linux/drivers/net/mlx4/cmd.c

444 lines
12 KiB
C
Raw Normal View History

/*
* Copyright (c) 2004, 2005 Topspin Communications. All rights reserved.
* Copyright (c) 2005, 2006, 2007, 2008 Mellanox Technologies. All rights reserved.
* Copyright (c) 2005, 2006, 2007 Cisco Systems, Inc. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* General Public License (GPL) Version 2, available from the file
* COPYING in the main directory of this source tree, or the
* OpenIB.org BSD license below:
*
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
*
* - Redistributions of source code must retain the above
* copyright notice, this list of conditions and the following
* disclaimer.
*
* - Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following
* disclaimer in the documentation and/or other materials
* provided with the distribution.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#include <linux/sched.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/pci.h>
#include <linux/errno.h>
#include <linux/mlx4/cmd.h>
#include <asm/io.h>
#include "mlx4.h"
#define CMD_POLL_TOKEN 0xffff
enum {
/* command completed successfully: */
CMD_STAT_OK = 0x00,
/* Internal error (such as a bus error) occurred while processing command: */
CMD_STAT_INTERNAL_ERR = 0x01,
/* Operation/command not supported or opcode modifier not supported: */
CMD_STAT_BAD_OP = 0x02,
/* Parameter not supported or parameter out of range: */
CMD_STAT_BAD_PARAM = 0x03,
/* System not enabled or bad system state: */
CMD_STAT_BAD_SYS_STATE = 0x04,
/* Attempt to access reserved or unallocaterd resource: */
CMD_STAT_BAD_RESOURCE = 0x05,
/* Requested resource is currently executing a command, or is otherwise busy: */
CMD_STAT_RESOURCE_BUSY = 0x06,
/* Required capability exceeds device limits: */
CMD_STAT_EXCEED_LIM = 0x08,
/* Resource is not in the appropriate state or ownership: */
CMD_STAT_BAD_RES_STATE = 0x09,
/* Index out of range: */
CMD_STAT_BAD_INDEX = 0x0a,
/* FW image corrupted: */
CMD_STAT_BAD_NVMEM = 0x0b,
/* Error in ICM mapping (e.g. not enough auxiliary ICM pages to execute command): */
CMD_STAT_ICM_ERROR = 0x0c,
/* Attempt to modify a QP/EE which is not in the presumed state: */
CMD_STAT_BAD_QP_STATE = 0x10,
/* Bad segment parameters (Address/Size): */
CMD_STAT_BAD_SEG_PARAM = 0x20,
/* Memory Region has Memory Windows bound to: */
CMD_STAT_REG_BOUND = 0x21,
/* HCA local attached memory not present: */
CMD_STAT_LAM_NOT_PRE = 0x22,
/* Bad management packet (silently discarded): */
CMD_STAT_BAD_PKT = 0x30,
/* More outstanding CQEs in CQ than new CQ size: */
CMD_STAT_BAD_SIZE = 0x40,
/* Multi Function device support required: */
CMD_STAT_MULTI_FUNC_REQ = 0x50,
};
enum {
HCR_IN_PARAM_OFFSET = 0x00,
HCR_IN_MODIFIER_OFFSET = 0x08,
HCR_OUT_PARAM_OFFSET = 0x0c,
HCR_TOKEN_OFFSET = 0x14,
HCR_STATUS_OFFSET = 0x18,
HCR_OPMOD_SHIFT = 12,
HCR_T_BIT = 21,
HCR_E_BIT = 22,
HCR_GO_BIT = 23
};
enum {
GO_BIT_TIMEOUT_MSECS = 10000
};
struct mlx4_cmd_context {
struct completion done;
int result;
int next;
u64 out_param;
u16 token;
};
static int mlx4_status_to_errno(u8 status)
{
static const int trans_table[] = {
[CMD_STAT_INTERNAL_ERR] = -EIO,
[CMD_STAT_BAD_OP] = -EPERM,
[CMD_STAT_BAD_PARAM] = -EINVAL,
[CMD_STAT_BAD_SYS_STATE] = -ENXIO,
[CMD_STAT_BAD_RESOURCE] = -EBADF,
[CMD_STAT_RESOURCE_BUSY] = -EBUSY,
[CMD_STAT_EXCEED_LIM] = -ENOMEM,
[CMD_STAT_BAD_RES_STATE] = -EBADF,
[CMD_STAT_BAD_INDEX] = -EBADF,
[CMD_STAT_BAD_NVMEM] = -EFAULT,
[CMD_STAT_ICM_ERROR] = -ENFILE,
[CMD_STAT_BAD_QP_STATE] = -EINVAL,
[CMD_STAT_BAD_SEG_PARAM] = -EFAULT,
[CMD_STAT_REG_BOUND] = -EBUSY,
[CMD_STAT_LAM_NOT_PRE] = -EAGAIN,
[CMD_STAT_BAD_PKT] = -EINVAL,
[CMD_STAT_BAD_SIZE] = -ENOMEM,
[CMD_STAT_MULTI_FUNC_REQ] = -EACCES,
};
if (status >= ARRAY_SIZE(trans_table) ||
(status != CMD_STAT_OK && trans_table[status] == 0))
return -EIO;
return trans_table[status];
}
static int cmd_pending(struct mlx4_dev *dev)
{
u32 status = readl(mlx4_priv(dev)->cmd.hcr + HCR_STATUS_OFFSET);
return (status & swab32(1 << HCR_GO_BIT)) ||
(mlx4_priv(dev)->cmd.toggle ==
!!(status & swab32(1 << HCR_T_BIT)));
}
static int mlx4_cmd_post(struct mlx4_dev *dev, u64 in_param, u64 out_param,
u32 in_modifier, u8 op_modifier, u16 op, u16 token,
int event)
{
struct mlx4_cmd *cmd = &mlx4_priv(dev)->cmd;
u32 __iomem *hcr = cmd->hcr;
int ret = -EAGAIN;
unsigned long end;
mutex_lock(&cmd->hcr_mutex);
end = jiffies;
if (event)
end += msecs_to_jiffies(GO_BIT_TIMEOUT_MSECS);
while (cmd_pending(dev)) {
if (time_after_eq(jiffies, end))
goto out;
cond_resched();
}
/*
* We use writel (instead of something like memcpy_toio)
* because writes of less than 32 bits to the HCR don't work
* (and some architectures such as ia64 implement memcpy_toio
* in terms of writeb).
*/
__raw_writel((__force u32) cpu_to_be32(in_param >> 32), hcr + 0);
__raw_writel((__force u32) cpu_to_be32(in_param & 0xfffffffful), hcr + 1);
__raw_writel((__force u32) cpu_to_be32(in_modifier), hcr + 2);
__raw_writel((__force u32) cpu_to_be32(out_param >> 32), hcr + 3);
__raw_writel((__force u32) cpu_to_be32(out_param & 0xfffffffful), hcr + 4);
__raw_writel((__force u32) cpu_to_be32(token << 16), hcr + 5);
/* __raw_writel may not order writes. */
wmb();
__raw_writel((__force u32) cpu_to_be32((1 << HCR_GO_BIT) |
(cmd->toggle << HCR_T_BIT) |
(event ? (1 << HCR_E_BIT) : 0) |
(op_modifier << HCR_OPMOD_SHIFT) |
op), hcr + 6);
/*
* Make sure that our HCR writes don't get mixed in with
* writes from another CPU starting a FW command.
*/
mmiowb();
cmd->toggle = cmd->toggle ^ 1;
ret = 0;
out:
mutex_unlock(&cmd->hcr_mutex);
return ret;
}
static int mlx4_cmd_poll(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
int out_is_imm, u32 in_modifier, u8 op_modifier,
u16 op, unsigned long timeout)
{
struct mlx4_priv *priv = mlx4_priv(dev);
void __iomem *hcr = priv->cmd.hcr;
int err = 0;
unsigned long end;
down(&priv->cmd.poll_sem);
err = mlx4_cmd_post(dev, in_param, out_param ? *out_param : 0,
in_modifier, op_modifier, op, CMD_POLL_TOKEN, 0);
if (err)
goto out;
end = msecs_to_jiffies(timeout) + jiffies;
while (cmd_pending(dev) && time_before(jiffies, end))
cond_resched();
if (cmd_pending(dev)) {
err = -ETIMEDOUT;
goto out;
}
if (out_is_imm)
*out_param =
(u64) be32_to_cpu((__force __be32)
__raw_readl(hcr + HCR_OUT_PARAM_OFFSET)) << 32 |
(u64) be32_to_cpu((__force __be32)
__raw_readl(hcr + HCR_OUT_PARAM_OFFSET + 4));
err = mlx4_status_to_errno(be32_to_cpu((__force __be32)
__raw_readl(hcr + HCR_STATUS_OFFSET)) >> 24);
out:
up(&priv->cmd.poll_sem);
return err;
}
void mlx4_cmd_event(struct mlx4_dev *dev, u16 token, u8 status, u64 out_param)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_cmd_context *context =
&priv->cmd.context[token & priv->cmd.token_mask];
/* previously timed out command completing at long last */
if (token != context->token)
return;
context->result = mlx4_status_to_errno(status);
context->out_param = out_param;
complete(&context->done);
}
static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
int out_is_imm, u32 in_modifier, u8 op_modifier,
u16 op, unsigned long timeout)
{
struct mlx4_cmd *cmd = &mlx4_priv(dev)->cmd;
struct mlx4_cmd_context *context;
int err = 0;
down(&cmd->event_sem);
spin_lock(&cmd->context_lock);
BUG_ON(cmd->free_head < 0);
context = &cmd->context[cmd->free_head];
context->token += cmd->token_mask + 1;
cmd->free_head = context->next;
spin_unlock(&cmd->context_lock);
init_completion(&context->done);
mlx4_cmd_post(dev, in_param, out_param ? *out_param : 0,
in_modifier, op_modifier, op, context->token, 1);
if (!wait_for_completion_timeout(&context->done, msecs_to_jiffies(timeout))) {
err = -EBUSY;
goto out;
}
err = context->result;
if (err)
goto out;
if (out_is_imm)
*out_param = context->out_param;
out:
spin_lock(&cmd->context_lock);
context->next = cmd->free_head;
cmd->free_head = context - cmd->context;
spin_unlock(&cmd->context_lock);
up(&cmd->event_sem);
return err;
}
int __mlx4_cmd(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
int out_is_imm, u32 in_modifier, u8 op_modifier,
u16 op, unsigned long timeout)
{
if (mlx4_priv(dev)->cmd.use_events)
return mlx4_cmd_wait(dev, in_param, out_param, out_is_imm,
in_modifier, op_modifier, op, timeout);
else
return mlx4_cmd_poll(dev, in_param, out_param, out_is_imm,
in_modifier, op_modifier, op, timeout);
}
EXPORT_SYMBOL_GPL(__mlx4_cmd);
int mlx4_cmd_init(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
mutex_init(&priv->cmd.hcr_mutex);
sema_init(&priv->cmd.poll_sem, 1);
priv->cmd.use_events = 0;
priv->cmd.toggle = 1;
priv->cmd.hcr = ioremap(pci_resource_start(dev->pdev, 0) + MLX4_HCR_BASE,
MLX4_HCR_SIZE);
if (!priv->cmd.hcr) {
mlx4_err(dev, "Couldn't map command register.");
return -ENOMEM;
}
priv->cmd.pool = pci_pool_create("mlx4_cmd", dev->pdev,
MLX4_MAILBOX_SIZE,
MLX4_MAILBOX_SIZE, 0);
if (!priv->cmd.pool) {
iounmap(priv->cmd.hcr);
return -ENOMEM;
}
return 0;
}
void mlx4_cmd_cleanup(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
pci_pool_destroy(priv->cmd.pool);
iounmap(priv->cmd.hcr);
}
/*
* Switch to using events to issue FW commands (can only be called
* after event queue for command events has been initialized).
*/
int mlx4_cmd_use_events(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
int i;
priv->cmd.context = kmalloc(priv->cmd.max_cmds *
sizeof (struct mlx4_cmd_context),
GFP_KERNEL);
if (!priv->cmd.context)
return -ENOMEM;
for (i = 0; i < priv->cmd.max_cmds; ++i) {
priv->cmd.context[i].token = i;
priv->cmd.context[i].next = i + 1;
}
priv->cmd.context[priv->cmd.max_cmds - 1].next = -1;
priv->cmd.free_head = 0;
sema_init(&priv->cmd.event_sem, priv->cmd.max_cmds);
spin_lock_init(&priv->cmd.context_lock);
for (priv->cmd.token_mask = 1;
priv->cmd.token_mask < priv->cmd.max_cmds;
priv->cmd.token_mask <<= 1)
; /* nothing */
--priv->cmd.token_mask;
priv->cmd.use_events = 1;
down(&priv->cmd.poll_sem);
return 0;
}
/*
* Switch back to polling (used when shutting down the device)
*/
void mlx4_cmd_use_polling(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
int i;
priv->cmd.use_events = 0;
for (i = 0; i < priv->cmd.max_cmds; ++i)
down(&priv->cmd.event_sem);
kfree(priv->cmd.context);
up(&priv->cmd.poll_sem);
}
struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev)
{
struct mlx4_cmd_mailbox *mailbox;
mailbox = kmalloc(sizeof *mailbox, GFP_KERNEL);
if (!mailbox)
return ERR_PTR(-ENOMEM);
mailbox->buf = pci_pool_alloc(mlx4_priv(dev)->cmd.pool, GFP_KERNEL,
&mailbox->dma);
if (!mailbox->buf) {
kfree(mailbox);
return ERR_PTR(-ENOMEM);
}
return mailbox;
}
EXPORT_SYMBOL_GPL(mlx4_alloc_cmd_mailbox);
void mlx4_free_cmd_mailbox(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox)
{
if (!mailbox)
return;
pci_pool_free(mlx4_priv(dev)->cmd.pool, mailbox->buf, mailbox->dma);
kfree(mailbox);
}
EXPORT_SYMBOL_GPL(mlx4_free_cmd_mailbox);