Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Tue,  5 Nov 2019 15:56:00 -0800
In-Reply-To: <20191105235608.107702-1-samitolvanen@google.com>
Message-Id: <20191105235608.107702-7-samitolvanen@google.com>
Mime-Version: 1.0
References: <20191018161033.261971-1-samitolvanen@google.com> <20191105235608.107702-1-samitolvanen@google.com>
Subject: [PATCH v5 06/14] scs: add accounting
From:   Sami Tolvanen <samitolvanen@google.com>
To:     Will Deacon <will@kernel.org>,
        Catalin Marinas <catalin.marinas@arm.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Masami Hiramatsu <mhiramat@kernel.org>,
        Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc:     Dave Martin <Dave.Martin@arm.com>,
        Kees Cook <keescook@chromium.org>,
        Laura Abbott <labbott@redhat.com>,
        Mark Rutland <mark.rutland@arm.com>,
        Marc Zyngier <maz@kernel.org>,
        Nick Desaulniers <ndesaulniers@google.com>,
        Jann Horn <jannh@google.com>,
        Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>,
        Masahiro Yamada <yamada.masahiro@socionext.com>,
        clang-built-linux@googlegroups.com,
        kernel-hardening@lists.openwall.com,
        linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org,
        Sami Tolvanen <samitolvanen@google.com>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

This change adds accounting for the memory allocated for shadow stacks.

Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
---
 drivers/base/node.c    |  6 ++++++
 fs/proc/meminfo.c      |  4 ++++
 include/linux/mmzone.h |  3 +++
 kernel/scs.c           | 20 ++++++++++++++++++++
 mm/page_alloc.c        |  6 ++++++
 mm/vmstat.c            |  3 +++
 6 files changed, 42 insertions(+)

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 296546ffed6c..111e58ec231e 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -415,6 +415,9 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       "Node %d AnonPages:      %8lu kB\n"
 		       "Node %d Shmem:          %8lu kB\n"
 		       "Node %d KernelStack:    %8lu kB\n"
+#ifdef CONFIG_SHADOW_CALL_STACK
+		       "Node %d ShadowCallStack:%8lu kB\n"
+#endif
 		       "Node %d PageTables:     %8lu kB\n"
 		       "Node %d NFS_Unstable:   %8lu kB\n"
 		       "Node %d Bounce:         %8lu kB\n"
@@ -438,6 +441,9 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       nid, K(node_page_state(pgdat, NR_ANON_MAPPED)),
 		       nid, K(i.sharedram),
 		       nid, sum_zone_node_page_state(nid, NR_KERNEL_STACK_KB),
+#ifdef CONFIG_SHADOW_CALL_STACK
+		       nid, sum_zone_node_page_state(nid, NR_KERNEL_SCS_BYTES) / 1024,
+#endif
 		       nid, K(sum_zone_node_page_state(nid, NR_PAGETABLE)),
 		       nid, K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
 		       nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)),
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 8c1f1bb1a5ce..49768005a79e 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -103,6 +103,10 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	show_val_kb(m, "SUnreclaim:     ", sunreclaim);
 	seq_printf(m, "KernelStack:    %8lu kB\n",
 		   global_zone_page_state(NR_KERNEL_STACK_KB));
+#ifdef CONFIG_SHADOW_CALL_STACK
+	seq_printf(m, "ShadowCallStack:%8lu kB\n",
+		   global_zone_page_state(NR_KERNEL_SCS_BYTES) / 1024);
+#endif
 	show_val_kb(m, "PageTables:     ",
 		    global_zone_page_state(NR_PAGETABLE));
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index bda20282746b..fcb8c1708f9e 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -200,6 +200,9 @@ enum zone_stat_item {
 	NR_MLOCK,		/* mlock()ed pages found and moved off LRU */
 	NR_PAGETABLE,		/* used for pagetables */
 	NR_KERNEL_STACK_KB,	/* measured in KiB */
+#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK)
+	NR_KERNEL_SCS_BYTES,	/* measured in bytes */
+#endif
 	/* Second 128 byte cacheline */
 	NR_BOUNCE,
 #if IS_ENABLED(CONFIG_ZSMALLOC)
diff --git a/kernel/scs.c b/kernel/scs.c
index e3234a4b92ec..4f5774b6f27d 100644
--- a/kernel/scs.c
+++ b/kernel/scs.c
@@ -12,6 +12,7 @@
 #include <linux/scs.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include <linux/vmstat.h>
 #include <asm/scs.h>
 
 static inline void *__scs_base(struct task_struct *tsk)
@@ -89,6 +90,11 @@ static void scs_free(void *s)
 	vfree_atomic(s);
 }
 
+static struct page *__scs_page(struct task_struct *tsk)
+{
+	return vmalloc_to_page(__scs_base(tsk));
+}
+
 static int scs_cleanup(unsigned int cpu)
 {
 	int i;
@@ -135,6 +141,11 @@ static inline void scs_free(void *s)
 	kmem_cache_free(scs_cache, s);
 }
 
+static struct page *__scs_page(struct task_struct *tsk)
+{
+	return virt_to_page(__scs_base(tsk));
+}
+
 void __init scs_init(void)
 {
 	scs_cache = kmem_cache_create("scs_cache", SCS_SIZE, SCS_SIZE,
@@ -153,6 +164,12 @@ void scs_task_reset(struct task_struct *tsk)
 	task_set_scs(tsk, __scs_base(tsk));
 }
 
+static void scs_account(struct task_struct *tsk, int account)
+{
+	mod_zone_page_state(page_zone(__scs_page(tsk)), NR_KERNEL_SCS_BYTES,
+		account * SCS_SIZE);
+}
+
 int scs_prepare(struct task_struct *tsk, int node)
 {
 	void *s;
@@ -162,6 +179,8 @@ int scs_prepare(struct task_struct *tsk, int node)
 		return -ENOMEM;
 
 	task_set_scs(tsk, s);
+	scs_account(tsk, 1);
+
 	return 0;
 }
 
@@ -182,6 +201,7 @@ void scs_release(struct task_struct *tsk)
 
 	WARN_ON(scs_corrupted(tsk));
 
+	scs_account(tsk, -1);
 	task_set_scs(tsk, NULL);
 	scs_free(s);
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ecc3dbad606b..fe17d69d98a7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5361,6 +5361,9 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 			" managed:%lukB"
 			" mlocked:%lukB"
 			" kernel_stack:%lukB"
+#ifdef CONFIG_SHADOW_CALL_STACK
+			" shadow_call_stack:%lukB"
+#endif
 			" pagetables:%lukB"
 			" bounce:%lukB"
 			" free_pcp:%lukB"
@@ -5382,6 +5385,9 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 			K(zone_managed_pages(zone)),
 			K(zone_page_state(zone, NR_MLOCK)),
 			zone_page_state(zone, NR_KERNEL_STACK_KB),
+#ifdef CONFIG_SHADOW_CALL_STACK
+			zone_page_state(zone, NR_KERNEL_SCS_BYTES) / 1024,
+#endif
 			K(zone_page_state(zone, NR_PAGETABLE)),
 			K(zone_page_state(zone, NR_BOUNCE)),
 			K(free_pcp),
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 6afc892a148a..9fe4afe670fe 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1118,6 +1118,9 @@ const char * const vmstat_text[] = {
 	"nr_mlock",
 	"nr_page_table_pages",
 	"nr_kernel_stack",
+#if IS_ENABLED(CONFIG_SHADOW_CALL_STACK)
+	"nr_shadow_call_stack_bytes",
+#endif
 	"nr_bounce",
 #if IS_ENABLED(CONFIG_ZSMALLOC)
 	"nr_zspages",
-- 
2.24.0.rc1.363.gb1bccd3e3d-goog