Merge tag 'v6.15-rc1' into x86/mm, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

7 files changed, 70 insertions, 44 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 033fba0633cf..a3f35c7d83b6 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -265,8 +265,7 @@ config FUNCTION_GRAPH_RETADDR
 
 config FUNCTION_TRACE_ARGS
        bool
-	depends on HAVE_FUNCTION_ARG_ACCESS_API
-	depends on DEBUG_INFO_BTF
+	depends on PROBE_EVENTS_BTF_ARGS
 	default y
 	help
 	  If supported with function argument access API and BTF, then
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 92015de6203d..1a48aedb5255 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -6855,6 +6855,7 @@ ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer)
 				}
 			}
 		}
+		cond_resched();
 	} while_for_each_ftrace_rec();
 
 	return fail ? -EINVAL : 0;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index d8d7b28e2c2f..c0f877d39a24 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -6016,7 +6016,7 @@ static void rb_update_meta_page(struct ring_buffer_per_cpu *cpu_buffer)
 	meta->read = cpu_buffer->read;
 
 	/* Some archs do not have data cache coherency between kernel and user-space */
-	flush_dcache_folio(virt_to_folio(cpu_buffer->meta_page));
+	flush_kernel_vmap_range(cpu_buffer->meta_page, PAGE_SIZE);
 }
 
 static void
@@ -7319,7 +7319,8 @@ consume:
 
 out:
 	/* Some archs do not have data cache coherency between kernel and user-space */
-	flush_dcache_folio(virt_to_folio(cpu_buffer->reader_page->page));
+	flush_kernel_vmap_range(cpu_buffer->reader_page->page,
+				buffer->subbuf_size + BUF_PAGE_HDR_SIZE);
 
 	rb_update_meta_page(cpu_buffer);
 
diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c
index 50344aa9f7f9..968c5c3b0246 100644
--- a/kernel/trace/rv/rv.c
+++ b/kernel/trace/rv/rv.c
@@ -809,7 +809,8 @@ int rv_register_monitor(struct rv_monitor *monitor, struct rv_monitor *parent)
 	if (p && rv_is_nested_monitor(p)) {
 		pr_info("Parent monitor %s is already nested, cannot nest further\n",
 			parent->name);
-		return -EINVAL;
+		retval = -EINVAL;
+		goto out_unlock;
 	}
 
 	r = kzalloc(sizeof(struct rv_monitor_def), GFP_KERNEL);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 103b193875b3..b581e388a9d9 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -50,6 +50,7 @@
 #include <linux/irq_work.h>
 #include <linux/workqueue.h>
 #include <linux/sort.h>
+#include <linux/io.h> /* vmap_page_range() */
 
 #include <asm/setup.h> /* COMMAND_LINE_SIZE */
 
@@ -3341,10 +3342,9 @@ out_nobuffer:
 }
 EXPORT_SYMBOL_GPL(trace_vbprintk);
 
-__printf(3, 0)
-static int
-__trace_array_vprintk(struct trace_buffer *buffer,
-		      unsigned long ip, const char *fmt, va_list args)
+static __printf(3, 0)
+int __trace_array_vprintk(struct trace_buffer *buffer,
+			  unsigned long ip, const char *fmt, va_list args)
 {
 	struct ring_buffer_event *event;
 	int len = 0, size;
@@ -3394,7 +3394,6 @@ out_nobuffer:
 	return len;
 }
 
-__printf(3, 0)
 int trace_array_vprintk(struct trace_array *tr,
 			unsigned long ip, const char *fmt, va_list args)
 {
@@ -3424,7 +3423,6 @@ int trace_array_vprintk(struct trace_array *tr,
  * Note, trace_array_init_printk() must be called on @tr before this
  * can be used.
  */
-__printf(3, 0)
 int trace_array_printk(struct trace_array *tr,
 		       unsigned long ip, const char *fmt, ...)
 {
@@ -3469,7 +3467,6 @@ int trace_array_init_printk(struct trace_array *tr)
 }
 EXPORT_SYMBOL_GPL(trace_array_init_printk);
 
-__printf(3, 4)
 int trace_array_printk_buf(struct trace_buffer *buffer,
 			   unsigned long ip, const char *fmt, ...)
 {
@@ -3485,7 +3482,6 @@ int trace_array_printk_buf(struct trace_buffer *buffer,
 	return ret;
 }
 
-__printf(2, 0)
 int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 {
 	return trace_array_vprintk(printk_trace, ip, fmt, args);
@@ -8505,6 +8501,10 @@ static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma)
 	struct trace_iterator *iter = &info->iter;
 	int ret = 0;
 
+	/* A memmap'ed buffer is not supported for user space mmap */
+	if (iter->tr->flags & TRACE_ARRAY_FL_MEMMAP)
+		return -ENODEV;
+
 	/* Currently the boot mapped buffer is not supported for mmap */
 	if (iter->tr->flags & TRACE_ARRAY_FL_BOOT)
 		return -ENODEV;
@@ -9609,13 +9609,11 @@ static void free_trace_buffers(struct trace_array *tr)
 		return;
 
 	free_trace_buffer(&tr->array_buffer);
+	kfree(tr->module_delta);
 
 #ifdef CONFIG_TRACER_MAX_TRACE
 	free_trace_buffer(&tr->max_buffer);
 #endif
-
-	if (tr->range_addr_start)
-		vunmap((void *)tr->range_addr_start);
 }
 
 static void init_trace_flags_index(struct trace_array *tr)
@@ -9808,29 +9806,27 @@ static int instance_mkdir(const char *name)
 	return ret;
 }
 
-static u64 map_pages(u64 start, u64 size)
+static u64 map_pages(unsigned long start, unsigned long size)
 {
-	struct page **pages;
-	phys_addr_t page_start;
-	unsigned int page_count;
-	unsigned int i;
-	void *vaddr;
-
-	page_count = DIV_ROUND_UP(size, PAGE_SIZE);
+	unsigned long vmap_start, vmap_end;
+	struct vm_struct *area;
+	int ret;
 
-	page_start = start;
-	pages = kmalloc_array(page_count, sizeof(struct page *), GFP_KERNEL);
-	if (!pages)
+	area = get_vm_area(size, VM_IOREMAP);
+	if (!area)
 		return 0;
 
-	for (i = 0; i < page_count; i++) {
-		phys_addr_t addr = page_start + i * PAGE_SIZE;
-		pages[i] = pfn_to_page(addr >> PAGE_SHIFT);
+	vmap_start = (unsigned long) area->addr;
+	vmap_end = vmap_start + size;
+
+	ret = vmap_page_range(vmap_start, vmap_end,
+			      start, pgprot_nx(PAGE_KERNEL));
+	if (ret < 0) {
+		free_vm_area(area);
+		return 0;
 	}
-	vaddr = vmap(pages, page_count, VM_MAP, PAGE_KERNEL);
-	kfree(pages);
 
-	return (u64)(unsigned long)vaddr;
+	return (u64)vmap_start;
 }
 
 /**
@@ -10709,6 +10705,7 @@ static inline void do_allocate_snapshot(const char *name) { }
 __init static void enable_instances(void)
 {
 	struct trace_array *tr;
+	bool memmap_area = false;
 	char *curr_str;
 	char *name;
 	char *str;
@@ -10777,6 +10774,7 @@ __init static void enable_instances(void)
 					name);
 				continue;
 			}
+			memmap_area = true;
 		} else if (tok) {
 			if (!reserve_mem_find_by_name(tok, &start, &size)) {
 				start = 0;
@@ -10787,7 +10785,20 @@ __init static void enable_instances(void)
 		}
 
 		if (start) {
-			addr = map_pages(start, size);
+			/* Start and size must be page aligned */
+			if (start & ~PAGE_MASK) {
+				pr_warn("Tracing: mapping start addr %pa is not page aligned\n", &start);
+				continue;
+			}
+			if (size & ~PAGE_MASK) {
+				pr_warn("Tracing: mapping size %pa is not page aligned\n", &size);
+				continue;
+			}
+
+			if (memmap_area)
+				addr = map_pages(start, size);
+			else
+				addr = (unsigned long)phys_to_virt(start);
 			if (addr) {
 				pr_info("Tracing: mapped boot instance %s at physical memory %pa of size 0x%lx\n",
 					name, &start, (unsigned long)size);
@@ -10814,10 +10825,13 @@ __init static void enable_instances(void)
 			update_printk_trace(tr);
 
 		/*
-		 * If start is set, then this is a mapped buffer, and
-		 * cannot be deleted by user space, so keep the reference
-		 * to it.
+		 * memmap'd buffers can not be freed.
 		 */
+		if (memmap_area) {
+			tr->flags |= TRACE_ARRAY_FL_MEMMAP;
+			tr->ref++;
+		}
+
 		if (start) {
 			tr->flags |= TRACE_ARRAY_FL_BOOT | TRACE_ARRAY_FL_LAST_BOOT;
 			tr->range_name = no_free_ptr(rname);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index c20f6bcc200a..79be1995db44 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -447,6 +447,7 @@ enum {
 	TRACE_ARRAY_FL_BOOT		= BIT(1),
 	TRACE_ARRAY_FL_LAST_BOOT	= BIT(2),
 	TRACE_ARRAY_FL_MOD_INIT		= BIT(3),
+	TRACE_ARRAY_FL_MEMMAP		= BIT(4),
 };
 
 #ifdef CONFIG_MODULES
@@ -852,13 +853,15 @@ static inline void __init disable_tracing_selftest(const char *reason)
 
 extern void *head_page(struct trace_array_cpu *data);
 extern unsigned long long ns2usecs(u64 nsec);
-extern int
-trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
-extern int
-trace_vprintk(unsigned long ip, const char *fmt, va_list args);
-extern int
-trace_array_vprintk(struct trace_array *tr,
-		    unsigned long ip, const char *fmt, va_list args);
+
+__printf(2, 0)
+int trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
+__printf(2, 0)
+int trace_vprintk(unsigned long ip, const char *fmt, va_list args);
+__printf(3, 0)
+int trace_array_vprintk(struct trace_array *tr,
+			unsigned long ip, const char *fmt, va_list args);
+__printf(3, 4)
 int trace_array_printk_buf(struct trace_buffer *buffer,
 			   unsigned long ip, const char *fmt, ...);
 void trace_printk_seq(struct trace_seq *s);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 8638b7f7ff85..069e92856bda 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -470,6 +470,7 @@ static void test_event_printk(struct trace_event_call *call)
 			case '%':
 				continue;
 			case 'p':
+ do_pointer:
 				/* Find dereferencing fields */
 				switch (fmt[i + 1]) {
 				case 'B': case 'R': case 'r':
@@ -498,6 +499,12 @@ static void test_event_printk(struct trace_event_call *call)
 						continue;
 					if (fmt[i + j] == '*') {
 						star = true;
+						/* Handle %*pbl case */
+						if (!j && fmt[i + 1] == 'p') {
+							arg++;
+							i++;
+							goto do_pointer;
+						}
 						continue;
 					}
 					if ((fmt[i + j] == 's')) {