OpenCloudOS-Kernel/drivers/pci/access.c

448 lines
11 KiB
C
Raw Normal View History

#include <linux/delay.h>
#include <linux/pci.h>
#include <linux/module.h>
#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 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/ioport.h>
#include <linux/wait.h>
#include "pci.h"
/*
* This interrupt-safe spinlock protects all accesses to PCI
* configuration space.
*/
static DEFINE_RAW_SPINLOCK(pci_lock);
/*
* Wrappers for all PCI configuration access functions. They just check
* alignment, do locking and call the low-level functions pointed to
* by pci_dev->ops.
*/
#define PCI_byte_BAD 0
#define PCI_word_BAD (pos & 1)
#define PCI_dword_BAD (pos & 3)
#define PCI_OP_READ(size,type,len) \
int pci_bus_read_config_##size \
(struct pci_bus *bus, unsigned int devfn, int pos, type *value) \
{ \
int res; \
unsigned long flags; \
u32 data = 0; \
if (PCI_##size##_BAD) return PCIBIOS_BAD_REGISTER_NUMBER; \
raw_spin_lock_irqsave(&pci_lock, flags); \
res = bus->ops->read(bus, devfn, pos, len, &data); \
*value = (type)data; \
raw_spin_unlock_irqrestore(&pci_lock, flags); \
return res; \
}
#define PCI_OP_WRITE(size,type,len) \
int pci_bus_write_config_##size \
(struct pci_bus *bus, unsigned int devfn, int pos, type value) \
{ \
int res; \
unsigned long flags; \
if (PCI_##size##_BAD) return PCIBIOS_BAD_REGISTER_NUMBER; \
raw_spin_lock_irqsave(&pci_lock, flags); \
res = bus->ops->write(bus, devfn, pos, len, value); \
raw_spin_unlock_irqrestore(&pci_lock, flags); \
return res; \
}
PCI_OP_READ(byte, u8, 1)
PCI_OP_READ(word, u16, 2)
PCI_OP_READ(dword, u32, 4)
PCI_OP_WRITE(byte, u8, 1)
PCI_OP_WRITE(word, u16, 2)
PCI_OP_WRITE(dword, u32, 4)
EXPORT_SYMBOL(pci_bus_read_config_byte);
EXPORT_SYMBOL(pci_bus_read_config_word);
EXPORT_SYMBOL(pci_bus_read_config_dword);
EXPORT_SYMBOL(pci_bus_write_config_byte);
EXPORT_SYMBOL(pci_bus_write_config_word);
EXPORT_SYMBOL(pci_bus_write_config_dword);
/**
* pci_bus_set_ops - Set raw operations of pci bus
* @bus: pci bus struct
* @ops: new raw operations
*
* Return previous raw operations
*/
struct pci_ops *pci_bus_set_ops(struct pci_bus *bus, struct pci_ops *ops)
{
struct pci_ops *old_ops;
unsigned long flags;
raw_spin_lock_irqsave(&pci_lock, flags);
old_ops = bus->ops;
bus->ops = ops;
raw_spin_unlock_irqrestore(&pci_lock, flags);
return old_ops;
}
EXPORT_SYMBOL(pci_bus_set_ops);
/**
* pci_read_vpd - Read one entry from Vital Product Data
* @dev: pci device struct
* @pos: offset in vpd space
* @count: number of bytes to read
* @buf: pointer to where to store result
*
*/
ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf)
{
if (!dev->vpd || !dev->vpd->ops)
return -ENODEV;
return dev->vpd->ops->read(dev, pos, count, buf);
}
EXPORT_SYMBOL(pci_read_vpd);
/**
* pci_write_vpd - Write entry to Vital Product Data
* @dev: pci device struct
* @pos: offset in vpd space
* @count: number of bytes to write
* @buf: buffer containing write data
*
*/
ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void *buf)
{
if (!dev->vpd || !dev->vpd->ops)
return -ENODEV;
return dev->vpd->ops->write(dev, pos, count, buf);
}
EXPORT_SYMBOL(pci_write_vpd);
/*
* The following routines are to prevent the user from accessing PCI config
* space when it's unsafe to do so. Some devices require this during BIST and
* we're required to prevent it during D-state transitions.
*
* We have a bit per device to indicate it's blocked and a global wait queue
* for callers to sleep on until devices are unblocked.
*/
static DECLARE_WAIT_QUEUE_HEAD(pci_ucfg_wait);
static noinline void pci_wait_ucfg(struct pci_dev *dev)
{
DECLARE_WAITQUEUE(wait, current);
__add_wait_queue(&pci_ucfg_wait, &wait);
do {
set_current_state(TASK_UNINTERRUPTIBLE);
raw_spin_unlock_irq(&pci_lock);
schedule();
raw_spin_lock_irq(&pci_lock);
} while (dev->block_ucfg_access);
__remove_wait_queue(&pci_ucfg_wait, &wait);
}
/* Returns 0 on success, negative values indicate error. */
#define PCI_USER_READ_CONFIG(size,type) \
int pci_user_read_config_##size \
(struct pci_dev *dev, int pos, type *val) \
{ \
int ret = 0; \
u32 data = -1; \
if (PCI_##size##_BAD) \
return -EINVAL; \
raw_spin_lock_irq(&pci_lock); \
if (unlikely(dev->block_ucfg_access)) pci_wait_ucfg(dev); \
ret = dev->bus->ops->read(dev->bus, dev->devfn, \
pos, sizeof(type), &data); \
raw_spin_unlock_irq(&pci_lock); \
*val = (type)data; \
if (ret > 0) \
ret = -EINVAL; \
return ret; \
}
/* Returns 0 on success, negative values indicate error. */
#define PCI_USER_WRITE_CONFIG(size,type) \
int pci_user_write_config_##size \
(struct pci_dev *dev, int pos, type val) \
{ \
int ret = -EIO; \
if (PCI_##size##_BAD) \
return -EINVAL; \
raw_spin_lock_irq(&pci_lock); \
if (unlikely(dev->block_ucfg_access)) pci_wait_ucfg(dev); \
ret = dev->bus->ops->write(dev->bus, dev->devfn, \
pos, sizeof(type), val); \
raw_spin_unlock_irq(&pci_lock); \
if (ret > 0) \
ret = -EINVAL; \
return ret; \
}
PCI_USER_READ_CONFIG(byte, u8)
PCI_USER_READ_CONFIG(word, u16)
PCI_USER_READ_CONFIG(dword, u32)
PCI_USER_WRITE_CONFIG(byte, u8)
PCI_USER_WRITE_CONFIG(word, u16)
PCI_USER_WRITE_CONFIG(dword, u32)
/* VPD access through PCI 2.2+ VPD capability */
#define PCI_VPD_PCI22_SIZE (PCI_VPD_ADDR_MASK + 1)
struct pci_vpd_pci22 {
struct pci_vpd base;
struct mutex lock;
u16 flag;
bool busy;
u8 cap;
};
/*
* Wait for last operation to complete.
* This code has to spin since there is no other notification from the PCI
* hardware. Since the VPD is often implemented by serial attachment to an
* EEPROM, it may take many milliseconds to complete.
*
* Returns 0 on success, negative values indicate error.
*/
static int pci_vpd_pci22_wait(struct pci_dev *dev)
{
struct pci_vpd_pci22 *vpd =
container_of(dev->vpd, struct pci_vpd_pci22, base);
unsigned long timeout = jiffies + HZ/20 + 2;
u16 status;
int ret;
if (!vpd->busy)
return 0;
for (;;) {
ret = pci_user_read_config_word(dev, vpd->cap + PCI_VPD_ADDR,
&status);
if (ret < 0)
return ret;
if ((status & PCI_VPD_ADDR_F) == vpd->flag) {
vpd->busy = false;
return 0;
}
if (time_after(jiffies, timeout)) {
dev_printk(KERN_DEBUG, &dev->dev,
"vpd r/w failed. This is likely a firmware "
"bug on this device. Contact the card "
"vendor for a firmware update.");
return -ETIMEDOUT;
}
if (fatal_signal_pending(current))
return -EINTR;
if (!cond_resched())
udelay(10);
}
}
static ssize_t pci_vpd_pci22_read(struct pci_dev *dev, loff_t pos, size_t count,
void *arg)
{
struct pci_vpd_pci22 *vpd =
container_of(dev->vpd, struct pci_vpd_pci22, base);
int ret;
loff_t end = pos + count;
u8 *buf = arg;
if (pos < 0 || pos > vpd->base.len || end > vpd->base.len)
return -EINVAL;
if (mutex_lock_killable(&vpd->lock))
return -EINTR;
ret = pci_vpd_pci22_wait(dev);
if (ret < 0)
goto out;
while (pos < end) {
u32 val;
unsigned int i, skip;
ret = pci_user_write_config_word(dev, vpd->cap + PCI_VPD_ADDR,
pos & ~3);
if (ret < 0)
break;
vpd->busy = true;
vpd->flag = PCI_VPD_ADDR_F;
ret = pci_vpd_pci22_wait(dev);
if (ret < 0)
break;
ret = pci_user_read_config_dword(dev, vpd->cap + PCI_VPD_DATA, &val);
if (ret < 0)
break;
skip = pos & 3;
for (i = 0; i < sizeof(u32); i++) {
if (i >= skip) {
*buf++ = val;
if (++pos == end)
break;
}
val >>= 8;
}
}
out:
mutex_unlock(&vpd->lock);
return ret ? ret : count;
}
static ssize_t pci_vpd_pci22_write(struct pci_dev *dev, loff_t pos, size_t count,
const void *arg)
{
struct pci_vpd_pci22 *vpd =
container_of(dev->vpd, struct pci_vpd_pci22, base);
const u8 *buf = arg;
loff_t end = pos + count;
int ret = 0;
if (pos < 0 || (pos & 3) || (count & 3) || end > vpd->base.len)
return -EINVAL;
if (mutex_lock_killable(&vpd->lock))
return -EINTR;
ret = pci_vpd_pci22_wait(dev);
if (ret < 0)
goto out;
while (pos < end) {
u32 val;
val = *buf++;
val |= *buf++ << 8;
val |= *buf++ << 16;
val |= *buf++ << 24;
ret = pci_user_write_config_dword(dev, vpd->cap + PCI_VPD_DATA, val);
if (ret < 0)
break;
ret = pci_user_write_config_word(dev, vpd->cap + PCI_VPD_ADDR,
pos | PCI_VPD_ADDR_F);
if (ret < 0)
break;
vpd->busy = true;
vpd->flag = 0;
ret = pci_vpd_pci22_wait(dev);
if (ret < 0)
break;
pos += sizeof(u32);
}
out:
mutex_unlock(&vpd->lock);
return ret ? ret : count;
}
static void pci_vpd_pci22_release(struct pci_dev *dev)
{
kfree(container_of(dev->vpd, struct pci_vpd_pci22, base));
}
static const struct pci_vpd_ops pci_vpd_pci22_ops = {
.read = pci_vpd_pci22_read,
.write = pci_vpd_pci22_write,
.release = pci_vpd_pci22_release,
};
int pci_vpd_pci22_init(struct pci_dev *dev)
{
struct pci_vpd_pci22 *vpd;
u8 cap;
cap = pci_find_capability(dev, PCI_CAP_ID_VPD);
if (!cap)
return -ENODEV;
vpd = kzalloc(sizeof(*vpd), GFP_ATOMIC);
if (!vpd)
return -ENOMEM;
vpd->base.len = PCI_VPD_PCI22_SIZE;
vpd->base.ops = &pci_vpd_pci22_ops;
mutex_init(&vpd->lock);
vpd->cap = cap;
vpd->busy = false;
dev->vpd = &vpd->base;
return 0;
}
/**
* pci_vpd_truncate - Set available Vital Product Data size
* @dev: pci device struct
* @size: available memory in bytes
*
* Adjust size of available VPD area.
*/
int pci_vpd_truncate(struct pci_dev *dev, size_t size)
{
if (!dev->vpd)
return -EINVAL;
/* limited by the access method */
if (size > dev->vpd->len)
return -EINVAL;
dev->vpd->len = size;
PCI: Fix oops in pci_vpd_truncate pci_vpd_truncate() should check for dev->vpd->attr, otherwise this might happen: sky2 driver version 1.22 Unable to handle kernel paging request for data at address 0x0000000c Faulting instruction address: 0xc01836fc Oops: Kernel access of bad area, sig: 11 [#1] [...] NIP [c01836fc] pci_vpd_truncate+0x38/0x40 LR [c029be18] sky2_probe+0x14c/0x518 Call Trace: [ef82bde0] [c029bda4] sky2_probe+0xd8/0x518 (unreliable) [ef82be20] [c018a11c] local_pci_probe+0x24/0x34 [ef82be30] [c018a14c] pci_call_probe+0x20/0x30 [ef82be50] [c018a330] __pci_device_probe+0x64/0x78 [ef82be60] [c018a44c] pci_device_probe+0x30/0x58 [ef82be80] [c01aa270] really_probe+0x78/0x1a0 [ef82bea0] [c01aa460] __driver_attach+0xa4/0xa8 [ef82bec0] [c01a96ac] bus_for_each_dev+0x60/0x9c [ef82bef0] [c01aa0b4] driver_attach+0x24/0x34 [ef82bf00] [c01a9e08] bus_add_driver+0x12c/0x1cc [ef82bf20] [c01aa87c] driver_register+0x6c/0x110 [ef82bf30] [c018a770] __pci_register_driver+0x4c/0x9c [ef82bf50] [c03782c8] sky2_init_module+0x30/0x40 [ef82bf60] [c0001dbc] do_one_initcall+0x34/0x1a0 [ef82bfd0] [c0362240] do_initcalls+0x38/0x58 This happens with CONFIG_SKY2=y, and "ip=on" kernel command line, so pci_vpd_truncate() is called before late_initcall(pci_sysfs_init), therefore ->attr isn't yet initialized. Acked-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-01 06:23:41 +08:00
if (dev->vpd->attr)
dev->vpd->attr->size = size;
return 0;
}
EXPORT_SYMBOL(pci_vpd_truncate);
/**
* pci_block_user_cfg_access - Block userspace PCI config reads/writes
* @dev: pci device struct
*
* When user access is blocked, any reads or writes to config space will
* sleep until access is unblocked again. We don't allow nesting of
* block/unblock calls.
*/
void pci_block_user_cfg_access(struct pci_dev *dev)
{
unsigned long flags;
int was_blocked;
raw_spin_lock_irqsave(&pci_lock, flags);
was_blocked = dev->block_ucfg_access;
dev->block_ucfg_access = 1;
raw_spin_unlock_irqrestore(&pci_lock, flags);
/* If we BUG() inside the pci_lock, we're guaranteed to hose
* the machine */
BUG_ON(was_blocked);
}
EXPORT_SYMBOL_GPL(pci_block_user_cfg_access);
/**
* pci_unblock_user_cfg_access - Unblock userspace PCI config reads/writes
* @dev: pci device struct
*
* This function allows userspace PCI config accesses to resume.
*/
void pci_unblock_user_cfg_access(struct pci_dev *dev)
{
unsigned long flags;
raw_spin_lock_irqsave(&pci_lock, flags);
/* This indicates a problem in the caller, but we don't need
* to kill them, unlike a double-block above. */
WARN_ON(!dev->block_ucfg_access);
dev->block_ucfg_access = 0;
wake_up_all(&pci_ucfg_wait);
raw_spin_unlock_irqrestore(&pci_lock, flags);
}
EXPORT_SYMBOL_GPL(pci_unblock_user_cfg_access);