mm/damon: implement primitives for physical address space monitoring

This implements the monitoring primitives for the physical memory
address space.  Internally, it uses the PTE Accessed bit, similar to
that of the virtual address spaces monitoring primitives.  It supports
only user memory pages, as idle pages tracking does.  If the monitoring
target physical memory address range contains non-user memory pages,
access check of the pages will do nothing but simply treat the pages as
not accessed.

Link: https://lkml.kernel.org/r/20211012205711.29216-6-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Amit Shah <amit@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rienjes <rientjes@google.com>
Cc: David Woodhouse <dwmw@amazon.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Leonard Foerster <foersleo@amazon.de>
Cc: Marco Elver <elver@google.com>
Cc: Markus Boehme <markubo@amazon.de>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/damon.h b/include/linux/damon.h
index f301bb53381c19d4ac6fc82e700c9a6d36a2df76..715dadd21f7cd41c07025d801b025344375db866 100644 (file)
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -351,4 +351,14 @@ void damon_va_set_primitives(struct damon_ctx *ctx);
 
 #endif /* CONFIG_DAMON_VADDR */
 
+#ifdef CONFIG_DAMON_PADDR
+
+/* Monitoring primitives for the physical memory address space */
+void damon_pa_prepare_access_checks(struct damon_ctx *ctx);
+unsigned int damon_pa_check_accesses(struct damon_ctx *ctx);
+bool damon_pa_target_valid(void *t);
+void damon_pa_set_primitives(struct damon_ctx *ctx);
+
+#endif /* CONFIG_DAMON_PADDR */
+
 #endif /* _DAMON_H */

diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig
index ba8898c7eb8eb35e12e4b21846ce06210ee1c3e1..2a5923be631e2873d7ccae3915d6038437cf5b2e 100644 (file)
--- a/mm/damon/Kconfig
+++ b/mm/damon/Kconfig
@@ -32,6 +32,14 @@ config DAMON_VADDR
          This builds the default data access monitoring primitives for DAMON
          that work for virtual address spaces.
 
+config DAMON_PADDR
+       bool "Data access monitoring primitives for the physical address space"
+       depends on DAMON && MMU
+       select PAGE_IDLE_FLAG
+       help
+         This builds the default data access monitoring primitives for DAMON
+         that works for the physical address space.
+
 config DAMON_VADDR_KUNIT_TEST
        bool "Test for DAMON primitives" if !KUNIT_ALL_TESTS
        depends on DAMON_VADDR && KUNIT=y

diff --git a/mm/damon/Makefile b/mm/damon/Makefile
index 99b1bfe01ff51d2b2d59e2ca1ae722a4db2bbcc8..8d9b0df797029811b11a73b42e65fb7667dc886e 100644 (file)
--- a/mm/damon/Makefile
+++ b/mm/damon/Makefile
@@ -2,4 +2,5 @@
 
 obj-$(CONFIG_DAMON)            := core.o
 obj-$(CONFIG_DAMON_VADDR)      += prmtv-common.o vaddr.o
+obj-$(CONFIG_DAMON_PADDR)      += prmtv-common.o paddr.o
 obj-$(CONFIG_DAMON_DBGFS)      += dbgfs.o

diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c
new file mode 100644 (file)
index 0000000..d7a2ecd
--- /dev/null
+++ b/mm/damon/paddr.c
@@ -0,0 +1,224 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DAMON Primitives for The Physical Address Space
+ *
+ * Author: SeongJae Park <sj@kernel.org>
+ */
+
+#define pr_fmt(fmt) "damon-pa: " fmt
+
+#include <linux/mmu_notifier.h>
+#include <linux/page_idle.h>
+#include <linux/pagemap.h>
+#include <linux/rmap.h>
+
+#include "prmtv-common.h"
+
+static bool __damon_pa_mkold(struct page *page, struct vm_area_struct *vma,
+               unsigned long addr, void *arg)
+{
+       struct page_vma_mapped_walk pvmw = {
+               .page = page,
+               .vma = vma,
+               .address = addr,
+       };
+
+       while (page_vma_mapped_walk(&pvmw)) {
+               addr = pvmw.address;
+               if (pvmw.pte)
+                       damon_ptep_mkold(pvmw.pte, vma->vm_mm, addr);
+               else
+                       damon_pmdp_mkold(pvmw.pmd, vma->vm_mm, addr);
+       }
+       return true;
+}
+
+static void damon_pa_mkold(unsigned long paddr)
+{
+       struct page *page = damon_get_page(PHYS_PFN(paddr));
+       struct rmap_walk_control rwc = {
+               .rmap_one = __damon_pa_mkold,
+               .anon_lock = page_lock_anon_vma_read,
+       };
+       bool need_lock;
+
+       if (!page)
+               return;
+
+       if (!page_mapped(page) || !page_rmapping(page)) {
+               set_page_idle(page);
+               goto out;
+       }
+
+       need_lock = !PageAnon(page) || PageKsm(page);
+       if (need_lock && !trylock_page(page))
+               goto out;
+
+       rmap_walk(page, &rwc);
+
+       if (need_lock)
+               unlock_page(page);
+
+out:
+       put_page(page);
+}
+
+static void __damon_pa_prepare_access_check(struct damon_ctx *ctx,
+                                           struct damon_region *r)
+{
+       r->sampling_addr = damon_rand(r->ar.start, r->ar.end);
+
+       damon_pa_mkold(r->sampling_addr);
+}
+
+void damon_pa_prepare_access_checks(struct damon_ctx *ctx)
+{
+       struct damon_target *t;
+       struct damon_region *r;
+
+       damon_for_each_target(t, ctx) {
+               damon_for_each_region(r, t)
+                       __damon_pa_prepare_access_check(ctx, r);
+       }
+}
+
+struct damon_pa_access_chk_result {
+       unsigned long page_sz;
+       bool accessed;
+};
+
+static bool __damon_pa_young(struct page *page, struct vm_area_struct *vma,
+               unsigned long addr, void *arg)
+{
+       struct damon_pa_access_chk_result *result = arg;
+       struct page_vma_mapped_walk pvmw = {
+               .page = page,
+               .vma = vma,
+               .address = addr,
+       };
+
+       result->accessed = false;
+       result->page_sz = PAGE_SIZE;
+       while (page_vma_mapped_walk(&pvmw)) {
+               addr = pvmw.address;
+               if (pvmw.pte) {
+                       result->accessed = pte_young(*pvmw.pte) ||
+                               !page_is_idle(page) ||
+                               mmu_notifier_test_young(vma->vm_mm, addr);
+               } else {
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+                       result->accessed = pmd_young(*pvmw.pmd) ||
+                               !page_is_idle(page) ||
+                               mmu_notifier_test_young(vma->vm_mm, addr);
+                       result->page_sz = ((1UL) << HPAGE_PMD_SHIFT);
+#else
+                       WARN_ON_ONCE(1);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+               }
+               if (result->accessed) {
+                       page_vma_mapped_walk_done(&pvmw);
+                       break;
+               }
+       }
+
+       /* If accessed, stop walking */
+       return !result->accessed;
+}
+
+static bool damon_pa_young(unsigned long paddr, unsigned long *page_sz)
+{
+       struct page *page = damon_get_page(PHYS_PFN(paddr));
+       struct damon_pa_access_chk_result result = {
+               .page_sz = PAGE_SIZE,
+               .accessed = false,
+       };
+       struct rmap_walk_control rwc = {
+               .arg = &result,
+               .rmap_one = __damon_pa_young,
+               .anon_lock = page_lock_anon_vma_read,
+       };
+       bool need_lock;
+
+       if (!page)
+               return false;
+
+       if (!page_mapped(page) || !page_rmapping(page)) {
+               if (page_is_idle(page))
+                       result.accessed = false;
+               else
+                       result.accessed = true;
+               put_page(page);
+               goto out;
+       }
+
+       need_lock = !PageAnon(page) || PageKsm(page);
+       if (need_lock && !trylock_page(page)) {
+               put_page(page);
+               return NULL;
+       }
+
+       rmap_walk(page, &rwc);
+
+       if (need_lock)
+               unlock_page(page);
+       put_page(page);
+
+out:
+       *page_sz = result.page_sz;
+       return result.accessed;
+}
+
+static void __damon_pa_check_access(struct damon_ctx *ctx,
+                                   struct damon_region *r)
+{
+       static unsigned long last_addr;
+       static unsigned long last_page_sz = PAGE_SIZE;
+       static bool last_accessed;
+
+       /* If the region is in the last checked page, reuse the result */
+       if (ALIGN_DOWN(last_addr, last_page_sz) ==
+                               ALIGN_DOWN(r->sampling_addr, last_page_sz)) {
+               if (last_accessed)
+                       r->nr_accesses++;
+               return;
+       }
+
+       last_accessed = damon_pa_young(r->sampling_addr, &last_page_sz);
+       if (last_accessed)
+               r->nr_accesses++;
+
+       last_addr = r->sampling_addr;
+}
+
+unsigned int damon_pa_check_accesses(struct damon_ctx *ctx)
+{
+       struct damon_target *t;
+       struct damon_region *r;
+       unsigned int max_nr_accesses = 0;
+
+       damon_for_each_target(t, ctx) {
+               damon_for_each_region(r, t) {
+                       __damon_pa_check_access(ctx, r);
+                       max_nr_accesses = max(r->nr_accesses, max_nr_accesses);
+               }
+       }
+
+       return max_nr_accesses;
+}
+
+bool damon_pa_target_valid(void *t)
+{
+       return true;
+}
+
+void damon_pa_set_primitives(struct damon_ctx *ctx)
+{
+       ctx->primitive.init = NULL;
+       ctx->primitive.update = NULL;
+       ctx->primitive.prepare_access_checks = damon_pa_prepare_access_checks;
+       ctx->primitive.check_accesses = damon_pa_check_accesses;
+       ctx->primitive.reset_aggregated = NULL;
+       ctx->primitive.target_valid = damon_pa_target_valid;
+       ctx->primitive.cleanup = NULL;
+       ctx->primitive.apply_scheme = NULL;
+}