[RFC PATCH 2/4] mm: Add a debug interface to control the range of speculative numa fault

[Baolin Wang]

Add a debug interface to control the range of speculative numa fault,
which can be used to tuning the performance or event close the speculative
numa fault window for some workloads.

Signed-off-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
---
 mm/memory.c | 46 +++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 43 insertions(+), 3 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 2c9ed63e4e23..a0f4a2a008cc 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4052,7 +4052,29 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 static unsigned long fault_around_bytes __read_mostly =
 	rounddown_pow_of_two(65536);
 
+static unsigned long numa_around_bytes __read_mostly;
+
 #ifdef CONFIG_DEBUG_FS
+static int numa_around_bytes_get(void *data, u64 *val)
+{
+	*val = numa_around_bytes;
+	return 0;
+}
+
+static int numa_around_bytes_set(void *data, u64 val)
+{
+	if (val / PAGE_SIZE > PTRS_PER_PTE)
+		return -EINVAL;
+	if (val > PAGE_SIZE)
+		numa_around_bytes = rounddown_pow_of_two(val);
+	else
+		numa_around_bytes = 0; /* rounddown_pow_of_two(0) is undefined */
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(numa_around_bytes_fops,
+			 numa_around_bytes_get,
+			 numa_around_bytes_set, "%llu\n");
+
 static int fault_around_bytes_get(void *data, u64 *val)
 {
 	*val = fault_around_bytes;
@@ -4080,6 +4102,8 @@ static int __init fault_around_debugfs(void)
 {
 	debugfs_create_file_unsafe("fault_around_bytes", 0644, NULL, NULL,
 				   &fault_around_bytes_fops);
+	debugfs_create_file_unsafe("numa_around_bytes", 0644, NULL, NULL,
+				   &numa_around_bytes_fops);
 	return 0;
 }
 late_initcall(fault_around_debugfs);
@@ -4348,10 +4372,13 @@ static bool try_next_numa_page(struct vm_fault *vmf, unsigned int win_pages,
 	((win) & NUMA_FAULT_WINDOW_SIZE_MASK))
 
 static inline unsigned int numa_fault_max_pages(struct vm_area_struct *vma,
-						unsigned long fault_address)
+						unsigned long fault_address,
+						unsigned long numa_around_size)
 {
+	unsigned long numa_around_addr =
+		(fault_address + numa_around_size) & PAGE_MASK;
 	unsigned long pmd_end_addr = (fault_address & PMD_MASK) + PMD_SIZE;
-	unsigned long max_fault_addr = min_t(unsigned long, pmd_end_addr,
+	unsigned long max_fault_addr = min3(numa_around_addr, pmd_end_addr,
 					    vma->vm_end);
 
 	return (max_fault_addr - fault_address - 1) >> PAGE_SHIFT;
@@ -4360,12 +4387,24 @@ static inline unsigned int numa_fault_max_pages(struct vm_area_struct *vma,
 static unsigned int adjust_numa_fault_window(struct vm_area_struct *vma,
 					     unsigned long fault_address)
 {
+	unsigned long numa_around_size = READ_ONCE(numa_around_bytes);
 	unsigned long numafault_ahead = GET_NUMA_FAULT_INFO(vma);
         unsigned long prev_start = NUMA_FAULT_WINDOW_START(numafault_ahead);
         unsigned int prev_pages = NUMA_FAULT_WINDOW_SIZE(numafault_ahead);
 	unsigned long win_start;
 	unsigned int win_pages, max_fault_pages;
 
+	/*
+	 * Shut down the proactive numa fault if the numa_around_bytes
+	 * is set to 0.
+	 */
+	if (!numa_around_size) {
+		if (numafault_ahead)
+			atomic_long_set(&vma->numafault_ahead_info,
+					NUMA_FAULT_INFO(0, 0));
+		return 0;
+	}
+
 	win_start = fault_address + PAGE_SIZE;
 
 	/*
@@ -4437,7 +4476,8 @@ static unsigned int adjust_numa_fault_window(struct vm_area_struct *vma,
 	 * Make sure the size of ahead numa fault address is less than the
 	 * size of current VMA or PMD.
 	 */
-	max_fault_pages = numa_fault_max_pages(vma, fault_address);
+	max_fault_pages = numa_fault_max_pages(vma, fault_address,
+					       numa_around_size);
 	if (win_pages > max_fault_pages)
 		win_pages = max_fault_pages;
 
-- 
2.27.0