aboutsummaryrefslogtreecommitdiffstats
path: root/arch/arm/kernel/psci.c
blob: f73891b6b7300dc67e353a8694a035e9a212c2d7 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
/*
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * Copyright (C) 2012 ARM Limited
 *
 * Author: Will Deacon <will.deacon@arm.com>
 */

#define pr_fmt(fmt) "psci: " fmt

#include <linux/init.h>
#include <linux/of.h>
#include <linux/reboot.h>
#include <linux/pm.h>
#include <uapi/linux/psci.h>

#include <asm/compiler.h>
#include <asm/errno.h>
#include <asm/opcodes-sec.h>
#include <asm/opcodes-virt.h>
#include <asm/psci.h>
#include <asm/system_misc.h>

struct psci_operations psci_ops;

static int (*invoke_psci_fn)(u32, u32, u32, u32);
typedef int (*psci_initcall_t)(const struct device_node *);

enum psci_function {
	PSCI_FN_CPU_SUSPEND,
	PSCI_FN_CPU_ON,
	PSCI_FN_CPU_OFF,
	PSCI_FN_MIGRATE,
	PSCI_FN_AFFINITY_INFO,
	PSCI_FN_MIGRATE_INFO_TYPE,
	PSCI_FN_MAX,
};

static u32 psci_function_id[PSCI_FN_MAX];

static int psci_to_linux_errno(int errno)
{
	switch (errno) {
	case PSCI_RET_SUCCESS:
		return 0;
	case PSCI_RET_NOT_SUPPORTED:
		return -EOPNOTSUPP;
	case PSCI_RET_INVALID_PARAMS:
		return -EINVAL;
	case PSCI_RET_DENIED:
		return -EPERM;
	};

	return -EINVAL;
}

static u32 psci_power_state_pack(struct psci_power_state state)
{
	return ((state.id << PSCI_0_2_POWER_STATE_ID_SHIFT)
			& PSCI_0_2_POWER_STATE_ID_MASK) |
		((state.type << PSCI_0_2_POWER_STATE_TYPE_SHIFT)
		 & PSCI_0_2_POWER_STATE_TYPE_MASK) |
		((state.affinity_level << PSCI_0_2_POWER_STATE_AFFL_SHIFT)
		 & PSCI_0_2_POWER_STATE_AFFL_MASK);
}

/*
 * The following two functions are invoked via the invoke_psci_fn pointer
 * and will not be inlined, allowing us to piggyback on the AAPCS.
 */
static noinline int __invoke_psci_fn_hvc(u32 function_id, u32 arg0, u32 arg1,
					 u32 arg2)
{
	asm volatile(
			__asmeq("%0", "r0")
			__asmeq("%1", "r1")
			__asmeq("%2", "r2")
			__asmeq("%3", "r3")
			__HVC(0)
		: "+r" (function_id)
		: "r" (arg0), "r" (arg1), "r" (arg2));

	return function_id;
}

static noinline int __invoke_psci_fn_smc(u32 function_id, u32 arg0, u32 arg1,
					 u32 arg2)
{
	asm volatile(
			__asmeq("%0", "r0")
			__asmeq("%1", "r1")
			__asmeq("%2", "r2")
			__asmeq("%3", "r3")
			__SMC(0)
		: "+r" (function_id)
		: "r" (arg0), "r" (arg1), "r" (arg2));

	return function_id;
}

static int psci_get_version(void)
{
	int err;

	err = invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0);
	return err;
}

static int psci_cpu_suspend(struct psci_power_state state,
			    unsigned long entry_point)
{
	int err;
	u32 fn, power_state;

	fn = psci_function_id[PSCI_FN_CPU_SUSPEND];
	power_state = psci_power_state_pack(state);
	err = invoke_psci_fn(fn, power_state, entry_point, 0);
	return psci_to_linux_errno(err);
}

static int psci_cpu_off(struct psci_power_state state)
{
	int err;
	u32 fn, power_state;

	fn = psci_function_id[PSCI_FN_CPU_OFF];
	power_state = psci_power_state_pack(state);
	err = invoke_psci_fn(fn, power_state, 0, 0);
	return psci_to_linux_errno(err);
}

static int psci_cpu_on(unsigned long cpuid, unsigned long entry_point)
{
	int err;
	u32 fn;

	fn = psci_function_id[PSCI_FN_CPU_ON];
	err = invoke_psci_fn(fn, cpuid, entry_point, 0);
	return psci_to_linux_errno(err);
}

static int psci_migrate(unsigned long cpuid)
{
	int err;
	u32 fn;

	fn = psci_function_id[PSCI_FN_MIGRATE];
	err = invoke_psci_fn(fn, cpuid, 0, 0);
	return psci_to_linux_errno(err);
}

static int psci_affinity_info(unsigned long target_affinity,
		unsigned long lowest_affinity_level)
{
	int err;
	u32 fn;

	fn = psci_function_id[PSCI_FN_AFFINITY_INFO];
	err = invoke_psci_fn(fn, target_affinity, lowest_affinity_level, 0);
	return err;
}

static int psci_migrate_info_type(void)
{
	int err;
	u32 fn;

	fn = psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE];
	err = invoke_psci_fn(fn, 0, 0, 0);
	return err;
}

static int get_set_conduit_method(struct device_node *np)
{
	const char *method;

	pr_info("probing for conduit method from DT.\n");

	if (of_property_read_string(np, "method", &method)) {
		pr_warn("missing \"method\" property\n");
		return -ENXIO;
	}

	if (!strcmp("hvc", method)) {
		invoke_psci_fn = __invoke_psci_fn_hvc;
	} else if (!strcmp("smc", method)) {
		invoke_psci_fn = __invoke_psci_fn_smc;
	} else {
		pr_warn("invalid \"method\" property: %s\n", method);
		return -EINVAL;
	}
	return 0;
}

static void psci_sys_reset(enum reboot_mode reboot_mode, const char *cmd)
{
	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0);
}

static void psci_sys_poweroff(void)
{
	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0);
}

/*
 * PSCI Function IDs for v0.2+ are well defined so use
 * standard values.
 */
static int psci_0_2_init(struct device_node *np)
{
	int err, ver;

	err = get_set_conduit_method(np);

	if (err)
		goto out_put_node;

	ver = psci_get_version();

	if (ver == PSCI_RET_NOT_SUPPORTED) {
		/* PSCI v0.2 mandates implementation of PSCI_ID_VERSION. */
		pr_err("PSCI firmware does not comply with the v0.2 spec.\n");
		err = -EOPNOTSUPP;
		goto out_put_node;
	} else {
		pr_info("PSCIv%d.%d detected in firmware.\n",
				PSCI_VERSION_MAJOR(ver),
				PSCI_VERSION_MINOR(ver));

		if (PSCI_VERSION_MAJOR(ver) == 0 &&
				PSCI_VERSION_MINOR(ver) < 2) {
			err = -EINVAL;
			pr_err("Conflicting PSCI version detected.\n");
			goto out_put_node;
		}
	}

	pr_info("Using standard PSCI v0.2 function IDs\n");
	psci_function_id[PSCI_FN_CPU_SUSPEND] = PSCI_0_2_FN_CPU_SUSPEND;
	psci_ops.cpu_suspend = psci_cpu_suspend;

	psci_function_id[PSCI_FN_CPU_OFF] = PSCI_0_2_FN_CPU_OFF;
	psci_ops.cpu_off = psci_cpu_off;

	psci_function_id[PSCI_FN_CPU_ON] = PSCI_0_2_FN_CPU_ON;
	psci_ops.cpu_on = psci_cpu_on;

	psci_function_id[PSCI_FN_MIGRATE] = PSCI_0_2_FN_MIGRATE;
	psci_ops.migrate = psci_migrate;

	psci_function_id[PSCI_FN_AFFINITY_INFO] = PSCI_0_2_FN_AFFINITY_INFO;
	psci_ops.affinity_info = psci_affinity_info;

	psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE] =
		PSCI_0_2_FN_MIGRATE_INFO_TYPE;
	psci_ops.migrate_info_type = psci_migrate_info_type;

	arm_pm_restart = psci_sys_reset;

	pm_power_off = psci_sys_poweroff;

out_put_node:
	of_node_put(np);
	return err;
}

/*
 * PSCI < v0.2 get PSCI Function IDs via DT.
 */
static int psci_0_1_init(struct device_node *np)
{
	u32 id;
	int err;

	err = get_set_conduit_method(np);

	if (err)
		goto out_put_node;

	pr_info("Using PSCI v0.1 Function IDs from DT\n");

	if (!of_property_read_u32(np, "cpu_suspend", &id)) {
		psci_function_id[PSCI_FN_CPU_SUSPEND] = id;
		psci_ops.cpu_suspend = psci_cpu_suspend;
	}

	if (!of_property_read_u32(np, "cpu_off", &id)) {
		psci_function_id[PSCI_FN_CPU_OFF] = id;
		psci_ops.cpu_off = psci_cpu_off;
	}

	if (!of_property_read_u32(np, "cpu_on", &id)) {
		psci_function_id[PSCI_FN_CPU_ON] = id;
		psci_ops.cpu_on = psci_cpu_on;
	}

	if (!of_property_read_u32(np, "migrate", &id)) {
		psci_function_id[PSCI_FN_MIGRATE] = id;
		psci_ops.migrate = psci_migrate;
	}

out_put_node:
	of_node_put(np);
	return err;
}

static const struct of_device_id psci_of_match[] __initconst = {
	{ .compatible = "arm,psci", .data = psci_0_1_init},
	{ .compatible = "arm,psci-0.2", .data = psci_0_2_init},
	{},
};

int __init psci_init(void)
{
	struct device_node *np;
	const struct of_device_id *matched_np;
	psci_initcall_t init_fn;

	np = of_find_matching_node_and_match(NULL, psci_of_match, &matched_np);
	if (!np)
		return -ENODEV;

	init_fn = (psci_initcall_t)matched_np->data;
	return init_fn(np);
}
The associated channel * @core_txq: The networking core TX queue structure * @buffer: The software buffer ring * @tsoh_page: Array of pages of TSO header buffers * @txd: The hardware descriptor ring * @ptr_mask: The size of the ring minus 1. * @initialised: Has hardware queue been initialised? * @read_count: Current read pointer. * This is the number of buffers that have been removed from both rings. * @old_write_count: The value of @write_count when last checked. * This is here for performance reasons. The xmit path will * only get the up-to-date value of @write_count if this * variable indicates that the queue is empty. This is to * avoid cache-line ping-pong between the xmit path and the * completion path. * @insert_count: Current insert pointer * This is the number of buffers that have been added to the * software ring. * @write_count: Current write pointer * This is the number of buffers that have been added to the * hardware ring. * @old_read_count: The value of read_count when last checked. * This is here for performance reasons. The xmit path will * only get the up-to-date value of read_count if this * variable indicates that the queue is full. This is to * avoid cache-line ping-pong between the xmit path and the * completion path. * @tso_bursts: Number of times TSO xmit invoked by kernel * @tso_long_headers: Number of packets with headers too long for standard * blocks * @tso_packets: Number of packets via the TSO xmit path * @pushes: Number of times the TX push feature has been used * @empty_read_count: If the completion path has seen the queue as empty * and the transmission path has not yet checked this, the value of * @read_count bitwise-added to %EFX_EMPTY_COUNT_VALID; otherwise 0. */ struct efx_tx_queue { /* Members which don't change on the fast path */ struct efx_nic *efx ____cacheline_aligned_in_smp; unsigned queue; struct efx_channel *channel; struct netdev_queue *core_txq; struct efx_tx_buffer *buffer; struct efx_buffer *tsoh_page; struct efx_special_buffer txd; unsigned int ptr_mask; bool initialised; /* Members used mainly on the completion path */ unsigned int read_count ____cacheline_aligned_in_smp; unsigned int old_write_count; /* Members used only on the xmit path */ unsigned int insert_count ____cacheline_aligned_in_smp; unsigned int write_count; unsigned int old_read_count; unsigned int tso_bursts; unsigned int tso_long_headers; unsigned int tso_packets; unsigned int pushes; /* Members shared between paths and sometimes updated */ unsigned int empty_read_count ____cacheline_aligned_in_smp; #define EFX_EMPTY_COUNT_VALID 0x80000000 atomic_t flush_outstanding; }; /** * struct efx_rx_buffer - An Efx RX data buffer * @dma_addr: DMA base address of the buffer * @skb: The associated socket buffer. Valid iff !(@flags & %EFX_RX_BUF_PAGE). * Will be %NULL if the buffer slot is currently free. * @page: The associated page buffer. Valif iff @flags & %EFX_RX_BUF_PAGE. * Will be %NULL if the buffer slot is currently free. * @len: Buffer length, in bytes. * @flags: Flags for buffer and packet state. */ struct efx_rx_buffer { dma_addr_t dma_addr; union { struct sk_buff *skb; struct page *page; } u; unsigned int len; u16 flags; }; #define EFX_RX_BUF_PAGE 0x0001 #define EFX_RX_PKT_CSUMMED 0x0002 #define EFX_RX_PKT_DISCARD 0x0004 /** * struct efx_rx_page_state - Page-based rx buffer state * * Inserted at the start of every page allocated for receive buffers. * Used to facilitate sharing dma mappings between recycled rx buffers * and those passed up to the kernel. * * @refcnt: Number of struct efx_rx_buffer's referencing this page. * When refcnt falls to zero, the page is unmapped for dma * @dma_addr: The dma address of this page. */ struct efx_rx_page_state { unsigned refcnt; dma_addr_t dma_addr; unsigned int __pad[0] ____cacheline_aligned; }; /** * struct efx_rx_queue - An Efx RX queue * @efx: The associated Efx NIC * @core_index: Index of network core RX queue. Will be >= 0 iff this * is associated with a real RX queue. * @buffer: The software buffer ring * @rxd: The hardware descriptor ring * @ptr_mask: The size of the ring minus 1. * @enabled: Receive queue enabled indicator. * @flush_pending: Set when a RX flush is pending. Has the same lifetime as * @rxq_flush_pending. * @added_count: Number of buffers added to the receive queue. * @notified_count: Number of buffers given to NIC (<= @added_count). * @removed_count: Number of buffers removed from the receive queue. * @max_fill: RX descriptor maximum fill level (<= ring size) * @fast_fill_trigger: RX descriptor fill level that will trigger a fast fill * (<= @max_fill) * @min_fill: RX descriptor minimum non-zero fill level. * This records the minimum fill level observed when a ring * refill was triggered. * @alloc_page_count: RX allocation strategy counter. * @alloc_skb_count: RX allocation strategy counter. * @slow_fill: Timer used to defer efx_nic_generate_fill_event(). */ struct efx_rx_queue { struct efx_nic *efx; int core_index; struct efx_rx_buffer *buffer; struct efx_special_buffer rxd; unsigned int ptr_mask; bool enabled; bool flush_pending; int added_count; int notified_count; int removed_count; unsigned int max_fill; unsigned int fast_fill_trigger; unsigned int min_fill; unsigned int min_overfill; unsigned int alloc_page_count; unsigned int alloc_skb_count; struct timer_list slow_fill; unsigned int slow_fill_count; }; /** * struct efx_buffer - An Efx general-purpose buffer * @addr: host base address of the buffer * @dma_addr: DMA base address of the buffer * @len: Buffer length, in bytes * * The NIC uses these buffers for its interrupt status registers and * MAC stats dumps. */ struct efx_buffer { void *addr; dma_addr_t dma_addr; unsigned int len; }; enum efx_rx_alloc_method { RX_ALLOC_METHOD_AUTO = 0, RX_ALLOC_METHOD_SKB = 1, RX_ALLOC_METHOD_PAGE = 2, }; /** * struct efx_channel - An Efx channel * * A channel comprises an event queue, at least one TX queue, at least * one RX queue, and an associated tasklet for processing the event * queue. * * @efx: Associated Efx NIC * @channel: Channel instance number * @type: Channel type definition * @enabled: Channel enabled indicator * @irq: IRQ number (MSI and MSI-X only) * @irq_moderation: IRQ moderation value (in hardware ticks) * @napi_dev: Net device used with NAPI * @napi_str: NAPI control structure * @work_pending: Is work pending via NAPI? * @eventq: Event queue buffer * @eventq_mask: Event queue pointer mask * @eventq_read_ptr: Event queue read pointer * @event_test_cpu: Last CPU to handle interrupt or test event for this channel * @irq_count: Number of IRQs since last adaptive moderation decision * @irq_mod_score: IRQ moderation score * @rx_alloc_level: Watermark based heuristic counter for pushing descriptors * and diagnostic counters * @rx_alloc_push_pages: RX allocation method currently in use for pushing * descriptors * @n_rx_tobe_disc: Count of RX_TOBE_DISC errors * @n_rx_ip_hdr_chksum_err: Count of RX IP header checksum errors * @n_rx_tcp_udp_chksum_err: Count of RX TCP and UDP checksum errors * @n_rx_mcast_mismatch: Count of unmatched multicast frames * @n_rx_frm_trunc: Count of RX_FRM_TRUNC errors * @n_rx_overlength: Count of RX_OVERLENGTH errors * @n_skbuff_leaks: Count of skbuffs leaked due to RX overrun * @rx_queue: RX queue for this channel * @tx_queue: TX queues for this channel */ struct efx_channel { struct efx_nic *efx; int channel; const struct efx_channel_type *type; bool enabled; int irq; unsigned int irq_moderation; struct net_device *napi_dev; struct napi_struct napi_str; bool work_pending; struct efx_special_buffer eventq; unsigned int eventq_mask; unsigned int eventq_read_ptr; int event_test_cpu; unsigned int irq_count; unsigned int irq_mod_score; #ifdef CONFIG_RFS_ACCEL unsigned int rfs_filters_added; #endif int rx_alloc_level; int rx_alloc_push_pages; unsigned n_rx_tobe_disc; unsigned n_rx_ip_hdr_chksum_err; unsigned n_rx_tcp_udp_chksum_err; unsigned n_rx_mcast_mismatch; unsigned n_rx_frm_trunc; unsigned n_rx_overlength; unsigned n_skbuff_leaks; /* Used to pipeline received packets in order to optimise memory * access with prefetches. */ struct efx_rx_buffer *rx_pkt; struct efx_rx_queue rx_queue; struct efx_tx_queue tx_queue[EFX_TXQ_TYPES]; }; /** * struct efx_channel_type - distinguishes traffic and extra channels * @handle_no_channel: Handle failure to allocate an extra channel * @pre_probe: Set up extra state prior to initialisation * @post_remove: Tear down extra state after finalisation, if allocated. * May be called on channels that have not been probed. * @get_name: Generate the channel's name (used for its IRQ handler) * @copy: Copy the channel state prior to reallocation. May be %NULL if * reallocation is not supported. * @receive_skb: Handle an skb ready to be passed to netif_receive_skb() * @keep_eventq: Flag for whether event queue should be kept initialised * while the device is stopped */ struct efx_channel_type { void (*handle_no_channel)(struct efx_nic *); int (*pre_probe)(struct efx_channel *); void (*post_remove)(struct efx_channel *); void (*get_name)(struct efx_channel *, char *buf, size_t len); struct efx_channel *(*copy)(const struct efx_channel *); void (*receive_skb)(struct efx_channel *, struct sk_buff *); bool keep_eventq; }; enum efx_led_mode { EFX_LED_OFF = 0, EFX_LED_ON = 1, EFX_LED_DEFAULT = 2 }; #define STRING_TABLE_LOOKUP(val, member) \ ((val) < member ## _max) ? member ## _names[val] : "(invalid)" extern const char *const efx_loopback_mode_names[]; extern const unsigned int efx_loopback_mode_max; #define LOOPBACK_MODE(efx) \ STRING_TABLE_LOOKUP((efx)->loopback_mode, efx_loopback_mode) extern const char *const efx_reset_type_names[]; extern const unsigned int efx_reset_type_max; #define RESET_TYPE(type) \ STRING_TABLE_LOOKUP(type, efx_reset_type) enum efx_int_mode { /* Be careful if altering to correct macro below */ EFX_INT_MODE_MSIX = 0, EFX_INT_MODE_MSI = 1, EFX_INT_MODE_LEGACY = 2, EFX_INT_MODE_MAX /* Insert any new items before this */ }; #define EFX_INT_MODE_USE_MSI(x) (((x)->interrupt_mode) <= EFX_INT_MODE_MSI) enum nic_state { STATE_UNINIT = 0, /* device being probed/removed or is frozen */ STATE_READY = 1, /* hardware ready and netdev registered */ STATE_DISABLED = 2, /* device disabled due to hardware errors */ }; /* * Alignment of page-allocated RX buffers * * Controls the number of bytes inserted at the start of an RX buffer. * This is the equivalent of NET_IP_ALIGN [which controls the alignment * of the skb->head for hardware DMA]. */ #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS #define EFX_PAGE_IP_ALIGN 0 #else #define EFX_PAGE_IP_ALIGN NET_IP_ALIGN #endif /* * Alignment of the skb->head which wraps a page-allocated RX buffer * * The skb allocated to wrap an rx_buffer can have this alignment. Since * the data is memcpy'd from the rx_buf, it does not need to be equal to * EFX_PAGE_IP_ALIGN. */ #define EFX_PAGE_SKB_ALIGN 2 /* Forward declaration */ struct efx_nic; /* Pseudo bit-mask flow control field */ #define EFX_FC_RX FLOW_CTRL_RX #define EFX_FC_TX FLOW_CTRL_TX #define EFX_FC_AUTO 4 /** * struct efx_link_state - Current state of the link * @up: Link is up * @fd: Link is full-duplex * @fc: Actual flow control flags * @speed: Link speed (Mbps) */ struct efx_link_state { bool up; bool fd; u8 fc; unsigned int speed; }; static inline bool efx_link_state_equal(const struct efx_link_state *left, const struct efx_link_state *right) { return left->up == right->up && left->fd == right->fd && left->fc == right->fc && left->speed == right->speed; } /** * struct efx_phy_operations - Efx PHY operations table * @probe: Probe PHY and initialise efx->mdio.mode_support, efx->mdio.mmds, * efx->loopback_modes. * @init: Initialise PHY * @fini: Shut down PHY * @reconfigure: Reconfigure PHY (e.g. for new link parameters) * @poll: Update @link_state and report whether it changed. * Serialised by the mac_lock. * @get_settings: Get ethtool settings. Serialised by the mac_lock. * @set_settings: Set ethtool settings. Serialised by the mac_lock. * @set_npage_adv: Set abilities advertised in (Extended) Next Page * (only needed where AN bit is set in mmds) * @test_alive: Test that PHY is 'alive' (online) * @test_name: Get the name of a PHY-specific test/result * @run_tests: Run tests and record results as appropriate (offline). * Flags are the ethtool tests flags. */ struct efx_phy_operations { int (*probe) (struct efx_nic *efx); int (*init) (struct efx_nic *efx); void (*fini) (struct efx_nic *efx); void (*remove) (struct efx_nic *efx); int (*reconfigure) (struct efx_nic *efx); bool (*poll) (struct efx_nic *efx); void (*get_settings) (struct efx_nic *efx, struct ethtool_cmd *ecmd); int (*set_settings) (struct efx_nic *efx, struct ethtool_cmd *ecmd); void (*set_npage_adv) (struct efx_nic *efx, u32); int (*test_alive) (struct efx_nic *efx); const char *(*test_name) (struct efx_nic *efx, unsigned int index); int (*run_tests) (struct efx_nic *efx, int *results, unsigned flags); int (*get_module_eeprom) (struct efx_nic *efx, struct ethtool_eeprom *ee, u8 *data); int (*get_module_info) (struct efx_nic *efx, struct ethtool_modinfo *modinfo); }; /** * enum efx_phy_mode - PHY operating mode flags * @PHY_MODE_NORMAL: on and should pass traffic * @PHY_MODE_TX_DISABLED: on with TX disabled * @PHY_MODE_LOW_POWER: set to low power through MDIO * @PHY_MODE_OFF: switched off through external control * @PHY_MODE_SPECIAL: on but will not pass traffic */ enum efx_phy_mode { PHY_MODE_NORMAL = 0, PHY_MODE_TX_DISABLED = 1, PHY_MODE_LOW_POWER = 2, PHY_MODE_OFF = 4, PHY_MODE_SPECIAL = 8, }; static inline bool efx_phy_mode_disabled(enum efx_phy_mode mode) { return !!(mode & ~PHY_MODE_TX_DISABLED); } /* * Efx extended statistics * * Not all statistics are provided by all supported MACs. The purpose * is this structure is to contain the raw statistics provided by each * MAC. */ struct efx_mac_stats { u64 tx_bytes; u64 tx_good_bytes; u64 tx_bad_bytes; u64 tx_packets; u64 tx_bad; u64 tx_pause; u64 tx_control; u64 tx_unicast; u64 tx_multicast; u64 tx_broadcast; u64 tx_lt64; u64 tx_64; u64 tx_65_to_127; u64 tx_128_to_255; u64 tx_256_to_511; u64 tx_512_to_1023; u64 tx_1024_to_15xx; u64 tx_15xx_to_jumbo; u64 tx_gtjumbo; u64 tx_collision; u64 tx_single_collision; u64 tx_multiple_collision; u64 tx_excessive_collision; u64 tx_deferred; u64 tx_late_collision; u64 tx_excessive_deferred; u64 tx_non_tcpudp; u64 tx_mac_src_error; u64 tx_ip_src_error; u64 rx_bytes; u64 rx_good_bytes; u64 rx_bad_bytes; u64 rx_packets; u64 rx_good; u64 rx_bad; u64 rx_pause; u64 rx_control; u64 rx_unicast; u64 rx_multicast; u64 rx_broadcast; u64 rx_lt64; u64 rx_64; u64 rx_65_to_127; u64 rx_128_to_255; u64 rx_256_to_511; u64 rx_512_to_1023; u64 rx_1024_to_15xx; u64 rx_15xx_to_jumbo; u64 rx_gtjumbo; u64 rx_bad_lt64; u64 rx_bad_64_to_15xx; u64 rx_bad_15xx_to_jumbo; u64 rx_bad_gtjumbo; u64 rx_overflow; u64 rx_missed; u64 rx_false_carrier; u64 rx_symbol_error; u64 rx_align_error; u64 rx_length_error; u64 rx_internal_error; u64 rx_good_lt64; }; /* Number of bits used in a multicast filter hash address */ #define EFX_MCAST_HASH_BITS 8 /* Number of (single-bit) entries in a multicast filter hash */ #define EFX_MCAST_HASH_ENTRIES (1 << EFX_MCAST_HASH_BITS) /* An Efx multicast filter hash */ union efx_multicast_hash { u8 byte[EFX_MCAST_HASH_ENTRIES / 8]; efx_oword_t oword[EFX_MCAST_HASH_ENTRIES / sizeof(efx_oword_t) / 8]; }; struct efx_filter_state; struct efx_vf; struct vfdi_status; /** * struct efx_nic - an Efx NIC * @name: Device name (net device name or bus id before net device registered) * @pci_dev: The PCI device * @type: Controller type attributes * @legacy_irq: IRQ number * @legacy_irq_enabled: Are IRQs enabled on NIC (INT_EN_KER register)? * @workqueue: Workqueue for port reconfigures and the HW monitor. * Work items do not hold and must not acquire RTNL. * @workqueue_name: Name of workqueue * @reset_work: Scheduled reset workitem * @membase_phys: Memory BAR value as physical address * @membase: Memory BAR value * @interrupt_mode: Interrupt mode * @timer_quantum_ns: Interrupt timer quantum, in nanoseconds * @irq_rx_adaptive: Adaptive IRQ moderation enabled for RX event queues * @irq_rx_moderation: IRQ moderation time for RX event queues * @msg_enable: Log message enable flags * @state: Device state number (%STATE_*). Serialised by the rtnl_lock. * @reset_pending: Bitmask for pending resets * @tx_queue: TX DMA queues * @rx_queue: RX DMA queues * @channel: Channels * @channel_name: Names for channels and their IRQs * @extra_channel_types: Types of extra (non-traffic) channels that * should be allocated for this NIC * @rxq_entries: Size of receive queues requested by user. * @txq_entries: Size of transmit queues requested by user. * @txq_stop_thresh: TX queue fill level at or above which we stop it. * @txq_wake_thresh: TX queue fill level at or below which we wake it. * @tx_dc_base: Base qword address in SRAM of TX queue descriptor caches * @rx_dc_base: Base qword address in SRAM of RX queue descriptor caches * @sram_lim_qw: Qword address limit of SRAM * @next_buffer_table: First available buffer table id * @n_channels: Number of channels in use * @n_rx_channels: Number of channels used for RX (= number of RX queues) * @n_tx_channels: Number of channels used for TX * @rx_buffer_len: RX buffer length * @rx_buffer_order: Order (log2) of number of pages for each RX buffer * @rx_hash_key: Toeplitz hash key for RSS * @rx_indir_table: Indirection table for RSS * @int_error_count: Number of internal errors seen recently * @int_error_expire: Time at which error count will be expired * @irq_status: Interrupt status buffer * @irq_zero_count: Number of legacy IRQs seen with queue flags == 0 * @irq_level: IRQ level/index for IRQs not triggered by an event queue * @selftest_work: Work item for asynchronous self-test * @mtd_list: List of MTDs attached to the NIC * @nic_data: Hardware dependent state * @mac_lock: MAC access lock. Protects @port_enabled, @phy_mode, * efx_monitor() and efx_reconfigure_port() * @port_enabled: Port enabled indicator. * Serialises efx_stop_all(), efx_start_all(), efx_monitor() and * efx_mac_work() with kernel interfaces. Safe to read under any * one of the rtnl_lock, mac_lock, or netif_tx_lock, but all three must * be held to modify it. * @port_initialized: Port initialized? * @net_dev: Operating system network device. Consider holding the rtnl lock * @stats_buffer: DMA buffer for statistics * @phy_type: PHY type * @phy_op: PHY interface * @phy_data: PHY private data (including PHY-specific stats) * @mdio: PHY MDIO interface * @mdio_bus: PHY MDIO bus ID (only used by Siena) * @phy_mode: PHY operating mode. Serialised by @mac_lock. * @link_advertising: Autonegotiation advertising flags * @link_state: Current state of the link * @n_link_state_changes: Number of times the link has changed state * @promiscuous: Promiscuous flag. Protected by netif_tx_lock. * @multicast_hash: Multicast hash table * @wanted_fc: Wanted flow control flags * @fc_disable: When non-zero flow control is disabled. Typically used to * ensure that network back pressure doesn't delay dma queue flushes. * Serialised by the rtnl lock. * @mac_work: Work item for changing MAC promiscuity and multicast hash * @loopback_mode: Loopback status * @loopback_modes: Supported loopback mode bitmask * @loopback_selftest: Offline self-test private state * @drain_pending: Count of RX and TX queues that haven't been flushed and drained. * @rxq_flush_pending: Count of number of receive queues that need to be flushed. * Decremented when the efx_flush_rx_queue() is called. * @rxq_flush_outstanding: Count of number of RX flushes started but not yet * completed (either success or failure). Not used when MCDI is used to * flush receive queues. * @flush_wq: wait queue used by efx_nic_flush_queues() to wait for flush completions. * @vf: Array of &struct efx_vf objects. * @vf_count: Number of VFs intended to be enabled. * @vf_init_count: Number of VFs that have been fully initialised. * @vi_scale: log2 number of vnics per VF. * @vf_buftbl_base: The zeroth buffer table index used to back VF queues. * @vfdi_status: Common VFDI status page to be dmad to VF address space. * @local_addr_list: List of local addresses. Protected by %local_lock. * @local_page_list: List of DMA addressable pages used to broadcast * %local_addr_list. Protected by %local_lock. * @local_lock: Mutex protecting %local_addr_list and %local_page_list. * @peer_work: Work item to broadcast peer addresses to VMs. * @ptp_data: PTP state data * @monitor_work: Hardware monitor workitem * @biu_lock: BIU (bus interface unit) lock * @last_irq_cpu: Last CPU to handle a possible test interrupt. This * field is used by efx_test_interrupts() to verify that an * interrupt has occurred. * @n_rx_nodesc_drop_cnt: RX no descriptor drop count * @mac_stats: MAC statistics. These include all statistics the MACs * can provide. Generic code converts these into a standard * &struct net_device_stats. * @stats_lock: Statistics update lock. Serialises statistics fetches * and access to @mac_stats. * * This is stored in the private area of the &struct net_device. */ struct efx_nic { /* The following fields should be written very rarely */ char name[IFNAMSIZ]; struct pci_dev *pci_dev; const struct efx_nic_type *type; int legacy_irq; bool legacy_irq_enabled; struct workqueue_struct *workqueue; char workqueue_name[16]; struct work_struct reset_work; resource_size_t membase_phys; void __iomem *membase; enum efx_int_mode interrupt_mode; unsigned int timer_quantum_ns; bool irq_rx_adaptive; unsigned int irq_rx_moderation; u32 msg_enable; enum nic_state state; unsigned long reset_pending; struct efx_channel *channel[EFX_MAX_CHANNELS]; char channel_name[EFX_MAX_CHANNELS][IFNAMSIZ + 6]; const struct efx_channel_type * extra_channel_type[EFX_MAX_EXTRA_CHANNELS]; unsigned rxq_entries; unsigned txq_entries; unsigned int txq_stop_thresh; unsigned int txq_wake_thresh; unsigned tx_dc_base; unsigned rx_dc_base; unsigned sram_lim_qw; unsigned next_buffer_table; unsigned n_channels; unsigned n_rx_channels; unsigned rss_spread; unsigned tx_channel_offset; unsigned n_tx_channels; unsigned int rx_buffer_len; unsigned int rx_buffer_order; u8 rx_hash_key[40]; u32 rx_indir_table[128]; unsigned int_error_count; unsigned long int_error_expire; struct efx_buffer irq_status; unsigned irq_zero_count; unsigned irq_level; struct delayed_work selftest_work; #ifdef CONFIG_SFC_MTD struct list_head mtd_list; #endif void *nic_data; struct mutex mac_lock; struct work_struct mac_work; bool port_enabled; bool port_initialized; struct net_device *net_dev; struct efx_buffer stats_buffer; unsigned int phy_type; const struct efx_phy_operations *phy_op; void *phy_data; struct mdio_if_info mdio; unsigned int mdio_bus; enum efx_phy_mode phy_mode; u32 link_advertising; struct efx_link_state link_state; unsigned int n_link_state_changes; bool promiscuous; union efx_multicast_hash multicast_hash; u8 wanted_fc; unsigned fc_disable; atomic_t rx_reset; enum efx_loopback_mode loopback_mode; u64 loopback_modes; void *loopback_selftest;