[PATCH v2 0/3] ring-buffer: Fix and unify size and page calculations

[PATCH v2 0/3] ring-buffer: Fix and unify size and page calculations

[Vincent Donnefort]

This short series unifies minimum page calculation for ring buffers and
fix a small issue with the number of pages calculation for trace
remotes.

v2:
  - Add a helper in "Account for ring buffer page header in size
    calculation" (Steven)
  - Split the nr_pages overflow handling into its own patch (Steven)
  - Rename the helpers into __calc_nr_pages_ring_buffer_desc() and
    rb_calculate_nr_pages() (Steven)
  - Use RING_BUFFER_MIN_NR_PAGES in trace_rb_cpu_prepare() (Sashiko)

v1: https://lore.kernel.org/all/20260907192643.42513-1-vdonnefort@google.com

Vincent Donnefort (3):
  tracing/remotes: Account for ring buffer page header in size
    calculation
  tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing
  ring-buffer: Unify ring buffer minimum page calculations

 include/linux/ring_buffer.h       | 26 +++++++++++++++++++++++--
 kernel/trace/ring_buffer.c        | 32 +++++++++++++------------------
 kernel/trace/simple_ring_buffer.c |  4 ++--
 kernel/trace/trace_remote.c       |  6 +++++-
 4 files changed, 44 insertions(+), 24 deletions(-)


base-commit: df2908090cda368b01ff43709f51890076c56157
-- 
2.55.0.1007.g17ff1f9808-goog

[PATCH v2 1/3] tracing/remotes: Account for ring buffer page header in size calculation

[Vincent Donnefort]

trace_buffer_desc_size() and trace_remote_alloc_buffer undercount the
required pages because every ring buffer page contains a header
(BUF_PAGE_HDR_SIZE). Account for that header to ensure allocated remote
ring buffers aren't smaller than requested by the user.

The newly introduced helper __calc_nr_pages_ring_buffer_desc() can
return a value that overflows the descriptor nr_pages field (32 bits).

Fixes: 2e67fabd8b77 ("ring-buffer: Introduce ring-buffer remotes")
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
---
 include/linux/ring_buffer.h | 15 +++++++++++++--
 kernel/trace/trace_remote.c |  2 +-
 2 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index afc7daa6ee7d..11bffb6a142d 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -3,8 +3,9 @@
 #define _LINUX_RING_BUFFER_H
 
 #include <linux/mm.h>
-#include <linux/seq_file.h>
 #include <linux/poll.h>
+#include <linux/ring_buffer_types.h>
+#include <linux/seq_file.h>
 
 #include <uapi/linux/trace_mmap.h>
 
@@ -279,9 +280,19 @@ static inline struct ring_buffer_desc *__first_ring_buffer_desc(struct trace_buf
 	return (struct ring_buffer_desc *)(&desc->__data[0]);
 }
 
+/*
+ * Returns the number of pages for a ring_buffer_desc. The caller must ensure it
+ * does not overflow ring_buffer_desc::nr_page_va.
+ */
+static inline unsigned long __calc_nr_pages_ring_buffer_desc(size_t size)
+{
+	/* Takes into account the reader page */
+	return max(DIV_ROUND_UP(size, PAGE_SIZE - BUF_PAGE_HDR_SIZE), 2UL) + 1;
+}
+
 static inline size_t trace_buffer_desc_size(size_t buffer_size, unsigned int nr_cpus)
 {
-	unsigned int nr_pages = max(DIV_ROUND_UP(buffer_size, PAGE_SIZE), 2UL) + 1;
+	unsigned long nr_pages = __calc_nr_pages_ring_buffer_desc(buffer_size);
 	struct ring_buffer_desc *rbdesc;
 
 	return size_add(offsetof(struct trace_buffer_desc, __data),
diff --git a/kernel/trace/trace_remote.c b/kernel/trace/trace_remote.c
index 75fa1ffc4c96..c17902e42ef1 100644
--- a/kernel/trace/trace_remote.c
+++ b/kernel/trace/trace_remote.c
@@ -980,7 +980,7 @@ int trace_remote_alloc_buffer(struct trace_buffer_desc *desc, size_t desc_size,
 			      const struct cpumask *cpumask)
 {
 	size_t min_desc_size = trace_buffer_desc_size(buffer_size, cpumask_weight(cpumask));
-	unsigned int nr_pages = max(DIV_ROUND_UP(buffer_size, PAGE_SIZE), 2UL) + 1;
+	unsigned int nr_pages = __calc_nr_pages_ring_buffer_desc(buffer_size);
 	struct ring_buffer_desc *rb_desc;
 	int cpu, ret = -ENOMEM;
 
-- 
2.55.0.1007.g17ff1f9808-goog

[PATCH v2 2/3] tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing

[Vincent Donnefort]

The number of pages per remote ring buffer is capped by
ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to
overflow that field would silently allocate a descriptor smaller than
what was asked for.

Return SIZE_MAX from trace_buffer_desc_size() on nr_page_va overflow.

Fixes: 2e67fabd8b77 ("ring-buffer: Introduce ring-buffer remotes")
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
---
 include/linux/ring_buffer.h | 4 ++++
 kernel/trace/trace_remote.c | 6 +++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 11bffb6a142d..eac3e9080c3c 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -295,6 +295,10 @@ static inline size_t trace_buffer_desc_size(size_t buffer_size, unsigned int nr_
 	unsigned long nr_pages = __calc_nr_pages_ring_buffer_desc(buffer_size);
 	struct ring_buffer_desc *rbdesc;
 
+	/* Capped by ring_buffer_desc::nr_page_va */
+	if (nr_pages > UINT_MAX)
+		return SIZE_MAX;
+
 	return size_add(offsetof(struct trace_buffer_desc, __data),
 			size_mul(nr_cpus, struct_size(rbdesc, page_va, nr_pages)));
 }
diff --git a/kernel/trace/trace_remote.c b/kernel/trace/trace_remote.c
index c17902e42ef1..2d5bc423efca 100644
--- a/kernel/trace/trace_remote.c
+++ b/kernel/trace/trace_remote.c
@@ -980,9 +980,12 @@ int trace_remote_alloc_buffer(struct trace_buffer_desc *desc, size_t desc_size,
 			      const struct cpumask *cpumask)
 {
 	size_t min_desc_size = trace_buffer_desc_size(buffer_size, cpumask_weight(cpumask));
-	unsigned int nr_pages = __calc_nr_pages_ring_buffer_desc(buffer_size);
 	struct ring_buffer_desc *rb_desc;
 	int cpu, ret = -ENOMEM;
+	unsigned int nr_pages;
+
+	if (min_desc_size == SIZE_MAX)
+		return -E2BIG;
 
 	if (desc_size < min_desc_size)
 		return -EINVAL;
@@ -991,6 +994,7 @@ int trace_remote_alloc_buffer(struct trace_buffer_desc *desc, size_t desc_size,
 	desc->struct_len = min_desc_size;
 
 	rb_desc = __first_ring_buffer_desc(desc);
+	nr_pages = __calc_nr_pages_ring_buffer_desc(buffer_size);
 
 	for_each_cpu(cpu, cpumask) {
 		unsigned int id;
-- 
2.55.0.1007.g17ff1f9808-goog

[PATCH v2 3/3] ring-buffer: Unify ring buffer minimum page calculations

[Vincent Donnefort]

The codebase scatters hardcoded minimum page limits across multiple
places. Introduce RING_BUFFER_MIN_NR_PAGES and rb_calculate_nr_pages()
to formalize the requirement of two pages in a ring buffer.

Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
---
 include/linux/ring_buffer.h       |  9 ++++++++-
 kernel/trace/ring_buffer.c        | 32 +++++++++++++------------------
 kernel/trace/simple_ring_buffer.c |  4 ++--
 3 files changed, 23 insertions(+), 22 deletions(-)

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index eac3e9080c3c..e4370064273e 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -98,6 +98,13 @@ struct trace_buffer *__ring_buffer_alloc_range(unsigned long size, unsigned flag
 
 void *ring_buffer_meta_scratch(struct trace_buffer *buffer, unsigned int *size);
 
+/*
+ * A minimum of 2 pages ensures we can always swap a page out of the ring
+ * buffer. This does not account for the reader page or any other page
+ * containing meta data used by static ring buffers.
+ */
+#define RING_BUFFER_MIN_NR_PAGES 2UL
+
 /*
  * Because the ring buffer is generic, if other users of the ring buffer get
  * traced by ftrace, it can produce lockdep warnings. We need to keep each
@@ -287,7 +294,7 @@ static inline struct ring_buffer_desc *__first_ring_buffer_desc(struct trace_buf
 static inline unsigned long __calc_nr_pages_ring_buffer_desc(size_t size)
 {
 	/* Takes into account the reader page */
-	return max(DIV_ROUND_UP(size, PAGE_SIZE - BUF_PAGE_HDR_SIZE), 2UL) + 1;
+	return max(DIV_ROUND_UP(size, PAGE_SIZE - BUF_PAGE_HDR_SIZE), RING_BUFFER_MIN_NR_PAGES) + 1;
 }
 
 static inline size_t trace_buffer_desc_size(size_t buffer_size, unsigned int nr_cpus)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 9c03a555a6ba..7137781ab0b8 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -642,6 +642,11 @@ static __always_inline unsigned int rb_subbuf_max_data_size(struct trace_buffer
 	return rb_subbuf_capacity(buffer) - RB_EVNT_HDR_SIZE - sizeof(event->array[0]);
 }
 
+static unsigned long rb_calculate_nr_pages(struct trace_buffer *buffer, unsigned long size)
+{
+	return max(DIV_ROUND_UP(size, rb_subbuf_capacity(buffer)), RING_BUFFER_MIN_NR_PAGES);
+}
+
 /**
  * rb_subbuf_start - Get the start address of a subbuffer
  * @buffer:	A trace buffer
@@ -2865,7 +2870,7 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags,
 			goto fail_free_buffers;
 
 		/* Need at least two pages plus the reader page */
-		if (nr_pages < 3)
+		if (nr_pages < RING_BUFFER_MIN_NR_PAGES + 1)
 			goto fail_free_buffers;
 
  again:
@@ -2877,7 +2882,7 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags,
 			ptr += subbuf_size * nr_pages;
 		}
 		if (ptr > end) {
-			if (nr_pages <= 3)
+			if (nr_pages <= RING_BUFFER_MIN_NR_PAGES + 1)
 				goto fail_free_buffers;
 			nr_pages--;
 			goto again;
@@ -2900,13 +2905,10 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags,
 		if (nr_pages > rb_static_max_pages())
 			goto fail_free_buffers;
 
-		if (nr_pages < 2)
+		if (nr_pages < RING_BUFFER_MIN_NR_PAGES)
 			goto fail_free_buffers;
 	} else {
-		/* need at least two pages */
-		nr_pages = DIV_ROUND_UP(size, rb_subbuf_capacity(buffer));
-		if (nr_pages < 2)
-			nr_pages = 2;
+		nr_pages = rb_calculate_nr_pages(buffer, size);
 	}
 
 	cpumask_set_cpu(cpu, buffer->cpumask);
@@ -3319,11 +3321,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size,
 	mutex_lock(&buffer->mutex);
 	atomic_inc(&buffer->resizing);
 
-	nr_pages = DIV_ROUND_UP(size, rb_subbuf_capacity(buffer));
-
-	/* we need a minimum of two pages */
-	if (nr_pages < 2)
-		nr_pages = 2;
+	nr_pages = rb_calculate_nr_pages(buffer, size);
 
 	if (cpu_id == RING_BUFFER_ALL_CPUS) {
 		/*
@@ -7495,12 +7493,8 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order)
 		}
 
 		/* Update the number of pages to match the new size */
-		nr_pages = old_capacity * buffer->buffers[cpu]->nr_pages;
-		nr_pages = DIV_ROUND_UP(nr_pages, rb_subbuf_capacity(buffer));
-
-		/* we need a minimum of two pages */
-		if (nr_pages < 2)
-			nr_pages = 2;
+		nr_pages = rb_calculate_nr_pages(buffer,
+						 old_capacity * buffer->buffers[cpu]->nr_pages);
 
 		cpu_buffer->nr_pages_to_update = nr_pages;
 
@@ -8095,7 +8089,7 @@ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node)
 	}
 	/* allocate minimum pages, user can later expand it */
 	if (!nr_pages_same)
-		nr_pages = 2;
+		nr_pages = RING_BUFFER_MIN_NR_PAGES;
 	buffer->buffers[cpu] =
 		rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
 	if (!buffer->buffers[cpu]) {
diff --git a/kernel/trace/simple_ring_buffer.c b/kernel/trace/simple_ring_buffer.c
index 49913bb0057a..abfaf9bee12e 100644
--- a/kernel/trace/simple_ring_buffer.c
+++ b/kernel/trace/simple_ring_buffer.c
@@ -383,8 +383,8 @@ int simple_ring_buffer_init_mm(struct simple_rb_per_cpu *cpu_buffer,
 	void *page;
 	int i;
 
-	/* At least 1 reader page and two pages in the ring-buffer */
-	if (desc->nr_page_va < 3)
+	/* At least RING_BUFFER_MIN_NR_PAGES and 1 reader page */
+	if (desc->nr_page_va < RING_BUFFER_MIN_NR_PAGES + 1)
 		return -EINVAL;
 
 	memset(cpu_buffer, 0, sizeof(*cpu_buffer));
-- 
2.55.0.1007.g17ff1f9808-goog