1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 /* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ /* * include/linux/eventpoll.h ( Efficient event polling implementation ) * Copyright (C) 2001,...,2006 Davide Libenzi * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * Davide Libenzi <davidel@xmailserver.org> * */ #ifndef _UAPI_LINUX_EVENTPOLL_H #define _UAPI_LINUX_EVENTPOLL_H /* For O_CLOEXEC */ #include <linux/fcntl.h> #include <linux/types.h> /* Flags for epoll_create1. */ #define EPOLL_CLOEXEC O_CLOEXEC /* Valid opcodes to issue to sys_epoll_ctl() */ #define EPOLL_CTL_ADD 1 #define EPOLL_CTL_DEL 2 #define EPOLL_CTL_MOD 3 /* Epoll event masks */ #define EPOLLIN (__force __poll_t)0x00000001 #define EPOLLPRI (__force __poll_t)0x00000002 #define EPOLLOUT (__force __poll_t)0x00000004 #define EPOLLERR (__force __poll_t)0x00000008 #define EPOLLHUP (__force __poll_t)0x00000010 #define EPOLLNVAL (__force __poll_t)0x00000020 #define EPOLLRDNORM (__force __poll_t)0x00000040 #define EPOLLRDBAND (__force __poll_t)0x00000080 #define EPOLLWRNORM (__force __poll_t)0x00000100 #define EPOLLWRBAND (__force __poll_t)0x00000200 #define EPOLLMSG (__force __poll_t)0x00000400 #define EPOLLRDHUP (__force __poll_t)0x00002000 /* Set exclusive wakeup mode for the target file descriptor */ #define EPOLLEXCLUSIVE ((__force __poll_t)(1U << 28)) /* * Request the handling of system wakeup events so as to prevent system suspends * from happening while those events are being processed. * * Assuming neither EPOLLET nor EPOLLONESHOT is set, system suspends will not be * re-allowed until epoll_wait is called again after consuming the wakeup * event(s). * * Requires CAP_BLOCK_SUSPEND */ #define EPOLLWAKEUP ((__force __poll_t)(1U << 29)) /* Set the One Shot behaviour for the target file descriptor */ #define EPOLLONESHOT ((__force __poll_t)(1U << 30)) /* Set the Edge Triggered behaviour for the target file descriptor */ #define EPOLLET ((__force __poll_t)(1U << 31)) /* * On x86-64 make the 64bit structure have the same alignment as the * 32bit structure. This makes 32bit emulation easier. * * UML/x86_64 needs the same packing as x86_64 */ #ifdef __x86_64__ #define EPOLL_PACKED __attribute__((packed)) #else #define EPOLL_PACKED #endif struct epoll_event { __poll_t events; __u64 data; } EPOLL_PACKED; #ifdef CONFIG_PM_SLEEP static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev) { if ((epev->events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND)) epev->events &= ~EPOLLWAKEUP; } #else static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev) { epev->events &= ~EPOLLWAKEUP; } #endif #endif /* _UAPI_LINUX_EVENTPOLL_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_GENERIC_PGALLOC_H #define __ASM_GENERIC_PGALLOC_H #ifdef CONFIG_MMU #define GFP_PGTABLE_KERNEL (GFP_KERNEL | __GFP_ZERO) #define GFP_PGTABLE_USER (GFP_PGTABLE_KERNEL | __GFP_ACCOUNT) /** * __pte_alloc_one_kernel - allocate a page for PTE-level kernel page table * @mm: the mm_struct of the current context * * This function is intended for architectures that need * anything beyond simple page allocation. * * Return: pointer to the allocated memory or %NULL on error */ static inline pte_t *__pte_alloc_one_kernel(struct mm_struct *mm) { return (pte_t *)__get_free_page(GFP_PGTABLE_KERNEL); } #ifndef __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL /** * pte_alloc_one_kernel - allocate a page for PTE-level kernel page table * @mm: the mm_struct of the current context * * Return: pointer to the allocated memory or %NULL on error */ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) { return __pte_alloc_one_kernel(mm); } #endif /** * pte_free_kernel - free PTE-level kernel page table page * @mm: the mm_struct of the current context * @pte: pointer to the memory containing the page table */ static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { free_page((unsigned long)pte); } /** * __pte_alloc_one - allocate a page for PTE-level user page table * @mm: the mm_struct of the current context * @gfp: GFP flags to use for the allocation * * Allocates a page and runs the pgtable_pte_page_ctor(). * * This function is intended for architectures that need * anything beyond simple page allocation or must have custom GFP flags. * * Return: `struct page` initialized as page table or %NULL on error */ static inline pgtable_t __pte_alloc_one(struct mm_struct *mm, gfp_t gfp) { struct page *pte; pte = alloc_page(gfp); if (!pte) return NULL; if (!pgtable_pte_page_ctor(pte)) { __free_page(pte); return NULL; } return pte; } #ifndef __HAVE_ARCH_PTE_ALLOC_ONE /** * pte_alloc_one - allocate a page for PTE-level user page table * @mm: the mm_struct of the current context * * Allocates a page and runs the pgtable_pte_page_ctor(). * * Return: `struct page` initialized as page table or %NULL on error */ static inline pgtable_t pte_alloc_one(struct mm_struct *mm) { return __pte_alloc_one(mm, GFP_PGTABLE_USER); } #endif /* * Should really implement gc for free page table pages. This could be * done with a reference count in struct page. */ /** * pte_free - free PTE-level user page table page * @mm: the mm_struct of the current context * @pte_page: the `struct page` representing the page table */ static inline void pte_free(struct mm_struct *mm, struct page *pte_page) { pgtable_pte_page_dtor(pte_page); __free_page(pte_page); } #if CONFIG_PGTABLE_LEVELS > 2 #ifndef __HAVE_ARCH_PMD_ALLOC_ONE /** * pmd_alloc_one - allocate a page for PMD-level page table * @mm: the mm_struct of the current context * * Allocates a page and runs the pgtable_pmd_page_ctor(). * Allocations use %GFP_PGTABLE_USER in user context and * %GFP_PGTABLE_KERNEL in kernel context. * * Return: pointer to the allocated memory or %NULL on error */ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { struct page *page; gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; page = alloc_pages(gfp, 0); if (!page) return NULL; if (!pgtable_pmd_page_ctor(page)) { __free_pages(page, 0); return NULL; } return (pmd_t *)page_address(page); } #endif #ifndef __HAVE_ARCH_PMD_FREE static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); pgtable_pmd_page_dtor(virt_to_page(pmd)); free_page((unsigned long)pmd); } #endif #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 #ifndef __HAVE_ARCH_PUD_ALLOC_ONE /** * pud_alloc_one - allocate a page for PUD-level page table * @mm: the mm_struct of the current context * * Allocates a page using %GFP_PGTABLE_USER for user context and * %GFP_PGTABLE_KERNEL for kernel context. * * Return: pointer to the allocated memory or %NULL on error */ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_PGTABLE_USER; if (mm == &init_mm) gfp = GFP_PGTABLE_KERNEL; return (pud_t *)get_zeroed_page(gfp); } #endif static inline void pud_free(struct mm_struct *mm, pud_t *pud) { BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); free_page((unsigned long)pud); } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #ifndef __HAVE_ARCH_PGD_FREE static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { free_page((unsigned long)pgd); } #endif #endif /* CONFIG_MMU */ #endif /* __ASM_GENERIC_PGALLOC_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_UDP_TUNNEL_H #define __NET_UDP_TUNNEL_H #include <net/ip_tunnels.h> #include <net/udp.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/ipv6_stubs.h> #endif struct udp_port_cfg { u8 family; /* Used only for kernel-created sockets */ union { struct in_addr local_ip; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr local_ip6; #endif }; union { struct in_addr peer_ip; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr peer_ip6; #endif }; __be16 local_udp_port; __be16 peer_udp_port; int bind_ifindex; unsigned int use_udp_checksums:1, use_udp6_tx_checksums:1, use_udp6_rx_checksums:1, ipv6_v6only:1; }; int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp); #if IS_ENABLED(CONFIG_IPV6) int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp); #else static inline int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { return 0; } #endif static inline int udp_sock_create(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { if (cfg->family == AF_INET) return udp_sock_create4(net, cfg, sockp); if (cfg->family == AF_INET6) return udp_sock_create6(net, cfg, sockp); return -EPFNOSUPPORT; } typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb); typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk, struct sk_buff *skb); typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk); typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk, struct list_head *head, struct sk_buff *skb); typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb, int nhoff); struct udp_tunnel_sock_cfg { void *sk_user_data; /* user data used by encap_rcv call back */ /* Used for setting up udp_sock fields, see udp.h for details */ __u8 encap_type; udp_tunnel_encap_rcv_t encap_rcv; udp_tunnel_encap_err_lookup_t encap_err_lookup; udp_tunnel_encap_destroy_t encap_destroy; udp_tunnel_gro_receive_t gro_receive; udp_tunnel_gro_complete_t gro_complete; }; /* Setup the given (UDP) sock to receive UDP encapsulated packets */ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, struct udp_tunnel_sock_cfg *sock_cfg); /* -- List of parsable UDP tunnel types -- * * Adding to this list will result in serious debate. The main issue is * that this list is essentially a list of workarounds for either poorly * designed tunnels, or poorly designed device offloads. * * The parsing supported via these types should really be used for Rx * traffic only as the network stack will have already inserted offsets for * the location of the headers in the skb. In addition any ports that are * pushed should be kept within the namespace without leaking to other * devices such as VFs or other ports on the same device. * * It is strongly encouraged to use CHECKSUM_COMPLETE for Rx to avoid the * need to use this for Rx checksum offload. It should not be necessary to * call this function to perform Tx offloads on outgoing traffic. */ enum udp_parsable_tunnel_type { UDP_TUNNEL_TYPE_VXLAN = BIT(0), /* RFC 7348 */ UDP_TUNNEL_TYPE_GENEVE = BIT(1), /* draft-ietf-nvo3-geneve */ UDP_TUNNEL_TYPE_VXLAN_GPE = BIT(2), /* draft-ietf-nvo3-vxlan-gpe */ }; struct udp_tunnel_info { unsigned short type; sa_family_t sa_family; __be16 port; u8 hw_priv; }; /* Notify network devices of offloadable types */ void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock, unsigned short type); void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock, unsigned short type); void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type); void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type); static inline void udp_tunnel_get_rx_info(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev); } static inline void udp_tunnel_drop_rx_info(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_UDP_TUNNEL_DROP_INFO, dev); } /* Transmit the skb using UDP encapsulation. */ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, bool xnet, bool nocheck); int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, struct in6_addr *saddr, struct in6_addr *daddr, __u8 prio, __u8 ttl, __be32 label, __be16 src_port, __be16 dst_port, bool nocheck); void udp_tunnel_sock_release(struct socket *sock); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, __be16 flags, __be64 tunnel_id, int md_size); #ifdef CONFIG_INET static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) { int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; return iptunnel_handle_offloads(skb, type); } #endif static inline void udp_tunnel_encap_enable(struct socket *sock) { struct udp_sock *up = udp_sk(sock->sk); if (up->encap_enabled) return; up->encap_enabled = 1; #if IS_ENABLED(CONFIG_IPV6) if (sock->sk->sk_family == PF_INET6) ipv6_stub->udpv6_encap_enable(); else #endif udp_encap_enable(); } #define UDP_TUNNEL_NIC_MAX_TABLES 4 enum udp_tunnel_nic_info_flags { /* Device callbacks may sleep */ UDP_TUNNEL_NIC_INFO_MAY_SLEEP = BIT(0), /* Device only supports offloads when it's open, all ports * will be removed before close and re-added after open. */ UDP_TUNNEL_NIC_INFO_OPEN_ONLY = BIT(1), /* Device supports only IPv4 tunnels */ UDP_TUNNEL_NIC_INFO_IPV4_ONLY = BIT(2), /* Device has hard-coded the IANA VXLAN port (4789) as VXLAN. * This port must not be counted towards n_entries of any table. * Driver will not receive any callback associated with port 4789. */ UDP_TUNNEL_NIC_INFO_STATIC_IANA_VXLAN = BIT(3), }; struct udp_tunnel_nic; #define UDP_TUNNEL_NIC_MAX_SHARING_DEVICES (U16_MAX / 2) struct udp_tunnel_nic_shared { struct udp_tunnel_nic *udp_tunnel_nic_info; struct list_head devices; }; struct udp_tunnel_nic_shared_node { struct net_device *dev; struct list_head list; }; /** * struct udp_tunnel_nic_info - driver UDP tunnel offload information * @set_port: callback for adding a new port * @unset_port: callback for removing a port * @sync_table: callback for syncing the entire port table at once * @shared: reference to device global state (optional) * @flags: device flags from enum udp_tunnel_nic_info_flags * @tables: UDP port tables this device has * @tables.n_entries: number of entries in this table * @tables.tunnel_types: types of tunnels this table accepts * * Drivers are expected to provide either @set_port and @unset_port callbacks * or the @sync_table callback. Callbacks are invoked with rtnl lock held. * * Devices which (misguidedly) share the UDP tunnel port table across multiple * netdevs should allocate an instance of struct udp_tunnel_nic_shared and * point @shared at it. * There must never be more than %UDP_TUNNEL_NIC_MAX_SHARING_DEVICES devices * sharing a table. * * Known limitations: * - UDP tunnel port notifications are fundamentally best-effort - * it is likely the driver will both see skbs which use a UDP tunnel port, * while not being a tunneled skb, and tunnel skbs from other ports - * drivers should only use these ports for non-critical RX-side offloads, * e.g. the checksum offload; * - none of the devices care about the socket family at present, so we don't * track it. Please extend this code if you care. */ struct udp_tunnel_nic_info { /* one-by-one */ int (*set_port)(struct net_device *dev, unsigned int table, unsigned int entry, struct udp_tunnel_info *ti); int (*unset_port)(struct net_device *dev, unsigned int table, unsigned int entry, struct udp_tunnel_info *ti); /* all at once */ int (*sync_table)(struct net_device *dev, unsigned int table); struct udp_tunnel_nic_shared *shared; unsigned int flags; struct udp_tunnel_nic_table_info { unsigned int n_entries; unsigned int tunnel_types; } tables[UDP_TUNNEL_NIC_MAX_TABLES]; }; /* UDP tunnel module dependencies * * Tunnel drivers are expected to have a hard dependency on the udp_tunnel * module. NIC drivers are not, they just attach their * struct udp_tunnel_nic_info to the netdev and wait for callbacks to come. * Loading a tunnel driver will cause the udp_tunnel module to be loaded * and only then will all the required state structures be allocated. * Since we want a weak dependency from the drivers and the core to udp_tunnel * we call things through the following stubs. */ struct udp_tunnel_nic_ops { void (*get_port)(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti); void (*set_port_priv)(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv); void (*add_port)(struct net_device *dev, struct udp_tunnel_info *ti); void (*del_port)(struct net_device *dev, struct udp_tunnel_info *ti); void (*reset_ntf)(struct net_device *dev); size_t (*dump_size)(struct net_device *dev, unsigned int table); int (*dump_write)(struct net_device *dev, unsigned int table, struct sk_buff *skb); }; #ifdef CONFIG_INET extern const struct udp_tunnel_nic_ops *udp_tunnel_nic_ops; #else #define udp_tunnel_nic_ops ((struct udp_tunnel_nic_ops *)NULL) #endif static inline void udp_tunnel_nic_get_port(struct net_device *dev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti) { /* This helper is used from .sync_table, we indicate empty entries * by zero'ed @ti. Drivers which need to know the details of a port * when it gets deleted should use the .set_port / .unset_port * callbacks. * Zero out here, otherwise !CONFIG_INET causes uninitilized warnings. */ memset(ti, 0, sizeof(*ti)); if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->get_port(dev, table, idx, ti); } static inline void udp_tunnel_nic_set_port_priv(struct net_device *dev, unsigned int table, unsigned int idx, u8 priv) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->set_port_priv(dev, table, idx, priv); } static inline void udp_tunnel_nic_add_port(struct net_device *dev, struct udp_tunnel_info *ti) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->add_port(dev, ti); } static inline void udp_tunnel_nic_del_port(struct net_device *dev, struct udp_tunnel_info *ti) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->del_port(dev, ti); } /** * udp_tunnel_nic_reset_ntf() - device-originating reset notification * @dev: network interface device structure * * Called by the driver to inform the core that the entire UDP tunnel port * state has been lost, usually due to device reset. Core will assume device * forgot all the ports and issue .set_port and .sync_table callbacks as * necessary. * * This function must be called with rtnl lock held, and will issue all * the callbacks before returning. */ static inline void udp_tunnel_nic_reset_ntf(struct net_device *dev) { if (udp_tunnel_nic_ops) udp_tunnel_nic_ops->reset_ntf(dev); } static inline size_t udp_tunnel_nic_dump_size(struct net_device *dev, unsigned int table) { if (!udp_tunnel_nic_ops) return 0; return udp_tunnel_nic_ops->dump_size(dev, table); } static inline int udp_tunnel_nic_dump_write(struct net_device *dev, unsigned int table, struct sk_buff *skb) { if (!udp_tunnel_nic_ops) return 0; return udp_tunnel_nic_ops->dump_write(dev, table, skb); } #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 /* * linux/include/video/vga.h -- standard VGA chipset interaction * * Copyright 1999 Jeff Garzik <jgarzik@pobox.com> * * Copyright history from vga16fb.c: * Copyright 1999 Ben Pfaff and Petr Vandrovec * Based on VGA info at http://www.osdever.net/FreeVGA/home.htm * Based on VESA framebuffer (c) 1998 Gerd Knorr * * This file is subject to the terms and conditions of the GNU General * Public License. See the file COPYING in the main directory of this * archive for more details. * */ #ifndef __linux_video_vga_h__ #define __linux_video_vga_h__ #include <linux/types.h> #include <linux/io.h> #include <asm/vga.h> #include <asm/byteorder.h> /* Some of the code below is taken from SVGAlib. The original, unmodified copyright notice for that code is below. */ /* VGAlib version 1.2 - (c) 1993 Tommy Frandsen */ /* */ /* This library is free software; you can redistribute it and/or */ /* modify it without any restrictions. This library is distributed */ /* in the hope that it will be useful, but without any warranty. */ /* Multi-chipset support Copyright 1993 Harm Hanemaayer */ /* partially copyrighted (C) 1993 by Hartmut Schirmer */ /* VGA data register ports */ #define VGA_CRT_DC 0x3D5 /* CRT Controller Data Register - color emulation */ #define VGA_CRT_DM 0x3B5 /* CRT Controller Data Register - mono emulation */ #define VGA_ATT_R 0x3C1 /* Attribute Controller Data Read Register */ #define VGA_ATT_W 0x3C0 /* Attribute Controller Data Write Register */ #define VGA_GFX_D 0x3CF /* Graphics Controller Data Register */ #define VGA_SEQ_D 0x3C5 /* Sequencer Data Register */ #define VGA_MIS_R 0x3CC /* Misc Output Read Register */ #define VGA_MIS_W 0x3C2 /* Misc Output Write Register */ #define VGA_FTC_R 0x3CA /* Feature Control Read Register */ #define VGA_IS1_RC 0x3DA /* Input Status Register 1 - color emulation */ #define VGA_IS1_RM 0x3BA /* Input Status Register 1 - mono emulation */ #define VGA_PEL_D 0x3C9 /* PEL Data Register */ #define VGA_PEL_MSK 0x3C6 /* PEL mask register */ /* EGA-specific registers */ #define EGA_GFX_E0 0x3CC /* Graphics enable processor 0 */ #define EGA_GFX_E1 0x3CA /* Graphics enable processor 1 */ /* VGA index register ports */ #define VGA_CRT_IC 0x3D4 /* CRT Controller Index - color emulation */ #define VGA_CRT_IM 0x3B4 /* CRT Controller Index - mono emulation */ #define VGA_ATT_IW 0x3C0 /* Attribute Controller Index & Data Write Register */ #define VGA_GFX_I 0x3CE /* Graphics Controller Index */ #define VGA_SEQ_I 0x3C4 /* Sequencer Index */ #define VGA_PEL_IW 0x3C8 /* PEL Write Index */ #define VGA_PEL_IR 0x3C7 /* PEL Read Index */ /* standard VGA indexes max counts */ #define VGA_CRT_C 0x19 /* Number of CRT Controller Registers */ #define VGA_ATT_C 0x15 /* Number of Attribute Controller Registers */ #define VGA_GFX_C 0x09 /* Number of Graphics Controller Registers */ #define VGA_SEQ_C 0x05 /* Number of Sequencer Registers */ #define VGA_MIS_C 0x01 /* Number of Misc Output Register */ /* VGA misc register bit masks */ #define VGA_MIS_COLOR 0x01 #define VGA_MIS_ENB_MEM_ACCESS 0x02 #define VGA_MIS_DCLK_28322_720 0x04 #define VGA_MIS_ENB_PLL_LOAD (0x04 | 0x08) #define VGA_MIS_SEL_HIGH_PAGE 0x20 /* VGA CRT controller register indices */ #define VGA_CRTC_H_TOTAL 0 #define VGA_CRTC_H_DISP 1 #define VGA_CRTC_H_BLANK_START 2 #define VGA_CRTC_H_BLANK_END 3 #define VGA_CRTC_H_SYNC_START 4 #define VGA_CRTC_H_SYNC_END 5 #define VGA_CRTC_V_TOTAL 6 #define VGA_CRTC_OVERFLOW 7 #define VGA_CRTC_PRESET_ROW 8 #define VGA_CRTC_MAX_SCAN 9 #define VGA_CRTC_CURSOR_START 0x0A #define VGA_CRTC_CURSOR_END 0x0B #define VGA_CRTC_START_HI 0x0C #define VGA_CRTC_START_LO 0x0D #define VGA_CRTC_CURSOR_HI 0x0E #define VGA_CRTC_CURSOR_LO 0x0F #define VGA_CRTC_V_SYNC_START 0x10 #define VGA_CRTC_V_SYNC_END 0x11 #define VGA_CRTC_V_DISP_END 0x12 #define VGA_CRTC_OFFSET 0x13 #define VGA_CRTC_UNDERLINE 0x14 #define VGA_CRTC_V_BLANK_START 0x15 #define VGA_CRTC_V_BLANK_END 0x16 #define VGA_CRTC_MODE 0x17 #define VGA_CRTC_LINE_COMPARE 0x18 #define VGA_CRTC_REGS VGA_CRT_C /* VGA CRT controller bit masks */ #define VGA_CR11_LOCK_CR0_CR7 0x80 /* lock writes to CR0 - CR7 */ #define VGA_CR17_H_V_SIGNALS_ENABLED 0x80 /* VGA attribute controller register indices */ #define VGA_ATC_PALETTE0 0x00 #define VGA_ATC_PALETTE1 0x01 #define VGA_ATC_PALETTE2 0x02 #define VGA_ATC_PALETTE3 0x03 #define VGA_ATC_PALETTE4 0x04 #define VGA_ATC_PALETTE5 0x05 #define VGA_ATC_PALETTE6 0x06 #define VGA_ATC_PALETTE7 0x07 #define VGA_ATC_PALETTE8 0x08 #define VGA_ATC_PALETTE9 0x09 #define VGA_ATC_PALETTEA 0x0A #define VGA_ATC_PALETTEB 0x0B #define VGA_ATC_PALETTEC 0x0C #define VGA_ATC_PALETTED 0x0D #define VGA_ATC_PALETTEE 0x0E #define VGA_ATC_PALETTEF 0x0F #define VGA_ATC_MODE 0x10 #define VGA_ATC_OVERSCAN 0x11 #define VGA_ATC_PLANE_ENABLE 0x12 #define VGA_ATC_PEL 0x13 #define VGA_ATC_COLOR_PAGE 0x14 #define VGA_AR_ENABLE_DISPLAY 0x20 /* VGA sequencer register indices */ #define VGA_SEQ_RESET 0x00 #define VGA_SEQ_CLOCK_MODE 0x01 #define VGA_SEQ_PLANE_WRITE 0x02 #define VGA_SEQ_CHARACTER_MAP 0x03 #define VGA_SEQ_MEMORY_MODE 0x04 /* VGA sequencer register bit masks */ #define VGA_SR01_CHAR_CLK_8DOTS 0x01 /* bit 0: character clocks 8 dots wide are generated */ #define VGA_SR01_SCREEN_OFF 0x20 /* bit 5: Screen is off */ #define VGA_SR02_ALL_PLANES 0x0F /* bits 3-0: enable access to all planes */ #define VGA_SR04_EXT_MEM 0x02 /* bit 1: allows complete mem access to 256K */ #define VGA_SR04_SEQ_MODE 0x04 /* bit 2: directs system to use a sequential addressing mode */ #define VGA_SR04_CHN_4M 0x08 /* bit 3: selects modulo 4 addressing for CPU access to display memory */ /* VGA graphics controller register indices */ #define VGA_GFX_SR_VALUE 0x00 #define VGA_GFX_SR_ENABLE 0x01 #define VGA_GFX_COMPARE_VALUE 0x02 #define VGA_GFX_DATA_ROTATE 0x03 #define VGA_GFX_PLANE_READ 0x04 #define VGA_GFX_MODE 0x05 #define VGA_GFX_MISC 0x06 #define VGA_GFX_COMPARE_MASK 0x07 #define VGA_GFX_BIT_MASK 0x08 /* VGA graphics controller bit masks */ #define VGA_GR06_GRAPHICS_MODE 0x01 /* macro for composing an 8-bit VGA register index and value * into a single 16-bit quantity */ #define VGA_OUT16VAL(v, r) (((v) << 8) | (r)) /* decide whether we should enable the faster 16-bit VGA register writes */ #ifdef __LITTLE_ENDIAN #define VGA_OUTW_WRITE #endif /* VGA State Save and Restore */ #define VGA_SAVE_FONT0 1 /* save/restore plane 2 fonts */ #define VGA_SAVE_FONT1 2 /* save/restore plane 3 fonts */ #define VGA_SAVE_TEXT 4 /* save/restore plane 0/1 fonts */ #define VGA_SAVE_FONTS 7 /* save/restore all fonts */ #define VGA_SAVE_MODE 8 /* save/restore video mode */ #define VGA_SAVE_CMAP 16 /* save/restore color map/DAC */ struct vgastate { void __iomem *vgabase; /* mmio base, if supported */ unsigned long membase; /* VGA window base, 0 for default - 0xA000 */ __u32 memsize; /* VGA window size, 0 for default 64K */ __u32 flags; /* what state[s] to save (see VGA_SAVE_*) */ __u32 depth; /* current fb depth, not important */ __u32 num_attr; /* number of att registers, 0 for default */ __u32 num_crtc; /* number of crt registers, 0 for default */ __u32 num_gfx; /* number of gfx registers, 0 for default */ __u32 num_seq; /* number of seq registers, 0 for default */ void *vidstate; }; extern int save_vga(struct vgastate *state); extern int restore_vga(struct vgastate *state); /* * generic VGA port read/write */ static inline unsigned char vga_io_r (unsigned short port) { return inb_p(port); } static inline void vga_io_w (unsigned short port, unsigned char val) { outb_p(val, port); } static inline void vga_io_w_fast (unsigned short port, unsigned char reg, unsigned char val) { outw(VGA_OUT16VAL (val, reg), port); } static inline unsigned char vga_mm_r (void __iomem *regbase, unsigned short port) { return readb (regbase + port); } static inline void vga_mm_w (void __iomem *regbase, unsigned short port, unsigned char val) { writeb (val, regbase + port); } static inline void vga_mm_w_fast (void __iomem *regbase, unsigned short port, unsigned char reg, unsigned char val) { writew (VGA_OUT16VAL (val, reg), regbase + port); } static inline unsigned char vga_r (void __iomem *regbase, unsigned short port) { if (regbase) return vga_mm_r (regbase, port); else return vga_io_r (port); } static inline void vga_w (void __iomem *regbase, unsigned short port, unsigned char val) { if (regbase) vga_mm_w (regbase, port, val); else vga_io_w (port, val); } static inline void vga_w_fast (void __iomem *regbase, unsigned short port, unsigned char reg, unsigned char val) { if (regbase) vga_mm_w_fast (regbase, port, reg, val); else vga_io_w_fast (port, reg, val); } /* * VGA CRTC register read/write */ static inline unsigned char vga_rcrt (void __iomem *regbase, unsigned char reg) { vga_w (regbase, VGA_CRT_IC, reg); return vga_r (regbase, VGA_CRT_DC); } static inline void vga_wcrt (void __iomem *regbase, unsigned char reg, unsigned char val) { #ifdef VGA_OUTW_WRITE vga_w_fast (regbase, VGA_CRT_IC, reg, val); #else vga_w (regbase, VGA_CRT_IC, reg); vga_w (regbase, VGA_CRT_DC, val); #endif /* VGA_OUTW_WRITE */ } static inline unsigned char vga_io_rcrt (unsigned char reg) { vga_io_w (VGA_CRT_IC, reg); return vga_io_r (VGA_CRT_DC); } static inline void vga_io_wcrt (unsigned char reg, unsigned char val) { #ifdef VGA_OUTW_WRITE vga_io_w_fast (VGA_CRT_IC, reg, val); #else vga_io_w (VGA_CRT_IC, reg); vga_io_w (VGA_CRT_DC, val); #endif /* VGA_OUTW_WRITE */ } static inline unsigned char vga_mm_rcrt (void __iomem *regbase, unsigned char reg) { vga_mm_w (regbase, VGA_CRT_IC, reg); return vga_mm_r (regbase, VGA_CRT_DC); } static inline void vga_mm_wcrt (void __iomem *regbase, unsigned char reg, unsigned char val) { #ifdef VGA_OUTW_WRITE vga_mm_w_fast (regbase, VGA_CRT_IC, reg, val); #else vga_mm_w (regbase, VGA_CRT_IC, reg); vga_mm_w (regbase, VGA_CRT_DC, val); #endif /* VGA_OUTW_WRITE */ } /* * VGA sequencer register read/write */ static inline unsigned char vga_rseq (void __iomem *regbase, unsigned char reg) { vga_w (regbase, VGA_SEQ_I, reg); return vga_r (regbase, VGA_SEQ_D); } static inline void vga_wseq (void __iomem *regbase, unsigned char reg, unsigned char val) { #ifdef VGA_OUTW_WRITE vga_w_fast (regbase, VGA_SEQ_I, reg, val); #else vga_w (regbase, VGA_SEQ_I, reg); vga_w (regbase, VGA_SEQ_D, val); #endif /* VGA_OUTW_WRITE */ } static inline unsigned char vga_io_rseq (unsigned char reg) { vga_io_w (VGA_SEQ_I, reg); return vga_io_r (VGA_SEQ_D); } static inline void vga_io_wseq (unsigned char reg, unsigned char val) { #ifdef VGA_OUTW_WRITE vga_io_w_fast (VGA_SEQ_I, reg, val); #else vga_io_w (VGA_SEQ_I, reg); vga_io_w (VGA_SEQ_D, val); #endif /* VGA_OUTW_WRITE */ } static inline unsigned char vga_mm_rseq (void __iomem *regbase, unsigned char reg) { vga_mm_w (regbase, VGA_SEQ_I, reg); return vga_mm_r (regbase, VGA_SEQ_D); } static inline void vga_mm_wseq (void __iomem *regbase, unsigned char reg, unsigned char val) { #ifdef VGA_OUTW_WRITE vga_mm_w_fast (regbase, VGA_SEQ_I, reg, val); #else vga_mm_w (regbase, VGA_SEQ_I, reg); vga_mm_w (regbase, VGA_SEQ_D, val); #endif /* VGA_OUTW_WRITE */ } /* * VGA graphics controller register read/write */ static inline unsigned char vga_rgfx (void __iomem *regbase, unsigned char reg) { vga_w (regbase, VGA_GFX_I, reg); return vga_r (regbase, VGA_GFX_D); } static inline void vga_wgfx (void __iomem *regbase, unsigned char reg, unsigned char val) { #ifdef VGA_OUTW_WRITE vga_w_fast (regbase, VGA_GFX_I, reg, val); #else vga_w (regbase, VGA_GFX_I, reg); vga_w (regbase, VGA_GFX_D, val); #endif /* VGA_OUTW_WRITE */ } static inline unsigned char vga_io_rgfx (unsigned char reg) { vga_io_w (VGA_GFX_I, reg); return vga_io_r (VGA_GFX_D); } static inline void vga_io_wgfx (unsigned char reg, unsigned char val) { #ifdef VGA_OUTW_WRITE vga_io_w_fast (VGA_GFX_I, reg, val); #else vga_io_w (VGA_GFX_I, reg); vga_io_w (VGA_GFX_D, val); #endif /* VGA_OUTW_WRITE */ } static inline unsigned char vga_mm_rgfx (void __iomem *regbase, unsigned char reg) { vga_mm_w (regbase, VGA_GFX_I, reg); return vga_mm_r (regbase, VGA_GFX_D); } static inline void vga_mm_wgfx (void __iomem *regbase, unsigned char reg, unsigned char val) { #ifdef VGA_OUTW_WRITE vga_mm_w_fast (regbase, VGA_GFX_I, reg, val); #else vga_mm_w (regbase, VGA_GFX_I, reg); vga_mm_w (regbase, VGA_GFX_D, val); #endif /* VGA_OUTW_WRITE */ } /* * VGA attribute controller register read/write */ static inline unsigned char vga_rattr (void __iomem *regbase, unsigned char reg) { vga_w (regbase, VGA_ATT_IW, reg); return vga_r (regbase, VGA_ATT_R); } static inline void vga_wattr (void __iomem *regbase, unsigned char reg, unsigned char val) { vga_w (regbase, VGA_ATT_IW, reg); vga_w (regbase, VGA_ATT_W, val); } static inline unsigned char vga_io_rattr (unsigned char reg) { vga_io_w (VGA_ATT_IW, reg); return vga_io_r (VGA_ATT_R); } static inline void vga_io_wattr (unsigned char reg, unsigned char val) { vga_io_w (VGA_ATT_IW, reg); vga_io_w (VGA_ATT_W, val); } static inline unsigned char vga_mm_rattr (void __iomem *regbase, unsigned char reg) { vga_mm_w (regbase, VGA_ATT_IW, reg); return vga_mm_r (regbase, VGA_ATT_R); } static inline void vga_mm_wattr (void __iomem *regbase, unsigned char reg, unsigned char val) { vga_mm_w (regbase, VGA_ATT_IW, reg); vga_mm_w (regbase, VGA_ATT_W, val); } #endif /* __linux_video_vga_h__ */
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/fat/inode.c * * Written 1992,1993 by Werner Almesberger * VFAT extensions by Gordon Chaffee, merged with msdos fs by Henrik Storner * Rewritten for the constant inumbers support by Al Viro * * Fixes: * * Max Cohan: Fixed invalid FSINFO offset when info_sector is 0 */ #include <linux/module.h> #include <linux/pagemap.h> #include <linux/mpage.h> #include <linux/vfs.h> #include <linux/seq_file.h> #include <linux/parser.h> #include <linux/uio.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <asm/unaligned.h> #include <linux/random.h> #include <linux/iversion.h> #include "fat.h" #ifndef CONFIG_FAT_DEFAULT_IOCHARSET /* if user don't select VFAT, this is undefined. */ #define CONFIG_FAT_DEFAULT_IOCHARSET "" #endif #define KB_IN_SECTORS 2 /* DOS dates from 1980/1/1 through 2107/12/31 */ #define FAT_DATE_MIN (0<<9 | 1<<5 | 1) #define FAT_DATE_MAX (127<<9 | 12<<5 | 31) #define FAT_TIME_MAX (23<<11 | 59<<5 | 29) /* * A deserialized copy of the on-disk structure laid out in struct * fat_boot_sector. */ struct fat_bios_param_block { u16 fat_sector_size; u8 fat_sec_per_clus; u16 fat_reserved; u8 fat_fats; u16 fat_dir_entries; u16 fat_sectors; u16 fat_fat_length; u32 fat_total_sect; u8 fat16_state; u32 fat16_vol_id; u32 fat32_length; u32 fat32_root_cluster; u16 fat32_info_sector; u8 fat32_state; u32 fat32_vol_id; }; static int fat_default_codepage = CONFIG_FAT_DEFAULT_CODEPAGE; static char fat_default_iocharset[] = CONFIG_FAT_DEFAULT_IOCHARSET; static struct fat_floppy_defaults { unsigned nr_sectors; unsigned sec_per_clus; unsigned dir_entries; unsigned media; unsigned fat_length; } floppy_defaults[] = { { .nr_sectors = 160 * KB_IN_SECTORS, .sec_per_clus = 1, .dir_entries = 64, .media = 0xFE, .fat_length = 1, }, { .nr_sectors = 180 * KB_IN_SECTORS, .sec_per_clus = 1, .dir_entries = 64, .media = 0xFC, .fat_length = 2, }, { .nr_sectors = 320 * KB_IN_SECTORS, .sec_per_clus = 2, .dir_entries = 112, .media = 0xFF, .fat_length = 1, }, { .nr_sectors = 360 * KB_IN_SECTORS, .sec_per_clus = 2, .dir_entries = 112, .media = 0xFD, .fat_length = 2, }, }; int fat_add_cluster(struct inode *inode) { int err, cluster; err = fat_alloc_clusters(inode, &cluster, 1); if (err) return err; /* FIXME: this cluster should be added after data of this * cluster is writed */ err = fat_chain_add(inode, cluster, 1); if (err) fat_free_clusters(inode, cluster); return err; } static inline int __fat_get_block(struct inode *inode, sector_t iblock, unsigned long *max_blocks, struct buffer_head *bh_result, int create) { struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); unsigned long mapped_blocks; sector_t phys, last_block; int err, offset; err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false); if (err) return err; if (phys) { map_bh(bh_result, sb, phys); *max_blocks = min(mapped_blocks, *max_blocks); return 0; } if (!create) return 0; if (iblock != MSDOS_I(inode)->mmu_private >> sb->s_blocksize_bits) { fat_fs_error(sb, "corrupted file size (i_pos %lld, %lld)", MSDOS_I(inode)->i_pos, MSDOS_I(inode)->mmu_private); return -EIO; } last_block = inode->i_blocks >> (sb->s_blocksize_bits - 9); offset = (unsigned long)iblock & (sbi->sec_per_clus - 1); /* * allocate a cluster according to the following. * 1) no more available blocks * 2) not part of fallocate region */ if (!offset && !(iblock < last_block)) { /* TODO: multiple cluster allocation would be desirable. */ err = fat_add_cluster(inode); if (err) return err; } /* available blocks on this cluster */ mapped_blocks = sbi->sec_per_clus - offset; *max_blocks = min(mapped_blocks, *max_blocks); MSDOS_I(inode)->mmu_private += *max_blocks << sb->s_blocksize_bits; err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false); if (err) return err; if (!phys) { fat_fs_error(sb, "invalid FAT chain (i_pos %lld, last_block %llu)", MSDOS_I(inode)->i_pos, (unsigned long long)last_block); return -EIO; } BUG_ON(*max_blocks != mapped_blocks); set_buffer_new(bh_result); map_bh(bh_result, sb, phys); return 0; } static int fat_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { struct super_block *sb = inode->i_sb; unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits; int err; err = __fat_get_block(inode, iblock, &max_blocks, bh_result, create); if (err) return err; bh_result->b_size = max_blocks << sb->s_blocksize_bits; return 0; } static int fat_writepage(struct page *page, struct writeback_control *wbc) { return block_write_full_page(page, fat_get_block, wbc); } static int fat_writepages(struct address_space *mapping, struct writeback_control *wbc) { return mpage_writepages(mapping, wbc, fat_get_block); } static int fat_readpage(struct file *file, struct page *page) { return mpage_readpage(page, fat_get_block); } static void fat_readahead(struct readahead_control *rac) { mpage_readahead(rac, fat_get_block); } static void fat_write_failed(struct address_space *mapping, loff_t to) { struct inode *inode = mapping->host; if (to > inode->i_size) { truncate_pagecache(inode, inode->i_size); fat_truncate_blocks(inode, inode->i_size); } } static int fat_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { int err; *pagep = NULL; err = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata, fat_get_block, &MSDOS_I(mapping->host)->mmu_private); if (err < 0) fat_write_failed(mapping, pos + len); return err; } static int fat_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *pagep, void *fsdata) { struct inode *inode = mapping->host; int err; err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata); if (err < len) fat_write_failed(mapping, pos + len); if (!(err < 0) && !(MSDOS_I(inode)->i_attrs & ATTR_ARCH)) { fat_truncate_time(inode, NULL, S_CTIME|S_MTIME); MSDOS_I(inode)->i_attrs |= ATTR_ARCH; mark_inode_dirty(inode); } return err; } static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); loff_t offset = iocb->ki_pos; ssize_t ret; if (iov_iter_rw(iter) == WRITE) { /* * FIXME: blockdev_direct_IO() doesn't use ->write_begin(), * so we need to update the ->mmu_private to block boundary. * * But we must fill the remaining area or hole by nul for * updating ->mmu_private. * * Return 0, and fallback to normal buffered write. */ loff_t size = offset + count; if (MSDOS_I(inode)->mmu_private < size) return 0; } /* * FAT need to use the DIO_LOCKING for avoiding the race * condition of fat_get_block() and ->truncate(). */ ret = blockdev_direct_IO(iocb, inode, iter, fat_get_block); if (ret < 0 && iov_iter_rw(iter) == WRITE) fat_write_failed(mapping, offset + count); return ret; } static int fat_get_block_bmap(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { struct super_block *sb = inode->i_sb; unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits; int err; sector_t bmap; unsigned long mapped_blocks; BUG_ON(create != 0); err = fat_bmap(inode, iblock, &bmap, &mapped_blocks, create, true); if (err) return err; if (bmap) { map_bh(bh_result, sb, bmap); max_blocks = min(mapped_blocks, max_blocks); } bh_result->b_size = max_blocks << sb->s_blocksize_bits; return 0; } static sector_t _fat_bmap(struct address_space *mapping, sector_t block) { sector_t blocknr; /* fat_get_cluster() assumes the requested blocknr isn't truncated. */ down_read(&MSDOS_I(mapping->host)->truncate_lock); blocknr = generic_block_bmap(mapping, block, fat_get_block_bmap); up_read(&MSDOS_I(mapping->host)->truncate_lock); return blocknr; } /* * fat_block_truncate_page() zeroes out a mapping from file offset `from' * up to the end of the block which corresponds to `from'. * This is required during truncate to physically zeroout the tail end * of that block so it doesn't yield old data if the file is later grown. * Also, avoid causing failure from fsx for cases of "data past EOF" */ int fat_block_truncate_page(struct inode *inode, loff_t from) { return block_truncate_page(inode->i_mapping, from, fat_get_block); } static const struct address_space_operations fat_aops = { .readpage = fat_readpage, .readahead = fat_readahead, .writepage = fat_writepage, .writepages = fat_writepages, .write_begin = fat_write_begin, .write_end = fat_write_end, .direct_IO = fat_direct_IO, .bmap = _fat_bmap }; /* * New FAT inode stuff. We do the following: * a) i_ino is constant and has nothing with on-disk location. * b) FAT manages its own cache of directory entries. * c) *This* cache is indexed by on-disk location. * d) inode has an associated directory entry, all right, but * it may be unhashed. * e) currently entries are stored within struct inode. That should * change. * f) we deal with races in the following way: * 1. readdir() and lookup() do FAT-dir-cache lookup. * 2. rename() unhashes the F-d-c entry and rehashes it in * a new place. * 3. unlink() and rmdir() unhash F-d-c entry. * 4. fat_write_inode() checks whether the thing is unhashed. * If it is we silently return. If it isn't we do bread(), * check if the location is still valid and retry if it * isn't. Otherwise we do changes. * 5. Spinlock is used to protect hash/unhash/location check/lookup * 6. fat_evict_inode() unhashes the F-d-c entry. * 7. lookup() and readdir() do igrab() if they find a F-d-c entry * and consider negative result as cache miss. */ static void fat_hash_init(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); int i; spin_lock_init(&sbi->inode_hash_lock); for (i = 0; i < FAT_HASH_SIZE; i++) INIT_HLIST_HEAD(&sbi->inode_hashtable[i]); } static inline unsigned long fat_hash(loff_t i_pos) { return hash_32(i_pos, FAT_HASH_BITS); } static void dir_hash_init(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); int i; spin_lock_init(&sbi->dir_hash_lock); for (i = 0; i < FAT_HASH_SIZE; i++) INIT_HLIST_HEAD(&sbi->dir_hashtable[i]); } void fat_attach(struct inode *inode, loff_t i_pos) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); if (inode->i_ino != MSDOS_ROOT_INO) { struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos); spin_lock(&sbi->inode_hash_lock); MSDOS_I(inode)->i_pos = i_pos; hlist_add_head(&MSDOS_I(inode)->i_fat_hash, head); spin_unlock(&sbi->inode_hash_lock); } /* If NFS support is enabled, cache the mapping of start cluster * to directory inode. This is used during reconnection of * dentries to the filesystem root. */ if (S_ISDIR(inode->i_mode) && sbi->options.nfs) { struct hlist_head *d_head = sbi->dir_hashtable; d_head += fat_dir_hash(MSDOS_I(inode)->i_logstart); spin_lock(&sbi->dir_hash_lock); hlist_add_head(&MSDOS_I(inode)->i_dir_hash, d_head); spin_unlock(&sbi->dir_hash_lock); } } EXPORT_SYMBOL_GPL(fat_attach); void fat_detach(struct inode *inode) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); spin_lock(&sbi->inode_hash_lock); MSDOS_I(inode)->i_pos = 0; hlist_del_init(&MSDOS_I(inode)->i_fat_hash); spin_unlock(&sbi->inode_hash_lock); if (S_ISDIR(inode->i_mode) && sbi->options.nfs) { spin_lock(&sbi->dir_hash_lock); hlist_del_init(&MSDOS_I(inode)->i_dir_hash); spin_unlock(&sbi->dir_hash_lock); } } EXPORT_SYMBOL_GPL(fat_detach); struct inode *fat_iget(struct super_block *sb, loff_t i_pos) { struct msdos_sb_info *sbi = MSDOS_SB(sb); struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos); struct msdos_inode_info *i; struct inode *inode = NULL; spin_lock(&sbi->inode_hash_lock); hlist_for_each_entry(i, head, i_fat_hash) { BUG_ON(i->vfs_inode.i_sb != sb); if (i->i_pos != i_pos) continue; inode = igrab(&i->vfs_inode); if (inode) break; } spin_unlock(&sbi->inode_hash_lock); return inode; } static int is_exec(unsigned char *extension) { unsigned char exe_extensions[] = "EXECOMBAT", *walk; for (walk = exe_extensions; *walk; walk += 3) if (!strncmp(extension, walk, 3)) return 1; return 0; } static int fat_calc_dir_size(struct inode *inode) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); int ret, fclus, dclus; inode->i_size = 0; if (MSDOS_I(inode)->i_start == 0) return 0; ret = fat_get_cluster(inode, FAT_ENT_EOF, &fclus, &dclus); if (ret < 0) return ret; inode->i_size = (fclus + 1) << sbi->cluster_bits; return 0; } static int fat_validate_dir(struct inode *dir) { struct super_block *sb = dir->i_sb; if (dir->i_nlink < 2) { /* Directory should have "."/".." entries at least. */ fat_fs_error(sb, "corrupted directory (invalid entries)"); return -EIO; } if (MSDOS_I(dir)->i_start == 0 || MSDOS_I(dir)->i_start == MSDOS_SB(sb)->root_cluster) { /* Directory should point valid cluster. */ fat_fs_error(sb, "corrupted directory (invalid i_start)"); return -EIO; } return 0; } /* doesn't deal with root inode */ int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); int error; MSDOS_I(inode)->i_pos = 0; inode->i_uid = sbi->options.fs_uid; inode->i_gid = sbi->options.fs_gid; inode_inc_iversion(inode); inode->i_generation = prandom_u32(); if ((de->attr & ATTR_DIR) && !IS_FREE(de->name)) { inode->i_generation &= ~1; inode->i_mode = fat_make_mode(sbi, de->attr, S_IRWXUGO); inode->i_op = sbi->dir_ops; inode->i_fop = &fat_dir_operations; MSDOS_I(inode)->i_start = fat_get_start(sbi, de); MSDOS_I(inode)->i_logstart = MSDOS_I(inode)->i_start; error = fat_calc_dir_size(inode); if (error < 0) return error; MSDOS_I(inode)->mmu_private = inode->i_size; set_nlink(inode, fat_subdirs(inode)); error = fat_validate_dir(inode); if (error < 0) return error; } else { /* not a directory */ inode->i_generation |= 1; inode->i_mode = fat_make_mode(sbi, de->attr, ((sbi->options.showexec && !is_exec(de->name + 8)) ? S_IRUGO|S_IWUGO : S_IRWXUGO)); MSDOS_I(inode)->i_start = fat_get_start(sbi, de); MSDOS_I(inode)->i_logstart = MSDOS_I(inode)->i_start; inode->i_size = le32_to_cpu(de->size); inode->i_op = &fat_file_inode_operations; inode->i_fop = &fat_file_operations; inode->i_mapping->a_ops = &fat_aops; MSDOS_I(inode)->mmu_private = inode->i_size; } if (de->attr & ATTR_SYS) { if (sbi->options.sys_immutable) inode->i_flags |= S_IMMUTABLE; } fat_save_attrs(inode, de->attr); inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1)) & ~((loff_t)sbi->cluster_size - 1)) >> 9; fat_time_fat2unix(sbi, &inode->i_mtime, de->time, de->date, 0); if (sbi->options.isvfat) { fat_time_fat2unix(sbi, &inode->i_ctime, de->ctime, de->cdate, de->ctime_cs); fat_time_fat2unix(sbi, &inode->i_atime, 0, de->adate, 0); } else fat_truncate_time(inode, &inode->i_mtime, S_ATIME|S_CTIME); return 0; } static inline void fat_lock_build_inode(struct msdos_sb_info *sbi) { if (sbi->options.nfs == FAT_NFS_NOSTALE_RO) mutex_lock(&sbi->nfs_build_inode_lock); } static inline void fat_unlock_build_inode(struct msdos_sb_info *sbi) { if (sbi->options.nfs == FAT_NFS_NOSTALE_RO) mutex_unlock(&sbi->nfs_build_inode_lock); } struct inode *fat_build_inode(struct super_block *sb, struct msdos_dir_entry *de, loff_t i_pos) { struct inode *inode; int err; fat_lock_build_inode(MSDOS_SB(sb)); inode = fat_iget(sb, i_pos); if (inode) goto out; inode = new_inode(sb); if (!inode) { inode = ERR_PTR(-ENOMEM); goto out; } inode->i_ino = iunique(sb, MSDOS_ROOT_INO); inode_set_iversion(inode, 1); err = fat_fill_inode(inode, de); if (err) { iput(inode); inode = ERR_PTR(err); goto out; } fat_attach(inode, i_pos); insert_inode_hash(inode); out: fat_unlock_build_inode(MSDOS_SB(sb)); return inode; } EXPORT_SYMBOL_GPL(fat_build_inode); static int __fat_write_inode(struct inode *inode, int wait); static void fat_free_eofblocks(struct inode *inode) { /* Release unwritten fallocated blocks on inode eviction. */ if ((inode->i_blocks << 9) > round_up(MSDOS_I(inode)->mmu_private, MSDOS_SB(inode->i_sb)->cluster_size)) { int err; fat_truncate_blocks(inode, MSDOS_I(inode)->mmu_private); /* Fallocate results in updating the i_start/iogstart * for the zero byte file. So, make it return to * original state during evict and commit it to avoid * any corruption on the next access to the cluster * chain for the file. */ err = __fat_write_inode(inode, inode_needs_sync(inode)); if (err) { fat_msg(inode->i_sb, KERN_WARNING, "Failed to " "update on disk inode for unused " "fallocated blocks, inode could be " "corrupted. Please run fsck"); } } } static void fat_evict_inode(struct inode *inode) { truncate_inode_pages_final(&inode->i_data); if (!inode->i_nlink) { inode->i_size = 0; fat_truncate_blocks(inode, 0); } else fat_free_eofblocks(inode); invalidate_inode_buffers(inode); clear_inode(inode); fat_cache_inval_inode(inode); fat_detach(inode); } static void fat_set_state(struct super_block *sb, unsigned int set, unsigned int force) { struct buffer_head *bh; struct fat_boot_sector *b; struct msdos_sb_info *sbi = MSDOS_SB(sb); /* do not change any thing if mounted read only */ if (sb_rdonly(sb) && !force) return; /* do not change state if fs was dirty */ if (sbi->dirty) { /* warn only on set (mount). */ if (set) fat_msg(sb, KERN_WARNING, "Volume was not properly " "unmounted. Some data may be corrupt. " "Please run fsck."); return; } bh = sb_bread(sb, 0); if (bh == NULL) { fat_msg(sb, KERN_ERR, "unable to read boot sector " "to mark fs as dirty"); return; } b = (struct fat_boot_sector *) bh->b_data; if (is_fat32(sbi)) { if (set) b->fat32.state |= FAT_STATE_DIRTY; else b->fat32.state &= ~FAT_STATE_DIRTY; } else /* fat 16 and 12 */ { if (set) b->fat16.state |= FAT_STATE_DIRTY; else b->fat16.state &= ~FAT_STATE_DIRTY; } mark_buffer_dirty(bh); sync_dirty_buffer(bh); brelse(bh); } static void fat_reset_iocharset(struct fat_mount_options *opts) { if (opts->iocharset != fat_default_iocharset) { /* Note: opts->iocharset can be NULL here */ kfree(opts->iocharset); opts->iocharset = fat_default_iocharset; } } static void delayed_free(struct rcu_head *p) { struct msdos_sb_info *sbi = container_of(p, struct msdos_sb_info, rcu); unload_nls(sbi->nls_disk); unload_nls(sbi->nls_io); fat_reset_iocharset(&sbi->options); kfree(sbi); } static void fat_put_super(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); fat_set_state(sb, 0, 0); iput(sbi->fsinfo_inode); iput(sbi->fat_inode); call_rcu(&sbi->rcu, delayed_free); } static struct kmem_cache *fat_inode_cachep; static struct inode *fat_alloc_inode(struct super_block *sb) { struct msdos_inode_info *ei; ei = kmem_cache_alloc(fat_inode_cachep, GFP_NOFS); if (!ei) return NULL; init_rwsem(&ei->truncate_lock); /* Zeroing to allow iput() even if partial initialized inode. */ ei->mmu_private = 0; ei->i_start = 0; ei->i_logstart = 0; ei->i_attrs = 0; ei->i_pos = 0; return &ei->vfs_inode; } static void fat_free_inode(struct inode *inode) { kmem_cache_free(fat_inode_cachep, MSDOS_I(inode)); } static void init_once(void *foo) { struct msdos_inode_info *ei = (struct msdos_inode_info *)foo; spin_lock_init(&ei->cache_lru_lock); ei->nr_caches = 0; ei->cache_valid_id = FAT_CACHE_VALID + 1; INIT_LIST_HEAD(&ei->cache_lru); INIT_HLIST_NODE(&ei->i_fat_hash); INIT_HLIST_NODE(&ei->i_dir_hash); inode_init_once(&ei->vfs_inode); } static int __init fat_init_inodecache(void) { fat_inode_cachep = kmem_cache_create("fat_inode_cache", sizeof(struct msdos_inode_info), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (fat_inode_cachep == NULL) return -ENOMEM; return 0; } static void __exit fat_destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(fat_inode_cachep); } static int fat_remount(struct super_block *sb, int *flags, char *data) { bool new_rdonly; struct msdos_sb_info *sbi = MSDOS_SB(sb); *flags |= SB_NODIRATIME | (sbi->options.isvfat ? 0 : SB_NOATIME); sync_filesystem(sb); /* make sure we update state on remount. */ new_rdonly = *flags & SB_RDONLY; if (new_rdonly != sb_rdonly(sb)) { if (new_rdonly) fat_set_state(sb, 0, 0); else fat_set_state(sb, 1, 1); } return 0; } static int fat_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); u64 id = huge_encode_dev(sb->s_bdev->bd_dev); /* If the count of free cluster is still unknown, counts it here. */ if (sbi->free_clusters == -1 || !sbi->free_clus_valid) { int err = fat_count_free_clusters(dentry->d_sb); if (err) return err; } buf->f_type = dentry->d_sb->s_magic; buf->f_bsize = sbi->cluster_size; buf->f_blocks = sbi->max_cluster - FAT_START_ENT; buf->f_bfree = sbi->free_clusters; buf->f_bavail = sbi->free_clusters; buf->f_fsid = u64_to_fsid(id); buf->f_namelen = (sbi->options.isvfat ? FAT_LFN_LEN : 12) * NLS_MAX_CHARSET_SIZE; return 0; } static int __fat_write_inode(struct inode *inode, int wait) { struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); struct buffer_head *bh; struct msdos_dir_entry *raw_entry; loff_t i_pos; sector_t blocknr; int err, offset; if (inode->i_ino == MSDOS_ROOT_INO) return 0; retry: i_pos = fat_i_pos_read(sbi, inode); if (!i_pos) return 0; fat_get_blknr_offset(sbi, i_pos, &blocknr, &offset); bh = sb_bread(sb, blocknr); if (!bh) { fat_msg(sb, KERN_ERR, "unable to read inode block " "for updating (i_pos %lld)", i_pos); return -EIO; } spin_lock(&sbi->inode_hash_lock); if (i_pos != MSDOS_I(inode)->i_pos) { spin_unlock(&sbi->inode_hash_lock); brelse(bh); goto retry; } raw_entry = &((struct msdos_dir_entry *) (bh->b_data))[offset]; if (S_ISDIR(inode->i_mode)) raw_entry->size = 0; else raw_entry->size = cpu_to_le32(inode->i_size); raw_entry->attr = fat_make_attrs(inode); fat_set_start(raw_entry, MSDOS_I(inode)->i_logstart); fat_time_unix2fat(sbi, &inode->i_mtime, &raw_entry->time, &raw_entry->date, NULL); if (sbi->options.isvfat) { __le16 atime; fat_time_unix2fat(sbi, &inode->i_ctime, &raw_entry->ctime, &raw_entry->cdate, &raw_entry->ctime_cs); fat_time_unix2fat(sbi, &inode->i_atime, &atime, &raw_entry->adate, NULL); } spin_unlock(&sbi->inode_hash_lock); mark_buffer_dirty(bh); err = 0; if (wait) err = sync_dirty_buffer(bh); brelse(bh); return err; } static int fat_write_inode(struct inode *inode, struct writeback_control *wbc) { int err; if (inode->i_ino == MSDOS_FSINFO_INO) { struct super_block *sb = inode->i_sb; mutex_lock(&MSDOS_SB(sb)->s_lock); err = fat_clusters_flush(sb); mutex_unlock(&MSDOS_SB(sb)->s_lock); } else err = __fat_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); return err; } int fat_sync_inode(struct inode *inode) { return __fat_write_inode(inode, 1); } EXPORT_SYMBOL_GPL(fat_sync_inode); static int fat_show_options(struct seq_file *m, struct dentry *root); static const struct super_operations fat_sops = { .alloc_inode = fat_alloc_inode, .free_inode = fat_free_inode, .write_inode = fat_write_inode, .evict_inode = fat_evict_inode, .put_super = fat_put_super, .statfs = fat_statfs, .remount_fs = fat_remount, .show_options = fat_show_options, }; static int fat_show_options(struct seq_file *m, struct dentry *root) { struct msdos_sb_info *sbi = MSDOS_SB(root->d_sb); struct fat_mount_options *opts = &sbi->options; int isvfat = opts->isvfat; if (!uid_eq(opts->fs_uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, opts->fs_uid)); if (!gid_eq(opts->fs_gid, GLOBAL_ROOT_GID)) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, opts->fs_gid)); seq_printf(m, ",fmask=%04o", opts->fs_fmask); seq_printf(m, ",dmask=%04o", opts->fs_dmask); if (opts->allow_utime) seq_printf(m, ",allow_utime=%04o", opts->allow_utime); if (sbi->nls_disk) /* strip "cp" prefix from displayed option */ seq_printf(m, ",codepage=%s", &sbi->nls_disk->charset[2]); if (isvfat) { if (sbi->nls_io) seq_printf(m, ",iocharset=%s", sbi->nls_io->charset); switch (opts->shortname) { case VFAT_SFN_DISPLAY_WIN95 | VFAT_SFN_CREATE_WIN95: seq_puts(m, ",shortname=win95"); break; case VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WINNT: seq_puts(m, ",shortname=winnt"); break; case VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WIN95: seq_puts(m, ",shortname=mixed"); break; case VFAT_SFN_DISPLAY_LOWER | VFAT_SFN_CREATE_WIN95: seq_puts(m, ",shortname=lower"); break; default: seq_puts(m, ",shortname=unknown"); break; } } if (opts->name_check != 'n') seq_printf(m, ",check=%c", opts->name_check); if (opts->usefree) seq_puts(m, ",usefree"); if (opts->quiet) seq_puts(m, ",quiet"); if (opts->showexec) seq_puts(m, ",showexec"); if (opts->sys_immutable) seq_puts(m, ",sys_immutable"); if (!isvfat) { if (opts->dotsOK) seq_puts(m, ",dotsOK=yes"); if (opts->nocase) seq_puts(m, ",nocase"); } else { if (opts->utf8) seq_puts(m, ",utf8"); if (opts->unicode_xlate) seq_puts(m, ",uni_xlate"); if (!opts->numtail) seq_puts(m, ",nonumtail"); if (opts->rodir) seq_puts(m, ",rodir"); } if (opts->flush) seq_puts(m, ",flush"); if (opts->tz_set) { if (opts->time_offset) seq_printf(m, ",time_offset=%d", opts->time_offset); else seq_puts(m, ",tz=UTC"); } if (opts->errors == FAT_ERRORS_CONT) seq_puts(m, ",errors=continue"); else if (opts->errors == FAT_ERRORS_PANIC) seq_puts(m, ",errors=panic"); else seq_puts(m, ",errors=remount-ro"); if (opts->nfs == FAT_NFS_NOSTALE_RO) seq_puts(m, ",nfs=nostale_ro"); else if (opts->nfs) seq_puts(m, ",nfs=stale_rw"); if (opts->discard) seq_puts(m, ",discard"); if (opts->dos1xfloppy) seq_puts(m, ",dos1xfloppy"); return 0; } enum { Opt_check_n, Opt_check_r, Opt_check_s, Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask, Opt_allow_utime, Opt_codepage, Opt_usefree, Opt_nocase, Opt_quiet, Opt_showexec, Opt_debug, Opt_immutable, Opt_dots, Opt_nodots, Opt_charset, Opt_shortname_lower, Opt_shortname_win95, Opt_shortname_winnt, Opt_shortname_mixed, Opt_utf8_no, Opt_utf8_yes, Opt_uni_xl_no, Opt_uni_xl_yes, Opt_nonumtail_no, Opt_nonumtail_yes, Opt_obsolete, Opt_flush, Opt_tz_utc, Opt_rodir, Opt_err_cont, Opt_err_panic, Opt_err_ro, Opt_discard, Opt_nfs, Opt_time_offset, Opt_nfs_stale_rw, Opt_nfs_nostale_ro, Opt_err, Opt_dos1xfloppy, }; static const match_table_t fat_tokens = { {Opt_check_r, "check=relaxed"}, {Opt_check_s, "check=strict"}, {Opt_check_n, "check=normal"}, {Opt_check_r, "check=r"}, {Opt_check_s, "check=s"}, {Opt_check_n, "check=n"}, {Opt_uid, "uid=%u"}, {Opt_gid, "gid=%u"}, {Opt_umask, "umask=%o"}, {Opt_dmask, "dmask=%o"}, {Opt_fmask, "fmask=%o"}, {Opt_allow_utime, "allow_utime=%o"}, {Opt_codepage, "codepage=%u"}, {Opt_usefree, "usefree"}, {Opt_nocase, "nocase"}, {Opt_quiet, "quiet"}, {Opt_showexec, "showexec"}, {Opt_debug, "debug"}, {Opt_immutable, "sys_immutable"}, {Opt_flush, "flush"}, {Opt_tz_utc, "tz=UTC"}, {Opt_time_offset, "time_offset=%d"}, {Opt_err_cont, "errors=continue"}, {Opt_err_panic, "errors=panic"}, {Opt_err_ro, "errors=remount-ro"}, {Opt_discard, "discard"}, {Opt_nfs_stale_rw, "nfs"}, {Opt_nfs_stale_rw, "nfs=stale_rw"}, {Opt_nfs_nostale_ro, "nfs=nostale_ro"}, {Opt_dos1xfloppy, "dos1xfloppy"}, {Opt_obsolete, "conv=binary"}, {Opt_obsolete, "conv=text"}, {Opt_obsolete, "conv=auto"}, {Opt_obsolete, "conv=b"}, {Opt_obsolete, "conv=t"}, {Opt_obsolete, "conv=a"}, {Opt_obsolete, "fat=%u"}, {Opt_obsolete, "blocksize=%u"}, {Opt_obsolete, "cvf_format=%20s"}, {Opt_obsolete, "cvf_options=%100s"}, {Opt_obsolete, "posix"}, {Opt_err, NULL}, }; static const match_table_t msdos_tokens = { {Opt_nodots, "nodots"}, {Opt_nodots, "dotsOK=no"}, {Opt_dots, "dots"}, {Opt_dots, "dotsOK=yes"}, {Opt_err, NULL} }; static const match_table_t vfat_tokens = { {Opt_charset, "iocharset=%s"}, {Opt_shortname_lower, "shortname=lower"}, {Opt_shortname_win95, "shortname=win95"}, {Opt_shortname_winnt, "shortname=winnt"}, {Opt_shortname_mixed, "shortname=mixed"}, {Opt_utf8_no, "utf8=0"}, /* 0 or no or false */ {Opt_utf8_no, "utf8=no"}, {Opt_utf8_no, "utf8=false"}, {Opt_utf8_yes, "utf8=1"}, /* empty or 1 or yes or true */ {Opt_utf8_yes, "utf8=yes"}, {Opt_utf8_yes, "utf8=true"}, {Opt_utf8_yes, "utf8"}, {Opt_uni_xl_no, "uni_xlate=0"}, /* 0 or no or false */ {Opt_uni_xl_no, "uni_xlate=no"}, {Opt_uni_xl_no, "uni_xlate=false"}, {Opt_uni_xl_yes, "uni_xlate=1"}, /* empty or 1 or yes or true */ {Opt_uni_xl_yes, "uni_xlate=yes"}, {Opt_uni_xl_yes, "uni_xlate=true"}, {Opt_uni_xl_yes, "uni_xlate"}, {Opt_nonumtail_no, "nonumtail=0"}, /* 0 or no or false */ {Opt_nonumtail_no, "nonumtail=no"}, {Opt_nonumtail_no, "nonumtail=false"}, {Opt_nonumtail_yes, "nonumtail=1"}, /* empty or 1 or yes or true */ {Opt_nonumtail_yes, "nonumtail=yes"}, {Opt_nonumtail_yes, "nonumtail=true"}, {Opt_nonumtail_yes, "nonumtail"}, {Opt_rodir, "rodir"}, {Opt_err, NULL} }; static int parse_options(struct super_block *sb, char *options, int is_vfat, int silent, int *debug, struct fat_mount_options *opts) { char *p; substring_t args[MAX_OPT_ARGS]; int option; char *iocharset; opts->isvfat = is_vfat; opts->fs_uid = current_uid(); opts->fs_gid = current_gid(); opts->fs_fmask = opts->fs_dmask = current_umask(); opts->allow_utime = -1; opts->codepage = fat_default_codepage; fat_reset_iocharset(opts); if (is_vfat) { opts->shortname = VFAT_SFN_DISPLAY_WINNT|VFAT_SFN_CREATE_WIN95; opts->rodir = 0; } else { opts->shortname = 0; opts->rodir = 1; } opts->name_check = 'n'; opts->quiet = opts->showexec = opts->sys_immutable = opts->dotsOK = 0; opts->unicode_xlate = 0; opts->numtail = 1; opts->usefree = opts->nocase = 0; opts->tz_set = 0; opts->nfs = 0; opts->errors = FAT_ERRORS_RO; *debug = 0; opts->utf8 = IS_ENABLED(CONFIG_FAT_DEFAULT_UTF8) && is_vfat; if (!options) goto out; while ((p = strsep(&options, ",")) != NULL) { int token; if (!*p) continue; token = match_token(p, fat_tokens, args); if (token == Opt_err) { if (is_vfat) token = match_token(p, vfat_tokens, args); else token = match_token(p, msdos_tokens, args); } switch (token) { case Opt_check_s: opts->name_check = 's'; break; case Opt_check_r: opts->name_check = 'r'; break; case Opt_check_n: opts->name_check = 'n'; break; case Opt_usefree: opts->usefree = 1; break; case Opt_nocase: if (!is_vfat) opts->nocase = 1; else { /* for backward compatibility */ opts->shortname = VFAT_SFN_DISPLAY_WIN95 | VFAT_SFN_CREATE_WIN95; } break; case Opt_quiet: opts->quiet = 1; break; case Opt_showexec: opts->showexec = 1; break; case Opt_debug: *debug = 1; break; case Opt_immutable: opts->sys_immutable = 1; break; case Opt_uid: if (match_int(&args[0], &option)) return -EINVAL; opts->fs_uid = make_kuid(current_user_ns(), option); if (!uid_valid(opts->fs_uid)) return -EINVAL; break; case Opt_gid: if (match_int(&args[0], &option)) return -EINVAL; opts->fs_gid = make_kgid(current_user_ns(), option); if (!gid_valid(opts->fs_gid)) return -EINVAL; break; case Opt_umask: if (match_octal(&args[0], &option)) return -EINVAL; opts->fs_fmask = opts->fs_dmask = option; break; case Opt_dmask: if (match_octal(&args[0], &option)) return -EINVAL; opts->fs_dmask = option; break; case Opt_fmask: if (match_octal(&args[0], &option)) return -EINVAL; opts->fs_fmask = option; break; case Opt_allow_utime: if (match_octal(&args[0], &option)) return -EINVAL; opts->allow_utime = option & (S_IWGRP | S_IWOTH); break; case Opt_codepage: if (match_int(&args[0], &option)) return -EINVAL; opts->codepage = option; break; case Opt_flush: opts->flush = 1; break; case Opt_time_offset: if (match_int(&args[0], &option)) return -EINVAL; /* * GMT+-12 zones may have DST corrections so at least * 13 hours difference is needed. Make the limit 24 * just in case someone invents something unusual. */ if (option < -24 * 60 || option > 24 * 60) return -EINVAL; opts->tz_set = 1; opts->time_offset = option; break; case Opt_tz_utc: opts->tz_set = 1; opts->time_offset = 0; break; case Opt_err_cont: opts->errors = FAT_ERRORS_CONT; break; case Opt_err_panic: opts->errors = FAT_ERRORS_PANIC; break; case Opt_err_ro: opts->errors = FAT_ERRORS_RO; break; case Opt_nfs_stale_rw: opts->nfs = FAT_NFS_STALE_RW; break; case Opt_nfs_nostale_ro: opts->nfs = FAT_NFS_NOSTALE_RO; break; case Opt_dos1xfloppy: opts->dos1xfloppy = 1; break; /* msdos specific */ case Opt_dots: opts->dotsOK = 1; break; case Opt_nodots: opts->dotsOK = 0; break; /* vfat specific */ case Opt_charset: fat_reset_iocharset(opts); iocharset = match_strdup(&args[0]); if (!iocharset) return -ENOMEM; opts->iocharset = iocharset; break; case Opt_shortname_lower: opts->shortname = VFAT_SFN_DISPLAY_LOWER | VFAT_SFN_CREATE_WIN95; break; case Opt_shortname_win95: opts->shortname = VFAT_SFN_DISPLAY_WIN95 | VFAT_SFN_CREATE_WIN95; break; case Opt_shortname_winnt: opts->shortname = VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WINNT; break; case Opt_shortname_mixed: opts->shortname = VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WIN95; break; case Opt_utf8_no: /* 0 or no or false */ opts->utf8 = 0; break; case Opt_utf8_yes: /* empty or 1 or yes or true */ opts->utf8 = 1; break; case Opt_uni_xl_no: /* 0 or no or false */ opts->unicode_xlate = 0; break; case Opt_uni_xl_yes: /* empty or 1 or yes or true */ opts->unicode_xlate = 1; break; case Opt_nonumtail_no: /* 0 or no or false */ opts->numtail = 1; /* negated option */ break; case Opt_nonumtail_yes: /* empty or 1 or yes or true */ opts->numtail = 0; /* negated option */ break; case Opt_rodir: opts->rodir = 1; break; case Opt_discard: opts->discard = 1; break; /* obsolete mount options */ case Opt_obsolete: fat_msg(sb, KERN_INFO, "\"%s\" option is obsolete, " "not supported now", p); break; /* unknown option */ default: if (!silent) { fat_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" " "or missing value", p); } return -EINVAL; } } out: /* UTF-8 doesn't provide FAT semantics */ if (!strcmp(opts->iocharset, "utf8")) { fat_msg(sb, KERN_WARNING, "utf8 is not a recommended IO charset" " for FAT filesystems, filesystem will be " "case sensitive!"); } /* If user doesn't specify allow_utime, it's initialized from dmask. */ if (opts->allow_utime == (unsigned short)-1) opts->allow_utime = ~opts->fs_dmask & (S_IWGRP | S_IWOTH); if (opts->unicode_xlate) opts->utf8 = 0; if (opts->nfs == FAT_NFS_NOSTALE_RO) { sb->s_flags |= SB_RDONLY; sb->s_export_op = &fat_export_ops_nostale; } return 0; } static int fat_read_root(struct inode *inode) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); int error; MSDOS_I(inode)->i_pos = MSDOS_ROOT_INO; inode->i_uid = sbi->options.fs_uid; inode->i_gid = sbi->options.fs_gid; inode_inc_iversion(inode); inode->i_generation = 0; inode->i_mode = fat_make_mode(sbi, ATTR_DIR, S_IRWXUGO); inode->i_op = sbi->dir_ops; inode->i_fop = &fat_dir_operations; if (is_fat32(sbi)) { MSDOS_I(inode)->i_start = sbi->root_cluster; error = fat_calc_dir_size(inode); if (error < 0) return error; } else { MSDOS_I(inode)->i_start = 0; inode->i_size = sbi->dir_entries * sizeof(struct msdos_dir_entry); } inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1)) & ~((loff_t)sbi->cluster_size - 1)) >> 9; MSDOS_I(inode)->i_logstart = 0; MSDOS_I(inode)->mmu_private = inode->i_size; fat_save_attrs(inode, ATTR_DIR); inode->i_mtime.tv_sec = inode->i_atime.tv_sec = inode->i_ctime.tv_sec = 0; inode->i_mtime.tv_nsec = inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec = 0; set_nlink(inode, fat_subdirs(inode)+2); return 0; } static unsigned long calc_fat_clusters(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); /* Divide first to avoid overflow */ if (!is_fat12(sbi)) { unsigned long ent_per_sec = sb->s_blocksize * 8 / sbi->fat_bits; return ent_per_sec * sbi->fat_length; } return sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits; } static bool fat_bpb_is_zero(struct fat_boot_sector *b) { if (get_unaligned_le16(&b->sector_size)) return false; if (b->sec_per_clus) return false; if (b->reserved) return false; if (b->fats) return false; if (get_unaligned_le16(&b->dir_entries)) return false; if (get_unaligned_le16(&b->sectors)) return false; if (b->media) return false; if (b->fat_length) return false; if (b->secs_track) return false; if (b->heads) return false; return true; } static int fat_read_bpb(struct super_block *sb, struct fat_boot_sector *b, int silent, struct fat_bios_param_block *bpb) { int error = -EINVAL; /* Read in BPB ... */ memset(bpb, 0, sizeof(*bpb)); bpb->fat_sector_size = get_unaligned_le16(&b->sector_size); bpb->fat_sec_per_clus = b->sec_per_clus; bpb->fat_reserved = le16_to_cpu(b->reserved); bpb->fat_fats = b->fats; bpb->fat_dir_entries = get_unaligned_le16(&b->dir_entries); bpb->fat_sectors = get_unaligned_le16(&b->sectors); bpb->fat_fat_length = le16_to_cpu(b->fat_length); bpb->fat_total_sect = le32_to_cpu(b->total_sect); bpb->fat16_state = b->fat16.state; bpb->fat16_vol_id = get_unaligned_le32(b->fat16.vol_id); bpb->fat32_length = le32_to_cpu(b->fat32.length); bpb->fat32_root_cluster = le32_to_cpu(b->fat32.root_cluster); bpb->fat32_info_sector = le16_to_cpu(b->fat32.info_sector); bpb->fat32_state = b->fat32.state; bpb->fat32_vol_id = get_unaligned_le32(b->fat32.vol_id); /* Validate this looks like a FAT filesystem BPB */ if (!bpb->fat_reserved) { if (!silent) fat_msg(sb, KERN_ERR, "bogus number of reserved sectors"); goto out; } if (!bpb->fat_fats) { if (!silent) fat_msg(sb, KERN_ERR, "bogus number of FAT structure"); goto out; } /* * Earlier we checked here that b->secs_track and b->head are nonzero, * but it turns out valid FAT filesystems can have zero there. */ if (!fat_valid_media(b->media)) { if (!silent) fat_msg(sb, KERN_ERR, "invalid media value (0x%02x)", (unsigned)b->media); goto out; } if (!is_power_of_2(bpb->fat_sector_size) || (bpb->fat_sector_size < 512) || (bpb->fat_sector_size > 4096)) { if (!silent) fat_msg(sb, KERN_ERR, "bogus logical sector size %u", (unsigned)bpb->fat_sector_size); goto out; } if (!is_power_of_2(bpb->fat_sec_per_clus)) { if (!silent) fat_msg(sb, KERN_ERR, "bogus sectors per cluster %u", (unsigned)bpb->fat_sec_per_clus); goto out; } if (bpb->fat_fat_length == 0 && bpb->fat32_length == 0) { if (!silent) fat_msg(sb, KERN_ERR, "bogus number of FAT sectors"); goto out; } error = 0; out: return error; } static int fat_read_static_bpb(struct super_block *sb, struct fat_boot_sector *b, int silent, struct fat_bios_param_block *bpb) { static const char *notdos1x = "This doesn't look like a DOS 1.x volume"; struct fat_floppy_defaults *fdefaults = NULL; int error = -EINVAL; sector_t bd_sects; unsigned i; bd_sects = i_size_read(sb->s_bdev->bd_inode) / SECTOR_SIZE; /* 16-bit DOS 1.x reliably wrote bootstrap short-jmp code */ if (b->ignored[0] != 0xeb || b->ignored[2] != 0x90) { if (!silent) fat_msg(sb, KERN_ERR, "%s; no bootstrapping code", notdos1x); goto out; } /* * If any value in this region is non-zero, it isn't archaic * DOS. */ if (!fat_bpb_is_zero(b)) { if (!silent) fat_msg(sb, KERN_ERR, "%s; DOS 2.x BPB is non-zero", notdos1x); goto out; } for (i = 0; i < ARRAY_SIZE(floppy_defaults); i++) { if (floppy_defaults[i].nr_sectors == bd_sects) { fdefaults = &floppy_defaults[i]; break; } } if (fdefaults == NULL) { if (!silent) fat_msg(sb, KERN_WARNING, "This looks like a DOS 1.x volume, but isn't a recognized floppy size (%llu sectors)", (u64)bd_sects); goto out; } if (!silent) fat_msg(sb, KERN_INFO, "This looks like a DOS 1.x volume; assuming default BPB values"); memset(bpb, 0, sizeof(*bpb)); bpb->fat_sector_size = SECTOR_SIZE; bpb->fat_sec_per_clus = fdefaults->sec_per_clus; bpb->fat_reserved = 1; bpb->fat_fats = 2; bpb->fat_dir_entries = fdefaults->dir_entries; bpb->fat_sectors = fdefaults->nr_sectors; bpb->fat_fat_length = fdefaults->fat_length; error = 0; out: return error; } /* * Read the super block of an MS-DOS FS. */ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, void (*setup)(struct super_block *)) { struct inode *root_inode = NULL, *fat_inode = NULL; struct inode *fsinfo_inode = NULL; struct buffer_head *bh; struct fat_bios_param_block bpb; struct msdos_sb_info *sbi; u16 logical_sector_size; u32 total_sectors, total_clusters, fat_clusters, rootdir_sectors; int debug; long error; char buf[50]; struct timespec64 ts; /* * GFP_KERNEL is ok here, because while we do hold the * superblock lock, memory pressure can't call back into * the filesystem, since we're only just about to mount * it and have no inodes etc active! */ sbi = kzalloc(sizeof(struct msdos_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; sb->s_fs_info = sbi; sb->s_flags |= SB_NODIRATIME; sb->s_magic = MSDOS_SUPER_MAGIC; sb->s_op = &fat_sops; sb->s_export_op = &fat_export_ops; /* * fat timestamps are complex and truncated by fat itself, so * we set 1 here to be fast */ sb->s_time_gran = 1; mutex_init(&sbi->nfs_build_inode_lock); ratelimit_state_init(&sbi->ratelimit, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); error = parse_options(sb, data, isvfat, silent, &debug, &sbi->options); if (error) goto out_fail; setup(sb); /* flavour-specific stuff that needs options */ error = -EIO; sb_min_blocksize(sb, 512); bh = sb_bread(sb, 0); if (bh == NULL) { fat_msg(sb, KERN_ERR, "unable to read boot sector"); goto out_fail; } error = fat_read_bpb(sb, (struct fat_boot_sector *)bh->b_data, silent, &bpb); if (error == -EINVAL && sbi->options.dos1xfloppy) error = fat_read_static_bpb(sb, (struct fat_boot_sector *)bh->b_data, silent, &bpb); brelse(bh); if (error == -EINVAL) goto out_invalid; else if (error) goto out_fail; logical_sector_size = bpb.fat_sector_size; sbi->sec_per_clus = bpb.fat_sec_per_clus; error = -EIO; if (logical_sector_size < sb->s_blocksize) { fat_msg(sb, KERN_ERR, "logical sector size too small for device" " (logical sector size = %u)", logical_sector_size); goto out_fail; } if (logical_sector_size > sb->s_blocksize) { struct buffer_head *bh_resize; if (!sb_set_blocksize(sb, logical_sector_size)) { fat_msg(sb, KERN_ERR, "unable to set blocksize %u", logical_sector_size); goto out_fail; } /* Verify that the larger boot sector is fully readable */ bh_resize = sb_bread(sb, 0); if (bh_resize == NULL) { fat_msg(sb, KERN_ERR, "unable to read boot sector" " (logical sector size = %lu)", sb->s_blocksize); goto out_fail; } brelse(bh_resize); } mutex_init(&sbi->s_lock); sbi->cluster_size = sb->s_blocksize * sbi->sec_per_clus; sbi->cluster_bits = ffs(sbi->cluster_size) - 1; sbi->fats = bpb.fat_fats; sbi->fat_bits = 0; /* Don't know yet */ sbi->fat_start = bpb.fat_reserved; sbi->fat_length = bpb.fat_fat_length; sbi->root_cluster = 0; sbi->free_clusters = -1; /* Don't know yet */ sbi->free_clus_valid = 0; sbi->prev_free = FAT_START_ENT; sb->s_maxbytes = 0xffffffff; fat_time_fat2unix(sbi, &ts, 0, cpu_to_le16(FAT_DATE_MIN), 0); sb->s_time_min = ts.tv_sec; fat_time_fat2unix(sbi, &ts, cpu_to_le16(FAT_TIME_MAX), cpu_to_le16(FAT_DATE_MAX), 0); sb->s_time_max = ts.tv_sec; if (!sbi->fat_length && bpb.fat32_length) { struct fat_boot_fsinfo *fsinfo; struct buffer_head *fsinfo_bh; /* Must be FAT32 */ sbi->fat_bits = 32; sbi->fat_length = bpb.fat32_length; sbi->root_cluster = bpb.fat32_root_cluster; /* MC - if info_sector is 0, don't multiply by 0 */ sbi->fsinfo_sector = bpb.fat32_info_sector; if (sbi->fsinfo_sector == 0) sbi->fsinfo_sector = 1; fsinfo_bh = sb_bread(sb, sbi->fsinfo_sector); if (fsinfo_bh == NULL) { fat_msg(sb, KERN_ERR, "bread failed, FSINFO block" " (sector = %lu)", sbi->fsinfo_sector); goto out_fail; } fsinfo = (struct fat_boot_fsinfo *)fsinfo_bh->b_data; if (!IS_FSINFO(fsinfo)) { fat_msg(sb, KERN_WARNING, "Invalid FSINFO signature: " "0x%08x, 0x%08x (sector = %lu)", le32_to_cpu(fsinfo->signature1), le32_to_cpu(fsinfo->signature2), sbi->fsinfo_sector); } else { if (sbi->options.usefree) sbi->free_clus_valid = 1; sbi->free_clusters = le32_to_cpu(fsinfo->free_clusters); sbi->prev_free = le32_to_cpu(fsinfo->next_cluster); } brelse(fsinfo_bh); } /* interpret volume ID as a little endian 32 bit integer */ if (is_fat32(sbi)) sbi->vol_id = bpb.fat32_vol_id; else /* fat 16 or 12 */ sbi->vol_id = bpb.fat16_vol_id; sbi->dir_per_block = sb->s_blocksize / sizeof(struct msdos_dir_entry); sbi->dir_per_block_bits = ffs(sbi->dir_per_block) - 1; sbi->dir_start = sbi->fat_start + sbi->fats * sbi->fat_length; sbi->dir_entries = bpb.fat_dir_entries; if (sbi->dir_entries & (sbi->dir_per_block - 1)) { if (!silent) fat_msg(sb, KERN_ERR, "bogus number of directory entries" " (%u)", sbi->dir_entries); goto out_invalid; } rootdir_sectors = sbi->dir_entries * sizeof(struct msdos_dir_entry) / sb->s_blocksize; sbi->data_start = sbi->dir_start + rootdir_sectors; total_sectors = bpb.fat_sectors; if (total_sectors == 0) total_sectors = bpb.fat_total_sect; total_clusters = (total_sectors - sbi->data_start) / sbi->sec_per_clus; if (!is_fat32(sbi)) sbi->fat_bits = (total_clusters > MAX_FAT12) ? 16 : 12; /* some OSes set FAT_STATE_DIRTY and clean it on unmount. */ if (is_fat32(sbi)) sbi->dirty = bpb.fat32_state & FAT_STATE_DIRTY; else /* fat 16 or 12 */ sbi->dirty = bpb.fat16_state & FAT_STATE_DIRTY; /* check that FAT table does not overflow */ fat_clusters = calc_fat_clusters(sb); total_clusters = min(total_clusters, fat_clusters - FAT_START_ENT); if (total_clusters > max_fat(sb)) { if (!silent) fat_msg(sb, KERN_ERR, "count of clusters too big (%u)", total_clusters); goto out_invalid; } sbi->max_cluster = total_clusters + FAT_START_ENT; /* check the free_clusters, it's not necessarily correct */ if (sbi->free_clusters != -1 && sbi->free_clusters > total_clusters) sbi->free_clusters = -1; /* check the prev_free, it's not necessarily correct */ sbi->prev_free %= sbi->max_cluster; if (sbi->prev_free < FAT_START_ENT) sbi->prev_free = FAT_START_ENT; /* set up enough so that it can read an inode */ fat_hash_init(sb); dir_hash_init(sb); fat_ent_access_init(sb); /* * The low byte of the first FAT entry must have the same value as * the media field of the boot sector. But in real world, too many * devices are writing wrong values. So, removed that validity check. * * The removed check compared the first FAT entry to a value dependent * on the media field like this: * == (0x0F00 | media), for FAT12 * == (0XFF00 | media), for FAT16 * == (0x0FFFFF | media), for FAT32 */ error = -EINVAL; sprintf(buf, "cp%d", sbi->options.codepage); sbi->nls_disk = load_nls(buf); if (!sbi->nls_disk) { fat_msg(sb, KERN_ERR, "codepage %s not found", buf); goto out_fail; } /* FIXME: utf8 is using iocharset for upper/lower conversion */ if (sbi->options.isvfat) { sbi->nls_io = load_nls(sbi->options.iocharset); if (!sbi->nls_io) { fat_msg(sb, KERN_ERR, "IO charset %s not found", sbi->options.iocharset); goto out_fail; } } error = -ENOMEM; fat_inode = new_inode(sb); if (!fat_inode) goto out_fail; sbi->fat_inode = fat_inode; fsinfo_inode = new_inode(sb); if (!fsinfo_inode) goto out_fail; fsinfo_inode->i_ino = MSDOS_FSINFO_INO; sbi->fsinfo_inode = fsinfo_inode; insert_inode_hash(fsinfo_inode); root_inode = new_inode(sb); if (!root_inode) goto out_fail; root_inode->i_ino = MSDOS_ROOT_INO; inode_set_iversion(root_inode, 1); error = fat_read_root(root_inode); if (error < 0) { iput(root_inode); goto out_fail; } error = -ENOMEM; insert_inode_hash(root_inode); fat_attach(root_inode, 0); sb->s_root = d_make_root(root_inode); if (!sb->s_root) { fat_msg(sb, KERN_ERR, "get root inode failed"); goto out_fail; } if (sbi->options.discard) { struct request_queue *q = bdev_get_queue(sb->s_bdev); if (!blk_queue_discard(q)) fat_msg(sb, KERN_WARNING, "mounting with \"discard\" option, but " "the device does not support discard"); } fat_set_state(sb, 1, 0); return 0; out_invalid: error = -EINVAL; if (!silent) fat_msg(sb, KERN_INFO, "Can't find a valid FAT filesystem"); out_fail: if (fsinfo_inode) iput(fsinfo_inode); if (fat_inode) iput(fat_inode); unload_nls(sbi->nls_io); unload_nls(sbi->nls_disk); fat_reset_iocharset(&sbi->options); sb->s_fs_info = NULL; kfree(sbi); return error; } EXPORT_SYMBOL_GPL(fat_fill_super); /* * helper function for fat_flush_inodes. This writes both the inode * and the file data blocks, waiting for in flight data blocks before * the start of the call. It does not wait for any io started * during the call */ static int writeback_inode(struct inode *inode) { int ret; /* if we used wait=1, sync_inode_metadata waits for the io for the * inode to finish. So wait=0 is sent down to sync_inode_metadata * and filemap_fdatawrite is used for the data blocks */ ret = sync_inode_metadata(inode, 0); if (!ret) ret = filemap_fdatawrite(inode->i_mapping); return ret; } /* * write data and metadata corresponding to i1 and i2. The io is * started but we do not wait for any of it to finish. * * filemap_flush is used for the block device, so if there is a dirty * page for a block already in flight, we will not wait and start the * io over again */ int fat_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2) { int ret = 0; if (!MSDOS_SB(sb)->options.flush) return 0; if (i1) ret = writeback_inode(i1); if (!ret && i2) ret = writeback_inode(i2); if (!ret) { struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping; ret = filemap_flush(mapping); } return ret; } EXPORT_SYMBOL_GPL(fat_flush_inodes); static int __init init_fat_fs(void) { int err; err = fat_cache_init(); if (err) return err; err = fat_init_inodecache(); if (err) goto failed; return 0; failed: fat_cache_destroy(); return err; } static void __exit exit_fat_fs(void) { fat_cache_destroy(); fat_destroy_inodecache(); } module_init(init_fat_fs) module_exit(exit_fat_fs) MODULE_LICENSE("GPL");
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_CONNTRACK_EXTEND_H #define _NF_CONNTRACK_EXTEND_H #include <linux/slab.h> #include <net/netfilter/nf_conntrack.h> enum nf_ct_ext_id { NF_CT_EXT_HELPER, #if IS_ENABLED(CONFIG_NF_NAT) NF_CT_EXT_NAT, #endif NF_CT_EXT_SEQADJ, NF_CT_EXT_ACCT, #ifdef CONFIG_NF_CONNTRACK_EVENTS NF_CT_EXT_ECACHE, #endif #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP NF_CT_EXT_TSTAMP, #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT NF_CT_EXT_TIMEOUT, #endif #ifdef CONFIG_NF_CONNTRACK_LABELS NF_CT_EXT_LABELS, #endif #if IS_ENABLED(CONFIG_NETFILTER_SYNPROXY) NF_CT_EXT_SYNPROXY, #endif NF_CT_EXT_NUM, }; #define NF_CT_EXT_HELPER_TYPE struct nf_conn_help #define NF_CT_EXT_NAT_TYPE struct nf_conn_nat #define NF_CT_EXT_SEQADJ_TYPE struct nf_conn_seqadj #define NF_CT_EXT_ACCT_TYPE struct nf_conn_acct #define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache #define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp #define NF_CT_EXT_TIMEOUT_TYPE struct nf_conn_timeout #define NF_CT_EXT_LABELS_TYPE struct nf_conn_labels #define NF_CT_EXT_SYNPROXY_TYPE struct nf_conn_synproxy /* Extensions: optional stuff which isn't permanently in struct. */ struct nf_ct_ext { u8 offset[NF_CT_EXT_NUM]; u8 len; char data[]; }; static inline bool __nf_ct_ext_exist(const struct nf_ct_ext *ext, u8 id) { return !!ext->offset[id]; } static inline bool nf_ct_ext_exist(const struct nf_conn *ct, u8 id) { return (ct->ext && __nf_ct_ext_exist(ct->ext, id)); } static inline void *__nf_ct_ext_find(const struct nf_conn *ct, u8 id) { if (!nf_ct_ext_exist(ct, id)) return NULL; return (void *)ct->ext + ct->ext->offset[id]; } #define nf_ct_ext_find(ext, id) \ ((id##_TYPE *)__nf_ct_ext_find((ext), (id))) /* Destroy all relationships */ void nf_ct_ext_destroy(struct nf_conn *ct); /* Add this type, returns pointer to data or NULL. */ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp); struct nf_ct_ext_type { /* Destroys relationships (can be NULL). */ void (*destroy)(struct nf_conn *ct); enum nf_ct_ext_id id; /* Length and min alignment. */ u8 len; u8 align; }; int nf_ct_extend_register(const struct nf_ct_ext_type *type); void nf_ct_extend_unregister(const struct nf_ct_ext_type *type); #endif /* _NF_CONNTRACK_EXTEND_H */
1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM filemap #if !defined(_TRACE_FILEMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FILEMAP_H #include <linux/types.h> #include <linux/tracepoint.h> #include <linux/mm.h> #include <linux/memcontrol.h> #include <linux/device.h> #include <linux/kdev_t.h> #include <linux/errseq.h> DECLARE_EVENT_CLASS(mm_filemap_op_page_cache, TP_PROTO(struct page *page), TP_ARGS(page), TP_STRUCT__entry( __field(unsigned long, pfn) __field(unsigned long, i_ino) __field(unsigned long, index) __field(dev_t, s_dev) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->i_ino = page->mapping->host->i_ino; __entry->index = page->index; if (page->mapping->host->i_sb) __entry->s_dev = page->mapping->host->i_sb->s_dev; else __entry->s_dev = page->mapping->host->i_rdev; ), TP_printk("dev %d:%d ino %lx page=%p pfn=%lu ofs=%lu", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, pfn_to_page(__entry->pfn), __entry->pfn, __entry->index << PAGE_SHIFT) ); DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_delete_from_page_cache, TP_PROTO(struct page *page), TP_ARGS(page) ); DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_add_to_page_cache, TP_PROTO(struct page *page), TP_ARGS(page) ); TRACE_EVENT(filemap_set_wb_err, TP_PROTO(struct address_space *mapping, errseq_t eseq), TP_ARGS(mapping, eseq), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(errseq_t, errseq) ), TP_fast_assign( __entry->i_ino = mapping->host->i_ino; __entry->errseq = eseq; if (mapping->host->i_sb) __entry->s_dev = mapping->host->i_sb->s_dev; else __entry->s_dev = mapping->host->i_rdev; ), TP_printk("dev=%d:%d ino=0x%lx errseq=0x%x", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->errseq) ); TRACE_EVENT(file_check_and_advance_wb_err, TP_PROTO(struct file *file, errseq_t old), TP_ARGS(file, old), TP_STRUCT__entry( __field(struct file *, file) __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(errseq_t, old) __field(errseq_t, new) ), TP_fast_assign( __entry->file = file; __entry->i_ino = file->f_mapping->host->i_ino; if (file->f_mapping->host->i_sb) __entry->s_dev = file->f_mapping->host->i_sb->s_dev; else __entry->s_dev = file->f_mapping->host->i_rdev; __entry->old = old; __entry->new = file->f_wb_err; ), TP_printk("file=%p dev=%d:%d ino=0x%lx old=0x%x new=0x%x", __entry->file, MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->old, __entry->new) ); #endif /* _TRACE_FILEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef INT_BLK_MQ_H #define INT_BLK_MQ_H #include "blk-stat.h" #include "blk-mq-tag.h" struct blk_mq_tag_set; struct blk_mq_ctxs { struct kobject kobj; struct blk_mq_ctx __percpu *queue_ctx; }; /** * struct blk_mq_ctx - State for a software queue facing the submitting CPUs */ struct blk_mq_ctx { struct { spinlock_t lock; struct list_head rq_lists[HCTX_MAX_TYPES]; } ____cacheline_aligned_in_smp; unsigned int cpu; unsigned short index_hw[HCTX_MAX_TYPES]; struct blk_mq_hw_ctx *hctxs[HCTX_MAX_TYPES]; /* incremented at dispatch time */ unsigned long rq_dispatched[2]; unsigned long rq_merged; /* incremented at completion time */ unsigned long ____cacheline_aligned_in_smp rq_completed[2]; struct request_queue *queue; struct blk_mq_ctxs *ctxs; struct kobject kobj; } ____cacheline_aligned_in_smp; void blk_mq_exit_queue(struct request_queue *q); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr); void blk_mq_wake_waiters(struct request_queue *q); bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *, unsigned int); void blk_mq_add_to_requeue_list(struct request *rq, bool at_head, bool kick_requeue_list); void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list); struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *start); void blk_mq_put_rq_ref(struct request *rq); /* * Internal helpers for allocating/freeing the request map */ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx); void blk_mq_free_rq_map(struct blk_mq_tags *tags, unsigned int flags); struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, unsigned int hctx_idx, unsigned int nr_tags, unsigned int reserved_tags, unsigned int flags); int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx, unsigned int depth); /* * Internal helpers for request insertion into sw queues */ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, bool at_head); void blk_mq_request_bypass_insert(struct request *rq, bool at_head, bool run_queue); void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, struct list_head *list); /* Used by blk_insert_cloned_request() to issue request directly */ blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last); void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct list_head *list); /* * CPU -> queue mappings */ extern int blk_mq_hw_queue_to_node(struct blk_mq_queue_map *qmap, unsigned int); /* * blk_mq_map_queue_type() - map (hctx_type,cpu) to hardware queue * @q: request queue * @type: the hctx type index * @cpu: CPU */ static inline struct blk_mq_hw_ctx *blk_mq_map_queue_type(struct request_queue *q, enum hctx_type type, unsigned int cpu) { return q->queue_hw_ctx[q->tag_set->map[type].mq_map[cpu]]; } /* * blk_mq_map_queue() - map (cmd_flags,type) to hardware queue * @q: request queue * @flags: request command flags * @cpu: cpu ctx */ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q, unsigned int flags, struct blk_mq_ctx *ctx) { enum hctx_type type = HCTX_TYPE_DEFAULT; /* * The caller ensure that if REQ_HIPRI, poll must be enabled. */ if (flags & REQ_HIPRI) type = HCTX_TYPE_POLL; else if ((flags & REQ_OP_MASK) == REQ_OP_READ) type = HCTX_TYPE_READ; return ctx->hctxs[type]; } /* * sysfs helpers */ extern void blk_mq_sysfs_init(struct request_queue *q); extern void blk_mq_sysfs_deinit(struct request_queue *q); extern int __blk_mq_register_dev(struct device *dev, struct request_queue *q); extern int blk_mq_sysfs_register(struct request_queue *q); extern void blk_mq_sysfs_unregister(struct request_queue *q); extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx); void blk_mq_release(struct request_queue *q); static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q, unsigned int cpu) { return per_cpu_ptr(q->queue_ctx, cpu); } /* * This assumes per-cpu software queueing queues. They could be per-node * as well, for instance. For now this is hardcoded as-is. Note that we don't * care about preemption, since we know the ctx's are persistent. This does * mean that we can't rely on ctx always matching the currently running CPU. */ static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q) { return __blk_mq_get_ctx(q, raw_smp_processor_id()); } struct blk_mq_alloc_data { /* input parameter */ struct request_queue *q; blk_mq_req_flags_t flags; unsigned int shallow_depth; unsigned int cmd_flags; /* input & output parameter */ struct blk_mq_ctx *ctx; struct blk_mq_hw_ctx *hctx; }; static inline bool blk_mq_is_sbitmap_shared(unsigned int flags) { return flags & BLK_MQ_F_TAG_HCTX_SHARED; } static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data) { if (data->q->elevator) return data->hctx->sched_tags; return data->hctx->tags; } static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx) { return test_bit(BLK_MQ_S_STOPPED, &hctx->state); } static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx) { return hctx->nr_ctx && hctx->tags; } unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part); void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part, unsigned int inflight[2]); static inline void blk_mq_put_dispatch_budget(struct request_queue *q) { if (q->mq_ops->put_budget) q->mq_ops->put_budget(q); } static inline bool blk_mq_get_dispatch_budget(struct request_queue *q) { if (q->mq_ops->get_budget) return q->mq_ops->get_budget(q); return true; } static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx) { if (blk_mq_is_sbitmap_shared(hctx->flags)) atomic_inc(&hctx->queue->nr_active_requests_shared_sbitmap); else atomic_inc(&hctx->nr_active); } static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx) { if (blk_mq_is_sbitmap_shared(hctx->flags)) atomic_dec(&hctx->queue->nr_active_requests_shared_sbitmap); else atomic_dec(&hctx->nr_active); } static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx) { if (blk_mq_is_sbitmap_shared(hctx->flags)) return atomic_read(&hctx->queue->nr_active_requests_shared_sbitmap); return atomic_read(&hctx->nr_active); } static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq) { blk_mq_put_tag(hctx->tags, rq->mq_ctx, rq->tag); rq->tag = BLK_MQ_NO_TAG; if (rq->rq_flags & RQF_MQ_INFLIGHT) { rq->rq_flags &= ~RQF_MQ_INFLIGHT; __blk_mq_dec_active_requests(hctx); } } static inline void blk_mq_put_driver_tag(struct request *rq) { if (rq->tag == BLK_MQ_NO_TAG || rq->internal_tag == BLK_MQ_NO_TAG) return; __blk_mq_put_driver_tag(rq->mq_hctx, rq); } static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap) { int cpu; for_each_possible_cpu(cpu) qmap->mq_map[cpu] = 0; } /* * blk_mq_plug() - Get caller context plug * @q: request queue * @bio : the bio being submitted by the caller context * * Plugging, by design, may delay the insertion of BIOs into the elevator in * order to increase BIO merging opportunities. This however can cause BIO * insertion order to change from the order in which submit_bio() is being * executed in the case of multiple contexts concurrently issuing BIOs to a * device, even if these context are synchronized to tightly control BIO issuing * order. While this is not a problem with regular block devices, this ordering * change can cause write BIO failures with zoned block devices as these * require sequential write patterns to zones. Prevent this from happening by * ignoring the plug state of a BIO issuing context if the target request queue * is for a zoned block device and the BIO to plug is a write operation. * * Return current->plug if the bio can be plugged and NULL otherwise */ static inline struct blk_plug *blk_mq_plug(struct request_queue *q, struct bio *bio) { /* * For regular block devices or read operations, use the context plug * which may be NULL if blk_start_plug() was not executed. */ if (!blk_queue_is_zoned(q) || !op_is_write(bio_op(bio))) return current->plug; /* Zoned block device write operation case: do not plug the BIO */ return NULL; } /* * For shared tag users, we track the number of currently active users * and attempt to provide a fair share of the tag depth for each of them. */ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, struct sbitmap_queue *bt) { unsigned int depth, users; if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) return true; /* * Don't try dividing an ant */ if (bt->sb.depth == 1) return true; if (blk_mq_is_sbitmap_shared(hctx->flags)) { struct request_queue *q = hctx->queue; struct blk_mq_tag_set *set = q->tag_set; if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) return true; users = atomic_read(&set->active_queues_shared_sbitmap); } else { if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) return true; users = atomic_read(&hctx->tags->active_queues); } if (!users) return true; /* * Allow at least some tags */ depth = max((bt->sb.depth + users - 1) / users, 4U); return __blk_mq_active_requests(hctx) < depth; } #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_IO_H #define _ASM_X86_IO_H /* * This file contains the definitions for the x86 IO instructions * inb/inw/inl/outb/outw/outl and the "string versions" of the same * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing" * versions of the single-IO instructions (inb_p/inw_p/..). * * This file is not meant to be obfuscating: it's just complicated * to (a) handle it all in a way that makes gcc able to optimize it * as well as possible and (b) trying to avoid writing the same thing * over and over again with slight variations and possibly making a * mistake somewhere. */ /* * Thanks to James van Artsdalen for a better timing-fix than * the two short jumps: using outb's to a nonexistent port seems * to guarantee better timings even on fast machines. * * On the other hand, I'd like to be sure of a non-existent port: * I feel a bit unsafe about using 0x80 (should be safe, though) * * Linus */ /* * Bit simplified and optimized by Jan Hubicka * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999. * * isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added, * isa_read[wl] and isa_write[wl] fixed * - Arnaldo Carvalho de Melo <acme@conectiva.com.br> */ #define ARCH_HAS_IOREMAP_WC #define ARCH_HAS_IOREMAP_WT #include <linux/string.h> #include <linux/compiler.h> #include <asm/page.h> #include <asm/early_ioremap.h> #include <asm/pgtable_types.h> #define build_mmio_read(name, size, type, reg, barrier) \ static inline type name(const volatile void __iomem *addr) \ { type ret; asm volatile("mov" size " %1,%0":reg (ret) \ :"m" (*(volatile type __force *)addr) barrier); return ret; } #define build_mmio_write(name, size, type, reg, barrier) \ static inline void name(type val, volatile void __iomem *addr) \ { asm volatile("mov" size " %0,%1": :reg (val), \ "m" (*(volatile type __force *)addr) barrier); } build_mmio_read(readb, "b", unsigned char, "=q", :"memory") build_mmio_read(readw, "w", unsigned short, "=r", :"memory") build_mmio_read(readl, "l", unsigned int, "=r", :"memory") build_mmio_read(__readb, "b", unsigned char, "=q", ) build_mmio_read(__readw, "w", unsigned short, "=r", ) build_mmio_read(__readl, "l", unsigned int, "=r", ) build_mmio_write(writeb, "b", unsigned char, "q", :"memory") build_mmio_write(writew, "w", unsigned short, "r", :"memory") build_mmio_write(writel, "l", unsigned int, "r", :"memory") build_mmio_write(__writeb, "b", unsigned char, "q", ) build_mmio_write(__writew, "w", unsigned short, "r", ) build_mmio_write(__writel, "l", unsigned int, "r", ) #define readb readb #define readw readw #define readl readl #define readb_relaxed(a) __readb(a) #define readw_relaxed(a) __readw(a) #define readl_relaxed(a) __readl(a) #define __raw_readb __readb #define __raw_readw __readw #define __raw_readl __readl #define writeb writeb #define writew writew #define writel writel #define writeb_relaxed(v, a) __writeb(v, a) #define writew_relaxed(v, a) __writew(v, a) #define writel_relaxed(v, a) __writel(v, a) #define __raw_writeb __writeb #define __raw_writew __writew #define __raw_writel __writel #ifdef CONFIG_X86_64 build_mmio_read(readq, "q", u64, "=r", :"memory") build_mmio_read(__readq, "q", u64, "=r", ) build_mmio_write(writeq, "q", u64, "r", :"memory") build_mmio_write(__writeq, "q", u64, "r", ) #define readq_relaxed(a) __readq(a) #define writeq_relaxed(v, a) __writeq(v, a) #define __raw_readq __readq #define __raw_writeq __writeq /* Let people know that we have them */ #define readq readq #define writeq writeq #endif #define ARCH_HAS_VALID_PHYS_ADDR_RANGE extern int valid_phys_addr_range(phys_addr_t addr, size_t size); extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); /** * virt_to_phys - map virtual addresses to physical * @address: address to remap * * The returned physical address is the physical (CPU) mapping for * the memory address given. It is only valid to use this function on * addresses directly mapped or allocated via kmalloc. * * This function does not give bus mappings for DMA transfers. In * almost all conceivable cases a device driver should not be using * this function */ static inline phys_addr_t virt_to_phys(volatile void *address) { return __pa(address); } #define virt_to_phys virt_to_phys /** * phys_to_virt - map physical address to virtual * @address: address to remap * * The returned virtual address is a current CPU mapping for * the memory address given. It is only valid to use this function on * addresses that have a kernel mapping * * This function does not handle bus mappings for DMA transfers. In * almost all conceivable cases a device driver should not be using * this function */ static inline void *phys_to_virt(phys_addr_t address) { return __va(address); } #define phys_to_virt phys_to_virt /* * Change "struct page" to physical address. */ #define page_to_phys(page) ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT) /* * ISA I/O bus memory addresses are 1:1 with the physical address. * However, we truncate the address to unsigned int to avoid undesirable * promitions in legacy drivers. */ static inline unsigned int isa_virt_to_bus(volatile void *address) { return (unsigned int)virt_to_phys(address); } #define isa_bus_to_virt phys_to_virt /* * However PCI ones are not necessarily 1:1 and therefore these interfaces * are forbidden in portable PCI drivers. * * Allow them on x86 for legacy drivers, though. */ #define virt_to_bus virt_to_phys #define bus_to_virt phys_to_virt /* * The default ioremap() behavior is non-cached; if you need something * else, you probably want one of the following. */ extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size); #define ioremap_uc ioremap_uc extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size); #define ioremap_cache ioremap_cache extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, unsigned long prot_val); #define ioremap_prot ioremap_prot extern void __iomem *ioremap_encrypted(resource_size_t phys_addr, unsigned long size); #define ioremap_encrypted ioremap_encrypted /** * ioremap - map bus memory into CPU space * @offset: bus address of the memory * @size: size of the resource to map * * ioremap performs a platform specific sequence of operations to * make bus memory CPU accessible via the readb/readw/readl/writeb/ * writew/writel functions and the other mmio helpers. The returned * address is not guaranteed to be usable directly as a virtual * address. * * If the area you are trying to map is a PCI BAR you should have a * look at pci_iomap(). */ void __iomem *ioremap(resource_size_t offset, unsigned long size); #define ioremap ioremap extern void iounmap(volatile void __iomem *addr); #define iounmap iounmap extern void set_iounmap_nonlazy(void); #ifdef __KERNEL__ void memcpy_fromio(void *, const volatile void __iomem *, size_t); void memcpy_toio(volatile void __iomem *, const void *, size_t); void memset_io(volatile void __iomem *, int, size_t); #define memcpy_fromio memcpy_fromio #define memcpy_toio memcpy_toio #define memset_io memset_io #include <asm-generic/iomap.h> /* * ISA space is 'always mapped' on a typical x86 system, no need to * explicitly ioremap() it. The fact that the ISA IO space is mapped * to PAGE_OFFSET is pure coincidence - it does not mean ISA values * are physical addresses. The following constant pointer can be * used as the IO-area pointer (it can be iounmapped as well, so the * analogy with PCI is quite large): */ #define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET)) #endif /* __KERNEL__ */ extern void native_io_delay(void); extern int io_delay_type; extern void io_delay_init(void); #if defined(CONFIG_PARAVIRT) #include <asm/paravirt.h> #else static inline void slow_down_io(void) { native_io_delay(); #ifdef REALLY_SLOW_IO native_io_delay(); native_io_delay(); native_io_delay(); #endif } #endif #ifdef CONFIG_AMD_MEM_ENCRYPT #include <linux/jump_label.h> extern struct static_key_false sev_enable_key; static inline bool sev_key_active(void) { return static_branch_unlikely(&sev_enable_key); } #else /* !CONFIG_AMD_MEM_ENCRYPT */ static inline bool sev_key_active(void) { return false; } #endif /* CONFIG_AMD_MEM_ENCRYPT */ #define BUILDIO(bwl, bw, type) \ static inline void out##bwl(unsigned type value, int port) \ { \ asm volatile("out" #bwl " %" #bw "0, %w1" \ : : "a"(value), "Nd"(port)); \ } \ \ static inline unsigned type in##bwl(int port) \ { \ unsigned type value; \ asm volatile("in" #bwl " %w1, %" #bw "0" \ : "=a"(value) : "Nd"(port)); \ return value; \ } \ \ static inline void out##bwl##_p(unsigned type value, int port) \ { \ out##bwl(value, port); \ slow_down_io(); \ } \ \ static inline unsigned type in##bwl##_p(int port) \ { \ unsigned type value = in##bwl(port); \ slow_down_io(); \ return value; \ } \ \ static inline void outs##bwl(int port, const void *addr, unsigned long count) \ { \ if (sev_key_active()) { \ unsigned type *value = (unsigned type *)addr; \ while (count) { \ out##bwl(*value, port); \ value++; \ count--; \ } \ } else { \ asm volatile("rep; outs" #bwl \ : "+S"(addr), "+c"(count) \ : "d"(port) : "memory"); \ } \ } \ \ static inline void ins##bwl(int port, void *addr, unsigned long count) \ { \ if (sev_key_active()) { \ unsigned type *value = (unsigned type *)addr; \ while (count) { \ *value = in##bwl(port); \ value++; \ count--; \ } \ } else { \ asm volatile("rep; ins" #bwl \ : "+D"(addr), "+c"(count) \ : "d"(port) : "memory"); \ } \ } BUILDIO(b, b, char) BUILDIO(w, w, short) BUILDIO(l, , int) #define inb inb #define inw inw #define inl inl #define inb_p inb_p #define inw_p inw_p #define inl_p inl_p #define insb insb #define insw insw #define insl insl #define outb outb #define outw outw #define outl outl #define outb_p outb_p #define outw_p outw_p #define outl_p outl_p #define outsb outsb #define outsw outsw #define outsl outsl extern void *xlate_dev_mem_ptr(phys_addr_t phys); extern void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr); #define xlate_dev_mem_ptr xlate_dev_mem_ptr #define unxlate_dev_mem_ptr unxlate_dev_mem_ptr extern int ioremap_change_attr(unsigned long vaddr, unsigned long size, enum page_cache_mode pcm); extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size); #define ioremap_wc ioremap_wc extern void __iomem *ioremap_wt(resource_size_t offset, unsigned long size); #define ioremap_wt ioremap_wt extern bool is_early_ioremap_ptep(pte_t *ptep); #define IO_SPACE_LIMIT 0xffff #include <asm-generic/io.h> #undef PCI_IOBASE #ifdef CONFIG_MTRR extern int __must_check arch_phys_wc_index(int handle); #define arch_phys_wc_index arch_phys_wc_index extern int __must_check arch_phys_wc_add(unsigned long base, unsigned long size); extern void arch_phys_wc_del(int handle); #define arch_phys_wc_add arch_phys_wc_add #endif #ifdef CONFIG_X86_PAT extern int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size); extern void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size); #define arch_io_reserve_memtype_wc arch_io_reserve_memtype_wc #endif extern bool arch_memremap_can_ram_remap(resource_size_t offset, unsigned long size, unsigned long flags); #define arch_memremap_can_ram_remap arch_memremap_can_ram_remap extern bool phys_mem_access_encrypted(unsigned long phys_addr, unsigned long size); /** * iosubmit_cmds512 - copy data to single MMIO location, in 512-bit units * @dst: destination, in MMIO space (must be 512-bit aligned) * @src: source * @count: number of 512 bits quantities to submit * * Submit data from kernel space to MMIO space, in units of 512 bits at a * time. Order of access is not guaranteed, nor is a memory barrier * performed afterwards. * * Warning: Do not use this helper unless your driver has checked that the CPU * instruction is supported on the platform. */ static inline void iosubmit_cmds512(void __iomem *dst, const void *src, size_t count) { const u8 *from = src; const u8 *end = from + count * 64; while (from < end) { movdir64b(dst, from); from += 64; } } #endif /* _ASM_X86_IO_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UACCESS_64_H #define _ASM_X86_UACCESS_64_H /* * User space memory access functions */ #include <linux/compiler.h> #include <linux/lockdep.h> #include <linux/kasan-checks.h> #include <asm/alternative.h> #include <asm/cpufeatures.h> #include <asm/page.h> /* * Copy To/From Userspace */ /* Handles exceptions in both to and from, but doesn't do access_ok */ __must_check unsigned long copy_user_enhanced_fast_string(void *to, const void *from, unsigned len); __must_check unsigned long copy_user_generic_string(void *to, const void *from, unsigned len); __must_check unsigned long copy_user_generic_unrolled(void *to, const void *from, unsigned len); static __always_inline __must_check unsigned long copy_user_generic(void *to, const void *from, unsigned len) { unsigned ret; /* * If CPU has ERMS feature, use copy_user_enhanced_fast_string. * Otherwise, if CPU has rep_good feature, use copy_user_generic_string. * Otherwise, use copy_user_generic_unrolled. */ alternative_call_2(copy_user_generic_unrolled, copy_user_generic_string, X86_FEATURE_REP_GOOD, copy_user_enhanced_fast_string, X86_FEATURE_ERMS, ASM_OUTPUT2("=a" (ret), "=D" (to), "=S" (from), "=d" (len)), "1" (to), "2" (from), "3" (len) : "memory", "rcx", "r8", "r9", "r10", "r11"); return ret; } static __always_inline __must_check unsigned long raw_copy_from_user(void *dst, const void __user *src, unsigned long size) { return copy_user_generic(dst, (__force void *)src, size); } static __always_inline __must_check unsigned long raw_copy_to_user(void __user *dst, const void *src, unsigned long size) { return copy_user_generic((__force void *)dst, src, size); } static __always_inline __must_check unsigned long raw_copy_in_user(void __user *dst, const void __user *src, unsigned long size) { return copy_user_generic((__force void *)dst, (__force void *)src, size); } extern long __copy_user_nocache(void *dst, const void __user *src, unsigned size, int zerorest); extern long __copy_user_flushcache(void *dst, const void __user *src, unsigned size); extern void memcpy_page_flushcache(char *to, struct page *page, size_t offset, size_t len); static inline int __copy_from_user_inatomic_nocache(void *dst, const void __user *src, unsigned size) { kasan_check_write(dst, size); return __copy_user_nocache(dst, src, size, 0); } static inline int __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size) { kasan_check_write(dst, size); return __copy_user_flushcache(dst, src, size); } #endif /* _ASM_X86_UACCESS_64_H */
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 /* SPDX-License-Identifier: GPL-2.0+ */ #ifndef _LINUX_XARRAY_H #define _LINUX_XARRAY_H /* * eXtensible Arrays * Copyright (c) 2017 Microsoft Corporation * Author: Matthew Wilcox <willy@infradead.org> * * See Documentation/core-api/xarray.rst for how to use the XArray. */ #include <linux/bug.h> #include <linux/compiler.h> #include <linux/gfp.h> #include <linux/kconfig.h> #include <linux/kernel.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/types.h> /* * The bottom two bits of the entry determine how the XArray interprets * the contents: * * 00: Pointer entry * 10: Internal entry * x1: Value entry or tagged pointer * * Attempting to store internal entries in the XArray is a bug. * * Most internal entries are pointers to the next node in the tree. * The following internal entries have a special meaning: * * 0-62: Sibling entries * 256: Retry entry * 257: Zero entry * * Errors are also represented as internal entries, but use the negative * space (-4094 to -2). They're never stored in the slots array; only * returned by the normal API. */ #define BITS_PER_XA_VALUE (BITS_PER_LONG - 1) /** * xa_mk_value() - Create an XArray entry from an integer. * @v: Value to store in XArray. * * Context: Any context. * Return: An entry suitable for storing in the XArray. */ static inline void *xa_mk_value(unsigned long v) { WARN_ON((long)v < 0); return (void *)((v << 1) | 1); } /** * xa_to_value() - Get value stored in an XArray entry. * @entry: XArray entry. * * Context: Any context. * Return: The value stored in the XArray entry. */ static inline unsigned long xa_to_value(const void *entry) { return (unsigned long)entry >> 1; } /** * xa_is_value() - Determine if an entry is a value. * @entry: XArray entry. * * Context: Any context. * Return: True if the entry is a value, false if it is a pointer. */ static inline bool xa_is_value(const void *entry) { return (unsigned long)entry & 1; } /** * xa_tag_pointer() - Create an XArray entry for a tagged pointer. * @p: Plain pointer. * @tag: Tag value (0, 1 or 3). * * If the user of the XArray prefers, they can tag their pointers instead * of storing value entries. Three tags are available (0, 1 and 3). * These are distinct from the xa_mark_t as they are not replicated up * through the array and cannot be searched for. * * Context: Any context. * Return: An XArray entry. */ static inline void *xa_tag_pointer(void *p, unsigned long tag) { return (void *)((unsigned long)p | tag); } /** * xa_untag_pointer() - Turn an XArray entry into a plain pointer. * @entry: XArray entry. * * If you have stored a tagged pointer in the XArray, call this function * to get the untagged version of the pointer. * * Context: Any context. * Return: A pointer. */ static inline void *xa_untag_pointer(void *entry) { return (void *)((unsigned long)entry & ~3UL); } /** * xa_pointer_tag() - Get the tag stored in an XArray entry. * @entry: XArray entry. * * If you have stored a tagged pointer in the XArray, call this function * to get the tag of that pointer. * * Context: Any context. * Return: A tag. */ static inline unsigned int xa_pointer_tag(void *entry) { return (unsigned long)entry & 3UL; } /* * xa_mk_internal() - Create an internal entry. * @v: Value to turn into an internal entry. * * Internal entries are used for a number of purposes. Entries 0-255 are * used for sibling entries (only 0-62 are used by the current code). 256 * is used for the retry entry. 257 is used for the reserved / zero entry. * Negative internal entries are used to represent errnos. Node pointers * are also tagged as internal entries in some situations. * * Context: Any context. * Return: An XArray internal entry corresponding to this value. */ static inline void *xa_mk_internal(unsigned long v) { return (void *)((v << 2) | 2); } /* * xa_to_internal() - Extract the value from an internal entry. * @entry: XArray entry. * * Context: Any context. * Return: The value which was stored in the internal entry. */ static inline unsigned long xa_to_internal(const void *entry) { return (unsigned long)entry >> 2; } /* * xa_is_internal() - Is the entry an internal entry? * @entry: XArray entry. * * Context: Any context. * Return: %true if the entry is an internal entry. */ static inline bool xa_is_internal(const void *entry) { return ((unsigned long)entry & 3) == 2; } #define XA_ZERO_ENTRY xa_mk_internal(257) /** * xa_is_zero() - Is the entry a zero entry? * @entry: Entry retrieved from the XArray * * The normal API will return NULL as the contents of a slot containing * a zero entry. You can only see zero entries by using the advanced API. * * Return: %true if the entry is a zero entry. */ static inline bool xa_is_zero(const void *entry) { return unlikely(entry == XA_ZERO_ENTRY); } /** * xa_is_err() - Report whether an XArray operation returned an error * @entry: Result from calling an XArray function * * If an XArray operation cannot complete an operation, it will return * a special value indicating an error. This function tells you * whether an error occurred; xa_err() tells you which error occurred. * * Context: Any context. * Return: %true if the entry indicates an error. */ static inline bool xa_is_err(const void *entry) { return unlikely(xa_is_internal(entry) && entry >= xa_mk_internal(-MAX_ERRNO)); } /** * xa_err() - Turn an XArray result into an errno. * @entry: Result from calling an XArray function. * * If an XArray operation cannot complete an operation, it will return * a special pointer value which encodes an errno. This function extracts * the errno from the pointer value, or returns 0 if the pointer does not * represent an errno. * * Context: Any context. * Return: A negative errno or 0. */ static inline int xa_err(void *entry) { /* xa_to_internal() would not do sign extension. */ if (xa_is_err(entry)) return (long)entry >> 2; return 0; } /** * struct xa_limit - Represents a range of IDs. * @min: The lowest ID to allocate (inclusive). * @max: The maximum ID to allocate (inclusive). * * This structure is used either directly or via the XA_LIMIT() macro * to communicate the range of IDs that are valid for allocation. * Two common ranges are predefined for you: * * xa_limit_32b - [0 - UINT_MAX] * * xa_limit_31b - [0 - INT_MAX] */ struct xa_limit { u32 max; u32 min; }; #define XA_LIMIT(_min, _max) (struct xa_limit) { .min = _min, .max = _max } #define xa_limit_32b XA_LIMIT(0, UINT_MAX) #define xa_limit_31b XA_LIMIT(0, INT_MAX) typedef unsigned __bitwise xa_mark_t; #define XA_MARK_0 ((__force xa_mark_t)0U) #define XA_MARK_1 ((__force xa_mark_t)1U) #define XA_MARK_2 ((__force xa_mark_t)2U) #define XA_PRESENT ((__force xa_mark_t)8U) #define XA_MARK_MAX XA_MARK_2 #define XA_FREE_MARK XA_MARK_0 enum xa_lock_type { XA_LOCK_IRQ = 1, XA_LOCK_BH = 2, }; /* * Values for xa_flags. The radix tree stores its GFP flags in the xa_flags, * and we remain compatible with that. */ #define XA_FLAGS_LOCK_IRQ ((__force gfp_t)XA_LOCK_IRQ) #define XA_FLAGS_LOCK_BH ((__force gfp_t)XA_LOCK_BH) #define XA_FLAGS_TRACK_FREE ((__force gfp_t)4U) #define XA_FLAGS_ZERO_BUSY ((__force gfp_t)8U) #define XA_FLAGS_ALLOC_WRAPPED ((__force gfp_t)16U) #define XA_FLAGS_ACCOUNT ((__force gfp_t)32U) #define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ (__force unsigned)(mark))) /* ALLOC is for a normal 0-based alloc. ALLOC1 is for an 1-based alloc */ #define XA_FLAGS_ALLOC (XA_FLAGS_TRACK_FREE | XA_FLAGS_MARK(XA_FREE_MARK)) #define XA_FLAGS_ALLOC1 (XA_FLAGS_TRACK_FREE | XA_FLAGS_ZERO_BUSY) /** * struct xarray - The anchor of the XArray. * @xa_lock: Lock that protects the contents of the XArray. * * To use the xarray, define it statically or embed it in your data structure. * It is a very small data structure, so it does not usually make sense to * allocate it separately and keep a pointer to it in your data structure. * * You may use the xa_lock to protect your own data structures as well. */ /* * If all of the entries in the array are NULL, @xa_head is a NULL pointer. * If the only non-NULL entry in the array is at index 0, @xa_head is that * entry. If any other entry in the array is non-NULL, @xa_head points * to an @xa_node. */ struct xarray { spinlock_t xa_lock; /* private: The rest of the data structure is not to be used directly. */ gfp_t xa_flags; void __rcu * xa_head; }; #define XARRAY_INIT(name, flags) { \ .xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock), \ .xa_flags = flags, \ .xa_head = NULL, \ } /** * DEFINE_XARRAY_FLAGS() - Define an XArray with custom flags. * @name: A string that names your XArray. * @flags: XA_FLAG values. * * This is intended for file scope definitions of XArrays. It declares * and initialises an empty XArray with the chosen name and flags. It is * equivalent to calling xa_init_flags() on the array, but it does the * initialisation at compiletime instead of runtime. */ #define DEFINE_XARRAY_FLAGS(name, flags) \ struct xarray name = XARRAY_INIT(name, flags) /** * DEFINE_XARRAY() - Define an XArray. * @name: A string that names your XArray. * * This is intended for file scope definitions of XArrays. It declares * and initialises an empty XArray with the chosen name. It is equivalent * to calling xa_init() on the array, but it does the initialisation at * compiletime instead of runtime. */ #define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0) /** * DEFINE_XARRAY_ALLOC() - Define an XArray which allocates IDs starting at 0. * @name: A string that names your XArray. * * This is intended for file scope definitions of allocating XArrays. * See also DEFINE_XARRAY(). */ #define DEFINE_XARRAY_ALLOC(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC) /** * DEFINE_XARRAY_ALLOC1() - Define an XArray which allocates IDs starting at 1. * @name: A string that names your XArray. * * This is intended for file scope definitions of allocating XArrays. * See also DEFINE_XARRAY(). */ #define DEFINE_XARRAY_ALLOC1(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC1) void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_erase(struct xarray *, unsigned long index); void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); void *xa_find(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); void *xa_find_after(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); unsigned int xa_extract(struct xarray *, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t); void xa_destroy(struct xarray *); /** * xa_init_flags() - Initialise an empty XArray with flags. * @xa: XArray. * @flags: XA_FLAG values. * * If you need to initialise an XArray with special flags (eg you need * to take the lock from interrupt context), use this function instead * of xa_init(). * * Context: Any context. */ static inline void xa_init_flags(struct xarray *xa, gfp_t flags) { spin_lock_init(&xa->xa_lock); xa->xa_flags = flags; xa->xa_head = NULL; } /** * xa_init() - Initialise an empty XArray. * @xa: XArray. * * An empty XArray is full of NULL entries. * * Context: Any context. */ static inline void xa_init(struct xarray *xa) { xa_init_flags(xa, 0); } /** * xa_empty() - Determine if an array has any present entries. * @xa: XArray. * * Context: Any context. * Return: %true if the array contains only NULL pointers. */ static inline bool xa_empty(const struct xarray *xa) { return xa->xa_head == NULL; } /** * xa_marked() - Inquire whether any entry in this array has a mark set * @xa: Array * @mark: Mark value * * Context: Any context. * Return: %true if any entry has this mark set. */ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) { return xa->xa_flags & XA_FLAGS_MARK(mark); } /** * xa_for_each_range() - Iterate over a portion of an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @start: First index to retrieve from array. * @last: Last index to retrieve from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you * want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set * to NULL and @index will have a value less than or equal to max. * * xa_for_each_range() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). * xa_for_each_range() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each() iterator instead. * The xas_for_each() iterator will expand into more inline code than * xa_for_each_range(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_range(xa, index, entry, start, last) \ for (index = start, \ entry = xa_find(xa, &index, last, XA_PRESENT); \ entry; \ entry = xa_find_after(xa, &index, last, XA_PRESENT)) /** * xa_for_each_start() - Iterate over a portion of an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @start: First index to retrieve from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you * want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set * to NULL and @index will have a value less than or equal to max. * * xa_for_each_start() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). * xa_for_each_start() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each() iterator instead. * The xas_for_each() iterator will expand into more inline code than * xa_for_each_start(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_start(xa, index, entry, start) \ xa_for_each_range(xa, index, entry, start, ULONG_MAX) /** * xa_for_each() - Iterate over present entries in an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you want * to skip or reprocess indices. It is safe to modify the array during the * iteration. At the end of the iteration, @entry will be set to NULL and * @index will have a value less than or equal to max. * * xa_for_each() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). xa_for_each() * will spin if it hits a retry entry; if you intend to see retry entries, * you should use the xas_for_each() iterator instead. The xas_for_each() * iterator will expand into more inline code than xa_for_each(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each(xa, index, entry) \ xa_for_each_start(xa, index, entry, 0) /** * xa_for_each_marked() - Iterate over marked entries in an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @filter: Selection criterion. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. The iteration will skip all entries in the array * which do not match @filter. You may modify @index during the iteration * if you want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set to * NULL and @index will have a value less than or equal to max. * * xa_for_each_marked() is O(n.log(n)) while xas_for_each_marked() is O(n). * You have to handle your own locking with xas_for_each(), and if you have * to unlock after each iteration, it will also end up being O(n.log(n)). * xa_for_each_marked() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each_marked() iterator * instead. The xas_for_each_marked() iterator will expand into more inline * code than xa_for_each_marked(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_marked(xa, index, entry, filter) \ for (index = 0, entry = xa_find(xa, &index, ULONG_MAX, filter); \ entry; entry = xa_find_after(xa, &index, ULONG_MAX, filter)) #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) #define xa_lock_bh(xa) spin_lock_bh(&(xa)->xa_lock) #define xa_unlock_bh(xa) spin_unlock_bh(&(xa)->xa_lock) #define xa_lock_irq(xa) spin_lock_irq(&(xa)->xa_lock) #define xa_unlock_irq(xa) spin_unlock_irq(&(xa)->xa_lock) #define xa_lock_irqsave(xa, flags) \ spin_lock_irqsave(&(xa)->xa_lock, flags) #define xa_unlock_irqrestore(xa, flags) \ spin_unlock_irqrestore(&(xa)->xa_lock, flags) #define xa_lock_nested(xa, subclass) \ spin_lock_nested(&(xa)->xa_lock, subclass) #define xa_lock_bh_nested(xa, subclass) \ spin_lock_bh_nested(&(xa)->xa_lock, subclass) #define xa_lock_irq_nested(xa, subclass) \ spin_lock_irq_nested(&(xa)->xa_lock, subclass) #define xa_lock_irqsave_nested(xa, flags, subclass) \ spin_lock_irqsave_nested(&(xa)->xa_lock, flags, subclass) /* * Versions of the normal API which require the caller to hold the * xa_lock. If the GFP flags allow it, they will drop the lock to * allocate memory, then reacquire it afterwards. These functions * may also re-enable interrupts if the XArray flags indicate the * locking should be interrupt safe. */ void *__xa_erase(struct xarray *, unsigned long index); void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); int __must_check __xa_insert(struct xarray *, unsigned long index, void *entry, gfp_t); int __must_check __xa_alloc(struct xarray *, u32 *id, void *entry, struct xa_limit, gfp_t); int __must_check __xa_alloc_cyclic(struct xarray *, u32 *id, void *entry, struct xa_limit, u32 *next, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); /** * xa_store_bh() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * This function is like calling xa_store() except it disables softirqs * while holding the array lock. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_bh(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; xa_lock_bh(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock_bh(xa); return curr; } /** * xa_store_irq() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * This function is like calling xa_store() except it disables interrupts * while holding the array lock. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_irq(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; xa_lock_irq(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock_irq(xa); return curr; } /** * xa_erase_bh() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The entry which used to be at this index. */ static inline void *xa_erase_bh(struct xarray *xa, unsigned long index) { void *entry; xa_lock_bh(xa); entry = __xa_erase(xa, index); xa_unlock_bh(xa); return entry; } /** * xa_erase_irq() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: The entry which used to be at this index. */ static inline void *xa_erase_irq(struct xarray *xa, unsigned long index) { void *entry; xa_lock_irq(xa); entry = __xa_erase(xa, index); xa_unlock_irq(xa); return entry; } /** * xa_cmpxchg() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * If the entry at @index is the same as @old, replace it with @entry. * If the return value is equal to @old, then the exchange was successful. * * Context: Any context. Takes and releases the xa_lock. May sleep * if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; xa_lock(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock(xa); return curr; } /** * xa_cmpxchg_bh() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * This function is like calling xa_cmpxchg() except it disables softirqs * while holding the array lock. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg_bh(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; xa_lock_bh(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock_bh(xa); return curr; } /** * xa_cmpxchg_irq() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * This function is like calling xa_cmpxchg() except it disables interrupts * while holding the array lock. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; xa_lock_irq(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock_irq(xa); return curr; } /** * xa_insert() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; xa_lock(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock(xa); return err; } /** * xa_insert_bh() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert_bh(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; xa_lock_bh(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock_bh(xa); return err; } /** * xa_insert_irq() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert_irq(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; xa_lock_irq(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock_irq(xa); return err; } /** * xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline __must_check int xa_alloc(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; xa_lock(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock(xa); return err; } /** * xa_alloc_bh() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline int __must_check xa_alloc_bh(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; xa_lock_bh(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_bh(xa); return err; } /** * xa_alloc_irq() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline int __must_check xa_alloc_irq(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; xa_lock_irq(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_irq(xa); return err; } /** * xa_alloc_cyclic() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; xa_lock(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock(xa); return err; } /** * xa_alloc_cyclic_bh() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic_bh(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; xa_lock_bh(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_bh(xa); return err; } /** * xa_alloc_cyclic_irq() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic_irq(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; xa_lock_irq(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_irq(xa); return err; } /** * xa_reserve() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * Ensures there is somewhere to store an entry at @index in the array. * If there is already something stored at @index, this function does * nothing. If there was nothing there, the entry is marked as reserved. * Loading from a reserved entry returns a %NULL pointer. * * If you do not use the entry that you have reserved, call xa_release() * or xa_erase() to free any unnecessary memory. * * Context: Any context. Takes and releases the xa_lock. * May sleep if the @gfp flags permit. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_reserve_bh() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * A softirq-disabling version of xa_reserve(). * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve_bh(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg_bh(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_reserve_irq() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * An interrupt-disabling version of xa_reserve(). * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve_irq(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg_irq(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_release() - Release a reserved entry. * @xa: XArray. * @index: Index of entry. * * After calling xa_reserve(), you can call this function to release the * reservation. If the entry at @index has been stored to, this function * will do nothing. */ static inline void xa_release(struct xarray *xa, unsigned long index) { xa_cmpxchg(xa, index, XA_ZERO_ENTRY, NULL, 0); } /* Everything below here is the Advanced API. Proceed with caution. */ /* * The xarray is constructed out of a set of 'chunks' of pointers. Choosing * the best chunk size requires some tradeoffs. A power of two recommends * itself so that we can walk the tree based purely on shifts and masks. * Generally, the larger the better; as the number of slots per level of the * tree increases, the less tall the tree needs to be. But that needs to be * balanced against the memory consumption of each node. On a 64-bit system, * xa_node is currently 576 bytes, and we get 7 of them per 4kB page. If we * doubled the number of slots per node, we'd get only 3 nodes per 4kB page. */ #ifndef XA_CHUNK_SHIFT #define XA_CHUNK_SHIFT (CONFIG_BASE_SMALL ? 4 : 6) #endif #define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT) #define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1) #define XA_MAX_MARKS 3 #define XA_MARK_LONGS DIV_ROUND_UP(XA_CHUNK_SIZE, BITS_PER_LONG) /* * @count is the count of every non-NULL element in the ->slots array * whether that is a value entry, a retry entry, a user pointer, * a sibling entry or a pointer to the next level of the tree. * @nr_values is the count of every element in ->slots which is * either a value entry or a sibling of a value entry. */ struct xa_node { unsigned char shift; /* Bits remaining in each slot */ unsigned char offset; /* Slot offset in parent */ unsigned char count; /* Total entry count */ unsigned char nr_values; /* Value entry count */ struct xa_node __rcu *parent; /* NULL at top of tree */ struct xarray *array; /* The array we belong to */ union { struct list_head private_list; /* For tree user */ struct rcu_head rcu_head; /* Used when freeing node */ }; void __rcu *slots[XA_CHUNK_SIZE]; union { unsigned long tags[XA_MAX_MARKS][XA_MARK_LONGS]; unsigned long marks[XA_MAX_MARKS][XA_MARK_LONGS]; }; }; void xa_dump(const struct xarray *); void xa_dump_node(const struct xa_node *); #ifdef XA_DEBUG #define XA_BUG_ON(xa, x) do { \ if (x) { \ xa_dump(xa); \ BUG(); \ } \ } while (0) #define XA_NODE_BUG_ON(node, x) do { \ if (x) { \ if (node) xa_dump_node(node); \ BUG(); \ } \ } while (0) #else #define XA_BUG_ON(xa, x) do { } while (0) #define XA_NODE_BUG_ON(node, x) do { } while (0) #endif /* Private */ static inline void *xa_head(const struct xarray *xa) { return rcu_dereference_check(xa->xa_head, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_head_locked(const struct xarray *xa) { return rcu_dereference_protected(xa->xa_head, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_entry(const struct xarray *xa, const struct xa_node *node, unsigned int offset) { XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); return rcu_dereference_check(node->slots[offset], lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_entry_locked(const struct xarray *xa, const struct xa_node *node, unsigned int offset) { XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); return rcu_dereference_protected(node->slots[offset], lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline struct xa_node *xa_parent(const struct xarray *xa, const struct xa_node *node) { return rcu_dereference_check(node->parent, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline struct xa_node *xa_parent_locked(const struct xarray *xa, const struct xa_node *node) { return rcu_dereference_protected(node->parent, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_mk_node(const struct xa_node *node) { return (void *)((unsigned long)node | 2); } /* Private */ static inline struct xa_node *xa_to_node(const void *entry) { return (struct xa_node *)((unsigned long)entry - 2); } /* Private */ static inline bool xa_is_node(const void *entry) { return xa_is_internal(entry) && (unsigned long)entry > 4096; } /* Private */ static inline void *xa_mk_sibling(unsigned int offset) { return xa_mk_internal(offset); } /* Private */ static inline unsigned long xa_to_sibling(const void *entry) { return xa_to_internal(entry); } /** * xa_is_sibling() - Is the entry a sibling entry? * @entry: Entry retrieved from the XArray * * Return: %true if the entry is a sibling entry. */ static inline bool xa_is_sibling(const void *entry) { return IS_ENABLED(CONFIG_XARRAY_MULTI) && xa_is_internal(entry) && (entry < xa_mk_sibling(XA_CHUNK_SIZE - 1)); } #define XA_RETRY_ENTRY xa_mk_internal(256) /** * xa_is_retry() - Is the entry a retry entry? * @entry: Entry retrieved from the XArray * * Return: %true if the entry is a retry entry. */ static inline bool xa_is_retry(const void *entry) { return unlikely(entry == XA_RETRY_ENTRY); } /** * xa_is_advanced() - Is the entry only permitted for the advanced API? * @entry: Entry to be stored in the XArray. * * Return: %true if the entry cannot be stored by the normal API. */ static inline bool xa_is_advanced(const void *entry) { return xa_is_internal(entry) && (entry <= XA_RETRY_ENTRY); } /** * typedef xa_update_node_t - A callback function from the XArray. * @node: The node which is being processed * * This function is called every time the XArray updates the count of * present and value entries in a node. It allows advanced users to * maintain the private_list in the node. * * Context: The xa_lock is held and interrupts may be disabled. * Implementations should not drop the xa_lock, nor re-enable * interrupts. */ typedef void (*xa_update_node_t)(struct xa_node *node); void xa_delete_node(struct xa_node *, xa_update_node_t); /* * The xa_state is opaque to its users. It contains various different pieces * of state involved in the current operation on the XArray. It should be * declared on the stack and passed between the various internal routines. * The various elements in it should not be accessed directly, but only * through the provided accessor functions. The below documentation is for * the benefit of those working on the code, not for users of the XArray. * * @xa_node usually points to the xa_node containing the slot we're operating * on (and @xa_offset is the offset in the slots array). If there is a * single entry in the array at index 0, there are no allocated xa_nodes to * point to, and so we store %NULL in @xa_node. @xa_node is set to * the value %XAS_RESTART if the xa_state is not walked to the correct * position in the tree of nodes for this operation. If an error occurs * during an operation, it is set to an %XAS_ERROR value. If we run off the * end of the allocated nodes, it is set to %XAS_BOUNDS. */ struct xa_state { struct xarray *xa; unsigned long xa_index; unsigned char xa_shift; unsigned char xa_sibs; unsigned char xa_offset; unsigned char xa_pad; /* Helps gcc generate better code */ struct xa_node *xa_node; struct xa_node *xa_alloc; xa_update_node_t xa_update; }; /* * We encode errnos in the xas->xa_node. If an error has happened, we need to * drop the lock to fix it, and once we've done so the xa_state is invalid. */ #define XA_ERROR(errno) ((struct xa_node *)(((unsigned long)errno << 2) | 2UL)) #define XAS_BOUNDS ((struct xa_node *)1UL) #define XAS_RESTART ((struct xa_node *)3UL) #define __XA_STATE(array, index, shift, sibs) { \ .xa = array, \ .xa_index = index, \ .xa_shift = shift, \ .xa_sibs = sibs, \ .xa_offset = 0, \ .xa_pad = 0, \ .xa_node = XAS_RESTART, \ .xa_alloc = NULL, \ .xa_update = NULL \ } /** * XA_STATE() - Declare an XArray operation state. * @name: Name of this operation state (usually xas). * @array: Array to operate on. * @index: Initial index of interest. * * Declare and initialise an xa_state on the stack. */ #define XA_STATE(name, array, index) \ struct xa_state name = __XA_STATE(array, index, 0, 0) /** * XA_STATE_ORDER() - Declare an XArray operation state. * @name: Name of this operation state (usually xas). * @array: Array to operate on. * @index: Initial index of interest. * @order: Order of entry. * * Declare and initialise an xa_state on the stack. This variant of * XA_STATE() allows you to specify the 'order' of the element you * want to operate on.` */ #define XA_STATE_ORDER(name, array, index, order) \ struct xa_state name = __XA_STATE(array, \ (index >> order) << order, \ order - (order % XA_CHUNK_SHIFT), \ (1U << (order % XA_CHUNK_SHIFT)) - 1) #define xas_marked(xas, mark) xa_marked((xas)->xa, (mark)) #define xas_trylock(xas) xa_trylock((xas)->xa) #define xas_lock(xas) xa_lock((xas)->xa) #define xas_unlock(xas) xa_unlock((xas)->xa) #define xas_lock_bh(xas) xa_lock_bh((xas)->xa) #define xas_unlock_bh(xas) xa_unlock_bh((xas)->xa) #define xas_lock_irq(xas) xa_lock_irq((xas)->xa) #define xas_unlock_irq(xas) xa_unlock_irq((xas)->xa) #define xas_lock_irqsave(xas, flags) \ xa_lock_irqsave((xas)->xa, flags) #define xas_unlock_irqrestore(xas, flags) \ xa_unlock_irqrestore((xas)->xa, flags) /** * xas_error() - Return an errno stored in the xa_state. * @xas: XArray operation state. * * Return: 0 if no error has been noted. A negative errno if one has. */ static inline int xas_error(const struct xa_state *xas) { return xa_err(xas->xa_node); } /** * xas_set_err() - Note an error in the xa_state. * @xas: XArray operation state. * @err: Negative error number. * * Only call this function with a negative @err; zero or positive errors * will probably not behave the way you think they should. If you want * to clear the error from an xa_state, use xas_reset(). */ static inline void xas_set_err(struct xa_state *xas, long err) { xas->xa_node = XA_ERROR(err); } /** * xas_invalid() - Is the xas in a retry or error state? * @xas: XArray operation state. * * Return: %true if the xas cannot be used for operations. */ static inline bool xas_invalid(const struct xa_state *xas) { return (unsigned long)xas->xa_node & 3; } /** * xas_valid() - Is the xas a valid cursor into the array? * @xas: XArray operation state. * * Return: %true if the xas can be used for operations. */ static inline bool xas_valid(const struct xa_state *xas) { return !xas_invalid(xas); } /** * xas_is_node() - Does the xas point to a node? * @xas: XArray operation state. * * Return: %true if the xas currently references a node. */ static inline bool xas_is_node(const struct xa_state *xas) { return xas_valid(xas) && xas->xa_node; } /* True if the pointer is something other than a node */ static inline bool xas_not_node(struct xa_node *node) { return ((unsigned long)node & 3) || !node; } /* True if the node represents RESTART or an error */ static inline bool xas_frozen(struct xa_node *node) { return (unsigned long)node & 2; } /* True if the node represents head-of-tree, RESTART or BOUNDS */ static inline bool xas_top(struct xa_node *node) { return node <= XAS_RESTART; } /** * xas_reset() - Reset an XArray operation state. * @xas: XArray operation state. * * Resets the error or walk state of the @xas so future walks of the * array will start from the root. Use this if you have dropped the * xarray lock and want to reuse the xa_state. * * Context: Any context. */ static inline void xas_reset(struct xa_state *xas) { xas->xa_node = XAS_RESTART; } /** * xas_retry() - Retry the operation if appropriate. * @xas: XArray operation state. * @entry: Entry from xarray. * * The advanced functions may sometimes return an internal entry, such as * a retry entry or a zero entry. This function sets up the @xas to restart * the walk from the head of the array if needed. * * Context: Any context. * Return: true if the operation needs to be retried. */ static inline bool xas_retry(struct xa_state *xas, const void *entry) { if (xa_is_zero(entry)) return true; if (!xa_is_retry(entry)) return false; xas_reset(xas); return true; } void *xas_load(struct xa_state *); void *xas_store(struct xa_state *, void *entry); void *xas_find(struct xa_state *, unsigned long max); void *xas_find_conflict(struct xa_state *); bool xas_get_mark(const struct xa_state *, xa_mark_t); void xas_set_mark(const struct xa_state *, xa_mark_t); void xas_clear_mark(const struct xa_state *, xa_mark_t); void *xas_find_marked(struct xa_state *, unsigned long max, xa_mark_t); void xas_init_marks(const struct xa_state *); bool xas_nomem(struct xa_state *, gfp_t); void xas_pause(struct xa_state *); void xas_create_range(struct xa_state *); #ifdef CONFIG_XARRAY_MULTI int xa_get_order(struct xarray *, unsigned long index); void xas_split(struct xa_state *, void *entry, unsigned int order); void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t); #else static inline int xa_get_order(struct xarray *xa, unsigned long index) { return 0; } static inline void xas_split(struct xa_state *xas, void *entry, unsigned int order) { xas_store(xas, entry); } static inline void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, gfp_t gfp) { } #endif /** * xas_reload() - Refetch an entry from the xarray. * @xas: XArray operation state. * * Use this function to check that a previously loaded entry still has * the same value. This is useful for the lockless pagecache lookup where * we walk the array with only the RCU lock to protect us, lock the page, * then check that the page hasn't moved since we looked it up. * * The caller guarantees that @xas is still valid. If it may be in an * error or restart state, call xas_load() instead. * * Return: The entry at this location in the xarray. */ static inline void *xas_reload(struct xa_state *xas) { struct xa_node *node = xas->xa_node; void *entry; char offset; if (!node) return xa_head(xas->xa); if (IS_ENABLED(CONFIG_XARRAY_MULTI)) { offset = (xas->xa_index >> node->shift) & XA_CHUNK_MASK; entry = xa_entry(xas->xa, node, offset); if (!xa_is_sibling(entry)) return entry; offset = xa_to_sibling(entry); } else { offset = xas->xa_offset; } return xa_entry(xas->xa, node, offset); } /** * xas_set() - Set up XArray operation state for a different index. * @xas: XArray operation state. * @index: New index into the XArray. * * Move the operation state to refer to a different index. This will * have the effect of starting a walk from the top; see xas_next() * to move to an adjacent index. */ static inline void xas_set(struct xa_state *xas, unsigned long index) { xas->xa_index = index; xas->xa_node = XAS_RESTART; } /** * xas_set_order() - Set up XArray operation state for a multislot entry. * @xas: XArray operation state. * @index: Target of the operation. * @order: Entry occupies 2^@order indices. */ static inline void xas_set_order(struct xa_state *xas, unsigned long index, unsigned int order) { #ifdef CONFIG_XARRAY_MULTI xas->xa_index = order < BITS_PER_LONG ? (index >> order) << order : 0; xas->xa_shift = order - (order % XA_CHUNK_SHIFT); xas->xa_sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; xas->xa_node = XAS_RESTART; #else BUG_ON(order > 0); xas_set(xas, index); #endif } /** * xas_set_update() - Set up XArray operation state for a callback. * @xas: XArray operation state. * @update: Function to call when updating a node. * * The XArray can notify a caller after it has updated an xa_node. * This is advanced functionality and is only needed by the page cache. */ static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update) { xas->xa_update = update; } /** * xas_next_entry() - Advance iterator to next present entry. * @xas: XArray operation state. * @max: Highest index to return. * * xas_next_entry() is an inline function to optimise xarray traversal for * speed. It is equivalent to calling xas_find(), and will call xas_find() * for all the hard cases. * * Return: The next present entry after the one currently referred to by @xas. */ static inline void *xas_next_entry(struct xa_state *xas, unsigned long max) { struct xa_node *node = xas->xa_node; void *entry; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK))) return xas_find(xas, max); do { if (unlikely(xas->xa_index >= max)) return xas_find(xas, max); if (unlikely(xas->xa_offset == XA_CHUNK_MASK)) return xas_find(xas, max); entry = xa_entry(xas->xa, node, xas->xa_offset + 1); if (unlikely(xa_is_internal(entry))) return xas_find(xas, max); xas->xa_offset++; xas->xa_index++; } while (!entry); return entry; } /* Private */ static inline unsigned int xas_find_chunk(struct xa_state *xas, bool advance, xa_mark_t mark) { unsigned long *addr = xas->xa_node->marks[(__force unsigned)mark]; unsigned int offset = xas->xa_offset; if (advance) offset++; if (XA_CHUNK_SIZE == BITS_PER_LONG) { if (offset < XA_CHUNK_SIZE) { unsigned long data = *addr & (~0UL << offset); if (data) return __ffs(data); } return XA_CHUNK_SIZE; } return find_next_bit(addr, XA_CHUNK_SIZE, offset); } /** * xas_next_marked() - Advance iterator to next marked entry. * @xas: XArray operation state. * @max: Highest index to return. * @mark: Mark to search for. * * xas_next_marked() is an inline function to optimise xarray traversal for * speed. It is equivalent to calling xas_find_marked(), and will call * xas_find_marked() for all the hard cases. * * Return: The next marked entry after the one currently referred to by @xas. */ static inline void *xas_next_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) { struct xa_node *node = xas->xa_node; void *entry; unsigned int offset; if (unlikely(xas_not_node(node) || node->shift)) return xas_find_marked(xas, max, mark); offset = xas_find_chunk(xas, true, mark); xas->xa_offset = offset; xas->xa_index = (xas->xa_index & ~XA_CHUNK_MASK) + offset; if (xas->xa_index > max) return NULL; if (offset == XA_CHUNK_SIZE) return xas_find_marked(xas, max, mark); entry = xa_entry(xas->xa, node, offset); if (!entry) return xas_find_marked(xas, max, mark); return entry; } /* * If iterating while holding a lock, drop the lock and reschedule * every %XA_CHECK_SCHED loops. */ enum { XA_CHECK_SCHED = 4096, }; /** * xas_for_each() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * @max: Maximum index to retrieve from array. * * The loop body will be executed for each entry present in the xarray * between the current xas position and @max. @entry will be set to * the entry retrieved from the xarray. It is safe to delete entries * from the array in the loop body. You should hold either the RCU lock * or the xa_lock while iterating. If you need to drop the lock, call * xas_pause() first. */ #define xas_for_each(xas, entry, max) \ for (entry = xas_find(xas, max); entry; \ entry = xas_next_entry(xas, max)) /** * xas_for_each_marked() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * @max: Maximum index to retrieve from array. * @mark: Mark to search for. * * The loop body will be executed for each marked entry in the xarray * between the current xas position and @max. @entry will be set to * the entry retrieved from the xarray. It is safe to delete entries * from the array in the loop body. You should hold either the RCU lock * or the xa_lock while iterating. If you need to drop the lock, call * xas_pause() first. */ #define xas_for_each_marked(xas, entry, max, mark) \ for (entry = xas_find_marked(xas, max, mark); entry; \ entry = xas_next_marked(xas, max, mark)) /** * xas_for_each_conflict() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * * The loop body will be executed for each entry in the XArray that * lies within the range specified by @xas. If the loop terminates * normally, @entry will be %NULL. The user may break out of the loop, * which will leave @entry set to the conflicting entry. The caller * may also call xa_set_err() to exit the loop while setting an error * to record the reason. */ #define xas_for_each_conflict(xas, entry) \ while ((entry = xas_find_conflict(xas))) void *__xas_next(struct xa_state *); void *__xas_prev(struct xa_state *); /** * xas_prev() - Move iterator to previous index. * @xas: XArray operation state. * * If the @xas was in an error state, it will remain in an error state * and this function will return %NULL. If the @xas has never been walked, * it will have the effect of calling xas_load(). Otherwise one will be * subtracted from the index and the state will be walked to the correct * location in the array for the next operation. * * If the iterator was referencing index 0, this function wraps * around to %ULONG_MAX. * * Return: The entry at the new index. This may be %NULL or an internal * entry. */ static inline void *xas_prev(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset == 0)) return __xas_prev(xas); xas->xa_index--; xas->xa_offset--; return xa_entry(xas->xa, node, xas->xa_offset); } /** * xas_next() - Move state to next index. * @xas: XArray operation state. * * If the @xas was in an error state, it will remain in an error state * and this function will return %NULL. If the @xas has never been walked, * it will have the effect of calling xas_load(). Otherwise one will be * added to the index and the state will be walked to the correct * location in the array for the next operation. * * If the iterator was referencing index %ULONG_MAX, this function wraps * around to 0. * * Return: The entry at the new index. This may be %NULL or an internal * entry. */ static inline void *xas_next(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset == XA_CHUNK_MASK)) return __xas_next(xas); xas->xa_index++; xas->xa_offset++; return xa_entry(xas->xa, node, xas->xa_offset); } #endif /* _LINUX_XARRAY_H */
1 1 1 1 1 1 1 1 1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/vmscan.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * * Swap reorganised 29.12.95, Stephen Tweedie. * kswapd added: 7.1.96 sct * Removed kswapd_ctl limits, and swap out as many pages as needed * to bring the system back to freepages.high: 2.4.97, Rik van Riel. * Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com). * Multiqueue VM started 5.8.00, Rik van Riel. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/module.h> #include <linux/gfp.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/highmem.h> #include <linux/vmpressure.h> #include <linux/vmstat.h> #include <linux/file.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> /* for try_to_release_page(), buffer_heads_over_limit */ #include <linux/mm_inline.h> #include <linux/backing-dev.h> #include <linux/rmap.h> #include <linux/topology.h> #include <linux/cpu.h> #include <linux/cpuset.h> #include <linux/compaction.h> #include <linux/notifier.h> #include <linux/rwsem.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/memcontrol.h> #include <linux/delayacct.h> #include <linux/sysctl.h> #include <linux/oom.h> #include <linux/pagevec.h> #include <linux/prefetch.h> #include <linux/printk.h> #include <linux/dax.h> #include <linux/psi.h> #include <asm/tlbflush.h> #include <asm/div64.h> #include <linux/swapops.h> #include <linux/balloon_compaction.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/vmscan.h> struct scan_control { /* How many pages shrink_list() should reclaim */ unsigned long nr_to_reclaim; /* * Nodemask of nodes allowed by the caller. If NULL, all nodes * are scanned. */ nodemask_t *nodemask; /* * The memory cgroup that hit its limit and as a result is the * primary target of this reclaim invocation. */ struct mem_cgroup *target_mem_cgroup; /* * Scan pressure balancing between anon and file LRUs */ unsigned long anon_cost; unsigned long file_cost; /* Can active pages be deactivated as part of reclaim? */ #define DEACTIVATE_ANON 1 #define DEACTIVATE_FILE 2 unsigned int may_deactivate:2; unsigned int force_deactivate:1; unsigned int skipped_deactivate:1; /* Writepage batching in laptop mode; RECLAIM_WRITE */ unsigned int may_writepage:1; /* Can mapped pages be reclaimed? */ unsigned int may_unmap:1; /* Can pages be swapped as part of reclaim? */ unsigned int may_swap:1; /* * Cgroup memory below memory.low is protected as long as we * don't threaten to OOM. If any cgroup is reclaimed at * reduced force or passed over entirely due to its memory.low * setting (memcg_low_skipped), and nothing is reclaimed as a * result, then go back for one more cycle that reclaims the protected * memory (memcg_low_reclaim) to avert OOM. */ unsigned int memcg_low_reclaim:1; unsigned int memcg_low_skipped:1; unsigned int hibernation_mode:1; /* One of the zones is ready for compaction */ unsigned int compaction_ready:1; /* There is easily reclaimable cold cache in the current node */ unsigned int cache_trim_mode:1; /* The file pages on the current node are dangerously low */ unsigned int file_is_tiny:1; /* Allocation order */ s8 order; /* Scan (total_size >> priority) pages at once */ s8 priority; /* The highest zone to isolate pages for reclaim from */ s8 reclaim_idx; /* This context's GFP mask */ gfp_t gfp_mask; /* Incremented by the number of inactive pages that were scanned */ unsigned long nr_scanned; /* Number of pages freed so far during a call to shrink_zones() */ unsigned long nr_reclaimed; struct { unsigned int dirty; unsigned int unqueued_dirty; unsigned int congested; unsigned int writeback; unsigned int immediate; unsigned int file_taken; unsigned int taken; } nr; /* for recording the reclaimed slab by now */ struct reclaim_state reclaim_state; }; #ifdef ARCH_HAS_PREFETCHW #define prefetchw_prev_lru_page(_page, _base, _field) \ do { \ if ((_page)->lru.prev != _base) { \ struct page *prev; \ \ prev = lru_to_page(&(_page->lru)); \ prefetchw(&prev->_field); \ } \ } while (0) #else #define prefetchw_prev_lru_page(_page, _base, _field) do { } while (0) #endif /* * From 0 .. 200. Higher means more swappy. */ int vm_swappiness = 60; static void set_task_reclaim_state(struct task_struct *task, struct reclaim_state *rs) { /* Check for an overwrite */ WARN_ON_ONCE(rs && task->reclaim_state); /* Check for the nulling of an already-nulled member */ WARN_ON_ONCE(!rs && !task->reclaim_state); task->reclaim_state = rs; } static LIST_HEAD(shrinker_list); static DECLARE_RWSEM(shrinker_rwsem); #ifdef CONFIG_MEMCG /* * We allow subsystems to populate their shrinker-related * LRU lists before register_shrinker_prepared() is called * for the shrinker, since we don't want to impose * restrictions on their internal registration order. * In this case shrink_slab_memcg() may find corresponding * bit is set in the shrinkers map. * * This value is used by the function to detect registering * shrinkers and to skip do_shrink_slab() calls for them. */ #define SHRINKER_REGISTERING ((struct shrinker *)~0UL) static DEFINE_IDR(shrinker_idr); static int shrinker_nr_max; static int prealloc_memcg_shrinker(struct shrinker *shrinker) { int id, ret = -ENOMEM; down_write(&shrinker_rwsem); /* This may call shrinker, so it must use down_read_trylock() */ id = idr_alloc(&shrinker_idr, SHRINKER_REGISTERING, 0, 0, GFP_KERNEL); if (id < 0) goto unlock; if (id >= shrinker_nr_max) { if (memcg_expand_shrinker_maps(id)) { idr_remove(&shrinker_idr, id); goto unlock; } shrinker_nr_max = id + 1; } shrinker->id = id; ret = 0; unlock: up_write(&shrinker_rwsem); return ret; } static void unregister_memcg_shrinker(struct shrinker *shrinker) { int id = shrinker->id; BUG_ON(id < 0); down_write(&shrinker_rwsem); idr_remove(&shrinker_idr, id); up_write(&shrinker_rwsem); } static bool cgroup_reclaim(struct scan_control *sc) { return sc->target_mem_cgroup; } /** * writeback_throttling_sane - is the usual dirty throttling mechanism available? * @sc: scan_control in question * * The normal page dirty throttling mechanism in balance_dirty_pages() is * completely broken with the legacy memcg and direct stalling in * shrink_page_list() is used for throttling instead, which lacks all the * niceties such as fairness, adaptive pausing, bandwidth proportional * allocation and configurability. * * This function tests whether the vmscan currently in progress can assume * that the normal dirty throttling mechanism is operational. */ static bool writeback_throttling_sane(struct scan_control *sc) { if (!cgroup_reclaim(sc)) return true; #ifdef CONFIG_CGROUP_WRITEBACK if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return true; #endif return false; } #else static int prealloc_memcg_shrinker(struct shrinker *shrinker) { return 0; } static void unregister_memcg_shrinker(struct shrinker *shrinker) { } static bool cgroup_reclaim(struct scan_control *sc) { return false; } static bool writeback_throttling_sane(struct scan_control *sc) { return true; } #endif /* * This misses isolated pages which are not accounted for to save counters. * As the data only determines if reclaim or compaction continues, it is * not expected that isolated pages will be a dominating factor. */ unsigned long zone_reclaimable_pages(struct zone *zone) { unsigned long nr; nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE); if (get_nr_swap_pages() > 0) nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); return nr; } /** * lruvec_lru_size - Returns the number of pages on the given LRU list. * @lruvec: lru vector * @lru: lru to use * @zone_idx: zones to consider (use MAX_NR_ZONES for the whole LRU list) */ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { unsigned long size = 0; int zid; for (zid = 0; zid <= zone_idx && zid < MAX_NR_ZONES; zid++) { struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid]; if (!managed_zone(zone)) continue; if (!mem_cgroup_disabled()) size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid); else size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru); } return size; } /* * Add a shrinker callback to be called from the vm. */ int prealloc_shrinker(struct shrinker *shrinker) { unsigned int size = sizeof(*shrinker->nr_deferred); if (shrinker->flags & SHRINKER_NUMA_AWARE) size *= nr_node_ids; shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); if (!shrinker->nr_deferred) return -ENOMEM; if (shrinker->flags & SHRINKER_MEMCG_AWARE) { if (prealloc_memcg_shrinker(shrinker)) goto free_deferred; } return 0; free_deferred: kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; return -ENOMEM; } void free_prealloced_shrinker(struct shrinker *shrinker) { if (!shrinker->nr_deferred) return; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; } void register_shrinker_prepared(struct shrinker *shrinker) { down_write(&shrinker_rwsem); list_add_tail(&shrinker->list, &shrinker_list); #ifdef CONFIG_MEMCG if (shrinker->flags & SHRINKER_MEMCG_AWARE) idr_replace(&shrinker_idr, shrinker, shrinker->id); #endif up_write(&shrinker_rwsem); } int register_shrinker(struct shrinker *shrinker) { int err = prealloc_shrinker(shrinker); if (err) return err; register_shrinker_prepared(shrinker); return 0; } EXPORT_SYMBOL(register_shrinker); /* * Remove one */ void unregister_shrinker(struct shrinker *shrinker) { if (!shrinker->nr_deferred) return; if (shrinker->flags & SHRINKER_MEMCG_AWARE) unregister_memcg_shrinker(shrinker); down_write(&shrinker_rwsem); list_del(&shrinker->list); up_write(&shrinker_rwsem); kfree(shrinker->nr_deferred); shrinker->nr_deferred = NULL; } EXPORT_SYMBOL(unregister_shrinker); #define SHRINK_BATCH 128 static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, struct shrinker *shrinker, int priority) { unsigned long freed = 0; unsigned long long delta; long total_scan; long freeable; long nr; long new_nr; int nid = shrinkctl->nid; long batch_size = shrinker->batch ? shrinker->batch : SHRINK_BATCH; long scanned = 0, next_deferred; if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) nid = 0; freeable = shrinker->count_objects(shrinker, shrinkctl); if (freeable == 0 || freeable == SHRINK_EMPTY) return freeable; /* * copy the current shrinker scan count into a local variable * and zero it so that other concurrent shrinker invocations * don't also do this scanning work. */ nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0); total_scan = nr; if (shrinker->seeks) { delta = freeable >> priority; delta *= 4; do_div(delta, shrinker->seeks); } else { /* * These objects don't require any IO to create. Trim * them aggressively under memory pressure to keep * them from causing refetches in the IO caches. */ delta = freeable / 2; } total_scan += delta; if (total_scan < 0) { pr_err("shrink_slab: %pS negative objects to delete nr=%ld\n", shrinker->scan_objects, total_scan); total_scan = freeable; next_deferred = nr; } else next_deferred = total_scan; /* * We need to avoid excessive windup on filesystem shrinkers * due to large numbers of GFP_NOFS allocations causing the * shrinkers to return -1 all the time. This results in a large * nr being built up so when a shrink that can do some work * comes along it empties the entire cache due to nr >>> * freeable. This is bad for sustaining a working set in * memory. * * Hence only allow the shrinker to scan the entire cache when * a large delta change is calculated directly. */ if (delta < freeable / 4) total_scan = min(total_scan, freeable / 2); /* * Avoid risking looping forever due to too large nr value: * never try to free more than twice the estimate number of * freeable entries. */ if (total_scan > freeable * 2) total_scan = freeable * 2; trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, freeable, delta, total_scan, priority); /* * Normally, we should not scan less than batch_size objects in one * pass to avoid too frequent shrinker calls, but if the slab has less * than batch_size objects in total and we are really tight on memory, * we will try to reclaim all available objects, otherwise we can end * up failing allocations although there are plenty of reclaimable * objects spread over several slabs with usage less than the * batch_size. * * We detect the "tight on memory" situations by looking at the total * number of objects we want to scan (total_scan). If it is greater * than the total number of objects on slab (freeable), we must be * scanning at high prio and therefore should try to reclaim as much as * possible. */ while (total_scan >= batch_size || total_scan >= freeable) { unsigned long ret; unsigned long nr_to_scan = min(batch_size, total_scan); shrinkctl->nr_to_scan = nr_to_scan; shrinkctl->nr_scanned = nr_to_scan; ret = shrinker->scan_objects(shrinker, shrinkctl); if (ret == SHRINK_STOP) break; freed += ret; count_vm_events(SLABS_SCANNED, shrinkctl->nr_scanned); total_scan -= shrinkctl->nr_scanned; scanned += shrinkctl->nr_scanned; cond_resched(); } if (next_deferred >= scanned) next_deferred -= scanned; else next_deferred = 0; /* * move the unused scan count back into the shrinker in a * manner that handles concurrent updates. If we exhausted the * scan, there is no need to do an update. */ if (next_deferred > 0) new_nr = atomic_long_add_return(next_deferred, &shrinker->nr_deferred[nid]); else new_nr = atomic_long_read(&shrinker->nr_deferred[nid]); trace_mm_shrink_slab_end(shrinker, nid, freed, nr, new_nr, total_scan); return freed; } #ifdef CONFIG_MEMCG static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { struct memcg_shrinker_map *map; unsigned long ret, freed = 0; int i; if (!mem_cgroup_online(memcg)) return 0; if (!down_read_trylock(&shrinker_rwsem)) return 0; map = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_map, true); if (unlikely(!map)) goto unlock; for_each_set_bit(i, map->map, shrinker_nr_max) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, .memcg = memcg, }; struct shrinker *shrinker; shrinker = idr_find(&shrinker_idr, i); if (unlikely(!shrinker || shrinker == SHRINKER_REGISTERING)) { if (!shrinker) clear_bit(i, map->map); continue; } /* Call non-slab shrinkers even though kmem is disabled */ if (!memcg_kmem_enabled() && !(shrinker->flags & SHRINKER_NONSLAB)) continue; ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) { clear_bit(i, map->map); /* * After the shrinker reported that it had no objects to * free, but before we cleared the corresponding bit in * the memcg shrinker map, a new object might have been * added. To make sure, we have the bit set in this * case, we invoke the shrinker one more time and reset * the bit if it reports that it is not empty anymore. * The memory barrier here pairs with the barrier in * memcg_set_shrinker_bit(): * * list_lru_add() shrink_slab_memcg() * list_add_tail() clear_bit() * <MB> <MB> * set_bit() do_shrink_slab() */ smp_mb__after_atomic(); ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) ret = 0; else memcg_set_shrinker_bit(memcg, nid, i); } freed += ret; if (rwsem_is_contended(&shrinker_rwsem)) { freed = freed ? : 1; break; } } unlock: up_read(&shrinker_rwsem); return freed; } #else /* CONFIG_MEMCG */ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { return 0; } #endif /* CONFIG_MEMCG */ /** * shrink_slab - shrink slab caches * @gfp_mask: allocation context * @nid: node whose slab caches to target * @memcg: memory cgroup whose slab caches to target * @priority: the reclaim priority * * Call the shrink functions to age shrinkable caches. * * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set, * unaware shrinkers will receive a node id of 0 instead. * * @memcg specifies the memory cgroup to target. Unaware shrinkers * are called only if it is the root cgroup. * * @priority is sc->priority, we take the number of objects and >> by priority * in order to get the scan target. * * Returns the number of reclaimed slab objects. */ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { unsigned long ret, freed = 0; struct shrinker *shrinker; /* * The root memcg might be allocated even though memcg is disabled * via "cgroup_disable=memory" boot parameter. This could make * mem_cgroup_is_root() return false, then just run memcg slab * shrink, but skip global shrink. This may result in premature * oom. */ if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) return shrink_slab_memcg(gfp_mask, nid, memcg, priority); if (!down_read_trylock(&shrinker_rwsem)) goto out; list_for_each_entry(shrinker, &shrinker_list, list) { struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, .memcg = memcg, }; ret = do_shrink_slab(&sc, shrinker, priority); if (ret == SHRINK_EMPTY) ret = 0; freed += ret; /* * Bail out if someone want to register a new shrinker to * prevent the registration from being stalled for long periods * by parallel ongoing shrinking. */ if (rwsem_is_contended(&shrinker_rwsem)) { freed = freed ? : 1; break; } } up_read(&shrinker_rwsem); out: cond_resched(); return freed; } void drop_slab_node(int nid) { unsigned long freed; do { struct mem_cgroup *memcg = NULL; if (fatal_signal_pending(current)) return; freed = 0; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { freed += shrink_slab(GFP_KERNEL, nid, memcg, 0); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); } while (freed > 10); } void drop_slab(void) { int nid; for_each_online_node(nid) drop_slab_node(nid); } static inline int is_page_cache_freeable(struct page *page) { /* * A freeable page cache page is referenced only by the caller * that isolated the page, the page cache and optional buffer * heads at page->private. */ int page_cache_pins = thp_nr_pages(page); return page_count(page) - page_has_private(page) == 1 + page_cache_pins; } static int may_write_to_inode(struct inode *inode) { if (current->flags & PF_SWAPWRITE) return 1; if (!inode_write_congested(inode)) return 1; if (inode_to_bdi(inode) == current->backing_dev_info) return 1; return 0; } /* * We detected a synchronous write error writing a page out. Probably * -ENOSPC. We need to propagate that into the address_space for a subsequent * fsync(), msync() or close(). * * The tricky part is that after writepage we cannot touch the mapping: nothing * prevents it from being freed up. But we have a ref on the page and once * that page is locked, the mapping is pinned. * * We're allowed to run sleeping lock_page() here because we know the caller has * __GFP_FS. */ static void handle_write_error(struct address_space *mapping, struct page *page, int error) { lock_page(page); if (page_mapping(page) == mapping) mapping_set_error(mapping, error); unlock_page(page); } /* possible outcome of pageout() */ typedef enum { /* failed to write page out, page is locked */ PAGE_KEEP, /* move page to the active list, page is locked */ PAGE_ACTIVATE, /* page has been sent to the disk successfully, page is unlocked */ PAGE_SUCCESS, /* page is clean and locked */ PAGE_CLEAN, } pageout_t; /* * pageout is called by shrink_page_list() for each dirty page. * Calls ->writepage(). */ static pageout_t pageout(struct page *page, struct address_space *mapping) { /* * If the page is dirty, only perform writeback if that write * will be non-blocking. To prevent this allocation from being * stalled by pagecache activity. But note that there may be * stalls if we need to run get_block(). We could test * PagePrivate for that. * * If this process is currently in __generic_file_write_iter() against * this page's queue, we can perform writeback even if that * will block. * * If the page is swapcache, write it back even if that would * block, for some throttling. This happens by accident, because * swap_backing_dev_info is bust: it doesn't reflect the * congestion state of the swapdevs. Easy to fix, if needed. */ if (!is_page_cache_freeable(page)) return PAGE_KEEP; if (!mapping) { /* * Some data journaling orphaned pages can have * page->mapping == NULL while being dirty with clean buffers. */ if (page_has_private(page)) { if (try_to_free_buffers(page)) { ClearPageDirty(page); pr_info("%s: orphaned page\n", __func__); return PAGE_CLEAN; } } return PAGE_KEEP; } if (mapping->a_ops->writepage == NULL) return PAGE_ACTIVATE; if (!may_write_to_inode(mapping->host)) return PAGE_KEEP; if (clear_page_dirty_for_io(page)) { int res; struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, .nr_to_write = SWAP_CLUSTER_MAX, .range_start = 0, .range_end = LLONG_MAX, .for_reclaim = 1, }; SetPageReclaim(page); res = mapping->a_ops->writepage(page, &wbc); if (res < 0) handle_write_error(mapping, page, res); if (res == AOP_WRITEPAGE_ACTIVATE) { ClearPageReclaim(page); return PAGE_ACTIVATE; } if (!PageWriteback(page)) { /* synchronous write or broken a_ops? */ ClearPageReclaim(page); } trace_mm_vmscan_writepage(page); inc_node_page_state(page, NR_VMSCAN_WRITE); return PAGE_SUCCESS; } return PAGE_CLEAN; } /* * Same as remove_mapping, but if the page is removed from the mapping, it * gets returned with a refcount of 0. */ static int __remove_mapping(struct address_space *mapping, struct page *page, bool reclaimed, struct mem_cgroup *target_memcg) { unsigned long flags; int refcount; void *shadow = NULL; BUG_ON(!PageLocked(page)); BUG_ON(mapping != page_mapping(page)); xa_lock_irqsave(&mapping->i_pages, flags); /* * The non racy check for a busy page. * * Must be careful with the order of the tests. When someone has * a ref to the page, it may be possible that they dirty it then * drop the reference. So if PageDirty is tested before page_count * here, then the following race may occur: * * get_user_pages(&page); * [user mapping goes away] * write_to(page); * !PageDirty(page) [good] * SetPageDirty(page); * put_page(page); * !page_count(page) [good, discard it] * * [oops, our write_to data is lost] * * Reversing the order of the tests ensures such a situation cannot * escape unnoticed. The smp_rmb is needed to ensure the page->flags * load is not satisfied before that of page->_refcount. * * Note that if SetPageDirty is always performed via set_page_dirty, * and thus under the i_pages lock, then this ordering is not required. */ refcount = 1 + compound_nr(page); if (!page_ref_freeze(page, refcount)) goto cannot_free; /* note: atomic_cmpxchg in page_ref_freeze provides the smp_rmb */ if (unlikely(PageDirty(page))) { page_ref_unfreeze(page, refcount); goto cannot_free; } if (PageSwapCache(page)) { swp_entry_t swap = { .val = page_private(page) }; mem_cgroup_swapout(page, swap); if (reclaimed && !mapping_exiting(mapping)) shadow = workingset_eviction(page, target_memcg); __delete_from_swap_cache(page, swap, shadow); xa_unlock_irqrestore(&mapping->i_pages, flags); put_swap_page(page, swap); } else { void (*freepage)(struct page *); freepage = mapping->a_ops->freepage; /* * Remember a shadow entry for reclaimed file cache in * order to detect refaults, thus thrashing, later on. * * But don't store shadows in an address space that is * already exiting. This is not just an optimization, * inode reclaim needs to empty out the radix tree or * the nodes are lost. Don't plant shadows behind its * back. * * We also don't store shadows for DAX mappings because the * only page cache pages found in these are zero pages * covering holes, and because we don't want to mix DAX * exceptional entries and shadow exceptional entries in the * same address_space. */ if (reclaimed && page_is_file_lru(page) && !mapping_exiting(mapping) && !dax_mapping(mapping)) shadow = workingset_eviction(page, target_memcg); __delete_from_page_cache(page, shadow); xa_unlock_irqrestore(&mapping->i_pages, flags); if (freepage != NULL) freepage(page); } return 1; cannot_free: xa_unlock_irqrestore(&mapping->i_pages, flags); return 0; } /* * Attempt to detach a locked page from its ->mapping. If it is dirty or if * someone else has a ref on the page, abort and return 0. If it was * successfully detached, return 1. Assumes the caller has a single ref on * this page. */ int remove_mapping(struct address_space *mapping, struct page *page) { if (__remove_mapping(mapping, page, false, NULL)) { /* * Unfreezing the refcount with 1 rather than 2 effectively * drops the pagecache ref for us without requiring another * atomic operation. */ page_ref_unfreeze(page, 1); return 1; } return 0; } /** * putback_lru_page - put previously isolated page onto appropriate LRU list * @page: page to be put back to appropriate lru list * * Add previously isolated @page to appropriate LRU list. * Page may still be unevictable for other reasons. * * lru_lock must not be held, interrupts must be enabled. */ void putback_lru_page(struct page *page) { lru_cache_add(page); put_page(page); /* drop ref from isolate */ } enum page_references { PAGEREF_RECLAIM, PAGEREF_RECLAIM_CLEAN, PAGEREF_KEEP, PAGEREF_ACTIVATE, }; static enum page_references page_check_references(struct page *page, struct scan_control *sc) { int referenced_ptes, referenced_page; unsigned long vm_flags; referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup, &vm_flags); referenced_page = TestClearPageReferenced(page); /* * Mlock lost the isolation race with us. Let try_to_unmap() * move the page to the unevictable list. */ if (vm_flags & VM_LOCKED) return PAGEREF_RECLAIM; if (referenced_ptes) { /* * All mapped pages start out with page table * references from the instantiating fault, so we need * to look twice if a mapped file page is used more * than once. * * Mark it and spare it for another trip around the * inactive list. Another page table reference will * lead to its activation. * * Note: the mark is set for activated pages as well * so that recently deactivated but used pages are * quickly recovered. */ SetPageReferenced(page); if (referenced_page || referenced_ptes > 1) return PAGEREF_ACTIVATE; /* * Activate file-backed executable pages after first usage. */ if ((vm_flags & VM_EXEC) && !PageSwapBacked(page)) return PAGEREF_ACTIVATE; return PAGEREF_KEEP; } /* Reclaim if clean, defer dirty pages to writeback */ if (referenced_page && !PageSwapBacked(page)) return PAGEREF_RECLAIM_CLEAN; return PAGEREF_RECLAIM; } /* Check if a page is dirty or under writeback */ static void page_check_dirty_writeback(struct page *page, bool *dirty, bool *writeback) { struct address_space *mapping; /* * Anonymous pages are not handled by flushers and must be written * from reclaim context. Do not stall reclaim based on them */ if (!page_is_file_lru(page) || (PageAnon(page) && !PageSwapBacked(page))) { *dirty = false; *writeback = false; return; } /* By default assume that the page flags are accurate */ *dirty = PageDirty(page); *writeback = PageWriteback(page); /* Verify dirty/writeback state if the filesystem supports it */ if (!page_has_private(page)) return; mapping = page_mapping(page); if (mapping && mapping->a_ops->is_dirty_writeback) mapping->a_ops->is_dirty_writeback(page, dirty, writeback); } /* * shrink_page_list() returns the number of reclaimed pages */ static unsigned int shrink_page_list(struct list_head *page_list, struct pglist_data *pgdat, struct scan_control *sc, struct reclaim_stat *stat, bool ignore_references) { LIST_HEAD(ret_pages); LIST_HEAD(free_pages); unsigned int nr_reclaimed = 0; unsigned int pgactivate = 0; memset(stat, 0, sizeof(*stat)); cond_resched(); while (!list_empty(page_list)) { struct address_space *mapping; struct page *page; enum page_references references = PAGEREF_RECLAIM; bool dirty, writeback, may_enter_fs; unsigned int nr_pages; cond_resched(); page = lru_to_page(page_list); list_del(&page->lru); if (!trylock_page(page)) goto keep; VM_BUG_ON_PAGE(PageActive(page), page); nr_pages = compound_nr(page); /* Account the number of base pages even though THP */ sc->nr_scanned += nr_pages; if (unlikely(!page_evictable(page))) goto activate_locked; if (!sc->may_unmap && page_mapped(page)) goto keep_locked; may_enter_fs = (sc->gfp_mask & __GFP_FS) || (PageSwapCache(page) && (sc->gfp_mask & __GFP_IO)); /* * The number of dirty pages determines if a node is marked * reclaim_congested which affects wait_iff_congested. kswapd * will stall and start writing pages if the tail of the LRU * is all dirty unqueued pages. */ page_check_dirty_writeback(page, &dirty, &writeback); if (dirty || writeback) stat->nr_dirty++; if (dirty && !writeback) stat->nr_unqueued_dirty++; /* * Treat this page as congested if the underlying BDI is or if * pages are cycling through the LRU so quickly that the * pages marked for immediate reclaim are making it to the * end of the LRU a second time. */ mapping = page_mapping(page); if (((dirty || writeback) && mapping && inode_write_congested(mapping->host)) || (writeback && PageReclaim(page))) stat->nr_congested++; /* * If a page at the tail of the LRU is under writeback, there * are three cases to consider. * * 1) If reclaim is encountering an excessive number of pages * under writeback and this page is both under writeback and * PageReclaim then it indicates that pages are being queued * for IO but are being recycled through the LRU before the * IO can complete. Waiting on the page itself risks an * indefinite stall if it is impossible to writeback the * page due to IO error or disconnected storage so instead * note that the LRU is being scanned too quickly and the * caller can stall after page list has been processed. * * 2) Global or new memcg reclaim encounters a page that is * not marked for immediate reclaim, or the caller does not * have __GFP_FS (or __GFP_IO if it's simply going to swap, * not to fs). In this case mark the page for immediate * reclaim and continue scanning. * * Require may_enter_fs because we would wait on fs, which * may not have submitted IO yet. And the loop driver might * enter reclaim, and deadlock if it waits on a page for * which it is needed to do the write (loop masks off * __GFP_IO|__GFP_FS for this reason); but more thought * would probably show more reasons. * * 3) Legacy memcg encounters a page that is already marked * PageReclaim. memcg does not have any dirty pages * throttling so we could easily OOM just because too many * pages are in writeback and there is nothing else to * reclaim. Wait for the writeback to complete. * * In cases 1) and 2) we activate the pages to get them out of * the way while we continue scanning for clean pages on the * inactive list and refilling from the active list. The * observation here is that waiting for disk writes is more * expensive than potentially causing reloads down the line. * Since they're marked for immediate reclaim, they won't put * memory pressure on the cache working set any longer than it * takes to write them to disk. */ if (PageWriteback(page)) { /* Case 1 above */ if (current_is_kswapd() && PageReclaim(page) && test_bit(PGDAT_WRITEBACK, &pgdat->flags)) { stat->nr_immediate++; goto activate_locked; /* Case 2 above */ } else if (writeback_throttling_sane(sc) || !PageReclaim(page) || !may_enter_fs) { /* * This is slightly racy - end_page_writeback() * might have just cleared PageReclaim, then * setting PageReclaim here end up interpreted * as PageReadahead - but that does not matter * enough to care. What we do want is for this * page to have PageReclaim set next time memcg * reclaim reaches the tests above, so it will * then wait_on_page_writeback() to avoid OOM; * and it's also appropriate in global reclaim. */ SetPageReclaim(page); stat->nr_writeback++; goto activate_locked; /* Case 3 above */ } else { unlock_page(page); wait_on_page_writeback(page); /* then go back and try same page again */ list_add_tail(&page->lru, page_list); continue; } } if (!ignore_references) references = page_check_references(page, sc); switch (references) { case PAGEREF_ACTIVATE: goto activate_locked; case PAGEREF_KEEP: stat->nr_ref_keep += nr_pages; goto keep_locked; case PAGEREF_RECLAIM: case PAGEREF_RECLAIM_CLEAN: ; /* try to reclaim the page below */ } /* * Anonymous process memory has backing store? * Try to allocate it some swap space here. * Lazyfree page could be freed directly */ if (PageAnon(page) && PageSwapBacked(page)) { if (!PageSwapCache(page)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; if (page_maybe_dma_pinned(page)) goto keep_locked; if (PageTransHuge(page)) { /* cannot split THP, skip it */ if (!can_split_huge_page(page, NULL)) goto activate_locked; /* * Split pages without a PMD map right * away. Chances are some or all of the * tail pages can be freed without IO. */ if (!compound_mapcount(page) && split_huge_page_to_list(page, page_list)) goto activate_locked; } if (!add_to_swap(page)) { if (!PageTransHuge(page)) goto activate_locked_split; /* Fallback to swap normal pages */ if (split_huge_page_to_list(page, page_list)) goto activate_locked; #ifdef CONFIG_TRANSPARENT_HUGEPAGE count_vm_event(THP_SWPOUT_FALLBACK); #endif if (!add_to_swap(page)) goto activate_locked_split; } may_enter_fs = true; /* Adding to swap updated mapping */ mapping = page_mapping(page); } } else if (unlikely(PageTransHuge(page))) { /* Split file THP */ if (split_huge_page_to_list(page, page_list)) goto keep_locked; } /* * THP may get split above, need minus tail pages and update * nr_pages to avoid accounting tail pages twice. * * The tail pages that are added into swap cache successfully * reach here. */ if ((nr_pages > 1) && !PageTransHuge(page)) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } /* * The page is mapped into the page tables of one or more * processes. Try to unmap it here. */ if (page_mapped(page)) { enum ttu_flags flags = TTU_BATCH_FLUSH; bool was_swapbacked = PageSwapBacked(page); if (unlikely(PageTransHuge(page))) flags |= TTU_SPLIT_HUGE_PMD; if (!try_to_unmap(page, flags)) { stat->nr_unmap_fail += nr_pages; if (!was_swapbacked && PageSwapBacked(page)) stat->nr_lazyfree_fail += nr_pages; goto activate_locked; } } if (PageDirty(page)) { /* * Only kswapd can writeback filesystem pages * to avoid risk of stack overflow. But avoid * injecting inefficient single-page IO into * flusher writeback as much as possible: only * write pages when we've encountered many * dirty pages, and when we've already scanned * the rest of the LRU for clean pages and see * the same dirty pages again (PageReclaim). */ if (page_is_file_lru(page) && (!current_is_kswapd() || !PageReclaim(page) || !test_bit(PGDAT_DIRTY, &pgdat->flags))) { /* * Immediately reclaim when written back. * Similar in principal to deactivate_page() * except we already have the page isolated * and know it's dirty */ inc_node_page_state(page, NR_VMSCAN_IMMEDIATE); SetPageReclaim(page); goto activate_locked; } if (references == PAGEREF_RECLAIM_CLEAN) goto keep_locked; if (!may_enter_fs) goto keep_locked; if (!sc->may_writepage) goto keep_locked; /* * Page is dirty. Flush the TLB if a writable entry * potentially exists to avoid CPU writes after IO * starts and then write it out here. */ try_to_unmap_flush_dirty(); switch (pageout(page, mapping)) { case PAGE_KEEP: goto keep_locked; case PAGE_ACTIVATE: goto activate_locked; case PAGE_SUCCESS: stat->nr_pageout += thp_nr_pages(page); if (PageWriteback(page)) goto keep; if (PageDirty(page)) goto keep; /* * A synchronous write - probably a ramdisk. Go * ahead and try to reclaim the page. */ if (!trylock_page(page)) goto keep; if (PageDirty(page) || PageWriteback(page)) goto keep_locked; mapping = page_mapping(page); case PAGE_CLEAN: ; /* try to free the page below */ } } /* * If the page has buffers, try to free the buffer mappings * associated with this page. If we succeed we try to free * the page as well. * * We do this even if the page is PageDirty(). * try_to_release_page() does not perform I/O, but it is * possible for a page to have PageDirty set, but it is actually * clean (all its buffers are clean). This happens if the * buffers were written out directly, with submit_bh(). ext3 * will do this, as well as the blockdev mapping. * try_to_release_page() will discover that cleanness and will * drop the buffers and mark the page clean - it can be freed. * * Rarely, pages can have buffers and no ->mapping. These are * the pages which were not successfully invalidated in * truncate_complete_page(). We try to drop those buffers here * and if that worked, and the page is no longer mapped into * process address space (page_count == 1) it can be freed. * Otherwise, leave the page on the LRU so it is swappable. */ if (page_has_private(page)) { if (!try_to_release_page(page, sc->gfp_mask)) goto activate_locked; if (!mapping && page_count(page) == 1) { unlock_page(page); if (put_page_testzero(page)) goto free_it; else { /* * rare race with speculative reference. * the speculative reference will free * this page shortly, so we may * increment nr_reclaimed here (and * leave it off the LRU). */ nr_reclaimed++; continue; } } } if (PageAnon(page) && !PageSwapBacked(page)) { /* follow __remove_mapping for reference */ if (!page_ref_freeze(page, 1)) goto keep_locked; if (PageDirty(page)) { page_ref_unfreeze(page, 1); goto keep_locked; } count_vm_event(PGLAZYFREED); count_memcg_page_event(page, PGLAZYFREED); } else if (!mapping || !__remove_mapping(mapping, page, true, sc->target_mem_cgroup)) goto keep_locked; unlock_page(page); free_it: /* * THP may get swapped out in a whole, need account * all base pages. */ nr_reclaimed += nr_pages; /* * Is there need to periodically free_page_list? It would * appear not as the counts should be low */ if (unlikely(PageTransHuge(page))) destroy_compound_page(page); else list_add(&page->lru, &free_pages); continue; activate_locked_split: /* * The tail pages that are failed to add into swap cache * reach here. Fixup nr_scanned and nr_pages. */ if (nr_pages > 1) { sc->nr_scanned -= (nr_pages - 1); nr_pages = 1; } activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ if (PageSwapCache(page) && (mem_cgroup_swap_full(page) || PageMlocked(page))) try_to_free_swap(page); VM_BUG_ON_PAGE(PageActive(page), page); if (!PageMlocked(page)) { int type = page_is_file_lru(page); SetPageActive(page); stat->nr_activate[type] += nr_pages; count_memcg_page_event(page, PGACTIVATE); } keep_locked: unlock_page(page); keep: list_add(&page->lru, &ret_pages); VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page); } pgactivate = stat->nr_activate[0] + stat->nr_activate[1]; mem_cgroup_uncharge_list(&free_pages); try_to_unmap_flush(); free_unref_page_list(&free_pages); list_splice(&ret_pages, page_list); count_vm_events(PGACTIVATE, pgactivate); return nr_reclaimed; } unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *page_list) { struct scan_control sc = { .gfp_mask = GFP_KERNEL, .priority = DEF_PRIORITY, .may_unmap = 1, }; struct reclaim_stat stat; unsigned int nr_reclaimed; struct page *page, *next; LIST_HEAD(clean_pages); list_for_each_entry_safe(page, next, page_list, lru) { if (page_is_file_lru(page) && !PageDirty(page) && !__PageMovable(page) && !PageUnevictable(page)) { ClearPageActive(page); list_move(&page->lru, &clean_pages); } } nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc, &stat, true); list_splice(&clean_pages, page_list); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)nr_reclaimed); /* * Since lazyfree pages are isolated from file LRU from the beginning, * they will rotate back to anonymous LRU in the end if it failed to * discard so isolated count will be mismatched. * Compensate the isolated count for both LRU lists. */ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, stat.nr_lazyfree_fail); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)stat.nr_lazyfree_fail); return nr_reclaimed; } /* * Attempt to remove the specified page from its LRU. Only take this page * if it is of the appropriate PageActive status. Pages which are being * freed elsewhere are also ignored. * * page: page to consider * mode: one of the LRU isolation modes defined above * * returns 0 on success, -ve errno on failure. */ int __isolate_lru_page(struct page *page, isolate_mode_t mode) { int ret = -EINVAL; /* Only take pages on the LRU. */ if (!PageLRU(page)) return ret; /* Compaction should not handle unevictable pages but CMA can do so */ if (PageUnevictable(page) && !(mode & ISOLATE_UNEVICTABLE)) return ret; ret = -EBUSY; /* * To minimise LRU disruption, the caller can indicate that it only * wants to isolate pages it will be able to operate on without * blocking - clean pages for the most part. * * ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages * that it is possible to migrate without blocking */ if (mode & ISOLATE_ASYNC_MIGRATE) { /* All the caller can do on PageWriteback is block */ if (PageWriteback(page)) return ret; if (PageDirty(page)) { struct address_space *mapping; bool migrate_dirty; /* * Only pages without mappings or that have a * ->migratepage callback are possible to migrate * without blocking. However, we can be racing with * truncation so it's necessary to lock the page * to stabilise the mapping as truncation holds * the page lock until after the page is removed * from the page cache. */ if (!trylock_page(page)) return ret; mapping = page_mapping(page); migrate_dirty = !mapping || mapping->a_ops->migratepage; unlock_page(page); if (!migrate_dirty) return ret; } } if ((mode & ISOLATE_UNMAPPED) && page_mapped(page)) return ret; if (likely(get_page_unless_zero(page))) { /* * Be careful not to clear PageLRU until after we're * sure the page is not being freed elsewhere -- the * page release code relies on it. */ ClearPageLRU(page); ret = 0; } return ret; } /* * Update LRU sizes after isolating pages. The LRU size updates must * be complete before mem_cgroup_update_lru_size due to a sanity check. */ static __always_inline void update_lru_sizes(struct lruvec *lruvec, enum lru_list lru, unsigned long *nr_zone_taken) { int zid; for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_zone_taken[zid]) continue; update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]); } } /** * pgdat->lru_lock is heavily contended. Some of the functions that * shrink the lists perform better by taking out a batch of pages * and working on them outside the LRU lock. * * For pagecache intensive workloads, this function is the hottest * spot in the kernel (apart from copy_*_user functions). * * Appropriate locks must be held before calling this function. * * @nr_to_scan: The number of eligible pages to look through on the list. * @lruvec: The LRU vector to pull pages from. * @dst: The temp list to put pages on to. * @nr_scanned: The number of pages that were scanned. * @sc: The scan_control struct for this reclaim session * @lru: LRU list id for isolating * * returns how many pages were moved onto *@dst. */ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, struct lruvec *lruvec, struct list_head *dst, unsigned long *nr_scanned, struct scan_control *sc, enum lru_list lru) { struct list_head *src = &lruvec->lists[lru]; unsigned long nr_taken = 0; unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 }; unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; unsigned long skipped = 0; unsigned long scan, total_scan, nr_pages; LIST_HEAD(pages_skipped); isolate_mode_t mode = (sc->may_unmap ? 0 : ISOLATE_UNMAPPED); total_scan = 0; scan = 0; while (scan < nr_to_scan && !list_empty(src)) { struct page *page; page = lru_to_page(src); prefetchw_prev_lru_page(page, src, flags); VM_BUG_ON_PAGE(!PageLRU(page), page); nr_pages = compound_nr(page); total_scan += nr_pages; if (page_zonenum(page) > sc->reclaim_idx) { list_move(&page->lru, &pages_skipped); nr_skipped[page_zonenum(page)] += nr_pages; continue; } /* * Do not count skipped pages because that makes the function * return with no isolated pages if the LRU mostly contains * ineligible pages. This causes the VM to not reclaim any * pages, triggering a premature OOM. * * Account all tail pages of THP. This would not cause * premature OOM since __isolate_lru_page() returns -EBUSY * only when the page is being freed somewhere else. */ scan += nr_pages; switch (__isolate_lru_page(page, mode)) { case 0: nr_taken += nr_pages; nr_zone_taken[page_zonenum(page)] += nr_pages; list_move(&page->lru, dst); break; case -EBUSY: /* else it is being freed elsewhere */ list_move(&page->lru, src); continue; default: BUG(); } } /* * Splice any skipped pages to the start of the LRU list. Note that * this disrupts the LRU order when reclaiming for lower zones but * we cannot splice to the tail. If we did then the SWAP_CLUSTER_MAX * scanning would soon rescan the same pages to skip and put the * system at risk of premature OOM. */ if (!list_empty(&pages_skipped)) { int zid; list_splice(&pages_skipped, src); for (zid = 0; zid < MAX_NR_ZONES; zid++) { if (!nr_skipped[zid]) continue; __count_zid_vm_events(PGSCAN_SKIP, zid, nr_skipped[zid]); skipped += nr_skipped[zid]; } } *nr_scanned = total_scan; trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan, total_scan, skipped, nr_taken, mode, lru); update_lru_sizes(lruvec, lru, nr_zone_taken); return nr_taken; } /** * isolate_lru_page - tries to isolate a page from its LRU list * @page: page to isolate from its LRU list * * Isolates a @page from an LRU list, clears PageLRU and adjusts the * vmstat statistic corresponding to whatever LRU list the page was on. * * Returns 0 if the page was removed from an LRU list. * Returns -EBUSY if the page was not on an LRU list. * * The returned page will have PageLRU() cleared. If it was found on * the active list, it will have PageActive set. If it was found on * the unevictable list, it will have the PageUnevictable bit set. That flag * may need to be cleared by the caller before letting the page go. * * The vmstat statistic corresponding to the list on which the page was * found will be decremented. * * Restrictions: * * (1) Must be called with an elevated refcount on the page. This is a * fundamental difference from isolate_lru_pages (which is called * without a stable reference). * (2) the lru_lock must not be held. * (3) interrupts must be enabled. */ int isolate_lru_page(struct page *page) { int ret = -EBUSY; VM_BUG_ON_PAGE(!page_count(page), page); WARN_RATELIMIT(PageTail(page), "trying to isolate tail page"); if (PageLRU(page)) { pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; spin_lock_irq(&pgdat->lru_lock); lruvec = mem_cgroup_page_lruvec(page, pgdat); if (PageLRU(page)) { int lru = page_lru(page); get_page(page); ClearPageLRU(page); del_page_from_lru_list(page, lruvec, lru); ret = 0; } spin_unlock_irq(&pgdat->lru_lock); } return ret; } /* * A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and * then get rescheduled. When there are massive number of tasks doing page * allocation, such sleeping direct reclaimers may keep piling up on each CPU, * the LRU list will go small and be scanned faster than necessary, leading to * unnecessary swapping, thrashing and OOM. */ static int too_many_isolated(struct pglist_data *pgdat, int file, struct scan_control *sc) { unsigned long inactive, isolated; if (current_is_kswapd()) return 0; if (!writeback_throttling_sane(sc)) return 0; if (file) { inactive = node_page_state(pgdat, NR_INACTIVE_FILE); isolated = node_page_state(pgdat, NR_ISOLATED_FILE); } else { inactive = node_page_state(pgdat, NR_INACTIVE_ANON); isolated = node_page_state(pgdat, NR_ISOLATED_ANON); } /* * GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they * won't get blocked by normal direct-reclaimers, forming a circular * deadlock. */ if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) inactive >>= 3; return isolated > inactive; } /* * This moves pages from @list to corresponding LRU list. * * We move them the other way if the page is referenced by one or more * processes, from rmap. * * If the pages are mostly unmapped, the processing is fast and it is * appropriate to hold zone_lru_lock across the whole operation. But if * the pages are mapped, the processing is slow (page_referenced()) so we * should drop zone_lru_lock around each page. It's impossible to balance * this, so instead we remove the pages from the LRU while processing them. * It is safe to rely on PG_active against the non-LRU pages in here because * nobody will play with that bit on a non-LRU page. * * The downside is that we have to touch page->_refcount against each page. * But we had to alter page->flags anyway. * * Returns the number of pages moved to the given lruvec. */ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec, struct list_head *list) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); int nr_pages, nr_moved = 0; LIST_HEAD(pages_to_free); struct page *page; enum lru_list lru; while (!list_empty(list)) { page = lru_to_page(list); VM_BUG_ON_PAGE(PageLRU(page), page); if (unlikely(!page_evictable(page))) { list_del(&page->lru); spin_unlock_irq(&pgdat->lru_lock); putback_lru_page(page); spin_lock_irq(&pgdat->lru_lock); continue; } lruvec = mem_cgroup_page_lruvec(page, pgdat); SetPageLRU(page); lru = page_lru(page); nr_pages = thp_nr_pages(page); update_lru_size(lruvec, lru, page_zonenum(page), nr_pages); list_move(&page->lru, &lruvec->lists[lru]); if (put_page_testzero(page)) { __ClearPageLRU(page); __ClearPageActive(page); del_page_from_lru_list(page, lruvec, lru); if (unlikely(PageCompound(page))) { spin_unlock_irq(&pgdat->lru_lock); destroy_compound_page(page); spin_lock_irq(&pgdat->lru_lock); } else list_add(&page->lru, &pages_to_free); } else { nr_moved += nr_pages; if (PageActive(page)) workingset_age_nonresident(lruvec, nr_pages); } } /* * To save our caller's stack, now use input list for pages to free. */ list_splice(&pages_to_free, list); return nr_moved; } /* * If a kernel thread (such as nfsd for loop-back mounts) services * a backing device by writing to the page cache it sets PF_LOCAL_THROTTLE. * In that case we should only throttle if the backing device it is * writing to is congested. In other cases it is safe to throttle. */ static int current_may_throttle(void) { return !(current->flags & PF_LOCAL_THROTTLE) || current->backing_dev_info == NULL || bdi_write_congested(current->backing_dev_info); } /* * shrink_inactive_list() is a helper for shrink_node(). It returns the number * of reclaimed pages */ static noinline_for_stack unsigned long shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { LIST_HEAD(page_list); unsigned long nr_scanned; unsigned int nr_reclaimed = 0; unsigned long nr_taken; struct reclaim_stat stat; bool file = is_file_lru(lru); enum vm_event_item item; struct pglist_data *pgdat = lruvec_pgdat(lruvec); bool stalled = false; while (unlikely(too_many_isolated(pgdat, file, sc))) { if (stalled) return 0; /* wait a bit for the reclaimer. */ msleep(100); stalled = true; /* We are about to die and free our memory. Return now. */ if (fatal_signal_pending(current)) return SWAP_CLUSTER_MAX; } lru_add_drain(); spin_lock_irq(&pgdat->lru_lock); nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT; if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned); __count_vm_events(PGSCAN_ANON + file, nr_scanned); spin_unlock_irq(&pgdat->lru_lock); if (nr_taken == 0) return 0; nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, &stat, false); spin_lock_irq(&pgdat->lru_lock); move_pages_to_lru(lruvec, &page_list); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); lru_note_cost(lruvec, file, stat.nr_pageout); item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT; if (!cgroup_reclaim(sc)) __count_vm_events(item, nr_reclaimed); __count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed); __count_vm_events(PGSTEAL_ANON + file, nr_reclaimed); spin_unlock_irq(&pgdat->lru_lock); mem_cgroup_uncharge_list(&page_list); free_unref_page_list(&page_list); /* * If dirty pages are scanned that are not queued for IO, it * implies that flushers are not doing their job. This can * happen when memory pressure pushes dirty pages to the end of * the LRU before the dirty limits are breached and the dirty * data has expired. It can also happen when the proportion of * dirty pages grows not through writes but through memory * pressure reclaiming all the clean cache. And in some cases, * the flushers simply cannot keep up with the allocation * rate. Nudge the flusher threads in case they are asleep. */ if (stat.nr_unqueued_dirty == nr_taken) wakeup_flusher_threads(WB_REASON_VMSCAN); sc->nr.dirty += stat.nr_dirty; sc->nr.congested += stat.nr_congested; sc->nr.unqueued_dirty += stat.nr_unqueued_dirty; sc->nr.writeback += stat.nr_writeback; sc->nr.immediate += stat.nr_immediate; sc->nr.taken += nr_taken; if (file) sc->nr.file_taken += nr_taken; trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, nr_scanned, nr_reclaimed, &stat, sc->priority, file); return nr_reclaimed; } static void shrink_active_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { unsigned long nr_taken; unsigned long nr_scanned; unsigned long vm_flags; LIST_HEAD(l_hold); /* The pages which were snipped off */ LIST_HEAD(l_active); LIST_HEAD(l_inactive); struct page *page; unsigned nr_deactivate, nr_activate; unsigned nr_rotated = 0; int file = is_file_lru(lru); struct pglist_data *pgdat = lruvec_pgdat(lruvec); lru_add_drain(); spin_lock_irq(&pgdat->lru_lock); nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold, &nr_scanned, sc, lru); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken); if (!cgroup_reclaim(sc)) __count_vm_events(PGREFILL, nr_scanned); __count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned); spin_unlock_irq(&pgdat->lru_lock); while (!list_empty(&l_hold)) { cond_resched(); page = lru_to_page(&l_hold); list_del(&page->lru); if (unlikely(!page_evictable(page))) { putback_lru_page(page); continue; } if (unlikely(buffer_heads_over_limit)) { if (page_has_private(page) && trylock_page(page)) { if (page_has_private(page)) try_to_release_page(page, 0); unlock_page(page); } } if (page_referenced(page, 0, sc->target_mem_cgroup, &vm_flags)) { /* * Identify referenced, file-backed active pages and * give them one more trip around the active list. So * that executable code get better chances to stay in * memory under moderate memory pressure. Anon pages * are not likely to be evicted by use-once streaming * IO, plus JVM can create lots of anon VM_EXEC pages, * so we ignore them here. */ if ((vm_flags & VM_EXEC) && page_is_file_lru(page)) { nr_rotated += thp_nr_pages(page); list_add(&page->lru, &l_active); continue; } } ClearPageActive(page); /* we are de-activating */ SetPageWorkingset(page); list_add(&page->lru, &l_inactive); } /* * Move pages back to the lru list. */ spin_lock_irq(&pgdat->lru_lock); nr_activate = move_pages_to_lru(lruvec, &l_active); nr_deactivate = move_pages_to_lru(lruvec, &l_inactive); /* Keep all free pages in l_active list */ list_splice(&l_inactive, &l_active); __count_vm_events(PGDEACTIVATE, nr_deactivate); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); spin_unlock_irq(&pgdat->lru_lock); mem_cgroup_uncharge_list(&l_active); free_unref_page_list(&l_active); trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate, nr_deactivate, nr_rotated, sc->priority, file); } unsigned long reclaim_pages(struct list_head *page_list) { int nid = NUMA_NO_NODE; unsigned int nr_reclaimed = 0; LIST_HEAD(node_page_list); struct reclaim_stat dummy_stat; struct page *page; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .priority = DEF_PRIORITY, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, }; while (!list_empty(page_list)) { page = lru_to_page(page_list); if (nid == NUMA_NO_NODE) { nid = page_to_nid(page); INIT_LIST_HEAD(&node_page_list); } if (nid == page_to_nid(page)) { ClearPageActive(page); list_move(&page->lru, &node_page_list); continue; } nr_reclaimed += shrink_page_list(&node_page_list, NODE_DATA(nid), &sc, &dummy_stat, false); while (!list_empty(&node_page_list)) { page = lru_to_page(&node_page_list); list_del(&page->lru); putback_lru_page(page); } nid = NUMA_NO_NODE; } if (!list_empty(&node_page_list)) { nr_reclaimed += shrink_page_list(&node_page_list, NODE_DATA(nid), &sc, &dummy_stat, false); while (!list_empty(&node_page_list)) { page = lru_to_page(&node_page_list); list_del(&page->lru); putback_lru_page(page); } } return nr_reclaimed; } static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc) { if (is_active_lru(lru)) { if (sc->may_deactivate & (1 << is_file_lru(lru))) shrink_active_list(nr_to_scan, lruvec, sc, lru); else sc->skipped_deactivate = 1; return 0; } return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); } /* * The inactive anon list should be small enough that the VM never has * to do too much work. * * The inactive file list should be small enough to leave most memory * to the established workingset on the scan-resistant active list, * but large enough to avoid thrashing the aggregate readahead window. * * Both inactive lists should also be large enough that each inactive * page has a chance to be referenced again before it is reclaimed. * * If that fails and refaulting is observed, the inactive list grows. * * The inactive_ratio is the target ratio of ACTIVE to INACTIVE pages * on this LRU, maintained by the pageout code. An inactive_ratio * of 3 means 3:1 or 25% of the pages are kept on the inactive list. * * total target max * memory ratio inactive * ------------------------------------- * 10MB 1 5MB * 100MB 1 50MB * 1GB 3 250MB * 10GB 10 0.9GB * 100GB 31 3GB * 1TB 101 10GB * 10TB 320 32GB */ static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru) { enum lru_list active_lru = inactive_lru + LRU_ACTIVE; unsigned long inactive, active; unsigned long inactive_ratio; unsigned long gb; inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru); active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru); gb = (inactive + active) >> (30 - PAGE_SHIFT); if (gb) inactive_ratio = int_sqrt(10 * gb); else inactive_ratio = 1; return inactive * inactive_ratio < active; } enum scan_balance { SCAN_EQUAL, SCAN_FRACT, SCAN_ANON, SCAN_FILE, }; /* * Determine how aggressively the anon and file LRU lists should be * scanned. The relative value of each set of LRU lists is determined * by looking at the fraction of the pages scanned we did rotate back * onto the active list instead of evict. * * nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan * nr[2] = file inactive pages to scan; nr[3] = file active pages to scan */ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, unsigned long *nr) { struct mem_cgroup *memcg = lruvec_memcg(lruvec); unsigned long anon_cost, file_cost, total_cost; int swappiness = mem_cgroup_swappiness(memcg); u64 fraction[ANON_AND_FILE]; u64 denominator = 0; /* gcc */ enum scan_balance scan_balance; unsigned long ap, fp; enum lru_list lru; /* If we have no swap space, do not bother scanning anon pages. */ if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) { scan_balance = SCAN_FILE; goto out; } /* * Global reclaim will swap to prevent OOM even with no * swappiness, but memcg users want to use this knob to * disable swapping for individual groups completely when * using the memory controller's swap limit feature would be * too expensive. */ if (cgroup_reclaim(sc) && !swappiness) { scan_balance = SCAN_FILE; goto out; } /* * Do not apply any pressure balancing cleverness when the * system is close to OOM, scan both anon and file equally * (unless the swappiness setting disagrees with swapping). */ if (!sc->priority && swappiness) { scan_balance = SCAN_EQUAL; goto out; } /* * If the system is almost out of file pages, force-scan anon. */ if (sc->file_is_tiny) { scan_balance = SCAN_ANON; goto out; } /* * If there is enough inactive page cache, we do not reclaim * anything from the anonymous working right now. */ if (sc->cache_trim_mode) { scan_balance = SCAN_FILE; goto out; } scan_balance = SCAN_FRACT; /* * Calculate the pressure balance between anon and file pages. * * The amount of pressure we put on each LRU is inversely * proportional to the cost of reclaiming each list, as * determined by the share of pages that are refaulting, times * the relative IO cost of bringing back a swapped out * anonymous page vs reloading a filesystem page (swappiness). * * Although we limit that influence to ensure no list gets * left behind completely: at least a third of the pressure is * applied, before swappiness. * * With swappiness at 100, anon and file have equal IO cost. */ total_cost = sc->anon_cost + sc->file_cost; anon_cost = total_cost + sc->anon_cost; file_cost = total_cost + sc->file_cost; total_cost = anon_cost + file_cost; ap = swappiness * (total_cost + 1); ap /= anon_cost + 1; fp = (200 - swappiness) * (total_cost + 1); fp /= file_cost + 1; fraction[0] = ap; fraction[1] = fp; denominator = ap + fp; out: for_each_evictable_lru(lru) { int file = is_file_lru(lru); unsigned long lruvec_size; unsigned long low, min; unsigned long scan; lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); mem_cgroup_protection(sc->target_mem_cgroup, memcg, &min, &low); if (min || low) { /* * Scale a cgroup's reclaim pressure by proportioning * its current usage to its memory.low or memory.min * setting. * * This is important, as otherwise scanning aggression * becomes extremely binary -- from nothing as we * approach the memory protection threshold, to totally * nominal as we exceed it. This results in requiring * setting extremely liberal protection thresholds. It * also means we simply get no protection at all if we * set it too low, which is not ideal. * * If there is any protection in place, we reduce scan * pressure by how much of the total memory used is * within protection thresholds. * * There is one special case: in the first reclaim pass, * we skip over all groups that are within their low * protection. If that fails to reclaim enough pages to * satisfy the reclaim goal, we come back and override * the best-effort low protection. However, we still * ideally want to honor how well-behaved groups are in * that case instead of simply punishing them all * equally. As such, we reclaim them based on how much * memory they are using, reducing the scan pressure * again by how much of the total memory used is under * hard protection. */ unsigned long cgroup_size = mem_cgroup_size(memcg); unsigned long protection; /* memory.low scaling, make sure we retry before OOM */ if (!sc->memcg_low_reclaim && low > min) { protection = low; sc->memcg_low_skipped = 1; } else { protection = min; } /* Avoid TOCTOU with earlier protection check */ cgroup_size = max(cgroup_size, protection); scan = lruvec_size - lruvec_size * protection / (cgroup_size + 1); /* * Minimally target SWAP_CLUSTER_MAX pages to keep * reclaim moving forwards, avoiding decrementing * sc->priority further than desirable. */ scan = max(scan, SWAP_CLUSTER_MAX); } else { scan = lruvec_size; } scan >>= sc->priority; /* * If the cgroup's already been deleted, make sure to * scrape out the remaining cache. */ if (!scan && !mem_cgroup_online(memcg)) scan = min(lruvec_size, SWAP_CLUSTER_MAX); switch (scan_balance) { case SCAN_EQUAL: /* Scan lists relative to size */ break; case SCAN_FRACT: /* * Scan types proportional to swappiness and * their relative recent reclaim efficiency. * Make sure we don't miss the last page on * the offlined memory cgroups because of a * round-off error. */ scan = mem_cgroup_online(memcg) ? div64_u64(scan * fraction[file], denominator) : DIV64_U64_ROUND_UP(scan * fraction[file], denominator); break; case SCAN_FILE: case SCAN_ANON: /* Scan one type exclusively */ if ((scan_balance == SCAN_FILE) != file) scan = 0; break; default: /* Look ma, no brain */ BUG(); } nr[lru] = scan; } } static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { unsigned long nr[NR_LRU_LISTS]; unsigned long targets[NR_LRU_LISTS]; unsigned long nr_to_scan; enum lru_list lru; unsigned long nr_reclaimed = 0; unsigned long nr_to_reclaim = sc->nr_to_reclaim; struct blk_plug plug; bool scan_adjusted; get_scan_count(lruvec, sc, nr); /* Record the original scan target for proportional adjustments later */ memcpy(targets, nr, sizeof(nr)); /* * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal * event that can occur when there is little memory pressure e.g. * multiple streaming readers/writers. Hence, we do not abort scanning * when the requested number of pages are reclaimed when scanning at * DEF_PRIORITY on the assumption that the fact we are direct * reclaiming implies that kswapd is not keeping up and it is best to * do a batch of work at once. For memcg reclaim one check is made to * abort proportional reclaim if either the file or anon lru has already * dropped to zero at the first pass. */ scan_adjusted = (!cgroup_reclaim(sc) && !current_is_kswapd() && sc->priority == DEF_PRIORITY); blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { unsigned long nr_anon, nr_file, percentage; unsigned long nr_scanned; for_each_evictable_lru(lru) { if (nr[lru]) { nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX); nr[lru] -= nr_to_scan; nr_reclaimed += shrink_list(lru, nr_to_scan, lruvec, sc); } } cond_resched(); if (nr_reclaimed < nr_to_reclaim || scan_adjusted) continue; /* * For kswapd and memcg, reclaim at least the number of pages * requested. Ensure that the anon and file LRUs are scanned * proportionally what was requested by get_scan_count(). We * stop reclaiming one LRU and reduce the amount scanning * proportional to the original scan target. */ nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE]; nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON]; /* * It's just vindictive to attack the larger once the smaller * has gone to zero. And given the way we stop scanning the * smaller below, this makes sure that we only make one nudge * towards proportionality once we've got nr_to_reclaim. */ if (!nr_file || !nr_anon) break; if (nr_file > nr_anon) { unsigned long scan_target = targets[LRU_INACTIVE_ANON] + targets[LRU_ACTIVE_ANON] + 1; lru = LRU_BASE; percentage = nr_anon * 100 / scan_target; } else { unsigned long scan_target = targets[LRU_INACTIVE_FILE] + targets[LRU_ACTIVE_FILE] + 1; lru = LRU_FILE; percentage = nr_file * 100 / scan_target; } /* Stop scanning the smaller of the LRU */ nr[lru] = 0; nr[lru + LRU_ACTIVE] = 0; /* * Recalculate the other LRU scan count based on its original * scan target and the percentage scanning already complete */ lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); lru += LRU_ACTIVE; nr_scanned = targets[lru] - nr[lru]; nr[lru] = targets[lru] * (100 - percentage) / 100; nr[lru] -= min(nr[lru], nr_scanned); scan_adjusted = true; } blk_finish_plug(&plug); sc->nr_reclaimed += nr_reclaimed; /* * Even if we did not try to evict anon pages at all, we want to * rebalance the anon lru active/inactive ratio. */ if (total_swap_pages && inactive_is_low(lruvec, LRU_INACTIVE_ANON)) shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); } /* Use reclaim/compaction for costly allocs or under memory pressure */ static bool in_reclaim_compaction(struct scan_control *sc) { if (IS_ENABLED(CONFIG_COMPACTION) && sc->order && (sc->order > PAGE_ALLOC_COSTLY_ORDER || sc->priority < DEF_PRIORITY - 2)) return true; return false; } /* * Reclaim/compaction is used for high-order allocation requests. It reclaims * order-0 pages before compacting the zone. should_continue_reclaim() returns * true if more pages should be reclaimed such that when the page allocator * calls try_to_compact_pages() that it will have enough free pages to succeed. * It will give up earlier than that if there is difficulty reclaiming pages. */ static inline bool should_continue_reclaim(struct pglist_data *pgdat, unsigned long nr_reclaimed, struct scan_control *sc) { unsigned long pages_for_compaction; unsigned long inactive_lru_pages; int z; /* If not in reclaim/compaction mode, stop */ if (!in_reclaim_compaction(sc)) return false; /* * Stop if we failed to reclaim any pages from the last SWAP_CLUSTER_MAX * number of pages that were scanned. This will return to the caller * with the risk reclaim/compaction and the resulting allocation attempt * fails. In the past we have tried harder for __GFP_RETRY_MAYFAIL * allocations through requiring that the full LRU list has been scanned * first, by assuming that zero delta of sc->nr_scanned means full LRU * scan, but that approximation was wrong, and there were corner cases * where always a non-zero amount of pages were scanned. */ if (!nr_reclaimed) return false; /* If compaction would go ahead or the allocation would succeed, stop */ for (z = 0; z <= sc->reclaim_idx; z++) { struct zone *zone = &pgdat->node_zones[z]; if (!managed_zone(zone)) continue; switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) { case COMPACT_SUCCESS: case COMPACT_CONTINUE: return false; default: /* check next zone */ ; } } /* * If we have not reclaimed enough pages for compaction and the * inactive lists are large enough, continue reclaiming */ pages_for_compaction = compact_gap(sc->order); inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE); if (get_nr_swap_pages() > 0) inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON); return inactive_lru_pages > pages_for_compaction; } static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc) { struct mem_cgroup *target_memcg = sc->target_mem_cgroup; struct mem_cgroup *memcg; memcg = mem_cgroup_iter(target_memcg, NULL, NULL); do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); unsigned long reclaimed; unsigned long scanned; /* * This loop can become CPU-bound when target memcgs * aren't eligible for reclaim - either because they * don't have any reclaimable pages, or because their * memory is explicitly protected. Avoid soft lockups. */ cond_resched(); mem_cgroup_calculate_protection(target_memcg, memcg); if (mem_cgroup_below_min(memcg)) { /* * Hard protection. * If there is no reclaimable memory, OOM. */ continue; } else if (mem_cgroup_below_low(memcg)) { /* * Soft protection. * Respect the protection only as long as * there is an unprotected supply * of reclaimable memory from other cgroups. */ if (!sc->memcg_low_reclaim) { sc->memcg_low_skipped = 1; continue; } memcg_memory_event(memcg, MEMCG_LOW); } reclaimed = sc->nr_reclaimed; scanned = sc->nr_scanned; shrink_lruvec(lruvec, sc); shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority); /* Record the group's reclaim efficiency */ vmpressure(sc->gfp_mask, memcg, false, sc->nr_scanned - scanned, sc->nr_reclaimed - reclaimed); } while ((memcg = mem_cgroup_iter(target_memcg, memcg, NULL))); } static void shrink_node(pg_data_t *pgdat, struct scan_control *sc) { struct reclaim_state *reclaim_state = current->reclaim_state; unsigned long nr_reclaimed, nr_scanned; struct lruvec *target_lruvec; bool reclaimable = false; unsigned long file; target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat); again: memset(&sc->nr, 0, sizeof(sc->nr)); nr_reclaimed = sc->nr_reclaimed; nr_scanned = sc->nr_scanned; /* * Determine the scan balance between anon and file LRUs. */ spin_lock_irq(&pgdat->lru_lock); sc->anon_cost = target_lruvec->anon_cost; sc->file_cost = target_lruvec->file_cost; spin_unlock_irq(&pgdat->lru_lock); /* * Target desirable inactive:active list ratios for the anon * and file LRU lists. */ if (!sc->force_deactivate) { unsigned long refaults; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); if (refaults != target_lruvec->refaults[0] || inactive_is_low(target_lruvec, LRU_INACTIVE_ANON)) sc->may_deactivate |= DEACTIVATE_ANON; else sc->may_deactivate &= ~DEACTIVATE_ANON; /* * When refaults are being observed, it means a new * workingset is being established. Deactivate to get * rid of any stale active pages quickly. */ refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); if (refaults != target_lruvec->refaults[1] || inactive_is_low(target_lruvec, LRU_INACTIVE_FILE)) sc->may_deactivate |= DEACTIVATE_FILE; else sc->may_deactivate &= ~DEACTIVATE_FILE; } else sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE; /* * If we have plenty of inactive file pages that aren't * thrashing, try to reclaim those first before touching * anonymous pages. */ file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE); if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE)) sc->cache_trim_mode = 1; else sc->cache_trim_mode = 0; /* * Prevent the reclaimer from falling into the cache trap: as * cache pages start out inactive, every cache fault will tip * the scan balance towards the file LRU. And as the file LRU * shrinks, so does the window for rotation from references. * This means we have a runaway feedback loop where a tiny * thrashing file LRU becomes infinitely more attractive than * anon pages. Try to detect this based on file LRU size. */ if (!cgroup_reclaim(sc)) { unsigned long total_high_wmark = 0; unsigned long free, anon; int z; free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES); file = node_page_state(pgdat, NR_ACTIVE_FILE) + node_page_state(pgdat, NR_INACTIVE_FILE); for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = &pgdat->node_zones[z]; if (!managed_zone(zone)) continue; total_high_wmark += high_wmark_pages(zone); } /* * Consider anon: if that's low too, this isn't a * runaway file reclaim problem, but rather just * extreme pressure. Reclaim as per usual then. */ anon = node_page_state(pgdat, NR_INACTIVE_ANON); sc->file_is_tiny = file + free <= total_high_wmark && !(sc->may_deactivate & DEACTIVATE_ANON) && anon >> sc->priority; } shrink_node_memcgs(pgdat, sc); if (reclaim_state) { sc->nr_reclaimed += reclaim_state->reclaimed_slab; reclaim_state->reclaimed_slab = 0; } /* Record the subtree's reclaim efficiency */ vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true, sc->nr_scanned - nr_scanned, sc->nr_reclaimed - nr_reclaimed); if (sc->nr_reclaimed - nr_reclaimed) reclaimable = true; if (current_is_kswapd()) { /* * If reclaim is isolating dirty pages under writeback, * it implies that the long-lived page allocation rate * is exceeding the page laundering rate. Either the * global limits are not being effective at throttling * processes due to the page distribution throughout * zones or there is heavy usage of a slow backing * device. The only option is to throttle from reclaim * context which is not ideal as there is no guarantee * the dirtying process is throttled in the same way * balance_dirty_pages() manages. * * Once a node is flagged PGDAT_WRITEBACK, kswapd will * count the number of pages under pages flagged for * immediate reclaim and stall if any are encountered * in the nr_immediate check below. */ if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken) set_bit(PGDAT_WRITEBACK, &pgdat->flags); /* Allow kswapd to start writing pages during reclaim.*/ if (sc->nr.unqueued_dirty == sc->nr.file_taken) set_bit(PGDAT_DIRTY, &pgdat->flags); /* * If kswapd scans pages marked for immediate * reclaim and under writeback (nr_immediate), it * implies that pages are cycling through the LRU * faster than they are written so also forcibly stall. */ if (sc->nr.immediate) congestion_wait(BLK_RW_ASYNC, HZ/10); } /* * Tag a node/memcg as congested if all the dirty pages * scanned were backed by a congested BDI and * wait_iff_congested will stall. * * Legacy memcg will stall in page writeback so avoid forcibly * stalling in wait_iff_congested(). */ if ((current_is_kswapd() || (cgroup_reclaim(sc) && writeback_throttling_sane(sc))) && sc->nr.dirty && sc->nr.dirty == sc->nr.congested) set_bit(LRUVEC_CONGESTED, &target_lruvec->flags); /* * Stall direct reclaim for IO completions if underlying BDIs * and node is congested. Allow kswapd to continue until it * starts encountering unqueued dirty pages or cycling through * the LRU too quickly. */ if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && test_bit(LRUVEC_CONGESTED, &target_lruvec->flags)) wait_iff_congested(BLK_RW_ASYNC, HZ/10); if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, sc)) goto again; /* * Kswapd gives up on balancing particular nodes after too * many failures to reclaim anything from them and goes to * sleep. On reclaim progress, reset the failure counter. A * successful direct reclaim run will revive a dormant kswapd. */ if (reclaimable) pgdat->kswapd_failures = 0; } /* * Returns true if compaction should go ahead for a costly-order request, or * the allocation would already succeed without compaction. Return false if we * should reclaim first. */ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) { unsigned long watermark; enum compact_result suitable; suitable = compaction_suitable(zone, sc->order, 0, sc->reclaim_idx); if (suitable == COMPACT_SUCCESS) /* Allocation should succeed already. Don't reclaim. */ return true; if (suitable == COMPACT_SKIPPED) /* Compaction cannot yet proceed. Do reclaim. */ return false; /* * Compaction is already possible, but it takes time to run and there * are potentially other callers using the pages just freed. So proceed * with reclaim to make a buffer of free pages available to give * compaction a reasonable chance of completing and allocating the page. * Note that we won't actually reclaim the whole buffer in one attempt * as the target watermark in should_continue_reclaim() is lower. But if * we are already above the high+gap watermark, don't reclaim at all. */ watermark = high_wmark_pages(zone) + compact_gap(sc->order); return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx); } /* * This is the direct reclaim path, for page-allocating processes. We only * try to reclaim pages from zones which will satisfy the caller's allocation * request. * * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. */ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; gfp_t orig_mask; pg_data_t *last_pgdat = NULL; /* * If the number of buffer_heads in the machine exceeds the maximum * allowed level, force direct reclaim to scan the highmem zone as * highmem pages could be pinning lowmem pages storing buffer_heads */ orig_mask = sc->gfp_mask; if (buffer_heads_over_limit) { sc->gfp_mask |= __GFP_HIGHMEM; sc->reclaim_idx = gfp_zone(sc->gfp_mask); } for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, sc->nodemask) { /* * Take care memory controller reclaiming has small influence * to global LRU. */ if (!cgroup_reclaim(sc)) { if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL)) continue; /* * If we already have plenty of memory free for * compaction in this zone, don't free any more. * Even though compaction is invoked for any * non-zero order, only frequent costly order * reclamation is disruptive enough to become a * noticeable problem, like transparent huge * page allocations. */ if (IS_ENABLED(CONFIG_COMPACTION) && sc->order > PAGE_ALLOC_COSTLY_ORDER && compaction_ready(zone, sc)) { sc->compaction_ready = true; continue; } /* * Shrink each node in the zonelist once. If the * zonelist is ordered by zone (not the default) then a * node may be shrunk multiple times but in that case * the user prefers lower zones being preserved. */ if (zone->zone_pgdat == last_pgdat) continue; /* * This steals pages from memory cgroups over softlimit * and returns the number of reclaimed pages and * scanned pages. This works for global memory pressure * and balancing, not for a memcg's limit. */ nr_soft_scanned = 0; nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone->zone_pgdat, sc->order, sc->gfp_mask, &nr_soft_scanned); sc->nr_reclaimed += nr_soft_reclaimed; sc->nr_scanned += nr_soft_scanned; /* need some check for avoid more shrink_zone() */ } /* See comment about same check for global reclaim above */ if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; shrink_node(zone->zone_pgdat, sc); } /* * Restore to original mask to avoid the impact on the caller if we * promoted it to __GFP_HIGHMEM. */ sc->gfp_mask = orig_mask; } static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat) { struct lruvec *target_lruvec; unsigned long refaults; target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat); refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON); target_lruvec->refaults[0] = refaults; refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE); target_lruvec->refaults[1] = refaults; } /* * This is the main entry point to direct page reclaim. * * If a full scan of the inactive list fails to free enough memory then we * are "out of memory" and something needs to be killed. * * If the caller is !__GFP_FS then the probability of a failure is reasonably * high - the zone may be full of dirty or under-writeback pages, which this * caller can't do much about. We kick the writeback threads and take explicit * naps in the hope that some of these pages can be written. But if the * allocating task holds filesystem locks which prevent writeout this might not * work, and the allocation attempt will fail. * * returns: 0, if no pages reclaimed * else, the number of pages reclaimed */ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct scan_control *sc) { int initial_priority = sc->priority; pg_data_t *last_pgdat; struct zoneref *z; struct zone *zone; retry: delayacct_freepages_start(); if (!cgroup_reclaim(sc)) __count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1); do { vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, sc->priority); sc->nr_scanned = 0; shrink_zones(zonelist, sc); if (sc->nr_reclaimed >= sc->nr_to_reclaim) break; if (sc->compaction_ready) break; /* * If we're getting trouble reclaiming, start doing * writepage even in laptop mode. */ if (sc->priority < DEF_PRIORITY - 2) sc->may_writepage = 1; } while (--sc->priority >= 0); last_pgdat = NULL; for_each_zone_zonelist_nodemask(zone, z, zonelist, sc->reclaim_idx, sc->nodemask) { if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat); if (cgroup_reclaim(sc)) { struct lruvec *lruvec; lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, zone->zone_pgdat); clear_bit(LRUVEC_CONGESTED, &lruvec->flags); } } delayacct_freepages_end(); if (sc->nr_reclaimed) return sc->nr_reclaimed; /* Aborted reclaim to try compaction? don't OOM, then */ if (sc->compaction_ready) return 1; /* * We make inactive:active ratio decisions based on the node's * composition of memory, but a restrictive reclaim_idx or a * memory.low cgroup setting can exempt large amounts of * memory from reclaim. Neither of which are very common, so * instead of doing costly eligibility calculations of the * entire cgroup subtree up front, we assume the estimates are * good, and retry with forcible deactivation if that fails. */ if (sc->skipped_deactivate) { sc->priority = initial_priority; sc->force_deactivate = 1; sc->skipped_deactivate = 0; goto retry; } /* Untapped cgroup reserves? Don't OOM, retry. */ if (sc->memcg_low_skipped) { sc->priority = initial_priority; sc->force_deactivate = 0; sc->memcg_low_reclaim = 1; sc->memcg_low_skipped = 0; goto retry; } return 0; } static bool allow_direct_reclaim(pg_data_t *pgdat) { struct zone *zone; unsigned long pfmemalloc_reserve = 0; unsigned long free_pages = 0; int i; bool wmark_ok; if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; if (!managed_zone(zone)) continue; if (!zone_reclaimable_pages(zone)) continue; pfmemalloc_reserve += min_wmark_pages(zone); free_pages += zone_page_state(zone, NR_FREE_PAGES); } /* If there are no reserves (unexpected config) then do not throttle */ if (!pfmemalloc_reserve) return true; wmark_ok = free_pages > pfmemalloc_reserve / 2; /* kswapd must be awake if processes are being throttled */ if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { if (READ_ONCE(pgdat->kswapd_highest_zoneidx) > ZONE_NORMAL) WRITE_ONCE(pgdat->kswapd_highest_zoneidx, ZONE_NORMAL); wake_up_interruptible(&pgdat->kswapd_wait); } return wmark_ok; } /* * Throttle direct reclaimers if backing storage is backed by the network * and the PFMEMALLOC reserve for the preferred node is getting dangerously * depleted. kswapd will continue to make progress and wake the processes * when the low watermark is reached. * * Returns true if a fatal signal was delivered during throttling. If this * happens, the page allocator should not consider triggering the OOM killer. */ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, nodemask_t *nodemask) { struct zoneref *z; struct zone *zone; pg_data_t *pgdat = NULL; /* * Kernel threads should not be throttled as they may be indirectly * responsible for cleaning pages necessary for reclaim to make forward * progress. kjournald for example may enter direct reclaim while * committing a transaction where throttling it could forcing other * processes to block on log_wait_commit(). */ if (current->flags & PF_KTHREAD) goto out; /* * If a fatal signal is pending, this process should not throttle. * It should return quickly so it can exit and free its memory */ if (fatal_signal_pending(current)) goto out; /* * Check if the pfmemalloc reserves are ok by finding the first node * with a usable ZONE_NORMAL or lower zone. The expectation is that * GFP_KERNEL will be required for allocating network buffers when * swapping over the network so ZONE_HIGHMEM is unusable. * * Throttling is based on the first usable node and throttled processes * wait on a queue until kswapd makes progress and wakes them. There * is an affinity then between processes waking up and where reclaim * progress has been made assuming the process wakes on the same node. * More importantly, processes running on remote nodes will not compete * for remote pfmemalloc reserves and processes on different nodes * should make reasonable progress. */ for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nodemask) { if (zone_idx(zone) > ZONE_NORMAL) continue; /* Throttle based on the first usable node */ pgdat = zone->zone_pgdat; if (allow_direct_reclaim(pgdat)) goto out; break; } /* If no zone was usable by the allocation flags then do not throttle */ if (!pgdat) goto out; /* Account for the throttling */ count_vm_event(PGSCAN_DIRECT_THROTTLE); /* * If the caller cannot enter the filesystem, it's possible that it * is due to the caller holding an FS lock or performing a journal * transaction in the case of a filesystem like ext[3|4]. In this case, * it is not safe to block on pfmemalloc_wait as kswapd could be * blocked waiting on the same lock. Instead, throttle for up to a * second before continuing. */ if (!(gfp_mask & __GFP_FS)) { wait_event_interruptible_timeout(pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat), HZ); goto check_pending; } /* Throttle until kswapd wakes the process */ wait_event_killable(zone->zone_pgdat->pfmemalloc_wait, allow_direct_reclaim(pgdat)); check_pending: if (fatal_signal_pending(current)) return true; out: return false; } unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *nodemask) { unsigned long nr_reclaimed; struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .gfp_mask = current_gfp_context(gfp_mask), .reclaim_idx = gfp_zone(gfp_mask), .order = order, .nodemask = nodemask, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = 1, }; /* * scan_control uses s8 fields for order, priority, and reclaim_idx. * Confirm they are large enough for max values. */ BUILD_BUG_ON(MAX_ORDER > S8_MAX); BUILD_BUG_ON(DEF_PRIORITY > S8_MAX); BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX); /* * Do not enter reclaim if fatal signal was delivered while throttled. * 1 is returned so that the page allocator does not OOM kill at this * point. */ if (throttle_direct_reclaim(sc.gfp_mask, zonelist, nodemask)) return 1; set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); trace_mm_vmscan_direct_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; } #ifdef CONFIG_MEMCG /* Only used by soft limit reclaim. Do not reuse for anything else. */ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned) { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); struct scan_control sc = { .nr_to_reclaim = SWAP_CLUSTER_MAX, .target_mem_cgroup = memcg, .may_writepage = !laptop_mode, .may_unmap = 1, .reclaim_idx = MAX_NR_ZONES - 1, .may_swap = !noswap, }; WARN_ON_ONCE(!current->reclaim_state); sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order, sc.gfp_mask); /* * NOTE: Although we can get the priority field, using it * here is not a good idea, since it limits the pages we can scan. * if we don't reclaim here, the shrink_node from balance_pgdat * will pick up pages from other mem cgroup's as well. We hack * the priority and make it zero. */ shrink_lruvec(lruvec, &sc); trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); *nr_scanned = sc.nr_scanned; return sc.nr_reclaimed; } unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, bool may_swap) { unsigned long nr_reclaimed; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK), .reclaim_idx = MAX_NR_ZONES - 1, .target_mem_cgroup = memcg, .priority = DEF_PRIORITY, .may_writepage = !laptop_mode, .may_unmap = 1, .may_swap = may_swap, }; /* * Traverse the ZONELIST_FALLBACK zonelist of the current node to put * equal pressure on all the nodes. This is based on the assumption that * the reclaim does not bail out early. */ struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); set_task_reclaim_state(current, &sc.reclaim_state); trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); memalloc_noreclaim_restore(noreclaim_flag); trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; } #endif static void age_active_anon(struct pglist_data *pgdat, struct scan_control *sc) { struct mem_cgroup *memcg; struct lruvec *lruvec; if (!total_swap_pages) return; lruvec = mem_cgroup_lruvec(NULL, pgdat); if (!inactive_is_low(lruvec, LRU_INACTIVE_ANON)) return; memcg = mem_cgroup_iter(NULL, NULL, NULL); do { lruvec = mem_cgroup_lruvec(memcg, pgdat); shrink_active_list(SWAP_CLUSTER_MAX, lruvec, sc, LRU_ACTIVE_ANON); memcg = mem_cgroup_iter(NULL, memcg, NULL); } while (memcg); } static bool pgdat_watermark_boosted(pg_data_t *pgdat, int highest_zoneidx) { int i; struct zone *zone; /* * Check for watermark boosts top-down as the higher zones * are more likely to be boosted. Both watermarks and boosts * should not be checked at the same time as reclaim would * start prematurely when there is no boosting and a lower * zone is balanced. */ for (i = highest_zoneidx; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; if (zone->watermark_boost) return true; } return false; } /* * Returns true if there is an eligible zone balanced for the request order * and highest_zoneidx */ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long mark = -1; struct zone *zone; /* * Check watermarks bottom-up as lower zones are more likely to * meet watermarks. */ for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; mark = high_wmark_pages(zone); if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx)) return true; } /* * If a node has no populated zone within highest_zoneidx, it does not * need balancing by definition. This can happen if a zone-restricted * allocation tries to wake a remote kswapd. */ if (mark == -1) return true; return false; } /* Clear pgdat state for congested, dirty or under writeback. */ static void clear_pgdat_congested(pg_data_t *pgdat) { struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat); clear_bit(LRUVEC_CONGESTED, &lruvec->flags); clear_bit(PGDAT_DIRTY, &pgdat->flags); clear_bit(PGDAT_WRITEBACK, &pgdat->flags); } /* * Prepare kswapd for sleeping. This verifies that there are no processes * waiting in throttle_direct_reclaim() and that watermarks have been met. * * Returns true if kswapd is ready to sleep */ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int highest_zoneidx) { /* * The throttled processes are normally woken up in balance_pgdat() as * soon as allow_direct_reclaim() is true. But there is a potential * race between when kswapd checks the watermarks and a process gets * throttled. There is also a potential race if processes get * throttled, kswapd wakes, a large process exits thereby balancing the * zones, which causes kswapd to exit balance_pgdat() before reaching * the wake up checks. If kswapd is going to sleep, no process should * be sleeping on pfmemalloc_wait, so wake them now if necessary. If * the wake up is premature, processes will wake kswapd and get * throttled again. The difference from wake ups in balance_pgdat() is * that here we are under prepare_to_wait(). */ if (waitqueue_active(&pgdat->pfmemalloc_wait)) wake_up_all(&pgdat->pfmemalloc_wait); /* Hopeless node, leave it to direct reclaim */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) return true; if (pgdat_balanced(pgdat, order, highest_zoneidx)) { clear_pgdat_congested(pgdat); return true; } return false; } /* * kswapd shrinks a node of pages that are at or below the highest usable * zone that is currently unbalanced. * * Returns true if kswapd scanned at least the requested number of pages to * reclaim or if the lack of progress was due to pages under writeback. * This is used to determine if the scanning priority needs to be raised. */ static bool kswapd_shrink_node(pg_data_t *pgdat, struct scan_control *sc) { struct zone *zone; int z; /* Reclaim a number of pages proportional to the number of zones */ sc->nr_to_reclaim = 0; for (z = 0; z <= sc->reclaim_idx; z++) { zone = pgdat->node_zones + z; if (!managed_zone(zone)) continue; sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX); } /* * Historically care was taken to put equal pressure on all zones but * now pressure is applied based on node LRU order. */ shrink_node(pgdat, sc); /* * Fragmentation may mean that the system cannot be rebalanced for * high-order allocations. If twice the allocation size has been * reclaimed then recheck watermarks only at order-0 to prevent * excessive reclaim. Assume that a process requested a high-order * can direct reclaim/compact. */ if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order)) sc->order = 0; return sc->nr_scanned >= sc->nr_to_reclaim; } /* * For kswapd, balance_pgdat() will reclaim pages across a node from zones * that are eligible for use by the caller until at least one zone is * balanced. * * Returns the order kswapd finished reclaiming at. * * kswapd scans the zones in the highmem->normal->dma direction. It skips * zones which have free_pages > high_wmark_pages(zone), but once a zone is * found to have free_pages <= high_wmark_pages(zone), any page in that zone * or lower is eligible for reclaim until at least one usable zone is * balanced. */ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx) { int i; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; unsigned long pflags; unsigned long nr_boost_reclaim; unsigned long zone_boosts[MAX_NR_ZONES] = { 0, }; bool boosted; struct zone *zone; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .order = order, .may_unmap = 1, }; set_task_reclaim_state(current, &sc.reclaim_state); psi_memstall_enter(&pflags); __fs_reclaim_acquire(); count_vm_event(PAGEOUTRUN); /* * Account for the reclaim boost. Note that the zone boost is left in * place so that parallel allocations that are near the watermark will * stall or direct reclaim until kswapd is finished. */ nr_boost_reclaim = 0; for (i = 0; i <= highest_zoneidx; i++) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; nr_boost_reclaim += zone->watermark_boost; zone_boosts[i] = zone->watermark_boost; } boosted = nr_boost_reclaim; restart: sc.priority = DEF_PRIORITY; do { unsigned long nr_reclaimed = sc.nr_reclaimed; bool raise_priority = true; bool balanced; bool ret; sc.reclaim_idx = highest_zoneidx; /* * If the number of buffer_heads exceeds the maximum allowed * then consider reclaiming from all zones. This has a dual * purpose -- on 64-bit systems it is expected that * buffer_heads are stripped during active rotation. On 32-bit * systems, highmem pages can pin lowmem memory and shrinking * buffers can relieve lowmem pressure. Reclaim may still not * go ahead if all eligible zones for the original allocation * request are balanced to avoid excessive reclaim from kswapd. */ if (buffer_heads_over_limit) { for (i = MAX_NR_ZONES - 1; i >= 0; i--) { zone = pgdat->node_zones + i; if (!managed_zone(zone)) continue; sc.reclaim_idx = i; break; } } /* * If the pgdat is imbalanced then ignore boosting and preserve * the watermarks for a later time and restart. Note that the * zone watermarks will be still reset at the end of balancing * on the grounds that the normal reclaim should be enough to * re-evaluate if boosting is required when kswapd next wakes. */ balanced = pgdat_balanced(pgdat, sc.order, highest_zoneidx); if (!balanced && nr_boost_reclaim) { nr_boost_reclaim = 0; goto restart; } /* * If boosting is not active then only reclaim if there are no * eligible zones. Note that sc.reclaim_idx is not used as * buffer_heads_over_limit may have adjusted it. */ if (!nr_boost_reclaim && balanced) goto out; /* Limit the priority of boosting to avoid reclaim writeback */ if (nr_boost_reclaim && sc.priority == DEF_PRIORITY - 2) raise_priority = false; /* * Do not writeback or swap pages for boosted reclaim. The * intent is to relieve pressure not issue sub-optimal IO * from reclaim context. If no pages are reclaimed, the * reclaim will be aborted. */ sc.may_writepage = !laptop_mode && !nr_boost_reclaim; sc.may_swap = !nr_boost_reclaim; /* * Do some background aging of the anon list, to give * pages a chance to be referenced before reclaiming. All * pages are rotated regardless of classzone as this is * about consistent aging. */ age_active_anon(pgdat, &sc); /* * If we're getting trouble reclaiming, start doing writepage * even in laptop mode. */ if (sc.priority < DEF_PRIORITY - 2) sc.may_writepage = 1; /* Call soft limit reclaim before calling shrink_node. */ sc.nr_scanned = 0; nr_soft_scanned = 0; nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(pgdat, sc.order, sc.gfp_mask, &nr_soft_scanned); sc.nr_reclaimed += nr_soft_reclaimed; /* * There should be no need to raise the scanning priority if * enough pages are already being scanned that that high * watermark would be met at 100% efficiency. */ if (kswapd_shrink_node(pgdat, &sc)) raise_priority = false; /* * If the low watermark is met there is no need for processes * to be throttled on pfmemalloc_wait as they should not be * able to safely make forward progress. Wake them */ if (waitqueue_active(&pgdat->pfmemalloc_wait) && allow_direct_reclaim(pgdat)) wake_up_all(&pgdat->pfmemalloc_wait); /* Check if kswapd should be suspending */ __fs_reclaim_release(); ret = try_to_freeze(); __fs_reclaim_acquire(); if (ret || kthread_should_stop()) break; /* * Raise priority if scanning rate is too low or there was no * progress in reclaiming pages */ nr_reclaimed = sc.nr_reclaimed - nr_reclaimed; nr_boost_reclaim -= min(nr_boost_reclaim, nr_reclaimed); /* * If reclaim made no progress for a boost, stop reclaim as * IO cannot be queued and it could be an infinite loop in * extreme circumstances. */ if (nr_boost_reclaim && !nr_reclaimed) break; if (raise_priority || !nr_reclaimed) sc.priority--; } while (sc.priority >= 1); if (!sc.nr_reclaimed) pgdat->kswapd_failures++; out: /* If reclaim was boosted, account for the reclaim done in this pass */ if (boosted) { unsigned long flags; for (i = 0; i <= highest_zoneidx; i++) { if (!zone_boosts[i]) continue; /* Increments are under the zone lock */ zone = pgdat->node_zones + i; spin_lock_irqsave(&zone->lock, flags); zone->watermark_boost -= min(zone->watermark_boost, zone_boosts[i]); spin_unlock_irqrestore(&zone->lock, flags); } /* * As there is now likely space, wakeup kcompact to defragment * pageblocks. */ wakeup_kcompactd(pgdat, pageblock_order, highest_zoneidx); } snapshot_refaults(NULL, pgdat); __fs_reclaim_release(); psi_memstall_leave(&pflags); set_task_reclaim_state(current, NULL); /* * Return the order kswapd stopped reclaiming at as * prepare_kswapd_sleep() takes it into account. If another caller * entered the allocator slow path while kswapd was awake, order will * remain at the higher level. */ return sc.order; } /* * The pgdat->kswapd_highest_zoneidx is used to pass the highest zone index to * be reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is * not a valid index then either kswapd runs for first time or kswapd couldn't * sleep after previous reclaim attempt (node is still unbalanced). In that * case return the zone index of the previous kswapd reclaim cycle. */ static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat, enum zone_type prev_highest_zoneidx) { enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); return curr_idx == MAX_NR_ZONES ? prev_highest_zoneidx : curr_idx; } static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, unsigned int highest_zoneidx) { long remaining = 0; DEFINE_WAIT(wait); if (freezing(current) || kthread_should_stop()) return; prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); /* * Try to sleep for a short interval. Note that kcompactd will only be * woken if it is possible to sleep for a short interval. This is * deliberate on the assumption that if reclaim cannot keep an * eligible zone balanced that it's also unlikely that compaction will * succeed. */ if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { /* * Compaction records what page blocks it recently failed to * isolate pages from and skips them in the future scanning. * When kswapd is going to sleep, it is reasonable to assume * that pages and compaction may succeed so reset the cache. */ reset_isolation_suitable(pgdat); /* * We have freed the memory, now we should compact it to make * allocation of the requested order possible. */ wakeup_kcompactd(pgdat, alloc_order, highest_zoneidx); remaining = schedule_timeout(HZ/10); /* * If woken prematurely then reset kswapd_highest_zoneidx and * order. The values will either be from a wakeup request or * the previous request that slept prematurely. */ if (remaining) { WRITE_ONCE(pgdat->kswapd_highest_zoneidx, kswapd_highest_zoneidx(pgdat, highest_zoneidx)); if (READ_ONCE(pgdat->kswapd_order) < reclaim_order) WRITE_ONCE(pgdat->kswapd_order, reclaim_order); } finish_wait(&pgdat->kswapd_wait, &wait); prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); } /* * After a short sleep, check if it was a premature sleep. If not, then * go fully to sleep until explicitly woken up. */ if (!remaining && prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) { trace_mm_vmscan_kswapd_sleep(pgdat->node_id); /* * vmstat counters are not perfectly accurate and the estimated * value for counters such as NR_FREE_PAGES can deviate from the * true value by nr_online_cpus * threshold. To avoid the zone * watermarks being breached while under pressure, we reduce the * per-cpu vmstat threshold while kswapd is awake and restore * them before going back to sleep. */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); if (!kthread_should_stop()) schedule(); set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold); } else { if (remaining) count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY); else count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY); } finish_wait(&pgdat->kswapd_wait, &wait); } /* * The background pageout daemon, started as a kernel thread * from the init process. * * This basically trickles out pages so that we have _some_ * free memory available even if there is no other activity * that frees anything up. This is needed for things like routing * etc, where we otherwise might have all activity going on in * asynchronous contexts that cannot page things out. * * If there are applications that are active memory-allocators * (most normal use), this basically shouldn't matter. */ static int kswapd(void *p) { unsigned int alloc_order, reclaim_order; unsigned int highest_zoneidx = MAX_NR_ZONES - 1; pg_data_t *pgdat = (pg_data_t*)p; struct task_struct *tsk = current; const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id); if (!cpumask_empty(cpumask)) set_cpus_allowed_ptr(tsk, cpumask); /* * Tell the memory management that we're a "memory allocator", * and that if we need more memory we should get access to it * regardless (see "__alloc_pages()"). "kswapd" should * never get caught in the normal page freeing logic. * * (Kswapd normally doesn't need memory anyway, but sometimes * you need a small amount of memory in order to be able to * page out something else, and this flag essentially protects * us from recursively trying to free more memory as we're * trying to free the first piece of memory in the first place). */ tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; set_freezable(); WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); for ( ; ; ) { bool ret; alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx); kswapd_try_sleep: kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order, highest_zoneidx); /* Read the new order and highest_zoneidx */ alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); highest_zoneidx = kswapd_highest_zoneidx(pgdat, highest_zoneidx); WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); ret = try_to_freeze(); if (kthread_should_stop()) break; /* * We can speed up thawing tasks if we don't call balance_pgdat * after returning from the refrigerator */ if (ret) continue; /* * Reclaim begins at the requested order but if a high-order * reclaim fails then kswapd falls back to reclaiming for * order-0. If that happens, kswapd will consider sleeping * for the order it finished reclaiming at (reclaim_order) * but kcompactd is woken to compact for the original * request (alloc_order). */ trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx, alloc_order); reclaim_order = balance_pgdat(pgdat, alloc_order, highest_zoneidx); if (reclaim_order < alloc_order) goto kswapd_try_sleep; } tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD); return 0; } /* * A zone is low on free memory or too fragmented for high-order memory. If * kswapd should reclaim (direct reclaim is deferred), wake it up for the zone's * pgdat. It will wake up kcompactd after reclaiming memory. If kswapd reclaim * has failed or is not needed, still wake up kcompactd if only compaction is * needed. */ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, enum zone_type highest_zoneidx) { pg_data_t *pgdat; enum zone_type curr_idx; if (!managed_zone(zone)) return; if (!cpuset_zone_allowed(zone, gfp_flags)) return; pgdat = zone->zone_pgdat; curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx); if (curr_idx == MAX_NR_ZONES || curr_idx < highest_zoneidx) WRITE_ONCE(pgdat->kswapd_highest_zoneidx, highest_zoneidx); if (READ_ONCE(pgdat->kswapd_order) < order) WRITE_ONCE(pgdat->kswapd_order, order); if (!waitqueue_active(&pgdat->kswapd_wait)) return; /* Hopeless node, leave it to direct reclaim if possible */ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES || (pgdat_balanced(pgdat, order, highest_zoneidx) && !pgdat_watermark_boosted(pgdat, highest_zoneidx))) { /* * There may be plenty of free memory available, but it's too * fragmented for high-order allocations. Wake up kcompactd * and rely on compaction_suitable() to determine if it's * needed. If it fails, it will defer subsequent attempts to * ratelimit its work. */ if (!(gfp_flags & __GFP_DIRECT_RECLAIM)) wakeup_kcompactd(pgdat, order, highest_zoneidx); return; } trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, highest_zoneidx, order, gfp_flags); wake_up_interruptible(&pgdat->kswapd_wait); } #ifdef CONFIG_HIBERNATION /* * Try to free `nr_to_reclaim' of memory, system-wide, and return the number of * freed pages. * * Rather than trying to age LRUs the aim is to preserve the overall * LRU order by reclaiming preferentially * inactive > active > active referenced > active mapped */ unsigned long shrink_all_memory(unsigned long nr_to_reclaim) { struct scan_control sc = { .nr_to_reclaim = nr_to_reclaim, .gfp_mask = GFP_HIGHUSER_MOVABLE, .reclaim_idx = MAX_NR_ZONES - 1, .priority = DEF_PRIORITY, .may_writepage = 1, .may_unmap = 1, .may_swap = 1, .hibernation_mode = 1, }; struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask); unsigned long nr_reclaimed; unsigned int noreclaim_flag; fs_reclaim_acquire(sc.gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); set_task_reclaim_state(current, &sc.reclaim_state); nr_reclaimed = do_try_to_free_pages(zonelist, &sc); set_task_reclaim_state(current, NULL); memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); return nr_reclaimed; } #endif /* CONFIG_HIBERNATION */ /* * This kswapd start function will be called by init and node-hot-add. * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added. */ int kswapd_run(int nid) { pg_data_t *pgdat = NODE_DATA(nid); int ret = 0; if (pgdat->kswapd) return 0; pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid); if (IS_ERR(pgdat->kswapd)) { /* failure at boot is fatal */ BUG_ON(system_state < SYSTEM_RUNNING); pr_err("Failed to start kswapd on node %d\n", nid); ret = PTR_ERR(pgdat->kswapd); pgdat->kswapd = NULL; } return ret; } /* * Called by memory hotplug when all memory in a node is offlined. Caller must * hold mem_hotplug_begin/end(). */ void kswapd_stop(int nid) { struct task_struct *kswapd = NODE_DATA(nid)->kswapd; if (kswapd) { kthread_stop(kswapd); NODE_DATA(nid)->kswapd = NULL; } } static int __init kswapd_init(void) { int nid; swap_setup(); for_each_node_state(nid, N_MEMORY) kswapd_run(nid); return 0; } module_init(kswapd_init) #ifdef CONFIG_NUMA /* * Node reclaim mode * * If non-zero call node_reclaim when the number of free pages falls below * the watermarks. */ int node_reclaim_mode __read_mostly; /* * These bit locations are exposed in the vm.zone_reclaim_mode sysctl * ABI. New bits are OK, but existing bits can never change. */ #define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */ #define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */ #define RECLAIM_UNMAP (1<<2) /* Unmap pages during reclaim */ /* * Priority for NODE_RECLAIM. This determines the fraction of pages * of a node considered for each zone_reclaim. 4 scans 1/16th of * a zone. */ #define NODE_RECLAIM_PRIORITY 4 /* * Percentage of pages in a zone that must be unmapped for node_reclaim to * occur. */ int sysctl_min_unmapped_ratio = 1; /* * If the number of slab pages in a zone grows beyond this percentage then * slab reclaim needs to occur. */ int sysctl_min_slab_ratio = 5; static inline unsigned long node_unmapped_file_pages(struct pglist_data *pgdat) { unsigned long file_mapped = node_page_state(pgdat, NR_FILE_MAPPED); unsigned long file_lru = node_page_state(pgdat, NR_INACTIVE_FILE) + node_page_state(pgdat, NR_ACTIVE_FILE); /* * It's possible for there to be more file mapped pages than * accounted for by the pages on the file LRU lists because * tmpfs pages accounted for as ANON can also be FILE_MAPPED */ return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0; } /* Work out how many page cache pages we can reclaim in this reclaim_mode */ static unsigned long node_pagecache_reclaimable(struct pglist_data *pgdat) { unsigned long nr_pagecache_reclaimable; unsigned long delta = 0; /* * If RECLAIM_UNMAP is set, then all file pages are considered * potentially reclaimable. Otherwise, we have to worry about * pages like swapcache and node_unmapped_file_pages() provides * a better estimate */ if (node_reclaim_mode & RECLAIM_UNMAP) nr_pagecache_reclaimable = node_page_state(pgdat, NR_FILE_PAGES); else nr_pagecache_reclaimable = node_unmapped_file_pages(pgdat); /* If we can't clean pages, remove dirty pages from consideration */ if (!(node_reclaim_mode & RECLAIM_WRITE)) delta += node_page_state(pgdat, NR_FILE_DIRTY); /* Watch for any possible underflows due to delta */ if (unlikely(delta > nr_pagecache_reclaimable)) delta = nr_pagecache_reclaimable; return nr_pagecache_reclaimable - delta; } /* * Try to free up some pages from this node through reclaim. */ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { /* Minimum pages needed in order to stay on node */ const unsigned long nr_pages = 1 << order; struct task_struct *p = current; unsigned int noreclaim_flag; struct scan_control sc = { .nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = current_gfp_context(gfp_mask), .order = order, .priority = NODE_RECLAIM_PRIORITY, .may_writepage = !!(node_reclaim_mode & RECLAIM_WRITE), .may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP), .may_swap = 1, .reclaim_idx = gfp_zone(gfp_mask), }; trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order, sc.gfp_mask); cond_resched(); fs_reclaim_acquire(sc.gfp_mask); /* * We need to be able to allocate from the reserves for RECLAIM_UNMAP * and we also need to be able to write out pages for RECLAIM_WRITE * and RECLAIM_UNMAP. */ noreclaim_flag = memalloc_noreclaim_save(); p->flags |= PF_SWAPWRITE; set_task_reclaim_state(p, &sc.reclaim_state); if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages) { /* * Free memory by calling shrink node with increasing * priorities until we have enough memory freed. */ do { shrink_node(pgdat, &sc); } while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0); } set_task_reclaim_state(p, NULL); current->flags &= ~PF_SWAPWRITE; memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(sc.gfp_mask); trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed); return sc.nr_reclaimed >= nr_pages; } int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order) { int ret; /* * Node reclaim reclaims unmapped file backed pages and * slab pages if we are over the defined limits. * * A small portion of unmapped file backed pages is needed for * file I/O otherwise pages read by file I/O will be immediately * thrown out if the node is overallocated. So we do not reclaim * if less than a specified percentage of the node is used by * unmapped file backed pages. */ if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages && node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <= pgdat->min_slab_pages) return NODE_RECLAIM_FULL; /* * Do not scan if the allocation should not be delayed. */ if (!gfpflags_allow_blocking(gfp_mask) || (current->flags & PF_MEMALLOC)) return NODE_RECLAIM_NOSCAN; /* * Only run node reclaim on the local node or on nodes that do not * have associated processors. This will favor the local processor * over remote processors and spread off node memory allocations * as wide as possible. */ if (node_state(pgdat->node_id, N_CPU) && pgdat->node_id != numa_node_id()) return NODE_RECLAIM_NOSCAN; if (test_and_set_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags)) return NODE_RECLAIM_NOSCAN; ret = __node_reclaim(pgdat, gfp_mask, order); clear_bit(PGDAT_RECLAIM_LOCKED, &pgdat->flags); if (!ret) count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED); return ret; } #endif /** * check_move_unevictable_pages - check pages for evictability and move to * appropriate zone lru list * @pvec: pagevec with lru pages to check * * Checks pages for evictability, if an evictable page is in the unevictable * lru list, moves it to the appropriate evictable lru list. This function * should be only used for lru pages. */ void check_move_unevictable_pages(struct pagevec *pvec) { struct lruvec *lruvec; struct pglist_data *pgdat = NULL; int pgscanned = 0; int pgrescued = 0; int i; for (i = 0; i < pvec->nr; i++) { struct page *page = pvec->pages[i]; struct pglist_data *pagepgdat = page_pgdat(page); int nr_pages; if (PageTransTail(page)) continue; nr_pages = thp_nr_pages(page); pgscanned += nr_pages; if (pagepgdat != pgdat) { if (pgdat) spin_unlock_irq(&pgdat->lru_lock); pgdat = pagepgdat; spin_lock_irq(&pgdat->lru_lock); } lruvec = mem_cgroup_page_lruvec(page, pgdat); if (!PageLRU(page) || !PageUnevictable(page)) continue; if (page_evictable(page)) { enum lru_list lru = page_lru_base_type(page); VM_BUG_ON_PAGE(PageActive(page), page); ClearPageUnevictable(page); del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE); add_page_to_lru_list(page, lruvec, lru); pgrescued += nr_pages; } } if (pgdat) { __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); spin_unlock_irq(&pgdat->lru_lock); } } EXPORT_SYMBOL_GPL(check_move_unevictable_pages);
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 /* SPDX-License-Identifier: GPL-2.0 */ /* Freezer declarations */ #ifndef FREEZER_H_INCLUDED #define FREEZER_H_INCLUDED #include <linux/debug_locks.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/atomic.h> #ifdef CONFIG_FREEZER extern atomic_t system_freezing_cnt; /* nr of freezing conds in effect */ extern bool pm_freezing; /* PM freezing in effect */ extern bool pm_nosig_freezing; /* PM nosig freezing in effect */ /* * Timeout for stopping processes */ extern unsigned int freeze_timeout_msecs; /* * Check if a process has been frozen */ static inline bool frozen(struct task_struct *p) { return p->flags & PF_FROZEN; } extern bool freezing_slow_path(struct task_struct *p); /* * Check if there is a request to freeze a process */ static inline bool freezing(struct task_struct *p) { if (likely(!atomic_read(&system_freezing_cnt))) return false; return freezing_slow_path(p); } /* Takes and releases task alloc lock using task_lock() */ extern void __thaw_task(struct task_struct *t); extern bool __refrigerator(bool check_kthr_stop); extern int freeze_processes(void); extern int freeze_kernel_threads(void); extern void thaw_processes(void); extern void thaw_kernel_threads(void); /* * DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION * If try_to_freeze causes a lockdep warning it means the caller may deadlock */ static inline bool try_to_freeze_unsafe(void) { might_sleep(); if (likely(!freezing(current))) return false; return __refrigerator(false); } static inline bool try_to_freeze(void) { if (!(current->flags & PF_NOFREEZE)) debug_check_no_locks_held(); return try_to_freeze_unsafe(); } extern bool freeze_task(struct task_struct *p); extern bool set_freezable(void); #ifdef CONFIG_CGROUP_FREEZER extern bool cgroup_freezing(struct task_struct *task); #else /* !CONFIG_CGROUP_FREEZER */ static inline bool cgroup_freezing(struct task_struct *task) { return false; } #endif /* !CONFIG_CGROUP_FREEZER */ /* * The PF_FREEZER_SKIP flag should be set by a vfork parent right before it * calls wait_for_completion(&vfork) and reset right after it returns from this * function. Next, the parent should call try_to_freeze() to freeze itself * appropriately in case the child has exited before the freezing of tasks is * complete. However, we don't want kernel threads to be frozen in unexpected * places, so we allow them to block freeze_processes() instead or to set * PF_NOFREEZE if needed. Fortunately, in the ____call_usermodehelper() case the * parent won't really block freeze_processes(), since ____call_usermodehelper() * (the child) does a little before exec/exit and it can't be frozen before * waking up the parent. */ /** * freezer_do_not_count - tell freezer to ignore %current * * Tell freezers to ignore the current task when determining whether the * target frozen state is reached. IOW, the current task will be * considered frozen enough by freezers. * * The caller shouldn't do anything which isn't allowed for a frozen task * until freezer_cont() is called. Usually, freezer[_do_not]_count() pair * wrap a scheduling operation and nothing much else. */ static inline void freezer_do_not_count(void) { current->flags |= PF_FREEZER_SKIP; } /** * freezer_count - tell freezer to stop ignoring %current * * Undo freezer_do_not_count(). It tells freezers that %current should be * considered again and tries to freeze if freezing condition is already in * effect. */ static inline void freezer_count(void) { current->flags &= ~PF_FREEZER_SKIP; /* * If freezing is in progress, the following paired with smp_mb() * in freezer_should_skip() ensures that either we see %true * freezing() or freezer_should_skip() sees !PF_FREEZER_SKIP. */ smp_mb(); try_to_freeze(); } /* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ static inline void freezer_count_unsafe(void) { current->flags &= ~PF_FREEZER_SKIP; smp_mb(); try_to_freeze_unsafe(); } /** * freezer_should_skip - whether to skip a task when determining frozen * state is reached * @p: task in quesion * * This function is used by freezers after establishing %true freezing() to * test whether a task should be skipped when determining the target frozen * state is reached. IOW, if this function returns %true, @p is considered * frozen enough. */ static inline bool freezer_should_skip(struct task_struct *p) { /* * The following smp_mb() paired with the one in freezer_count() * ensures that either freezer_count() sees %true freezing() or we * see cleared %PF_FREEZER_SKIP and return %false. This makes it * impossible for a task to slip frozen state testing after * clearing %PF_FREEZER_SKIP. */ smp_mb(); return p->flags & PF_FREEZER_SKIP; } /* * These functions are intended to be used whenever you want allow a sleeping * task to be frozen. Note that neither return any clear indication of * whether a freeze event happened while in this function. */ /* Like schedule(), but should not block the freezer. */ static inline void freezable_schedule(void) { freezer_do_not_count(); schedule(); freezer_count(); } /* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ static inline void freezable_schedule_unsafe(void) { freezer_do_not_count(); schedule(); freezer_count_unsafe(); } /* * Like schedule_timeout(), but should not block the freezer. Do not * call this with locks held. */ static inline long freezable_schedule_timeout(long timeout) { long __retval; freezer_do_not_count(); __retval = schedule_timeout(timeout); freezer_count(); return __retval; } /* * Like schedule_timeout_interruptible(), but should not block the freezer. Do not * call this with locks held. */ static inline long freezable_schedule_timeout_interruptible(long timeout) { long __retval; freezer_do_not_count(); __retval = schedule_timeout_interruptible(timeout); freezer_count(); return __retval; } /* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ static inline long freezable_schedule_timeout_interruptible_unsafe(long timeout) { long __retval; freezer_do_not_count(); __retval = schedule_timeout_interruptible(timeout); freezer_count_unsafe(); return __retval; } /* Like schedule_timeout_killable(), but should not block the freezer. */ static inline long freezable_schedule_timeout_killable(long timeout) { long __retval; freezer_do_not_count(); __retval = schedule_timeout_killable(timeout); freezer_count(); return __retval; } /* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ static inline long freezable_schedule_timeout_killable_unsafe(long timeout) { long __retval; freezer_do_not_count(); __retval = schedule_timeout_killable(timeout); freezer_count_unsafe(); return __retval; } /* * Like schedule_hrtimeout_range(), but should not block the freezer. Do not * call this with locks held. */ static inline int freezable_schedule_hrtimeout_range(ktime_t *expires, u64 delta, const enum hrtimer_mode mode) { int __retval; freezer_do_not_count(); __retval = schedule_hrtimeout_range(expires, delta, mode); freezer_count(); return __retval; } /* * Freezer-friendly wrappers around wait_event_interruptible(), * wait_event_killable() and wait_event_interruptible_timeout(), originally * defined in <linux/wait.h> */ /* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */ #define wait_event_freezekillable_unsafe(wq, condition) \ ({ \ int __retval; \ freezer_do_not_count(); \ __retval = wait_event_killable(wq, (condition)); \ freezer_count_unsafe(); \ __retval; \ }) #else /* !CONFIG_FREEZER */ static inline bool frozen(struct task_struct *p) { return false; } static inline bool freezing(struct task_struct *p) { return false; } static inline void __thaw_task(struct task_struct *t) {} static inline bool __refrigerator(bool check_kthr_stop) { return false; } static inline int freeze_processes(void) { return -ENOSYS; } static inline int freeze_kernel_threads(void) { return -ENOSYS; } static inline void thaw_processes(void) {} static inline void thaw_kernel_threads(void) {} static inline bool try_to_freeze_nowarn(void) { return false; } static inline bool try_to_freeze(void) { return false; } static inline void freezer_do_not_count(void) {} static inline void freezer_count(void) {} static inline int freezer_should_skip(struct task_struct *p) { return 0; } static inline void set_freezable(void) {} #define freezable_schedule() schedule() #define freezable_schedule_unsafe() schedule() #define freezable_schedule_timeout(timeout) schedule_timeout(timeout) #define freezable_schedule_timeout_interruptible(timeout) \ schedule_timeout_interruptible(timeout) #define freezable_schedule_timeout_interruptible_unsafe(timeout) \ schedule_timeout_interruptible(timeout) #define freezable_schedule_timeout_killable(timeout) \ schedule_timeout_killable(timeout) #define freezable_schedule_timeout_killable_unsafe(timeout) \ schedule_timeout_killable(timeout) #define freezable_schedule_hrtimeout_range(expires, delta, mode) \ schedule_hrtimeout_range(expires, delta, mode) #define wait_event_freezekillable_unsafe(wq, condition) \ wait_event_killable(wq, condition) #endif /* !CONFIG_FREEZER */ #endif /* FREEZER_H_INCLUDED */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 /* SPDX-License-Identifier: GPL-2.0 */ /* File: linux/xattr.h Extended attributes handling. Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org> Copyright (c) 2001-2002 Silicon Graphics, Inc. All Rights Reserved. Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #ifndef _LINUX_XATTR_H #define _LINUX_XATTR_H #include <linux/slab.h> #include <linux/types.h> #include <linux/spinlock.h> #include <linux/mm.h> #include <uapi/linux/xattr.h> struct inode; struct dentry; /* * struct xattr_handler: When @name is set, match attributes with exactly that * name. When @prefix is set instead, match attributes with that prefix and * with a non-empty suffix. */ struct xattr_handler { const char *name; const char *prefix; int flags; /* fs private flags */ bool (*list)(struct dentry *dentry); int (*get)(const struct xattr_handler *, struct dentry *dentry, struct inode *inode, const char *name, void *buffer, size_t size); int (*set)(const struct xattr_handler *, struct dentry *dentry, struct inode *inode, const char *name, const void *buffer, size_t size, int flags); }; const char *xattr_full_name(const struct xattr_handler *, const char *); struct xattr { const char *name; void *value; size_t value_len; }; ssize_t __vfs_getxattr(struct dentry *, struct inode *, const char *, void *, size_t); ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t); ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size); int __vfs_setxattr(struct dentry *, struct inode *, const char *, const void *, size_t, int); int __vfs_setxattr_noperm(struct dentry *, const char *, const void *, size_t, int); int __vfs_setxattr_locked(struct dentry *, const char *, const void *, size_t, int, struct inode **); int vfs_setxattr(struct dentry *, const char *, const void *, size_t, int); int __vfs_removexattr(struct dentry *, const char *); int __vfs_removexattr_locked(struct dentry *, const char *, struct inode **); int vfs_removexattr(struct dentry *, const char *); ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size); ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, size_t size, gfp_t flags); int xattr_supported_namespace(struct inode *inode, const char *prefix); static inline const char *xattr_prefix(const struct xattr_handler *handler) { return handler->prefix ?: handler->name; } struct simple_xattrs { struct list_head head; spinlock_t lock; }; struct simple_xattr { struct list_head list; char *name; size_t size; char value[]; }; /* * initialize the simple_xattrs structure */ static inline void simple_xattrs_init(struct simple_xattrs *xattrs) { INIT_LIST_HEAD(&xattrs->head); spin_lock_init(&xattrs->lock); } /* * free all the xattrs */ static inline void simple_xattrs_free(struct simple_xattrs *xattrs) { struct simple_xattr *xattr, *node; list_for_each_entry_safe(xattr, node, &xattrs->head, list) { kfree(xattr->name); kvfree(xattr); } } struct simple_xattr *simple_xattr_alloc(const void *value, size_t size); int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, void *buffer, size_t size); int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, const void *value, size_t size, int flags, ssize_t *removed_size); ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size); void simple_xattr_list_add(struct simple_xattrs *xattrs, struct simple_xattr *new_xattr); #endif /* _LINUX_XATTR_H */
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * SR-IPv6 implementation * * Author: * David Lebrun <david.lebrun@uclouvain.be> */ #ifndef _NET_SEG6_H #define _NET_SEG6_H #include <linux/net.h> #include <linux/ipv6.h> #include <linux/seg6.h> #include <linux/rhashtable-types.h> static inline void update_csum_diff4(struct sk_buff *skb, __be32 from, __be32 to) { __be32 diff[] = { ~from, to }; skb->csum = ~csum_partial((char *)diff, sizeof(diff), ~skb->csum); } static inline void update_csum_diff16(struct sk_buff *skb, __be32 *from, __be32 *to) { __be32 diff[] = { ~from[0], ~from[1], ~from[2], ~from[3], to[0], to[1], to[2], to[3], }; skb->csum = ~csum_partial((char *)diff, sizeof(diff), ~skb->csum); } struct seg6_pernet_data { struct mutex lock; struct in6_addr __rcu *tun_src; #ifdef CONFIG_IPV6_SEG6_HMAC struct rhashtable hmac_infos; #endif }; static inline struct seg6_pernet_data *seg6_pernet(struct net *net) { #if IS_ENABLED(CONFIG_IPV6) return net->ipv6.seg6_data; #else return NULL; #endif } extern int seg6_init(void); extern void seg6_exit(void); extern int seg6_iptunnel_init(void); extern void seg6_iptunnel_exit(void); extern int seg6_local_init(void); extern void seg6_local_exit(void); extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced); extern int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto); extern int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh); extern int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, u32 tbl_id); #endif
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _X_TABLES_H #define _X_TABLES_H #include <linux/netdevice.h> #include <linux/static_key.h> #include <linux/netfilter.h> #include <uapi/linux/netfilter/x_tables.h> /* Test a struct->invflags and a boolean for inequality */ #define NF_INVF(ptr, flag, boolean) \ ((boolean) ^ !!((ptr)->invflags & (flag))) /** * struct xt_action_param - parameters for matches/targets * * @match: the match extension * @target: the target extension * @matchinfo: per-match data * @targetinfo: per-target data * @state: pointer to hook state this packet came from * @fragoff: packet is a fragment, this is the data offset * @thoff: position of transport header relative to skb->data * * Fields written to by extensions: * * @hotdrop: drop packet if we had inspection problems */ struct xt_action_param { union { const struct xt_match *match; const struct xt_target *target; }; union { const void *matchinfo, *targinfo; }; const struct nf_hook_state *state; int fragoff; unsigned int thoff; bool hotdrop; }; static inline struct net *xt_net(const struct xt_action_param *par) { return par->state->net; } static inline struct net_device *xt_in(const struct xt_action_param *par) { return par->state->in; } static inline const char *xt_inname(const struct xt_action_param *par) { return par->state->in->name; } static inline struct net_device *xt_out(const struct xt_action_param *par) { return par->state->out; } static inline const char *xt_outname(const struct xt_action_param *par) { return par->state->out->name; } static inline unsigned int xt_hooknum(const struct xt_action_param *par) { return par->state->hook; } static inline u_int8_t xt_family(const struct xt_action_param *par) { return par->state->pf; } /** * struct xt_mtchk_param - parameters for match extensions' * checkentry functions * * @net: network namespace through which the check was invoked * @table: table the rule is tried to be inserted into * @entryinfo: the family-specific rule data * (struct ipt_ip, ip6t_ip, arpt_arp or (note) ebt_entry) * @match: struct xt_match through which this function was invoked * @matchinfo: per-match data * @hook_mask: via which hooks the new rule is reachable * Other fields as above. */ struct xt_mtchk_param { struct net *net; const char *table; const void *entryinfo; const struct xt_match *match; void *matchinfo; unsigned int hook_mask; u_int8_t family; bool nft_compat; }; /** * struct xt_mdtor_param - match destructor parameters * Fields as above. */ struct xt_mtdtor_param { struct net *net; const struct xt_match *match; void *matchinfo; u_int8_t family; }; /** * struct xt_tgchk_param - parameters for target extensions' * checkentry functions * * @entryinfo: the family-specific rule data * (struct ipt_entry, ip6t_entry, arpt_entry, ebt_entry) * * Other fields see above. */ struct xt_tgchk_param { struct net *net; const char *table; const void *entryinfo; const struct xt_target *target; void *targinfo; unsigned int hook_mask; u_int8_t family; bool nft_compat; }; /* Target destructor parameters */ struct xt_tgdtor_param { struct net *net; const struct xt_target *target; void *targinfo; u_int8_t family; }; struct xt_match { struct list_head list; const char name[XT_EXTENSION_MAXNAMELEN]; u_int8_t revision; /* Return true or false: return FALSE and set *hotdrop = 1 to force immediate packet drop. */ /* Arguments changed since 2.6.9, as this must now handle non-linear skb, using skb_header_pointer and skb_ip_make_writable. */ bool (*match)(const struct sk_buff *skb, struct xt_action_param *); /* Called when user tries to insert an entry of this type. */ int (*checkentry)(const struct xt_mtchk_param *); /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_mtdtor_param *); #ifdef CONFIG_COMPAT /* Called when userspace align differs from kernel space one */ void (*compat_from_user)(void *dst, const void *src); int (*compat_to_user)(void __user *dst, const void *src); #endif /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; const char *table; unsigned int matchsize; unsigned int usersize; #ifdef CONFIG_COMPAT unsigned int compatsize; #endif unsigned int hooks; unsigned short proto; unsigned short family; }; /* Registration hooks for targets. */ struct xt_target { struct list_head list; const char name[XT_EXTENSION_MAXNAMELEN]; u_int8_t revision; /* Returns verdict. Argument order changed since 2.6.9, as this must now handle non-linear skbs, using skb_copy_bits and skb_ip_make_writable. */ unsigned int (*target)(struct sk_buff *skb, const struct xt_action_param *); /* Called when user tries to insert an entry of this type: hook_mask is a bitmask of hooks from which it can be called. */ /* Should return 0 on success or an error code otherwise (-Exxxx). */ int (*checkentry)(const struct xt_tgchk_param *); /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_tgdtor_param *); #ifdef CONFIG_COMPAT /* Called when userspace align differs from kernel space one */ void (*compat_from_user)(void *dst, const void *src); int (*compat_to_user)(void __user *dst, const void *src); #endif /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; const char *table; unsigned int targetsize; unsigned int usersize; #ifdef CONFIG_COMPAT unsigned int compatsize; #endif unsigned int hooks; unsigned short proto; unsigned short family; }; /* Furniture shopping... */ struct xt_table { struct list_head list; /* What hooks you will enter on */ unsigned int valid_hooks; /* Man behind the curtain... */ struct xt_table_info *private; /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; u_int8_t af; /* address/protocol family */ int priority; /* hook order */ /* called when table is needed in the given netns */ int (*table_init)(struct net *net); /* A unique name... */ const char name[XT_TABLE_MAXNAMELEN]; }; #include <linux/netfilter_ipv4.h> /* The table itself */ struct xt_table_info { /* Size per table */ unsigned int size; /* Number of entries: FIXME. --RR */ unsigned int number; /* Initial number of entries. Needed for module usage count */ unsigned int initial_entries; /* Entry points and underflows */ unsigned int hook_entry[NF_INET_NUMHOOKS]; unsigned int underflow[NF_INET_NUMHOOKS]; /* * Number of user chains. Since tables cannot have loops, at most * @stacksize jumps (number of user chains) can possibly be made. */ unsigned int stacksize; void ***jumpstack; unsigned char entries[] __aligned(8); }; int xt_register_target(struct xt_target *target); void xt_unregister_target(struct xt_target *target); int xt_register_targets(struct xt_target *target, unsigned int n); void xt_unregister_targets(struct xt_target *target, unsigned int n); int xt_register_match(struct xt_match *target); void xt_unregister_match(struct xt_match *target); int xt_register_matches(struct xt_match *match, unsigned int n); void xt_unregister_matches(struct xt_match *match, unsigned int n); int xt_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset); int xt_check_table_hooks(const struct xt_table_info *info, unsigned int valid_hooks); unsigned int *xt_alloc_entry_offsets(unsigned int size); bool xt_find_jump_offset(const unsigned int *offsets, unsigned int target, unsigned int size); int xt_check_proc_name(const char *name, unsigned int size); int xt_check_match(struct xt_mtchk_param *, unsigned int size, u16 proto, bool inv_proto); int xt_check_target(struct xt_tgchk_param *, unsigned int size, u16 proto, bool inv_proto); int xt_match_to_user(const struct xt_entry_match *m, struct xt_entry_match __user *u); int xt_target_to_user(const struct xt_entry_target *t, struct xt_entry_target __user *u); int xt_data_to_user(void __user *dst, const void *src, int usersize, int size, int aligned_size); void *xt_copy_counters(sockptr_t arg, unsigned int len, struct xt_counters_info *info); struct xt_counters *xt_counters_alloc(unsigned int counters); struct xt_table *xt_register_table(struct net *net, const struct xt_table *table, struct xt_table_info *bootstrap, struct xt_table_info *newinfo); void *xt_unregister_table(struct xt_table *table); struct xt_table_info *xt_replace_table(struct xt_table *table, unsigned int num_counters, struct xt_table_info *newinfo, int *error); struct xt_match *xt_find_match(u8 af, const char *name, u8 revision); struct xt_match *xt_request_find_match(u8 af, const char *name, u8 revision); struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision); int xt_find_revision(u8 af, const char *name, u8 revision, int target, int *err); struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, const char *name); struct xt_table *xt_request_find_table_lock(struct net *net, u_int8_t af, const char *name); void xt_table_unlock(struct xt_table *t); int xt_proto_init(struct net *net, u_int8_t af); void xt_proto_fini(struct net *net, u_int8_t af); struct xt_table_info *xt_alloc_table_info(unsigned int size); void xt_free_table_info(struct xt_table_info *info); /** * xt_recseq - recursive seqcount for netfilter use * * Packet processing changes the seqcount only if no recursion happened * get_counters() can use read_seqcount_begin()/read_seqcount_retry(), * because we use the normal seqcount convention : * Low order bit set to 1 if a writer is active. */ DECLARE_PER_CPU(seqcount_t, xt_recseq); /* xt_tee_enabled - true if x_tables needs to handle reentrancy * * Enabled if current ip(6)tables ruleset has at least one -j TEE rule. */ extern struct static_key xt_tee_enabled; /** * xt_write_recseq_begin - start of a write section * * Begin packet processing : all readers must wait the end * 1) Must be called with preemption disabled * 2) softirqs must be disabled too (or we should use this_cpu_add()) * Returns : * 1 if no recursion on this cpu * 0 if recursion detected */ static inline unsigned int xt_write_recseq_begin(void) { unsigned int addend; /* * Low order bit of sequence is set if we already * called xt_write_recseq_begin(). */ addend = (__this_cpu_read(xt_recseq.sequence) + 1) & 1; /* * This is kind of a write_seqcount_begin(), but addend is 0 or 1 * We dont check addend value to avoid a test and conditional jump, * since addend is most likely 1 */ __this_cpu_add(xt_recseq.sequence, addend); smp_mb(); return addend; } /** * xt_write_recseq_end - end of a write section * @addend: return value from previous xt_write_recseq_begin() * * End packet processing : all readers can proceed * 1) Must be called with preemption disabled * 2) softirqs must be disabled too (or we should use this_cpu_add()) */ static inline void xt_write_recseq_end(unsigned int addend) { /* this is kind of a write_seqcount_end(), but addend is 0 or 1 */ smp_wmb(); __this_cpu_add(xt_recseq.sequence, addend); } /* * This helper is performance critical and must be inlined */ static inline unsigned long ifname_compare_aligned(const char *_a, const char *_b, const char *_mask) { const unsigned long *a = (const unsigned long *)_a; const unsigned long *b = (const unsigned long *)_b; const unsigned long *mask = (const unsigned long *)_mask; unsigned long ret; ret = (a[0] ^ b[0]) & mask[0]; if (IFNAMSIZ > sizeof(unsigned long)) ret |= (a[1] ^ b[1]) & mask[1]; if (IFNAMSIZ > 2 * sizeof(unsigned long)) ret |= (a[2] ^ b[2]) & mask[2]; if (IFNAMSIZ > 3 * sizeof(unsigned long)) ret |= (a[3] ^ b[3]) & mask[3]; BUILD_BUG_ON(IFNAMSIZ > 4 * sizeof(unsigned long)); return ret; } struct xt_percpu_counter_alloc_state { unsigned int off; const char __percpu *mem; }; bool xt_percpu_counter_alloc(struct xt_percpu_counter_alloc_state *state, struct xt_counters *counter); void xt_percpu_counter_free(struct xt_counters *cnt); static inline struct xt_counters * xt_get_this_cpu_counter(struct xt_counters *cnt) { if (nr_cpu_ids > 1) return this_cpu_ptr((void __percpu *) (unsigned long) cnt->pcnt); return cnt; } static inline struct xt_counters * xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) { if (nr_cpu_ids > 1) return per_cpu_ptr((void __percpu *) (unsigned long) cnt->pcnt, cpu); return cnt; } struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *); #ifdef CONFIG_COMPAT #include <net/compat.h> struct compat_xt_entry_match { union { struct { u_int16_t match_size; char name[XT_FUNCTION_MAXNAMELEN - 1]; u_int8_t revision; } user; struct { u_int16_t match_size; compat_uptr_t match; } kernel; u_int16_t match_size; } u; unsigned char data[]; }; struct compat_xt_entry_target { union { struct { u_int16_t target_size; char name[XT_FUNCTION_MAXNAMELEN - 1]; u_int8_t revision; } user; struct { u_int16_t target_size; compat_uptr_t target; } kernel; u_int16_t target_size; } u; unsigned char data[]; }; /* FIXME: this works only on 32 bit tasks * need to change whole approach in order to calculate align as function of * current task alignment */ struct compat_xt_counters { compat_u64 pcnt, bcnt; /* Packet and byte counters */ }; struct compat_xt_counters_info { char name[XT_TABLE_MAXNAMELEN]; compat_uint_t num_counters; struct compat_xt_counters counters[]; }; struct _compat_xt_align { __u8 u8; __u16 u16; __u32 u32; compat_u64 u64; }; #define COMPAT_XT_ALIGN(s) __ALIGN_KERNEL((s), __alignof__(struct _compat_xt_align)) void xt_compat_lock(u_int8_t af); void xt_compat_unlock(u_int8_t af); int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta); void xt_compat_flush_offsets(u_int8_t af); int xt_compat_init_offsets(u8 af, unsigned int number); int xt_compat_calc_jump(u_int8_t af, unsigned int offset); int xt_compat_match_offset(const struct xt_match *match); void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, unsigned int *size); int xt_compat_match_to_user(const struct xt_entry_match *m, void __user **dstptr, unsigned int *size); int xt_compat_target_offset(const struct xt_target *target); void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, unsigned int *size); int xt_compat_target_to_user(const struct xt_entry_target *t, void __user **dstptr, unsigned int *size); int xt_compat_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset); #endif /* CONFIG_COMPAT */ #endif /* _X_TABLES_H */
1 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * * This file contains the interface functions for the various time related * system calls: time, stime, gettimeofday, settimeofday, adjtime * * Modification history: * * 1993-09-02 Philip Gladstone * Created file with time related functions from sched/core.c and adjtimex() * 1993-10-08 Torsten Duwe * adjtime interface update and CMOS clock write code * 1995-08-13 Torsten Duwe * kernel PLL updated to 1994-12-13 specs (rfc-1589) * 1999-01-16 Ulrich Windl * Introduced error checking for many cases in adjtimex(). * Updated NTP code according to technical memorandum Jan '96 * "A Kernel Model for Precision Timekeeping" by Dave Mills * Allow time_constant larger than MAXTC(6) for NTP v4 (MAXTC == 10) * (Even though the technical memorandum forbids it) * 2004-07-14 Christoph Lameter * Added getnstimeofday to allow the posix timer functions to return * with nanosecond accuracy */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/timex.h> #include <linux/capability.h> #include <linux/timekeeper_internal.h> #include <linux/errno.h> #include <linux/syscalls.h> #include <linux/security.h> #include <linux/fs.h> #include <linux/math64.h> #include <linux/ptrace.h> #include <linux/uaccess.h> #include <linux/compat.h> #include <asm/unistd.h> #include <generated/timeconst.h> #include "timekeeping.h" /* * The timezone where the local system is located. Used as a default by some * programs who obtain this value by using gettimeofday. */ struct timezone sys_tz; EXPORT_SYMBOL(sys_tz); #ifdef __ARCH_WANT_SYS_TIME /* * sys_time() can be implemented in user-level using * sys_gettimeofday(). Is this for backwards compatibility? If so, * why not move it into the appropriate arch directory (for those * architectures that need it). */ SYSCALL_DEFINE1(time, __kernel_old_time_t __user *, tloc) { __kernel_old_time_t i = (__kernel_old_time_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) return -EFAULT; } force_successful_syscall_return(); return i; } /* * sys_stime() can be implemented in user-level using * sys_settimeofday(). Is this for backwards compatibility? If so, * why not move it into the appropriate arch directory (for those * architectures that need it). */ SYSCALL_DEFINE1(stime, __kernel_old_time_t __user *, tptr) { struct timespec64 tv; int err; if (get_user(tv.tv_sec, tptr)) return -EFAULT; tv.tv_nsec = 0; err = security_settime64(&tv, NULL); if (err) return err; do_settimeofday64(&tv); return 0; } #endif /* __ARCH_WANT_SYS_TIME */ #ifdef CONFIG_COMPAT_32BIT_TIME #ifdef __ARCH_WANT_SYS_TIME32 /* old_time32_t is a 32 bit "long" and needs to get converted. */ SYSCALL_DEFINE1(time32, old_time32_t __user *, tloc) { old_time32_t i; i = (old_time32_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) return -EFAULT; } force_successful_syscall_return(); return i; } SYSCALL_DEFINE1(stime32, old_time32_t __user *, tptr) { struct timespec64 tv; int err; if (get_user(tv.tv_sec, tptr)) return -EFAULT; tv.tv_nsec = 0; err = security_settime64(&tv, NULL); if (err) return err; do_settimeofday64(&tv); return 0; } #endif /* __ARCH_WANT_SYS_TIME32 */ #endif SYSCALL_DEFINE2(gettimeofday, struct __kernel_old_timeval __user *, tv, struct timezone __user *, tz) { if (likely(tv != NULL)) { struct timespec64 ts; ktime_get_real_ts64(&ts); if (put_user(ts.tv_sec, &tv->tv_sec) || put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (unlikely(tz != NULL)) { if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) return -EFAULT; } return 0; } /* * In case for some reason the CMOS clock has not already been running * in UTC, but in some local time: The first time we set the timezone, * we will warp the clock so that it is ticking UTC time instead of * local time. Presumably, if someone is setting the timezone then we * are running in an environment where the programs understand about * timezones. This should be done at boot time in the /etc/rc script, * as soon as possible, so that the clock can be set right. Otherwise, * various programs will get confused when the clock gets warped. */ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz) { static int firsttime = 1; int error = 0; if (tv && !timespec64_valid_settod(tv)) return -EINVAL; error = security_settime64(tv, tz); if (error) return error; if (tz) { /* Verify we're within the +-15 hrs range */ if (tz->tz_minuteswest > 15*60 || tz->tz_minuteswest < -15*60) return -EINVAL; sys_tz = *tz; update_vsyscall_tz(); if (firsttime) { firsttime = 0; if (!tv) timekeeping_warp_clock(); } } if (tv) return do_settimeofday64(tv); return 0; } SYSCALL_DEFINE2(settimeofday, struct __kernel_old_timeval __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; struct timezone new_tz; if (tv) { if (get_user(new_ts.tv_sec, &tv->tv_sec) || get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; new_ts.tv_nsec *= NSEC_PER_USEC; } if (tz) { if (copy_from_user(&new_tz, tz, sizeof(*tz))) return -EFAULT; } return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(gettimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { if (tv) { struct timespec64 ts; ktime_get_real_ts64(&ts); if (put_user(ts.tv_sec, &tv->tv_sec) || put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (tz) { if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) return -EFAULT; } return 0; } COMPAT_SYSCALL_DEFINE2(settimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; struct timezone new_tz; if (tv) { if (get_user(new_ts.tv_sec, &tv->tv_sec) || get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; new_ts.tv_nsec *= NSEC_PER_USEC; } if (tz) { if (copy_from_user(&new_tz, tz, sizeof(*tz))) return -EFAULT; } return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); } #endif #ifdef CONFIG_64BIT SYSCALL_DEFINE1(adjtimex, struct __kernel_timex __user *, txc_p) { struct __kernel_timex txc; /* Local copy of parameter */ int ret; /* Copy the user data space into the kernel copy * structure. But bear in mind that the structures * may change */ if (copy_from_user(&txc, txc_p, sizeof(struct __kernel_timex))) return -EFAULT; ret = do_adjtimex(&txc); return copy_to_user(txc_p, &txc, sizeof(struct __kernel_timex)) ? -EFAULT : ret; } #endif #ifdef CONFIG_COMPAT_32BIT_TIME int get_old_timex32(struct __kernel_timex *txc, const struct old_timex32 __user *utp) { struct old_timex32 tx32; memset(txc, 0, sizeof(struct __kernel_timex)); if (copy_from_user(&tx32, utp, sizeof(struct old_timex32))) return -EFAULT; txc->modes = tx32.modes; txc->offset = tx32.offset; txc->freq = tx32.freq; txc->maxerror = tx32.maxerror; txc->esterror = tx32.esterror; txc->status = tx32.status; txc->constant = tx32.constant; txc->precision = tx32.precision; txc->tolerance = tx32.tolerance; txc->time.tv_sec = tx32.time.tv_sec; txc->time.tv_usec = tx32.time.tv_usec; txc->tick = tx32.tick; txc->ppsfreq = tx32.ppsfreq; txc->jitter = tx32.jitter; txc->shift = tx32.shift; txc->stabil = tx32.stabil; txc->jitcnt = tx32.jitcnt; txc->calcnt = tx32.calcnt; txc->errcnt = tx32.errcnt; txc->stbcnt = tx32.stbcnt; return 0; } int put_old_timex32(struct old_timex32 __user *utp, const struct __kernel_timex *txc) { struct old_timex32 tx32; memset(&tx32, 0, sizeof(struct old_timex32)); tx32.modes = txc->modes; tx32.offset = txc->offset; tx32.freq = txc->freq; tx32.maxerror = txc->maxerror; tx32.esterror = txc->esterror; tx32.status = txc->status; tx32.constant = txc->constant; tx32.precision = txc->precision; tx32.tolerance = txc->tolerance; tx32.time.tv_sec = txc->time.tv_sec; tx32.time.tv_usec = txc->time.tv_usec; tx32.tick = txc->tick; tx32.ppsfreq = txc->ppsfreq; tx32.jitter = txc->jitter; tx32.shift = txc->shift; tx32.stabil = txc->stabil; tx32.jitcnt = txc->jitcnt; tx32.calcnt = txc->calcnt; tx32.errcnt = txc->errcnt; tx32.stbcnt = txc->stbcnt; tx32.tai = txc->tai; if (copy_to_user(utp, &tx32, sizeof(struct old_timex32))) return -EFAULT; return 0; } SYSCALL_DEFINE1(adjtimex_time32, struct old_timex32 __user *, utp) { struct __kernel_timex txc; int err, ret; err = get_old_timex32(&txc, utp); if (err) return err; ret = do_adjtimex(&txc); err = put_old_timex32(utp, &txc); if (err) return err; return ret; } #endif /* * Convert jiffies to milliseconds and back. * * Avoid unnecessary multiplications/divisions in the * two most common HZ cases: */ unsigned int jiffies_to_msecs(const unsigned long j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; #elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC); #else # if BITS_PER_LONG == 32 return (HZ_TO_MSEC_MUL32 * j + (1ULL << HZ_TO_MSEC_SHR32) - 1) >> HZ_TO_MSEC_SHR32; # else return DIV_ROUND_UP(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); # endif #endif } EXPORT_SYMBOL(jiffies_to_msecs); unsigned int jiffies_to_usecs(const unsigned long j) { /* * Hz usually doesn't go much further MSEC_PER_SEC. * jiffies_to_usecs() and usecs_to_jiffies() depend on that. */ BUILD_BUG_ON(HZ > USEC_PER_SEC); #if !(USEC_PER_SEC % HZ) return (USEC_PER_SEC / HZ) * j; #else # if BITS_PER_LONG == 32 return (HZ_TO_USEC_MUL32 * j) >> HZ_TO_USEC_SHR32; # else return (j * HZ_TO_USEC_NUM) / HZ_TO_USEC_DEN; # endif #endif } EXPORT_SYMBOL(jiffies_to_usecs); /* * mktime64 - Converts date to seconds. * Converts Gregorian date to seconds since 1970-01-01 00:00:00. * Assumes input in normal date format, i.e. 1980-12-31 23:59:59 * => year=1980, mon=12, day=31, hour=23, min=59, sec=59. * * [For the Julian calendar (which was used in Russia before 1917, * Britain & colonies before 1752, anywhere else before 1582, * and is still in use by some communities) leave out the * -year/100+year/400 terms, and add 10.] * * This algorithm was first published by Gauss (I think). * * A leap second can be indicated by calling this function with sec as * 60 (allowable under ISO 8601). The leap second is treated the same * as the following second since they don't exist in UNIX time. * * An encoding of midnight at the end of the day as 24:00:00 - ie. midnight * tomorrow - (allowable under ISO 8601) is supported. */ time64_t mktime64(const unsigned int year0, const unsigned int mon0, const unsigned int day, const unsigned int hour, const unsigned int min, const unsigned int sec) { unsigned int mon = mon0, year = year0; /* 1..12 -> 11,12,1..10 */ if (0 >= (int) (mon -= 2)) { mon += 12; /* Puts Feb last since it has leap day */ year -= 1; } return ((((time64_t) (year/4 - year/100 + year/400 + 367*mon/12 + day) + year*365 - 719499 )*24 + hour /* now have hours - midnight tomorrow handled here */ )*60 + min /* now have minutes */ )*60 + sec; /* finally seconds */ } EXPORT_SYMBOL(mktime64); struct __kernel_old_timeval ns_to_kernel_old_timeval(const s64 nsec) { struct timespec64 ts = ns_to_timespec64(nsec); struct __kernel_old_timeval tv; tv.tv_sec = ts.tv_sec; tv.tv_usec = (suseconds_t)ts.tv_nsec / 1000; return tv; } EXPORT_SYMBOL(ns_to_kernel_old_timeval); /** * set_normalized_timespec - set timespec sec and nsec parts and normalize * * @ts: pointer to timespec variable to be set * @sec: seconds to set * @nsec: nanoseconds to set * * Set seconds and nanoseconds field of a timespec variable and * normalize to the timespec storage format * * Note: The tv_nsec part is always in the range of * 0 <= tv_nsec < NSEC_PER_SEC * For negative values only the tv_sec field is negative ! */ void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec) { while (nsec >= NSEC_PER_SEC) { /* * The following asm() prevents the compiler from * optimising this loop into a modulo operation. See * also __iter_div_u64_rem() in include/linux/time.h */ asm("" : "+rm"(nsec)); nsec -= NSEC_PER_SEC; ++sec; } while (nsec < 0) { asm("" : "+rm"(nsec)); nsec += NSEC_PER_SEC; --sec; } ts->tv_sec = sec; ts->tv_nsec = nsec; } EXPORT_SYMBOL(set_normalized_timespec64); /** * ns_to_timespec64 - Convert nanoseconds to timespec64 * @nsec: the nanoseconds value to be converted * * Returns the timespec64 representation of the nsec parameter. */ struct timespec64 ns_to_timespec64(const s64 nsec) { struct timespec64 ts = { 0, 0 }; s32 rem; if (likely(nsec > 0)) { ts.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); ts.tv_nsec = rem; } else if (nsec < 0) { /* * With negative times, tv_sec points to the earlier * second, and tv_nsec counts the nanoseconds since * then, so tv_nsec is always a positive number. */ ts.tv_sec = -div_u64_rem(-nsec - 1, NSEC_PER_SEC, &rem) - 1; ts.tv_nsec = NSEC_PER_SEC - rem - 1; } return ts; } EXPORT_SYMBOL(ns_to_timespec64); /** * msecs_to_jiffies: - convert milliseconds to jiffies * @m: time in milliseconds * * conversion is done as follows: * * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET) * * - 'too large' values [that would result in larger than * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too. * * - all other values are converted to jiffies by either multiplying * the input value by a factor or dividing it with a factor and * handling any 32-bit overflows. * for the details see __msecs_to_jiffies() * * msecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the * code, __msecs_to_jiffies() is called if the value passed does not * allow constant folding and the actual conversion must be done at * runtime. * the _msecs_to_jiffies helpers are the HZ dependent conversion * routines found in include/linux/jiffies.h */ unsigned long __msecs_to_jiffies(const unsigned int m) { /* * Negative value, means infinite timeout: */ if ((int)m < 0) return MAX_JIFFY_OFFSET; return _msecs_to_jiffies(m); } EXPORT_SYMBOL(__msecs_to_jiffies); unsigned long __usecs_to_jiffies(const unsigned int u) { if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET)) return MAX_JIFFY_OFFSET; return _usecs_to_jiffies(u); } EXPORT_SYMBOL(__usecs_to_jiffies); /* * The TICK_NSEC - 1 rounds up the value to the next resolution. Note * that a remainder subtract here would not do the right thing as the * resolution values don't fall on second boundries. I.e. the line: * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding. * Note that due to the small error in the multiplier here, this * rounding is incorrect for sufficiently large values of tv_nsec, but * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're * OK. * * Rather, we just shift the bits off the right. * * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec * value to a scaled second value. */ unsigned long timespec64_to_jiffies(const struct timespec64 *value) { u64 sec = value->tv_sec; long nsec = value->tv_nsec + TICK_NSEC - 1; if (sec >= MAX_SEC_IN_JIFFIES){ sec = MAX_SEC_IN_JIFFIES; nsec = 0; } return ((sec * SEC_CONVERSION) + (((u64)nsec * NSEC_CONVERSION) >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; } EXPORT_SYMBOL(timespec64_to_jiffies); void jiffies_to_timespec64(const unsigned long jiffies, struct timespec64 *value) { /* * Convert jiffies to nanoseconds and separate with * one divide. */ u32 rem; value->tv_sec = div_u64_rem((u64)jiffies * TICK_NSEC, NSEC_PER_SEC, &rem); value->tv_nsec = rem; } EXPORT_SYMBOL(jiffies_to_timespec64); /* * Convert jiffies/jiffies_64 to clock_t and back. */ clock_t jiffies_to_clock_t(unsigned long x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ return x * (USER_HZ / HZ); # else return x / (HZ / USER_HZ); # endif #else return div_u64((u64)x * TICK_NSEC, NSEC_PER_SEC / USER_HZ); #endif } EXPORT_SYMBOL(jiffies_to_clock_t); unsigned long clock_t_to_jiffies(unsigned long x) { #if (HZ % USER_HZ)==0 if (x >= ~0UL / (HZ / USER_HZ)) return ~0UL; return x * (HZ / USER_HZ); #else /* Don't worry about loss of precision here .. */ if (x >= ~0UL / HZ * USER_HZ) return ~0UL; /* .. but do try to contain it here */ return div_u64((u64)x * HZ, USER_HZ); #endif } EXPORT_SYMBOL(clock_t_to_jiffies); u64 jiffies_64_to_clock_t(u64 x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ x = div_u64(x * USER_HZ, HZ); # elif HZ > USER_HZ x = div_u64(x, HZ / USER_HZ); # else /* Nothing to do */ # endif #else /* * There are better ways that don't overflow early, * but even this doesn't overflow in hundreds of years * in 64 bits, so.. */ x = div_u64(x * TICK_NSEC, (NSEC_PER_SEC / USER_HZ)); #endif return x; } EXPORT_SYMBOL(jiffies_64_to_clock_t); u64 nsec_to_clock_t(u64 x) { #if (NSEC_PER_SEC % USER_HZ) == 0 return div_u64(x, NSEC_PER_SEC / USER_HZ); #elif (USER_HZ % 512) == 0 return div_u64(x * USER_HZ / 512, NSEC_PER_SEC / 512); #else /* * max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024, * overflow after 64.99 years. * exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ... */ return div_u64(x * 9, (9ull * NSEC_PER_SEC + (USER_HZ / 2)) / USER_HZ); #endif } u64 jiffies64_to_nsecs(u64 j) { #if !(NSEC_PER_SEC % HZ) return (NSEC_PER_SEC / HZ) * j; # else return div_u64(j * HZ_TO_NSEC_NUM, HZ_TO_NSEC_DEN); #endif } EXPORT_SYMBOL(jiffies64_to_nsecs); u64 jiffies64_to_msecs(const u64 j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; #else return div_u64(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); #endif } EXPORT_SYMBOL(jiffies64_to_msecs); /** * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64 * * @n: nsecs in u64 * * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. * And this doesn't return MAX_JIFFY_OFFSET since this function is designed * for scheduler, not for use in device drivers to calculate timeout value. * * note: * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years */ u64 nsecs_to_jiffies64(u64 n) { #if (NSEC_PER_SEC % HZ) == 0 /* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */ return div_u64(n, NSEC_PER_SEC / HZ); #elif (HZ % 512) == 0 /* overflow after 292 years if HZ = 1024 */ return div_u64(n * HZ / 512, NSEC_PER_SEC / 512); #else /* * Generic case - optimized for cases where HZ is a multiple of 3. * overflow after 64.99 years, exact for HZ = 60, 72, 90, 120 etc. */ return div_u64(n * 9, (9ull * NSEC_PER_SEC + HZ / 2) / HZ); #endif } EXPORT_SYMBOL(nsecs_to_jiffies64); /** * nsecs_to_jiffies - Convert nsecs in u64 to jiffies * * @n: nsecs in u64 * * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. * And this doesn't return MAX_JIFFY_OFFSET since this function is designed * for scheduler, not for use in device drivers to calculate timeout value. * * note: * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years */ unsigned long nsecs_to_jiffies(u64 n) { return (unsigned long)nsecs_to_jiffies64(n); } EXPORT_SYMBOL_GPL(nsecs_to_jiffies); /* * Add two timespec64 values and do a safety check for overflow. * It's assumed that both values are valid (>= 0). * And, each timespec64 is in normalized form. */ struct timespec64 timespec64_add_safe(const struct timespec64 lhs, const struct timespec64 rhs) { struct timespec64 res; set_normalized_timespec64(&res, (timeu64_t) lhs.tv_sec + rhs.tv_sec, lhs.tv_nsec + rhs.tv_nsec); if (unlikely(res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec)) { res.tv_sec = TIME64_MAX; res.tv_nsec = 0; } return res; } int get_timespec64(struct timespec64 *ts, const struct __kernel_timespec __user *uts) { struct __kernel_timespec kts; int ret; ret = copy_from_user(&kts, uts, sizeof(kts)); if (ret) return -EFAULT; ts->tv_sec = kts.tv_sec; /* Zero out the padding in compat mode */ if (in_compat_syscall()) kts.tv_nsec &= 0xFFFFFFFFUL; /* In 32-bit mode, this drops the padding */ ts->tv_nsec = kts.tv_nsec; return 0; } EXPORT_SYMBOL_GPL(get_timespec64); int put_timespec64(const struct timespec64 *ts, struct __kernel_timespec __user *uts) { struct __kernel_timespec kts = { .tv_sec = ts->tv_sec, .tv_nsec = ts->tv_nsec }; return copy_to_user(uts, &kts, sizeof(kts)) ? -EFAULT : 0; } EXPORT_SYMBOL_GPL(put_timespec64); static int __get_old_timespec32(struct timespec64 *ts64, const struct old_timespec32 __user *cts) { struct old_timespec32 ts; int ret; ret = copy_from_user(&ts, cts, sizeof(ts)); if (ret) return -EFAULT; ts64->tv_sec = ts.tv_sec; ts64->tv_nsec = ts.tv_nsec; return 0; } static int __put_old_timespec32(const struct timespec64 *ts64, struct old_timespec32 __user *cts) { struct old_timespec32 ts = { .tv_sec = ts64->tv_sec, .tv_nsec = ts64->tv_nsec }; return copy_to_user(cts, &ts, sizeof(ts)) ? -EFAULT : 0; } int get_old_timespec32(struct timespec64 *ts, const void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0; else return __get_old_timespec32(ts, uts); } EXPORT_SYMBOL_GPL(get_old_timespec32); int put_old_timespec32(const struct timespec64 *ts, void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0; else return __put_old_timespec32(ts, uts); } EXPORT_SYMBOL_GPL(put_old_timespec32); int get_itimerspec64(struct itimerspec64 *it, const struct __kernel_itimerspec __user *uit) { int ret; ret = get_timespec64(&it->it_interval, &uit->it_interval); if (ret) return ret; ret = get_timespec6