[PATCH v9 0/9] Request for inclusion: per-cgroup tcp memory pressure controls

@@ -289,7 +289,9 @@ to trigger slab reclaim when those limits are reached.
 
 2.7.1 Current Kernel Memory resources accounted
 
-None
+* sockets memory pressure: some sockets protocols have memory pressure
+thresholds. The Memory Controller allows them to be controlled individually
+per cgroup, instead of globally.
 
 3. User Interface
 

@@ -85,6 +85,8 @@ extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
 extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
 extern struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm);
 
+extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
+
 static inline
 int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup)
 {

@@ -381,5 +383,25 @@ mem_cgroup_print_bad_page(struct page *page)
 }
 #endif
 
+#ifdef CONFIG_INET
+enum {
+	UNDER_LIMIT,
+	SOFT_LIMIT,
+	OVER_LIMIT,
+};
+
+struct sock;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+void sock_update_memcg(struct sock *sk);
+void sock_release_memcg(struct sock *sk);
+#else
+static inline void sock_update_memcg(struct sock *sk)
+{
+}
+static inline void sock_release_memcg(struct sock *sk)
+{
+}
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
+#endif /* CONFIG_INET */
 #endif /* _LINUX_MEMCONTROL_H */
 

@@ -54,6 +54,7 @@
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <linux/memcontrol.h>
+#include <linux/res_counter.h>
 
 #include <linux/filter.h>
 #include <linux/rculist_nulls.h>

@@ -168,6 +169,7 @@ struct sock_common {
 	/* public: */
 };
 
+struct cg_proto;
 /**
   *	struct sock - network layer representation of sockets
   *	@__sk_common: shared layout with inet_timewait_sock

@@ -228,6 +230,7 @@ struct sock_common {
   *	@sk_security: used by security modules
   *	@sk_mark: generic packet mark
   *	@sk_classid: this socket's cgroup classid
+  *	@sk_cgrp: this socket's cgroup-specific proto data
   *	@sk_write_pending: a write to stream socket waits to start
   *	@sk_state_change: callback to indicate change in the state of the sock
   *	@sk_data_ready: callback to indicate there is data to be processed

@@ -339,6 +342,7 @@ struct sock {
 #endif
 	__u32			sk_mark;
 	u32			sk_classid;
+	struct cg_proto		*sk_cgrp;
 	void			(*sk_state_change)(struct sock *sk);
 	void			(*sk_data_ready)(struct sock *sk, int bytes);
 	void			(*sk_write_space)(struct sock *sk);

@@ -834,6 +838,37 @@ struct proto {
 #ifdef SOCK_REFCNT_DEBUG
 	atomic_t		socks;
 #endif
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+	/*
+	 * cgroup specific init/deinit functions. Called once for all
+	 * protocols that implement it, from cgroups populate function.
+	 * This function has to setup any files the protocol want to
+	 * appear in the kmem cgroup filesystem.
+	 */
+	int			(*init_cgroup)(struct cgroup *cgrp,
+					       struct cgroup_subsys *ss);
+	void			(*destroy_cgroup)(struct cgroup *cgrp,
+						  struct cgroup_subsys *ss);
+	struct cg_proto		*(*proto_cgroup)(struct mem_cgroup *memcg);
+#endif
+};
+
+struct cg_proto {
+	void			(*enter_memory_pressure)(struct sock *sk);
+	struct res_counter	*memory_allocated;	/* Current allocated memory. */
+	struct percpu_counter	*sockets_allocated;	/* Current number of sockets. */
+	int			*memory_pressure;
+	long			*sysctl_mem;
+	/*
+	 * memcg field is used to find which memcg we belong directly
+	 * Each memcg struct can hold more than one cg_proto, so container_of
+	 * won't really cut.
+	 *
+	 * The elegant solution would be having an inverse function to
+	 * proto_cgroup in struct proto, but that means polluting the structure
+	 * for everybody, instead of just for memcg users.
+	 */
+	struct mem_cgroup	*memcg;
 };
 
 extern int proto_register(struct proto *prot, int alloc_slab);

@@ -852,7 +887,7 @@ static inline void sk_refcnt_debug_dec(struct sock *sk)
 	       sk->sk_prot->name, sk, atomic_read(&sk->sk_prot->socks));
 }
 
-static inline void sk_refcnt_debug_release(const struct sock *sk)
+inline void sk_refcnt_debug_release(const struct sock *sk)
 {
 	if (atomic_read(&sk->sk_refcnt) != 1)
 		printk(KERN_DEBUG "Destruction of the %s socket %p delayed, refcnt=%d\n",

@@ -864,6 +899,24 @@ static inline void sk_refcnt_debug_release(const struct sock *sk)
 #define sk_refcnt_debug_release(sk) do { } while (0)
 #endif /* SOCK_REFCNT_DEBUG */
 
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+extern struct jump_label_key memcg_socket_limit_enabled;
+static inline struct cg_proto *parent_cg_proto(struct proto *proto,
+					       struct cg_proto *cg_proto)
+{
+	return proto->proto_cgroup(parent_mem_cgroup(cg_proto->memcg));
+}
+#define mem_cgroup_sockets_enabled static_branch(&memcg_socket_limit_enabled)
+#else
+#define mem_cgroup_sockets_enabled 0
+static inline struct cg_proto *parent_cg_proto(struct proto *proto,
+					       struct cg_proto *cg_proto)
+{
+	return NULL;
+}
+#endif
+
+
 static inline bool sk_has_memory_pressure(const struct sock *sk)
 {
 	return sk->sk_prot->memory_pressure != NULL;

@@ -873,6 +926,10 @@ static inline bool sk_under_memory_pressure(const struct sock *sk)
 {
 	if (!sk->sk_prot->memory_pressure)
 		return false;
+
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
+		return !!*sk->sk_cgrp->memory_pressure;
+
 	return !!*sk->sk_prot->memory_pressure;
 }
 

@@ -880,52 +937,136 @@ static inline void sk_leave_memory_pressure(struct sock *sk)
 {
 	int *memory_pressure = sk->sk_prot->memory_pressure;
 
-	if (memory_pressure && *memory_pressure)
+	if (!memory_pressure)
+		return;
+
+	if (*memory_pressure)
 		*memory_pressure = 0;
+
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
+		struct cg_proto *cg_proto = sk->sk_cgrp;
+		struct proto *prot = sk->sk_prot;
+
+		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
+			if (*cg_proto->memory_pressure)
+				*cg_proto->memory_pressure = 0;
+	}
+
 }
 
 static inline void sk_enter_memory_pressure(struct sock *sk)
 {
-	if (sk->sk_prot->enter_memory_pressure)
-		sk->sk_prot->enter_memory_pressure(sk);
+	if (!sk->sk_prot->enter_memory_pressure)
+		return;
+
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
+		struct cg_proto *cg_proto = sk->sk_cgrp;
+		struct proto *prot = sk->sk_prot;
+
+		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
+			cg_proto->enter_memory_pressure(sk);
+	}
+
+	sk->sk_prot->enter_memory_pressure(sk);
 }
 
 static inline long sk_prot_mem_limits(const struct sock *sk, int index)
 {
 	long *prot = sk->sk_prot->sysctl_mem;
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
+		prot = sk->sk_cgrp->sysctl_mem;
 	return prot[index];
 }
 
+static inline void memcg_memory_allocated_add(struct cg_proto *prot,
+					      unsigned long amt,
+					      int *parent_status)
+{
+	struct res_counter *fail;
+	int ret;
+
+	ret = res_counter_charge(prot->memory_allocated,
+				 amt << PAGE_SHIFT, &fail);
+
+	if (ret < 0)
+		*parent_status = OVER_LIMIT;
+}
+
+static inline void memcg_memory_allocated_sub(struct cg_proto *prot,
+					      unsigned long amt)
+{
+	res_counter_uncharge(prot->memory_allocated, amt << PAGE_SHIFT);
+}
+
+static inline u64 memcg_memory_allocated_read(struct cg_proto *prot)
+{
+	u64 ret;
+	ret = res_counter_read_u64(prot->memory_allocated, RES_USAGE);
+	return ret >> PAGE_SHIFT;
+}
+
 static inline long
 sk_memory_allocated(const struct sock *sk)
 {
 	struct proto *prot = sk->sk_prot;
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
+		return memcg_memory_allocated_read(sk->sk_cgrp);
+
 	return atomic_long_read(prot->memory_allocated);
 }
 
 static inline long
-sk_memory_allocated_add(struct sock *sk, int amt)
+sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status)
 {
 	struct proto *prot = sk->sk_prot;
+
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
+		memcg_memory_allocated_add(sk->sk_cgrp, amt, parent_status);
+		/* update the root cgroup regardless */
+		atomic_long_add_return(amt, prot->memory_allocated);
+		return memcg_memory_allocated_read(sk->sk_cgrp);
+	}
+
 	return atomic_long_add_return(amt, prot->memory_allocated);
 }
 
 static inline void
-sk_memory_allocated_sub(struct sock *sk, int amt)
+sk_memory_allocated_sub(struct sock *sk, int amt, int parent_status)
 {
 	struct proto *prot = sk->sk_prot;
+
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp &&
+	    parent_status != OVER_LIMIT) /* Otherwise was uncharged already */
+		memcg_memory_allocated_sub(sk->sk_cgrp, amt);
+
 	atomic_long_sub(amt, prot->memory_allocated);
 }
 
 static inline void sk_sockets_allocated_dec(struct sock *sk)
 {
 	struct proto *prot = sk->sk_prot;
+
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
+		struct cg_proto *cg_proto = sk->sk_cgrp;
+
+		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
+			percpu_counter_dec(cg_proto->sockets_allocated);
+	}
+
 	percpu_counter_dec(prot->sockets_allocated);
 }
 
 static inline void sk_sockets_allocated_inc(struct sock *sk)
 {
 	struct proto *prot = sk->sk_prot;
+
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
+		struct cg_proto *cg_proto = sk->sk_cgrp;
+
+		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
+			percpu_counter_inc(cg_proto->sockets_allocated);
+	}
+
 	percpu_counter_inc(prot->sockets_allocated);
 }
 

@@ -934,6 +1075,9 @@ sk_sockets_allocated_read_positive(struct sock *sk)
 {
 	struct proto *prot = sk->sk_prot;
 
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
+		return percpu_counter_sum_positive(sk->sk_cgrp->sockets_allocated);
+
 	return percpu_counter_sum_positive(prot->sockets_allocated);
 }
 

@@ -379,7 +379,48 @@ enum mem_type {
 
 static void mem_cgroup_get(struct mem_cgroup *memcg);
 static void mem_cgroup_put(struct mem_cgroup *memcg);
-static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
+
+/* Writing them here to avoid exposing memcg's inner layout */
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_INET
+#include <net/sock.h>
+
+static bool mem_cgroup_is_root(struct mem_cgroup *memcg);
+void sock_update_memcg(struct sock *sk)
+{
+	/* A socket spends its whole life in the same cgroup */
+	if (sk->sk_cgrp) {
+		WARN_ON(1);
+		return;
+	}
+	if (static_branch(&memcg_socket_limit_enabled)) {
+		struct mem_cgroup *memcg;
+
+		BUG_ON(!sk->sk_prot->proto_cgroup);
+
+		rcu_read_lock();
+		memcg = mem_cgroup_from_task(current);
+		if (!mem_cgroup_is_root(memcg)) {
+			mem_cgroup_get(memcg);
+			sk->sk_cgrp = sk->sk_prot->proto_cgroup(memcg);
+		}
+		rcu_read_unlock();
+	}
+}
+EXPORT_SYMBOL(sock_update_memcg);
+
+void sock_release_memcg(struct sock *sk)
+{
+	if (static_branch(&memcg_socket_limit_enabled) && sk->sk_cgrp) {
+		struct mem_cgroup *memcg;
+		WARN_ON(!sk->sk_cgrp->memcg);
+		memcg = sk->sk_cgrp->memcg;
+		mem_cgroup_put(memcg);
+	}
+}
+#endif /* CONFIG_INET */
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
+
 static void drain_all_stock_async(struct mem_cgroup *memcg);
 
 static struct mem_cgroup_per_zone *

@@ -4932,12 +4973,13 @@ static void mem_cgroup_put(struct mem_cgroup *memcg)
 /*
  * Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled.
  */
-static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
+struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 {
 	if (!memcg->res.parent)
 		return NULL;
 	return mem_cgroup_from_res_counter(memcg->res.parent, res);
 }
+EXPORT_SYMBOL(parent_mem_cgroup);
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
 static void __init enable_swap_cgroup(void)

@@ -111,6 +111,7 @@
 #include <linux/init.h>
 #include <linux/highmem.h>
 #include <linux/user_namespace.h>
+#include <linux/jump_label.h>
 
 #include <asm/uaccess.h>
 #include <asm/system.h>

@@ -141,6 +142,9 @@
 static struct lock_class_key af_family_keys[AF_MAX];
 static struct lock_class_key af_family_slock_keys[AF_MAX];
 
+struct jump_label_key memcg_socket_limit_enabled;
+EXPORT_SYMBOL(memcg_socket_limit_enabled);
+
 /*
  * Make lock validator output more readable. (we pre-construct these
  * strings build-time, so that runtime initialization of socket

@@ -1677,23 +1681,27 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
 	struct proto *prot = sk->sk_prot;
 	int amt = sk_mem_pages(size);
 	long allocated;
+	int parent_status = UNDER_LIMIT;
 
 	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
 
-	allocated = sk_memory_allocated_add(sk, amt);
+	allocated = sk_memory_allocated_add(sk, amt, &parent_status);
 
 	/* Under limit. */
-	if (allocated <= sk_prot_mem_limits(sk, 0)) {
+	if (parent_status == UNDER_LIMIT &&
+			allocated <= sk_prot_mem_limits(sk, 0)) {
 		sk_leave_memory_pressure(sk);
 		return 1;
 	}
 
-	/* Under pressure. */
-	if (allocated > sk_prot_mem_limits(sk, 1))
+	/* Under pressure. (we or our parents) */
+	if ((parent_status > SOFT_LIMIT) ||
+			allocated > sk_prot_mem_limits(sk, 1))
 		sk_enter_memory_pressure(sk);
 
-	/* Over hard limit. */
-	if (allocated > sk_prot_mem_limits(sk, 2))
+	/* Over hard limit (we or our parents) */
+	if ((parent_status == OVER_LIMIT) ||
+			(allocated > sk_prot_mem_limits(sk, 2)))
 		goto suppress_allocation;
 
 	/* guarantee minimum buffer size under pressure */

@@ -1740,7 +1748,7 @@ suppress_allocation:
 	/* Alas. Undo changes. */
 	sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM;
 
-	sk_memory_allocated_sub(sk, amt);
+	sk_memory_allocated_sub(sk, amt, parent_status);
 
 	return 0;
 }

@@ -1753,7 +1761,7 @@ EXPORT_SYMBOL(__sk_mem_schedule);
 void __sk_mem_reclaim(struct sock *sk)
 {
 	sk_memory_allocated_sub(sk,
-				sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT);
+				sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT, 0);
 	sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1;
 
 	if (sk_under_memory_pressure(sk) &&

@@ -53,6 +53,7 @@
 #include <linux/security.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/memcontrol.h>
 
 #include <linux/filter.h>
 #include <linux/rculist_nulls.h>

@@ -863,6 +864,99 @@ static inline void sk_refcnt_debug_release(const struct sock *sk)
 #define sk_refcnt_debug_release(sk) do { } while (0)
 #endif /* SOCK_REFCNT_DEBUG */
 
+static inline bool sk_has_memory_pressure(const struct sock *sk)
+{
+	return sk->sk_prot->memory_pressure != NULL;
+}
+
+static inline bool sk_under_memory_pressure(const struct sock *sk)
+{
+	if (!sk->sk_prot->memory_pressure)
+		return false;
+	return !!*sk->sk_prot->memory_pressure;
+}
+
+static inline void sk_leave_memory_pressure(struct sock *sk)
+{
+	int *memory_pressure = sk->sk_prot->memory_pressure;
+
+	if (memory_pressure && *memory_pressure)
+		*memory_pressure = 0;
+}
+
+static inline void sk_enter_memory_pressure(struct sock *sk)
+{
+	if (sk->sk_prot->enter_memory_pressure)
+		sk->sk_prot->enter_memory_pressure(sk);
+}
+
+static inline long sk_prot_mem_limits(const struct sock *sk, int index)
+{
+	long *prot = sk->sk_prot->sysctl_mem;
+	return prot[index];
+}
+
+static inline long
+sk_memory_allocated(const struct sock *sk)
+{
+	struct proto *prot = sk->sk_prot;
+	return atomic_long_read(prot->memory_allocated);
+}
+
+static inline long
+sk_memory_allocated_add(struct sock *sk, int amt)
+{
+	struct proto *prot = sk->sk_prot;
+	return atomic_long_add_return(amt, prot->memory_allocated);
+}
+
+static inline void
+sk_memory_allocated_sub(struct sock *sk, int amt)
+{
+	struct proto *prot = sk->sk_prot;
+	atomic_long_sub(amt, prot->memory_allocated);
+}
+
+static inline void sk_sockets_allocated_dec(struct sock *sk)
+{
+	struct proto *prot = sk->sk_prot;
+	percpu_counter_dec(prot->sockets_allocated);
+}
+
+static inline void sk_sockets_allocated_inc(struct sock *sk)
+{
+	struct proto *prot = sk->sk_prot;
+	percpu_counter_inc(prot->sockets_allocated);
+}
+
+static inline int
+sk_sockets_allocated_read_positive(struct sock *sk)
+{
+	struct proto *prot = sk->sk_prot;
+
+	return percpu_counter_sum_positive(prot->sockets_allocated);
+}
+
+static inline int
+proto_sockets_allocated_sum_positive(struct proto *prot)
+{
+	return percpu_counter_sum_positive(prot->sockets_allocated);
+}
+
+static inline long
+proto_memory_allocated(struct proto *prot)
+{
+	return atomic_long_read(prot->memory_allocated);
+}
+
+static inline bool
+proto_memory_pressure(struct proto *prot)
+{
+	if (!prot->memory_pressure)
+		return false;
+	return !!*prot->memory_pressure;
+}
+
 
 #ifdef CONFIG_PROC_FS
 /* Called with local bh disabled */

@@ -1670,7 +1764,7 @@ static inline struct page *sk_stream_alloc_page(struct sock *sk)
 
 	page = alloc_pages(sk->sk_allocation, 0);
 	if (!page) {
-		sk->sk_prot->enter_memory_pressure(sk);
+		sk_enter_memory_pressure(sk);
 		sk_stream_moderate_sndbuf(sk);
 	}
 	return page;

@@ -44,6 +44,7 @@
 #include <net/dst.h>
 
 #include <linux/seq_file.h>
+#include <linux/memcontrol.h>
 
 extern struct inet_hashinfo tcp_hashinfo;
 

@@ -285,7 +286,7 @@ static inline bool tcp_too_many_orphans(struct sock *sk, int shift)
 	}
 
 	if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
-	    atomic_long_read(&tcp_memory_allocated) > sysctl_tcp_mem[2])
+	    sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2))
 		return true;
 	return false;
 }

@@ -1288,7 +1288,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
 		newsk->sk_wq = NULL;
 
 		if (newsk->sk_prot->sockets_allocated)
-			percpu_counter_inc(newsk->sk_prot->sockets_allocated);
+			sk_sockets_allocated_inc(newsk);
 
 		if (sock_flag(newsk, SOCK_TIMESTAMP) ||
 		    sock_flag(newsk, SOCK_TIMESTAMPING_RX_SOFTWARE))

@@ -1679,28 +1679,28 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
 	long allocated;
 
 	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
-	allocated = atomic_long_add_return(amt, prot->memory_allocated);
+
+	allocated = sk_memory_allocated_add(sk, amt);
 
 	/* Under limit. */
-	if (allocated <= prot->sysctl_mem[0]) {
-		if (prot->memory_pressure && *prot->memory_pressure)
-			*prot->memory_pressure = 0;
+	if (allocated <= sk_prot_mem_limits(sk, 0)) {
+		sk_leave_memory_pressure(sk);
 		return 1;
 	}
 
 	/* Under pressure. */
-	if (allocated > prot->sysctl_mem[1])
-		if (prot->enter_memory_pressure)
-			prot->enter_memory_pressure(sk);
+	if (allocated > sk_prot_mem_limits(sk, 1))
+		sk_enter_memory_pressure(sk);
 
 	/* Over hard limit. */
-	if (allocated > prot->sysctl_mem[2])
+	if (allocated > sk_prot_mem_limits(sk, 2))
 		goto suppress_allocation;
 
 	/* guarantee minimum buffer size under pressure */
 	if (kind == SK_MEM_RECV) {
 		if (atomic_read(&sk->sk_rmem_alloc) < prot->sysctl_rmem[0])
 			return 1;
+
 	} else { /* SK_MEM_SEND */
 		if (sk->sk_type == SOCK_STREAM) {
 			if (sk->sk_wmem_queued < prot->sysctl_wmem[0])

@@ -1710,13 +1710,13 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
 				return 1;
 	}
 
-	if (prot->memory_pressure) {
+	if (sk_has_memory_pressure(sk)) {
 		int alloc;
 
-		if (!*prot->memory_pressure)
+		if (!sk_under_memory_pressure(sk))
 			return 1;
-		alloc = percpu_counter_read_positive(prot->sockets_allocated);
-		if (prot->sysctl_mem[2] > alloc *
+		alloc = sk_sockets_allocated_read_positive(sk);
+		if (sk_prot_mem_limits(sk, 2) > alloc *
 		    sk_mem_pages(sk->sk_wmem_queued +
 				 atomic_read(&sk->sk_rmem_alloc) +
 				 sk->sk_forward_alloc))

@@ -1739,7 +1739,9 @@ suppress_allocation:
 
 	/* Alas. Undo changes. */
 	sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM;
-	atomic_long_sub(amt, prot->memory_allocated);
+
+	sk_memory_allocated_sub(sk, amt);
+
 	return 0;
 }
 EXPORT_SYMBOL(__sk_mem_schedule);

@@ -1750,15 +1752,13 @@ EXPORT_SYMBOL(__sk_mem_schedule);
  */
 void __sk_mem_reclaim(struct sock *sk)
 {
-	struct proto *prot = sk->sk_prot;
-
-	atomic_long_sub(sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT,
-		   prot->memory_allocated);
+	sk_memory_allocated_sub(sk,
+				sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT);
 	sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1;
 
-	if (prot->memory_pressure && *prot->memory_pressure &&
-	    (atomic_long_read(prot->memory_allocated) < prot->sysctl_mem[0]))
-		*prot->memory_pressure = 0;
+	if (sk_under_memory_pressure(sk) &&
+	    (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
+		sk_leave_memory_pressure(sk);
 }
 EXPORT_SYMBOL(__sk_mem_reclaim);
 

@@ -2474,16 +2474,27 @@ static char proto_method_implemented(const void *method)
 {
 	return method == NULL ? 'n' : 'y';
 }
+static long sock_prot_memory_allocated(struct proto *proto)
+{
+	return proto->memory_allocated != NULL ? proto_memory_allocated(proto): -1L;
+}
+
+static char *sock_prot_memory_pressure(struct proto *proto)
+{
+	return proto->memory_pressure != NULL ?
+	proto_memory_pressure(proto) ? "yes" : "no" : "NI";
+}
 
 static void proto_seq_printf(struct seq_file *seq, struct proto *proto)
 {
+
 	seq_printf(seq, "%-9s %4u %6d  %6ld   %-3s %6u   %-3s  %-10s "
 			"%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n",
 		   proto->name,
 		   proto->obj_size,
 		   sock_prot_inuse_get(seq_file_net(seq), proto),
-		   proto->memory_allocated != NULL ? atomic_long_read(proto->memory_allocated) : -1L,
-		   proto->memory_pressure != NULL ? *proto->memory_pressure ? "yes" : "no" : "NI",
+		   sock_prot_memory_allocated(proto),
+		   sock_prot_memory_pressure(proto),
 		   proto->max_header,
 		   proto->slab == NULL ? "no" : "yes",
 		   module_name(proto->owner),

@@ -56,17 +56,17 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
 
 	local_bh_disable();
 	orphans = percpu_counter_sum_positive(&tcp_orphan_count);
-	sockets = percpu_counter_sum_positive(&tcp_sockets_allocated);
+	sockets = proto_sockets_allocated_sum_positive(&tcp_prot);
 	local_bh_enable();
 
 	socket_seq_show(seq);
 	seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n",
 		   sock_prot_inuse_get(net, &tcp_prot), orphans,
 		   tcp_death_row.tw_count, sockets,
-		   atomic_long_read(&tcp_memory_allocated));
+		   proto_memory_allocated(&tcp_prot));
 	seq_printf(seq, "UDP: inuse %d mem %ld\n",
 		   sock_prot_inuse_get(net, &udp_prot),
-		   atomic_long_read(&udp_memory_allocated));
+		   proto_memory_allocated(&udp_prot));
 	seq_printf(seq, "UDPLITE: inuse %d\n",
 		   sock_prot_inuse_get(net, &udplite_prot));
 	seq_printf(seq, "RAW: inuse %d\n",

@@ -322,7 +322,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
 	/* Check #1 */
 	if (tp->rcv_ssthresh < tp->window_clamp &&
 	    (int)tp->rcv_ssthresh < tcp_space(sk) &&
-	    !tcp_memory_pressure) {
+	    !sk_under_memory_pressure(sk)) {
 		int incr;
 
 		/* Check #2. Increase window, if skb with such overhead

@@ -411,8 +411,8 @@ static void tcp_clamp_window(struct sock *sk)
 
 	if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
-	    !tcp_memory_pressure &&
-	    atomic_long_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) {
+	    !sk_under_memory_pressure(sk) &&
+	    sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
 		sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
 				    sysctl_tcp_rmem[2]);
 	}

@@ -4864,7 +4864,7 @@ static int tcp_prune_queue(struct sock *sk)
 
 	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
 		tcp_clamp_window(sk);
-	else if (tcp_memory_pressure)
+	else if (sk_under_memory_pressure(sk))
 		tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
 
 	tcp_collapse_ofo_queue(sk);

@@ -4930,11 +4930,11 @@ static int tcp_should_expand_sndbuf(const struct sock *sk)
 		return 0;
 
 	/* If we are under global TCP memory pressure, do not expand.  */
-	if (tcp_memory_pressure)
+	if (sk_under_memory_pressure(sk))
 		return 0;
 
 	/* If we are under soft global TCP memory pressure, do not expand.  */
-	if (atomic_long_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0])
+	if (sk_memory_allocated(sk) >= sk_prot_mem_limits(sk, 0))
 		return 0;
 
 	/* If we filled the congestion window, do not expand.  */

@@ -1915,7 +1915,7 @@ static int tcp_v4_init_sock(struct sock *sk)
 	sk->sk_rcvbuf = sysctl_tcp_rmem[1];
 
 	local_bh_disable();
-	percpu_counter_inc(&tcp_sockets_allocated);
+	sk_sockets_allocated_inc(sk);
 	local_bh_enable();
 
 	return 0;

@@ -1971,7 +1971,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
 		tp->cookie_values = NULL;
 	}
 
-	percpu_counter_dec(&tcp_sockets_allocated);
+	sk_sockets_allocated_dec(sk);
 }
 EXPORT_SYMBOL(tcp_v4_destroy_sock);
 

@@ -1919,7 +1919,7 @@ u32 __tcp_select_window(struct sock *sk)
 	if (free_space < (full_space >> 1)) {
 		icsk->icsk_ack.quick = 0;
 
-		if (tcp_memory_pressure)
+		if (sk_under_memory_pressure(sk))
 			tp->rcv_ssthresh = min(tp->rcv_ssthresh,
 					       4U * tp->advmss);
 

@@ -261,7 +261,7 @@ static void tcp_delack_timer(unsigned long data)
 	}
 
 out:
-	if (tcp_memory_pressure)
+	if (sk_under_memory_pressure(sk))
 		sk_mem_reclaim(sk);
 out_unlock:
 	bh_unlock_sock(sk);

@@ -1995,7 +1995,7 @@ static int tcp_v6_init_sock(struct sock *sk)
 	sk->sk_rcvbuf = sysctl_tcp_rmem[1];
 
 	local_bh_disable();
-	percpu_counter_inc(&tcp_sockets_allocated);
+	sk_sockets_allocated_inc(sk);
 	local_bh_enable();
 
 	return 0;

@@ -78,6 +78,7 @@ Brief summary of control files.
 
  memory.independent_kmem_limit	 # select whether or not kernel memory limits are
 				   independent of user limits
+ memory.kmem.tcp.limit_in_bytes  # set/show hard limit for tcp buf memory
 
 1. History
 

@@ -14,4 +14,6 @@ struct tcp_memcontrol {
 struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg);
 int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss);
 void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss);
+unsigned long long tcp_max_memory(const struct mem_cgroup *memcg);
+void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx);
 #endif /* _TCP_MEMCG_H */

@@ -24,6 +24,7 @@
 #include <net/cipso_ipv4.h>
 #include <net/inet_frag.h>
 #include <net/ping.h>
+#include <net/tcp_memcontrol.h>
 
 static int zero;
 static int tcp_retr1_max = 255;

@@ -182,6 +183,9 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write,
 	int ret;
 	unsigned long vec[3];
 	struct net *net = current->nsproxy->net_ns;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+	struct mem_cgroup *memcg;
+#endif
 
 	ctl_table tmp = {
 		.data = &vec,

@@ -198,6 +202,16 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write,
 	if (ret)
 		return ret;
 
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+	rcu_read_lock();
+	memcg = mem_cgroup_from_task(current);
+
+	tcp_prot_mem(memcg, vec[0], 0);
+	tcp_prot_mem(memcg, vec[1], 1);
+	tcp_prot_mem(memcg, vec[2], 2);
+	rcu_read_unlock();
+#endif
+
 	net->ipv4.sysctl_tcp_mem[0] = vec[0];
 	net->ipv4.sysctl_tcp_mem[1] = vec[1];
 	net->ipv4.sysctl_tcp_mem[2] = vec[2];

@@ -6,6 +6,19 @@
 #include <linux/memcontrol.h>
 #include <linux/module.h>
 
+static u64 tcp_cgroup_read(struct cgroup *cont, struct cftype *cft);
+static int tcp_cgroup_write(struct cgroup *cont, struct cftype *cft,
+			    const char *buffer);
+
+static struct cftype tcp_files[] = {
+	{
+		.name = "kmem.tcp.limit_in_bytes",
+		.write_string = tcp_cgroup_write,
+		.read_u64 = tcp_cgroup_read,
+		.private = RES_LIMIT,
+	},
+};
+
 static inline struct tcp_memcontrol *tcp_from_cgproto(struct cg_proto *cg_proto)
 {
 	return container_of(cg_proto, struct tcp_memcontrol, cg_proto);

@@ -34,7 +47,7 @@ int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
 
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)
-		return 0;
+		goto create_files;
 
 	tcp = tcp_from_cgproto(cg_proto);
 

@@ -57,7 +70,9 @@ int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
 	cg_proto->sockets_allocated = &tcp->tcp_sockets_allocated;
 	cg_proto->memcg = memcg;
 
-	return 0;
+create_files:
+	return cgroup_add_files(cgrp, ss, tcp_files,
+				ARRAY_SIZE(tcp_files));
 }
 EXPORT_SYMBOL(tcp_init_cgroup);
 

@@ -66,6 +81,7 @@ void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
 	struct cg_proto *cg_proto;
 	struct tcp_memcontrol *tcp;
+	u64 val;
 
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)

@@ -73,5 +89,122 @@ void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
 
 	tcp = tcp_from_cgproto(cg_proto);
 	percpu_counter_destroy(&tcp->tcp_sockets_allocated);
+
+	val = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_USAGE);
+
+	if (val != RESOURCE_MAX)
+		jump_label_dec(&memcg_socket_limit_enabled);
 }
 EXPORT_SYMBOL(tcp_destroy_cgroup);
+
+static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
+{
+	struct net *net = current->nsproxy->net_ns;
+	struct tcp_memcontrol *tcp;
+	struct cg_proto *cg_proto;
+	u64 old_lim;
+	int i;
+	int ret;
+
+	cg_proto = tcp_prot.proto_cgroup(memcg);
+	if (!cg_proto)
+		return -EINVAL;
+
+	if (val > RESOURCE_MAX)
+		val = RESOURCE_MAX;
+
+	tcp = tcp_from_cgproto(cg_proto);
+
+	old_lim = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT);
+	ret = res_counter_set_limit(&tcp->tcp_memory_allocated, val);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < 3; i++)
+		tcp->tcp_prot_mem[i] = min_t(long, val >> PAGE_SHIFT,
+					     net->ipv4.sysctl_tcp_mem[i]);
+
+	if (val == RESOURCE_MAX && old_lim != RESOURCE_MAX)
+		jump_label_dec(&memcg_socket_limit_enabled);
+	else if (old_lim == RESOURCE_MAX && val != RESOURCE_MAX)
+		jump_label_inc(&memcg_socket_limit_enabled);
+
+	return 0;
+}
+
+static int tcp_cgroup_write(struct cgroup *cont, struct cftype *cft,
+			    const char *buffer)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	unsigned long long val;
+	int ret = 0;
+
+	switch (cft->private) {
+	case RES_LIMIT:
+		/* see memcontrol.c */
+		ret = res_counter_memparse_write_strategy(buffer, &val);
+		if (ret)
+			break;
+		ret = tcp_update_limit(memcg, val);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	return ret;
+}
+
+static u64 tcp_read_stat(struct mem_cgroup *memcg, int type, u64 default_val)
+{
+	struct tcp_memcontrol *tcp;
+	struct cg_proto *cg_proto;
+
+	cg_proto = tcp_prot.proto_cgroup(memcg);
+	if (!cg_proto)
+		return default_val;
+
+	tcp = tcp_from_cgproto(cg_proto);
+	return res_counter_read_u64(&tcp->tcp_memory_allocated, type);
+}
+
+static u64 tcp_cgroup_read(struct cgroup *cont, struct cftype *cft)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	u64 val;
+
+	switch (cft->private) {
+	case RES_LIMIT:
+		val = tcp_read_stat(memcg, RES_LIMIT, RESOURCE_MAX);
+		break;
+	default:
+		BUG();
+	}
+	return val;
+}
+
+unsigned long long tcp_max_memory(const struct mem_cgroup *memcg)
+{
+	struct tcp_memcontrol *tcp;
+	struct cg_proto *cg_proto;
+
+	cg_proto = tcp_prot.proto_cgroup((struct mem_cgroup *)memcg);
+	if (!cg_proto)
+		return 0;
+
+	tcp = tcp_from_cgproto(cg_proto);
+	return res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT);
+}
+
+void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx)
+{
+	struct tcp_memcontrol *tcp;
+	struct cg_proto *cg_proto;
+
+	cg_proto = tcp_prot.proto_cgroup(memcg);
+	if (!cg_proto)
+		return;
+
+	tcp = tcp_from_cgproto(cg_proto);
+
+	tcp->tcp_prot_mem[idx] = val;
+}