1
0
Fork 0
alistair23-linux/drivers/watchdog/hpwdt.c

905 lines
22 KiB
C
Raw Normal View History

/*
* HP WatchDog Driver
* based on
*
* SoftDog 0.05: A Software Watchdog Device
*
* (c) Copyright 2007 Hewlett-Packard Development Company, L.P.
* Thomas Mingarelli <thomas.mingarelli@hp.com>
*
* 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
*
*/
#include <linux/device.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/io.h>
#include <linux/bitops.h>
#include <linux/kernel.h>
#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/pci.h>
#include <linux/pci_ids.h>
#include <linux/types.h>
#include <linux/uaccess.h>
#include <linux/watchdog.h>
#ifdef CONFIG_HPWDT_NMI_DECODING
#include <linux/dmi.h>
#include <linux/spinlock.h>
#include <linux/nmi.h>
#include <linux/kdebug.h>
#include <linux/notifier.h>
[WATCHDOG] hpwdt: set the mapped BIOS address space as executable The address provided by the SMBIOS/DMI CRU information is mapped via ioremap() in the virtual address space. However, since the address is executed (i.e. call'd), we need to set that pages as executable. Without that, I get following oops on a HP ProLiant DL385 G2 machine with BIOS from 05/29/2008 when I trigger crashdump: BUG: unable to handle kernel paging request at ffffc20011090c00 IP: [<ffffc20011090c00>] 0xffffc20011090c00 PGD 12f813067 PUD 7fe6a067 PMD 7effe067 PTE 80000000fffd3173 Oops: 0011 [1] SMP last sysfs file: /sys/devices/system/cpu/cpu3/cache/index2/shared_cpu_map CPU 1 Modules linked in: autofs4 ipv6 af_packet cpufreq_conservative cpufreq_userspace cpufreq_powersave powernow_k8 fuse loop dm_mod rtc_cmos ipmi_si sg rtc_core i2c _piix4 ipmi_msghandler bnx2 sr_mod container button i2c_core hpilo joydev pcspkr rtc_lib shpchp hpwdt cdrom pci_hotplug usbhid hid ff_memless ohci_hcd ehci_hcd uhci_hcd usbcore edd ext3 mbcache jbd fan ide_pci_generic serverworks ide_core p ata_serverworks pata_acpi cciss ata_generic libata scsi_mod dock thermal process or thermal_sys hwmon Supported: Yes Pid: 0, comm: swapper Not tainted 2.6.27.5-HEAD_20081111100657-default #1 RIP: 0010:[<ffffc20011090c00>] [<ffffc20011090c00>] 0xffffc20011090c00 RSP: 0018:ffff88012f6f9e68 EFLAGS: 00010046 RAX: 0000000000000d02 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffff88012f6f9e98 R08: 666666666666660a R09: ffffffffa1006fc0 R10: 0000000000000000 R11: ffff88012f6f3ea8 R12: ffffc20011090c00 R13: ffff88012f6f9ee8 R14: 000000000000000e R15: 0000000000000000 FS: 00007ff70b29a6f0(0000) GS:ffff88012f6512c0(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: ffffc20011090c00 CR3: 0000000000201000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper (pid: 0, threadinfo ffff88012f6f2000, task ffff88007fa8a1c0) Stack: ffffffffa0f8502b 0000000000000002 ffffffff80738d50 0000000000000000 0000000000000046 0000000000000046 00000000fffffffe ffffffffa0f852ec 0000000000000000 ffffffff804ad9a6 0000000000000000 0000000000000000 Call Trace: Inexact backtrace: <NMI> [<ffffffffa0f8502b>] ? asminline_call+0x2b/0x55 [hpwdt] [<ffffffffa0f852ec>] hpwdt_pretimeout+0x3c/0xa0 [hpwdt] [<ffffffff804ad9a6>] ? notifier_call_chain+0x29/0x4c [<ffffffff802587e4>] ? notify_die+0x2d/0x32 [<ffffffff804abbdc>] ? default_do_nmi+0x53/0x1d9 [<ffffffff804abd90>] ? do_nmi+0x2e/0x43 [<ffffffff804ab552>] ? nmi+0xa2/0xd0 [<ffffffff80221ef9>] ? native_safe_halt+0x2/0x3 <<EOE>> [<ffffffff8021345d>] ? default_idle+0x38/0x54 [<ffffffff8021359a>] ? c1e_idle+0x118/0x11c [<ffffffff8020b3b5>] ? cpu_idle+0xa9/0xf1 Code: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff <55> 50 e8 00 00 00 00 58 48 2d 07 10 40 00 48 8b e8 58 e9 68 02 RIP [<ffffc20011090c00>] 0xffffc20011090c00 RSP <ffff88012f6f9e68> CR2: ffffc20011090c00 Kernel panic - not syncing: Fatal exception Signed-off-by: Bernhard Walle <bwalle@suse.de> Signed-off-by: Wim Van Sebroeck <wim@iguana.be> Cc: Ingo Molnar <mingo@elte.hu> Acked-by: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Thomas Mingarelli <Thomas.Mingarelli@hp.com> Cc: Alan Cox <alan@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2008-11-14 07:47:03 -07:00
#include <asm/cacheflush.h>
#endif /* CONFIG_HPWDT_NMI_DECODING */
#define HPWDT_VERSION "1.3.0"
#define SECS_TO_TICKS(secs) ((secs) * 1000 / 128)
#define TICKS_TO_SECS(ticks) ((ticks) * 128 / 1000)
#define HPWDT_MAX_TIMER TICKS_TO_SECS(65535)
#define DEFAULT_MARGIN 30
static unsigned int soft_margin = DEFAULT_MARGIN; /* in seconds */
static unsigned int reload; /* the computed soft_margin */
static int nowayout = WATCHDOG_NOWAYOUT;
static char expect_release;
static unsigned long hpwdt_is_open;
static void __iomem *pci_mem_addr; /* the PCI-memory address */
static unsigned long __iomem *hpwdt_timer_reg;
static unsigned long __iomem *hpwdt_timer_con;
static DEFINE_PCI_DEVICE_TABLE(hpwdt_devices) = {
{ PCI_DEVICE(PCI_VENDOR_ID_COMPAQ, 0xB203) }, /* iLO2 */
{ PCI_DEVICE(PCI_VENDOR_ID_HP, 0x3306) }, /* iLO3 */
{0}, /* terminate list */
};
MODULE_DEVICE_TABLE(pci, hpwdt_devices);
#ifdef CONFIG_HPWDT_NMI_DECODING
#define PCI_BIOS32_SD_VALUE 0x5F32335F /* "_32_" */
#define CRU_BIOS_SIGNATURE_VALUE 0x55524324
#define PCI_BIOS32_PARAGRAPH_LEN 16
#define PCI_ROM_BASE1 0x000F0000
#define ROM_SIZE 0x10000
struct bios32_service_dir {
u32 signature;
u32 entry_point;
u8 revision;
u8 length;
u8 checksum;
u8 reserved[5];
};
/* type 212 */
struct smbios_cru64_info {
u8 type;
u8 byte_length;
u16 handle;
u32 signature;
u64 physical_address;
u32 double_length;
u32 double_offset;
};
#define SMBIOS_CRU64_INFORMATION 212
/* type 219 */
struct smbios_proliant_info {
u8 type;
u8 byte_length;
u16 handle;
u32 power_features;
u32 omega_features;
u32 reserved;
u32 misc_features;
};
#define SMBIOS_ICRU_INFORMATION 219
struct cmn_registers {
union {
struct {
u8 ral;
u8 rah;
u16 rea2;
};
u32 reax;
} u1;
union {
struct {
u8 rbl;
u8 rbh;
u8 reb2l;
u8 reb2h;
};
u32 rebx;
} u2;
union {
struct {
u8 rcl;
u8 rch;
u16 rec2;
};
u32 recx;
} u3;
union {
struct {
u8 rdl;
u8 rdh;
u16 red2;
};
u32 redx;
} u4;
u32 resi;
u32 redi;
u16 rds;
u16 res;
u32 reflags;
} __attribute__((packed));
static unsigned int hpwdt_nmi_decoding;
static unsigned int allow_kdump;
static unsigned int priority; /* hpwdt at end of die_notify list */
static unsigned int is_icru;
static DEFINE_SPINLOCK(rom_lock);
static void *cru_rom_addr;
static struct cmn_registers cmn_regs;
extern asmlinkage void asminline_call(struct cmn_registers *pi86Regs,
unsigned long *pRomEntry);
#ifdef CONFIG_X86_32
/* --32 Bit Bios------------------------------------------------------------ */
#define HPWDT_ARCH 32
asm(".text \n\t"
".align 4 \n"
"asminline_call: \n\t"
"pushl %ebp \n\t"
"movl %esp, %ebp \n\t"
"pusha \n\t"
"pushf \n\t"
"push %es \n\t"
"push %ds \n\t"
"pop %es \n\t"
"movl 8(%ebp),%eax \n\t"
"movl 4(%eax),%ebx \n\t"
"movl 8(%eax),%ecx \n\t"
"movl 12(%eax),%edx \n\t"
"movl 16(%eax),%esi \n\t"
"movl 20(%eax),%edi \n\t"
"movl (%eax),%eax \n\t"
"push %cs \n\t"
"call *12(%ebp) \n\t"
"pushf \n\t"
"pushl %eax \n\t"
"movl 8(%ebp),%eax \n\t"
"movl %ebx,4(%eax) \n\t"
"movl %ecx,8(%eax) \n\t"
"movl %edx,12(%eax) \n\t"
"movl %esi,16(%eax) \n\t"
"movl %edi,20(%eax) \n\t"
"movw %ds,24(%eax) \n\t"
"movw %es,26(%eax) \n\t"
"popl %ebx \n\t"
"movl %ebx,(%eax) \n\t"
"popl %ebx \n\t"
"movl %ebx,28(%eax) \n\t"
"pop %es \n\t"
"popf \n\t"
"popa \n\t"
"leave \n\t"
"ret \n\t"
".previous");
/*
* cru_detect
*
* Routine Description:
* This function uses the 32-bit BIOS Service Directory record to
* search for a $CRU record.
*
* Return Value:
* 0 : SUCCESS
* <0 : FAILURE
*/
static int __devinit cru_detect(unsigned long map_entry,
unsigned long map_offset)
{
void *bios32_map;
unsigned long *bios32_entrypoint;
unsigned long cru_physical_address;
unsigned long cru_length;
unsigned long physical_bios_base = 0;
unsigned long physical_bios_offset = 0;
int retval = -ENODEV;
bios32_map = ioremap(map_entry, (2 * PAGE_SIZE));
if (bios32_map == NULL)
return -ENODEV;
bios32_entrypoint = bios32_map + map_offset;
cmn_regs.u1.reax = CRU_BIOS_SIGNATURE_VALUE;
asminline_call(&cmn_regs, bios32_entrypoint);
if (cmn_regs.u1.ral != 0) {
printk(KERN_WARNING
"hpwdt: Call succeeded but with an error: 0x%x\n",
cmn_regs.u1.ral);
} else {
physical_bios_base = cmn_regs.u2.rebx;
physical_bios_offset = cmn_regs.u4.redx;
cru_length = cmn_regs.u3.recx;
cru_physical_address =
physical_bios_base + physical_bios_offset;
/* If the values look OK, then map it in. */
if ((physical_bios_base + physical_bios_offset)) {
cru_rom_addr =
ioremap(cru_physical_address, cru_length);
if (cru_rom_addr)
retval = 0;
}
printk(KERN_DEBUG "hpwdt: CRU Base Address: 0x%lx\n",
physical_bios_base);
printk(KERN_DEBUG "hpwdt: CRU Offset Address: 0x%lx\n",
physical_bios_offset);
printk(KERN_DEBUG "hpwdt: CRU Length: 0x%lx\n",
cru_length);
printk(KERN_DEBUG "hpwdt: CRU Mapped Address: %p\n",
&cru_rom_addr);
}
iounmap(bios32_map);
return retval;
}
/*
* bios_checksum
*/
static int __devinit bios_checksum(const char __iomem *ptr, int len)
{
char sum = 0;
int i;
/*
* calculate checksum of size bytes. This should add up
* to zero if we have a valid header.
*/
for (i = 0; i < len; i++)
sum += ptr[i];
return ((sum == 0) && (len > 0));
}
/*
* bios32_present
*
* Routine Description:
* This function finds the 32-bit BIOS Service Directory
*
* Return Value:
* 0 : SUCCESS
* <0 : FAILURE
*/
static int __devinit bios32_present(const char __iomem *p)
{
struct bios32_service_dir *bios_32_ptr;
int length;
unsigned long map_entry, map_offset;
bios_32_ptr = (struct bios32_service_dir *) p;
/*
* Search for signature by checking equal to the swizzled value
* instead of calling another routine to perform a strcmp.
*/
if (bios_32_ptr->signature == PCI_BIOS32_SD_VALUE) {
length = bios_32_ptr->length * PCI_BIOS32_PARAGRAPH_LEN;
if (bios_checksum(p, length)) {
/*
* According to the spec, we're looking for the
* first 4KB-aligned address below the entrypoint
* listed in the header. The Service Directory code
* is guaranteed to occupy no more than 2 4KB pages.
*/
map_entry = bios_32_ptr->entry_point & ~(PAGE_SIZE - 1);
map_offset = bios_32_ptr->entry_point - map_entry;
return cru_detect(map_entry, map_offset);
}
}
return -ENODEV;
}
static int __devinit detect_cru_service(void)
{
char __iomem *p, *q;
int rc = -1;
/*
* Search from 0x0f0000 through 0x0fffff, inclusive.
*/
p = ioremap(PCI_ROM_BASE1, ROM_SIZE);
if (p == NULL)
return -ENOMEM;
for (q = p; q < p + ROM_SIZE; q += 16) {
rc = bios32_present(q);
if (!rc)
break;
}
iounmap(p);
return rc;
}
/* ------------------------------------------------------------------------- */
#endif /* CONFIG_X86_32 */
#ifdef CONFIG_X86_64
/* --64 Bit Bios------------------------------------------------------------ */
#define HPWDT_ARCH 64
asm(".text \n\t"
".align 4 \n"
"asminline_call: \n\t"
"pushq %rbp \n\t"
"movq %rsp, %rbp \n\t"
"pushq %rax \n\t"
"pushq %rbx \n\t"
"pushq %rdx \n\t"
"pushq %r12 \n\t"
"pushq %r9 \n\t"
"movq %rsi, %r12 \n\t"
"movq %rdi, %r9 \n\t"
"movl 4(%r9),%ebx \n\t"
"movl 8(%r9),%ecx \n\t"
"movl 12(%r9),%edx \n\t"
"movl 16(%r9),%esi \n\t"
"movl 20(%r9),%edi \n\t"
"movl (%r9),%eax \n\t"
"call *%r12 \n\t"
"pushfq \n\t"
"popq %r12 \n\t"
"movl %eax, (%r9) \n\t"
"movl %ebx, 4(%r9) \n\t"
"movl %ecx, 8(%r9) \n\t"
"movl %edx, 12(%r9) \n\t"
"movl %esi, 16(%r9) \n\t"
"movl %edi, 20(%r9) \n\t"
"movq %r12, %rax \n\t"
"movl %eax, 28(%r9) \n\t"
"popq %r9 \n\t"
"popq %r12 \n\t"
"popq %rdx \n\t"
"popq %rbx \n\t"
"popq %rax \n\t"
"leave \n\t"
"ret \n\t"
".previous");
/*
* dmi_find_cru
*
* Routine Description:
* This function checks whether or not a SMBIOS/DMI record is
* the 64bit CRU info or not
*/
static void __devinit dmi_find_cru(const struct dmi_header *dm, void *dummy)
{
struct smbios_cru64_info *smbios_cru64_ptr;
unsigned long cru_physical_address;
if (dm->type == SMBIOS_CRU64_INFORMATION) {
smbios_cru64_ptr = (struct smbios_cru64_info *) dm;
if (smbios_cru64_ptr->signature == CRU_BIOS_SIGNATURE_VALUE) {
cru_physical_address =
smbios_cru64_ptr->physical_address +
smbios_cru64_ptr->double_offset;
cru_rom_addr = ioremap(cru_physical_address,
smbios_cru64_ptr->double_length);
[WATCHDOG] hpwdt: set the mapped BIOS address space as executable The address provided by the SMBIOS/DMI CRU information is mapped via ioremap() in the virtual address space. However, since the address is executed (i.e. call'd), we need to set that pages as executable. Without that, I get following oops on a HP ProLiant DL385 G2 machine with BIOS from 05/29/2008 when I trigger crashdump: BUG: unable to handle kernel paging request at ffffc20011090c00 IP: [<ffffc20011090c00>] 0xffffc20011090c00 PGD 12f813067 PUD 7fe6a067 PMD 7effe067 PTE 80000000fffd3173 Oops: 0011 [1] SMP last sysfs file: /sys/devices/system/cpu/cpu3/cache/index2/shared_cpu_map CPU 1 Modules linked in: autofs4 ipv6 af_packet cpufreq_conservative cpufreq_userspace cpufreq_powersave powernow_k8 fuse loop dm_mod rtc_cmos ipmi_si sg rtc_core i2c _piix4 ipmi_msghandler bnx2 sr_mod container button i2c_core hpilo joydev pcspkr rtc_lib shpchp hpwdt cdrom pci_hotplug usbhid hid ff_memless ohci_hcd ehci_hcd uhci_hcd usbcore edd ext3 mbcache jbd fan ide_pci_generic serverworks ide_core p ata_serverworks pata_acpi cciss ata_generic libata scsi_mod dock thermal process or thermal_sys hwmon Supported: Yes Pid: 0, comm: swapper Not tainted 2.6.27.5-HEAD_20081111100657-default #1 RIP: 0010:[<ffffc20011090c00>] [<ffffc20011090c00>] 0xffffc20011090c00 RSP: 0018:ffff88012f6f9e68 EFLAGS: 00010046 RAX: 0000000000000d02 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffff88012f6f9e98 R08: 666666666666660a R09: ffffffffa1006fc0 R10: 0000000000000000 R11: ffff88012f6f3ea8 R12: ffffc20011090c00 R13: ffff88012f6f9ee8 R14: 000000000000000e R15: 0000000000000000 FS: 00007ff70b29a6f0(0000) GS:ffff88012f6512c0(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: ffffc20011090c00 CR3: 0000000000201000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper (pid: 0, threadinfo ffff88012f6f2000, task ffff88007fa8a1c0) Stack: ffffffffa0f8502b 0000000000000002 ffffffff80738d50 0000000000000000 0000000000000046 0000000000000046 00000000fffffffe ffffffffa0f852ec 0000000000000000 ffffffff804ad9a6 0000000000000000 0000000000000000 Call Trace: Inexact backtrace: <NMI> [<ffffffffa0f8502b>] ? asminline_call+0x2b/0x55 [hpwdt] [<ffffffffa0f852ec>] hpwdt_pretimeout+0x3c/0xa0 [hpwdt] [<ffffffff804ad9a6>] ? notifier_call_chain+0x29/0x4c [<ffffffff802587e4>] ? notify_die+0x2d/0x32 [<ffffffff804abbdc>] ? default_do_nmi+0x53/0x1d9 [<ffffffff804abd90>] ? do_nmi+0x2e/0x43 [<ffffffff804ab552>] ? nmi+0xa2/0xd0 [<ffffffff80221ef9>] ? native_safe_halt+0x2/0x3 <<EOE>> [<ffffffff8021345d>] ? default_idle+0x38/0x54 [<ffffffff8021359a>] ? c1e_idle+0x118/0x11c [<ffffffff8020b3b5>] ? cpu_idle+0xa9/0xf1 Code: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff <55> 50 e8 00 00 00 00 58 48 2d 07 10 40 00 48 8b e8 58 e9 68 02 RIP [<ffffc20011090c00>] 0xffffc20011090c00 RSP <ffff88012f6f9e68> CR2: ffffc20011090c00 Kernel panic - not syncing: Fatal exception Signed-off-by: Bernhard Walle <bwalle@suse.de> Signed-off-by: Wim Van Sebroeck <wim@iguana.be> Cc: Ingo Molnar <mingo@elte.hu> Acked-by: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Thomas Mingarelli <Thomas.Mingarelli@hp.com> Cc: Alan Cox <alan@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2008-11-14 07:47:03 -07:00
set_memory_x((unsigned long)cru_rom_addr & PAGE_MASK,
smbios_cru64_ptr->double_length >> PAGE_SHIFT);
}
}
}
static int __devinit detect_cru_service(void)
{
cru_rom_addr = NULL;
dmi_walk(dmi_find_cru, NULL);
/* if cru_rom_addr has been set then we found a CRU service */
return ((cru_rom_addr != NULL) ? 0 : -ENODEV);
}
/* ------------------------------------------------------------------------- */
#endif /* CONFIG_X86_64 */
#endif /* CONFIG_HPWDT_NMI_DECODING */
/*
* Watchdog operations
*/
static void hpwdt_start(void)
{
reload = SECS_TO_TICKS(soft_margin);
iowrite16(reload, hpwdt_timer_reg);
iowrite16(0x85, hpwdt_timer_con);
}
static void hpwdt_stop(void)
{
unsigned long data;
data = ioread16(hpwdt_timer_con);
data &= 0xFE;
iowrite16(data, hpwdt_timer_con);
}
static void hpwdt_ping(void)
{
iowrite16(reload, hpwdt_timer_reg);
}
static int hpwdt_change_timer(int new_margin)
{
if (new_margin < 1 || new_margin > HPWDT_MAX_TIMER) {
printk(KERN_WARNING
"hpwdt: New value passed in is invalid: %d seconds.\n",
new_margin);
return -EINVAL;
}
soft_margin = new_margin;
printk(KERN_DEBUG
"hpwdt: New timer passed in is %d seconds.\n",
new_margin);
reload = SECS_TO_TICKS(soft_margin);
return 0;
}
static int hpwdt_time_left(void)
{
return TICKS_TO_SECS(ioread16(hpwdt_timer_reg));
}
#ifdef CONFIG_HPWDT_NMI_DECODING
/*
* NMI Handler
*/
static int hpwdt_pretimeout(struct notifier_block *nb, unsigned long ulReason,
void *data)
{
unsigned long rom_pl;
static int die_nmi_called;
if (ulReason != DIE_NMIUNKNOWN)
goto out;
if (!hpwdt_nmi_decoding)
goto out;
spin_lock_irqsave(&rom_lock, rom_pl);
if (!die_nmi_called && !is_icru)
asminline_call(&cmn_regs, cru_rom_addr);
die_nmi_called = 1;
spin_unlock_irqrestore(&rom_lock, rom_pl);
if (!is_icru) {
if (cmn_regs.u1.ral == 0) {
printk(KERN_WARNING "hpwdt: An NMI occurred, "
"but unable to determine source.\n");
}
}
if (allow_kdump)
hpwdt_stop();
panic("An NMI occurred, please see the Integrated "
"Management Log for details.\n");
out:
return NOTIFY_OK;
}
#endif /* CONFIG_HPWDT_NMI_DECODING */
/*
* /dev/watchdog handling
*/
static int hpwdt_open(struct inode *inode, struct file *file)
{
/* /dev/watchdog can only be opened once */
if (test_and_set_bit(0, &hpwdt_is_open))
return -EBUSY;
/* Start the watchdog */
hpwdt_start();
hpwdt_ping();
return nonseekable_open(inode, file);
}
static int hpwdt_release(struct inode *inode, struct file *file)
{
/* Stop the watchdog */
if (expect_release == 42) {
hpwdt_stop();
} else {
printk(KERN_CRIT
"hpwdt: Unexpected close, not stopping watchdog!\n");
hpwdt_ping();
}
expect_release = 0;
/* /dev/watchdog is being closed, make sure it can be re-opened */
clear_bit(0, &hpwdt_is_open);
return 0;
}
static ssize_t hpwdt_write(struct file *file, const char __user *data,
size_t len, loff_t *ppos)
{
/* See if we got the magic character 'V' and reload the timer */
if (len) {
if (!nowayout) {
size_t i;
/* note: just in case someone wrote the magic character
* five months ago... */
expect_release = 0;
/* scan to see whether or not we got the magic char. */
for (i = 0; i != len; i++) {
char c;
if (get_user(c, data + i))
return -EFAULT;
if (c == 'V')
expect_release = 42;
}
}
/* someone wrote to us, we should reload the timer */
hpwdt_ping();
}
return len;
}
static const struct watchdog_info ident = {
.options = WDIOF_SETTIMEOUT |
WDIOF_KEEPALIVEPING |
WDIOF_MAGICCLOSE,
.identity = "HP iLO2+ HW Watchdog Timer",
};
static long hpwdt_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
void __user *argp = (void __user *)arg;
int __user *p = argp;
int new_margin;
int ret = -ENOTTY;
switch (cmd) {
case WDIOC_GETSUPPORT:
ret = 0;
if (copy_to_user(argp, &ident, sizeof(ident)))
ret = -EFAULT;
break;
case WDIOC_GETSTATUS:
case WDIOC_GETBOOTSTATUS:
ret = put_user(0, p);
break;
case WDIOC_KEEPALIVE:
hpwdt_ping();
ret = 0;
break;
case WDIOC_SETTIMEOUT:
ret = get_user(new_margin, p);
if (ret)
break;
ret = hpwdt_change_timer(new_margin);
if (ret)
break;
hpwdt_ping();
/* Fall */
case WDIOC_GETTIMEOUT:
ret = put_user(soft_margin, p);
break;
case WDIOC_GETTIMELEFT:
ret = put_user(hpwdt_time_left(), p);
break;
}
return ret;
}
/*
* Kernel interfaces
*/
static const struct file_operations hpwdt_fops = {
.owner = THIS_MODULE,
.llseek = no_llseek,
.write = hpwdt_write,
.unlocked_ioctl = hpwdt_ioctl,
.open = hpwdt_open,
.release = hpwdt_release,
};
static struct miscdevice hpwdt_miscdev = {
.minor = WATCHDOG_MINOR,
.name = "watchdog",
.fops = &hpwdt_fops,
};
#ifdef CONFIG_HPWDT_NMI_DECODING
static struct notifier_block die_notifier = {
.notifier_call = hpwdt_pretimeout,
.priority = 0,
};
#endif /* CONFIG_HPWDT_NMI_DECODING */
/*
* Init & Exit
*/
#ifdef CONFIG_HPWDT_NMI_DECODING
x86, nmi_watchdog: Remove ARCH_HAS_NMI_WATCHDOG and rely on CONFIG_HARDLOCKUP_DETECTOR The x86 arch has shifted its use of the nmi_watchdog from a local implementation to the global one provide by kernel/watchdog.c. This shift has caused a whole bunch of compile problems under different config options. I attempt to simplify things with the patch below. In order to simplify things, I had to come to terms with the meaning of two terms ARCH_HAS_NMI_WATCHDOG and CONFIG_HARDLOCKUP_DETECTOR. Basically they mean the same thing, the former on a local level and the latter on a global level. With the old x86 nmi watchdog gone, there is no need to rely on defining the ARCH_HAS_NMI_WATCHDOG variable because it doesn't make sense any more. x86 will now use the global implementation. The changes below do a few things. First it changes the few places that relied on ARCH_HAS_NMI_WATCHDOG to use CONFIG_X86_LOCAL_APIC (the former was an alias for the latter anyway, so nothing unusual here). Those pieces of code were relying more on local apic functionality the nmi watchdog functionality, so the change should make sense. Second, I removed the x86 implementation of touch_nmi_watchdog(). It isn't need now, instead x86 will rely on kernel/watchdog.c's implementation. Third, I removed the #define ARCH_HAS_NMI_WATCHDOG itself from x86. And tweaked the include/linux/nmi.h file to tell users to look for an externally defined touch_nmi_watchdog in the case of ARCH_HAS_NMI_WATCHDOG _or_ CONFIG_HARDLOCKUP_DETECTOR. This changes removes some of the ugliness in that file. Finally, I added a Kconfig dependency for CONFIG_HARDLOCKUP_DETECTOR that said you can't have ARCH_HAS_NMI_WATCHDOG _and_ CONFIG_HARDLOCKUP_DETECTOR. You can only have one nmi_watchdog. Tested with ARCH=i386: allnoconfig, defconfig, allyesconfig, (various broken configs) ARCH=x86_64: allnoconfig, defconfig, allyesconfig, (various broken configs) Hopefully, after this patch I won't get any more compile broken emails. :-) v3: changed a couple of 'linux/nmi.h' -> 'asm/nmi.h' to pick-up correct function prototypes when CONFIG_HARDLOCKUP_DETECTOR is not set. Signed-off-by: Don Zickus <dzickus@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com LKML-Reference: <1293044403-14117-1-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-12-22 12:00:03 -07:00
#ifdef CONFIG_X86_LOCAL_APIC
static void __devinit hpwdt_check_nmi_decoding(struct pci_dev *dev)
{
/*
* If nmi_watchdog is turned off then we can turn on
* our nmi decoding capability.
*/
hpwdt_nmi_decoding = 1;
}
#else
static void __devinit hpwdt_check_nmi_decoding(struct pci_dev *dev)
{
dev_warn(&dev->dev, "NMI decoding is disabled. "
"Your kernel does not support a NMI Watchdog.\n");
}
x86, nmi_watchdog: Remove ARCH_HAS_NMI_WATCHDOG and rely on CONFIG_HARDLOCKUP_DETECTOR The x86 arch has shifted its use of the nmi_watchdog from a local implementation to the global one provide by kernel/watchdog.c. This shift has caused a whole bunch of compile problems under different config options. I attempt to simplify things with the patch below. In order to simplify things, I had to come to terms with the meaning of two terms ARCH_HAS_NMI_WATCHDOG and CONFIG_HARDLOCKUP_DETECTOR. Basically they mean the same thing, the former on a local level and the latter on a global level. With the old x86 nmi watchdog gone, there is no need to rely on defining the ARCH_HAS_NMI_WATCHDOG variable because it doesn't make sense any more. x86 will now use the global implementation. The changes below do a few things. First it changes the few places that relied on ARCH_HAS_NMI_WATCHDOG to use CONFIG_X86_LOCAL_APIC (the former was an alias for the latter anyway, so nothing unusual here). Those pieces of code were relying more on local apic functionality the nmi watchdog functionality, so the change should make sense. Second, I removed the x86 implementation of touch_nmi_watchdog(). It isn't need now, instead x86 will rely on kernel/watchdog.c's implementation. Third, I removed the #define ARCH_HAS_NMI_WATCHDOG itself from x86. And tweaked the include/linux/nmi.h file to tell users to look for an externally defined touch_nmi_watchdog in the case of ARCH_HAS_NMI_WATCHDOG _or_ CONFIG_HARDLOCKUP_DETECTOR. This changes removes some of the ugliness in that file. Finally, I added a Kconfig dependency for CONFIG_HARDLOCKUP_DETECTOR that said you can't have ARCH_HAS_NMI_WATCHDOG _and_ CONFIG_HARDLOCKUP_DETECTOR. You can only have one nmi_watchdog. Tested with ARCH=i386: allnoconfig, defconfig, allyesconfig, (various broken configs) ARCH=x86_64: allnoconfig, defconfig, allyesconfig, (various broken configs) Hopefully, after this patch I won't get any more compile broken emails. :-) v3: changed a couple of 'linux/nmi.h' -> 'asm/nmi.h' to pick-up correct function prototypes when CONFIG_HARDLOCKUP_DETECTOR is not set. Signed-off-by: Don Zickus <dzickus@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: fweisbec@gmail.com LKML-Reference: <1293044403-14117-1-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-12-22 12:00:03 -07:00
#endif /* CONFIG_X86_LOCAL_APIC */
/*
* dmi_find_icru
*
* Routine Description:
* This function checks whether or not we are on an iCRU-based server.
* This check is independent of architecture and needs to be made for
* any ProLiant system.
*/
static void __devinit dmi_find_icru(const struct dmi_header *dm, void *dummy)
{
struct smbios_proliant_info *smbios_proliant_ptr;
if (dm->type == SMBIOS_ICRU_INFORMATION) {
smbios_proliant_ptr = (struct smbios_proliant_info *) dm;
if (smbios_proliant_ptr->misc_features & 0x01)
is_icru = 1;
}
}
static int __devinit hpwdt_init_nmi_decoding(struct pci_dev *dev)
{
int retval;
/*
* On typical CRU-based systems we need to map that service in
* the BIOS. For 32 bit Operating Systems we need to go through
* the 32 Bit BIOS Service Directory. For 64 bit Operating
* Systems we get that service through SMBIOS.
*
* On systems that support the new iCRU service all we need to
* do is call dmi_walk to get the supported flag value and skip
* the old cru detect code.
*/
dmi_walk(dmi_find_icru, NULL);
if (!is_icru) {
/*
* We need to map the ROM to get the CRU service.
* For 32 bit Operating Systems we need to go through the 32 Bit
* BIOS Service Directory
* For 64 bit Operating Systems we get that service through SMBIOS.
*/
retval = detect_cru_service();
if (retval < 0) {
dev_warn(&dev->dev,
"Unable to detect the %d Bit CRU Service.\n",
HPWDT_ARCH);
return retval;
}
/*
* We know this is the only CRU call we need to make so lets keep as
* few instructions as possible once the NMI comes in.
*/
cmn_regs.u1.rah = 0x0D;
cmn_regs.u1.ral = 0x02;
}
/*
* If the priority is set to 1, then we will be put first on the
* die notify list to handle a critical NMI. The default is to
* be last so other users of the NMI signal can function.
*/
if (priority)
die_notifier.priority = 0x7FFFFFFF;
retval = register_die_notifier(&die_notifier);
if (retval != 0) {
dev_warn(&dev->dev,
"Unable to register a die notifier (err=%d).\n",
retval);
if (cru_rom_addr)
iounmap(cru_rom_addr);
}
dev_info(&dev->dev,
"HP Watchdog Timer Driver: NMI decoding initialized"
", allow kernel dump: %s (default = 0/OFF)"
", priority: %s (default = 0/LAST).\n",
(allow_kdump == 0) ? "OFF" : "ON",
(priority == 0) ? "LAST" : "FIRST");
return 0;
}
static void hpwdt_exit_nmi_decoding(void)
{
unregister_die_notifier(&die_notifier);
if (cru_rom_addr)
iounmap(cru_rom_addr);
}
#else /* !CONFIG_HPWDT_NMI_DECODING */
static void __devinit hpwdt_check_nmi_decoding(struct pci_dev *dev)
{
}
static int __devinit hpwdt_init_nmi_decoding(struct pci_dev *dev)
{
return 0;
}
static void hpwdt_exit_nmi_decoding(void)
{
}
#endif /* CONFIG_HPWDT_NMI_DECODING */
static int __devinit hpwdt_init_one(struct pci_dev *dev,
const struct pci_device_id *ent)
{
int retval;
/*
* Check if we can do NMI decoding or not
*/
hpwdt_check_nmi_decoding(dev);
/*
* First let's find out if we are on an iLO2+ server. We will
* not run on a legacy ASM box.
* So we only support the G5 ProLiant servers and higher.
*/
if (dev->subsystem_vendor != PCI_VENDOR_ID_HP) {
dev_warn(&dev->dev,
"This server does not have an iLO2+ ASIC.\n");
return -ENODEV;
}
if (pci_enable_device(dev)) {
dev_warn(&dev->dev,
"Not possible to enable PCI Device: 0x%x:0x%x.\n",
ent->vendor, ent->device);
return -ENODEV;
}
pci_mem_addr = pci_iomap(dev, 1, 0x80);
if (!pci_mem_addr) {
dev_warn(&dev->dev,
"Unable to detect the iLO2+ server memory.\n");
retval = -ENOMEM;
goto error_pci_iomap;
}
hpwdt_timer_reg = pci_mem_addr + 0x70;
hpwdt_timer_con = pci_mem_addr + 0x72;
/* Make sure that we have a valid soft_margin */
if (hpwdt_change_timer(soft_margin))
hpwdt_change_timer(DEFAULT_MARGIN);
/* Initialize NMI Decoding functionality */
retval = hpwdt_init_nmi_decoding(dev);
if (retval != 0)
goto error_init_nmi_decoding;
retval = misc_register(&hpwdt_miscdev);
if (retval < 0) {
dev_warn(&dev->dev,
"Unable to register miscdev on minor=%d (err=%d).\n",
WATCHDOG_MINOR, retval);
goto error_misc_register;
}
dev_info(&dev->dev, "HP Watchdog Timer Driver: %s"
", timer margin: %d seconds (nowayout=%d).\n",
HPWDT_VERSION, soft_margin, nowayout);
return 0;
error_misc_register:
hpwdt_exit_nmi_decoding();
error_init_nmi_decoding:
pci_iounmap(dev, pci_mem_addr);
error_pci_iomap:
pci_disable_device(dev);
return retval;
}
static void __devexit hpwdt_exit(struct pci_dev *dev)
{
if (!nowayout)
hpwdt_stop();
misc_deregister(&hpwdt_miscdev);
hpwdt_exit_nmi_decoding();
pci_iounmap(dev, pci_mem_addr);
pci_disable_device(dev);
}
static struct pci_driver hpwdt_driver = {
.name = "hpwdt",
.id_table = hpwdt_devices,
.probe = hpwdt_init_one,
.remove = __devexit_p(hpwdt_exit),
};
static void __exit hpwdt_cleanup(void)
{
pci_unregister_driver(&hpwdt_driver);
}
static int __init hpwdt_init(void)
{
return pci_register_driver(&hpwdt_driver);
}
MODULE_AUTHOR("Tom Mingarelli");
MODULE_DESCRIPTION("hp watchdog driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(HPWDT_VERSION);
MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR);
module_param(soft_margin, int, 0);
MODULE_PARM_DESC(soft_margin, "Watchdog timeout in seconds");
module_param(nowayout, int, 0);
MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
#ifdef CONFIG_HPWDT_NMI_DECODING
module_param(allow_kdump, int, 0);
MODULE_PARM_DESC(allow_kdump, "Start a kernel dump after NMI occurs");
module_param(priority, int, 0);
MODULE_PARM_DESC(priority, "The hpwdt driver handles NMIs first or last"
" (default = 0/Last)\n");
#endif /* !CONFIG_HPWDT_NMI_DECODING */
module_init(hpwdt_init);
module_exit(hpwdt_cleanup);