Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

No conflicts!

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/bootconfig.h

@@ -110,7 +110,7 @@ static inline __init bool xbc_node_is_leaf(struct xbc_node *node)
 }
 
 /* Tree-based key-value access APIs */
-struct xbc_node * __init xbc_node_find_child(struct xbc_node *parent,
+struct xbc_node * __init xbc_node_find_subkey(struct xbc_node *parent,
 					     const char *key);
 
 const char * __init xbc_node_find_value(struct xbc_node *parent,
@@ -148,7 +148,7 @@ xbc_find_value(const char *key, struct xbc_node **vnode)
  */
 static inline struct xbc_node * __init xbc_find_node(const char *key)
 {
-	return xbc_node_find_child(NULL, key);
+	return xbc_node_find_subkey(NULL, key);
 }
 
 /**

include/linux/cacheinfo.h

@@ -79,24 +79,6 @@ struct cpu_cacheinfo {
 	bool cpu_map_populated;
 };
 
-/*
- * Helpers to make sure "func" is executed on the cpu whose cache
- * attributes are being detected
- */
-#define DEFINE_SMP_CALL_CACHE_FUNCTION(func)			\
-static inline void _##func(void *ret)				\
-{								\
-	int cpu = smp_processor_id();				\
-	*(int *)ret = __##func(cpu);				\
-}								\
-								\
-int func(unsigned int cpu)					\
-{								\
-	int ret;						\
-	smp_call_function_single(cpu, _##func, &ret, true);	\
-	return ret;						\
-}
-
 struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu);
 int init_cache_level(unsigned int cpu);
 int populate_cache_leaves(unsigned int cpu);

include/linux/ceph/ceph_fs.h

@@ -299,6 +299,7 @@ enum {
 	CEPH_SESSION_FLUSHMSG_ACK,
 	CEPH_SESSION_FORCE_RO,
 	CEPH_SESSION_REJECT,
+	CEPH_SESSION_REQUEST_FLUSH_MDLOG,
 };
 
 extern const char *ceph_session_op_name(int op);

include/linux/cgroup-defs.h

@@ -752,107 +752,54 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {}
  * sock_cgroup_data is embedded at sock->sk_cgrp_data and contains
  * per-socket cgroup information except for memcg association.
  *
- * On legacy hierarchies, net_prio and net_cls controllers directly set
- * attributes on each sock which can then be tested by the network layer.
- * On the default hierarchy, each sock is associated with the cgroup it was
- * created in and the networking layer can match the cgroup directly.
- *
- * To avoid carrying all three cgroup related fields separately in sock,
- * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer.
- * On boot, sock_cgroup_data records the cgroup that the sock was created
- * in so that cgroup2 matches can be made; however, once either net_prio or
- * net_cls starts being used, the area is overridden to carry prioidx and/or
- * classid.  The two modes are distinguished by whether the lowest bit is
- * set.  Clear bit indicates cgroup pointer while set bit prioidx and
- * classid.
- *
- * While userland may start using net_prio or net_cls at any time, once
- * either is used, cgroup2 matching no longer works.  There is no reason to
- * mix the two and this is in line with how legacy and v2 compatibility is
- * handled.  On mode switch, cgroup references which are already being
- * pointed to by socks may be leaked.  While this can be remedied by adding
- * synchronization around sock_cgroup_data, given that the number of leaked
- * cgroups is bound and highly unlikely to be high, this seems to be the
- * better trade-off.
+ * On legacy hierarchies, net_prio and net_cls controllers directly
+ * set attributes on each sock which can then be tested by the network
+ * layer. On the default hierarchy, each sock is associated with the
+ * cgroup it was created in and the networking layer can match the
+ * cgroup directly.
  */
 struct sock_cgroup_data {
-	union {
-#ifdef __LITTLE_ENDIAN
-		struct {
-			u8	is_data : 1;
-			u8	no_refcnt : 1;
-			u8	unused : 6;
-			u8	padding;
-			u16	prioidx;
-			u32	classid;
-		} __packed;
-#else
-		struct {
-			u32	classid;
-			u16	prioidx;
-			u8	padding;
-			u8	unused : 6;
-			u8	no_refcnt : 1;
-			u8	is_data : 1;
-		} __packed;
+	struct cgroup	*cgroup; /* v2 */
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	u32		classid; /* v1 */
+#endif
+#ifdef CONFIG_CGROUP_NET_PRIO
+	u16		prioidx; /* v1 */
 #endif
-		u64		val;
-	};
 };
 
-/*
- * There's a theoretical window where the following accessors race with
- * updaters and return part of the previous pointer as the prioidx or
- * classid.  Such races are short-lived and the result isn't critical.
- */
 static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd)
 {
-	/* fallback to 1 which is always the ID of the root cgroup */
-	return (skcd->is_data & 1) ? skcd->prioidx : 1;
+#ifdef CONFIG_CGROUP_NET_PRIO
+	return READ_ONCE(skcd->prioidx);
+#else
+	return 1;
+#endif
 }
 
 static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd)
 {
-	/* fallback to 0 which is the unconfigured default classid */
-	return (skcd->is_data & 1) ? skcd->classid : 0;
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	return READ_ONCE(skcd->classid);
+#else
+	return 0;
+#endif
 }
 
-/*
- * If invoked concurrently, the updaters may clobber each other.  The
- * caller is responsible for synchronization.
- */
 static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd,
 					   u16 prioidx)
 {
-	struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }};
-
-	if (sock_cgroup_prioidx(&skcd_buf) == prioidx)
-		return;
-
-	if (!(skcd_buf.is_data & 1)) {
-		skcd_buf.val = 0;
-		skcd_buf.is_data = 1;
-	}
-
-	skcd_buf.prioidx = prioidx;
-	WRITE_ONCE(skcd->val, skcd_buf.val);	/* see sock_cgroup_ptr() */
+#ifdef CONFIG_CGROUP_NET_PRIO
+	WRITE_ONCE(skcd->prioidx, prioidx);
+#endif
 }
 
 static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd,
 					   u32 classid)
 {
-	struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }};
-
-	if (sock_cgroup_classid(&skcd_buf) == classid)
-		return;
-
-	if (!(skcd_buf.is_data & 1)) {
-		skcd_buf.val = 0;
-		skcd_buf.is_data = 1;
-	}
-
-	skcd_buf.classid = classid;
-	WRITE_ONCE(skcd->val, skcd_buf.val);	/* see sock_cgroup_ptr() */
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	WRITE_ONCE(skcd->classid, classid);
+#endif
 }
 
 #else	/* CONFIG_SOCK_CGROUP_DATA */

include/linux/cgroup.h

@@ -829,33 +829,13 @@ static inline void cgroup_account_cputime_field(struct task_struct *task,
  */
 #ifdef CONFIG_SOCK_CGROUP_DATA
 
-#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
-extern spinlock_t cgroup_sk_update_lock;
-#endif
-
-void cgroup_sk_alloc_disable(void);
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd);
 void cgroup_sk_clone(struct sock_cgroup_data *skcd);
 void cgroup_sk_free(struct sock_cgroup_data *skcd);
 
 static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
 {
-#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
-	unsigned long v;
-
-	/*
-	 * @skcd->val is 64bit but the following is safe on 32bit too as we
-	 * just need the lower ulong to be written and read atomically.
-	 */
-	v = READ_ONCE(skcd->val);
-
-	if (v & 3)
-		return &cgrp_dfl_root.cgrp;
-
-	return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp;
-#else
-	return (struct cgroup *)(unsigned long)skcd->val;
-#endif
+	return skcd->cgroup;
 }
 
 #else	/* CONFIG_CGROUP_DATA */

include/linux/compat.h

@@ -395,14 +395,6 @@ struct compat_kexec_segment;
 struct compat_mq_attr;
 struct compat_msgbuf;
 
-#define BITS_PER_COMPAT_LONG    (8*sizeof(compat_long_t))
-
-#define BITS_TO_COMPAT_LONGS(bits) DIV_ROUND_UP(bits, BITS_PER_COMPAT_LONG)
-
-long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask,
-		       unsigned long bitmap_size);
-long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask,
-		       unsigned long bitmap_size);
 void copy_siginfo_to_external32(struct compat_siginfo *to,
 		const struct kernel_siginfo *from);
 int copy_siginfo_from_user32(kernel_siginfo_t *to,
@@ -519,8 +511,6 @@ extern long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 
 struct epoll_event;	/* fortunately, this one is fixed-layout */
 
-extern void __user *compat_alloc_user_space(unsigned long len);
-
 int compat_restore_altstack(const compat_stack_t __user *uss);
 int __compat_save_altstack(compat_stack_t __user *, unsigned long);
 #define unsafe_compat_save_altstack(uss, sp, label) do { \
@@ -807,26 +797,6 @@ asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr
 /* mm/fadvise.c: No generic prototype for fadvise64_64 */
 
 /* mm/, CONFIG_MMU only */
-asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
-				 compat_ulong_t mode,
-				 compat_ulong_t __user *nmask,
-				 compat_ulong_t maxnode, compat_ulong_t flags);
-asmlinkage long compat_sys_get_mempolicy(int __user *policy,
-					 compat_ulong_t __user *nmask,
-					 compat_ulong_t maxnode,
-					 compat_ulong_t addr,
-					 compat_ulong_t flags);
-asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask,
-					 compat_ulong_t maxnode);
-asmlinkage long compat_sys_migrate_pages(compat_pid_t pid,
-		compat_ulong_t maxnode, const compat_ulong_t __user *old_nodes,
-		const compat_ulong_t __user *new_nodes);
-asmlinkage long compat_sys_move_pages(pid_t pid, compat_ulong_t nr_pages,
-				      __u32 __user *pages,
-				      const int __user *nodes,
-				      int __user *status,
-				      int flags);
-
 asmlinkage long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid,
 					compat_pid_t pid, int sig,
 					struct compat_siginfo __user *uinfo);
@@ -976,6 +946,15 @@ static inline bool in_compat_syscall(void) { return false; }
 
 #endif /* CONFIG_COMPAT */
 
+#define BITS_PER_COMPAT_LONG    (8*sizeof(compat_long_t))
+
+#define BITS_TO_COMPAT_LONGS(bits) DIV_ROUND_UP(bits, BITS_PER_COMPAT_LONG)
+
+long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask,
+		       unsigned long bitmap_size);
+long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask,
+		       unsigned long bitmap_size);
+
 /*
  * Some legacy ABIs like the i386 one use less than natural alignment for 64-bit
  * types, and will need special compat treatment for that.  Most architectures

include/linux/compiler-clang.h

@@ -62,19 +62,6 @@
 #define __no_sanitize_coverage
 #endif
 
-/*
- * Not all versions of clang implement the type-generic versions
- * of the builtin overflow checkers. Fortunately, clang implements
- * __has_builtin allowing us to avoid awkward version
- * checks. Unfortunately, we don't know which version of gcc clang
- * pretends to be, so the macro may or may not be defined.
- */
-#if __has_builtin(__builtin_mul_overflow) && \
-    __has_builtin(__builtin_add_overflow) && \
-    __has_builtin(__builtin_sub_overflow)
-#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
-#endif
-
 #if __has_feature(shadow_call_stack)
 # define __noscs	__attribute__((__no_sanitize__("shadow-call-stack")))
 #endif

include/linux/compiler-gcc.h

@@ -43,9 +43,6 @@
 
 #define __compiletime_object_size(obj) __builtin_object_size(obj, 0)
 
-#define __compiletime_warning(message) __attribute__((__warning__(message)))
-#define __compiletime_error(message) __attribute__((__error__(message)))
-
 #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__)
 #define __latent_entropy __attribute__((latent_entropy))
 #endif
@@ -98,10 +95,8 @@
 
 #if GCC_VERSION >= 70000
 #define KASAN_ABI_VERSION 5
-#elif GCC_VERSION >= 50000
+#else
 #define KASAN_ABI_VERSION 4
-#elif GCC_VERSION >= 40902
-#define KASAN_ABI_VERSION 3
 #endif
 
 #if __has_attribute(__no_sanitize_address__)
@@ -128,10 +123,6 @@
 #define __no_sanitize_coverage
 #endif
 
-#if GCC_VERSION >= 50100
-#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
-#endif
-
 /*
  * Turn individual warnings and errors on and off locally, depending
  * on version.

include/linux/compiler.h

@@ -188,6 +188,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
     (typeof(ptr)) (__ptr + (off)); })
 #endif
 
+#define absolute_pointer(val)	RELOC_HIDE((void *)(val), 0)
+
 #ifndef OPTIMIZER_HIDE_VAR
 /* Make the optimizer believe the variable can be manipulated arbitrarily. */
 #define OPTIMIZER_HIDE_VAR(var)						\

include/linux/compiler_attributes.h

@@ -20,26 +20,6 @@
  * Provide links to the documentation of each supported compiler, if it exists.
  */
 
-/*
- * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17.
- * In the meantime, to support gcc < 5, we implement __has_attribute
- * by hand.
- */
-#ifndef __has_attribute
-# define __has_attribute(x) __GCC4_has_attribute_##x
-# define __GCC4_has_attribute___assume_aligned__      1
-# define __GCC4_has_attribute___copy__                0
-# define __GCC4_has_attribute___designated_init__     0
-# define __GCC4_has_attribute___externally_visible__  1
-# define __GCC4_has_attribute___no_caller_saved_registers__ 0
-# define __GCC4_has_attribute___noclone__             1
-# define __GCC4_has_attribute___no_profile_instrument_function__ 0
-# define __GCC4_has_attribute___nonstring__           0
-# define __GCC4_has_attribute___no_sanitize_address__ 1
-# define __GCC4_has_attribute___no_sanitize_undefined__ 1
-# define __GCC4_has_attribute___fallthrough__         0
-#endif
-
 /*
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alias-function-attribute
  */
@@ -74,7 +54,6 @@
  * compiler should see some alignment anyway, when the return value is
  * massaged by 'flags = ptr & 3; ptr &= ~3;').
  *
- * Optional: only supported since gcc >= 4.9
  * Optional: not supported by icc
  *
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-assume_005faligned-function-attribute
@@ -137,6 +116,17 @@
 # define __designated_init
 #endif
 
+/*
+ * Optional: only supported since clang >= 14.0
+ *
+ *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-error-function-attribute
+ */
+#if __has_attribute(__error__)
+# define __compiletime_error(msg)       __attribute__((__error__(msg)))
+#else
+# define __compiletime_error(msg)
+#endif
+
 /*
  * Optional: not supported by clang
  *
@@ -298,6 +288,17 @@
  */
 #define __must_check                    __attribute__((__warn_unused_result__))
 
+/*
+ * Optional: only supported since clang >= 14.0
+ *
+ *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-warning-function-attribute
+ */
+#if __has_attribute(__warning__)
+# define __compiletime_warning(msg)     __attribute__((__warning__(msg)))
+#else
+# define __compiletime_warning(msg)
+#endif
+
 /*
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-weak-function-attribute
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-weak-variable-attribute

include/linux/compiler_types.h

@@ -294,12 +294,6 @@ struct ftrace_likely_data {
 #ifndef __compiletime_object_size
 # define __compiletime_object_size(obj) -1
 #endif
-#ifndef __compiletime_warning
-# define __compiletime_warning(message)
-#endif
-#ifndef __compiletime_error
-# define __compiletime_error(message)
-#endif
 
 #ifdef __OPTIMIZE__
 # define __compiletime_assert(condition, msg, prefix, suffix)		\

include/linux/cpu.h

@@ -143,12 +143,6 @@ static inline int remove_cpu(unsigned int cpu) { return -EPERM; }
 static inline void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { }
 #endif	/* !CONFIG_HOTPLUG_CPU */
 
-/* Wrappers which go away once all code is converted */
-static inline void cpu_hotplug_begin(void) { cpus_write_lock(); }
-static inline void cpu_hotplug_done(void) { cpus_write_unlock(); }
-static inline void get_online_cpus(void) { cpus_read_lock(); }
-static inline void put_online_cpus(void) { cpus_read_unlock(); }
-
 #ifdef CONFIG_PM_SLEEP_SMP
 extern int freeze_secondary_cpus(int primary);
 extern void thaw_secondary_cpus(void);

include/linux/cpufreq.h

@@ -9,10 +9,14 @@
 #define _LINUX_CPUFREQ_H
 
 #include <linux/clk.h>
+#include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/completion.h>
 #include <linux/kobject.h>
 #include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pm_opp.h>
 #include <linux/pm_qos.h>
 #include <linux/spinlock.h>
 #include <linux/sysfs.h>
@@ -365,14 +369,17 @@ struct cpufreq_driver {
 	int		(*suspend)(struct cpufreq_policy *policy);
 	int		(*resume)(struct cpufreq_policy *policy);
 
-	/* Will be called after the driver is fully initialized */
-	void		(*ready)(struct cpufreq_policy *policy);
-
 	struct freq_attr **attr;
 
 	/* platform specific boost support code */
 	bool		boost_enabled;
 	int		(*set_boost)(struct cpufreq_policy *policy, int state);
+
+	/*
+	 * Set by drivers that want to register with the energy model after the
+	 * policy is properly initialized, but before the governor is started.
+	 */
+	void		(*register_em)(struct cpufreq_policy *policy);
 };
 
 /* flags */
@@ -995,6 +1002,55 @@ static inline int cpufreq_table_count_valid_entries(const struct cpufreq_policy
 
 	return count;
 }
+
+static inline int parse_perf_domain(int cpu, const char *list_name,
+				    const char *cell_name)
+{
+	struct device_node *cpu_np;
+	struct of_phandle_args args;
+	int ret;
+
+	cpu_np = of_cpu_device_node_get(cpu);
+	if (!cpu_np)
+		return -ENODEV;
+
+	ret = of_parse_phandle_with_args(cpu_np, list_name, cell_name, 0,
+					 &args);
+	if (ret < 0)
+		return ret;
+
+	of_node_put(cpu_np);
+
+	return args.args[0];
+}
+
+static inline int of_perf_domain_get_sharing_cpumask(int pcpu, const char *list_name,
+						     const char *cell_name, struct cpumask *cpumask)
+{
+	int target_idx;
+	int cpu, ret;
+
+	ret = parse_perf_domain(pcpu, list_name, cell_name);
+	if (ret < 0)
+		return ret;
+
+	target_idx = ret;
+	cpumask_set_cpu(pcpu, cpumask);
+
+	for_each_possible_cpu(cpu) {
+		if (cpu == pcpu)
+			continue;
+
+		ret = parse_perf_domain(pcpu, list_name, cell_name);
+		if (ret < 0)
+			continue;
+
+		if (target_idx == ret)
+			cpumask_set_cpu(cpu, cpumask);
+	}
+
+	return target_idx;
+}
 #else
 static inline int cpufreq_boost_trigger_state(int state)
 {
@@ -1014,6 +1070,12 @@ static inline bool policy_has_boost_freq(struct cpufreq_policy *policy)
 {
 	return false;
 }
+
+static inline int of_perf_domain_get_sharing_cpumask(int pcpu, const char *list_name,
+						     const char *cell_name, struct cpumask *cpumask)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
@@ -1035,7 +1097,6 @@ void arch_set_freq_scale(const struct cpumask *cpus,
 {
 }
 #endif
-
 /* the following are really really optional */
 extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs;
 extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs;
@@ -1046,4 +1107,10 @@ unsigned int cpufreq_generic_get(unsigned int cpu);
 void cpufreq_generic_init(struct cpufreq_policy *policy,
 		struct cpufreq_frequency_table *table,
 		unsigned int transition_latency);
+
+static inline void cpufreq_register_em_with_opp(struct cpufreq_policy *policy)
+{
+	dev_pm_opp_of_register_em(get_cpu_device(policy->cpu),
+				  policy->related_cpus);
+}
 #endif /* _LINUX_CPUFREQ_H */

include/linux/cpuhotplug.h

@@ -22,8 +22,42 @@
  *              AP_ACTIVE			AP_ACTIVE
  */
 
+/*
+ * CPU hotplug states. The state machine invokes the installed state
+ * startup callbacks sequentially from CPUHP_OFFLINE + 1 to CPUHP_ONLINE
+ * during a CPU online operation. During a CPU offline operation the
+ * installed teardown callbacks are invoked in the reverse order from
+ * CPU_ONLINE - 1 down to CPUHP_OFFLINE.
+ *
+ * The state space has three sections: PREPARE, STARTING and ONLINE.
+ *
+ * PREPARE: The callbacks are invoked on a control CPU before the
+ * hotplugged CPU is started up or after the hotplugged CPU has died.
+ *
+ * STARTING: The callbacks are invoked on the hotplugged CPU from the low level
+ * hotplug startup/teardown code with interrupts disabled.
+ *
+ * ONLINE: The callbacks are invoked on the hotplugged CPU from the per CPU
+ * hotplug thread with interrupts and preemption enabled.
+ *
+ * Adding explicit states to this enum is only necessary when:
+ *
+ * 1) The state is within the STARTING section
+ *
+ * 2) The state has ordering constraints vs. other states in the
+ *    same section.
+ *
+ * If neither #1 nor #2 apply, please use the dynamic state space when
+ * setting up a state by using CPUHP_PREPARE_DYN or CPUHP_PREPARE_ONLINE
+ * for the @state argument of the setup function.
+ *
+ * See Documentation/core-api/cpu_hotplug.rst for further information and
+ * examples.
+ */
 enum cpuhp_state {
 	CPUHP_INVALID = -1,
+
+	/* PREPARE section invoked on a control CPU */
 	CPUHP_OFFLINE = 0,
 	CPUHP_CREATE_THREADS,
 	CPUHP_PERF_PREPARE,
@@ -95,6 +129,11 @@ enum cpuhp_state {
 	CPUHP_BP_PREPARE_DYN,
 	CPUHP_BP_PREPARE_DYN_END		= CPUHP_BP_PREPARE_DYN + 20,
 	CPUHP_BRINGUP_CPU,
+
+	/*
+	 * STARTING section invoked on the hotplugged CPU in low level
+	 * bringup and teardown code.
+	 */
 	CPUHP_AP_IDLE_DEAD,
 	CPUHP_AP_OFFLINE,
 	CPUHP_AP_SCHED_STARTING,
@@ -155,6 +194,8 @@ enum cpuhp_state {
 	CPUHP_AP_ARM_CACHE_B15_RAC_DYING,
 	CPUHP_AP_ONLINE,
 	CPUHP_TEARDOWN_CPU,
+
+	/* Online section invoked on the hotplugged CPU from the hotplug thread */
 	CPUHP_AP_ONLINE_IDLE,
 	CPUHP_AP_SCHED_WAIT_EMPTY,
 	CPUHP_AP_SMPBOOT_THREADS,
@@ -216,14 +257,15 @@ int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state, const char *name,
 				   int (*teardown)(unsigned int cpu),
 				   bool multi_instance);
 /**
- * cpuhp_setup_state - Setup hotplug state callbacks with calling the callbacks
+ * cpuhp_setup_state - Setup hotplug state callbacks with calling the @startup
+ *                     callback
  * @state:	The state for which the calls are installed
  * @name:	Name of the callback (will be used in debug output)
- * @startup:	startup callback function
- * @teardown:	teardown callback function
+ * @startup:	startup callback function or NULL if not required
+ * @teardown:	teardown callback function or NULL if not required
  *
- * Installs the callback functions and invokes the startup callback on
- * the present cpus which have already reached the @state.
+ * Installs the callback functions and invokes the @startup callback on
+ * the online cpus which have already reached the @state.
  */
 static inline int cpuhp_setup_state(enum cpuhp_state state,
 				    const char *name,
@@ -233,6 +275,18 @@ static inline int cpuhp_setup_state(enum cpuhp_state state,
 	return __cpuhp_setup_state(state, name, true, startup, teardown, false);
 }
 
+/**
+ * cpuhp_setup_state_cpuslocked - Setup hotplug state callbacks with calling
+ *				  @startup callback from a cpus_read_lock()
+ *				  held region
+ * @state:	The state for which the calls are installed
+ * @name:	Name of the callback (will be used in debug output)
+ * @startup:	startup callback function or NULL if not required
+ * @teardown:	teardown callback function or NULL if not required
+ *
+ * Same as cpuhp_setup_state() except that it must be invoked from within a
+ * cpus_read_lock() held region.
+ */
 static inline int cpuhp_setup_state_cpuslocked(enum cpuhp_state state,
 					       const char *name,
 					       int (*startup)(unsigned int cpu),
@@ -244,14 +298,14 @@ static inline int cpuhp_setup_state_cpuslocked(enum cpuhp_state state,
 
 /**
  * cpuhp_setup_state_nocalls - Setup hotplug state callbacks without calling the
- *			       callbacks
+ *			       @startup callback
  * @state:	The state for which the calls are installed
  * @name:	Name of the callback.
- * @startup:	startup callback function
- * @teardown:	teardown callback function
+ * @startup:	startup callback function or NULL if not required
+ * @teardown:	teardown callback function or NULL if not required
  *
- * Same as @cpuhp_setup_state except that no calls are executed are invoked
- * during installation of this callback. NOP if SMP=n or HOTPLUG_CPU=n.
+ * Same as cpuhp_setup_state() except that the @startup callback is not
+ * invoked during installation. NOP if SMP=n or HOTPLUG_CPU=n.
  */
 static inline int cpuhp_setup_state_nocalls(enum cpuhp_state state,
 					    const char *name,
@@ -262,6 +316,19 @@ static inline int cpuhp_setup_state_nocalls(enum cpuhp_state state,
 				   false);
 }
 
+/**
+ * cpuhp_setup_state_nocalls_cpuslocked - Setup hotplug state callbacks without
+ *					  invoking the @startup callback from
+ *					  a cpus_read_lock() held region
+ *			       callbacks
+ * @state:	The state for which the calls are installed
+ * @name:	Name of the callback.
+ * @startup:	startup callback function or NULL if not required
+ * @teardown:	teardown callback function or NULL if not required
+ *
+ * Same as cpuhp_setup_state_nocalls() except that it must be invoked from
+ * within a cpus_read_lock() held region.
+ */
 static inline int cpuhp_setup_state_nocalls_cpuslocked(enum cpuhp_state state,
 						     const char *name,
 						     int (*startup)(unsigned int cpu),
@@ -275,13 +342,13 @@ static inline int cpuhp_setup_state_nocalls_cpuslocked(enum cpuhp_state state,
  * cpuhp_setup_state_multi - Add callbacks for multi state
  * @state:	The state for which the calls are installed
  * @name:	Name of the callback.
- * @startup:	startup callback function
- * @teardown:	teardown callback function
+ * @startup:	startup callback function or NULL if not required
+ * @teardown:	teardown callback function or NULL if not required
  *
  * Sets the internal multi_instance flag and prepares a state to work as a multi
  * instance callback. No callbacks are invoked at this point. The callbacks are
  * invoked once an instance for this state are registered via
- * @cpuhp_state_add_instance or @cpuhp_state_add_instance_nocalls.
+ * cpuhp_state_add_instance() or cpuhp_state_add_instance_nocalls()
  */
 static inline int cpuhp_setup_state_multi(enum cpuhp_state state,
 					  const char *name,
@@ -306,9 +373,10 @@ int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state,
  * @state:	The state for which the instance is installed
  * @node:	The node for this individual state.
  *
- * Installs the instance for the @state and invokes the startup callback on
- * the present cpus which have already reached the @state. The @state must have
- * been earlier marked as multi-instance by @cpuhp_setup_state_multi.
+ * Installs the instance for the @state and invokes the registered startup
+ * callback on the online cpus which have already reached the @state. The
+ * @state must have been earlier marked as multi-instance by
+ * cpuhp_setup_state_multi().
  */
 static inline int cpuhp_state_add_instance(enum cpuhp_state state,
 					   struct hlist_node *node)
@@ -322,8 +390,9 @@ static inline int cpuhp_state_add_instance(enum cpuhp_state state,
  * @state:	The state for which the instance is installed
  * @node:	The node for this individual state.
  *
- * Installs the instance for the @state The @state must have been earlier
- * marked as multi-instance by @cpuhp_setup_state_multi.
+ * Installs the instance for the @state. The @state must have been earlier
+ * marked as multi-instance by cpuhp_setup_state_multi. NOP if SMP=n or
+ * HOTPLUG_CPU=n.
  */
 static inline int cpuhp_state_add_instance_nocalls(enum cpuhp_state state,
 						   struct hlist_node *node)
@@ -331,6 +400,17 @@ static inline int cpuhp_state_add_instance_nocalls(enum cpuhp_state state,
 	return __cpuhp_state_add_instance(state, node, false);
 }
 
+/**
+ * cpuhp_state_add_instance_nocalls_cpuslocked - Add an instance for a state
+ *						 without invoking the startup
+ *						 callback from a cpus_read_lock()
+ *						 held region.
+ * @state:	The state for which the instance is installed
+ * @node:	The node for this individual state.
+ *
+ * Same as cpuhp_state_add_instance_nocalls() except that it must be
+ * invoked from within a cpus_read_lock() held region.
+ */
 static inline int
 cpuhp_state_add_instance_nocalls_cpuslocked(enum cpuhp_state state,
 					    struct hlist_node *node)
@@ -346,7 +426,7 @@ void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke);
  * @state:	The state for which the calls are removed
  *
  * Removes the callback functions and invokes the teardown callback on
- * the present cpus which have already reached the @state.
+ * the online cpus which have already reached the @state.
  */
 static inline void cpuhp_remove_state(enum cpuhp_state state)
 {
@@ -355,7 +435,7 @@ static inline void cpuhp_remove_state(enum cpuhp_state state)
 
 /**
  * cpuhp_remove_state_nocalls - Remove hotplug state callbacks without invoking
- *				teardown
+ *				the teardown callback
  * @state:	The state for which the calls are removed
  */
 static inline void cpuhp_remove_state_nocalls(enum cpuhp_state state)
@@ -363,6 +443,14 @@ static inline void cpuhp_remove_state_nocalls(enum cpuhp_state state)
 	__cpuhp_remove_state(state, false);
 }
 
+/**
+ * cpuhp_remove_state_nocalls_cpuslocked - Remove hotplug state callbacks without invoking
+ *					   teardown from a cpus_read_lock() held region.
+ * @state:	The state for which the calls are removed
+ *
+ * Same as cpuhp_remove_state nocalls() except that it must be invoked
+ * from within a cpus_read_lock() held region.
+ */
 static inline void cpuhp_remove_state_nocalls_cpuslocked(enum cpuhp_state state)
 {
 	__cpuhp_remove_state_cpuslocked(state, false);
@@ -390,8 +478,8 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state,
  * @state:	The state from which the instance is removed
  * @node:	The node for this individual state.
  *
- * Removes the instance and invokes the teardown callback on the present cpus
- * which have already reached the @state.
+ * Removes the instance and invokes the teardown callback on the online cpus
+ * which have already reached @state.
  */
 static inline int cpuhp_state_remove_instance(enum cpuhp_state state,
 					      struct hlist_node *node)

include/linux/damon.h

@@ -0,0 +1,268 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * DAMON api
+ *
+ * Author: SeongJae Park <sjpark@amazon.de>
+ */
+
+#ifndef _DAMON_H_
+#define _DAMON_H_
+
+#include <linux/mutex.h>
+#include <linux/time64.h>
+#include <linux/types.h>
+
+/* Minimal region size.  Every damon_region is aligned by this. */
+#define DAMON_MIN_REGION	PAGE_SIZE
+
+/**
+ * struct damon_addr_range - Represents an address region of [@start, @end).
+ * @start:	Start address of the region (inclusive).
+ * @end:	End address of the region (exclusive).
+ */
+struct damon_addr_range {
+	unsigned long start;
+	unsigned long end;
+};
+
+/**
+ * struct damon_region - Represents a monitoring target region.
+ * @ar:			The address range of the region.
+ * @sampling_addr:	Address of the sample for the next access check.
+ * @nr_accesses:	Access frequency of this region.
+ * @list:		List head for siblings.
+ */
+struct damon_region {
+	struct damon_addr_range ar;
+	unsigned long sampling_addr;
+	unsigned int nr_accesses;
+	struct list_head list;
+};
+
+/**
+ * struct damon_target - Represents a monitoring target.
+ * @id:			Unique identifier for this target.
+ * @nr_regions:		Number of monitoring target regions of this target.
+ * @regions_list:	Head of the monitoring target regions of this target.
+ * @list:		List head for siblings.
+ *
+ * Each monitoring context could have multiple targets.  For example, a context
+ * for virtual memory address spaces could have multiple target processes.  The
+ * @id of each target should be unique among the targets of the context.  For
+ * example, in the virtual address monitoring context, it could be a pidfd or
+ * an address of an mm_struct.
+ */
+struct damon_target {
+	unsigned long id;
+	unsigned int nr_regions;
+	struct list_head regions_list;
+	struct list_head list;
+};
+
+struct damon_ctx;
+
+/**
+ * struct damon_primitive	Monitoring primitives for given use cases.
+ *
+ * @init:			Initialize primitive-internal data structures.
+ * @update:			Update primitive-internal data structures.
+ * @prepare_access_checks:	Prepare next access check of target regions.
+ * @check_accesses:		Check the accesses to target regions.
+ * @reset_aggregated:		Reset aggregated accesses monitoring results.
+ * @target_valid:		Determine if the target is valid.
+ * @cleanup:			Clean up the context.
+ *
+ * DAMON can be extended for various address spaces and usages.  For this,
+ * users should register the low level primitives for their target address
+ * space and usecase via the &damon_ctx.primitive.  Then, the monitoring thread
+ * (&damon_ctx.kdamond) calls @init and @prepare_access_checks before starting
+ * the monitoring, @update after each &damon_ctx.primitive_update_interval, and
+ * @check_accesses, @target_valid and @prepare_access_checks after each
+ * &damon_ctx.sample_interval.  Finally, @reset_aggregated is called after each
+ * &damon_ctx.aggr_interval.
+ *
+ * @init should initialize primitive-internal data structures.  For example,
+ * this could be used to construct proper monitoring target regions and link
+ * those to @damon_ctx.adaptive_targets.
+ * @update should update the primitive-internal data structures.  For example,
+ * this could be used to update monitoring target regions for current status.
+ * @prepare_access_checks should manipulate the monitoring regions to be
+ * prepared for the next access check.
+ * @check_accesses should check the accesses to each region that made after the
+ * last preparation and update the number of observed accesses of each region.
+ * It should also return max number of observed accesses that made as a result
+ * of its update.  The value will be used for regions adjustment threshold.
+ * @reset_aggregated should reset the access monitoring results that aggregated
+ * by @check_accesses.
+ * @target_valid should check whether the target is still valid for the
+ * monitoring.
+ * @cleanup is called from @kdamond just before its termination.
+ */
+struct damon_primitive {
+	void (*init)(struct damon_ctx *context);
+	void (*update)(struct damon_ctx *context);
+	void (*prepare_access_checks)(struct damon_ctx *context);
+	unsigned int (*check_accesses)(struct damon_ctx *context);
+	void (*reset_aggregated)(struct damon_ctx *context);
+	bool (*target_valid)(void *target);
+	void (*cleanup)(struct damon_ctx *context);
+};
+
+/*
+ * struct damon_callback	Monitoring events notification callbacks.
+ *
+ * @before_start:	Called before starting the monitoring.
+ * @after_sampling:	Called after each sampling.
+ * @after_aggregation:	Called after each aggregation.
+ * @before_terminate:	Called before terminating the monitoring.
+ * @private:		User private data.
+ *
+ * The monitoring thread (&damon_ctx.kdamond) calls @before_start and
+ * @before_terminate just before starting and finishing the monitoring,
+ * respectively.  Therefore, those are good places for installing and cleaning
+ * @private.
+ *
+ * The monitoring thread calls @after_sampling and @after_aggregation for each
+ * of the sampling intervals and aggregation intervals, respectively.
+ * Therefore, users can safely access the monitoring results without additional
+ * protection.  For the reason, users are recommended to use these callback for
+ * the accesses to the results.
+ *
+ * If any callback returns non-zero, monitoring stops.
+ */
+struct damon_callback {
+	void *private;
+
+	int (*before_start)(struct damon_ctx *context);
+	int (*after_sampling)(struct damon_ctx *context);
+	int (*after_aggregation)(struct damon_ctx *context);
+	int (*before_terminate)(struct damon_ctx *context);
+};
+
+/**
+ * struct damon_ctx - Represents a context for each monitoring.  This is the
+ * main interface that allows users to set the attributes and get the results
+ * of the monitoring.
+ *
+ * @sample_interval:		The time between access samplings.
+ * @aggr_interval:		The time between monitor results aggregations.
+ * @primitive_update_interval:	The time between monitoring primitive updates.
+ *
+ * For each @sample_interval, DAMON checks whether each region is accessed or
+ * not.  It aggregates and keeps the access information (number of accesses to
+ * each region) for @aggr_interval time.  DAMON also checks whether the target
+ * memory regions need update (e.g., by ``mmap()`` calls from the application,
+ * in case of virtual memory monitoring) and applies the changes for each
+ * @primitive_update_interval.  All time intervals are in micro-seconds.
+ * Please refer to &struct damon_primitive and &struct damon_callback for more
+ * detail.
+ *
+ * @kdamond:		Kernel thread who does the monitoring.
+ * @kdamond_stop:	Notifies whether kdamond should stop.
+ * @kdamond_lock:	Mutex for the synchronizations with @kdamond.
+ *
+ * For each monitoring context, one kernel thread for the monitoring is
+ * created.  The pointer to the thread is stored in @kdamond.
+ *
+ * Once started, the monitoring thread runs until explicitly required to be
+ * terminated or every monitoring target is invalid.  The validity of the
+ * targets is checked via the &damon_primitive.target_valid of @primitive.  The
+ * termination can also be explicitly requested by writing non-zero to
+ * @kdamond_stop.  The thread sets @kdamond to NULL when it terminates.
+ * Therefore, users can know whether the monitoring is ongoing or terminated by
+ * reading @kdamond.  Reads and writes to @kdamond and @kdamond_stop from
+ * outside of the monitoring thread must be protected by @kdamond_lock.
+ *
+ * Note that the monitoring thread protects only @kdamond and @kdamond_stop via
+ * @kdamond_lock.  Accesses to other fields must be protected by themselves.
+ *
+ * @primitive:	Set of monitoring primitives for given use cases.
+ * @callback:	Set of callbacks for monitoring events notifications.
+ *
+ * @min_nr_regions:	The minimum number of adaptive monitoring regions.
+ * @max_nr_regions:	The maximum number of adaptive monitoring regions.
+ * @adaptive_targets:	Head of monitoring targets (&damon_target) list.
+ */
+struct damon_ctx {
+	unsigned long sample_interval;
+	unsigned long aggr_interval;
+	unsigned long primitive_update_interval;
+
+/* private: internal use only */
+	struct timespec64 last_aggregation;
+	struct timespec64 last_primitive_update;
+
+/* public: */
+	struct task_struct *kdamond;
+	bool kdamond_stop;
+	struct mutex kdamond_lock;
+
+	struct damon_primitive primitive;
+	struct damon_callback callback;
+
+	unsigned long min_nr_regions;
+	unsigned long max_nr_regions;
+	struct list_head adaptive_targets;
+};
+
+#define damon_next_region(r) \
+	(container_of(r->list.next, struct damon_region, list))
+
+#define damon_prev_region(r) \
+	(container_of(r->list.prev, struct damon_region, list))
+
+#define damon_for_each_region(r, t) \
+	list_for_each_entry(r, &t->regions_list, list)
+
+#define damon_for_each_region_safe(r, next, t) \
+	list_for_each_entry_safe(r, next, &t->regions_list, list)
+
+#define damon_for_each_target(t, ctx) \
+	list_for_each_entry(t, &(ctx)->adaptive_targets, list)
+
+#define damon_for_each_target_safe(t, next, ctx)	\
+	list_for_each_entry_safe(t, next, &(ctx)->adaptive_targets, list)
+
+#ifdef CONFIG_DAMON
+
+struct damon_region *damon_new_region(unsigned long start, unsigned long end);
+inline void damon_insert_region(struct damon_region *r,
+		struct damon_region *prev, struct damon_region *next,
+		struct damon_target *t);
+void damon_add_region(struct damon_region *r, struct damon_target *t);
+void damon_destroy_region(struct damon_region *r, struct damon_target *t);
+
+struct damon_target *damon_new_target(unsigned long id);
+void damon_add_target(struct damon_ctx *ctx, struct damon_target *t);
+void damon_free_target(struct damon_target *t);
+void damon_destroy_target(struct damon_target *t);
+unsigned int damon_nr_regions(struct damon_target *t);
+
+struct damon_ctx *damon_new_ctx(void);
+void damon_destroy_ctx(struct damon_ctx *ctx);
+int damon_set_targets(struct damon_ctx *ctx,
+		unsigned long *ids, ssize_t nr_ids);
+int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
+		unsigned long aggr_int, unsigned long primitive_upd_int,
+		unsigned long min_nr_reg, unsigned long max_nr_reg);
+int damon_nr_running_ctxs(void);
+
+int damon_start(struct damon_ctx **ctxs, int nr_ctxs);
+int damon_stop(struct damon_ctx **ctxs, int nr_ctxs);
+
+#endif	/* CONFIG_DAMON */
+
+#ifdef CONFIG_DAMON_VADDR
+
+/* Monitoring primitives for virtual memory address spaces */
+void damon_va_init(struct damon_ctx *ctx);
+void damon_va_update(struct damon_ctx *ctx);
+void damon_va_prepare_access_checks(struct damon_ctx *ctx);
+unsigned int damon_va_check_accesses(struct damon_ctx *ctx);
+bool damon_va_target_valid(void *t);
+void damon_va_cleanup(struct damon_ctx *ctx);
+void damon_va_set_primitives(struct damon_ctx *ctx);
+
+#endif	/* CONFIG_DAMON_VADDR */
+
+#endif	/* _DAMON_H */

include/linux/dax.h

@@ -41,7 +41,6 @@ struct dax_operations {
 extern struct attribute_group dax_attribute_group;
 
 #if IS_ENABLED(CONFIG_DAX)
-struct dax_device *dax_get_by_host(const char *host);
 struct dax_device *alloc_dax(void *private, const char *host,
 		const struct dax_operations *ops, unsigned long flags);
 void put_dax(struct dax_device *dax_dev);
@@ -58,8 +57,6 @@ static inline void set_dax_synchronous(struct dax_device *dax_dev)
 {
 	__set_dax_synchronous(dax_dev);
 }
-bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
-		int blocksize, sector_t start, sector_t len);
 /*
  * Check if given mapping is supported by the file / underlying device.
  */
@@ -73,10 +70,6 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 	return dax_synchronous(dax_dev);
 }
 #else
-static inline struct dax_device *dax_get_by_host(const char *host)
-{
-	return NULL;
-}
 static inline struct dax_device *alloc_dax(void *private, const char *host,
 		const struct dax_operations *ops, unsigned long flags)
 {
@@ -106,12 +99,6 @@ static inline bool dax_synchronous(struct dax_device *dax_dev)
 static inline void set_dax_synchronous(struct dax_device *dax_dev)
 {
 }
-static inline bool dax_supported(struct dax_device *dax_dev,
-		struct block_device *bdev, int blocksize, sector_t start,
-		sector_t len)
-{
-	return false;
-}
 static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 				struct dax_device *dax_dev)
 {
@@ -122,22 +109,12 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 struct writeback_control;
 int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
 #if IS_ENABLED(CONFIG_FS_DAX)
-bool __bdev_dax_supported(struct block_device *bdev, int blocksize);
-static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize)
-{
-	return __bdev_dax_supported(bdev, blocksize);
-}
-
-bool __generic_fsdax_supported(struct dax_device *dax_dev,
+bool generic_fsdax_supported(struct dax_device *dax_dev,
 		struct block_device *bdev, int blocksize, sector_t start,
 		sector_t sectors);
-static inline bool generic_fsdax_supported(struct dax_device *dax_dev,
-		struct block_device *bdev, int blocksize, sector_t start,
-		sector_t sectors)
-{
-	return __generic_fsdax_supported(dax_dev, bdev, blocksize, start,
-			sectors);
-}
+
+bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
+		int blocksize, sector_t start, sector_t len);
 
 static inline void fs_put_dax(struct dax_device *dax_dev)
 {
@@ -153,15 +130,11 @@ struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t st
 dax_entry_t dax_lock_page(struct page *page);
 void dax_unlock_page(struct page *page, dax_entry_t cookie);
 #else
-static inline bool bdev_dax_supported(struct block_device *bdev,
-		int blocksize)
-{
-	return false;
-}
+#define generic_fsdax_supported		NULL
 
-static inline bool generic_fsdax_supported(struct dax_device *dax_dev,
+static inline bool dax_supported(struct dax_device *dax_dev,
 		struct block_device *bdev, int blocksize, sector_t start,
-		sector_t sectors)
+		sector_t len)
 {
 	return false;
 }

include/linux/dmaengine.h

@@ -380,6 +380,7 @@ enum dma_slave_buswidth {
 	DMA_SLAVE_BUSWIDTH_16_BYTES = 16,
 	DMA_SLAVE_BUSWIDTH_32_BYTES = 32,
 	DMA_SLAVE_BUSWIDTH_64_BYTES = 64,
+	DMA_SLAVE_BUSWIDTH_128_BYTES = 128,
 };
 
 /**
@@ -398,7 +399,7 @@ enum dma_slave_buswidth {
  * @src_addr_width: this is the width in bytes of the source (RX)
  * register where DMA data shall be read. If the source
  * is memory this may be ignored depending on architecture.
- * Legal values: 1, 2, 3, 4, 8, 16, 32, 64.
+ * Legal values: 1, 2, 3, 4, 8, 16, 32, 64, 128.
  * @dst_addr_width: same as src_addr_width but for destination
  * target (TX) mutatis mutandis.
  * @src_maxburst: the maximum number of words (note: words, as in

include/linux/energy_model.h

@@ -11,7 +11,7 @@
 #include <linux/types.h>
 
 /**
- * em_perf_state - Performance state of a performance domain
+ * struct em_perf_state - Performance state of a performance domain
  * @frequency:	The frequency in KHz, for consistency with CPUFreq
  * @power:	The power consumed at this level (by 1 CPU or by a registered
  *		device). It can be a total power: static and dynamic.
@@ -25,7 +25,7 @@ struct em_perf_state {
 };
 
 /**
- * em_perf_domain - Performance domain
+ * struct em_perf_domain - Performance domain
  * @table:		List of performance states, in ascending order
  * @nr_perf_states:	Number of performance states
  * @milliwatts:		Flag indicating the power values are in milli-Watts
@@ -103,12 +103,12 @@ void em_dev_unregister_perf_domain(struct device *dev);
 
 /**
  * em_cpu_energy() - Estimates the energy consumed by the CPUs of a
-		performance domain
+ *		performance domain
  * @pd		: performance domain for which energy has to be estimated
  * @max_util	: highest utilization among CPUs of the domain
  * @sum_util	: sum of the utilization of all CPUs in the domain
  * @allowed_cpu_cap	: maximum allowed CPU capacity for the @pd, which
-			  might reflect reduced frequency (due to thermal)
+ *			  might reflect reduced frequency (due to thermal)
  *
  * This function must be used only for CPU devices. There is no validation,
  * i.e. if the EM is a CPU type and has cpumask allocated. It is called from

include/linux/eventpoll.h

@@ -68,4 +68,22 @@ static inline void eventpoll_release(struct file *file) {}
 
 #endif
 
+#if defined(CONFIG_ARM) && defined(CONFIG_OABI_COMPAT)
+/* ARM OABI has an incompatible struct layout and needs a special handler */
+extern struct epoll_event __user *
+epoll_put_uevent(__poll_t revents, __u64 data,
+		 struct epoll_event __user *uevent);
+#else
+static inline struct epoll_event __user *
+epoll_put_uevent(__poll_t revents, __u64 data,
+		 struct epoll_event __user *uevent)
+{
+	if (__put_user(revents, &uevent->events) ||
+	    __put_user(data, &uevent->data))
+		return NULL;
+
+	return uevent+1;
+}
+#endif
+
 #endif /* #ifndef _LINUX_EVENTPOLL_H */

include/linux/file.h

@@ -94,6 +94,9 @@ extern void fd_install(unsigned int fd, struct file *file);
 
 extern int __receive_fd(struct file *file, int __user *ufd,
 			unsigned int o_flags);
+
+extern int receive_fd(struct file *file, unsigned int o_flags);
+
 static inline int receive_fd_user(struct file *file, int __user *ufd,
 				  unsigned int o_flags)
 {
@@ -101,10 +104,6 @@ static inline int receive_fd_user(struct file *file, int __user *ufd,
 		return -EFAULT;
 	return __receive_fd(file, ufd, o_flags);
 }
-static inline int receive_fd(struct file *file, unsigned int o_flags)
-{
-	return __receive_fd(file, NULL, o_flags);
-}
 int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags);
 
 extern void flush_delayed_fput(void);

include/linux/fs.h

@@ -3439,6 +3439,8 @@ extern int buffer_migrate_page_norefs(struct address_space *,
 #define buffer_migrate_page_norefs NULL
 #endif
 
+int may_setattr(struct user_namespace *mnt_userns, struct inode *inode,
+		unsigned int ia_valid);
 int setattr_prepare(struct user_namespace *, struct dentry *, struct iattr *);
 extern int inode_newsize_ok(const struct inode *, loff_t offset);
 void setattr_copy(struct user_namespace *, struct inode *inode,
@@ -3592,7 +3594,7 @@ int proc_nr_dentry(struct ctl_table *table, int write,
 		  void *buffer, size_t *lenp, loff_t *ppos);
 int proc_nr_inodes(struct ctl_table *table, int write,
 		   void *buffer, size_t *lenp, loff_t *ppos);
-int __init get_filesystem_list(char *buf);
+int __init list_bdev_fs_names(char *buf, size_t size);
 
 #define __FMODE_EXEC		((__force int) FMODE_EXEC)
 #define __FMODE_NONOTIFY	((__force int) FMODE_NONOTIFY)

include/linux/highmem-internal.h

@@ -90,7 +90,11 @@ static inline void __kunmap_local(void *vaddr)
 
 static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 {
-	preempt_disable();
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		migrate_disable();
+	else
+		preempt_disable();
+
 	pagefault_disable();
 	return __kmap_local_page_prot(page, prot);
 }
@@ -102,7 +106,11 @@ static inline void *kmap_atomic(struct page *page)
 
 static inline void *kmap_atomic_pfn(unsigned long pfn)
 {
-	preempt_disable();
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		migrate_disable();
+	else
+		preempt_disable();
+
 	pagefault_disable();
 	return __kmap_local_pfn_prot(pfn, kmap_prot);
 }
@@ -111,7 +119,10 @@ static inline void __kunmap_atomic(void *addr)
 {
 	kunmap_local_indexed(addr);
 	pagefault_enable();
-	preempt_enable();
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		migrate_enable();
+	else
+		preempt_enable();
 }
 
 unsigned int __nr_free_highpages(void);
@@ -179,7 +190,10 @@ static inline void __kunmap_local(void *addr)
 
 static inline void *kmap_atomic(struct page *page)
 {
-	preempt_disable();
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		migrate_disable();
+	else
+		preempt_disable();
 	pagefault_disable();
 	return page_address(page);
 }
@@ -200,7 +214,10 @@ static inline void __kunmap_atomic(void *addr)
 	kunmap_flush_on_unmap(addr);
 #endif
 	pagefault_enable();
-	preempt_enable();
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
+		migrate_enable();
+	else
+		preempt_enable();
 }
 
 static inline unsigned int nr_free_highpages(void) { return 0; }

include/linux/hugetlb.h

@@ -858,6 +858,11 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 
 void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm);
 
+static inline void hugetlb_count_init(struct mm_struct *mm)
+{
+	atomic_long_set(&mm->hugetlb_usage, 0);
+}
+
 static inline void hugetlb_count_add(long l, struct mm_struct *mm)
 {
 	atomic_long_add(l, &mm->hugetlb_usage);
@@ -1042,6 +1047,10 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 	return &mm->page_table_lock;
 }
 
+static inline void hugetlb_count_init(struct mm_struct *mm)
+{
+}
+
 static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m)
 {
 }

include/linux/memblock.h

@@ -118,6 +118,7 @@ int memblock_mark_nomap(phys_addr_t base, phys_addr_t size);
 int memblock_clear_nomap(phys_addr_t base, phys_addr_t size);
 
 void memblock_free_all(void);
+void memblock_free_ptr(void *ptr, size_t size);
 void reset_node_managed_pages(pg_data_t *pgdat);
 void reset_all_zones_managed_pages(void);
 

include/linux/memory.h

@@ -23,6 +23,48 @@
 
 #define MIN_MEMORY_BLOCK_SIZE     (1UL << SECTION_SIZE_BITS)
 
+/**
+ * struct memory_group - a logical group of memory blocks
+ * @nid: The node id for all memory blocks inside the memory group.
+ * @blocks: List of all memory blocks belonging to this memory group.
+ * @present_kernel_pages: Present (online) memory outside ZONE_MOVABLE of this
+ *			  memory group.
+ * @present_movable_pages: Present (online) memory in ZONE_MOVABLE of this
+ *			   memory group.
+ * @is_dynamic: The memory group type: static vs. dynamic
+ * @s.max_pages: Valid with &memory_group.is_dynamic == false. The maximum
+ *		 number of pages we'll have in this static memory group.
+ * @d.unit_pages: Valid with &memory_group.is_dynamic == true. Unit in pages
+ *		  in which memory is added/removed in this dynamic memory group.
+ *		  This granularity defines the alignment of a unit in physical
+ *		  address space; it has to be at least as big as a single
+ *		  memory block.
+ *
+ * A memory group logically groups memory blocks; each memory block
+ * belongs to at most one memory group. A memory group corresponds to
+ * a memory device, such as a DIMM or a NUMA node, which spans multiple
+ * memory blocks and might even span multiple non-contiguous physical memory
+ * ranges.
+ *
+ * Modification of members after registration is serialized by memory
+ * hot(un)plug code.
+ */
+struct memory_group {
+	int nid;
+	struct list_head memory_blocks;
+	unsigned long present_kernel_pages;
+	unsigned long present_movable_pages;
+	bool is_dynamic;
+	union {
+		struct {
+			unsigned long max_pages;
+		} s;
+		struct {
+			unsigned long unit_pages;
+		} d;
+	};
+};
+
 struct memory_block {
 	unsigned long start_section_nr;
 	unsigned long state;		/* serialized by the dev->lock */
@@ -34,6 +76,8 @@ struct memory_block {
 	 * lay at the beginning of the memory block.
 	 */
 	unsigned long nr_vmemmap_pages;
+	struct memory_group *group;	/* group (if any) for this block */
+	struct list_head group_next;	/* next block inside memory group */
 };
 
 int arch_get_memory_phys_device(unsigned long start_pfn);
@@ -86,7 +130,8 @@ static inline int memory_notify(unsigned long val, void *v)
 extern int register_memory_notifier(struct notifier_block *nb);
 extern void unregister_memory_notifier(struct notifier_block *nb);
 int create_memory_block_devices(unsigned long start, unsigned long size,
-				unsigned long vmemmap_pages);
+				unsigned long vmemmap_pages,
+				struct memory_group *group);
 void remove_memory_block_devices(unsigned long start, unsigned long size);
 extern void memory_dev_init(void);
 extern int memory_notify(unsigned long val, void *v);
@@ -96,6 +141,14 @@ extern int walk_memory_blocks(unsigned long start, unsigned long size,
 			      void *arg, walk_memory_blocks_func_t func);
 extern int for_each_memory_block(void *arg, walk_memory_blocks_func_t func);
 #define CONFIG_MEM_BLOCK_SIZE	(PAGES_PER_SECTION<<PAGE_SHIFT)
+
+extern int memory_group_register_static(int nid, unsigned long max_pages);
+extern int memory_group_register_dynamic(int nid, unsigned long unit_pages);
+extern int memory_group_unregister(int mgid);
+struct memory_group *memory_group_find_by_id(int mgid);
+typedef int (*walk_memory_groups_func_t)(struct memory_group *, void *);
+int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
+			       struct memory_group *excluded, void *arg);
 #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
 
 #ifdef CONFIG_MEMORY_HOTPLUG

include/linux/memory_hotplug.h

@@ -12,6 +12,7 @@ struct zone;
 struct pglist_data;
 struct mem_section;
 struct memory_block;
+struct memory_group;
 struct resource;
 struct vmem_altmap;
 
@@ -50,6 +51,11 @@ typedef int __bitwise mhp_t;
  * Only selected architectures support it with SPARSE_VMEMMAP.
  */
 #define MHP_MEMMAP_ON_MEMORY   ((__force mhp_t)BIT(1))
+/*
+ * The nid field specifies a memory group id (mgid) instead. The memory group
+ * implies the node id (nid).
+ */
+#define MHP_NID_IS_MGID		((__force mhp_t)BIT(2))
 
 /*
  * Extended parameters for memory hotplug:
@@ -95,13 +101,15 @@ static inline void zone_seqlock_init(struct zone *zone)
 extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages);
 extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
 extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
-extern void adjust_present_page_count(struct zone *zone, long nr_pages);
+extern void adjust_present_page_count(struct page *page,
+				      struct memory_group *group,
+				      long nr_pages);
 /* VM interface that may be used by firmware interface */
 extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
 				     struct zone *zone);
 extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages);
 extern int online_pages(unsigned long pfn, unsigned long nr_pages,
-			struct zone *zone);
+			struct zone *zone, struct memory_group *group);
 extern struct zone *test_pages_in_a_zone(unsigned long start_pfn,
 					 unsigned long end_pfn);
 extern void __offline_isolated_pages(unsigned long start_pfn,
@@ -130,8 +138,7 @@ static inline bool movable_node_is_enabled(void)
 	return movable_node_enabled;
 }
 
-extern void arch_remove_memory(int nid, u64 start, u64 size,
-			       struct vmem_altmap *altmap);
+extern void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap);
 extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages,
 			   struct vmem_altmap *altmap);
 
@@ -292,25 +299,27 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
 #ifdef CONFIG_MEMORY_HOTREMOVE
 
 extern void try_offline_node(int nid);
-extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
-extern int remove_memory(int nid, u64 start, u64 size);
-extern void __remove_memory(int nid, u64 start, u64 size);
-extern int offline_and_remove_memory(int nid, u64 start, u64 size);
+extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
+			 struct memory_group *group);
+extern int remove_memory(u64 start, u64 size);
+extern void __remove_memory(u64 start, u64 size);
+extern int offline_and_remove_memory(u64 start, u64 size);
 
 #else
 static inline void try_offline_node(int nid) {}
 
-static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
+static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
+				struct memory_group *group)
 {
 	return -EINVAL;
 }
 
-static inline int remove_memory(int nid, u64 start, u64 size)
+static inline int remove_memory(u64 start, u64 size)
 {
 	return -EBUSY;
 }
 
-static inline void __remove_memory(int nid, u64 start, u64 size) {}
+static inline void __remove_memory(u64 start, u64 size) {}
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
 extern void set_zone_contiguous(struct zone *zone);
@@ -339,7 +348,8 @@ extern void sparse_remove_section(struct mem_section *ms,
 		unsigned long map_offset, struct vmem_altmap *altmap);
 extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
 					  unsigned long pnum);
-extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
+extern struct zone *zone_for_pfn_range(int online_type, int nid,
+		struct memory_group *group, unsigned long start_pfn,
 		unsigned long nr_pages);
 extern int arch_create_linear_mapping(int nid, u64 start, u64 size,
 				      struct mhp_params *params);

include/linux/mmap_lock.h

@@ -101,14 +101,14 @@ static inline bool mmap_write_trylock(struct mm_struct *mm)
 
 static inline void mmap_write_unlock(struct mm_struct *mm)
 {
-	up_write(&mm->mmap_lock);
 	__mmap_lock_trace_released(mm, true);
+	up_write(&mm->mmap_lock);
 }
 
 static inline void mmap_write_downgrade(struct mm_struct *mm)
 {
-	downgrade_write(&mm->mmap_lock);
 	__mmap_lock_trace_acquire_returned(mm, false, true);
+	downgrade_write(&mm->mmap_lock);
 }
 
 static inline void mmap_read_lock(struct mm_struct *mm)
@@ -140,23 +140,14 @@ static inline bool mmap_read_trylock(struct mm_struct *mm)
 
 static inline void mmap_read_unlock(struct mm_struct *mm)
 {
-	up_read(&mm->mmap_lock);
 	__mmap_lock_trace_released(mm, false);
-}
-
-static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm)
-{
-	if (mmap_read_trylock(mm)) {
-		rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_);
-		return true;
-	}
-	return false;
+	up_read(&mm->mmap_lock);
 }
 
 static inline void mmap_read_unlock_non_owner(struct mm_struct *mm)
 {
-	up_read_non_owner(&mm->mmap_lock);
 	__mmap_lock_trace_released(mm, false);
+	up_read_non_owner(&mm->mmap_lock);
 }
 
 static inline void mmap_assert_locked(struct mm_struct *mm)

include/linux/mmzone.h

@@ -540,6 +540,10 @@ struct zone {
 	 * is calculated as:
 	 *	present_pages = spanned_pages - absent_pages(pages in holes);
 	 *
+	 * present_early_pages is present pages existing within the zone
+	 * located on memory available since early boot, excluding hotplugged
+	 * memory.
+	 *
 	 * managed_pages is present pages managed by the buddy system, which
 	 * is calculated as (reserved_pages includes pages allocated by the
 	 * bootmem allocator):
@@ -572,6 +576,9 @@ struct zone {
 	atomic_long_t		managed_pages;
 	unsigned long		spanned_pages;
 	unsigned long		present_pages;
+#if defined(CONFIG_MEMORY_HOTPLUG)
+	unsigned long		present_early_pages;
+#endif
 #ifdef CONFIG_CMA
 	unsigned long		cma_pages;
 #endif
@@ -1525,18 +1532,6 @@ void sparse_init(void);
 #define subsection_map_init(_pfn, _nr_pages) do {} while (0)
 #endif /* CONFIG_SPARSEMEM */
 
-/*
- * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we
- * need to check pfn validity within that MAX_ORDER_NR_PAGES block.
- * pfn_valid_within() should be used in this case; we optimise this away
- * when we have no holes within a MAX_ORDER_NR_PAGES block.
- */
-#ifdef CONFIG_HOLES_IN_ZONE
-#define pfn_valid_within(pfn) pfn_valid(pfn)
-#else
-#define pfn_valid_within(pfn) (1)
-#endif
-
 #endif /* !__GENERATING_BOUNDS.H */
 #endif /* !__ASSEMBLY__ */
 #endif /* _LINUX_MMZONE_H */

include/linux/once.h

@@ -16,7 +16,7 @@ void __do_once_done(bool *done, struct static_key_true *once_key,
  * out the condition into a nop. DO_ONCE() guarantees type safety of
  * arguments!
  *
- * Not that the following is not equivalent ...
+ * Note that the following is not equivalent ...
  *
  *   DO_ONCE(func, arg);
  *   DO_ONCE(func, arg);

include/linux/overflow.h

@@ -6,12 +6,9 @@
 #include <linux/limits.h>
 
 /*
- * In the fallback code below, we need to compute the minimum and
- * maximum values representable in a given type. These macros may also
- * be useful elsewhere, so we provide them outside the
- * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block.
- *
- * It would seem more obvious to do something like
+ * We need to compute the minimum and maximum values representable in a given
+ * type. These macros may also be useful elsewhere. It would seem more obvious
+ * to do something like:
  *
  * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0)
  * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0)
@@ -54,7 +51,6 @@ static inline bool __must_check __must_check_overflow(bool overflow)
 	return unlikely(overflow);
 }
 
-#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW
 /*
  * For simplicity and code hygiene, the fallback code below insists on
  * a, b and *d having the same type (similar to the min() and max()
@@ -90,134 +86,6 @@ static inline bool __must_check __must_check_overflow(bool overflow)
 	__builtin_mul_overflow(__a, __b, __d);	\
 }))
 
-#else
-
-
-/* Checking for unsigned overflow is relatively easy without causing UB. */
-#define __unsigned_add_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = __a + __b;			\
-	*__d < __a;				\
-})
-#define __unsigned_sub_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = __a - __b;			\
-	__a < __b;				\
-})
-/*
- * If one of a or b is a compile-time constant, this avoids a division.
- */
-#define __unsigned_mul_overflow(a, b, d) ({		\
-	typeof(a) __a = (a);				\
-	typeof(b) __b = (b);				\
-	typeof(d) __d = (d);				\
-	(void) (&__a == &__b);				\
-	(void) (&__a == __d);				\
-	*__d = __a * __b;				\
-	__builtin_constant_p(__b) ?			\
-	  __b > 0 && __a > type_max(typeof(__a)) / __b : \
-	  __a > 0 && __b > type_max(typeof(__b)) / __a;	 \
-})
-
-/*
- * For signed types, detecting overflow is much harder, especially if
- * we want to avoid UB. But the interface of these macros is such that
- * we must provide a result in *d, and in fact we must produce the
- * result promised by gcc's builtins, which is simply the possibly
- * wrapped-around value. Fortunately, we can just formally do the
- * operations in the widest relevant unsigned type (u64) and then
- * truncate the result - gcc is smart enough to generate the same code
- * with and without the (u64) casts.
- */
-
-/*
- * Adding two signed integers can overflow only if they have the same
- * sign, and overflow has happened iff the result has the opposite
- * sign.
- */
-#define __signed_add_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = (u64)__a + (u64)__b;		\
-	(((~(__a ^ __b)) & (*__d ^ __a))	\
-		& type_min(typeof(__a))) != 0;	\
-})
-
-/*
- * Subtraction is similar, except that overflow can now happen only
- * when the signs are opposite. In this case, overflow has happened if
- * the result has the opposite sign of a.
- */
-#define __signed_sub_overflow(a, b, d) ({	\
-	typeof(a) __a = (a);			\
-	typeof(b) __b = (b);			\
-	typeof(d) __d = (d);			\
-	(void) (&__a == &__b);			\
-	(void) (&__a == __d);			\
-	*__d = (u64)__a - (u64)__b;		\
-	((((__a ^ __b)) & (*__d ^ __a))		\
-		& type_min(typeof(__a))) != 0;	\
-})
-
-/*
- * Signed multiplication is rather hard. gcc always follows C99, so
- * division is truncated towards 0. This means that we can write the
- * overflow check like this:
- *
- * (a > 0 && (b > MAX/a || b < MIN/a)) ||
- * (a < -1 && (b > MIN/a || b < MAX/a) ||
- * (a == -1 && b == MIN)
- *
- * The redundant casts of -1 are to silence an annoying -Wtype-limits
- * (included in -Wextra) warning: When the type is u8 or u16, the
- * __b_c_e in check_mul_overflow obviously selects
- * __unsigned_mul_overflow, but unfortunately gcc still parses this
- * code and warns about the limited range of __b.
- */
-
-#define __signed_mul_overflow(a, b, d) ({				\
-	typeof(a) __a = (a);						\
-	typeof(b) __b = (b);						\
-	typeof(d) __d = (d);						\
-	typeof(a) __tmax = type_max(typeof(a));				\
-	typeof(a) __tmin = type_min(typeof(a));				\
-	(void) (&__a == &__b);						\
-	(void) (&__a == __d);						\
-	*__d = (u64)__a * (u64)__b;					\
-	(__b > 0   && (__a > __tmax/__b || __a < __tmin/__b)) ||	\
-	(__b < (typeof(__b))-1  && (__a > __tmin/__b || __a < __tmax/__b)) || \
-	(__b == (typeof(__b))-1 && __a == __tmin);			\
-})
-
-
-#define check_add_overflow(a, b, d)	__must_check_overflow(		\
-	__builtin_choose_expr(is_signed_type(typeof(a)),		\
-			__signed_add_overflow(a, b, d),			\
-			__unsigned_add_overflow(a, b, d)))
-
-#define check_sub_overflow(a, b, d)	__must_check_overflow(		\
-	__builtin_choose_expr(is_signed_type(typeof(a)),		\
-			__signed_sub_overflow(a, b, d),			\
-			__unsigned_sub_overflow(a, b, d)))
-
-#define check_mul_overflow(a, b, d)	__must_check_overflow(		\
-	__builtin_choose_expr(is_signed_type(typeof(a)),		\
-			__signed_mul_overflow(a, b, d),			\
-			__unsigned_mul_overflow(a, b, d)))
-
-#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */
-
 /** check_shl_overflow() - Calculate a left-shifted value and check overflow
  *
  * @a: Value to be shifted

include/linux/page-flags.h

@@ -131,7 +131,7 @@ enum pageflags {
 #ifdef CONFIG_MEMORY_FAILURE
 	PG_hwpoison,		/* hardware poisoned page. Don't touch */
 #endif
-#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
+#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT)
 	PG_young,
 	PG_idle,
 #endif
@@ -178,6 +178,8 @@ enum pageflags {
 	PG_reported = PG_uptodate,
 };
 
+#define PAGEFLAGS_MASK		((1UL << NR_PAGEFLAGS) - 1)
+
 #ifndef __GENERATING_BOUNDS_H
 
 static inline unsigned long _compound_head(const struct page *page)
@@ -439,7 +441,7 @@ PAGEFLAG_FALSE(HWPoison)
 #define __PG_HWPOISON 0
 #endif
 
-#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
+#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT)
 TESTPAGEFLAG(Young, young, PF_ANY)
 SETPAGEFLAG(Young, young, PF_ANY)
 TESTCLEARFLAG(Young, young, PF_ANY)
@@ -778,6 +780,15 @@ static inline int PageSlabPfmemalloc(struct page *page)
 	return PageActive(page);
 }
 
+/*
+ * A version of PageSlabPfmemalloc() for opportunistic checks where the page
+ * might have been freed under us and not be a PageSlab anymore.
+ */
+static inline int __PageSlabPfmemalloc(struct page *page)
+{
+	return PageActive(page);
+}
+
 static inline void SetPageSlabPfmemalloc(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageSlab(page), page);
@@ -822,7 +833,7 @@ static inline void ClearPageSlabPfmemalloc(struct page *page)
  * alloc-free cycle to prevent from reusing the page.
  */
 #define PAGE_FLAGS_CHECK_AT_PREP	\
-	(((1UL << NR_PAGEFLAGS) - 1) & ~__PG_HWPOISON)
+	(PAGEFLAGS_MASK & ~__PG_HWPOISON)
 
 #define PAGE_FLAGS_PRIVATE				\
 	(1UL << PG_private | 1UL << PG_private_2)

include/linux/page_ext.h

@@ -19,7 +19,7 @@ struct page_ext_operations {
 enum page_ext_flags {
 	PAGE_EXT_OWNER,
 	PAGE_EXT_OWNER_ALLOCATED,
-#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT)
+#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT)
 	PAGE_EXT_YOUNG,
 	PAGE_EXT_IDLE,
 #endif

include/linux/page_idle.h

@@ -6,7 +6,7 @@
 #include <linux/page-flags.h>
 #include <linux/page_ext.h>
 
-#ifdef CONFIG_IDLE_PAGE_TRACKING
+#ifdef CONFIG_PAGE_IDLE_FLAG
 
 #ifdef CONFIG_64BIT
 static inline bool page_is_young(struct page *page)
@@ -106,7 +106,7 @@ static inline void clear_page_idle(struct page *page)
 }
 #endif /* CONFIG_64BIT */
 
-#else /* !CONFIG_IDLE_PAGE_TRACKING */
+#else /* !CONFIG_PAGE_IDLE_FLAG */
 
 static inline bool page_is_young(struct page *page)
 {
@@ -135,6 +135,6 @@ static inline void clear_page_idle(struct page *page)
 {
 }
 
-#endif /* CONFIG_IDLE_PAGE_TRACKING */
+#endif /* CONFIG_PAGE_IDLE_FLAG */
 
 #endif /* _LINUX_MM_PAGE_IDLE_H */

include/linux/pagemap.h

@@ -521,18 +521,17 @@ static inline struct page *read_mapping_page(struct address_space *mapping,
  */
 static inline pgoff_t page_to_index(struct page *page)
 {
-	pgoff_t pgoff;
+	struct page *head;
 
 	if (likely(!PageTransTail(page)))
 		return page->index;
 
+	head = compound_head(page);
 	/*
 	 *  We don't initialize ->index for tail pages: calculate based on
 	 *  head page
 	 */
-	pgoff = compound_head(page)->index;
-	pgoff += page - compound_head(page);
-	return pgoff;
+	return head->index + page - head;
 }
 
 extern pgoff_t hugetlb_basepage_index(struct page *page);

include/linux/pci-acpi.h

@@ -122,6 +122,9 @@ static inline void pci_acpi_add_edr_notifier(struct pci_dev *pdev) { }
 static inline void pci_acpi_remove_edr_notifier(struct pci_dev *pdev) { }
 #endif /* CONFIG_PCIE_EDR */
 
+int pci_acpi_set_companion_lookup_hook(struct acpi_device *(*func)(struct pci_dev *));
+void pci_acpi_clear_companion_lookup_hook(void);
+
 #else	/* CONFIG_ACPI */
 static inline void acpi_pci_add_bus(struct pci_bus *bus) { }
 static inline void acpi_pci_remove_bus(struct pci_bus *bus) { }

include/linux/pci-epc.h

@@ -62,31 +62,32 @@ pci_epc_interface_string(enum pci_epc_interface_type type)
  * @owner: the module owner containing the ops
  */
 struct pci_epc_ops {
-	int	(*write_header)(struct pci_epc *epc, u8 func_no,
+	int	(*write_header)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 				struct pci_epf_header *hdr);
-	int	(*set_bar)(struct pci_epc *epc, u8 func_no,
+	int	(*set_bar)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			   struct pci_epf_bar *epf_bar);
-	void	(*clear_bar)(struct pci_epc *epc, u8 func_no,
+	void	(*clear_bar)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			     struct pci_epf_bar *epf_bar);
-	int	(*map_addr)(struct pci_epc *epc, u8 func_no,
+	int	(*map_addr)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			    phys_addr_t addr, u64 pci_addr, size_t size);
-	void	(*unmap_addr)(struct pci_epc *epc, u8 func_no,
+	void	(*unmap_addr)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			      phys_addr_t addr);
-	int	(*set_msi)(struct pci_epc *epc, u8 func_no, u8 interrupts);
-	int	(*get_msi)(struct pci_epc *epc, u8 func_no);
-	int	(*set_msix)(struct pci_epc *epc, u8 func_no, u16 interrupts,
-			    enum pci_barno, u32 offset);
-	int	(*get_msix)(struct pci_epc *epc, u8 func_no);
-	int	(*raise_irq)(struct pci_epc *epc, u8 func_no,
+	int	(*set_msi)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
+			   u8 interrupts);
+	int	(*get_msi)(struct pci_epc *epc, u8 func_no, u8 vfunc_no);
+	int	(*set_msix)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
+			    u16 interrupts, enum pci_barno, u32 offset);
+	int	(*get_msix)(struct pci_epc *epc, u8 func_no, u8 vfunc_no);
+	int	(*raise_irq)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			     enum pci_epc_irq_type type, u16 interrupt_num);
-	int	(*map_msi_irq)(struct pci_epc *epc, u8 func_no,
+	int	(*map_msi_irq)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			       phys_addr_t phys_addr, u8 interrupt_num,
 			       u32 entry_size, u32 *msi_data,
 			       u32 *msi_addr_offset);
 	int	(*start)(struct pci_epc *epc);
 	void	(*stop)(struct pci_epc *epc);
 	const struct pci_epc_features* (*get_features)(struct pci_epc *epc,
-						       u8 func_no);
+						       u8 func_no, u8 vfunc_no);
 	struct module *owner;
 };
 
@@ -128,6 +129,8 @@ struct pci_epc_mem {
  *       single window.
  * @num_windows: number of windows supported by device
  * @max_functions: max number of functions that can be configured in this EPC
+ * @max_vfs: Array indicating the maximum number of virtual functions that can
+ *   be associated with each physical function
  * @group: configfs group representing the PCI EPC device
  * @lock: mutex to protect pci_epc ops
  * @function_num_map: bitmap to manage physical function number
@@ -141,6 +144,7 @@ struct pci_epc {
 	struct pci_epc_mem		*mem;
 	unsigned int			num_windows;
 	u8				max_functions;
+	u8				*max_vfs;
 	struct config_group		*group;
 	/* mutex to protect against concurrent access of EP controller */
 	struct mutex			lock;
@@ -208,31 +212,32 @@ void pci_epc_linkup(struct pci_epc *epc);
 void pci_epc_init_notify(struct pci_epc *epc);
 void pci_epc_remove_epf(struct pci_epc *epc, struct pci_epf *epf,
 			enum pci_epc_interface_type type);
-int pci_epc_write_header(struct pci_epc *epc, u8 func_no,
+int pci_epc_write_header(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			 struct pci_epf_header *hdr);
-int pci_epc_set_bar(struct pci_epc *epc, u8 func_no,
+int pci_epc_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 		    struct pci_epf_bar *epf_bar);
-void pci_epc_clear_bar(struct pci_epc *epc, u8 func_no,
+void pci_epc_clear_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 		       struct pci_epf_bar *epf_bar);
-int pci_epc_map_addr(struct pci_epc *epc, u8 func_no,
+int pci_epc_map_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 		     phys_addr_t phys_addr,
 		     u64 pci_addr, size_t size);
-void pci_epc_unmap_addr(struct pci_epc *epc, u8 func_no,
+void pci_epc_unmap_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			phys_addr_t phys_addr);
-int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts);
-int pci_epc_get_msi(struct pci_epc *epc, u8 func_no);
-int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts,
-		     enum pci_barno, u32 offset);
-int pci_epc_get_msix(struct pci_epc *epc, u8 func_no);
-int pci_epc_map_msi_irq(struct pci_epc *epc, u8 func_no,
+int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
+		    u8 interrupts);
+int pci_epc_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no);
+int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
+		     u16 interrupts, enum pci_barno, u32 offset);
+int pci_epc_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no);
+int pci_epc_map_msi_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			phys_addr_t phys_addr, u8 interrupt_num,
 			u32 entry_size, u32 *msi_data, u32 *msi_addr_offset);
-int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no,
+int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 		      enum pci_epc_irq_type type, u16 interrupt_num);
 int pci_epc_start(struct pci_epc *epc);
 void pci_epc_stop(struct pci_epc *epc);
 const struct pci_epc_features *pci_epc_get_features(struct pci_epc *epc,
-						    u8 func_no);
+						    u8 func_no, u8 vfunc_no);
 enum pci_barno
 pci_epc_get_first_free_bar(const struct pci_epc_features *epc_features);
 enum pci_barno pci_epc_get_next_free_bar(const struct pci_epc_features

include/linux/pci-epf.h

@@ -121,8 +121,10 @@ struct pci_epf_bar {
  * @bar: represents the BAR of EPF device
  * @msi_interrupts: number of MSI interrupts required by this function
  * @msix_interrupts: number of MSI-X interrupts required by this function
- * @func_no: unique function number within this endpoint device
+ * @func_no: unique (physical) function number within this endpoint device
+ * @vfunc_no: unique virtual function number within a physical function
  * @epc: the EPC device to which this EPF device is bound
+ * @epf_pf: the physical EPF device to which this virtual EPF device is bound
  * @driver: the EPF driver to which this EPF device is bound
  * @list: to add pci_epf as a list of PCI endpoint functions to pci_epc
  * @nb: notifier block to notify EPF of any EPC events (like linkup)
@@ -133,6 +135,10 @@ struct pci_epf_bar {
  * @sec_epc_bar: represents the BAR of EPF device associated with secondary EPC
  * @sec_epc_func_no: unique (physical) function number within the secondary EPC
  * @group: configfs group associated with the EPF device
+ * @is_bound: indicates if bind notification to function driver has been invoked
+ * @is_vf: true - virtual function, false - physical function
+ * @vfunction_num_map: bitmap to manage virtual function number
+ * @pci_vepf: list of virtual endpoint functions associated with this function
  */
 struct pci_epf {
 	struct device		dev;
@@ -142,8 +148,10 @@ struct pci_epf {
 	u8			msi_interrupts;
 	u16			msix_interrupts;
 	u8			func_no;
+	u8			vfunc_no;
 
 	struct pci_epc		*epc;
+	struct pci_epf		*epf_pf;
 	struct pci_epf_driver	*driver;
 	struct list_head	list;
 	struct notifier_block   nb;
@@ -156,6 +164,10 @@ struct pci_epf {
 	struct pci_epf_bar	sec_epc_bar[6];
 	u8			sec_epc_func_no;
 	struct config_group	*group;
+	unsigned int		is_bound;
+	unsigned int		is_vf;
+	unsigned long		vfunction_num_map;
+	struct list_head	pci_vepf;
 };
 
 /**
@@ -199,4 +211,6 @@ int pci_epf_bind(struct pci_epf *epf);
 void pci_epf_unbind(struct pci_epf *epf);
 struct config_group *pci_epf_type_add_cfs(struct pci_epf *epf,
 					  struct config_group *group);
+int pci_epf_add_vepf(struct pci_epf *epf_pf, struct pci_epf *epf_vf);
+void pci_epf_remove_vepf(struct pci_epf *epf_pf, struct pci_epf *epf_vf);
 #endif /* __LINUX_PCI_EPF_H */

include/linux/pci.h

@@ -49,6 +49,12 @@
 			       PCI_STATUS_SIG_TARGET_ABORT | \
 			       PCI_STATUS_PARITY)
 
+/* Number of reset methods used in pci_reset_fn_methods array in pci.c */
+#define PCI_NUM_RESET_METHODS 7
+
+#define PCI_RESET_PROBE		true
+#define PCI_RESET_DO_RESET	false
+
 /*
  * The PCI interface treats multi-function devices as independent
  * devices.  The slot/function address of each device is encoded
@@ -288,21 +294,14 @@ enum pci_bus_speed {
 enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev);
 enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev);
 
-struct pci_cap_saved_data {
-	u16		cap_nr;
-	bool		cap_extended;
-	unsigned int	size;
-	u32		data[];
-};
-
-struct pci_cap_saved_state {
-	struct hlist_node		next;
-	struct pci_cap_saved_data	cap;
+struct pci_vpd {
+	struct mutex	lock;
+	unsigned int	len;
+	u8		cap;
 };
 
 struct irq_affinity;
 struct pcie_link_state;
-struct pci_vpd;
 struct pci_sriov;
 struct pci_p2pdma;
 struct rcec_ea;
@@ -333,6 +332,7 @@ struct pci_dev {
 	struct rcec_ea	*rcec_ea;	/* RCEC cached endpoint association */
 	struct pci_dev  *rcec;          /* Associated RCEC device */
 #endif
+	u32		devcap;		/* PCIe Device Capabilities */
 	u8		pcie_cap;	/* PCIe capability offset */
 	u8		msi_cap;	/* MSI capability offset */
 	u8		msix_cap;	/* MSI-X capability offset */
@@ -388,6 +388,7 @@ struct pci_dev {
 					   supported from root to here */
 	u16		l1ss;		/* L1SS Capability pointer */
 #endif
+	unsigned int	pasid_no_tlp:1;		/* PASID works without TLP Prefix */
 	unsigned int	eetlp_prefix_path:1;	/* End-to-End TLP Prefix */
 
 	pci_channel_state_t error_state;	/* Current connectivity state */
@@ -427,7 +428,6 @@ struct pci_dev {
 	unsigned int	state_saved:1;
 	unsigned int	is_physfn:1;
 	unsigned int	is_virtfn:1;
-	unsigned int	reset_fn:1;
 	unsigned int	is_hotplug_bridge:1;
 	unsigned int	shpc_managed:1;		/* SHPC owned by shpchp */
 	unsigned int	is_thunderbolt:1;	/* Thunderbolt controller */
@@ -473,7 +473,7 @@ struct pci_dev {
 #ifdef CONFIG_PCI_MSI
 	const struct attribute_group **msi_irq_groups;
 #endif
-	struct pci_vpd *vpd;
+	struct pci_vpd	vpd;
 #ifdef CONFIG_PCIE_DPC
 	u16		dpc_cap;
 	unsigned int	dpc_rp_extensions:1;
@@ -505,6 +505,9 @@ struct pci_dev {
 	char		*driver_override; /* Driver name to force a match */
 
 	unsigned long	priv_flags;	/* Private flags for the PCI driver */
+
+	/* These methods index pci_reset_fn_methods[] */
+	u8 reset_methods[PCI_NUM_RESET_METHODS]; /* In priority order */
 };
 
 static inline struct pci_dev *pci_physfn(struct pci_dev *dev)
@@ -526,6 +529,16 @@ static inline int pci_channel_offline(struct pci_dev *pdev)
 	return (pdev->error_state != pci_channel_io_normal);
 }
 
+/*
+ * Currently in ACPI spec, for each PCI host bridge, PCI Segment
+ * Group number is limited to a 16-bit value, therefore (int)-1 is
+ * not a valid PCI domain number, and can be used as a sentinel
+ * value indicating ->domain_nr is not set by the driver (and
+ * CONFIG_PCI_DOMAINS_GENERIC=y archs will set it with
+ * pci_bus_find_domain_nr()).
+ */
+#define PCI_DOMAIN_NR_NOT_SET (-1)
+
 struct pci_host_bridge {
 	struct device	dev;
 	struct pci_bus	*bus;		/* Root bus */
@@ -533,6 +546,7 @@ struct pci_host_bridge {
 	struct pci_ops	*child_ops;
 	void		*sysdata;
 	int		busnr;
+	int		domain_nr;
 	struct list_head windows;	/* resource_entry */
 	struct list_head dma_ranges;	/* dma ranges resource list */
 	u8 (*swizzle_irq)(struct pci_dev *, u8 *); /* Platform IRQ swizzler */
@@ -1257,7 +1271,7 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev,
 			     enum pci_bus_speed *speed,
 			     enum pcie_link_width *width);
 void pcie_print_link_status(struct pci_dev *dev);
-bool pcie_has_flr(struct pci_dev *dev);
+int pcie_reset_flr(struct pci_dev *dev, bool probe);
 int pcie_flr(struct pci_dev *dev);
 int __pci_reset_function_locked(struct pci_dev *dev);
 int pci_reset_function(struct pci_dev *dev);
@@ -1307,12 +1321,6 @@ int pci_load_saved_state(struct pci_dev *dev,
 			 struct pci_saved_state *state);
 int pci_load_and_free_saved_state(struct pci_dev *dev,
 				  struct pci_saved_state **state);
-struct pci_cap_saved_state *pci_find_saved_cap(struct pci_dev *dev, char cap);
-struct pci_cap_saved_state *pci_find_saved_ext_cap(struct pci_dev *dev,
-						   u16 cap);
-int pci_add_cap_save_buffer(struct pci_dev *dev, char cap, unsigned int size);
-int pci_add_ext_cap_save_buffer(struct pci_dev *dev,
-				u16 cap, unsigned int size);
 int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state);
 int pci_set_power_state(struct pci_dev *dev, pci_power_t state);
 pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state);
@@ -1779,8 +1787,9 @@ static inline void pci_disable_device(struct pci_dev *dev) { }
 static inline int pcim_enable_device(struct pci_dev *pdev) { return -EIO; }
 static inline int pci_assign_resource(struct pci_dev *dev, int i)
 { return -EBUSY; }
-static inline int __pci_register_driver(struct pci_driver *drv,
-					struct module *owner)
+static inline int __must_check __pci_register_driver(struct pci_driver *drv,
+						     struct module *owner,
+						     const char *mod_name)
 { return 0; }
 static inline int pci_register_driver(struct pci_driver *drv)
 { return 0; }
@@ -1920,9 +1929,7 @@ int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma);
 #define pci_resource_end(dev, bar)	((dev)->resource[(bar)].end)
 #define pci_resource_flags(dev, bar)	((dev)->resource[(bar)].flags)
 #define pci_resource_len(dev,bar) \
-	((pci_resource_start((dev), (bar)) == 0 &&	\
-	  pci_resource_end((dev), (bar)) ==		\
-	  pci_resource_start((dev), (bar))) ? 0 :	\
+	((pci_resource_end((dev), (bar)) == 0) ? 0 :	\
 							\
 	 (pci_resource_end((dev), (bar)) -		\
 	  pci_resource_start((dev), (bar)) + 1))
@@ -2289,20 +2296,6 @@ int pci_enable_atomic_ops_to_root(struct pci_dev *dev, u32 cap_mask);
 #define PCI_VPD_LRDT_RO_DATA		PCI_VPD_LRDT_ID(PCI_VPD_LTIN_RO_DATA)
 #define PCI_VPD_LRDT_RW_DATA		PCI_VPD_LRDT_ID(PCI_VPD_LTIN_RW_DATA)
 
-/* Small Resource Data Type Tag Item Names */
-#define PCI_VPD_STIN_END		0x0f	/* End */
-
-#define PCI_VPD_SRDT_END		(PCI_VPD_STIN_END << 3)
-
-#define PCI_VPD_SRDT_TIN_MASK		0x78
-#define PCI_VPD_SRDT_LEN_MASK		0x07
-#define PCI_VPD_LRDT_TIN_MASK		0x7f
-
-#define PCI_VPD_LRDT_TAG_SIZE		3
-#define PCI_VPD_SRDT_TAG_SIZE		1
-
-#define PCI_VPD_INFO_FLD_HDR_SIZE	3
-
 #define PCI_VPD_RO_KEYWORD_PARTNO	"PN"
 #define PCI_VPD_RO_KEYWORD_SERIALNO	"SN"
 #define PCI_VPD_RO_KEYWORD_MFR_ID	"MN"
@@ -2310,83 +2303,45 @@ int pci_enable_atomic_ops_to_root(struct pci_dev *dev, u32 cap_mask);
 #define PCI_VPD_RO_KEYWORD_CHKSUM	"RV"
 
 /**
- * pci_vpd_lrdt_size - Extracts the Large Resource Data Type length
- * @lrdt: Pointer to the beginning of the Large Resource Data Type tag
+ * pci_vpd_alloc - Allocate buffer and read VPD into it
+ * @dev: PCI device
+ * @size: pointer to field where VPD length is returned
  *
- * Returns the extracted Large Resource Data Type length.
+ * Returns pointer to allocated buffer or an ERR_PTR in case of failure
  */
-static inline u16 pci_vpd_lrdt_size(const u8 *lrdt)
-{
-	return (u16)lrdt[1] + ((u16)lrdt[2] << 8);
-}
+void *pci_vpd_alloc(struct pci_dev *dev, unsigned int *size);
 
 /**
- * pci_vpd_lrdt_tag - Extracts the Large Resource Data Type Tag Item
- * @lrdt: Pointer to the beginning of the Large Resource Data Type tag
+ * pci_vpd_find_id_string - Locate id string in VPD
+ * @buf: Pointer to buffered VPD data
+ * @len: The length of the buffer area in which to search
+ * @size: Pointer to field where length of id string is returned
  *
- * Returns the extracted Large Resource Data Type Tag item.
+ * Returns the index of the id string or -ENOENT if not found.
  */
-static inline u16 pci_vpd_lrdt_tag(const u8 *lrdt)
-{
-	return (u16)(lrdt[0] & PCI_VPD_LRDT_TIN_MASK);
-}
+int pci_vpd_find_id_string(const u8 *buf, unsigned int len, unsigned int *size);
 
 /**
- * pci_vpd_srdt_size - Extracts the Small Resource Data Type length
- * @srdt: Pointer to the beginning of the Small Resource Data Type tag
- *
- * Returns the extracted Small Resource Data Type length.
- */
-static inline u8 pci_vpd_srdt_size(const u8 *srdt)
-{
-	return (*srdt) & PCI_VPD_SRDT_LEN_MASK;
-}
-
-/**
- * pci_vpd_srdt_tag - Extracts the Small Resource Data Type Tag Item
- * @srdt: Pointer to the beginning of the Small Resource Data Type tag
- *
- * Returns the extracted Small Resource Data Type Tag Item.
- */
-static inline u8 pci_vpd_srdt_tag(const u8 *srdt)
-{
-	return ((*srdt) & PCI_VPD_SRDT_TIN_MASK) >> 3;
-}
-
-/**
- * pci_vpd_info_field_size - Extracts the information field length
- * @info_field: Pointer to the beginning of an information field header
- *
- * Returns the extracted information field length.
- */
-static inline u8 pci_vpd_info_field_size(const u8 *info_field)
-{
-	return info_field[2];
-}
-
-/**
- * pci_vpd_find_tag - Locates the Resource Data Type tag provided
- * @buf: Pointer to buffered vpd data
- * @len: The length of the vpd buffer
- * @rdt: The Resource Data Type to search for
- *
- * Returns the index where the Resource Data Type was found or
- * -ENOENT otherwise.
- */
-int pci_vpd_find_tag(const u8 *buf, unsigned int len, u8 rdt);
-
-/**
- * pci_vpd_find_info_keyword - Locates an information field keyword in the VPD
- * @buf: Pointer to buffered vpd data
- * @off: The offset into the buffer at which to begin the search
- * @len: The length of the buffer area, relative to off, in which to search
+ * pci_vpd_find_ro_info_keyword - Locate info field keyword in VPD RO section
+ * @buf: Pointer to buffered VPD data
+ * @len: The length of the buffer area in which to search
  * @kw: The keyword to search for
+ * @size: Pointer to field where length of found keyword data is returned
  *
- * Returns the index where the information field keyword was found or
- * -ENOENT otherwise.
+ * Returns the index of the information field keyword data or -ENOENT if
+ * not found.
  */
-int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off,
-			      unsigned int len, const char *kw);
+int pci_vpd_find_ro_info_keyword(const void *buf, unsigned int len,
+				 const char *kw, unsigned int *size);
+
+/**
+ * pci_vpd_check_csum - Check VPD checksum
+ * @buf: Pointer to buffered VPD data
+ * @len: VPD size
+ *
+ * Returns 1 if VPD has no checksum, otherwise 0 or an errno
+ */
+int pci_vpd_check_csum(const void *buf, unsigned int len);
 
 /* PCI <-> OF binding helpers */
 #ifdef CONFIG_OF

include/linux/pci_hotplug.h

@@ -44,7 +44,7 @@ struct hotplug_slot_ops {
 	int (*get_attention_status)	(struct hotplug_slot *slot, u8 *value);
 	int (*get_latch_status)		(struct hotplug_slot *slot, u8 *value);
 	int (*get_adapter_status)	(struct hotplug_slot *slot, u8 *value);
-	int (*reset_slot)		(struct hotplug_slot *slot, int probe);
+	int (*reset_slot)		(struct hotplug_slot *slot, bool probe);
 };
 
 /**

include/linux/pci_ids.h

@@ -2453,7 +2453,8 @@
 #define PCI_VENDOR_ID_TDI               0x192E
 #define PCI_DEVICE_ID_TDI_EHCI          0x0101
 
-#define PCI_VENDOR_ID_FREESCALE		0x1957
+#define PCI_VENDOR_ID_FREESCALE		0x1957	/* duplicate: NXP */
+#define PCI_VENDOR_ID_NXP		0x1957	/* duplicate: FREESCALE */
 #define PCI_DEVICE_ID_MPC8308		0xc006
 #define PCI_DEVICE_ID_MPC8315E		0x00b4
 #define PCI_DEVICE_ID_MPC8315		0x00b5

include/linux/platform_data/dma-dw.h

@@ -41,36 +41,39 @@ struct dw_dma_slave {
 
 /**
  * struct dw_dma_platform_data - Controller configuration parameters
+ * @nr_masters: Number of AHB masters supported by the controller
  * @nr_channels: Number of channels supported by hardware (max 8)
  * @chan_allocation_order: Allocate channels starting from 0 or 7
  * @chan_priority: Set channel priority increasing from 0 to 7 or 7 to 0.
  * @block_size: Maximum block size supported by the controller
- * @nr_masters: Number of AHB masters supported by the controller
  * @data_width: Maximum data width supported by hardware per AHB master
  *		(in bytes, power of 2)
  * @multi_block: Multi block transfers supported by hardware per channel.
  * @max_burst: Maximum value of burst transaction size supported by hardware
  *	       per channel (in units of CTL.SRC_TR_WIDTH/CTL.DST_TR_WIDTH).
  * @protctl: Protection control signals setting per channel.
+ * @quirks: Optional platform quirks.
  */
 struct dw_dma_platform_data {
-	unsigned int	nr_channels;
+	u32		nr_masters;
+	u32		nr_channels;
 #define CHAN_ALLOCATION_ASCENDING	0	/* zero to seven */
 #define CHAN_ALLOCATION_DESCENDING	1	/* seven to zero */
-	unsigned char	chan_allocation_order;
+	u32		chan_allocation_order;
 #define CHAN_PRIORITY_ASCENDING		0	/* chan0 highest */
 #define CHAN_PRIORITY_DESCENDING	1	/* chan7 highest */
-	unsigned char	chan_priority;
-	unsigned int	block_size;
-	unsigned char	nr_masters;
-	unsigned char	data_width[DW_DMA_MAX_NR_MASTERS];
-	unsigned char	multi_block[DW_DMA_MAX_NR_CHANNELS];
+	u32		chan_priority;
+	u32		block_size;
+	u32		data_width[DW_DMA_MAX_NR_MASTERS];
+	u32		multi_block[DW_DMA_MAX_NR_CHANNELS];
 	u32		max_burst[DW_DMA_MAX_NR_CHANNELS];
 #define CHAN_PROTCTL_PRIVILEGED		BIT(0)
 #define CHAN_PROTCTL_BUFFERABLE		BIT(1)
 #define CHAN_PROTCTL_CACHEABLE		BIT(2)
 #define CHAN_PROTCTL_MASK		GENMASK(2, 0)
-	unsigned char	protctl;
+	u32		protctl;
+#define DW_DMA_QUIRK_XBAR_PRESENT	BIT(0)
+	u32		quirks;
 };
 
 #endif /* _PLATFORM_DATA_DMA_DW_H */

include/linux/pwm.h

@@ -404,7 +404,7 @@ int pwm_set_chip_data(struct pwm_device *pwm, void *data);
 void *pwm_get_chip_data(struct pwm_device *pwm);
 
 int pwmchip_add(struct pwm_chip *chip);
-int pwmchip_remove(struct pwm_chip *chip);
+void pwmchip_remove(struct pwm_chip *chip);
 
 int devm_pwmchip_add(struct device *dev, struct pwm_chip *chip);
 

include/linux/qcom_scm.h

@@ -109,6 +109,12 @@ extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt,
 			     u32 *resp);
 
 extern int qcom_scm_qsmmu500_wait_safe_toggle(bool en);
+
+extern int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val,
+			      u64 limit_node, u32 node_id, u64 version);
+extern int qcom_scm_lmh_profile_change(u32 profile_id);
+extern bool qcom_scm_lmh_dcvsh_available(void);
+
 #else
 
 #include <linux/errno.h>
@@ -170,5 +176,13 @@ static inline int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt,
 
 static inline int qcom_scm_qsmmu500_wait_safe_toggle(bool en)
 		{ return -ENODEV; }
+
+static inline int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val,
+				     u64 limit_node, u32 node_id, u64 version)
+		{ return -ENODEV; }
+
+static inline int qcom_scm_lmh_profile_change(u32 profile_id) { return -ENODEV; }
+
+static inline bool qcom_scm_lmh_dcvsh_available(void) { return -ENODEV; }
 #endif
 #endif

include/linux/rwsem.h

@@ -142,22 +142,14 @@ struct rw_semaphore {
 #define DECLARE_RWSEM(lockname) \
 	struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname)
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-extern void  __rwsem_init(struct rw_semaphore *rwsem, const char *name,
+extern void  __init_rwsem(struct rw_semaphore *rwsem, const char *name,
 			  struct lock_class_key *key);
-#else
-static inline void  __rwsem_init(struct rw_semaphore *rwsem, const char *name,
-				 struct lock_class_key *key)
-{
-}
-#endif
 
 #define init_rwsem(sem)						\
 do {								\
 	static struct lock_class_key __key;			\
 								\
-	init_rwbase_rt(&(sem)->rwbase);			\
-	__rwsem_init((sem), #sem, &__key);			\
+	__init_rwsem((sem), #sem, &__key);			\
 } while (0)
 
 static __always_inline int rwsem_is_locked(struct rw_semaphore *sem)

include/linux/sched/user.h

@@ -4,6 +4,7 @@
 
 #include <linux/uidgid.h>
 #include <linux/atomic.h>
+#include <linux/percpu_counter.h>
 #include <linux/refcount.h>
 #include <linux/ratelimit.h>
 
@@ -13,7 +14,7 @@
 struct user_struct {
 	refcount_t __count;	/* reference count */
 #ifdef CONFIG_EPOLL
-	atomic_long_t epoll_watches; /* The number of file descriptors currently watched */
+	struct percpu_counter epoll_watches; /* The number of file descriptors currently watched */
 #endif
 	unsigned long unix_inflight;	/* How many files in flight in unix sockets */
 	atomic_long_t pipe_bufs;  /* how many pages are allocated in pipe buffers */

include/linux/skbuff.h

@@ -1940,7 +1940,7 @@ static inline void __skb_insert(struct sk_buff *newsk,
 	WRITE_ONCE(newsk->prev, prev);
 	WRITE_ONCE(next->prev, newsk);
 	WRITE_ONCE(prev->next, newsk);
-	list->qlen++;
+	WRITE_ONCE(list->qlen, list->qlen + 1);
 }
 
 static inline void __skb_queue_splice(const struct sk_buff_head *list,

include/linux/slub_def.h

@@ -10,6 +10,7 @@
 #include <linux/kfence.h>
 #include <linux/kobject.h>
 #include <linux/reciprocal_div.h>
+#include <linux/local_lock.h>
 
 enum stat_item {
 	ALLOC_FASTPATH,		/* Allocation from cpu slab */
@@ -40,6 +41,10 @@ enum stat_item {
 	CPU_PARTIAL_DRAIN,	/* Drain cpu partial to node partial */
 	NR_SLUB_STAT_ITEMS };
 
+/*
+ * When changing the layout, make sure freelist and tid are still compatible
+ * with this_cpu_cmpxchg_double() alignment requirements.
+ */
 struct kmem_cache_cpu {
 	void **freelist;	/* Pointer to next available object */
 	unsigned long tid;	/* Globally unique transaction id */
@@ -47,6 +52,7 @@ struct kmem_cache_cpu {
 #ifdef CONFIG_SLUB_CPU_PARTIAL
 	struct page *partial;	/* Partially allocated frozen slabs */
 #endif
+	local_lock_t lock;	/* Protects the fields above */
 #ifdef CONFIG_SLUB_STATS
 	unsigned stat[NR_SLUB_STAT_ITEMS];
 #endif

include/linux/syscalls.h

@@ -1373,6 +1373,9 @@ long ksys_old_shmctl(int shmid, int cmd, struct shmid_ds __user *buf);
 long compat_ksys_semtimedop(int semid, struct sembuf __user *tsems,
 			    unsigned int nsops,
 			    const struct old_timespec32 __user *timeout);
+long __do_semtimedop(int semid, struct sembuf *tsems, unsigned int nsops,
+		     const struct timespec64 *timeout,
+		     struct ipc_namespace *ns);
 
 int __sys_getsockopt(int fd, int level, int optname, char __user *optval,
 		int __user *optlen);

include/linux/thermal.h

@@ -285,7 +285,7 @@ struct thermal_zone_params {
 };
 
 /**
- * struct thermal_zone_of_device_ops - scallbacks for handling DT based zones
+ * struct thermal_zone_of_device_ops - callbacks for handling DT based zones
  *
  * Mandatory:
  * @get_temp: a pointer to a function that reads the sensor temperature.
@@ -404,12 +404,13 @@ static inline void thermal_zone_device_unregister(
 	struct thermal_zone_device *tz)
 { }
 static inline struct thermal_cooling_device *
-thermal_cooling_device_register(char *type, void *devdata,
+thermal_cooling_device_register(const char *type, void *devdata,
 	const struct thermal_cooling_device_ops *ops)
 { return ERR_PTR(-ENODEV); }
 static inline struct thermal_cooling_device *
 thermal_of_cooling_device_register(struct device_node *np,
-	char *type, void *devdata, const struct thermal_cooling_device_ops *ops)
+	const char *type, void *devdata,
+	const struct thermal_cooling_device_ops *ops)
 { return ERR_PTR(-ENODEV); }
 static inline struct thermal_cooling_device *
 devm_thermal_of_cooling_device_register(struct device *dev,

include/linux/threads.h

@@ -38,7 +38,7 @@
  * Define a minimum number of pids per cpu.  Heuristically based
  * on original pid max of 32k for 32 cpus.  Also, increase the
  * minimum settable value for pid_max on the running system based
- * on similar defaults.  See kernel/pid.c:pidmap_init() for details.
+ * on similar defaults.  See kernel/pid.c:pid_idr_init() for details.
  */
 #define PIDS_PER_CPU_DEFAULT	1024
 #define PIDS_PER_CPU_MIN	8

include/linux/time64.h

@@ -25,7 +25,9 @@ struct itimerspec64 {
 #define TIME64_MIN			(-TIME64_MAX - 1)
 
 #define KTIME_MAX			((s64)~((u64)1 << 63))
+#define KTIME_MIN			(-KTIME_MAX - 1)
 #define KTIME_SEC_MAX			(KTIME_MAX / NSEC_PER_SEC)
+#define KTIME_SEC_MIN			(KTIME_MIN / NSEC_PER_SEC)
 
 /*
  * Limits for settimeofday():
@@ -124,10 +126,13 @@ static inline bool timespec64_valid_settod(const struct timespec64 *ts)
  */
 static inline s64 timespec64_to_ns(const struct timespec64 *ts)
 {
-	/* Prevent multiplication overflow */
-	if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX)
+	/* Prevent multiplication overflow / underflow */
+	if (ts->tv_sec >= KTIME_SEC_MAX)
 		return KTIME_MAX;
 
+	if (ts->tv_sec <= KTIME_SEC_MIN)
+		return KTIME_MIN;
+
 	return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec;
 }
 

include/linux/uaccess.h

@@ -200,16 +200,6 @@ copy_to_user(void __user *to, const void *from, unsigned long n)
 		n = _copy_to_user(to, from, n);
 	return n;
 }
-#ifdef CONFIG_COMPAT
-static __always_inline unsigned long __must_check
-copy_in_user(void __user *to, const void __user *from, unsigned long n)
-{
-	might_fault();
-	if (access_ok(to, n) && access_ok(from, n))
-		n = raw_copy_in_user(to, from, n);
-	return n;
-}
-#endif
 
 #ifndef copy_mc_to_kernel
 /*

include/linux/uio.h

@@ -47,6 +47,7 @@ struct iov_iter {
 		};
 		loff_t xarray_start;
 	};
+	size_t truncated;
 };
 
 static inline enum iter_type iov_iter_type(const struct iov_iter *i)
@@ -254,8 +255,10 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count)
 	 * conversion in assignement is by definition greater than all
 	 * values of size_t, including old i->count.
 	 */
-	if (i->count > count)
+	if (i->count > count) {
+		i->truncated += i->count - count;
 		i->count = count;
+	}
 }
 
 /*
@@ -264,6 +267,7 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count)
  */
 static inline void iov_iter_reexpand(struct iov_iter *i, size_t count)
 {
+	i->truncated -= count - i->count;
 	i->count = count;
 }
 

include/linux/units.h

@@ -20,9 +20,13 @@
 #define PICO	1000000000000ULL
 #define FEMTO	1000000000000000ULL
 
-#define MILLIWATT_PER_WATT	1000L
-#define MICROWATT_PER_MILLIWATT	1000L
-#define MICROWATT_PER_WATT	1000000L
+#define HZ_PER_KHZ		1000UL
+#define KHZ_PER_MHZ		1000UL
+#define HZ_PER_MHZ		1000000UL
+
+#define MILLIWATT_PER_WATT	1000UL
+#define MICROWATT_PER_MILLIWATT	1000UL
+#define MICROWATT_PER_WATT	1000000UL
 
 #define ABSOLUTE_ZERO_MILLICELSIUS -273150
 

include/linux/vdpa.h

@@ -43,17 +43,17 @@ struct vdpa_vq_state_split {
  * @last_used_idx: used index
  */
 struct vdpa_vq_state_packed {
-        u16	last_avail_counter:1;
-        u16	last_avail_idx:15;
-        u16	last_used_counter:1;
-        u16	last_used_idx:15;
+	u16	last_avail_counter:1;
+	u16	last_avail_idx:15;
+	u16	last_used_counter:1;
+	u16	last_used_idx:15;
 };
 
 struct vdpa_vq_state {
-     union {
-          struct vdpa_vq_state_split split;
-          struct vdpa_vq_state_packed packed;
-     };
+	union {
+		struct vdpa_vq_state_split split;
+		struct vdpa_vq_state_packed packed;
+	};
 };
 
 struct vdpa_mgmt_dev;
@@ -65,6 +65,7 @@ struct vdpa_mgmt_dev;
  * @config: the configuration ops for this device.
  * @index: device index
  * @features_valid: were features initialized? for legacy guests
+ * @use_va: indicate whether virtual address must be used by this device
  * @nvqs: maximum number of supported virtqueues
  * @mdev: management device pointer; caller must setup when registering device as part
  *	  of dev_add() mgmtdev ops callback before invoking _vdpa_register_device().
@@ -75,6 +76,7 @@ struct vdpa_device {
 	const struct vdpa_config_ops *config;
 	unsigned int index;
 	bool features_valid;
+	bool use_va;
 	int nvqs;
 	struct vdpa_mgmt_dev *mdev;
 };
@@ -89,6 +91,16 @@ struct vdpa_iova_range {
 	u64 last;
 };
 
+/**
+ * Corresponding file area for device memory mapping
+ * @file: vma->vm_file for the mapping
+ * @offset: mapping offset in the vm_file
+ */
+struct vdpa_map_file {
+	struct file *file;
+	u64 offset;
+};
+
 /**
  * struct vdpa_config_ops - operations for configuring a vDPA device.
  * Note: vDPA device drivers are required to implement all of the
@@ -131,7 +143,7 @@ struct vdpa_iova_range {
  *				@vdev: vdpa device
  *				@idx: virtqueue index
  *				@state: pointer to returned state (last_avail_idx)
- * @get_vq_notification: 	Get the notification area for a virtqueue
+ * @get_vq_notification:	Get the notification area for a virtqueue
  *				@vdev: vdpa device
  *				@idx: virtqueue index
  *				Returns the notifcation area
@@ -171,6 +183,9 @@ struct vdpa_iova_range {
  * @set_status:			Set the device status
  *				@vdev: vdpa device
  *				@status: virtio device status
+ * @reset:			Reset device
+ *				@vdev: vdpa device
+ *				Returns integer: success (0) or error (< 0)
  * @get_config_size:		Get the size of the configuration space
  *				@vdev: vdpa device
  *				Returns size_t: configuration size
@@ -255,6 +270,7 @@ struct vdpa_config_ops {
 	u32 (*get_vendor_id)(struct vdpa_device *vdev);
 	u8 (*get_status)(struct vdpa_device *vdev);
 	void (*set_status)(struct vdpa_device *vdev, u8 status);
+	int (*reset)(struct vdpa_device *vdev);
 	size_t (*get_config_size)(struct vdpa_device *vdev);
 	void (*get_config)(struct vdpa_device *vdev, unsigned int offset,
 			   void *buf, unsigned int len);
@@ -266,7 +282,7 @@ struct vdpa_config_ops {
 	/* DMA ops */
 	int (*set_map)(struct vdpa_device *vdev, struct vhost_iotlb *iotlb);
 	int (*dma_map)(struct vdpa_device *vdev, u64 iova, u64 size,
-		       u64 pa, u32 perm);
+		       u64 pa, u32 perm, void *opaque);
 	int (*dma_unmap)(struct vdpa_device *vdev, u64 iova, u64 size);
 
 	/* Free device resources */
@@ -275,7 +291,8 @@ struct vdpa_config_ops {
 
 struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 					const struct vdpa_config_ops *config,
-					size_t size, const char *name);
+					size_t size, const char *name,
+					bool use_va);
 
 /**
  * vdpa_alloc_device - allocate and initilaize a vDPA device
@@ -285,15 +302,16 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
  * @parent: the parent device
  * @config: the bus operations that is supported by this device
  * @name: name of the vdpa device
+ * @use_va: indicate whether virtual address must be used by this device
  *
  * Return allocated data structure or ERR_PTR upon error
  */
-#define vdpa_alloc_device(dev_struct, member, parent, config, name)   \
+#define vdpa_alloc_device(dev_struct, member, parent, config, name, use_va)   \
 			  container_of(__vdpa_alloc_device( \
 				       parent, config, \
 				       sizeof(dev_struct) + \
 				       BUILD_BUG_ON_ZERO(offsetof( \
-				       dev_struct, member)), name), \
+				       dev_struct, member)), name, use_va), \
 				       dev_struct, member)
 
 int vdpa_register_device(struct vdpa_device *vdev, int nvqs);
@@ -348,27 +366,27 @@ static inline struct device *vdpa_get_dma_dev(struct vdpa_device *vdev)
 	return vdev->dma_dev;
 }
 
-static inline void vdpa_reset(struct vdpa_device *vdev)
+static inline int vdpa_reset(struct vdpa_device *vdev)
 {
-        const struct vdpa_config_ops *ops = vdev->config;
+	const struct vdpa_config_ops *ops = vdev->config;
 
 	vdev->features_valid = false;
-        ops->set_status(vdev, 0);
+	return ops->reset(vdev);
 }
 
 static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features)
 {
-        const struct vdpa_config_ops *ops = vdev->config;
+	const struct vdpa_config_ops *ops = vdev->config;
 
 	vdev->features_valid = true;
-        return ops->set_features(vdev, features);
+	return ops->set_features(vdev, features);
 }
 
-
-static inline void vdpa_get_config(struct vdpa_device *vdev, unsigned offset,
-				   void *buf, unsigned int len)
+static inline void vdpa_get_config(struct vdpa_device *vdev,
+				   unsigned int offset, void *buf,
+				   unsigned int len)
 {
-        const struct vdpa_config_ops *ops = vdev->config;
+	const struct vdpa_config_ops *ops = vdev->config;
 
 	/*
 	 * Config accesses aren't supposed to trigger before features are set.

include/linux/vhost_iotlb.h

@@ -17,6 +17,7 @@ struct vhost_iotlb_map {
 	u32 perm;
 	u32 flags_padding;
 	u64 __subtree_last;
+	void *opaque;
 };
 
 #define VHOST_IOTLB_FLAG_RETIRE 0x1
@@ -29,6 +30,8 @@ struct vhost_iotlb {
 	unsigned int flags;
 };
 
+int vhost_iotlb_add_range_ctx(struct vhost_iotlb *iotlb, u64 start, u64 last,
+			      u64 addr, unsigned int perm, void *opaque);
 int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, u64 start, u64 last,
 			  u64 addr, unsigned int perm);
 void vhost_iotlb_del_range(struct vhost_iotlb *iotlb, u64 start, u64 last);

include/linux/vmalloc.h

@@ -225,9 +225,6 @@ static inline bool is_vm_area_hugepages(const void *addr)
 }
 
 #ifdef CONFIG_MMU
-int vmap_range(unsigned long addr, unsigned long end,
-			phys_addr_t phys_addr, pgprot_t prot,
-			unsigned int max_page_shift);
 void vunmap_range(unsigned long addr, unsigned long end);
 static inline void set_vm_flush_reset_perms(void *addr)
 {