OpenCloudOS-Kernel/arch/x86/pci/mmconfig_32.c

149 lines
3.4 KiB
C
Raw Normal View History

/*
* Copyright (C) 2004 Matthew Wilcox <matthew@wil.cx>
* Copyright (C) 2004 Intel Corp.
*
* This code is released under the GNU General Public License version 2.
*/
/*
* mmconfig.c - Low-level direct PCI config space access via MMCONFIG
*/
#include <linux/pci.h>
#include <linux/init.h>
#include <linux/acpi.h>
#include <asm/e820.h>
#include "pci.h"
/* Assume systems with more busses have correct MCFG */
#define mmcfg_virt_addr ((void __iomem *) fix_to_virt(FIX_PCIE_MCFG))
/* The base address of the last MMCONFIG device accessed */
static u32 mmcfg_last_accessed_device;
[PATCH] arch/i386/pci/mmconfig.c tlb flush fix We use the fixmap for accessing pci config space in pci_mmcfg_read/write(). The problem is in pci_exp_set_dev_base(). It is caching a last accessed address to avoid calling set_fixmap_nocache() whenever pci_mmcfg_read/write() is used. static inline void pci_exp_set_dev_base(int bus, int devfn) { u32 dev_base = base | (bus << 20) | (devfn << 12); if (dev_base != mmcfg_last_accessed_device) { mmcfg_last_accessed_device = dev_base; set_fixmap_nocache(FIX_PCIE_MCFG, dev_base); } } cpu0 cpu1 --------------------------------------------------------------------------- pci_mmcfg_read("device-A") pci_exp_set_dev_base() set_fixmap_nocache() pci_mmcfg_read("device-B") pci_exp_set_dev_base() set_fixmap_nocache() pci_mmcfg_read("device-B") pci_exp_set_dev_base() /* doesn't flush tlb */ But if cpus accessed the above order, the second pci_mmcfg_read() on cpu0 doesn't flush the TLB, because "mmcfg_last_accessed_device" is device-B. So, second pci_mmcfg_read() on cpu0 accesses a device-A via a previous TLB cache. This problem became the cause of several strange behavior. This patches fixes this situation by adds "mmcfg_last_accessed_cpu" check. [ Alternatively, we could make a per-cpu mapping area or something. Not that it's probably worth it, but if we wanted to avoid all locking and instead just disable preemption, that would be the way to go. --Linus ] Signed-off-by: OGAWA Hirofumi <hogawa@miraclelinux.com> Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-23 09:00:43 +08:00
static int mmcfg_last_accessed_cpu;
/*
* Functions for accessing PCI configuration space with MMCONFIG accesses
*/
static u32 get_base_addr(unsigned int seg, int bus, unsigned devfn)
{
struct acpi_mcfg_allocation *cfg;
int cfg_num;
if (seg == 0 && bus < PCI_MMCFG_MAX_CHECK_BUS &&
test_bit(PCI_SLOT(devfn) + 32*bus, pci_mmcfg_fallback_slots))
return 0;
for (cfg_num = 0; cfg_num < pci_mmcfg_config_num; cfg_num++) {
cfg = &pci_mmcfg_config[cfg_num];
if (cfg->pci_segment == seg &&
(cfg->start_bus_number <= bus) &&
(cfg->end_bus_number >= bus))
return cfg->address;
}
/* Fall back to type 0 */
return 0;
}
/*
* This is always called under pci_config_lock
*/
static void pci_exp_set_dev_base(unsigned int base, int bus, int devfn)
{
u32 dev_base = base | (bus << 20) | (devfn << 12);
[PATCH] arch/i386/pci/mmconfig.c tlb flush fix We use the fixmap for accessing pci config space in pci_mmcfg_read/write(). The problem is in pci_exp_set_dev_base(). It is caching a last accessed address to avoid calling set_fixmap_nocache() whenever pci_mmcfg_read/write() is used. static inline void pci_exp_set_dev_base(int bus, int devfn) { u32 dev_base = base | (bus << 20) | (devfn << 12); if (dev_base != mmcfg_last_accessed_device) { mmcfg_last_accessed_device = dev_base; set_fixmap_nocache(FIX_PCIE_MCFG, dev_base); } } cpu0 cpu1 --------------------------------------------------------------------------- pci_mmcfg_read("device-A") pci_exp_set_dev_base() set_fixmap_nocache() pci_mmcfg_read("device-B") pci_exp_set_dev_base() set_fixmap_nocache() pci_mmcfg_read("device-B") pci_exp_set_dev_base() /* doesn't flush tlb */ But if cpus accessed the above order, the second pci_mmcfg_read() on cpu0 doesn't flush the TLB, because "mmcfg_last_accessed_device" is device-B. So, second pci_mmcfg_read() on cpu0 accesses a device-A via a previous TLB cache. This problem became the cause of several strange behavior. This patches fixes this situation by adds "mmcfg_last_accessed_cpu" check. [ Alternatively, we could make a per-cpu mapping area or something. Not that it's probably worth it, but if we wanted to avoid all locking and instead just disable preemption, that would be the way to go. --Linus ] Signed-off-by: OGAWA Hirofumi <hogawa@miraclelinux.com> Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-23 09:00:43 +08:00
int cpu = smp_processor_id();
if (dev_base != mmcfg_last_accessed_device ||
cpu != mmcfg_last_accessed_cpu) {
mmcfg_last_accessed_device = dev_base;
[PATCH] arch/i386/pci/mmconfig.c tlb flush fix We use the fixmap for accessing pci config space in pci_mmcfg_read/write(). The problem is in pci_exp_set_dev_base(). It is caching a last accessed address to avoid calling set_fixmap_nocache() whenever pci_mmcfg_read/write() is used. static inline void pci_exp_set_dev_base(int bus, int devfn) { u32 dev_base = base | (bus << 20) | (devfn << 12); if (dev_base != mmcfg_last_accessed_device) { mmcfg_last_accessed_device = dev_base; set_fixmap_nocache(FIX_PCIE_MCFG, dev_base); } } cpu0 cpu1 --------------------------------------------------------------------------- pci_mmcfg_read("device-A") pci_exp_set_dev_base() set_fixmap_nocache() pci_mmcfg_read("device-B") pci_exp_set_dev_base() set_fixmap_nocache() pci_mmcfg_read("device-B") pci_exp_set_dev_base() /* doesn't flush tlb */ But if cpus accessed the above order, the second pci_mmcfg_read() on cpu0 doesn't flush the TLB, because "mmcfg_last_accessed_device" is device-B. So, second pci_mmcfg_read() on cpu0 accesses a device-A via a previous TLB cache. This problem became the cause of several strange behavior. This patches fixes this situation by adds "mmcfg_last_accessed_cpu" check. [ Alternatively, we could make a per-cpu mapping area or something. Not that it's probably worth it, but if we wanted to avoid all locking and instead just disable preemption, that would be the way to go. --Linus ] Signed-off-by: OGAWA Hirofumi <hogawa@miraclelinux.com> Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-23 09:00:43 +08:00
mmcfg_last_accessed_cpu = cpu;
set_fixmap_nocache(FIX_PCIE_MCFG, dev_base);
}
}
static int pci_mmcfg_read(unsigned int seg, unsigned int bus,
unsigned int devfn, int reg, int len, u32 *value)
{
unsigned long flags;
u32 base;
if ((bus > 255) || (devfn > 255) || (reg > 4095)) {
*value = -1;
return -EINVAL;
}
base = get_base_addr(seg, bus, devfn);
if (!base)
return pci_conf1_read(seg,bus,devfn,reg,len,value);
spin_lock_irqsave(&pci_config_lock, flags);
pci_exp_set_dev_base(base, bus, devfn);
switch (len) {
case 1:
*value = mmio_config_readb(mmcfg_virt_addr + reg);
break;
case 2:
*value = mmio_config_readw(mmcfg_virt_addr + reg);
break;
case 4:
*value = mmio_config_readl(mmcfg_virt_addr + reg);
break;
}
spin_unlock_irqrestore(&pci_config_lock, flags);
return 0;
}
static int pci_mmcfg_write(unsigned int seg, unsigned int bus,
unsigned int devfn, int reg, int len, u32 value)
{
unsigned long flags;
u32 base;
if ((bus > 255) || (devfn > 255) || (reg > 4095))
return -EINVAL;
base = get_base_addr(seg, bus, devfn);
if (!base)
return pci_conf1_write(seg,bus,devfn,reg,len,value);
spin_lock_irqsave(&pci_config_lock, flags);
pci_exp_set_dev_base(base, bus, devfn);
switch (len) {
case 1:
mmio_config_writeb(mmcfg_virt_addr + reg, value);
break;
case 2:
mmio_config_writew(mmcfg_virt_addr + reg, value);
break;
case 4:
mmio_config_writel(mmcfg_virt_addr + reg, value);
break;
}
spin_unlock_irqrestore(&pci_config_lock, flags);
return 0;
}
static struct pci_raw_ops pci_mmcfg = {
.read = pci_mmcfg_read,
.write = pci_mmcfg_write,
};
int __init pci_mmcfg_arch_reachable(unsigned int seg, unsigned int bus,
unsigned int devfn)
{
return get_base_addr(seg, bus, devfn) != 0;
}
int __init pci_mmcfg_arch_init(void)
{
printk(KERN_INFO "PCI: Using MMCONFIG\n");
raw_pci_ops = &pci_mmcfg;
return 1;
}