diff mbox series

[v4,06/17] scs: add accounting

Message ID 20191101221150.116536-7-samitolvanen@google.com (mailing list archive)
State New, archived
Headers show
Series [v4,01/17] arm64: mm: avoid x18 in idmap_kpti_install_ng_mappings | expand

Commit Message

Sami Tolvanen Nov. 1, 2019, 10:11 p.m. UTC 
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           | 19 +++++++++++++++++++
 mm/page_alloc.c        |  6 ++++++
 mm/vmstat.c            |  3 +++
 6 files changed, 41 insertions(+)

Comments

Marc Zyngier Nov. 4, 2019, 1:13 p.m. UTC | #1 
On 2019-11-01 23:21, Sami Tolvanen wrote:
> 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           | 19 +++++++++++++++++++
>  mm/page_alloc.c        |  6 ++++++
>  mm/vmstat.c            |  3 +++
>  6 files changed, 41 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)

Is there any reason why you're not consistently using only one of
"#if IS_ENABLED(...)" or "#ifdef ...", but instead a mix of both?

Thanks,

         M.
Sami Tolvanen Nov. 4, 2019, 4:42 p.m. UTC | #2 
On Mon, Nov 4, 2019 at 5:13 AM Marc Zyngier <maz@kernel.org> wrote:
> Is there any reason why you're not consistently using only one of
> "#if IS_ENABLED(...)" or "#ifdef ...", but instead a mix of both?

This is to match the style already used in each file. For example,
fs/proc/meminfo.c uses #ifdef for other configs in the same function,
and include/linux/mmzone.h uses #if IS_ENABLED(...).

Sami
Marc Zyngier Nov. 4, 2019, 4:59 p.m. UTC | #3 
On 2019-11-04 17:52, Sami Tolvanen wrote:
> On Mon, Nov 4, 2019 at 5:13 AM Marc Zyngier <maz@kernel.org> wrote:
>> Is there any reason why you're not consistently using only one of
>> "#if IS_ENABLED(...)" or "#ifdef ...", but instead a mix of both?
>
> This is to match the style already used in each file. For example,
> fs/proc/meminfo.c uses #ifdef for other configs in the same function,
> and include/linux/mmzone.h uses #if IS_ENABLED(...).

Ah, fair enough.

         M.
diff mbox series

Patch

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 7c1a40020754..7780fc4e29ac 100644
--- a/kernel/scs.c
+++ b/kernel/scs.c
@@ -11,6 +11,7 @@ 
 #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)
@@ -74,6 +75,11 @@  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;
@@ -107,6 +113,11 @@  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,
@@ -135,6 +146,12 @@  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;
@@ -145,6 +162,7 @@  int scs_prepare(struct task_struct *tsk, int node)
 
 	task_set_scs(tsk, s);
 	scs_set_magic(tsk);
+	scs_account(tsk, 1);
 
 	return 0;
 }
@@ -164,6 +182,7 @@  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",