[PATCH v9 12/25] dept: Distinguish each syscall context from another

From: Byungchul Park <max.byungchul.park@gmail.com>
To: linux-kernel@vger.kernel.org
Cc: torvalds@linux-foundation.org, damien.lemoal@opensource.wdc.com,
	linux-ide@vger.kernel.org, adilger.kernel@dilger.ca,
	linux-ext4@vger.kernel.org, mingo@redhat.com,
	peterz@infradead.org, will@kernel.org, tglx@linutronix.de,
	rostedt@goodmis.org, joel@joelfernandes.org, sashal@kernel.org,
	daniel.vetter@ffwll.ch, duyuyang@gmail.com,
	johannes.berg@intel.com, tj@kernel.org, tytso@mit.edu,
	willy@infradead.org, david@fromorbit.com, amir73il@gmail.com,
	gregkh@linuxfoundation.org, kernel-team@lge.com,
	linux-mm@kvack.org, akpm@linux-foundation.org, mhocko@kernel.org,
	minchan@kernel.org, hannes@cmpxchg.org, vdavydov.dev@gmail.com,
	sj@kernel.org, jglisse@redhat.com, dennis@kernel.org,
	cl@linux.com, penberg@kernel.org, rientjes@google.com,
	vbabka@suse.cz, ngupta@vflare.org, linux-block@vger.kernel.org,
	paolo.valente@linaro.org, josef@toxicpanda.com,
	linux-fsdevel@vger.kernel.org, viro@zeniv.linux.org.uk,
	jack@suse.cz, jlayton@kernel.org, dan.j.williams@intel.com,
	hch@infradead.org, djwong@kernel.org,
	dri-devel@lists.freedesktop.org, rodrigosiqueiramelo@gmail.com,
	melissa.srw@gmail.com, hamohammed.sa@gmail.com,
	42.hyeyoo@gmail.com, chris.p.wilson@intel.com,
	gwan-gyeong.mun@intel.com, max.byungchul.park@gmail.com,
	boqun.feng@gmail.com, longman@redhat.com, hdanton@sina.com
Subject: [PATCH v9 12/25] dept: Distinguish each syscall context from another
Date: Tue, 31 Jan 2023 17:39:41 +0900	[thread overview]
Message-ID: <1675154394-25598-13-git-send-email-max.byungchul.park@gmail.com> (raw)
In-Reply-To: <1675154394-25598-1-git-send-email-max.byungchul.park@gmail.com>

It enters kernel mode on each syscall and each syscall handling should
be considered independently from the point of view of Dept. Otherwise,
Dept may wrongly track dependencies across different syscalls.

That might be a real dependency from user mode. However, now that Dept
just started to work, conservatively let Dept not track dependencies
across different syscalls.

Signed-off-by: Byungchul Park <max.byungchul.park@gmail.com>
---
 arch/arm64/kernel/syscall.c |  2 ++
 arch/x86/entry/common.c     |  4 +++
 include/linux/dept.h        | 39 +++++++++++++++-----------
 kernel/dependency/dept.c    | 67 +++++++++++++++++++++++----------------------
 4 files changed, 63 insertions(+), 49 deletions(-)

diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index a5de47e..e26d0ca 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -7,6 +7,7 @@
 #include <linux/ptrace.h>
 #include <linux/randomize_kstack.h>
 #include <linux/syscalls.h>
+#include <linux/dept.h>
 
 #include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
@@ -105,6 +106,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	 */
 
 	local_daif_restore(DAIF_PROCCTX);
+	dept_kernel_enter();
 
 	if (flags & _TIF_MTE_ASYNC_FAULT) {
 		/*
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 6c28264..7cdd27a 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -19,6 +19,7 @@
 #include <linux/nospec.h>
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
+#include <linux/dept.h>
 
 #ifdef CONFIG_XEN_PV
 #include <xen/xen-ops.h>
@@ -72,6 +73,7 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr)
 
 __visible noinstr void do_syscall_64(struct pt_regs *regs, int nr)
 {
+	dept_kernel_enter();
 	add_random_kstack_offset();
 	nr = syscall_enter_from_user_mode(regs, nr);
 
@@ -120,6 +122,7 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
 {
 	int nr = syscall_32_enter(regs);
 
+	dept_kernel_enter();
 	add_random_kstack_offset();
 	/*
 	 * Subtlety here: if ptrace pokes something larger than 2^31-1 into
@@ -140,6 +143,7 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 	int nr = syscall_32_enter(regs);
 	int res;
 
+	dept_kernel_enter();
 	add_random_kstack_offset();
 	/*
 	 * This cannot use syscall_enter_from_user_mode() as it has to
diff --git a/include/linux/dept.h b/include/linux/dept.h
index b6d45b4..f62c7b6 100644
--- a/include/linux/dept.h
+++ b/include/linux/dept.h
@@ -25,11 +25,16 @@
 #define DEPT_MAX_SUBCLASSES_USR		(DEPT_MAX_SUBCLASSES / DEPT_MAX_SUBCLASSES_EVT)
 #define DEPT_MAX_SUBCLASSES_CACHE	2
 
-#define DEPT_SIRQ			0
-#define DEPT_HIRQ			1
-#define DEPT_IRQS_NR			2
-#define DEPT_SIRQF			(1UL << DEPT_SIRQ)
-#define DEPT_HIRQF			(1UL << DEPT_HIRQ)
+enum {
+	DEPT_CXT_SIRQ = 0,
+	DEPT_CXT_HIRQ,
+	DEPT_CXT_IRQS_NR,
+	DEPT_CXT_PROCESS = DEPT_CXT_IRQS_NR,
+	DEPT_CXTS_NR
+};
+
+#define DEPT_SIRQF			(1UL << DEPT_CXT_SIRQ)
+#define DEPT_HIRQF			(1UL << DEPT_CXT_HIRQ)
 
 struct dept_ecxt;
 struct dept_iecxt {
@@ -94,8 +99,8 @@ struct dept_class {
 			/*
 			 * for tracking IRQ dependencies
 			 */
-			struct dept_iecxt iecxt[DEPT_IRQS_NR];
-			struct dept_iwait iwait[DEPT_IRQS_NR];
+			struct dept_iecxt iecxt[DEPT_CXT_IRQS_NR];
+			struct dept_iwait iwait[DEPT_CXT_IRQS_NR];
 
 			/*
 			 * classified by a map embedded in task_struct,
@@ -207,8 +212,8 @@ struct dept_ecxt {
 			/*
 			 * where the IRQ-enabled happened
 			 */
-			unsigned long	enirq_ip[DEPT_IRQS_NR];
-			struct dept_stack *enirq_stack[DEPT_IRQS_NR];
+			unsigned long	enirq_ip[DEPT_CXT_IRQS_NR];
+			struct dept_stack *enirq_stack[DEPT_CXT_IRQS_NR];
 
 			/*
 			 * where the event context started
@@ -252,8 +257,8 @@ struct dept_wait {
 			/*
 			 * where the IRQ wait happened
 			 */
-			unsigned long	irq_ip[DEPT_IRQS_NR];
-			struct dept_stack *irq_stack[DEPT_IRQS_NR];
+			unsigned long	irq_ip[DEPT_CXT_IRQS_NR];
+			struct dept_stack *irq_stack[DEPT_CXT_IRQS_NR];
 
 			/*
 			 * where the wait happened
@@ -406,19 +411,19 @@ struct dept_task {
 	int				wait_hist_pos;
 
 	/*
-	 * sequential id to identify each IRQ context
+	 * sequential id to identify each context
 	 */
-	unsigned int			irq_id[DEPT_IRQS_NR];
+	unsigned int			cxt_id[DEPT_CXTS_NR];
 
 	/*
 	 * for tracking IRQ-enabled points with cross-event
 	 */
-	unsigned int			wgen_enirq[DEPT_IRQS_NR];
+	unsigned int			wgen_enirq[DEPT_CXT_IRQS_NR];
 
 	/*
 	 * for keeping up-to-date IRQ-enabled points
 	 */
-	unsigned long			enirq_ip[DEPT_IRQS_NR];
+	unsigned long			enirq_ip[DEPT_CXT_IRQS_NR];
 
 	/*
 	 * current effective IRQ-enabled flag
@@ -470,7 +475,7 @@ struct dept_task {
 	.wait_hist = { { .wait = NULL, } },			\
 	.ecxt_held_pos = 0,					\
 	.wait_hist_pos = 0,					\
-	.irq_id = { 0U },					\
+	.cxt_id = { 0U },					\
 	.wgen_enirq = { 0U },					\
 	.enirq_ip = { 0UL },					\
 	.eff_enirqf = 0UL,					\
@@ -509,6 +514,7 @@ struct dept_task {
 extern void dept_ecxt_exit(struct dept_map *m, unsigned long e_f, unsigned long ip);
 extern void dept_sched_enter(void);
 extern void dept_sched_exit(void);
+extern void dept_kernel_enter(void);
 
 static inline void dept_ecxt_enter_nokeep(struct dept_map *m)
 {
@@ -560,6 +566,7 @@ static inline void dept_ecxt_enter_nokeep(struct dept_map *m)
 #define dept_ecxt_exit(m, e_f, ip)			do { } while (0)
 #define dept_sched_enter()				do { } while (0)
 #define dept_sched_exit()				do { } while (0)
+#define dept_kernel_enter()				do { } while (0)
 #define dept_ecxt_enter_nokeep(m)			do { } while (0)
 #define dept_key_init(k)				do { (void)(k); } while (0)
 #define dept_key_destroy(k)				do { (void)(k); } while (0)
diff --git a/kernel/dependency/dept.c b/kernel/dependency/dept.c
index ede82cc..dd90746 100644
--- a/kernel/dependency/dept.c
+++ b/kernel/dependency/dept.c
@@ -221,9 +221,9 @@ static inline struct dept_class *dep_tc(struct dept_dep *d)
 
 static inline const char *irq_str(int irq)
 {
-	if (irq == DEPT_SIRQ)
+	if (irq == DEPT_CXT_SIRQ)
 		return "softirq";
-	if (irq == DEPT_HIRQ)
+	if (irq == DEPT_CXT_HIRQ)
 		return "hardirq";
 	return "(unknown)";
 }
@@ -407,7 +407,7 @@ static void initialize_class(struct dept_class *c)
 {
 	int i;
 
-	for (i = 0; i < DEPT_IRQS_NR; i++) {
+	for (i = 0; i < DEPT_CXT_IRQS_NR; i++) {
 		struct dept_iecxt *ie = &c->iecxt[i];
 		struct dept_iwait *iw = &c->iwait[i];
 
@@ -432,7 +432,7 @@ static void initialize_ecxt(struct dept_ecxt *e)
 {
 	int i;
 
-	for (i = 0; i < DEPT_IRQS_NR; i++) {
+	for (i = 0; i < DEPT_CXT_IRQS_NR; i++) {
 		e->enirq_stack[i] = NULL;
 		e->enirq_ip[i] = 0UL;
 	}
@@ -448,7 +448,7 @@ static void initialize_wait(struct dept_wait *w)
 {
 	int i;
 
-	for (i = 0; i < DEPT_IRQS_NR; i++) {
+	for (i = 0; i < DEPT_CXT_IRQS_NR; i++) {
 		w->irq_stack[i] = NULL;
 		w->irq_ip[i] = 0UL;
 	}
@@ -487,7 +487,7 @@ static void destroy_ecxt(struct dept_ecxt *e)
 {
 	int i;
 
-	for (i = 0; i < DEPT_IRQS_NR; i++)
+	for (i = 0; i < DEPT_CXT_IRQS_NR; i++)
 		if (e->enirq_stack[i])
 			put_stack(e->enirq_stack[i]);
 	if (e->class)
@@ -503,7 +503,7 @@ static void destroy_wait(struct dept_wait *w)
 {
 	int i;
 
-	for (i = 0; i < DEPT_IRQS_NR; i++)
+	for (i = 0; i < DEPT_CXT_IRQS_NR; i++)
 		if (w->irq_stack[i])
 			put_stack(w->irq_stack[i]);
 	if (w->class)
@@ -652,7 +652,7 @@ static void print_diagram(struct dept_dep *d)
 	const char *tc_n = tc->sched_map ? "<sched>" : (tc->name ?: "(unknown)");
 
 	irqf = e->enirqf & w->irqf;
-	for_each_set_bit(irq, &irqf, DEPT_IRQS_NR) {
+	for_each_set_bit(irq, &irqf, DEPT_CXT_IRQS_NR) {
 		if (!firstline)
 			pr_warn("\nor\n\n");
 		firstline = false;
@@ -685,7 +685,7 @@ static void print_dep(struct dept_dep *d)
 	const char *tc_n = tc->sched_map ? "<sched>" : (tc->name ?: "(unknown)");
 
 	irqf = e->enirqf & w->irqf;
-	for_each_set_bit(irq, &irqf, DEPT_IRQS_NR) {
+	for_each_set_bit(irq, &irqf, DEPT_CXT_IRQS_NR) {
 		pr_warn("%s has been enabled:\n", irq_str(irq));
 		print_ip_stack(e->enirq_ip[irq], e->enirq_stack[irq]);
 		pr_warn("\n");
@@ -911,7 +911,7 @@ static void bfs(struct dept_class *c, bfs_f *cb, void *in, void **out)
  */
 
 static inline unsigned long cur_enirqf(void);
-static inline int cur_irq(void);
+static inline int cur_cxt(void);
 static inline unsigned int cur_ctxt_id(void);
 
 static inline struct dept_iecxt *iecxt(struct dept_class *c, int irq)
@@ -1459,7 +1459,7 @@ static void add_dep(struct dept_ecxt *e, struct dept_wait *w)
 	if (d) {
 		check_dl_bfs(d);
 
-		for (i = 0; i < DEPT_IRQS_NR; i++) {
+		for (i = 0; i < DEPT_CXT_IRQS_NR; i++) {
 			struct dept_iwait *fiw = iwait(fc, i);
 			struct dept_iecxt *found_ie;
 			struct dept_iwait *found_iw;
@@ -1495,7 +1495,7 @@ static void add_wait(struct dept_class *c, unsigned long ip,
 	struct dept_task *dt = dept_task();
 	struct dept_wait *w;
 	unsigned int wg = 0U;
-	int irq;
+	int cxt;
 	int i;
 
 	if (DEPT_WARN_ON(!valid_class(c)))
@@ -1511,9 +1511,9 @@ static void add_wait(struct dept_class *c, unsigned long ip,
 	w->wait_stack = get_current_stack();
 	w->sched_sleep = sched_sleep;
 
-	irq = cur_irq();
-	if (irq < DEPT_IRQS_NR)
-		add_iwait(c, irq, w);
+	cxt = cur_cxt();
+	if (cxt == DEPT_CXT_HIRQ || cxt == DEPT_CXT_SIRQ)
+		add_iwait(c, cxt, w);
 
 	/*
 	 * Avoid adding dependency between user aware nested ecxt and
@@ -1594,7 +1594,7 @@ static bool add_ecxt(struct dept_map *m, struct dept_class *c,
 	eh->sub_l = sub_l;
 
 	irqf = cur_enirqf();
-	for_each_set_bit(irq, &irqf, DEPT_IRQS_NR)
+	for_each_set_bit(irq, &irqf, DEPT_CXT_IRQS_NR)
 		add_iecxt(c, irq, e, false);
 
 	del_ecxt(e);
@@ -1746,7 +1746,7 @@ static void do_event(struct dept_map *m, struct dept_class *c,
 			add_dep(eh->ecxt, wh->wait);
 	}
 
-	for (i = 0; i < DEPT_IRQS_NR; i++) {
+	for (i = 0; i < DEPT_CXT_IRQS_NR; i++) {
 		struct dept_ecxt *e;
 
 		if (before(dt->wgen_enirq[i], wg))
@@ -1788,7 +1788,7 @@ static void disconnect_class(struct dept_class *c)
 		call_rcu(&d->rh, del_dep_rcu);
 	}
 
-	for (i = 0; i < DEPT_IRQS_NR; i++) {
+	for (i = 0; i < DEPT_CXT_IRQS_NR; i++) {
 		stale_iecxt(iecxt(c, i));
 		stale_iwait(iwait(c, i));
 	}
@@ -1813,27 +1813,21 @@ static inline unsigned long cur_enirqf(void)
 	return 0UL;
 }
 
-static inline int cur_irq(void)
+static inline int cur_cxt(void)
 {
 	if (lockdep_softirq_context(current))
-		return DEPT_SIRQ;
+		return DEPT_CXT_SIRQ;
 	if (lockdep_hardirq_context())
-		return DEPT_HIRQ;
-	return DEPT_IRQS_NR;
+		return DEPT_CXT_HIRQ;
+	return DEPT_CXT_PROCESS;
 }
 
 static inline unsigned int cur_ctxt_id(void)
 {
 	struct dept_task *dt = dept_task();
-	int irq = cur_irq();
+	int cxt = cur_cxt();
 
-	/*
-	 * Normal process context
-	 */
-	if (irq == DEPT_IRQS_NR)
-		return 0U;
-
-	return dt->irq_id[irq] | (1UL << irq);
+	return dt->cxt_id[cxt] | (1UL << cxt);
 }
 
 static void enirq_transition(int irq)
@@ -1884,7 +1878,7 @@ static void enirq_update(unsigned long ip)
 	/*
 	 * Do enirq_transition() only on an OFF -> ON transition.
 	 */
-	for_each_set_bit(irq, &irqf, DEPT_IRQS_NR) {
+	for_each_set_bit(irq, &irqf, DEPT_CXT_IRQS_NR) {
 		if (prev & (1UL << irq))
 			continue;
 
@@ -1983,6 +1977,13 @@ void dept_hardirqs_off_ip(unsigned long ip)
 }
 EXPORT_SYMBOL_GPL(dept_hardirqs_off_ip);
 
+void dept_kernel_enter(void)
+{
+	struct dept_task *dt = dept_task();
+
+	dt->cxt_id[DEPT_CXT_PROCESS] += 1UL << DEPT_CXTS_NR;
+}
+
 /*
  * Ensure it's the outmost softirq context.
  */
@@ -1990,7 +1991,7 @@ void dept_softirq_enter(void)
 {
 	struct dept_task *dt = dept_task();
 
-	dt->irq_id[DEPT_SIRQ] += 1UL << DEPT_IRQS_NR;
+	dt->cxt_id[DEPT_CXT_SIRQ] += 1UL << DEPT_CXTS_NR;
 }
 
 /*
@@ -2000,7 +2001,7 @@ void dept_hardirq_enter(void)
 {
 	struct dept_task *dt = dept_task();
 
-	dt->irq_id[DEPT_HIRQ] += 1UL << DEPT_IRQS_NR;
+	dt->cxt_id[DEPT_CXT_HIRQ] += 1UL << DEPT_CXTS_NR;
 }
 
 void dept_sched_enter(void)
-- 
1.9.1

