1 files changed, 140 insertions, 1 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index dc568ca295bd..d2f3ca792936 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -51,6 +51,7 @@
 #include <linux/proc_ns.h>
 #include <linux/mount.h>
 #include <linux/min_heap.h>
+#include <linux/highmem.h>
 
 #include "internal.h"
 
@@ -1895,6 +1896,12 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 	if (sample_type & PERF_SAMPLE_CGROUP)
 		size += sizeof(data->cgroup);
 
+	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
+		size += sizeof(data->data_page_size);
+
+	if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)
+		size += sizeof(data->code_page_size);
+
 	event->header_size = size;
 }
 
@@ -6931,6 +6938,12 @@ void perf_output_sample(struct perf_output_handle *handle,
 	if (sample_type & PERF_SAMPLE_CGROUP)
 		perf_output_put(handle, data->cgroup);
 
+	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
+		perf_output_put(handle, data->data_page_size);
+
+	if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)
+		perf_output_put(handle, data->code_page_size);
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		perf_output_put(handle, data->aux_size);
 
@@ -6988,6 +7001,121 @@ static u64 perf_virt_to_phys(u64 virt)
 	return phys_addr;
 }
 
+#ifdef CONFIG_MMU
+
+/*
+ * Return the MMU page size of a given virtual address.
+ *
+ * This generic implementation handles page-table aligned huge pages, as well
+ * as non-page-table aligned hugetlbfs compound pages.
+ *
+ * If an architecture supports and uses non-page-table aligned pages in their
+ * kernel mapping it will need to provide it's own implementation of this
+ * function.
+ */
+__weak u64 arch_perf_get_page_size(struct mm_struct *mm, unsigned long addr)
+{
+	struct page *page;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pgd = pgd_offset(mm, addr);
+	if (pgd_none(*pgd))
+		return 0;
+
+	p4d = p4d_offset(pgd, addr);
+	if (!p4d_present(*p4d))
+		return 0;
+
+	if (p4d_leaf(*p4d))
+		return 1ULL << P4D_SHIFT;
+
+	pud = pud_offset(p4d, addr);
+	if (!pud_present(*pud))
+		return 0;
+
+	if (pud_leaf(*pud)) {
+#ifdef pud_page
+		page = pud_page(*pud);
+		if (PageHuge(page))
+			return page_size(compound_head(page));
+#endif
+		return 1ULL << PUD_SHIFT;
+	}
+
+	pmd = pmd_offset(pud, addr);
+	if (!pmd_present(*pmd))
+		return 0;
+
+	if (pmd_leaf(*pmd)) {
+#ifdef pmd_page
+		page = pmd_page(*pmd);
+		if (PageHuge(page))
+			return page_size(compound_head(page));
+#endif
+		return 1ULL << PMD_SHIFT;
+	}
+
+	pte = pte_offset_map(pmd, addr);
+	if (!pte_present(*pte)) {
+		pte_unmap(pte);
+		return 0;
+	}
+
+	page = pte_page(*pte);
+	if (PageHuge(page)) {
+		u64 size = page_size(compound_head(page));
+		pte_unmap(pte);
+		return size;
+	}
+
+	pte_unmap(pte);
+	return PAGE_SIZE;
+}
+
+#else
+
+static u64 arch_perf_get_page_size(struct mm_struct *mm, unsigned long addr)
+{
+	return 0;
+}
+
+#endif
+
+static u64 perf_get_page_size(unsigned long addr)
+{
+	struct mm_struct *mm;
+	unsigned long flags;
+	u64 size;
+
+	if (!addr)
+		return 0;
+
+	/*
+	 * Software page-table walkers must disable IRQs,
+	 * which prevents any tear down of the page tables.
+	 */
+	local_irq_save(flags);
+
+	mm = current->mm;
+	if (!mm) {
+		/*
+		 * For kernel threads and the like, use init_mm so that
+		 * we can find kernel memory.
+		 */
+		mm = &init_mm;
+	}
+
+	size = arch_perf_get_page_size(mm, addr);
+
+	local_irq_restore(flags);
+
+	return size;
+}
+
 static struct perf_callchain_entry __empty_callchain = { .nr = 0, };
 
 struct perf_callchain_entry *
@@ -7023,7 +7151,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 
 	__perf_event_header__init_id(header, data, event);
 
-	if (sample_type & PERF_SAMPLE_IP)
+	if (sample_type & (PERF_SAMPLE_IP | PERF_SAMPLE_CODE_PAGE_SIZE))
 		data->ip = perf_instruction_pointer(regs);
 
 	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
@@ -7142,6 +7270,17 @@ void perf_prepare_sample(struct perf_event_header *header,
 	}
 #endif
 
+	/*
+	 * PERF_DATA_PAGE_SIZE requires PERF_SAMPLE_ADDR. If the user doesn't
+	 * require PERF_SAMPLE_ADDR, kernel implicitly retrieve the data->addr,
+	 * but the value will not dump to the userspace.
+	 */
+	if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)
+		data->data_page_size = perf_get_page_size(data->addr);
+
+	if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)
+		data->code_page_size = perf_get_page_size(data->ip);
+
 	if (sample_type & PERF_SAMPLE_AUX) {
 		u64 size;