Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 338 insertions, 0 deletions

diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
new file mode 100644
index 000000000..55c20ad1f
--- /dev/null
+++ b/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);
+}