabled: %d\n", regval);
+}
+
+static const struct of_device_id sifive_l2_ids[] = {
+	{ .compatible = "sifive,fu540-c000-ccache" },
+	{ /* end of table */ },
+};
+
+static ATOMIC_NOTIFIER_HEAD(l2_err_chain);
+
+int register_sifive_l2_error_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_register(&l2_err_chain, nb);
+}
+EXPORT_SYMBOL_GPL(register_sifive_l2_error_notifier);
+
+int unregister_sifive_l2_error_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_unregister(&l2_err_chain, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_sifive_l2_error_notifier);
+
+static irqreturn_t l2_int_handler(int irq, void *device)
+{
+	unsigned int regval, add_h, add_l;
+
+	if (irq == g_irq[DIR_CORR]) {
+		add_h = readl(l2_base + SIFIVE_L2_DIRECCFIX_HIGH);
+		add_l = readl(l2_base + SIFIVE_L2_DIRECCFIX_LOW);
+		pr_err("L2CACHE: DirError @ 0x%08X.%08X\n", add_h, add_l);
+		regval = readl(l2_base + SIFIVE_L2_DIRECCFIX_COUNT);
+		atomic_notifier_call_chain(&l2_err_chain, SIFIVE_L2_ERR_TYPE_CE,
+					   "DirECCFix");
+	}
+	if (irq == g_irq[DATA_CORR]) {
+		add_h = readl(l2_base + SIFIVE_L2_DATECCFIX_HIGH);
+		add_l = readl(l2_base + SIFIVE_L2_DATECCFIX_LOW);
+		pr_err("L2CACHE: DataError @ 0x%08X.%08X\n", add_h, add_l);
+		regval = readl(l2_base + SIFIVE_L2_DATECCFIX_COUNT);
+		atomic_notifier_call_chain(&l2_err_chain, SIFIVE_L2_ERR_TYPE_CE,
+					   "DatECCFix");
+	}
+	if (irq == g_irq[DATA_UNCORR]) {
+		add_h = readl(l2_base + SIFIVE_L2_DATECCFAIL_HIGH);
+		add_l = readl(l2_base + SIFIVE_L2_DATECCFAIL_LOW);
+		pr_err("L2CACHE: DataFail @ 0x%08X.%08X\n", add_h, add_l);
+		regval = readl(l2_base + SIFIVE_L2_DATECCFAIL_COUNT);
+		atomic_notifier_call_chain(&l2_err_chain, SIFIVE_L2_ERR_TYPE_UE,
+					   "DatECCFail");
+	}
+
+	return IRQ_HANDLED;
+}
+
+int __init sifive_l2_init(void)
+{
+	struct device_node *np;
+	struct resource res;
+	int i, rc;
+
+	np = of_find_matching_node(NULL, sifive_l2_ids);
+	if (!np)
+		return -ENODEV;
+
+	if (of_address_to_resource(np, 0, &res))
+		return -ENODEV;
+
+	l2_base = ioremap(res.start, resource_size(&res));
+	if (!l2_base)
+		return -ENOMEM;
+
+	for (i = 0; i < SIFIVE_L2_MAX_ECCINTR; i++) {
+		g_irq[i] = irq_of_parse_and_map(np, i);
+		rc = request_irq(g_irq[i], l2_int_handler, 0, "l2_ecc", NULL);
+		if (rc) {
+			pr_err("L2CACHE: Could not request IRQ %d\n", g_irq[i]);
+			return rc;
+		}
+	}
+
+	l2_config_read();
+
+#ifdef CONFIG_DEBUG_FS
+	setup_sifive_debug();
+#endif
+	return 0;
+}
+device_initcall(sifive_l2_init);