aboutsummaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/acpi/acpi_bus.h1
-rw-r--r--include/drm/drm_atomic_helper.h2
-rw-r--r--include/drm/drm_gpuvm.h2
-rw-r--r--include/drm/drm_prime.h7
-rw-r--r--include/linux/acpi.h22
-rw-r--r--include/linux/amd-pstate.h4
-rw-r--r--include/linux/arm_ffa.h2
-rw-r--r--include/linux/avf/virtchnl.h35
-rw-r--r--include/linux/blk-pm.h1
-rw-r--r--include/linux/blk_types.h4
-rw-r--r--include/linux/bpf.h5
-rw-r--r--include/linux/cache.h25
-rw-r--r--include/linux/closure.h9
-rw-r--r--include/linux/debugfs.h19
-rw-r--r--include/linux/dma-fence.h15
-rw-r--r--include/linux/dpll.h3
-rw-r--r--include/linux/ethtool.h75
-rw-r--r--include/linux/framer/framer-provider.h194
-rw-r--r--include/linux/framer/framer.h205
-rw-r--r--include/linux/framer/pef2256.h31
-rw-r--r--include/linux/fw_table.h3
-rw-r--r--include/linux/hid.h3
-rw-r--r--include/linux/highmem.h2
-rw-r--r--include/linux/hugetlb.h5
-rw-r--r--include/linux/ieee80211.h4
-rw-r--r--include/linux/io_uring_types.h3
-rw-r--r--include/linux/iommu.h1
-rw-r--r--include/linux/jbd2.h3
-rw-r--r--include/linux/kprobes.h13
-rw-r--r--include/linux/mdio.h1
-rw-r--r--include/linux/mlx5/driver.h3
-rw-r--r--include/linux/mlx5/mlx5_ifc.h54
-rw-r--r--include/linux/mm_types.h2
-rw-r--r--include/linux/netdevice.h142
-rw-r--r--include/linux/pagemap.h17
-rw-r--r--include/linux/phy.h81
-rw-r--r--include/linux/platform_data/microchip-ksz.h23
-rw-r--r--include/linux/platform_data/x86/asus-wmi.h3
-rw-r--r--include/linux/rethook.h7
-rw-r--r--include/linux/rtnetlink.h41
-rw-r--r--include/linux/skbuff.h20
-rw-r--r--include/linux/skmsg.h1
-rw-r--r--include/linux/stmmac.h1
-rw-r--r--include/linux/tcp.h256
-rw-r--r--include/linux/units.h1
-rw-r--r--include/linux/usb/phy.h13
-rw-r--r--include/linux/usb/r8152.h1
-rw-r--r--include/linux/vfio.h8
-rw-r--r--include/linux/virtio_vsock.h1
-rw-r--r--include/net/act_api.h2
-rw-r--r--include/net/addrconf.h12
-rw-r--r--include/net/af_unix.h1
-rw-r--r--include/net/af_vsock.h2
-rw-r--r--include/net/cfg80211.h46
-rw-r--r--include/net/dropreason-core.h6
-rw-r--r--include/net/genetlink.h2
-rw-r--r--include/net/if_inet6.h4
-rw-r--r--include/net/inet_sock.h5
-rw-r--r--include/net/ip.h10
-rw-r--r--include/net/ip6_fib.h4
-rw-r--r--include/net/mana/gdma.h7
-rw-r--r--include/net/neighbour.h2
-rw-r--r--include/net/netdev_rx_queue.h4
-rw-r--r--include/net/netfilter/nf_flow_table.h10
-rw-r--r--include/net/netlink.h2
-rw-r--r--include/net/netns/core.h1
-rw-r--r--include/net/netns/ipv4.h50
-rw-r--r--include/net/page_pool/helpers.h77
-rw-r--r--include/net/page_pool/types.h6
-rw-r--r--include/net/sock.h1
-rw-r--r--include/net/tcp.h9
-rw-r--r--include/net/tcp_ao.h6
-rw-r--r--include/net/tcp_states.h2
-rw-r--r--include/net/xdp_sock.h111
-rw-r--r--include/net/xdp_sock_drv.h34
-rw-r--r--include/net/xsk_buff_pool.h8
-rw-r--r--include/rdma/ib_umem.h9
-rw-r--r--include/rdma/ib_verbs.h1
-rw-r--r--include/scsi/scsi_device.h12
-rw-r--r--include/sound/cs35l41.h2
-rw-r--r--include/uapi/linux/bpf.h11
-rw-r--r--include/uapi/linux/ethtool.h13
-rw-r--r--include/uapi/linux/ethtool_netlink.h1
-rw-r--r--include/uapi/linux/fcntl.h3
-rw-r--r--include/uapi/linux/fuse.h10
-rw-r--r--include/uapi/linux/if_link.h521
-rw-r--r--include/uapi/linux/if_xdp.h47
-rw-r--r--include/uapi/linux/mptcp_pm.h2
-rw-r--r--include/uapi/linux/netdev.h41
-rw-r--r--include/uapi/linux/stddef.h2
-rw-r--r--include/uapi/linux/v4l2-subdev.h2
91 files changed, 2094 insertions, 381 deletions
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index afeed6e72049..1216d72c650f 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -542,6 +542,7 @@ int acpi_device_set_power(struct acpi_device *device, int state);
int acpi_bus_init_power(struct acpi_device *device);
int acpi_device_fix_up_power(struct acpi_device *device);
void acpi_device_fix_up_power_extended(struct acpi_device *adev);
+void acpi_device_fix_up_power_children(struct acpi_device *adev);
int acpi_bus_update_power(acpi_handle handle, int *state_p);
int acpi_device_update_power(struct acpi_device *device, int *state_p);
bool acpi_bus_power_manageable(acpi_handle handle);
diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h
index 536a0b0091c3..006b5c977ad7 100644
--- a/include/drm/drm_atomic_helper.h
+++ b/include/drm/drm_atomic_helper.h
@@ -97,6 +97,8 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
int drm_atomic_helper_prepare_planes(struct drm_device *dev,
struct drm_atomic_state *state);
+void drm_atomic_helper_unprepare_planes(struct drm_device *dev,
+ struct drm_atomic_state *state);
#define DRM_PLANE_COMMIT_ACTIVE_ONLY BIT(0)
#define DRM_PLANE_COMMIT_NO_DISABLE_AFTER_MODESET BIT(1)
diff --git a/include/drm/drm_gpuvm.h b/include/drm/drm_gpuvm.h
index bdfafc4a7705..c7a0594bdab1 100644
--- a/include/drm/drm_gpuvm.h
+++ b/include/drm/drm_gpuvm.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
#ifndef __DRM_GPUVM_H__
#define __DRM_GPUVM_H__
diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h
index a7abf9f3e697..2a1d01e5b56b 100644
--- a/include/drm/drm_prime.h
+++ b/include/drm/drm_prime.h
@@ -60,12 +60,19 @@ enum dma_data_direction;
struct drm_device;
struct drm_gem_object;
+struct drm_file;
/* core prime functions */
struct dma_buf *drm_gem_dmabuf_export(struct drm_device *dev,
struct dma_buf_export_info *exp_info);
void drm_gem_dmabuf_release(struct dma_buf *dma_buf);
+int drm_gem_prime_fd_to_handle(struct drm_device *dev,
+ struct drm_file *file_priv, int prime_fd, uint32_t *handle);
+int drm_gem_prime_handle_to_fd(struct drm_device *dev,
+ struct drm_file *file_priv, uint32_t handle, uint32_t flags,
+ int *prime_fd);
+
/* helper functions for exporting */
int drm_gem_map_attach(struct dma_buf *dma_buf,
struct dma_buf_attachment *attach);
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 54189e0e5f41..4db54e928b36 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -15,7 +15,6 @@
#include <linux/mod_devicetable.h>
#include <linux/property.h>
#include <linux/uuid.h>
-#include <linux/fw_table.h>
struct irq_domain;
struct irq_domain_ops;
@@ -25,22 +24,13 @@ struct irq_domain_ops;
#endif
#include <acpi/acpi.h>
-#ifdef CONFIG_ACPI_TABLE_LIB
-#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI)
-#define __init_or_acpilib
-#define __initdata_or_acpilib
-#else
-#define EXPORT_SYMBOL_ACPI_LIB(x)
-#define __init_or_acpilib __init
-#define __initdata_or_acpilib __initdata
-#endif
-
#ifdef CONFIG_ACPI
#include <linux/list.h>
#include <linux/dynamic_debug.h>
#include <linux/module.h>
#include <linux/mutex.h>
+#include <linux/fw_table.h>
#include <acpi/acpi_bus.h>
#include <acpi/acpi_drivers.h>
@@ -48,6 +38,16 @@ struct irq_domain_ops;
#include <acpi/acpi_io.h>
#include <asm/acpi.h>
+#ifdef CONFIG_ACPI_TABLE_LIB
+#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI)
+#define __init_or_acpilib
+#define __initdata_or_acpilib
+#else
+#define EXPORT_SYMBOL_ACPI_LIB(x)
+#define __init_or_acpilib __init
+#define __initdata_or_acpilib __initdata
+#endif
+
static inline acpi_handle acpi_device_handle(struct acpi_device *adev)
{
return adev ? adev->handle : NULL;
diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h
index 446394f84606..6ad02ad9c7b4 100644
--- a/include/linux/amd-pstate.h
+++ b/include/linux/amd-pstate.h
@@ -70,6 +70,10 @@ struct amd_cpudata {
u32 nominal_perf;
u32 lowest_nonlinear_perf;
u32 lowest_perf;
+ u32 min_limit_perf;
+ u32 max_limit_perf;
+ u32 min_limit_freq;
+ u32 max_limit_freq;
u32 max_freq;
u32 min_freq;
diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h
index 1abedb5b2e48..3d0fde57ba90 100644
--- a/include/linux/arm_ffa.h
+++ b/include/linux/arm_ffa.h
@@ -209,6 +209,8 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) { return false; }
#define module_ffa_driver(__ffa_driver) \
module_driver(__ffa_driver, ffa_register, ffa_unregister)
+extern struct bus_type ffa_bus_type;
+
/* FFA transport related */
struct ffa_partition_info {
u16 id;
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 6b3acf15be5c..a44d9dc7e3eb 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -118,6 +118,7 @@ enum virtchnl_ops {
VIRTCHNL_OP_GET_STATS = 15,
VIRTCHNL_OP_RSVD = 16,
VIRTCHNL_OP_EVENT = 17, /* must ALWAYS be 17 */
+ VIRTCHNL_OP_CONFIG_RSS_HFUNC = 18,
/* opcode 19 is reserved */
VIRTCHNL_OP_IWARP = 20, /* advanced opcode */
VIRTCHNL_OP_RDMA = VIRTCHNL_OP_IWARP,
@@ -911,6 +912,29 @@ struct virtchnl_rss_hena {
VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hena);
+/* Type of RSS algorithm */
+enum virtchnl_rss_algorithm {
+ VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC = 0,
+ VIRTCHNL_RSS_ALG_R_ASYMMETRIC = 1,
+ VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC = 2,
+ VIRTCHNL_RSS_ALG_XOR_SYMMETRIC = 3,
+};
+
+/* VIRTCHNL_OP_CONFIG_RSS_HFUNC
+ * VF sends this message to configure the RSS hash function. Only supported
+ * if both PF and VF drivers set the VIRTCHNL_VF_OFFLOAD_RSS_PF bit during
+ * configuration negotiation.
+ * The hash function is initialized to VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC
+ * by the PF.
+ */
+struct virtchnl_rss_hfunc {
+ u16 vsi_id;
+ u16 rss_algorithm; /* enum virtchnl_rss_algorithm */
+ u32 reserved;
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hfunc);
+
/* VIRTCHNL_OP_ENABLE_CHANNELS
* VIRTCHNL_OP_DISABLE_CHANNELS
* VF sends these messages to enable or disable channels based on
@@ -1095,14 +1119,6 @@ enum virtchnl_vfr_states {
VIRTCHNL_VFR_VFACTIVE,
};
-/* Type of RSS algorithm */
-enum virtchnl_rss_algorithm {
- VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC = 0,
- VIRTCHNL_RSS_ALG_R_ASYMMETRIC = 1,
- VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC = 2,
- VIRTCHNL_RSS_ALG_XOR_SYMMETRIC = 3,
-};
-
#define VIRTCHNL_MAX_NUM_PROTO_HDRS 32
#define PROTO_HDR_SHIFT 5
#define PROTO_HDR_FIELD_START(proto_hdr_type) ((proto_hdr_type) << PROTO_HDR_SHIFT)
@@ -1542,6 +1558,9 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
vrl->lut_entries);
}
break;
+ case VIRTCHNL_OP_CONFIG_RSS_HFUNC:
+ valid_len = sizeof(struct virtchnl_rss_hfunc);
+ break;
case VIRTCHNL_OP_GET_RSS_HENA_CAPS:
break;
case VIRTCHNL_OP_SET_RSS_HENA:
diff --git a/include/linux/blk-pm.h b/include/linux/blk-pm.h
index 2580e05a8ab6..004b38a538ff 100644
--- a/include/linux/blk-pm.h
+++ b/include/linux/blk-pm.h
@@ -15,7 +15,6 @@ extern int blk_pre_runtime_suspend(struct request_queue *q);
extern void blk_post_runtime_suspend(struct request_queue *q, int err);
extern void blk_pre_runtime_resume(struct request_queue *q);
extern void blk_post_runtime_resume(struct request_queue *q);
-extern void blk_set_runtime_active(struct request_queue *q);
#else
static inline void blk_pm_runtime_init(struct request_queue *q,
struct device *dev) {}
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d5c5e59ddbd2..b29ebd53417d 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -49,9 +49,10 @@ struct block_device {
bool bd_write_holder;
bool bd_has_submit_bio;
dev_t bd_dev;
+ struct inode *bd_inode; /* will die */
+
atomic_t bd_openers;
spinlock_t bd_size_lock; /* for bd_inode->i_size updates */
- struct inode * bd_inode; /* will die */
void * bd_claiming;
void * bd_holder;
const struct blk_holder_ops *bd_holder_ops;
@@ -69,6 +70,7 @@ struct block_device {
#ifdef CONFIG_FAIL_MAKE_REQUEST
bool bd_make_it_fail;
#endif
+ bool bd_ro_warned;
/*
* keep this out-of-line as it's both big and not needed in the fast
* path
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 258ba232e302..d5d8e2083610 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1347,6 +1347,8 @@ static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
struct bpf_func_info_aux {
u16 linkage;
bool unreliable;
+ bool called : 1;
+ bool verified : 1;
};
enum bpf_jit_poke_reason {
@@ -3177,6 +3179,9 @@ enum bpf_text_poke_type {
int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
void *addr1, void *addr2);
+void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+ struct bpf_prog *new, struct bpf_prog *old);
+
void *bpf_arch_text_copy(void *dst, void *src, size_t len);
int bpf_arch_text_invalidate(void *dst, size_t len);
diff --git a/include/linux/cache.h b/include/linux/cache.h
index 9900d20b76c2..0ecb17bb6883 100644
--- a/include/linux/cache.h
+++ b/include/linux/cache.h
@@ -85,6 +85,31 @@
#define cache_line_size() L1_CACHE_BYTES
#endif
+#ifndef __cacheline_group_begin
+#define __cacheline_group_begin(GROUP) \
+ __u8 __cacheline_group_begin__##GROUP[0]
+#endif
+
+#ifndef __cacheline_group_end
+#define __cacheline_group_end(GROUP) \
+ __u8 __cacheline_group_end__##GROUP[0]
+#endif
+
+#ifndef CACHELINE_ASSERT_GROUP_MEMBER
+#define CACHELINE_ASSERT_GROUP_MEMBER(TYPE, GROUP, MEMBER) \
+ BUILD_BUG_ON(!(offsetof(TYPE, MEMBER) >= \
+ offsetofend(TYPE, __cacheline_group_begin__##GROUP) && \
+ offsetofend(TYPE, MEMBER) <= \
+ offsetof(TYPE, __cacheline_group_end__##GROUP)))
+#endif
+
+#ifndef CACHELINE_ASSERT_GROUP_SIZE
+#define CACHELINE_ASSERT_GROUP_SIZE(TYPE, GROUP, SIZE) \
+ BUILD_BUG_ON(offsetof(TYPE, __cacheline_group_end__##GROUP) - \
+ offsetofend(TYPE, __cacheline_group_begin__##GROUP) > \
+ SIZE)
+#endif
+
/*
* Helper to add padding within a struct to ensure data fall into separate
* cachelines.
diff --git a/include/linux/closure.h b/include/linux/closure.h
index de7bb47d8a46..c554c6a08768 100644
--- a/include/linux/closure.h
+++ b/include/linux/closure.h
@@ -104,7 +104,7 @@
struct closure;
struct closure_syncer;
-typedef void (closure_fn) (struct closure *);
+typedef void (closure_fn) (struct work_struct *);
extern struct dentry *bcache_debug;
struct closure_waitlist {
@@ -254,7 +254,7 @@ static inline void closure_queue(struct closure *cl)
INIT_WORK(&cl->work, cl->work.func);
BUG_ON(!queue_work(wq, &cl->work));
} else
- cl->fn(cl);
+ cl->fn(&cl->work);
}
/**
@@ -309,6 +309,11 @@ static inline void closure_wake_up(struct closure_waitlist *list)
__closure_wake_up(list);
}
+#define CLOSURE_CALLBACK(name) void name(struct work_struct *ws)
+#define closure_type(name, type, member) \
+ struct closure *cl = container_of(ws, struct closure, work); \
+ type *name = container_of(cl, type, member)
+
/**
* continue_at - jump to another function with barrier
*
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index ea2d919fd9c7..c9c65b132c0f 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -171,6 +171,25 @@ ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf,
ssize_t debugfs_read_file_str(struct file *file, char __user *user_buf,
size_t count, loff_t *ppos);
+/**
+ * struct debugfs_cancellation - cancellation data
+ * @list: internal, for keeping track
+ * @cancel: callback to call
+ * @cancel_data: extra data for the callback to call
+ */
+struct debugfs_cancellation {
+ struct list_head list;
+ void (*cancel)(struct dentry *, void *);
+ void *cancel_data;
+};
+
+void __acquires(cancellation)
+debugfs_enter_cancellation(struct file *file,
+ struct debugfs_cancellation *cancellation);
+void __releases(cancellation)
+debugfs_leave_cancellation(struct file *file,
+ struct debugfs_cancellation *cancellation);
+
#else
#include <linux/err.h>
diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index ebe78bd3d121..b3772edca2e6 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -499,6 +499,21 @@ static inline bool dma_fence_is_later(struct dma_fence *f1,
}
/**
+ * dma_fence_is_later_or_same - return true if f1 is later or same as f2
+ * @f1: the first fence from the same context
+ * @f2: the second fence from the same context
+ *
+ * Returns true if f1 is chronologically later than f2 or the same fence. Both
+ * fences must be from the same context, since a seqno is not re-used across
+ * contexts.
+ */
+static inline bool dma_fence_is_later_or_same(struct dma_fence *f1,
+ struct dma_fence *f2)
+{
+ return f1 == f2 || dma_fence_is_later(f1, f2);
+}
+
+/**
* dma_fence_later - return the chronologically later fence
* @f1: the first fence from the same context
* @f2: the second fence from the same context
diff --git a/include/linux/dpll.h b/include/linux/dpll.h
index 578fc5fa3750..b1a5f9ca8ee5 100644
--- a/include/linux/dpll.h
+++ b/include/linux/dpll.h
@@ -17,9 +17,6 @@ struct dpll_pin;
struct dpll_device_ops {
int (*mode_get)(const struct dpll_device *dpll, void *dpll_priv,
enum dpll_mode *mode, struct netlink_ext_ack *extack);
- bool (*mode_supported)(const struct dpll_device *dpll, void *dpll_priv,
- const enum dpll_mode mode,
- struct netlink_ext_ack *extack);
int (*lock_status_get)(const struct dpll_device *dpll, void *dpll_priv,
enum dpll_lock_status *status,
struct netlink_ext_ack *extack);
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index c2bb74143eda..cfcd952a1d4f 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -95,6 +95,7 @@ struct kernel_ethtool_ringparam {
* @ETHTOOL_RING_USE_TX_PUSH: capture for setting tx_push
* @ETHTOOL_RING_USE_RX_PUSH: capture for setting rx_push
* @ETHTOOL_RING_USE_TX_PUSH_BUF_LEN: capture for setting tx_push_buf_len
+ * @ETHTOOL_RING_USE_TCP_DATA_SPLIT: capture for setting tcp_data_split
*/
enum ethtool_supported_ring_param {
ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0),
@@ -102,6 +103,7 @@ enum ethtool_supported_ring_param {
ETHTOOL_RING_USE_TX_PUSH = BIT(2),
ETHTOOL_RING_USE_RX_PUSH = BIT(3),
ETHTOOL_RING_USE_TX_PUSH_BUF_LEN = BIT(4),
+ ETHTOOL_RING_USE_TCP_DATA_SPLIT = BIT(5),
};
#define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit))
@@ -595,9 +597,46 @@ struct ethtool_mm_stats {
};
/**
+ * struct ethtool_rxfh_param - RXFH (RSS) parameters
+ * @hfunc: Defines the current RSS hash function used by HW (or to be set to).
+ * Valid values are one of the %ETH_RSS_HASH_*.
+ * @indir_size: On SET, the array size of the user buffer for the
+ * indirection table, which may be zero, or
+ * %ETH_RXFH_INDIR_NO_CHANGE. On GET (read from the driver),
+ * the array size of the hardware indirection table.
+ * @indir: The indirection table of size @indir_size entries.
+ * @key_size: On SET, the array size of the user buffer for the hash key,
+ * which may be zero. On GET (read from the driver), the size of the
+ * hardware hash key.
+ * @key: The hash key of size @key_size bytes.
+ * @rss_context: RSS context identifier. Context 0 is the default for normal
+ * traffic; other contexts can be referenced as the destination for RX flow
+ * classification rules. On SET, %ETH_RXFH_CONTEXT_ALLOC is used
+ * to allocate a new RSS context; on return this field will
+ * contain the ID of the newly allocated context.
+ * @rss_delete: Set to non-ZERO to remove the @rss_context context.
+ * @input_xfrm: Defines how the input data is transformed. Valid values are one
+ * of %RXH_XFRM_*.
+ */
+struct ethtool_rxfh_param {
+ u8 hfunc;
+ u32 indir_size;
+ u32 *indir;
+ u32 key_size;
+ u8 *key;
+ u32 rss_context;
+ u8 rss_delete;
+ u8 input_xfrm;
+};
+
+/**
* struct ethtool_ops - optional netdev operations
* @cap_link_lanes_supported: indicates if the driver supports lanes
* parameter.
+ * @cap_rss_ctx_supported: indicates if the driver supports RSS
+ * contexts.
+ * @cap_rss_sym_xor_supported: indicates if the driver supports symmetric-xor
+ * RSS.
* @supported_coalesce_params: supported types of interrupt coalescing.
* @supported_ring_params: supported ring params.
* @get_drvinfo: Report driver/device information. Modern drivers no
@@ -694,15 +733,6 @@ struct ethtool_mm_stats {
* will remain unchanged.
* Returns a negative error code or zero. An error code must be returned
* if at least one unsupported change was requested.
- * @get_rxfh_context: Get the contents of the RX flow hash indirection table,
- * hash key, and/or hash function assiciated to the given rss context.
- * Returns a negative error code or zero.
- * @set_rxfh_context: Create, remove and configure RSS contexts. Allows setting
- * the contents of the RX flow hash indirection table, hash key, and/or
- * hash function associated to the given context. Arguments which are set
- * to %NULL or zero will remain unchanged.
- * Returns a negative error code or zero. An error code must be returned
- * if at least one unsupported change was requested.
* @get_channels: Get number of channels.
* @set_channels: Set number of channels. Returns a negative error code or
* zero.
@@ -785,6 +815,8 @@ struct ethtool_mm_stats {
*/
struct ethtool_ops {
u32 cap_link_lanes_supported:1;
+ u32 cap_rss_ctx_supported:1;
+ u32 cap_rss_sym_xor_supported:1;
u32 supported_coalesce_params;
u32 supported_ring_params;
void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *);
@@ -844,15 +876,9 @@ struct ethtool_ops {
int (*reset)(struct net_device *, u32 *);
u32 (*get_rxfh_key_size)(struct net_device *);
u32 (*get_rxfh_indir_size)(struct net_device *);
- int (*get_rxfh)(struct net_device *, u32 *indir, u8 *key,
- u8 *hfunc);
- int (*set_rxfh)(struct net_device *, const u32 *indir,
- const u8 *key, const u8 hfunc);
- int (*get_rxfh_context)(struct net_device *, u32 *indir, u8 *key,
- u8 *hfunc, u32 rss_context);
- int (*set_rxfh_context)(struct net_device *, const u32 *indir,
- const u8 *key, const u8 hfunc,
- u32 *rss_context, bool delete);
+ int (*get_rxfh)(struct net_device *, struct ethtool_rxfh_param *);
+ int (*set_rxfh)(struct net_device *, struct ethtool_rxfh_param *,
+ struct netlink_ext_ack *extack);
void (*get_channels)(struct net_device *, struct ethtool_channels *);
int (*set_channels)(struct net_device *, struct ethtool_channels *);
int (*get_dump_flag)(struct net_device *, struct ethtool_dump *);
@@ -1061,6 +1087,19 @@ int ethtool_get_ts_info_by_layer(struct net_device *dev, struct ethtool_ts_info
*/
extern __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...);
+/**
+ * ethtool_puts - Write string to ethtool string data
+ * @data: Pointer to a pointer to the start of string to update
+ * @str: String to write
+ *
+ * Write string to *data without a trailing newline. Update *data
+ * to point at start of next string.
+ *
+ * Prefer this function to ethtool_sprintf() when given only
+ * two arguments or if @fmt is just "%s".
+ */
+extern void ethtool_puts(u8 **data, const char *str);
+
/* Link mode to forced speed capabilities maps */
struct ethtool_forced_speed_map {
u32 speed;
diff --git a/include/linux/framer/framer-provider.h b/include/linux/framer/framer-provider.h
new file mode 100644
index 000000000000..782cd5fc83d5
--- /dev/null
+++ b/include/linux/framer/framer-provider.h
@@ -0,0 +1,194 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Generic framer profider header file
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+
+#ifndef __DRIVERS_PROVIDER_FRAMER_H
+#define __DRIVERS_PROVIDER_FRAMER_H
+
+#include <linux/export.h>
+#include <linux/framer/framer.h>
+#include <linux/types.h>
+
+#define FRAMER_FLAG_POLL_STATUS BIT(0)
+
+/**
+ * struct framer_ops - set of function pointers for performing framer operations
+ * @init: operation to be performed for initializing the framer
+ * @exit: operation to be performed while exiting
+ * @power_on: powering on the framer
+ * @power_off: powering off the framer
+ * @flags: OR-ed flags (FRAMER_FLAG_*) to ask for core functionality
+ * - @FRAMER_FLAG_POLL_STATUS:
+ * Ask the core to perform a polling to get the framer status and
+ * notify consumers on change.
+ * The framer should call @framer_notify_status_change() when it
+ * detects a status change. This is usually done using interrupts.
+ * If the framer cannot detect this change, it can ask the core for
+ * a status polling. The core will call @get_status() periodically
+ * and, on change detected, it will notify the consumer.
+ * the @get_status()
+ * @owner: the module owner containing the ops
+ */
+struct framer_ops {
+ int (*init)(struct framer *framer);
+ void (*exit)(struct framer *framer);
+ int (*power_on)(struct framer *framer);
+ int (*power_off)(struct framer *framer);
+
+ /**
+ * @get_status:
+ *
+ * Optional.
+ *
+ * Used to get the framer status. framer_init() must have
+ * been called on the framer.
+ *
+ * Returns: 0 if successful, an negative error code otherwise
+ */
+ int (*get_status)(struct framer *framer, struct framer_status *status);
+
+ /**
+ * @set_config:
+ *
+ * Optional.
+ *
+ * Used to set the framer configuration. framer_init() must have
+ * been called on the framer.
+ *
+ * Returns: 0 if successful, an negative error code otherwise
+ */
+ int (*set_config)(struct framer *framer, const struct framer_config *config);
+
+ /**
+ * @get_config:
+ *
+ * Optional.
+ *
+ * Used to get the framer configuration. framer_init() must have
+ * been called on the framer.
+ *
+ * Returns: 0 if successful, an negative error code otherwise
+ */
+ int (*get_config)(struct framer *framer, struct framer_config *config);
+
+ u32 flags;
+ struct module *owner;
+};
+
+/**
+ * struct framer_provider - represents the framer provider
+ * @dev: framer provider device
+ * @children: can be used to override the default (dev->of_node) child node
+ * @owner: the module owner having of_xlate
+ * @list: to maintain a linked list of framer providers
+ * @of_xlate: function pointer to obtain framer instance from framer pointer
+ */
+struct framer_provider {
+ struct device *dev;
+ struct module *owner;
+ struct list_head list;
+ struct framer * (*of_xlate)(struct device *dev,
+ struct of_phandle_args *args);
+};
+
+static inline void framer_set_drvdata(struct framer *framer, void *data)
+{
+ dev_set_drvdata(&framer->dev, data);
+}
+
+static inline void *framer_get_drvdata(struct framer *framer)
+{
+ return dev_get_drvdata(&framer->dev);
+}
+
+#if IS_ENABLED(CONFIG_GENERIC_FRAMER)
+
+/* Create and destroy a framer */
+struct framer *framer_create(struct device *dev, struct device_node *node,
+ const struct framer_ops *ops);
+void framer_destroy(struct framer *framer);
+
+/* devm version */
+struct framer *devm_framer_create(struct device *dev, struct device_node *node,
+ const struct framer_ops *ops);
+
+struct framer *framer_provider_simple_of_xlate(struct device *dev,
+ struct of_phandle_args *args);
+
+struct framer_provider *
+__framer_provider_of_register(struct device *dev, struct module *owner,
+ struct framer *(*of_xlate)(struct device *dev,
+ struct of_phandle_args *args));
+
+void framer_provider_of_unregister(struct framer_provider *framer_provider);
+
+struct framer_provider *
+__devm_framer_provider_of_register(struct device *dev, struct module *owner,
+ struct framer *(*of_xlate)(struct device *dev,
+ struct of_phandle_args *args));
+
+void framer_notify_status_change(struct framer *framer);
+
+#else /* IS_ENABLED(CONFIG_GENERIC_FRAMER) */
+
+static inline struct framer *framer_create(struct device *dev, struct device_node *node,
+ const struct framer_ops *ops)
+{
+ return ERR_PTR(-ENOSYS);
+}
+
+static inline void framer_destroy(struct framer *framer)
+{
+}
+
+/* devm version */
+static inline struct framer *devm_framer_create(struct device *dev, struct device_node *node,
+ const struct framer_ops *ops)
+{
+ return ERR_PTR(-ENOSYS);
+}
+
+static inline struct framer *framer_provider_simple_of_xlate(struct device *dev,
+ struct of_phandle_args *args)
+{
+ return ERR_PTR(-ENOSYS);
+}
+
+static inline struct framer_provider *
+__framer_provider_of_register(struct device *dev, struct module *owner,
+ struct framer *(*of_xlate)(struct device *dev,
+ struct of_phandle_args *args))
+{
+ return ERR_PTR(-ENOSYS);
+}
+
+void framer_provider_of_unregister(struct framer_provider *framer_provider)
+{
+}
+
+static inline struct framer_provider *
+__devm_framer_provider_of_register(struct device *dev, struct module *owner,
+ struct framer *(*of_xlate)(struct device *dev,
+ struct of_phandle_args *args))
+{
+ return ERR_PTR(-ENOSYS);
+}
+
+void framer_notify_status_change(struct framer *framer)
+{
+}
+
+#endif /* IS_ENABLED(CONFIG_GENERIC_FRAMER) */
+
+#define framer_provider_of_register(dev, xlate) \
+ __framer_provider_of_register((dev), THIS_MODULE, (xlate))
+
+#define devm_framer_provider_of_register(dev, xlate) \
+ __devm_framer_provider_of_register((dev), THIS_MODULE, (xlate))
+
+#endif /* __DRIVERS_PROVIDER_FRAMER_H */
diff --git a/include/linux/framer/framer.h b/include/linux/framer/framer.h
new file mode 100644
index 000000000000..9a9b88962c29
--- /dev/null
+++ b/include/linux/framer/framer.h
@@ -0,0 +1,205 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Generic framer header file
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+
+#ifndef __DRIVERS_FRAMER_H
+#define __DRIVERS_FRAMER_H
+
+#include <linux/err.h>
+#include <linux/mutex.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/device.h>
+#include <linux/workqueue.h>
+
+/**
+ * enum framer_iface - Framer interface
+ * @FRAMER_IFACE_E1: E1 interface
+ * @FRAMER_IFACE_T1: T1 interface
+ */
+enum framer_iface {
+ FRAMER_IFACE_E1,
+ FRAMER_IFACE_T1,
+};
+
+/**
+ * enum framer_clock_type - Framer clock type
+ * @FRAMER_CLOCK_EXT: External clock
+ * @FRAMER_CLOCK_INT: Internal clock
+ */
+enum framer_clock_type {
+ FRAMER_CLOCK_EXT,
+ FRAMER_CLOCK_INT,
+};
+
+/**
+ * struct framer_config - Framer configuration
+ * @iface: Framer line interface
+ * @clock_type: Framer clock type
+ * @line_clock_rate: Framer line clock rate
+ */
+struct framer_config {
+ enum framer_iface iface;
+ enum framer_clock_type clock_type;
+ unsigned long line_clock_rate;
+};
+
+/**
+ * struct framer_status - Framer status
+ * @link_is_on: Framer link state. true, the link is on, false, the link is off.
+ */
+struct framer_status {
+ bool link_is_on;
+};
+
+/**
+ * enum framer_event - Event available for notification
+ * @FRAMER_EVENT_STATUS: Event notified on framer_status changes
+ */
+enum framer_event {
+ FRAMER_EVENT_STATUS,
+};
+
+/**
+ * struct framer - represents the framer device
+ * @dev: framer device
+ * @id: id of the framer device
+ * @ops: function pointers for performing framer operations
+ * @mutex: mutex to protect framer_ops
+ * @init_count: used to protect when the framer is used by multiple consumers
+ * @power_count: used to protect when the framer is used by multiple consumers
+ * @pwr: power regulator associated with the framer
+ * @notify_status_work: work structure used for status notifications
+ * @notifier_list: notifier list used for notifications
+ * @polling_work: delayed work structure used for the polling task
+ * @prev_status: previous read status used by the polling task to detect changes
+ */
+struct framer {
+ struct device dev;
+ int id;
+ const struct framer_ops *ops;
+ struct mutex mutex; /* Protect framer */
+ int init_count;
+ int power_count;
+ struct regulator *pwr;
+ struct work_struct notify_status_work;
+ struct blocking_notifier_head notifier_list;
+ struct delayed_work polling_work;
+ struct framer_status prev_status;
+};
+
+#if IS_ENABLED(CONFIG_GENERIC_FRAMER)
+int framer_pm_runtime_get(struct framer *framer);
+int framer_pm_runtime_get_sync(struct framer *framer);
+int framer_pm_runtime_put(struct framer *framer);
+int framer_pm_runtime_put_sync(struct framer *framer);
+int framer_init(struct framer *framer);
+int framer_exit(struct framer *framer);
+int framer_power_on(struct framer *framer);
+int framer_power_off(struct framer *framer);
+int framer_get_status(struct framer *framer, struct framer_status *status);
+int framer_get_config(struct framer *framer, struct framer_config *config);
+int framer_set_config(struct framer *framer, const struct framer_config *config);
+int framer_notifier_register(struct framer *framer, struct notifier_block *nb);
+int framer_notifier_unregister(struct framer *framer, struct notifier_block *nb);
+
+struct framer *framer_get(struct device *dev, const char *con_id);
+void framer_put(struct device *dev, struct framer *framer);
+
+struct framer *devm_framer_get(struct device *dev, const char *con_id);
+struct framer *devm_framer_optional_get(struct device *dev, const char *con_id);
+#else
+static inline int framer_pm_runtime_get(struct framer *framer)
+{
+ return -ENOSYS;
+}
+
+static inline int framer_pm_runtime_get_sync(struct framer *framer)
+{
+ return -ENOSYS;
+}
+
+static inline int framer_pm_runtime_put(struct framer *framer)
+{
+ return -ENOSYS;
+}
+
+static inline int framer_pm_runtime_put_sync(struct framer *framer)
+{
+ return -ENOSYS;
+}
+
+static inline int framer_init(struct framer *framer)
+{
+ return -ENOSYS;
+}
+
+static inline int framer_exit(struct framer *framer)
+{
+ return -ENOSYS;
+}
+
+static inline int framer_power_on(struct framer *framer)
+{
+ return -ENOSYS;
+}
+
+static inline int framer_power_off(struct framer *framer)
+{
+ return -ENOSYS;
+}
+
+static inline int framer_get_status(struct framer *framer, struct framer_status *status)
+{
+ return -ENOSYS;
+}
+
+static inline int framer_get_config(struct framer *framer, struct framer_config *config)
+{
+ return -ENOSYS;
+}
+
+static inline int framer_set_config(struct framer *framer, const struct framer_config *config)
+{
+ return -ENOSYS;
+}
+
+static inline int framer_notifier_register(struct framer *framer,
+ struct notifier_block *nb)
+{
+ return -ENOSYS;
+}
+
+static inline int framer_notifier_unregister(struct framer *framer,
+ struct notifier_block *nb)
+{
+ return -ENOSYS;
+}
+
+struct framer *framer_get(struct device *dev, const char *con_id)
+{
+ return ERR_PTR(-ENOSYS);
+}
+
+void framer_put(struct device *dev, struct framer *framer)
+{
+}
+
+static inline struct framer *devm_framer_get(struct device *dev, const char *con_id)
+{
+ return ERR_PTR(-ENOSYS);
+}
+
+static inline struct framer *devm_framer_optional_get(struct device *dev, const char *con_id)
+{
+ return NULL;
+}
+
+#endif
+
+#endif /* __DRIVERS_FRAMER_H */
diff --git a/include/linux/framer/pef2256.h b/include/linux/framer/pef2256.h
new file mode 100644
index 000000000000..71d80af58c40
--- /dev/null
+++ b/include/linux/framer/pef2256.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * PEF2256 consumer API
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+#ifndef __PEF2256_H__
+#define __PEF2256_H__
+
+#include <linux/types.h>
+
+struct pef2256;
+struct regmap;
+
+/* Retrieve the PEF2256 regmap */
+struct regmap *pef2256_get_regmap(struct pef2256 *pef2256);
+
+/* PEF2256 hardware versions */
+enum pef2256_version {
+ PEF2256_VERSION_UNKNOWN,
+ PEF2256_VERSION_1_2,
+ PEF2256_VERSION_2_1,
+ PEF2256_VERSION_2_2,
+};
+
+/* Get the PEF2256 hardware version */
+enum pef2256_version pef2256_get_version(struct pef2256 *pef2256);
+
+#endif /* __PEF2256_H__ */
diff --git a/include/linux/fw_table.h b/include/linux/fw_table.h
index ff8fa58d5818..ca49947f0a77 100644
--- a/include/linux/fw_table.h
+++ b/include/linux/fw_table.h
@@ -25,9 +25,6 @@ struct acpi_subtable_proc {
int count;
};
-#include <linux/acpi.h>
-#include <acpi/acpi.h>
-
union acpi_subtable_headers {
struct acpi_subtable_header common;
struct acpi_hmat_structure hmat;
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 5a8387a4a712..bf43f3ff6664 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -679,6 +679,7 @@ struct hid_device { /* device report descriptor */
struct list_head debug_list;
spinlock_t debug_list_lock;
wait_queue_head_t debug_wait;
+ struct kref ref;
unsigned int id; /* system unique id */
@@ -687,6 +688,8 @@ struct hid_device { /* device report descriptor */
#endif /* CONFIG_BPF */
};
+void hiddev_free(struct kref *ref);
+
#define to_hid_device(pdev) \
container_of(pdev, struct hid_device, dev)
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 4cacc0e43b51..be20cff4ba73 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -454,7 +454,7 @@ static inline void memcpy_from_folio(char *to, struct folio *folio,
memcpy(to, from, chunk);
kunmap_local(from);
- from += chunk;
+ to += chunk;
offset += chunk;
len -= chunk;
} while (len > 0);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d3acecc5db4b..236ec7b63c54 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -1268,10 +1268,7 @@ static inline bool __vma_shareable_lock(struct vm_area_struct *vma)
return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data;
}
-static inline bool __vma_private_lock(struct vm_area_struct *vma)
-{
- return (!(vma->vm_flags & VM_MAYSHARE)) && vma->vm_private_data;
-}
+bool __vma_private_lock(struct vm_area_struct *vma);
/*
* Safe version of huge_pte_offset() to check the locks. See comments
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 5e5ea216f341..8ad008591e32 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2830,12 +2830,14 @@ ieee80211_he_oper_size(const u8 *he_oper_ie)
static inline const struct ieee80211_he_6ghz_oper *
ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper)
{
- const u8 *ret = (const void *)&he_oper->optional;
+ const u8 *ret;
u32 he_oper_params;
if (!he_oper)
return NULL;
+ ret = (const void *)&he_oper->optional;
+
he_oper_params = le32_to_cpu(he_oper->he_oper_params);
if (!(he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO))
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index d3009d56af0b..805bb635cdf5 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -340,6 +340,9 @@ struct io_ring_ctx {
struct list_head io_buffers_cache;
+ /* deferred free list, protected by ->uring_lock */
+ struct hlist_head io_buf_list;
+
/* Keep this last, we don't need it for the fast path */
struct wait_queue_head poll_wq;
struct io_restriction restrictions;
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index ec289c1016f5..6291aa7b079b 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -845,6 +845,7 @@ static inline void dev_iommu_priv_set(struct device *dev, void *priv)
dev->iommu->priv = priv;
}
+extern struct mutex iommu_probe_device_lock;
int iommu_probe_device(struct device *dev);
int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 6dcbb4eb80fb..beb30719ee16 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1374,6 +1374,9 @@ JBD2_FEATURE_INCOMPAT_FUNCS(csum2, CSUM_V2)
JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3)
JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT)
+/* Journal high priority write IO operation flags */
+#define JBD2_JOURNAL_REQ_FLAGS (REQ_META | REQ_SYNC | REQ_IDLE)
+
/*
* Journal flag definitions
*/
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index ab1da3142b06..0ff44d6633e3 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -139,7 +139,7 @@ static inline bool kprobe_ftrace(struct kprobe *p)
*
*/
struct kretprobe_holder {
- struct kretprobe *rp;
+ struct kretprobe __rcu *rp;
struct objpool_head pool;
};
@@ -197,10 +197,8 @@ extern int arch_trampoline_kprobe(struct kprobe *p);
#ifdef CONFIG_KRETPROBE_ON_RETHOOK
static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri)
{
- RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(),
- "Kretprobe is accessed from instance under preemptive context");
-
- return (struct kretprobe *)READ_ONCE(ri->node.rethook->data);
+ /* rethook::data is non-changed field, so that you can access it freely. */
+ return (struct kretprobe *)ri->node.rethook->data;
}
static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri)
{
@@ -245,10 +243,7 @@ unsigned long kretprobe_trampoline_handler(struct pt_regs *regs,
static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri)
{
- RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(),
- "Kretprobe is accessed from instance under preemptive context");
-
- return READ_ONCE(ri->rph->rp);
+ return rcu_dereference_check(ri->rph->rp, rcu_read_lock_any_held());
}
static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri)
diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index 007fd9c3e4b6..79ceee3c8673 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -38,6 +38,7 @@ struct mdio_device {
/* Bus address of the MDIO device (0-31) */
int addr;
int flags;
+ int reset_state;
struct gpio_desc *reset_gpio;
struct reset_control *reset_ctrl;
unsigned int reset_assert_delay;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index d2b8d4a74a30..7ee5b79ff3d6 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -150,6 +150,7 @@ enum {
MLX5_REG_MTPPSE = 0x9054,
MLX5_REG_MTUTC = 0x9055,
MLX5_REG_MPEGC = 0x9056,
+ MLX5_REG_MPIR = 0x9059,
MLX5_REG_MCQS = 0x9060,
MLX5_REG_MCQI = 0x9061,
MLX5_REG_MCC = 0x9062,
@@ -678,6 +679,8 @@ struct mlx5e_resources {
struct mlx5_td td;
u32 mkey;
struct mlx5_sq_bfreg bfreg;
+#define MLX5_MAX_NUM_TC 8
+ u32 tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC];
} hw_objs;
struct net_device *uplink_netdev;
struct mutex uplink_netdev_lock;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index ce2e71cd6d2a..fee20fc010c2 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -435,7 +435,7 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
u8 flow_table_modify[0x1];
u8 reformat[0x1];
u8 decap[0x1];
- u8 reserved_at_9[0x1];
+ u8 reset_root_to_default[0x1];
u8 pop_vlan[0x1];
u8 push_vlan[0x1];
u8 reserved_at_c[0x1];
@@ -621,7 +621,7 @@ struct mlx5_ifc_fte_match_set_misc_bits {
u8 reserved_at_140[0x8];
u8 bth_dst_qp[0x18];
- u8 reserved_at_160[0x20];
+ u8 inner_esp_spi[0x20];
u8 outer_esp_spi[0x20];
u8 reserved_at_1a0[0x60];
};
@@ -1801,7 +1801,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 disable_local_lb_uc[0x1];
u8 disable_local_lb_mc[0x1];
u8 log_min_hairpin_wq_data_sz[0x5];
- u8 reserved_at_3e8[0x2];
+ u8 reserved_at_3e8[0x1];
+ u8 silent_mode[0x1];
u8 vhca_state[0x1];
u8 log_max_vlan_list[0x5];
u8 reserved_at_3f0[0x3];
@@ -1818,7 +1819,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 reserved_at_460[0x1];
u8 ats[0x1];
- u8 reserved_at_462[0x1];
+ u8 cross_vhca_rqt[0x1];
u8 log_max_uctx[0x5];
u8 reserved_at_468[0x1];
u8 crypto[0x1];
@@ -1943,6 +1944,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
enum {
MLX5_CROSS_VHCA_OBJ_TO_OBJ_SUPPORTED_LOCAL_FLOW_TABLE_TO_REMOTE_FLOW_TABLE_MISS = 0x80000,
+ MLX5_CROSS_VHCA_OBJ_TO_OBJ_SUPPORTED_LOCAL_FLOW_TABLE_ROOT_TO_REMOTE_FLOW_TABLE = (1ULL << 20),
};
enum {
@@ -1992,7 +1994,11 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
u8 reserved_at_260[0x120];
u8 reserved_at_380[0x10];
u8 ec_vf_vport_base[0x10];
- u8 reserved_at_3a0[0x460];
+
+ u8 reserved_at_3a0[0x10];
+ u8 max_rqt_vhca_id[0x10];
+
+ u8 reserved_at_3c0[0x440];
};
enum mlx5_ifc_flow_destination_type {
@@ -2151,6 +2157,13 @@ struct mlx5_ifc_rq_num_bits {
u8 rq_num[0x18];
};
+struct mlx5_ifc_rq_vhca_bits {
+ u8 reserved_at_0[0x8];
+ u8 rq_num[0x18];
+ u8 reserved_at_20[0x10];
+ u8 rq_vhca_id[0x10];
+};
+
struct mlx5_ifc_mac_address_layout_bits {
u8 reserved_at_0[0x10];
u8 mac_addr_47_32[0x10];
@@ -3901,7 +3914,10 @@ struct mlx5_ifc_rqtc_bits {
u8 reserved_at_e0[0x6a0];
- struct mlx5_ifc_rq_num_bits rq_num[];
+ union {
+ DECLARE_FLEX_ARRAY(struct mlx5_ifc_rq_num_bits, rq_num);
+ DECLARE_FLEX_ARRAY(struct mlx5_ifc_rq_vhca_bits, rq_vhca);
+ };
};
enum {
@@ -4744,7 +4760,10 @@ struct mlx5_ifc_set_l2_table_entry_in_bits {
u8 reserved_at_c0[0x20];
- u8 reserved_at_e0[0x13];
+ u8 reserved_at_e0[0x10];
+ u8 silent_mode_valid[0x1];
+ u8 silent_mode[0x1];
+ u8 reserved_at_f2[0x1];
u8 vlan_valid[0x1];
u8 vlan[0xc];
@@ -10089,6 +10108,20 @@ struct mlx5_ifc_mpegc_reg_bits {
u8 reserved_at_60[0x100];
};
+struct mlx5_ifc_mpir_reg_bits {
+ u8 sdm[0x1];
+ u8 reserved_at_1[0x1b];
+ u8 host_buses[0x4];
+
+ u8 reserved_at_20[0x20];
+
+ u8 local_port[0x8];
+ u8 reserved_at_28[0x15];
+ u8 sd_group[0x3];
+
+ u8 reserved_at_60[0x20];
+};
+
enum {
MLX5_MTUTC_FREQ_ADJ_UNITS_PPB = 0x0,
MLX5_MTUTC_FREQ_ADJ_UNITS_SCALED_PPM = 0x1,
@@ -12004,6 +12037,13 @@ enum {
MLX5_IPSEC_ASO_INC_SN = 0x2,
};
+enum {
+ MLX5_IPSEC_ASO_REPLAY_WIN_32BIT = 0x0,
+ MLX5_IPSEC_ASO_REPLAY_WIN_64BIT = 0x1,
+ MLX5_IPSEC_ASO_REPLAY_WIN_128BIT = 0x2,
+ MLX5_IPSEC_ASO_REPLAY_WIN_256BIT = 0x3,
+};
+
struct mlx5_ifc_ipsec_aso_bits {
u8 valid[0x1];
u8 reserved_at_201[0x1];
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 957ce38768b2..64e4572ef06d 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -125,7 +125,7 @@ struct page {
struct page_pool *pp;
unsigned long _pp_mapping_pad;
unsigned long dma_addr;
- atomic_long_t pp_frag_count;
+ atomic_long_t pp_ref_count;
};
struct { /* Tail pages of compound page */
unsigned long compound_head; /* Bit zero is set */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 998c7aaa98b8..1b935ee341b4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -382,6 +382,7 @@ struct napi_struct {
/* control-path-only fields follow */
struct list_head dev_list;
struct hlist_node napi_hash_node;
+ int irq;
};
enum {
@@ -665,6 +666,10 @@ struct netdev_queue {
#ifdef CONFIG_XDP_SOCKETS
struct xsk_buff_pool *pool;
#endif
+ /* NAPI instance for the queue
+ * Readers and writers must hold RTNL
+ */
+ struct napi_struct *napi;
/*
* write-mostly part
*/
@@ -1865,6 +1870,7 @@ enum netdev_stat_type {
* @netdev_ops: Includes several pointers to callbacks,
* if one wants to override the ndo_*() functions
* @xdp_metadata_ops: Includes pointers to XDP metadata callbacks.
+ * @xsk_tx_metadata_ops: Includes pointers to AF_XDP TX metadata callbacks.
* @ethtool_ops: Management operations
* @l3mdev_ops: Layer 3 master device operations
* @ndisc_ops: Includes callbacks for different IPv6 neighbour
@@ -2091,6 +2097,70 @@ enum netdev_stat_type {
*/
struct net_device {
+ /* Cacheline organization can be found documented in
+ * Documentation/networking/net_cachelines/net_device.rst.
+ * Please update the document when adding new fields.
+ */
+
+ /* TX read-mostly hotpath */
+ __cacheline_group_begin(net_device_read_tx);
+ unsigned long long priv_flags;
+ const struct net_device_ops *netdev_ops;
+ const struct header_ops *header_ops;
+ struct netdev_queue *_tx;
+ unsigned int real_num_tx_queues;
+ unsigned int gso_max_size;
+ unsigned int gso_ipv4_max_size;
+ u16 gso_max_segs;
+ s16 num_tc;
+ /* Note : dev->mtu is often read without holding a lock.
+ * Writers usually hold RTNL.
+ * It is recommended to use READ_ONCE() to annotate the reads,
+ * and to use WRITE_ONCE() to annotate the writes.
+ */
+ unsigned int mtu;
+ unsigned short needed_headroom;
+ struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE];
+#ifdef CONFIG_XPS
+ struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX];
+#endif
+#ifdef CONFIG_NETFILTER_EGRESS
+ struct nf_hook_entries __rcu *nf_hooks_egress;
+#endif
+#ifdef CONFIG_NET_XGRESS
+ struct bpf_mprog_entry __rcu *tcx_egress;
+#endif
+ __cacheline_group_end(net_device_read_tx);
+
+ /* TXRX read-mostly hotpath */
+ __cacheline_group_begin(net_device_read_txrx);
+ unsigned int flags;
+ unsigned short hard_header_len;
+ netdev_features_t features;
+ struct inet6_dev __rcu *ip6_ptr;
+ __cacheline_group_end(net_device_read_txrx);
+
+ /* RX read-mostly hotpath */
+ __cacheline_group_begin(net_device_read_rx);
+ struct list_head ptype_specific;
+ int ifindex;
+ unsigned int real_num_rx_queues;
+ struct netdev_rx_queue *_rx;
+ unsigned long gro_flush_timeout;
+ int napi_defer_hard_irqs;
+ unsigned int gro_max_size;
+ unsigned int gro_ipv4_max_size;
+ rx_handler_func_t __rcu *rx_handler;
+ void __rcu *rx_handler_data;
+ possible_net_t nd_net;
+#ifdef CONFIG_NETPOLL
+ struct netpoll_info __rcu *npinfo;
+#endif
+#ifdef CONFIG_NET_XGRESS
+ struct bpf_mprog_entry __rcu *tcx_ingress;
+#endif
+ __cacheline_group_end(net_device_read_rx);
+
char name[IFNAMSIZ];
struct netdev_name_node *name_node;
struct dev_ifalias __rcu *ifalias;
@@ -2115,7 +2185,6 @@ struct net_device {
struct list_head unreg_list;
struct list_head close_list;
struct list_head ptype_all;
- struct list_head ptype_specific;
struct {
struct list_head upper;
@@ -2123,25 +2192,13 @@ struct net_device {
} adj_list;
/* Read-mostly cache-line for fast-path access */
- unsigned int flags;
xdp_features_t xdp_features;
- unsigned long long priv_flags;
- const struct net_device_ops *netdev_ops;
const struct xdp_metadata_ops *xdp_metadata_ops;
- int ifindex;
+ const struct xsk_tx_metadata_ops *xsk_tx_metadata_ops;
unsigned short gflags;
- unsigned short hard_header_len;
- /* Note : dev->mtu is often read without holding a lock.
- * Writers usually hold RTNL.
- * It is recommended to use READ_ONCE() to annotate the reads,
- * and to use WRITE_ONCE() to annotate the writes.
- */
- unsigned int mtu;
- unsigned short needed_headroom;
unsigned short needed_tailroom;
- netdev_features_t features;
netdev_features_t hw_features;
netdev_features_t wanted_features;
netdev_features_t vlan_features;
@@ -2185,8 +2242,6 @@ struct net_device {
const struct tlsdev_ops *tlsdev_ops;
#endif
- const struct header_ops *header_ops;
-
unsigned char operstate;
unsigned char link_mode;
@@ -2227,9 +2282,7 @@ struct net_device {
/* Protocol-specific pointers */
-
struct in_device __rcu *ip_ptr;
- struct inet6_dev __rcu *ip6_ptr;
#if IS_ENABLED(CONFIG_VLAN_8021Q)
struct vlan_info __rcu *vlan_info;
#endif
@@ -2264,26 +2317,14 @@ struct net_device {
/* Interface address info used in eth_type_trans() */
const unsigned char *dev_addr;
- struct netdev_rx_queue *_rx;
unsigned int num_rx_queues;
- unsigned int real_num_rx_queues;
-
struct bpf_prog __rcu *xdp_prog;
- unsigned long gro_flush_timeout;
- int napi_defer_hard_irqs;
#define GRO_LEGACY_MAX_SIZE 65536u
/* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE),
* and shinfo->gso_segs is a 16bit field.
*/
#define GRO_MAX_SIZE (8 * 65535u)
- unsigned int gro_max_size;
- unsigned int gro_ipv4_max_size;
unsigned int xdp_zc_max_segs;
- rx_handler_func_t __rcu *rx_handler;
- void __rcu *rx_handler_data;
-#ifdef CONFIG_NET_XGRESS
- struct bpf_mprog_entry __rcu *tcx_ingress;
-#endif
struct netdev_queue __rcu *ingress_queue;
#ifdef CONFIG_NETFILTER_INGRESS
struct nf_hook_entries __rcu *nf_hooks_ingress;
@@ -2298,25 +2339,13 @@ struct net_device {
/*
* Cache lines mostly used on transmit path
*/
- struct netdev_queue *_tx ____cacheline_aligned_in_smp;
unsigned int num_tx_queues;
- unsigned int real_num_tx_queues;
struct Qdisc __rcu *qdisc;
unsigned int tx_queue_len;
spinlock_t tx_global_lock;
struct xdp_dev_bulk_queue __percpu *xdp_bulkq;
-#ifdef CONFIG_XPS
- struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX];
-#endif
-#ifdef CONFIG_NET_XGRESS
- struct bpf_mprog_entry __rcu *tcx_egress;
-#endif
-#ifdef CONFIG_NETFILTER_EGRESS
- struct nf_hook_entries __rcu *nf_hooks_egress;
-#endif
-
#ifdef CONFIG_NET_SCHED
DECLARE_HASHTABLE (qdisc_hash, 4);
#endif
@@ -2355,12 +2384,6 @@ struct net_device {
bool needs_free_netdev;
void (*priv_destructor)(struct net_device *dev);
-#ifdef CONFIG_NETPOLL
- struct netpoll_info __rcu *npinfo;
-#endif
-
- possible_net_t nd_net;
-
/* mid-layer private */
void *ml_priv;
enum netdev_ml_priv_type ml_priv_type;
@@ -2395,20 +2418,15 @@ struct net_device {
*/
#define GSO_MAX_SIZE (8 * GSO_MAX_SEGS)
- unsigned int gso_max_size;
#define TSO_LEGACY_MAX_SIZE 65536
#define TSO_MAX_SIZE UINT_MAX
unsigned int tso_max_size;
- u16 gso_max_segs;
#define TSO_MAX_SEGS U16_MAX
u16 tso_max_segs;
- unsigned int gso_ipv4_max_size;
#ifdef CONFIG_DCB
const struct dcbnl_rtnl_ops *dcbnl_ops;
#endif
- s16 num_tc;
- struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE];
u8 prio_tc_map[TC_BITMASK + 1];
#if IS_ENABLED(CONFIG_FCOE)
@@ -2655,6 +2673,15 @@ static inline void *netdev_priv(const struct net_device *dev)
*/
#define SET_NETDEV_DEVTYPE(net, devtype) ((net)->dev.type = (devtype))
+void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index,
+ enum netdev_queue_type type,
+ struct napi_struct *napi);
+
+static inline void netif_napi_set_irq(struct napi_struct *napi, int irq)
+{
+ napi->irq = irq;
+}
+
/* Default NAPI poll() weight
* Device drivers are strongly advised to not use bigger value
*/
@@ -4203,6 +4230,15 @@ static inline void netdev_ref_replace(struct net_device *odev,
void linkwatch_fire_event(struct net_device *dev);
/**
+ * linkwatch_sync_dev - sync linkwatch for the given device
+ * @dev: network device to sync linkwatch for
+ *
+ * Sync linkwatch for the given device, removing it from the
+ * pending work list (if queued).
+ */
+void linkwatch_sync_dev(struct net_device *dev);
+
+/**
* netif_carrier_ok - test if carrier present
* @dev: network device
*
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index bcc1ea44b4e8..06142ff7f9ce 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -204,6 +204,8 @@ enum mapping_flags {
AS_NO_WRITEBACK_TAGS = 5,
AS_LARGE_FOLIO_SUPPORT = 6,
AS_RELEASE_ALWAYS, /* Call ->release_folio(), even if no private data */
+ AS_STABLE_WRITES, /* must wait for writeback before modifying
+ folio contents */
};
/**
@@ -289,6 +291,21 @@ static inline void mapping_clear_release_always(struct address_space *mapping)
clear_bit(AS_RELEASE_ALWAYS, &mapping->flags);
}
+static inline bool mapping_stable_writes(const struct address_space *mapping)
+{
+ return test_bit(AS_STABLE_WRITES, &mapping->flags);
+}
+
+static inline void mapping_set_stable_writes(struct address_space *mapping)
+{
+ set_bit(AS_STABLE_WRITES, &mapping->flags);
+}
+
+static inline void mapping_clear_stable_writes(struct address_space *mapping)
+{
+ clear_bit(AS_STABLE_WRITES, &mapping->flags);
+}
+
static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
{
return mapping->gfp_mask;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 6e7ebcc50b85..e9e85d347587 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -327,7 +327,8 @@ struct mdio_bus_stats {
/**
* struct phy_package_shared - Shared information in PHY packages
- * @addr: Common PHY address used to combine PHYs in one package
+ * @base_addr: Base PHY address of PHY package used to combine PHYs
+ * in one package and for offset calculation of phy_package_read/write
* @refcnt: Number of PHYs connected to this shared data
* @flags: Initialization of PHY package
* @priv_size: Size of the shared private data @priv
@@ -338,7 +339,7 @@ struct mdio_bus_stats {
* phy_package_leave().
*/
struct phy_package_shared {
- int addr;
+ u8 base_addr;
refcount_t refcnt;
unsigned long flags;
size_t priv_size;
@@ -1866,6 +1867,7 @@ int genphy_c45_an_config_aneg(struct phy_device *phydev);
int genphy_c45_an_disable_aneg(struct phy_device *phydev);
int genphy_c45_read_mdix(struct phy_device *phydev);
int genphy_c45_pma_read_abilities(struct phy_device *phydev);
+int genphy_c45_pma_read_ext_abilities(struct phy_device *phydev);
int genphy_c45_pma_baset1_read_abilities(struct phy_device *phydev);
int genphy_c45_read_eee_abilities(struct phy_device *phydev);
int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev);
@@ -1975,10 +1977,10 @@ int phy_ethtool_get_link_ksettings(struct net_device *ndev,
int phy_ethtool_set_link_ksettings(struct net_device *ndev,
const struct ethtool_link_ksettings *cmd);
int phy_ethtool_nway_reset(struct net_device *ndev);
-int phy_package_join(struct phy_device *phydev, int addr, size_t priv_size);
+int phy_package_join(struct phy_device *phydev, int base_addr, size_t priv_size);
void phy_package_leave(struct phy_device *phydev);
int devm_phy_package_join(struct device *dev, struct phy_device *phydev,
- int addr, size_t priv_size);
+ int base_addr, size_t priv_size);
int __init mdio_bus_init(void);
void mdio_bus_exit(void);
@@ -2001,48 +2003,83 @@ int __phy_hwtstamp_set(struct phy_device *phydev,
struct kernel_hwtstamp_config *config,
struct netlink_ext_ack *extack);
-static inline int phy_package_read(struct phy_device *phydev, u32 regnum)
+static inline int phy_package_address(struct phy_device *phydev,
+ unsigned int addr_offset)
{
struct phy_package_shared *shared = phydev->shared;
+ u8 base_addr = shared->base_addr;
- if (!shared)
+ if (addr_offset >= PHY_MAX_ADDR - base_addr)
return -EIO;
- return mdiobus_read(phydev->mdio.bus, shared->addr, regnum);
+ /* we know that addr will be in the range 0..31 and thus the
+ * implicit cast to a signed int is not a problem.
+ */
+ return base_addr + addr_offset;
}
-static inline int __phy_package_read(struct phy_device *phydev, u32 regnum)
+static inline int phy_package_read(struct phy_device *phydev,
+ unsigned int addr_offset, u32 regnum)
{
- struct phy_package_shared *shared = phydev->shared;
+ int addr = phy_package_address(phydev, addr_offset);
- if (!shared)
- return -EIO;
+ if (addr < 0)
+ return addr;
+
+ return mdiobus_read(phydev->mdio.bus, addr, regnum);
+}
+
+static inline int __phy_package_read(struct phy_device *phydev,
+ unsigned int addr_offset, u32 regnum)
+{
+ int addr = phy_package_address(phydev, addr_offset);
+
+ if (addr < 0)
+ return addr;
- return __mdiobus_read(phydev->mdio.bus, shared->addr, regnum);
+ return __mdiobus_read(phydev->mdio.bus, addr, regnum);
}
static inline int phy_package_write(struct phy_device *phydev,
- u32 regnum, u16 val)
+ unsigned int addr_offset, u32 regnum,
+ u16 val)
{
- struct phy_package_shared *shared = phydev->shared;
+ int addr = phy_package_address(phydev, addr_offset);
- if (!shared)
- return -EIO;
+ if (addr < 0)
+ return addr;
- return mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val);
+ return mdiobus_write(phydev->mdio.bus, addr, regnum, val);
}
static inline int __phy_package_write(struct phy_device *phydev,
- u32 regnum, u16 val)
+ unsigned int addr_offset, u32 regnum,
+ u16 val)
{
- struct phy_package_shared *shared = phydev->shared;
+ int addr = phy_package_address(phydev, addr_offset);
- if (!shared)
- return -EIO;
+ if (addr < 0)
+ return addr;
- return __mdiobus_write(phydev->mdio.bus, shared->addr, regnum, val);
+ return __mdiobus_write(phydev->mdio.bus, addr, regnum, val);
}
+int __phy_package_read_mmd(struct phy_device *phydev,
+ unsigned int addr_offset, int devad,
+ u32 regnum);
+
+int phy_package_read_mmd(struct phy_device *phydev,
+ unsigned int addr_offset, int devad,
+ u32 regnum);
+
+int __phy_package_write_mmd(struct phy_device *phydev,
+ unsigned int addr_offset, int devad,
+ u32 regnum, u16 val);
+
+int phy_package_write_mmd(struct phy_device *phydev,
+ unsigned int addr_offset, int devad,
+ u32 regnum, u16 val);
+
static inline bool __phy_package_set_once(struct phy_device *phydev,
unsigned int b)
{
diff --git a/include/linux/platform_data/microchip-ksz.h b/include/linux/platform_data/microchip-ksz.h
index ea1cc6d829e9..f177416635a2 100644
--- a/include/linux/platform_data/microchip-ksz.h
+++ b/include/linux/platform_data/microchip-ksz.h
@@ -20,10 +20,31 @@
#define __MICROCHIP_KSZ_H
#include <linux/types.h>
+#include <linux/platform_data/dsa.h>
+
+enum ksz_chip_id {
+ KSZ8563_CHIP_ID = 0x8563,
+ KSZ8795_CHIP_ID = 0x8795,
+ KSZ8794_CHIP_ID = 0x8794,
+ KSZ8765_CHIP_ID = 0x8765,
+ KSZ8830_CHIP_ID = 0x8830,
+ KSZ9477_CHIP_ID = 0x00947700,
+ KSZ9896_CHIP_ID = 0x00989600,
+ KSZ9897_CHIP_ID = 0x00989700,
+ KSZ9893_CHIP_ID = 0x00989300,
+ KSZ9563_CHIP_ID = 0x00956300,
+ KSZ9567_CHIP_ID = 0x00956700,
+ LAN9370_CHIP_ID = 0x00937000,
+ LAN9371_CHIP_ID = 0x00937100,
+ LAN9372_CHIP_ID = 0x00937200,
+ LAN9373_CHIP_ID = 0x00937300,
+ LAN9374_CHIP_ID = 0x00937400,
+};
struct ksz_platform_data {
+ /* Must be first such that dsa_register_switch() can access it */
+ struct dsa_chip_data cd;
u32 chip_id;
- u16 enabled_ports;
};
#endif
diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h
index 63e630276499..ab1c7deff118 100644
--- a/include/linux/platform_data/x86/asus-wmi.h
+++ b/include/linux/platform_data/x86/asus-wmi.h
@@ -114,6 +114,9 @@
/* Charging mode - 1=Barrel, 2=USB */
#define ASUS_WMI_DEVID_CHARGE_MODE 0x0012006C
+/* MCU powersave mode */
+#define ASUS_WMI_DEVID_MCU_POWERSAVE 0x001200E2
+
/* epu is connected? 1 == true */
#define ASUS_WMI_DEVID_EGPU_CONNECTED 0x00090018
/* egpu on/off */
diff --git a/include/linux/rethook.h b/include/linux/rethook.h
index ce69b2b7bc35..ba60962805f6 100644
--- a/include/linux/rethook.h
+++ b/include/linux/rethook.h
@@ -28,7 +28,12 @@ typedef void (*rethook_handler_t) (struct rethook_node *, void *, unsigned long,
*/
struct rethook {
void *data;
- rethook_handler_t handler;
+ /*
+ * To avoid sparse warnings, this uses a raw function pointer with
+ * __rcu, instead of rethook_handler_t. But this must be same as
+ * rethook_handler_t.
+ */
+ void (__rcu *handler) (struct rethook_node *, void *, unsigned long, struct pt_regs *);
struct objpool_head pool;
struct rcu_head rcu;
};
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 3d6cf306cd55..410529fca18b 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -10,6 +10,13 @@
#include <uapi/linux/rtnetlink.h>
extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo);
+
+static inline int rtnetlink_maybe_send(struct sk_buff *skb, struct net *net,
+ u32 pid, u32 group, int echo)
+{
+ return !skb ? 0 : rtnetlink_send(skb, net, pid, group, echo);
+}
+
extern int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid);
extern void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid,
u32 group, const struct nlmsghdr *nlh, gfp_t flags);
@@ -72,6 +79,18 @@ static inline bool lockdep_rtnl_is_held(void)
#define rtnl_dereference(p) \
rcu_dereference_protected(p, lockdep_rtnl_is_held())
+/**
+ * rcu_replace_pointer_rtnl - replace an RCU pointer under rtnl_lock, returning
+ * its old value
+ * @rp: RCU pointer, whose value is returned
+ * @p: regular pointer
+ *
+ * Perform a replacement under rtnl_lock, where @rp is an RCU-annotated
+ * pointer. The old value of @rp is returned, and @rp is set to @p
+ */
+#define rcu_replace_pointer_rtnl(rp, p) \
+ rcu_replace_pointer(rp, p, lockdep_rtnl_is_held())
+
static inline struct netdev_queue *dev_ingress_queue(struct net_device *dev)
{
return rtnl_dereference(dev->ingress_queue);
@@ -130,4 +149,26 @@ extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
extern void rtnl_offload_xstats_notify(struct net_device *dev);
+static inline int rtnl_has_listeners(const struct net *net, u32 group)
+{
+ struct sock *rtnl = net->rtnl;
+
+ return netlink_has_listeners(rtnl, group);
+}
+
+/**
+ * rtnl_notify_needed - check if notification is needed
+ * @net: Pointer to the net namespace
+ * @nlflags: netlink ingress message flags
+ * @group: rtnl group
+ *
+ * Based on the ingress message flags and rtnl group, returns true
+ * if a notification is needed, false otherwise.
+ */
+static inline bool
+rtnl_notify_needed(const struct net *net, u16 nlflags, u32 group)
+{
+ return (nlflags & NLM_F_ECHO) || rtnl_has_listeners(net, group);
+}
+
#endif /* __LINUX_RTNETLINK_H */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 27998f73183e..7ce38874dbd1 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -566,6 +566,15 @@ struct ubuf_info_msgzc {
int mm_account_pinned_pages(struct mmpin *mmp, size_t size);
void mm_unaccount_pinned_pages(struct mmpin *mmp);
+/* Preserve some data across TX submission and completion.
+ *
+ * Note, this state is stored in the driver. Extending the layout
+ * might need some special care.
+ */
+struct xsk_tx_metadata_compl {
+ __u64 *tx_timestamp;
+};
+
/* This data is invariant across clones and lives at
* the end of the header data, ie. at skb->end.
*/
@@ -578,7 +587,10 @@ struct skb_shared_info {
/* Warning: this field is not always filled in (UFO)! */
unsigned short gso_segs;
struct sk_buff *frag_list;
- struct skb_shared_hwtstamps hwtstamps;
+ union {
+ struct skb_shared_hwtstamps hwtstamps;
+ struct xsk_tx_metadata_compl xsk_meta;
+ };
unsigned int gso_type;
u32 tskey;
@@ -1057,7 +1069,7 @@ struct sk_buff {
refcount_t users;
#ifdef CONFIG_SKB_EXTENSIONS
- /* only useable after checking ->active_extensions != 0 */
+ /* only usable after checking ->active_extensions != 0 */
struct skb_ext *extensions;
#endif
};
@@ -3299,7 +3311,7 @@ static inline struct page *__dev_alloc_pages(gfp_t gfp_mask,
unsigned int order)
{
/* This piece of code contains several assumptions.
- * 1. This is for device Rx, therefor a cold page is preferred.
+ * 1. This is for device Rx, therefore a cold page is preferred.
* 2. The expectation is the user wants a compound page.
* 3. If requesting a order 0 page it will not be compound
* due to the check to see if order has a value in prep_new_page
@@ -4235,7 +4247,7 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a,
{
const void *a = skb_metadata_end(skb_a);
const void *b = skb_metadata_end(skb_b);
- /* Using more efficient varaiant than plain call to memcmp(). */
+ /* Using more efficient variant than plain call to memcmp(). */
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
u64 diffs = 0;
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index c1637515a8a4..c953b8c0d2f4 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -106,6 +106,7 @@ struct sk_psock {
struct mutex work_mutex;
struct sk_psock_work_state work_state;
struct delayed_work work;
+ struct sock *sk_pair;
struct rcu_work rwork;
};
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 0b4658a7eceb..dee5ad6e48c5 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -175,6 +175,7 @@ struct stmmac_fpe_cfg {
bool hs_enable; /* FPE handshake enable */
enum stmmac_fpe_state lp_fpe_state; /* Link Partner FPE state */
enum stmmac_fpe_state lo_fpe_state; /* Local station FPE state */
+ u32 fpe_csr; /* MAC_FPE_CTRL_STS reg cache */
};
struct stmmac_safety_feature_cfg {
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 68f3d315d2e1..89b290d8c8dc 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -169,7 +169,7 @@ struct tcp_request_sock {
#ifdef CONFIG_TCP_AO
u8 ao_keyid;
u8 ao_rcv_next;
- u8 maclen;
+ bool used_tcp_ao;
#endif
};
@@ -180,37 +180,131 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
static inline bool tcp_rsk_used_ao(const struct request_sock *req)
{
- /* The real length of MAC is saved in the request socket,
- * signing anything with zero-length makes no sense, so here is
- * a little hack..
- */
#ifndef CONFIG_TCP_AO
return false;
#else
- return tcp_rsk(req)->maclen != 0;
+ return tcp_rsk(req)->used_tcp_ao;
#endif
}
#define TCP_RMEM_TO_WIN_SCALE 8
struct tcp_sock {
+ /* Cacheline organization can be found documented in
+ * Documentation/networking/net_cachelines/tcp_sock.rst.
+ * Please update the document when adding new fields.
+ */
+
/* inet_connection_sock has to be the first member of tcp_sock */
struct inet_connection_sock inet_conn;
- u16 tcp_header_len; /* Bytes of tcp header to send */
+
+ /* TX read-mostly hotpath cache lines */
+ __cacheline_group_begin(tcp_sock_read_tx);
+ /* timestamp of last sent data packet (for restart window) */
+ u32 max_window; /* Maximal window ever seen from peer */
+ u32 rcv_ssthresh; /* Current window clamp */
+ u32 reordering; /* Packet reordering metric. */
+ u32 notsent_lowat; /* TCP_NOTSENT_LOWAT */
u16 gso_segs; /* Max number of segs per GSO packet */
+ /* from STCP, retrans queue hinting */
+ struct sk_buff *lost_skb_hint;
+ struct sk_buff *retransmit_skb_hint;
+ __cacheline_group_end(tcp_sock_read_tx);
+
+ /* TXRX read-mostly hotpath cache lines */
+ __cacheline_group_begin(tcp_sock_read_txrx);
+ u32 tsoffset; /* timestamp offset */
+ u32 snd_wnd; /* The window we expect to receive */
+ u32 mss_cache; /* Cached effective mss, not including SACKS */
+ u32 snd_cwnd; /* Sending congestion window */
+ u32 prr_out; /* Total number of pkts sent during Recovery. */
+ u32 lost_out; /* Lost packets */
+ u32 sacked_out; /* SACK'd packets */
+ u16 tcp_header_len; /* Bytes of tcp header to send */
+ u8 chrono_type : 2, /* current chronograph type */
+ repair : 1,
+ is_sack_reneg:1, /* in recovery from loss with SACK reneg? */
+ is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
+ __cacheline_group_end(tcp_sock_read_txrx);
+
+ /* RX read-mostly hotpath cache lines */
+ __cacheline_group_begin(tcp_sock_read_rx);
+ u32 copied_seq; /* Head of yet unread data */
+ u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */
+ u32 snd_wl1; /* Sequence for window update */
+ u32 tlp_high_seq; /* snd_nxt at the time of TLP */
+ u32 rttvar_us; /* smoothed mdev_max */
+ u32 retrans_out; /* Retransmitted packets out */
+ u16 advmss; /* Advertised MSS */
+ u16 urg_data; /* Saved octet of OOB data and control flags */
+ u32 lost; /* Total data packets lost incl. rexmits */
+ struct minmax rtt_min;
+ /* OOO segments go in this rbtree. Socket lock must be held. */
+ struct rb_root out_of_order_queue;
+ u32 snd_ssthresh; /* Slow start size threshold */
+ __cacheline_group_end(tcp_sock_read_rx);
+ /* TX read-write hotpath cache lines */
+ __cacheline_group_begin(tcp_sock_write_tx) ____cacheline_aligned;
+ u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut
+ * The total number of segments sent.
+ */
+ u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut
+ * total number of data segments sent.
+ */
+ u64 bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut
+ * total number of data bytes sent.
+ */
+ u32 snd_sml; /* Last byte of the most recently transmitted small packet */
+ u32 chrono_start; /* Start time in jiffies of a TCP chrono */
+ u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */
+ u32 write_seq; /* Tail(+1) of data held in tcp send buffer */
+ u32 pushed_seq; /* Last pushed seq, required to talk to windows */
+ u32 lsndtime;
+ u32 mdev_us; /* medium deviation */
+ u64 tcp_wstamp_ns; /* departure time for next sent data packet */
+ u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */
+ u64 tcp_mstamp; /* most recent packet received/sent */
+ u32 rtt_seq; /* sequence number to update rttvar */
+ struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */
+ struct sk_buff *highest_sack; /* skb just after the highest
+ * skb with SACKed bit set
+ * (validity guaranteed only if
+ * sacked_out > 0)
+ */
+ u8 ecn_flags; /* ECN status bits. */
+ __cacheline_group_end(tcp_sock_write_tx);
+
+ /* TXRX read-write hotpath cache lines */
+ __cacheline_group_begin(tcp_sock_write_txrx);
/*
* Header prediction flags
* 0x5?10 << 16 + snd_wnd in net byte order
*/
__be32 pred_flags;
-
+ u32 rcv_nxt; /* What we want to receive next */
+ u32 snd_nxt; /* Next sequence we send */
+ u32 snd_una; /* First byte we want an ack for */
+ u32 window_clamp; /* Maximal window to advertise */
+ u32 srtt_us; /* smoothed round trip time << 3 in usecs */
+ u32 packets_out; /* Packets which are "in flight" */
+ u32 snd_up; /* Urgent pointer */
+ u32 delivered; /* Total data packets delivered incl. rexmits */
+ u32 delivered_ce; /* Like the above but only ECE marked packets */
+ u32 app_limited; /* limited until "delivered" reaches this val */
+ u32 rcv_wnd; /* Current receiver window */
/*
- * RFC793 variables by their proper names. This means you can
- * read the code and the spec side by side (and laugh ...)
- * See RFC793 and RFC1122. The RFC writes these in capitals.
+ * Options received (usually on last packet, some only on SYN packets).
*/
- u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived
+ struct tcp_options_received rx_opt;
+ u8 nonagle : 4,/* Disable Nagle algorithm? */
+ rate_app_limited:1; /* rate_{delivered,interval_us} limited? */
+ __cacheline_group_end(tcp_sock_write_txrx);
+
+ /* RX read-write hotpath cache lines */
+ __cacheline_group_begin(tcp_sock_write_rx);
+ u64 bytes_received;
+ /* RFC4898 tcpEStatsAppHCThruOctetsReceived
* sum(delta(rcv_nxt)), or how many bytes
* were acked.
*/
@@ -220,45 +314,44 @@ struct tcp_sock {
u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn
* total number of data segments in.
*/
- u32 rcv_nxt; /* What we want to receive next */
- u32 copied_seq; /* Head of yet unread data */
u32 rcv_wup; /* rcv_nxt on last window update sent */
- u32 snd_nxt; /* Next sequence we send */
- u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut
- * The total number of segments sent.
- */
- u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut
- * total number of data segments sent.
- */
- u64 bytes_sent; /* RFC4898 tcpEStatsPerfHCDataOctetsOut
- * total number of data bytes sent.
- */
+ u32 max_packets_out; /* max packets_out in last window */
+ u32 cwnd_usage_seq; /* right edge of cwnd usage tracking flight */
+ u32 rate_delivered; /* saved rate sample: packets delivered */
+ u32 rate_interval_us; /* saved rate sample: time elapsed */
+ u32 rcv_rtt_last_tsecr;
+ u64 first_tx_mstamp; /* start of window send phase */
+ u64 delivered_mstamp; /* time we reached "delivered" */
u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked
* sum(delta(snd_una)), or how many bytes
* were acked.
*/
+ struct {
+ u32 rtt_us;
+ u32 seq;
+ u64 time;
+ } rcv_rtt_est;
+/* Receiver queue space */
+ struct {
+ u32 space;
+ u32 seq;
+ u64 time;
+ } rcvq_space;
+ __cacheline_group_end(tcp_sock_write_rx);
+ /* End of Hot Path */
+
+/*
+ * RFC793 variables by their proper names. This means you can
+ * read the code and the spec side by side (and laugh ...)
+ * See RFC793 and RFC1122. The RFC writes these in capitals.
+ */
u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups
* total number of DSACK blocks received
*/
- u32 snd_una; /* First byte we want an ack for */
- u32 snd_sml; /* Last byte of the most recently transmitted small packet */
- u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */
- u32 lsndtime; /* timestamp of last sent data packet (for restart window) */
u32 last_oow_ack_time; /* timestamp of last out-of-window ACK */
u32 compressed_ack_rcv_nxt;
-
- u32 tsoffset; /* timestamp offset */
-
struct list_head tsq_node; /* anchor in tsq_tasklet.head list */
- struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */
-
- u32 snd_wl1; /* Sequence for window update */
- u32 snd_wnd; /* The window we expect to receive */
- u32 max_window; /* Maximal window ever seen from peer */
- u32 mss_cache; /* Cached effective mss, not including SACKS */
- u32 window_clamp; /* Maximal window to advertise */
- u32 rcv_ssthresh; /* Current window clamp */
u8 scaling_ratio; /* see tcp_win_from_space() */
/* Information of the most recently (s)acked skb */
struct tcp_rack {
@@ -272,24 +365,16 @@ struct tcp_sock {
dsack_seen:1, /* Whether DSACK seen after last adj */
advanced:1; /* mstamp advanced since last lost marking */
} rack;
- u16 advmss; /* Advertised MSS */
u8 compressed_ack;
u8 dup_ack_counter:2,
tlp_retrans:1, /* TLP is a retransmission */
tcp_usec_ts:1, /* TSval values in usec */
unused:4;
- u32 chrono_start; /* Start time in jiffies of a TCP chrono */
- u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */
- u8 chrono_type:2, /* current chronograph type */
- rate_app_limited:1, /* rate_{delivered,interval_us} limited? */
+ u8 thin_lto : 1,/* Use linear timeouts for thin streams */
+ recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */
fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */
- is_sack_reneg:1, /* in recovery from loss with SACK reneg? */
- fastopen_client_fail:2; /* reason why fastopen failed */
- u8 nonagle : 4,/* Disable Nagle algorithm? */
- thin_lto : 1,/* Use linear timeouts for thin streams */
- recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */
- repair : 1,
+ fastopen_client_fail:2, /* reason why fastopen failed */
frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */
u8 repair_queue;
u8 save_syn:2, /* Save headers of SYN packet */
@@ -297,45 +382,19 @@ struct tcp_sock {
syn_fastopen:1, /* SYN includes Fast Open option */
syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */
syn_fastopen_ch:1, /* Active TFO re-enabling probe */
- syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
- is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
- u32 tlp_high_seq; /* snd_nxt at the time of TLP */
+ syn_data_acked:1;/* data in SYN is acked by SYN-ACK */
u32 tcp_tx_delay; /* delay (in usec) added to TX packets */
- u64 tcp_wstamp_ns; /* departure time for next sent data packet */
- u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */
/* RTT measurement */
- u64 tcp_mstamp; /* most recent packet received/sent */
- u32 srtt_us; /* smoothed round trip time << 3 in usecs */
- u32 mdev_us; /* medium deviation */
u32 mdev_max_us; /* maximal mdev for the last rtt period */
- u32 rttvar_us; /* smoothed mdev_max */
- u32 rtt_seq; /* sequence number to update rttvar */
- struct minmax rtt_min;
- u32 packets_out; /* Packets which are "in flight" */
- u32 retrans_out; /* Retransmitted packets out */
- u32 max_packets_out; /* max packets_out in last window */
- u32 cwnd_usage_seq; /* right edge of cwnd usage tracking flight */
-
- u16 urg_data; /* Saved octet of OOB data and control flags */
- u8 ecn_flags; /* ECN status bits. */
u8 keepalive_probes; /* num of allowed keep alive probes */
- u32 reordering; /* Packet reordering metric. */
u32 reord_seen; /* number of data packet reordering events */
- u32 snd_up; /* Urgent pointer */
-
-/*
- * Options received (usually on last packet, some only on SYN packets).
- */
- struct tcp_options_received rx_opt;
/*
* Slow start and congestion control (see also Nagle, and Karn & Partridge)
*/
- u32 snd_ssthresh; /* Slow start size threshold */
- u32 snd_cwnd; /* Sending congestion window */
u32 snd_cwnd_cnt; /* Linear increase counter */
u32 snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */
u32 snd_cwnd_used;
@@ -343,32 +402,10 @@ struct tcp_sock {
u32 prior_cwnd; /* cwnd right before starting loss recovery */
u32 prr_delivered; /* Number of newly delivered packets to
* receiver in Recovery. */
- u32 prr_out; /* Total number of pkts sent during Recovery. */
- u32 delivered; /* Total data packets delivered incl. rexmits */
- u32 delivered_ce; /* Like the above but only ECE marked packets */
- u32 lost; /* Total data packets lost incl. rexmits */
- u32 app_limited; /* limited until "delivered" reaches this val */
- u64 first_tx_mstamp; /* start of window send phase */
- u64 delivered_mstamp; /* time we reached "delivered" */
- u32 rate_delivered; /* saved rate sample: packets delivered */
- u32 rate_interval_us; /* saved rate sample: time elapsed */
-
- u32 rcv_wnd; /* Current receiver window */
- u32 write_seq; /* Tail(+1) of data held in tcp send buffer */
- u32 notsent_lowat; /* TCP_NOTSENT_LOWAT */
- u32 pushed_seq; /* Last pushed seq, required to talk to windows */
- u32 lost_out; /* Lost packets */
- u32 sacked_out; /* SACK'd packets */
struct hrtimer pacing_timer;
struct hrtimer compressed_ack_timer;
- /* from STCP, retrans queue hinting */
- struct sk_buff* lost_skb_hint;
- struct sk_buff *retransmit_skb_hint;
-
- /* OOO segments go in this rbtree. Socket lock must be held. */
- struct rb_root out_of_order_queue;
struct sk_buff *ooo_last_skb; /* cache rb_last(out_of_order_queue) */
/* SACKs data, these 2 need to be together (see tcp_options_write) */
@@ -377,12 +414,6 @@ struct tcp_sock {
struct tcp_sack_block recv_sack_cache[4];
- struct sk_buff *highest_sack; /* skb just after the highest
- * skb with SACKed bit set
- * (validity guaranteed only if
- * sacked_out > 0)
- */
-
int lost_cnt_hint;
u32 prior_ssthresh; /* ssthresh saved at recovery start */
@@ -433,21 +464,6 @@ struct tcp_sock {
u32 rcv_ooopack; /* Received out-of-order packets, for tcpinfo */
-/* Receiver side RTT estimation */
- u32 rcv_rtt_last_tsecr;
- struct {
- u32 rtt_us;
- u32 seq;
- u64 time;
- } rcv_rtt_est;
-
-/* Receiver queue space */
- struct {
- u32 space;
- u32 seq;
- u64 time;
- } rcvq_space;
-
/* TCP-specific MTU probe information. */
struct {
u32 probe_seq_start;
diff --git a/include/linux/units.h b/include/linux/units.h
index ff1bd6b5f5b3..45110daaf8d3 100644
--- a/include/linux/units.h
+++ b/include/linux/units.h
@@ -2,6 +2,7 @@
#ifndef _LINUX_UNITS_H
#define _LINUX_UNITS_H
+#include <linux/bits.h>
#include <linux/math.h>
/* Metric prefixes in accordance with Système international (d'unités) */
diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h
index b513749582d7..e4de6bc1f69b 100644
--- a/include/linux/usb/phy.h
+++ b/include/linux/usb/phy.h
@@ -144,10 +144,6 @@ struct usb_phy {
*/
int (*set_wakeup)(struct usb_phy *x, bool enabled);
- /* notify phy port status change */
- int (*notify_port_status)(struct usb_phy *x, int port,
- u16 portstatus, u16 portchange);
-
/* notify phy connect status change */
int (*notify_connect)(struct usb_phy *x,
enum usb_device_speed speed);
@@ -321,15 +317,6 @@ usb_phy_set_wakeup(struct usb_phy *x, bool enabled)
}
static inline int
-usb_phy_notify_port_status(struct usb_phy *x, int port, u16 portstatus, u16 portchange)
-{
- if (x && x->notify_port_status)
- return x->notify_port_status(x, port, portstatus, portchange);
- else
- return 0;
-}
-
-static inline int
usb_phy_notify_connect(struct usb_phy *x, enum usb_device_speed speed)
{
if (x && x->notify_connect)
diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h
index 287e9d83fb8b..33a4c146dc19 100644
--- a/include/linux/usb/r8152.h
+++ b/include/linux/usb/r8152.h
@@ -30,6 +30,7 @@
#define VENDOR_ID_NVIDIA 0x0955
#define VENDOR_ID_TPLINK 0x2357
#define VENDOR_ID_DLINK 0x2001
+#define VENDOR_ID_ASUS 0x0b05
#if IS_REACHABLE(CONFIG_USB_RTL8152)
extern u8 rtl8152_get_version(struct usb_interface *intf);
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 454e9295970c..a65b2513f8cd 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -289,16 +289,12 @@ void vfio_combine_iova_ranges(struct rb_root_cached *root, u32 cur_nodes,
/*
* External user API
*/
-#if IS_ENABLED(CONFIG_VFIO_GROUP)
struct iommu_group *vfio_file_iommu_group(struct file *file);
+
+#if IS_ENABLED(CONFIG_VFIO_GROUP)
bool vfio_file_is_group(struct file *file);
bool vfio_file_has_dev(struct file *file, struct vfio_device *device);
#else
-static inline struct iommu_group *vfio_file_iommu_group(struct file *file)
-{
- return NULL;
-}
-
static inline bool vfio_file_is_group(struct file *file)
{
return false;
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index ebb3ce63d64d..c82089dee0c8 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -256,4 +256,5 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit);
void virtio_transport_deliver_tap_pkt(struct sk_buff *skb);
int virtio_transport_purge_skbs(void *vsk, struct sk_buff_head *list);
int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t read_actor);
+int virtio_transport_notify_set_rcvlowat(struct vsock_sock *vsk, int val);
#endif /* _LINUX_VIRTIO_VSOCK_H */
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 4ae0580b63ca..ea13e1e4a7c2 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -191,7 +191,7 @@ int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index,
struct nlattr *est, struct tc_action **a,
const struct tc_action_ops *ops, int bind,
u32 flags);
-void tcf_idr_insert_many(struct tc_action *actions[]);
+void tcf_idr_insert_many(struct tc_action *actions[], int init_res[]);
void tcf_idr_cleanup(struct tc_action_net *tn, u32 index);
int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
struct tc_action **a, int bind);
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 82da55101b5a..61ebe723ee4d 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -31,17 +31,22 @@ struct prefix_info {
__u8 length;
__u8 prefix_len;
+ union __packed {
+ __u8 flags;
+ struct __packed {
#if defined(__BIG_ENDIAN_BITFIELD)
- __u8 onlink : 1,
+ __u8 onlink : 1,
autoconf : 1,
reserved : 6;
#elif defined(__LITTLE_ENDIAN_BITFIELD)
- __u8 reserved : 6,
+ __u8 reserved : 6,
autoconf : 1,
onlink : 1;
#else
#error "Please fix <asm/byteorder.h>"
#endif
+ };
+ };
__be32 valid;
__be32 prefered;
__be32 reserved2;
@@ -49,6 +54,9 @@ struct prefix_info {
struct in6_addr prefix;
};
+/* rfc4861 4.6.2: IPv6 PIO is 32 bytes in size */
+static_assert(sizeof(struct prefix_info) == 32);
+
#include <linux/ipv6.h>
#include <linux/netdevice.h>
#include <net/if_inet6.h>
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 824c258143a3..49c4640027d8 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -75,6 +75,7 @@ struct unix_sock {
};
#define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk)
+#define unix_peer(sk) (unix_sk(sk)->peer)
#define peer_wait peer_wq.wait
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index e302c0e804d0..535701efc1e5 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -137,7 +137,6 @@ struct vsock_transport {
u64 (*stream_rcvhiwat)(struct vsock_sock *);
bool (*stream_is_active)(struct vsock_sock *);
bool (*stream_allow)(u32 cid, u32 port);
- int (*set_rcvlowat)(struct vsock_sock *vsk, int val);
/* SEQ_PACKET. */
ssize_t (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg,
@@ -168,6 +167,7 @@ struct vsock_transport {
struct vsock_transport_send_notify_data *);
/* sk_lock held by the caller */
void (*notify_buffer_size)(struct vsock_sock *, u64 *);
+ int (*notify_set_rcvlowat)(struct vsock_sock *vsk, int val);
/* Shutdown. */
int (*shutdown)(struct vsock_sock *, int);
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 602960dafe0f..ac1fb326dcda 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -9375,4 +9375,50 @@ bool cfg80211_valid_disable_subchannel_bitmap(u16 *bitmap,
*/
void cfg80211_links_removed(struct net_device *dev, u16 link_mask);
+#ifdef CONFIG_CFG80211_DEBUGFS
+/**
+ * wiphy_locked_debugfs_read - do a locked read in debugfs
+ * @wiphy: the wiphy to use
+ * @file: the file being read
+ * @buf: the buffer to fill and then read from
+ * @bufsize: size of the buffer
+ * @userbuf: the user buffer to copy to
+ * @count: read count
+ * @ppos: read position
+ * @handler: the read handler to call (under wiphy lock)
+ * @data: additional data to pass to the read handler
+ */
+ssize_t wiphy_locked_debugfs_read(struct wiphy *wiphy, struct file *file,
+ char *buf, size_t bufsize,
+ char __user *userbuf, size_t count,
+ loff_t *ppos,
+ ssize_t (*handler)(struct wiphy *wiphy,
+ struct file *file,
+ char *buf,
+ size_t bufsize,
+ void *data),
+ void *data);
+
+/**
+ * wiphy_locked_debugfs_write - do a locked write in debugfs
+ * @wiphy: the wiphy to use
+ * @file: the file being written to
+ * @buf: the buffer to copy the user data to
+ * @bufsize: size of the buffer
+ * @userbuf: the user buffer to copy from
+ * @count: read count
+ * @handler: the write handler to call (under wiphy lock)
+ * @data: additional data to pass to the write handler
+ */
+ssize_t wiphy_locked_debugfs_write(struct wiphy *wiphy, struct file *file,
+ char *buf, size_t bufsize,
+ const char __user *userbuf, size_t count,
+ ssize_t (*handler)(struct wiphy *wiphy,
+ struct file *file,
+ char *buf,
+ size_t count,
+ void *data),
+ void *data);
+#endif
+
#endif /* __NET_CFG80211_H */
diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h
index 3c70ad53a49c..278e4c7d465c 100644
--- a/include/net/dropreason-core.h
+++ b/include/net/dropreason-core.h
@@ -86,6 +86,7 @@
FN(IPV6_NDISC_NS_OTHERHOST) \
FN(QUEUE_PURGE) \
FN(TC_ERROR) \
+ FN(PACKET_SOCK_ERROR) \
FNe(MAX)
/**
@@ -379,6 +380,11 @@ enum skb_drop_reason {
/** @SKB_DROP_REASON_TC_ERROR: generic internal tc error. */
SKB_DROP_REASON_TC_ERROR,
/**
+ * @SKB_DROP_REASON_PACKET_SOCK_ERROR: generic packet socket errors
+ * after its filter matches an incoming packet.
+ */
+ SKB_DROP_REASON_PACKET_SOCK_ERROR,
+ /**
* @SKB_DROP_REASON_MAX: the maximum of core drop reasons, which
* shouldn't be used as a real 'reason' - only for tracing code gen
*/
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index e18a4c0d69ee..c53244f20437 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -12,10 +12,12 @@
* struct genl_multicast_group - generic netlink multicast group
* @name: name of the multicast group, names are per-family
* @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM)
+ * @cap_sys_admin: whether %CAP_SYS_ADMIN is required for binding
*/
struct genl_multicast_group {
char name[GENL_NAMSIZ];
u8 flags;
+ u8 cap_sys_admin:1;
};
struct genl_split_ops;
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 3e454c4d7ba6..f07642264c1e 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -22,10 +22,6 @@
#define IF_RS_SENT 0x10
#define IF_READY 0x80000000
-/* prefix flags */
-#define IF_PREFIX_ONLINK 0x01
-#define IF_PREFIX_AUTOCONF 0x02
-
enum {
INET6_IFADDR_STATE_PREDAD,
INET6_IFADDR_STATE_DAD,
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 74db6d97cae1..aa86453f6b9b 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -234,10 +234,7 @@ struct inet_sock {
int uc_index;
int mc_index;
__be32 mc_addr;
- struct {
- __u16 lo;
- __u16 hi;
- } local_port_range;
+ u32 local_port_range; /* high << 16 | low */
struct ip_mc_socklist __rcu *mc_list;
struct inet_cork_full cork;
diff --git a/include/net/ip.h b/include/net/ip.h
index 1fc4c8d69e33..de0c69c57e3c 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -349,8 +349,14 @@ static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_o
} \
}
-void inet_get_local_port_range(const struct net *net, int *low, int *high);
-void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high);
+static inline void inet_get_local_port_range(const struct net *net, int *low, int *high)
+{
+ u32 range = READ_ONCE(net->ipv4.ip_local_ports.range);
+
+ *low = range & 0xffff;
+ *high = range >> 16;
+}
+bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high);
#ifdef CONFIG_SYSCTL
static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 1ba9f4ddf2f6..95ed495c3a40 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -328,8 +328,10 @@ static inline bool fib6_info_hold_safe(struct fib6_info *f6i)
static inline void fib6_info_release(struct fib6_info *f6i)
{
- if (f6i && refcount_dec_and_test(&f6i->fib6_ref))
+ if (f6i && refcount_dec_and_test(&f6i->fib6_ref)) {
+ DEBUG_NET_WARN_ON_ONCE(!hlist_unhashed(&f6i->gc_link));
call_rcu(&f6i->rcu, fib6_info_destroy_rcu);
+ }
}
enum fib6_walk_state {
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 88b6ef7ce1a6..76f2fd2645b7 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -293,6 +293,7 @@ struct gdma_queue {
u32 head;
u32 tail;
+ struct list_head entry;
/* Extra fields specific to EQ/CQ. */
union {
@@ -328,6 +329,7 @@ struct gdma_queue_spec {
void *context;
unsigned long log2_throttle_limit;
+ unsigned int msix_index;
} eq;
struct {
@@ -344,7 +346,9 @@ struct gdma_queue_spec {
struct gdma_irq_context {
void (*handler)(void *arg);
- void *arg;
+ /* Protect the eq_list */
+ spinlock_t lock;
+ struct list_head eq_list;
char name[MANA_IRQ_NAME_SZ];
};
@@ -355,7 +359,6 @@ struct gdma_context {
unsigned int max_num_queues;
unsigned int max_num_msix;
unsigned int num_msix_usable;
- struct gdma_resource msix_resource;
struct gdma_irq_context *irq_contexts;
/* L2 MTU */
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 07022bb0d44d..0d28172193fa 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -162,7 +162,7 @@ struct neighbour {
struct rcu_head rcu;
struct net_device *dev;
netdevice_tracker dev_tracker;
- u8 primary_key[0];
+ u8 primary_key[];
} __randomize_layout;
struct neigh_ops {
diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h
index cdcafb30d437..aa1716fb0e53 100644
--- a/include/net/netdev_rx_queue.h
+++ b/include/net/netdev_rx_queue.h
@@ -21,6 +21,10 @@ struct netdev_rx_queue {
#ifdef CONFIG_XDP_SOCKETS
struct xsk_buff_pool *pool;
#endif
+ /* NAPI instance for the queue
+ * Readers and writers must hold RTNL
+ */
+ struct napi_struct *napi;
} ____cacheline_aligned_in_smp;
/*
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index fe1507c1db82..692d5955911c 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -62,6 +62,8 @@ struct nf_flowtable_type {
enum flow_offload_tuple_dir dir,
struct nf_flow_rule *flow_rule);
void (*free)(struct nf_flowtable *ft);
+ void (*get)(struct nf_flowtable *ft);
+ void (*put)(struct nf_flowtable *ft);
nf_hookfn *hook;
struct module *owner;
};
@@ -240,6 +242,11 @@ nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table,
}
list_add_tail(&block_cb->list, &block->cb_list);
+ up_write(&flow_table->flow_block_lock);
+
+ if (flow_table->type->get)
+ flow_table->type->get(flow_table);
+ return 0;
unlock:
up_write(&flow_table->flow_block_lock);
@@ -262,6 +269,9 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table,
WARN_ON(true);
}
up_write(&flow_table->flow_block_lock);
+
+ if (flow_table->type->put)
+ flow_table->type->put(flow_table);
}
void flow_offload_route_init(struct flow_offload *flow,
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 167b91348e57..28039e57070a 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -1214,7 +1214,7 @@ static inline void *nla_data(const struct nlattr *nla)
* nla_len - length of payload
* @nla: netlink attribute
*/
-static inline int nla_len(const struct nlattr *nla)
+static inline u16 nla_len(const struct nlattr *nla)
{
return nla->nla_len - NLA_HDRLEN;
}
diff --git a/include/net/netns/core.h b/include/net/netns/core.h
index a91ef9f8de60..78214f1b43a2 100644
--- a/include/net/netns/core.h
+++ b/include/net/netns/core.h
@@ -13,6 +13,7 @@ struct netns_core {
struct ctl_table_header *sysctl_hdr;
int sysctl_somaxconn;
+ int sysctl_optmem_max;
u8 sysctl_txrehash;
#ifdef CONFIG_PROC_FS
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 73f43f699199..c356c458b340 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -19,8 +19,7 @@ struct hlist_head;
struct fib_table;
struct sock;
struct local_ports {
- seqlock_t lock;
- int range[2];
+ u32 range; /* high << 16 | low */
bool warned;
};
@@ -42,6 +41,38 @@ struct inet_timewait_death_row {
struct tcp_fastopen_context;
struct netns_ipv4 {
+ /* Cacheline organization can be found documented in
+ * Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst.
+ * Please update the document when adding new fields.
+ */
+
+ /* TX readonly hotpath cache lines */
+ __cacheline_group_begin(netns_ipv4_read_tx);
+ u8 sysctl_tcp_early_retrans;
+ u8 sysctl_tcp_tso_win_divisor;
+ u8 sysctl_tcp_tso_rtt_log;
+ u8 sysctl_tcp_autocorking;
+ int sysctl_tcp_min_snd_mss;
+ unsigned int sysctl_tcp_notsent_lowat;
+ int sysctl_tcp_limit_output_bytes;
+ int sysctl_tcp_min_rtt_wlen;
+ int sysctl_tcp_wmem[3];
+ u8 sysctl_ip_fwd_use_pmtu;
+ __cacheline_group_end(netns_ipv4_read_tx);
+
+ /* TXRX readonly hotpath cache lines */
+ __cacheline_group_begin(netns_ipv4_read_txrx);
+ u8 sysctl_tcp_moderate_rcvbuf;
+ __cacheline_group_end(netns_ipv4_read_txrx);
+
+ /* RX readonly hotpath cache line */
+ __cacheline_group_begin(netns_ipv4_read_rx);
+ u8 sysctl_ip_early_demux;
+ u8 sysctl_tcp_early_demux;
+ int sysctl_tcp_reordering;
+ int sysctl_tcp_rmem[3];
+ __cacheline_group_end(netns_ipv4_read_rx);
+
struct inet_timewait_death_row tcp_death_row;
struct udp_table *udp_table;
@@ -96,17 +127,14 @@ struct netns_ipv4 {
u8 sysctl_ip_default_ttl;
u8 sysctl_ip_no_pmtu_disc;
- u8 sysctl_ip_fwd_use_pmtu;
u8 sysctl_ip_fwd_update_priority;
u8 sysctl_ip_nonlocal_bind;
u8 sysctl_ip_autobind_reuse;
/* Shall we try to damage output packets if routing dev changes? */
u8 sysctl_ip_dynaddr;
- u8 sysctl_ip_early_demux;
#ifdef CONFIG_NET_L3_MASTER_DEV
u8 sysctl_raw_l3mdev_accept;
#endif
- u8 sysctl_tcp_early_demux;
u8 sysctl_udp_early_demux;
u8 sysctl_nexthop_compat_mode;
@@ -119,7 +147,6 @@ struct netns_ipv4 {
u8 sysctl_tcp_mtu_probing;
int sysctl_tcp_mtu_probe_floor;
int sysctl_tcp_base_mss;
- int sysctl_tcp_min_snd_mss;
int sysctl_tcp_probe_threshold;
u32 sysctl_tcp_probe_interval;
@@ -135,17 +162,14 @@ struct netns_ipv4 {
u8 sysctl_tcp_backlog_ack_defer;
u8 sysctl_tcp_pingpong_thresh;
- int sysctl_tcp_reordering;
u8 sysctl_tcp_retries1;
u8 sysctl_tcp_retries2;
u8 sysctl_tcp_orphan_retries;
u8 sysctl_tcp_tw_reuse;
int sysctl_tcp_fin_timeout;
- unsigned int sysctl_tcp_notsent_lowat;
u8 sysctl_tcp_sack;
u8 sysctl_tcp_window_scaling;
u8 sysctl_tcp_timestamps;
- u8 sysctl_tcp_early_retrans;
u8 sysctl_tcp_recovery;
u8 sysctl_tcp_thin_linear_timeouts;
u8 sysctl_tcp_slow_start_after_idle;
@@ -161,21 +185,13 @@ struct netns_ipv4 {
u8 sysctl_tcp_frto;
u8 sysctl_tcp_nometrics_save;
u8 sysctl_tcp_no_ssthresh_metrics_save;
- u8 sysctl_tcp_moderate_rcvbuf;
- u8 sysctl_tcp_tso_win_divisor;
u8 sysctl_tcp_workaround_signed_windows;
- int sysctl_tcp_limit_output_bytes;
int sysctl_tcp_challenge_ack_limit;
- int sysctl_tcp_min_rtt_wlen;
u8 sysctl_tcp_min_tso_segs;
- u8 sysctl_tcp_tso_rtt_log;
- u8 sysctl_tcp_autocorking;
u8 sysctl_tcp_reflect_tos;
int sysctl_tcp_invalid_ratelimit;
int sysctl_tcp_pacing_ss_ratio;
int sysctl_tcp_pacing_ca_ratio;
- int sysctl_tcp_wmem[3];
- int sysctl_tcp_rmem[3];
unsigned int sysctl_tcp_child_ehash_entries;
unsigned long sysctl_tcp_comp_sack_delay_ns;
unsigned long sysctl_tcp_comp_sack_slack_ns;
diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index 7dc65774cde5..1d397c1a0043 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -11,7 +11,7 @@
* The page_pool allocator is optimized for recycling page or page fragment used
* by skb packet and xdp frame.
*
- * Basic use involves replacing and alloc_pages() calls with page_pool_alloc(),
+ * Basic use involves replacing any alloc_pages() calls with page_pool_alloc(),
* which allocate memory with or without page splitting depending on the
* requested memory size.
*
@@ -29,7 +29,7 @@
* page allocated from page pool. Page splitting enables memory saving and thus
* avoids TLB/cache miss for data access, but there also is some cost to
* implement page splitting, mainly some cache line dirtying/bouncing for
- * 'struct page' and atomic operation for page->pp_frag_count.
+ * 'struct page' and atomic operation for page->pp_ref_count.
*
* The API keeps track of in-flight pages, in order to let API users know when
* it is safe to free a page_pool object, the API users must call
@@ -37,15 +37,15 @@
* attach the page_pool object to a page_pool-aware object like skbs marked with
* skb_mark_for_recycle().
*
- * page_pool_put_page() may be called multi times on the same page if a page is
- * split into multi fragments. For the last fragment, it will either recycle the
- * page, or in case of page->_refcount > 1, it will release the DMA mapping and
- * in-flight state accounting.
+ * page_pool_put_page() may be called multiple times on the same page if a page
+ * is split into multiple fragments. For the last fragment, it will either
+ * recycle the page, or in case of page->_refcount > 1, it will release the DMA
+ * mapping and in-flight state accounting.
*
* dma_sync_single_range_for_device() is only called for the last fragment when
* page_pool is created with PP_FLAG_DMA_SYNC_DEV flag, so it depends on the
* last freed fragment to do the sync_for_device operation for all fragments in
- * the same page when a page is split, the API user must setup pool->p.max_len
+ * the same page when a page is split. The API user must setup pool->p.max_len
* and pool->p.offset correctly and ensure that page_pool_put_page() is called
* with dma_sync_size being -1 for fragment API.
*/
@@ -210,69 +210,82 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool)
return pool->p.dma_dir;
}
-/* pp_frag_count represents the number of writers who can update the page
- * either by updating skb->data or via DMA mappings for the device.
- * We can't rely on the page refcnt for that as we don't know who might be
- * holding page references and we can't reliably destroy or sync DMA mappings
- * of the fragments.
+/**
+ * page_pool_fragment_page() - split a fresh page into fragments
+ * @page: page to split
+ * @nr: references to set
+ *
+ * pp_ref_count represents the number of outstanding references to the page,
+ * which will be freed using page_pool APIs (rather than page allocator APIs
+ * like put_page()). Such references are usually held by page_pool-aware
+ * objects like skbs marked for page pool recycling.
*
- * When pp_frag_count reaches 0 we can either recycle the page if the page
- * refcnt is 1 or return it back to the memory allocator and destroy any
- * mappings we have.
+ * This helper allows the caller to take (set) multiple references to a
+ * freshly allocated page. The page must be freshly allocated (have a
+ * pp_ref_count of 1). This is commonly done by drivers and
+ * "fragment allocators" to save atomic operations - either when they know
+ * upfront how many references they will need; or to take MAX references and
+ * return the unused ones with a single atomic dec(), instead of performing
+ * multiple atomic inc() operations.
*/
static inline void page_pool_fragment_page(struct page *page, long nr)
{
- atomic_long_set(&page->pp_frag_count, nr);
+ atomic_long_set(&page->pp_ref_count, nr);
}
-static inline long page_pool_defrag_page(struct page *page, long nr)
+static inline long page_pool_unref_page(struct page *page, long nr)
{
long ret;
- /* If nr == pp_frag_count then we have cleared all remaining
+ /* If nr == pp_ref_count then we have cleared all remaining
* references to the page:
* 1. 'n == 1': no need to actually overwrite it.
* 2. 'n != 1': overwrite it with one, which is the rare case
- * for pp_frag_count draining.
+ * for pp_ref_count draining.
*
* The main advantage to doing this is that not only we avoid a atomic
* update, as an atomic_read is generally a much cheaper operation than
* an atomic update, especially when dealing with a page that may be
- * partitioned into only 2 or 3 pieces; but also unify the pp_frag_count
+ * referenced by only 2 or 3 users; but also unify the pp_ref_count
* handling by ensuring all pages have partitioned into only 1 piece
* initially, and only overwrite it when the page is partitioned into
* more than one piece.
*/
- if (atomic_long_read(&page->pp_frag_count) == nr) {
+ if (atomic_long_read(&page->pp_ref_count) == nr) {
/* As we have ensured nr is always one for constant case using
* the BUILD_BUG_ON(), only need to handle the non-constant case
- * here for pp_frag_count draining, which is a rare case.
+ * here for pp_ref_count draining, which is a rare case.
*/
BUILD_BUG_ON(__builtin_constant_p(nr) && nr != 1);
if (!__builtin_constant_p(nr))
- atomic_long_set(&page->pp_frag_count, 1);
+ atomic_long_set(&page->pp_ref_count, 1);
return 0;
}
- ret = atomic_long_sub_return(nr, &page->pp_frag_count);
+ ret = atomic_long_sub_return(nr, &page->pp_ref_count);
WARN_ON(ret < 0);
- /* We are the last user here too, reset pp_frag_count back to 1 to
+ /* We are the last user here too, reset pp_ref_count back to 1 to
* ensure all pages have been partitioned into 1 piece initially,
* this should be the rare case when the last two fragment users call
- * page_pool_defrag_page() currently.
+ * page_pool_unref_page() currently.
*/
if (unlikely(!ret))
- atomic_long_set(&page->pp_frag_count, 1);
+ atomic_long_set(&page->pp_ref_count, 1);
return ret;
}
-static inline bool page_pool_is_last_frag(struct page *page)
+static inline void page_pool_ref_page(struct page *page)
+{
+ atomic_long_inc(&page->pp_ref_count);
+}
+
+static inline bool page_pool_is_last_ref(struct page *page)
{
- /* If page_pool_defrag_page() returns 0, we were the last user */
- return page_pool_defrag_page(page, 1) == 0;
+ /* If page_pool_unref_page() returns 0, we were the last user */
+ return page_pool_unref_page(page, 1) == 0;
}
/**
@@ -297,10 +310,10 @@ static inline void page_pool_put_page(struct page_pool *pool,
* allow registering MEM_TYPE_PAGE_POOL, but shield linker.
*/
#ifdef CONFIG_PAGE_POOL
- if (!page_pool_is_last_frag(page))
+ if (!page_pool_is_last_ref(page))
return;
- page_pool_put_defragged_page(pool, page, dma_sync_size, allow_direct);
+ page_pool_put_unrefed_page(pool, page, dma_sync_size, allow_direct);
#endif
}
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index ac286ea8ce2d..76481c465375 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -234,9 +234,9 @@ static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data,
}
#endif
-void page_pool_put_defragged_page(struct page_pool *pool, struct page *page,
- unsigned int dma_sync_size,
- bool allow_direct);
+void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page,
+ unsigned int dma_sync_size,
+ bool allow_direct);
static inline bool is_page_pool_compiled_in(void)
{
diff --git a/include/net/sock.h b/include/net/sock.h
index 1d6931caf0c3..8b6fe164b218 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2920,7 +2920,6 @@ extern __u32 sysctl_wmem_max;
extern __u32 sysctl_rmem_max;
extern int sysctl_tstamp_allow_data;
-extern int sysctl_optmem_max;
extern __u32 sysctl_wmem_default;
extern __u32 sysctl_rmem_default;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 973555cb1d3f..f5ca4abaee8b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1518,17 +1518,22 @@ static inline int tcp_full_space(const struct sock *sk)
return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
}
-static inline void tcp_adjust_rcv_ssthresh(struct sock *sk)
+static inline void __tcp_adjust_rcv_ssthresh(struct sock *sk, u32 new_ssthresh)
{
int unused_mem = sk_unused_reserved_mem(sk);
struct tcp_sock *tp = tcp_sk(sk);
- tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
+ tp->rcv_ssthresh = min(tp->rcv_ssthresh, new_ssthresh);
if (unused_mem)
tp->rcv_ssthresh = max_t(u32, tp->rcv_ssthresh,
tcp_win_from_space(sk, unused_mem));
}
+static inline void tcp_adjust_rcv_ssthresh(struct sock *sk)
+{
+ __tcp_adjust_rcv_ssthresh(sk, 4U * tcp_sk(sk)->advmss);
+}
+
void tcp_cleanup_rbuf(struct sock *sk, int copied);
void __tcp_cleanup_rbuf(struct sock *sk, int copied);
diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h
index 4d900ef8dfc3..0f2dcc9e8d46 100644
--- a/include/net/tcp_ao.h
+++ b/include/net/tcp_ao.h
@@ -62,11 +62,17 @@ static inline int tcp_ao_maclen(const struct tcp_ao_key *key)
return key->maclen;
}
+/* Use tcp_ao_len_aligned() for TCP header calculations */
static inline int tcp_ao_len(const struct tcp_ao_key *key)
{
return tcp_ao_maclen(key) + sizeof(struct tcp_ao_hdr);
}
+static inline int tcp_ao_len_aligned(const struct tcp_ao_key *key)
+{
+ return round_up(tcp_ao_len(key), 4);
+}
+
static inline unsigned int tcp_ao_digest_size(struct tcp_ao_key *key)
{
return key->digest_size;
diff --git a/include/net/tcp_states.h b/include/net/tcp_states.h
index cc00118acca1..d60e8148ff4c 100644
--- a/include/net/tcp_states.h
+++ b/include/net/tcp_states.h
@@ -22,6 +22,7 @@ enum {
TCP_LISTEN,
TCP_CLOSING, /* Now a valid state */
TCP_NEW_SYN_RECV,
+ TCP_BOUND_INACTIVE, /* Pseudo-state for inet_diag */
TCP_MAX_STATES /* Leave at the end! */
};
@@ -43,6 +44,7 @@ enum {
TCPF_LISTEN = (1 << TCP_LISTEN),
TCPF_CLOSING = (1 << TCP_CLOSING),
TCPF_NEW_SYN_RECV = (1 << TCP_NEW_SYN_RECV),
+ TCPF_BOUND_INACTIVE = (1 << TCP_BOUND_INACTIVE),
};
#endif /* _LINUX_TCP_STATES_H */
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index f83128007fb0..3cb4dc9bd70e 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -30,6 +30,7 @@ struct xdp_umem {
struct user_struct *user;
refcount_t users;
u8 flags;
+ u8 tx_metadata_len;
bool zc;
struct page **pgs;
int id;
@@ -92,12 +93,105 @@ struct xdp_sock {
struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */
};
+/*
+ * AF_XDP TX metadata hooks for network devices.
+ * The following hooks can be defined; unless noted otherwise, they are
+ * optional and can be filled with a null pointer.
+ *
+ * void (*tmo_request_timestamp)(void *priv)
+ * Called when AF_XDP frame requested egress timestamp.
+ *
+ * u64 (*tmo_fill_timestamp)(void *priv)
+ * Called when AF_XDP frame, that had requested egress timestamp,
+ * received a completion. The hook needs to return the actual HW timestamp.
+ *
+ * void (*tmo_request_checksum)(u16 csum_start, u16 csum_offset, void *priv)
+ * Called when AF_XDP frame requested HW checksum offload. csum_start
+ * indicates position where checksumming should start.
+ * csum_offset indicates position where checksum should be stored.
+ *
+ */
+struct xsk_tx_metadata_ops {
+ void (*tmo_request_timestamp)(void *priv);
+ u64 (*tmo_fill_timestamp)(void *priv);
+ void (*tmo_request_checksum)(u16 csum_start, u16 csum_offset, void *priv);
+};
+
#ifdef CONFIG_XDP_SOCKETS
int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp);
void __xsk_map_flush(void);
+/**
+ * xsk_tx_metadata_to_compl - Save enough relevant metadata information
+ * to perform tx completion in the future.
+ * @meta: pointer to AF_XDP metadata area
+ * @compl: pointer to output struct xsk_tx_metadata_to_compl
+ *
+ * This function should be called by the networking device when
+ * it prepares AF_XDP egress packet. The value of @compl should be stored
+ * and passed to xsk_tx_metadata_complete upon TX completion.
+ */
+static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta,
+ struct xsk_tx_metadata_compl *compl)
+{
+ if (!meta)
+ return;
+
+ if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)
+ compl->tx_timestamp = &meta->completion.tx_timestamp;
+ else
+ compl->tx_timestamp = NULL;
+}
+
+/**
+ * xsk_tx_metadata_request - Evaluate AF_XDP TX metadata at submission
+ * and call appropriate xsk_tx_metadata_ops operation.
+ * @meta: pointer to AF_XDP metadata area
+ * @ops: pointer to struct xsk_tx_metadata_ops
+ * @priv: pointer to driver-private aread
+ *
+ * This function should be called by the networking device when
+ * it prepares AF_XDP egress packet.
+ */
+static inline void xsk_tx_metadata_request(const struct xsk_tx_metadata *meta,
+ const struct xsk_tx_metadata_ops *ops,
+ void *priv)
+{
+ if (!meta)
+ return;
+
+ if (ops->tmo_request_timestamp)
+ if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)
+ ops->tmo_request_timestamp(priv);
+
+ if (ops->tmo_request_checksum)
+ if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM)
+ ops->tmo_request_checksum(meta->request.csum_start,
+ meta->request.csum_offset, priv);
+}
+
+/**
+ * xsk_tx_metadata_complete - Evaluate AF_XDP TX metadata at completion
+ * and call appropriate xsk_tx_metadata_ops operation.
+ * @compl: pointer to completion metadata produced from xsk_tx_metadata_to_compl
+ * @ops: pointer to struct xsk_tx_metadata_ops
+ * @priv: pointer to driver-private aread
+ *
+ * This function should be called by the networking device upon
+ * AF_XDP egress completion.
+ */
+static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl,
+ const struct xsk_tx_metadata_ops *ops,
+ void *priv)
+{
+ if (!compl)
+ return;
+
+ *compl->tx_timestamp = ops->tmo_fill_timestamp(priv);
+}
+
#else
static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
@@ -114,6 +208,23 @@ static inline void __xsk_map_flush(void)
{
}
+static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta,
+ struct xsk_tx_metadata_compl *compl)
+{
+}
+
+static inline void xsk_tx_metadata_request(struct xsk_tx_metadata *meta,
+ const struct xsk_tx_metadata_ops *ops,
+ void *priv)
+{
+}
+
+static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl,
+ const struct xsk_tx_metadata_ops *ops,
+ void *priv)
+{
+}
+
#endif /* CONFIG_XDP_SOCKETS */
#if defined(CONFIG_XDP_SOCKETS) && defined(CONFIG_DEBUG_NET)
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 1f6fc8c7a84c..81e02de3f453 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -165,6 +165,30 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
return xp_raw_get_data(pool, addr);
}
+#define XDP_TXMD_FLAGS_VALID ( \
+ XDP_TXMD_FLAGS_TIMESTAMP | \
+ XDP_TXMD_FLAGS_CHECKSUM | \
+ 0)
+
+static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta)
+{
+ return !(meta->flags & ~XDP_TXMD_FLAGS_VALID);
+}
+
+static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr)
+{
+ struct xsk_tx_metadata *meta;
+
+ if (!pool->tx_metadata_len)
+ return NULL;
+
+ meta = xp_raw_get_data(pool, addr) - pool->tx_metadata_len;
+ if (unlikely(!xsk_buff_valid_tx_metadata(meta)))
+ return NULL; /* no way to signal the error to the user */
+
+ return meta;
+}
+
static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
{
struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
@@ -324,6 +348,16 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
return NULL;
}
+static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta)
+{
+ return false;
+}
+
+static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr)
+{
+ return NULL;
+}
+
static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp, struct xsk_buff_pool *pool)
{
}
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index b0bdff26fc88..8d48d37ab7c0 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -33,6 +33,7 @@ struct xdp_buff_xsk {
};
#define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb))
+#define XSK_TX_COMPL_FITS(t) BUILD_BUG_ON(sizeof(struct xsk_tx_metadata_compl) > sizeof(t))
struct xsk_dma_map {
dma_addr_t *dma_pages;
@@ -77,10 +78,12 @@ struct xsk_buff_pool {
u32 chunk_size;
u32 chunk_shift;
u32 frame_len;
+ u8 tx_metadata_len; /* inherited from umem */
u8 cached_need_wakeup;
bool uses_need_wakeup;
bool dma_need_sync;
bool unaligned;
+ bool tx_sw_csum;
void *addrs;
/* Mutual exclusion of the completion ring in the SKB mode. Two cases to protect:
* NAPI TX thread and sendmsg error paths in the SKB destructor callback and when
@@ -233,4 +236,9 @@ static inline u64 xp_get_handle(struct xdp_buff_xsk *xskb)
return xskb->orig_addr + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
}
+static inline bool xp_tx_metadata_enabled(const struct xsk_buff_pool *pool)
+{
+ return pool->tx_metadata_len > 0;
+}
+
#endif /* XSK_BUFF_POOL_H_ */
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 95896472a82b..565a85044541 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -77,6 +77,13 @@ static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter,
{
__rdma_block_iter_start(biter, umem->sgt_append.sgt.sgl,
umem->sgt_append.sgt.nents, pgsz);
+ biter->__sg_advance = ib_umem_offset(umem) & ~(pgsz - 1);
+ biter->__sg_numblocks = ib_umem_num_dma_blocks(umem, pgsz);
+}
+
+static inline bool __rdma_umem_block_iter_next(struct ib_block_iter *biter)
+{
+ return __rdma_block_iter_next(biter) && biter->__sg_numblocks--;
}
/**
@@ -92,7 +99,7 @@ static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter,
*/
#define rdma_umem_for_each_dma_block(umem, biter, pgsz) \
for (__rdma_umem_block_iter_start(biter, umem, pgsz); \
- __rdma_block_iter_next(biter);)
+ __rdma_umem_block_iter_next(biter);)
#ifdef CONFIG_INFINIBAND_USER_MEM
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index fb1a2d6b1969..b7b6b58dd348 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2850,6 +2850,7 @@ struct ib_block_iter {
/* internal states */
struct scatterlist *__sg; /* sg holding the current aligned block */
dma_addr_t __dma_addr; /* unaligned DMA address of this block */
+ size_t __sg_numblocks; /* ib_umem_num_dma_blocks() */
unsigned int __sg_nents; /* number of SG entries */
unsigned int __sg_advance; /* number of bytes to advance in sg in next step */
unsigned int __pg_bit; /* alignment of current block */
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 10480eb582b2..5ec1e71a09de 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -167,19 +167,25 @@ struct scsi_device {
* power state for system suspend/resume (suspend to RAM and
* hibernation) operations.
*/
- bool manage_system_start_stop;
+ unsigned manage_system_start_stop:1;
/*
* If true, let the high-level device driver (sd) manage the device
* power state for runtime device suspand and resume operations.
*/
- bool manage_runtime_start_stop;
+ unsigned manage_runtime_start_stop:1;
/*
* If true, let the high-level device driver (sd) manage the device
* power state for system shutdown (power off) operations.
*/
- bool manage_shutdown;
+ unsigned manage_shutdown:1;
+
+ /*
+ * If set and if the device is runtime suspended, ask the high-level
+ * device driver (sd) to force a runtime resume of the device.
+ */
+ unsigned force_runtime_start_on_system_start:1;
unsigned removable:1;
unsigned changed:1; /* Data invalid due to media change */
diff --git a/include/sound/cs35l41.h b/include/sound/cs35l41.h
index 043f8ac65dbf..68e053fe7340 100644
--- a/include/sound/cs35l41.h
+++ b/include/sound/cs35l41.h
@@ -906,6 +906,6 @@ int cs35l41_init_boost(struct device *dev, struct regmap *regmap,
bool cs35l41_safe_reset(struct regmap *regmap, enum cs35l41_boost_type b_type);
int cs35l41_mdsync_up(struct regmap *regmap);
int cs35l41_global_enable(struct device *dev, struct regmap *regmap, enum cs35l41_boost_type b_type,
- int enable, bool firmware_running);
+ int enable, struct cs_dsp *dsp);
#endif /* __CS35L41_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 7a5498242eaa..b1e8c5bdfc82 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6563,6 +6563,16 @@ struct bpf_link_info {
__u64 missed;
} kprobe_multi;
struct {
+ __aligned_u64 path;
+ __aligned_u64 offsets;
+ __aligned_u64 ref_ctr_offsets;
+ __aligned_u64 cookies;
+ __u32 path_size; /* in/out: real path size on success, including zero byte */
+ __u32 count; /* in/out: uprobe_multi offsets/ref_ctr_offsets/cookies count */
+ __u32 flags;
+ __u32 pid;
+ } uprobe_multi;
+ struct {
__u32 type; /* enum bpf_perf_event_type */
__u32 :32;
union {
@@ -6892,6 +6902,7 @@ enum {
BPF_TCP_LISTEN,
BPF_TCP_CLOSING, /* Now a valid state */
BPF_TCP_NEW_SYN_RECV,
+ BPF_TCP_BOUND_INACTIVE,
BPF_TCP_MAX_STATES /* Leave at the end! */
};
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index f7fba0dc87e5..0787d561ace0 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1266,6 +1266,8 @@ struct ethtool_rxfh_indir {
* hardware hash key.
* @hfunc: Defines the current RSS hash function used by HW (or to be set to).
* Valid values are one of the %ETH_RSS_HASH_*.
+ * @input_xfrm: Defines how the input data is transformed. Valid values are one
+ * of %RXH_XFRM_*.
* @rsvd8: Reserved for future use; see the note on reserved space.
* @rsvd32: Reserved for future use; see the note on reserved space.
* @rss_config: RX ring/queue index for each hash value i.e., indirection table
@@ -1285,7 +1287,8 @@ struct ethtool_rxfh {
__u32 indir_size;
__u32 key_size;
__u8 hfunc;
- __u8 rsvd8[3];
+ __u8 input_xfrm;
+ __u8 rsvd8[2];
__u32 rsvd32;
__u32 rss_config[];
};
@@ -1992,6 +1995,14 @@ static inline int ethtool_validate_duplex(__u8 duplex)
#define WOL_MODE_COUNT 8
+/* RSS hash function data
+ * XOR the corresponding source and destination fields of each specified
+ * protocol. Both copies of the XOR'ed fields are fed into the RSS and RXHASH
+ * calculation. Note that this XORing reduces the input set entropy and could
+ * be exploited to reduce the RSS queue spread.
+ */
+#define RXH_XFRM_SYM_XOR (1 << 0)
+
/* L2-L4 network traffic flow types */
#define TCP_V4_FLOW 0x01 /* hash or spec (tcp_ip4_spec) */
#define UDP_V4_FLOW 0x02 /* hash or spec (udp_ip4_spec) */
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 73e2c10dc2cc..3f89074aa06c 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -908,6 +908,7 @@ enum {
ETHTOOL_A_RSS_HFUNC, /* u32 */
ETHTOOL_A_RSS_INDIR, /* binary */
ETHTOOL_A_RSS_HKEY, /* binary */
+ ETHTOOL_A_RSS_INPUT_XFRM, /* u32 */
__ETHTOOL_A_RSS_CNT,
ETHTOOL_A_RSS_MAX = (__ETHTOOL_A_RSS_CNT - 1),
diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h
index 6c80f96049bd..282e90aeb163 100644
--- a/include/uapi/linux/fcntl.h
+++ b/include/uapi/linux/fcntl.h
@@ -116,5 +116,8 @@
#define AT_HANDLE_FID AT_REMOVEDIR /* file handle is needed to
compare object identity and may not
be usable to open_by_handle_at(2) */
+#if defined(__KERNEL__)
+#define AT_GETATTR_NOSEC 0x80000000
+#endif
#endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index db92a7202b34..e7418d15fe39 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -209,7 +209,7 @@
* - add FUSE_HAS_EXPIRE_ONLY
*
* 7.39
- * - add FUSE_DIRECT_IO_RELAX
+ * - add FUSE_DIRECT_IO_ALLOW_MMAP
* - add FUSE_STATX and related structures
*/
@@ -409,8 +409,7 @@ struct fuse_file_lock {
* FUSE_CREATE_SUPP_GROUP: add supplementary group info to create, mkdir,
* symlink and mknod (single group that matches parent)
* FUSE_HAS_EXPIRE_ONLY: kernel supports expiry-only entry invalidation
- * FUSE_DIRECT_IO_RELAX: relax restrictions in FOPEN_DIRECT_IO mode, for now
- * allow shared mmap
+ * FUSE_DIRECT_IO_ALLOW_MMAP: allow shared mmap in FOPEN_DIRECT_IO mode.
*/
#define FUSE_ASYNC_READ (1 << 0)
#define FUSE_POSIX_LOCKS (1 << 1)
@@ -449,7 +448,10 @@ struct fuse_file_lock {
#define FUSE_HAS_INODE_DAX (1ULL << 33)
#define FUSE_CREATE_SUPP_GROUP (1ULL << 34)
#define FUSE_HAS_EXPIRE_ONLY (1ULL << 35)
-#define FUSE_DIRECT_IO_RELAX (1ULL << 36)
+#define FUSE_DIRECT_IO_ALLOW_MMAP (1ULL << 36)
+
+/* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */
+#define FUSE_DIRECT_IO_RELAX FUSE_DIRECT_IO_ALLOW_MMAP
/**
* CUSE INIT request/reply flags
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 8181ef23a7a2..ab9bcff96e4d 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -461,6 +461,286 @@ enum in6_addr_gen_mode {
/* Bridge section */
+/**
+ * DOC: Bridge enum definition
+ *
+ * Please *note* that the timer values in the following section are expected
+ * in clock_t format, which is seconds multiplied by USER_HZ (generally
+ * defined as 100).
+ *
+ * @IFLA_BR_FORWARD_DELAY
+ * The bridge forwarding delay is the time spent in LISTENING state
+ * (before moving to LEARNING) and in LEARNING state (before moving
+ * to FORWARDING). Only relevant if STP is enabled.
+ *
+ * The valid values are between (2 * USER_HZ) and (30 * USER_HZ).
+ * The default value is (15 * USER_HZ).
+ *
+ * @IFLA_BR_HELLO_TIME
+ * The time between hello packets sent by the bridge, when it is a root
+ * bridge or a designated bridge. Only relevant if STP is enabled.
+ *
+ * The valid values are between (1 * USER_HZ) and (10 * USER_HZ).
+ * The default value is (2 * USER_HZ).
+ *
+ * @IFLA_BR_MAX_AGE
+ * The hello packet timeout is the time until another bridge in the
+ * spanning tree is assumed to be dead, after reception of its last hello
+ * message. Only relevant if STP is enabled.
+ *
+ * The valid values are between (6 * USER_HZ) and (40 * USER_HZ).
+ * The default value is (20 * USER_HZ).
+ *
+ * @IFLA_BR_AGEING_TIME
+ * Configure the bridge's FDB entries aging time. It is the time a MAC
+ * address will be kept in the FDB after a packet has been received from
+ * that address. After this time has passed, entries are cleaned up.
+ * Allow values outside the 802.1 standard specification for special cases:
+ *
+ * * 0 - entry never ages (all permanent)
+ * * 1 - entry disappears (no persistence)
+ *
+ * The default value is (300 * USER_HZ).
+ *
+ * @IFLA_BR_STP_STATE
+ * Turn spanning tree protocol on (*IFLA_BR_STP_STATE* > 0) or off
+ * (*IFLA_BR_STP_STATE* == 0) for this bridge.
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_PRIORITY
+ * Set this bridge's spanning tree priority, used during STP root bridge
+ * election.
+ *
+ * The valid values are between 0 and 65535.
+ *
+ * @IFLA_BR_VLAN_FILTERING
+ * Turn VLAN filtering on (*IFLA_BR_VLAN_FILTERING* > 0) or off
+ * (*IFLA_BR_VLAN_FILTERING* == 0). When disabled, the bridge will not
+ * consider the VLAN tag when handling packets.
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_VLAN_PROTOCOL
+ * Set the protocol used for VLAN filtering.
+ *
+ * The valid values are 0x8100(802.1Q) or 0x88A8(802.1AD). The default value
+ * is 0x8100(802.1Q).
+ *
+ * @IFLA_BR_GROUP_FWD_MASK
+ * The group forwarding mask. This is the bitmask that is applied to
+ * decide whether to forward incoming frames destined to link-local
+ * addresses (of the form 01:80:C2:00:00:0X).
+ *
+ * The default value is 0, which means the bridge does not forward any
+ * link-local frames coming on this port.
+ *
+ * @IFLA_BR_ROOT_ID
+ * The bridge root id, read only.
+ *
+ * @IFLA_BR_BRIDGE_ID
+ * The bridge id, read only.
+ *
+ * @IFLA_BR_ROOT_PORT
+ * The bridge root port, read only.
+ *
+ * @IFLA_BR_ROOT_PATH_COST
+ * The bridge root path cost, read only.
+ *
+ * @IFLA_BR_TOPOLOGY_CHANGE
+ * The bridge topology change, read only.
+ *
+ * @IFLA_BR_TOPOLOGY_CHANGE_DETECTED
+ * The bridge topology change detected, read only.
+ *
+ * @IFLA_BR_HELLO_TIMER
+ * The bridge hello timer, read only.
+ *
+ * @IFLA_BR_TCN_TIMER
+ * The bridge tcn timer, read only.
+ *
+ * @IFLA_BR_TOPOLOGY_CHANGE_TIMER
+ * The bridge topology change timer, read only.
+ *
+ * @IFLA_BR_GC_TIMER
+ * The bridge gc timer, read only.
+ *
+ * @IFLA_BR_GROUP_ADDR
+ * Set the MAC address of the multicast group this bridge uses for STP.
+ * The address must be a link-local address in standard Ethernet MAC address
+ * format. It is an address of the form 01:80:C2:00:00:0X, with X in [0, 4..f].
+ *
+ * The default value is 0.
+ *
+ * @IFLA_BR_FDB_FLUSH
+ * Flush bridge's fdb dynamic entries.
+ *
+ * @IFLA_BR_MCAST_ROUTER
+ * Set bridge's multicast router if IGMP snooping is enabled.
+ * The valid values are:
+ *
+ * * 0 - disabled.
+ * * 1 - automatic (queried).
+ * * 2 - permanently enabled.
+ *
+ * The default value is 1.
+ *
+ * @IFLA_BR_MCAST_SNOOPING
+ * Turn multicast snooping on (*IFLA_BR_MCAST_SNOOPING* > 0) or off
+ * (*IFLA_BR_MCAST_SNOOPING* == 0).
+ *
+ * The default value is 1.
+ *
+ * @IFLA_BR_MCAST_QUERY_USE_IFADDR
+ * If enabled use the bridge's own IP address as source address for IGMP
+ * queries (*IFLA_BR_MCAST_QUERY_USE_IFADDR* > 0) or the default of 0.0.0.0
+ * (*IFLA_BR_MCAST_QUERY_USE_IFADDR* == 0).
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_QUERIER
+ * Enable (*IFLA_BR_MULTICAST_QUERIER* > 0) or disable
+ * (*IFLA_BR_MULTICAST_QUERIER* == 0) IGMP querier, ie sending of multicast
+ * queries by the bridge.
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_HASH_ELASTICITY
+ * Set multicast database hash elasticity, It is the maximum chain length in
+ * the multicast hash table. This attribute is *deprecated* and the value
+ * is always 16.
+ *
+ * @IFLA_BR_MCAST_HASH_MAX
+ * Set maximum size of the multicast hash table
+ *
+ * The default value is 4096, the value must be a power of 2.
+ *
+ * @IFLA_BR_MCAST_LAST_MEMBER_CNT
+ * The Last Member Query Count is the number of Group-Specific Queries
+ * sent before the router assumes there are no local members. The Last
+ * Member Query Count is also the number of Group-and-Source-Specific
+ * Queries sent before the router assumes there are no listeners for a
+ * particular source.
+ *
+ * The default value is 2.
+ *
+ * @IFLA_BR_MCAST_STARTUP_QUERY_CNT
+ * The Startup Query Count is the number of Queries sent out on startup,
+ * separated by the Startup Query Interval.
+ *
+ * The default value is 2.
+ *
+ * @IFLA_BR_MCAST_LAST_MEMBER_INTVL
+ * The Last Member Query Interval is the Max Response Time inserted into
+ * Group-Specific Queries sent in response to Leave Group messages, and
+ * is also the amount of time between Group-Specific Query messages.
+ *
+ * The default value is (1 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_MEMBERSHIP_INTVL
+ * The interval after which the bridge will leave a group, if no membership
+ * reports for this group are received.
+ *
+ * The default value is (260 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_QUERIER_INTVL
+ * The interval between queries sent by other routers. if no queries are
+ * seen after this delay has passed, the bridge will start to send its own
+ * queries (as if *IFLA_BR_MCAST_QUERIER_INTVL* was enabled).
+ *
+ * The default value is (255 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_QUERY_INTVL
+ * The Query Interval is the interval between General Queries sent by
+ * the Querier.
+ *
+ * The default value is (125 * USER_HZ). The minimum value is (1 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_QUERY_RESPONSE_INTVL
+ * The Max Response Time used to calculate the Max Resp Code inserted
+ * into the periodic General Queries.
+ *
+ * The default value is (10 * USER_HZ).
+ *
+ * @IFLA_BR_MCAST_STARTUP_QUERY_INTVL
+ * The interval between queries in the startup phase.
+ *
+ * The default value is (125 * USER_HZ) / 4. The minimum value is (1 * USER_HZ).
+ *
+ * @IFLA_BR_NF_CALL_IPTABLES
+ * Enable (*NF_CALL_IPTABLES* > 0) or disable (*NF_CALL_IPTABLES* == 0)
+ * iptables hooks on the bridge.
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_NF_CALL_IP6TABLES
+ * Enable (*NF_CALL_IP6TABLES* > 0) or disable (*NF_CALL_IP6TABLES* == 0)
+ * ip6tables hooks on the bridge.
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_NF_CALL_ARPTABLES
+ * Enable (*NF_CALL_ARPTABLES* > 0) or disable (*NF_CALL_ARPTABLES* == 0)
+ * arptables hooks on the bridge.
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_VLAN_DEFAULT_PVID
+ * VLAN ID applied to untagged and priority-tagged incoming packets.
+ *
+ * The default value is 1. Setting to the special value 0 makes all ports of
+ * this bridge not have a PVID by default, which means that they will
+ * not accept VLAN-untagged traffic.
+ *
+ * @IFLA_BR_PAD
+ * Bridge attribute padding type for netlink message.
+ *
+ * @IFLA_BR_VLAN_STATS_ENABLED
+ * Enable (*IFLA_BR_VLAN_STATS_ENABLED* == 1) or disable
+ * (*IFLA_BR_VLAN_STATS_ENABLED* == 0) per-VLAN stats accounting.
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_STATS_ENABLED
+ * Enable (*IFLA_BR_MCAST_STATS_ENABLED* > 0) or disable
+ * (*IFLA_BR_MCAST_STATS_ENABLED* == 0) multicast (IGMP/MLD) stats
+ * accounting.
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MCAST_IGMP_VERSION
+ * Set the IGMP version.
+ *
+ * The valid values are 2 and 3. The default value is 2.
+ *
+ * @IFLA_BR_MCAST_MLD_VERSION
+ * Set the MLD version.
+ *
+ * The valid values are 1 and 2. The default value is 1.
+ *
+ * @IFLA_BR_VLAN_STATS_PER_PORT
+ * Enable (*IFLA_BR_VLAN_STATS_PER_PORT* == 1) or disable
+ * (*IFLA_BR_VLAN_STATS_PER_PORT* == 0) per-VLAN per-port stats accounting.
+ * Can be changed only when there are no port VLANs configured.
+ *
+ * The default value is 0 (disabled).
+ *
+ * @IFLA_BR_MULTI_BOOLOPT
+ * The multi_boolopt is used to control new boolean options to avoid adding
+ * new netlink attributes. You can look at ``enum br_boolopt_id`` for those
+ * options.
+ *
+ * @IFLA_BR_MCAST_QUERIER_STATE
+ * Bridge mcast querier states, read only.
+ *
+ * @IFLA_BR_FDB_N_LEARNED
+ * The number of dynamically learned FDB entries for the current bridge,
+ * read only.
+ *
+ * @IFLA_BR_FDB_MAX_LEARNED
+ * Set the number of max dynamically learned FDB entries for the current
+ * bridge.
+ */
enum {
IFLA_BR_UNSPEC,
IFLA_BR_FORWARD_DELAY,
@@ -522,11 +802,252 @@ struct ifla_bridge_id {
__u8 addr[6]; /* ETH_ALEN */
};
+/**
+ * DOC: Bridge mode enum definition
+ *
+ * @BRIDGE_MODE_HAIRPIN
+ * Controls whether traffic may be sent back out of the port on which it
+ * was received. This option is also called reflective relay mode, and is
+ * used to support basic VEPA (Virtual Ethernet Port Aggregator)
+ * capabilities. By default, this flag is turned off and the bridge will
+ * not forward traffic back out of the receiving port.
+ */
enum {
BRIDGE_MODE_UNSPEC,
BRIDGE_MODE_HAIRPIN,
};
+/**
+ * DOC: Bridge port enum definition
+ *
+ * @IFLA_BRPORT_STATE
+ * The operation state of the port. Here are the valid values.
+ *
+ * * 0 - port is in STP *DISABLED* state. Make this port completely
+ * inactive for STP. This is also called BPDU filter and could be used
+ * to disable STP on an untrusted port, like a leaf virtual device.
+ * The traffic forwarding is also stopped on this port.
+ * * 1 - port is in STP *LISTENING* state. Only valid if STP is enabled
+ * on the bridge. In this state the port listens for STP BPDUs and
+ * drops all other traffic frames.
+ * * 2 - port is in STP *LEARNING* state. Only valid if STP is enabled on
+ * the bridge. In this state the port will accept traffic only for the
+ * purpose of updating MAC address tables.
+ * * 3 - port is in STP *FORWARDING* state. Port is fully active.
+ * * 4 - port is in STP *BLOCKING* state. Only valid if STP is enabled on
+ * the bridge. This state is used during the STP election process.
+ * In this state, port will only process STP BPDUs.
+ *
+ * @IFLA_BRPORT_PRIORITY
+ * The STP port priority. The valid values are between 0 and 255.
+ *
+ * @IFLA_BRPORT_COST
+ * The STP path cost of the port. The valid values are between 1 and 65535.
+ *
+ * @IFLA_BRPORT_MODE
+ * Set the bridge port mode. See *BRIDGE_MODE_HAIRPIN* for more details.
+ *
+ * @IFLA_BRPORT_GUARD
+ * Controls whether STP BPDUs will be processed by the bridge port. By
+ * default, the flag is turned off to allow BPDU processing. Turning this
+ * flag on will disable the bridge port if a STP BPDU packet is received.
+ *
+ * If the bridge has Spanning Tree enabled, hostile devices on the network
+ * may send BPDU on a port and cause network failure. Setting *guard on*
+ * will detect and stop this by disabling the port. The port will be
+ * restarted if the link is brought down, or removed and reattached.
+ *
+ * @IFLA_BRPORT_PROTECT
+ * Controls whether a given port is allowed to become a root port or not.
+ * Only used when STP is enabled on the bridge. By default the flag is off.
+ *
+ * This feature is also called root port guard. If BPDU is received from a
+ * leaf (edge) port, it should not be elected as root port. This could
+ * be used if using STP on a bridge and the downstream bridges are not fully
+ * trusted; this prevents a hostile guest from rerouting traffic.
+ *
+ * @IFLA_BRPORT_FAST_LEAVE
+ * This flag allows the bridge to immediately stop multicast traffic
+ * forwarding on a port that receives an IGMP Leave message. It is only used
+ * when IGMP snooping is enabled on the bridge. By default the flag is off.
+ *
+ * @IFLA_BRPORT_LEARNING
+ * Controls whether a given port will learn *source* MAC addresses from
+ * received traffic or not. Also controls whether dynamic FDB entries
+ * (which can also be added by software) will be refreshed by incoming
+ * traffic. By default this flag is on.
+ *
+ * @IFLA_BRPORT_UNICAST_FLOOD
+ * Controls whether unicast traffic for which there is no FDB entry will
+ * be flooded towards this port. By default this flag is on.
+ *
+ * @IFLA_BRPORT_PROXYARP
+ * Enable proxy ARP on this port.
+ *
+ * @IFLA_BRPORT_LEARNING_SYNC
+ * Controls whether a given port will sync MAC addresses learned on device
+ * port to bridge FDB.
+ *
+ * @IFLA_BRPORT_PROXYARP_WIFI
+ * Enable proxy ARP on this port which meets extended requirements by
+ * IEEE 802.11 and Hotspot 2.0 specifications.
+ *
+ * @IFLA_BRPORT_ROOT_ID
+ *
+ * @IFLA_BRPORT_BRIDGE_ID
+ *
+ * @IFLA_BRPORT_DESIGNATED_PORT
+ *
+ * @IFLA_BRPORT_DESIGNATED_COST
+ *
+ * @IFLA_BRPORT_ID
+ *
+ * @IFLA_BRPORT_NO
+ *
+ * @IFLA_BRPORT_TOPOLOGY_CHANGE_ACK
+ *
+ * @IFLA_BRPORT_CONFIG_PENDING
+ *
+ * @IFLA_BRPORT_MESSAGE_AGE_TIMER
+ *
+ * @IFLA_BRPORT_FORWARD_DELAY_TIMER
+ *
+ * @IFLA_BRPORT_HOLD_TIMER
+ *
+ * @IFLA_BRPORT_FLUSH
+ * Flush bridge ports' fdb dynamic entries.
+ *
+ * @IFLA_BRPORT_MULTICAST_ROUTER
+ * Configure the port's multicast router presence. A port with
+ * a multicast router will receive all multicast traffic.
+ * The valid values are:
+ *
+ * * 0 disable multicast routers on this port
+ * * 1 let the system detect the presence of routers (default)
+ * * 2 permanently enable multicast traffic forwarding on this port
+ * * 3 enable multicast routers temporarily on this port, not depending
+ * on incoming queries.
+ *
+ * @IFLA_BRPORT_PAD
+ *
+ * @IFLA_BRPORT_MCAST_FLOOD
+ * Controls whether a given port will flood multicast traffic for which
+ * there is no MDB entry. By default this flag is on.
+ *
+ * @IFLA_BRPORT_MCAST_TO_UCAST
+ * Controls whether a given port will replicate packets using unicast
+ * instead of multicast. By default this flag is off.
+ *
+ * This is done by copying the packet per host and changing the multicast
+ * destination MAC to a unicast one accordingly.
+ *
+ * *mcast_to_unicast* works on top of the multicast snooping feature of the
+ * bridge. Which means unicast copies are only delivered to hosts which
+ * are interested in unicast and signaled this via IGMP/MLD reports previously.
+ *
+ * This feature is intended for interface types which have a more reliable
+ * and/or efficient way to deliver unicast packets than broadcast ones
+ * (e.g. WiFi).
+ *
+ * However, it should only be enabled on interfaces where no IGMPv2/MLDv1
+ * report suppression takes place. IGMP/MLD report suppression issue is
+ * usually overcome by the network daemon (supplicant) enabling AP isolation
+ * and by that separating all STAs.
+ *
+ * Delivery of STA-to-STA IP multicast is made possible again by enabling
+ * and utilizing the bridge hairpin mode, which considers the incoming port
+ * as a potential outgoing port, too (see *BRIDGE_MODE_HAIRPIN* option).
+ * Hairpin mode is performed after multicast snooping, therefore leading
+ * to only deliver reports to STAs running a multicast router.
+ *
+ * @IFLA_BRPORT_VLAN_TUNNEL
+ * Controls whether vlan to tunnel mapping is enabled on the port.
+ * By default this flag is off.
+ *
+ * @IFLA_BRPORT_BCAST_FLOOD
+ * Controls flooding of broadcast traffic on the given port. By default
+ * this flag is on.
+ *
+ * @IFLA_BRPORT_GROUP_FWD_MASK
+ * Set the group forward mask. This is a bitmask that is applied to
+ * decide whether to forward incoming frames destined to link-local
+ * addresses. The addresses of the form are 01:80:C2:00:00:0X (defaults
+ * to 0, which means the bridge does not forward any link-local frames
+ * coming on this port).
+ *
+ * @IFLA_BRPORT_NEIGH_SUPPRESS
+ * Controls whether neighbor discovery (arp and nd) proxy and suppression
+ * is enabled on the port. By default this flag is off.
+ *
+ * @IFLA_BRPORT_ISOLATED
+ * Controls whether a given port will be isolated, which means it will be
+ * able to communicate with non-isolated ports only. By default this
+ * flag is off.
+ *
+ * @IFLA_BRPORT_BACKUP_PORT
+ * Set a backup port. If the port loses carrier all traffic will be
+ * redirected to the configured backup port. Set the value to 0 to disable
+ * it.
+ *
+ * @IFLA_BRPORT_MRP_RING_OPEN
+ *
+ * @IFLA_BRPORT_MRP_IN_OPEN
+ *
+ * @IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT
+ * The number of per-port EHT hosts limit. The default value is 512.
+ * Setting to 0 is not allowed.
+ *
+ * @IFLA_BRPORT_MCAST_EHT_HOSTS_CNT
+ * The current number of tracked hosts, read only.
+ *
+ * @IFLA_BRPORT_LOCKED
+ * Controls whether a port will be locked, meaning that hosts behind the
+ * port will not be able to communicate through the port unless an FDB
+ * entry with the unit's MAC address is in the FDB. The common use case is
+ * that hosts are allowed access through authentication with the IEEE 802.1X
+ * protocol or based on whitelists. By default this flag is off.
+ *
+ * Please note that secure 802.1X deployments should always use the
+ * *BR_BOOLOPT_NO_LL_LEARN* flag, to not permit the bridge to populate its
+ * FDB based on link-local (EAPOL) traffic received on the port.
+ *
+ * @IFLA_BRPORT_MAB
+ * Controls whether a port will use MAC Authentication Bypass (MAB), a
+ * technique through which select MAC addresses may be allowed on a locked
+ * port, without using 802.1X authentication. Packets with an unknown source
+ * MAC address generates a "locked" FDB entry on the incoming bridge port.
+ * The common use case is for user space to react to these bridge FDB
+ * notifications and optionally replace the locked FDB entry with a normal
+ * one, allowing traffic to pass for whitelisted MAC addresses.
+ *
+ * Setting this flag also requires *IFLA_BRPORT_LOCKED* and
+ * *IFLA_BRPORT_LEARNING*. *IFLA_BRPORT_LOCKED* ensures that unauthorized
+ * data packets are dropped, and *IFLA_BRPORT_LEARNING* allows the dynamic
+ * FDB entries installed by user space (as replacements for the locked FDB
+ * entries) to be refreshed and/or aged out.
+ *
+ * @IFLA_BRPORT_MCAST_N_GROUPS
+ *
+ * @IFLA_BRPORT_MCAST_MAX_GROUPS
+ * Sets the maximum number of MDB entries that can be registered for a
+ * given port. Attempts to register more MDB entries at the port than this
+ * limit allows will be rejected, whether they are done through netlink
+ * (e.g. the bridge tool), or IGMP or MLD membership reports. Setting a
+ * limit of 0 disables the limit. The default value is 0.
+ *
+ * @IFLA_BRPORT_NEIGH_VLAN_SUPPRESS
+ * Controls whether neighbor discovery (arp and nd) proxy and suppression is
+ * enabled for a given port. By default this flag is off.
+ *
+ * Note that this option only takes effect when *IFLA_BRPORT_NEIGH_SUPPRESS*
+ * is enabled for a given port.
+ *
+ * @IFLA_BRPORT_BACKUP_NHID
+ * The FDB nexthop object ID to attach to packets being redirected to a
+ * backup port that has VLAN tunnel mapping enabled (via the
+ * *IFLA_BRPORT_VLAN_TUNNEL* option). Setting a value of 0 (default) has
+ * the effect of not attaching any ID.
+ */
enum {
IFLA_BRPORT_UNSPEC,
IFLA_BRPORT_STATE, /* Spanning tree state */
diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index 8d48863472b9..d31698410410 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -33,7 +33,13 @@
#define XDP_USE_SG (1 << 4)
/* Flags for xsk_umem_config flags */
-#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
+#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
+
+/* Force checksum calculation in software. Can be used for testing or
+ * working around potential HW issues. This option causes performance
+ * degradation and only works in XDP_COPY mode.
+ */
+#define XDP_UMEM_TX_SW_CSUM (1 << 1)
struct sockaddr_xdp {
__u16 sxdp_family;
@@ -76,6 +82,7 @@ struct xdp_umem_reg {
__u32 chunk_size;
__u32 headroom;
__u32 flags;
+ __u32 tx_metadata_len;
};
struct xdp_statistics {
@@ -105,6 +112,41 @@ struct xdp_options {
#define XSK_UNALIGNED_BUF_ADDR_MASK \
((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1)
+/* Request transmit timestamp. Upon completion, put it into tx_timestamp
+ * field of struct xsk_tx_metadata.
+ */
+#define XDP_TXMD_FLAGS_TIMESTAMP (1 << 0)
+
+/* Request transmit checksum offload. Checksum start position and offset
+ * are communicated via csum_start and csum_offset fields of struct
+ * xsk_tx_metadata.
+ */
+#define XDP_TXMD_FLAGS_CHECKSUM (1 << 1)
+
+/* AF_XDP offloads request. 'request' union member is consumed by the driver
+ * when the packet is being transmitted. 'completion' union member is
+ * filled by the driver when the transmit completion arrives.
+ */
+struct xsk_tx_metadata {
+ __u64 flags;
+
+ union {
+ struct {
+ /* XDP_TXMD_FLAGS_CHECKSUM */
+
+ /* Offset from desc->addr where checksumming should start. */
+ __u16 csum_start;
+ /* Offset from csum_start where checksum should be stored. */
+ __u16 csum_offset;
+ } request;
+
+ struct {
+ /* XDP_TXMD_FLAGS_TIMESTAMP */
+ __u64 tx_timestamp;
+ } completion;
+ };
+};
+
/* Rx/Tx descriptor */
struct xdp_desc {
__u64 addr;
@@ -121,4 +163,7 @@ struct xdp_desc {
*/
#define XDP_PKT_CONTD (1 << 0)
+/* TX packet carries valid metadata. */
+#define XDP_TX_METADATA (1 << 1)
+
#endif /* _LINUX_IF_XDP_H */
diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h
index b5d11aece408..50589e5dd6a3 100644
--- a/include/uapi/linux/mptcp_pm.h
+++ b/include/uapi/linux/mptcp_pm.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
/* Do not edit directly, auto-generated from: */
-/* Documentation/netlink/specs/mptcp.yaml */
+/* Documentation/netlink/specs/mptcp_pm.yaml */
/* YNL-GEN uapi header */
#ifndef _UAPI_LINUX_MPTCP_PM_H
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 2b37233e00c0..424c5e28f495 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -48,9 +48,23 @@ enum netdev_xdp_act {
enum netdev_xdp_rx_metadata {
NETDEV_XDP_RX_METADATA_TIMESTAMP = 1,
NETDEV_XDP_RX_METADATA_HASH = 2,
+};
- /* private: */
- NETDEV_XDP_RX_METADATA_MASK = 3,
+/**
+ * enum netdev_xsk_flags
+ * @NETDEV_XSK_FLAGS_TX_TIMESTAMP: HW timestamping egress packets is supported
+ * by the driver.
+ * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the
+ * driver.
+ */
+enum netdev_xsk_flags {
+ NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1,
+ NETDEV_XSK_FLAGS_TX_CHECKSUM = 2,
+};
+
+enum netdev_queue_type {
+ NETDEV_QUEUE_TYPE_RX,
+ NETDEV_QUEUE_TYPE_TX,
};
enum {
@@ -59,6 +73,7 @@ enum {
NETDEV_A_DEV_XDP_FEATURES,
NETDEV_A_DEV_XDP_ZC_MAX_SEGS,
NETDEV_A_DEV_XDP_RX_METADATA_FEATURES,
+ NETDEV_A_DEV_XSK_FEATURES,
__NETDEV_A_DEV_MAX,
NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
@@ -95,6 +110,26 @@ enum {
};
enum {
+ NETDEV_A_NAPI_IFINDEX = 1,
+ NETDEV_A_NAPI_ID,
+ NETDEV_A_NAPI_IRQ,
+ NETDEV_A_NAPI_PID,
+
+ __NETDEV_A_NAPI_MAX,
+ NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
+};
+
+enum {
+ NETDEV_A_QUEUE_ID = 1,
+ NETDEV_A_QUEUE_IFINDEX,
+ NETDEV_A_QUEUE_TYPE,
+ NETDEV_A_QUEUE_NAPI_ID,
+
+ __NETDEV_A_QUEUE_MAX,
+ NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
+};
+
+enum {
NETDEV_CMD_DEV_GET = 1,
NETDEV_CMD_DEV_ADD_NTF,
NETDEV_CMD_DEV_DEL_NTF,
@@ -104,6 +139,8 @@ enum {
NETDEV_CMD_PAGE_POOL_DEL_NTF,
NETDEV_CMD_PAGE_POOL_CHANGE_NTF,
NETDEV_CMD_PAGE_POOL_STATS_GET,
+ NETDEV_CMD_QUEUE_GET,
+ NETDEV_CMD_NAPI_GET,
__NETDEV_CMD_MAX,
NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h
index 5c6c4269f7ef..2ec6f35cda32 100644
--- a/include/uapi/linux/stddef.h
+++ b/include/uapi/linux/stddef.h
@@ -27,7 +27,7 @@
union { \
struct { MEMBERS } ATTRS; \
struct TAG { MEMBERS } ATTRS NAME; \
- }
+ } ATTRS
#ifdef __cplusplus
/* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */
diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h
index 4a195b68f28f..b383c2fe0cf3 100644
--- a/include/uapi/linux/v4l2-subdev.h
+++ b/include/uapi/linux/v4l2-subdev.h
@@ -239,7 +239,7 @@ struct v4l2_subdev_routing {
* set (which is the default), the 'stream' fields will be forced to 0 by the
* kernel.
*/
- #define V4L2_SUBDEV_CLIENT_CAP_STREAMS (1U << 0)
+ #define V4L2_SUBDEV_CLIENT_CAP_STREAMS (1ULL << 0)
/**
* struct v4l2_subdev_client_capability - Capabilities of the client accessing