On Thu, Jun 08, 2006 at 06:48:23AM +0800, Zou Nan hai wrote:
> The ia64 kdump patch is in 2 parts.
>
> the kexec-kdump-ia64-2.6.16.patch should apply on top of the previous
> kexec patch by Khalid in Tony's test tree.
>
> the kexec-tools-kdump-ia64.patch should apply to kexec-tools-1.101
> with kexec-tools-1.101-kdump.patch
>
>
> To test it.
> Build first SMP kernel with KEXEC and KDUMP enabled.
>
> Boot it with kernel parameter "crashkernel=XXX@YYY"
> means reserver XXX from YYY for crashdumping.
> Build an UP kernel with KEXEC KDUMP VMCORE enabled.
> load this kernel as a crashdumping kernel
> kexec -p vmlinux.gz --initrd=initrd --append="...."
>
> trigger a crash,
> maybe "echo c > /proc/sysrq-trigger"
> after the crash kernel boots,
> cp /proc/vmcore core
>
> gdb first_kernel_vmlinux core
>
> please test and review.
>
> Signed-off-by: Khalid Aziz <khalid_aziz@xxxxxx>
> Signed-off-by: Zou Nan hai <nanhai.zou@xxxxxxxxx>
Hi,
I'm very excited to be able to play with the new version of this patch,
but the version you posted seems to included include all the kexec patch
that went into Tony Luck's tree. Here is a rediff relative to the
existing kexec patch (no other changes).
The code does seem to be working for me. The main difficulty so far
seems to have been finding an appropriate place and size and place for
the reserved area. 128M@256M seems to work for me, offering enough
memory and not lie on a resource boundry for me.
Lastly, is it possible for you to comment on what areas of concern
you have with regards to kdump/kexec on ia64. I am looking to port this
code to xen, as my colleague Magnus Damm and I have already done so for i386
(complete) and x86_64 (almost complete).
http://lists.xensource.com/archives/html/xen-devel/2006-05/msg01272.html
Signed-Off-By: Horms <horms@xxxxxxxxxxxx>
arch/ia64/Kconfig | 8 ++
arch/ia64/kernel/crash.c | 113 +++++++++++++++++++++++++++++++++++-
arch/ia64/kernel/efi.c | 17 ++++-
arch/ia64/kernel/machine_kexec.c | 43 ++-----------
arch/ia64/kernel/relocate_kernel.S | 38 +++++-------
arch/ia64/kernel/setup.c | 38 ++++++++++++
include/asm-ia64/kexec.h | 4 -
include/asm-ia64/meminit.h | 3
include/linux/irq.h | 1
kernel/irq/manage.c | 19 ++++++
10 files changed, 218 insertions(+), 66 deletions(-)
34b91b63c4f4144a4e67c67dca97b424ed8fc26c
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 4bab62d..1202c6e 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -413,6 +413,8 @@ config IA64_PALINFO
config SGI_SN
def_bool y if (IA64_SGI_SN2 || IA64_GENERIC)
+source "drivers/sn/Kconfig"
+
config KEXEC
bool "kexec system call (EXPERIMENTAL)"
depends on EXPERIMENTAL
@@ -430,7 +432,11 @@ config KEXEC
support. As of this writing the exact hardware interface is
strongly in flux, so no good recommendation can be made.
-source "drivers/sn/Kconfig"
+config CRASH_DUMP
+ bool "kernel crash dumps (EXPERIMENTAL)"
+ depends on EXPERIMENTAL
+ help
+ Generate crash dump after being started by kexec.
source "drivers/firmware/Kconfig"
diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c
index a0e49b7..03c3118 100644
--- a/arch/ia64/kernel/crash.c
+++ b/arch/ia64/kernel/crash.c
@@ -4,8 +4,8 @@
* Architecture specific (ia64) functions for kexec based crash dumps.
*
* Created by: Khalid Aziz <khalid.aziz@xxxxxx>
- *
* Copyright (C) 2005 Hewlett-Packard Development Company, L.P.
+ * Copyright (C) 2005 Intel Corp Zou Nan hai <nanhai.zou@xxxxxxxxx>
*
*/
#include <linux/init.h>
@@ -13,6 +13,7 @@ #include <linux/types.h>
#include <linux/kernel.h>
#include <linux/smp.h>
#include <linux/irq.h>
+#include <linux/pci.h>
#include <linux/reboot.h>
#include <linux/kexec.h>
#include <linux/irq.h>
@@ -20,6 +21,111 @@ #include <linux/delay.h>
#include <linux/elf.h>
#include <linux/elfcore.h>
#include <linux/device.h>
+#include <asm/uaccess.h>
+
+size_t copy_oldmem_page(unsigned long pfn, char *buf,
+ size_t csize, unsigned long offset, int userbuf)
+{
+ void *vaddr;
+
+ if (!csize)
+ return 0;
+ vaddr = page_address(pfn_to_page(pfn));
+
+ if (userbuf) {
+ if (copy_to_user(buf, (vaddr + offset), csize)) {
+ return -EFAULT;
+ }
+ } else
+ memcpy(buf, (vaddr + offset), csize);
+ return csize;
+}
+
+static void device_shootdown(void)
+{
+ struct pci_dev *dev;
+ irq_desc_t *desc;
+ u16 pci_command;
+
+ list_for_each_entry(dev, &pci_devices, global_list) {
+ desc = irq_descp(dev->irq);
+ if (!desc->action)
+ continue;
+ pci_read_config_word(dev, PCI_COMMAND, &pci_command);
+ if (pci_command & PCI_COMMAND_MASTER) {
+ pci_command &= ~PCI_COMMAND_MASTER;
+ pci_write_config_word(dev, PCI_COMMAND, pci_command);
+ }
+ disable_irq_nosync(dev->irq);
+ desc->handler->end(dev->irq);
+ }
+}
+
+static Elf64_Word
+*append_elf_note(Elf64_Word *buf, char *name, unsigned type, void *data,
+ size_t data_len)
+{
+ struct elf_note *note = (struct elf_note *)buf;
+ note->n_namesz = strlen(name) + 1;
+ note->n_descsz = data_len;
+ note->n_type = type;
+ buf += (sizeof(*note) + 3)/4;
+ memcpy(buf, name, note->n_namesz);
+ buf += (note->n_namesz + 3)/4;
+ memcpy(buf, data, data_len);
+ buf += (data_len + 3)/4;
+ return buf;
+}
+
+static void
+final_note(void *buf)
+{
+ memset(buf, 0, sizeof(struct elf_note));
+}
+
+static void
+crash_save_this_cpu(void)
+{
+ void *buf;
+ struct elf_prstatus prstatus;
+ int cpu = smp_processor_id();
+ elf_greg_t *dst = (elf_greg_t *)&prstatus.pr_reg;
+
+ memset(&prstatus, 0, sizeof(prstatus));
+ prstatus.pr_pid = current->pid;
+
+ dst[1] = ia64_getreg(_IA64_REG_GP);
+ dst[12] = ia64_getreg(_IA64_REG_SP);
+ dst[13] = ia64_getreg(_IA64_REG_TP);
+
+ dst[42] = ia64_getreg(_IA64_REG_IP);
+ dst[45] = ia64_getreg(_IA64_REG_AR_RSC);
+
+ ia64_setreg(_IA64_REG_AR_RSC, 0);
+ ia64_srlz_i();
+
+ dst[46] = ia64_getreg(_IA64_REG_AR_BSP);
+ dst[47] = ia64_getreg(_IA64_REG_AR_BSPSTORE);
+
+ dst[48] = ia64_getreg(_IA64_REG_AR_RNAT);
+ dst[49] = ia64_getreg(_IA64_REG_AR_CCV);
+ dst[50] = ia64_getreg(_IA64_REG_AR_UNAT);
+
+ dst[51] = ia64_getreg(_IA64_REG_AR_FPSR);
+ dst[52] = ia64_getreg(_IA64_REG_AR_PFS);
+ dst[53] = ia64_getreg(_IA64_REG_AR_LC);
+
+ dst[54] = ia64_getreg(_IA64_REG_AR_LC);
+ dst[55] = ia64_getreg(_IA64_REG_AR_CSD);
+ dst[56] = ia64_getreg(_IA64_REG_AR_SSD);
+
+ buf = (u64 *) per_cpu_ptr(crash_notes, cpu);
+ if (!buf)
+ return;
+ buf = append_elf_note(buf, "CORE", NT_PRSTATUS, &prstatus,
+ sizeof(prstatus));
+ final_note(buf);
+}
void
machine_crash_shutdown(struct pt_regs *pt)
@@ -32,8 +138,11 @@ machine_crash_shutdown(struct pt_regs *p
* In practice this means shooting down the other cpus in
* an SMP system.
*/
- if (in_interrupt())
+ if (in_interrupt()) {
ia64_eoi();
+ }
+ crash_save_this_cpu();
+ device_shootdown();
#ifdef CONFIG_SMP
smp_send_stop();
#endif
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index c33d0ba..5c657e6 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -27,6 +27,7 @@ #include <linux/init.h>
#include <linux/types.h>
#include <linux/time.h>
#include <linux/efi.h>
+#include <linux/kexec.h>
#include <asm/io.h>
#include <asm/kregs.h>
@@ -42,7 +43,7 @@ extern efi_status_t efi_call_phys (void
struct efi efi;
EXPORT_SYMBOL(efi);
static efi_runtime_services_t *runtime;
-static unsigned long mem_limit = ~0UL, max_addr = ~0UL;
+static unsigned long mem_limit = ~0UL, max_addr = ~0UL, min_addr = 0UL;
#define efi_call_virt(f, args...) (*(f))(args)
@@ -422,6 +423,8 @@ efi_init (void)
mem_limit = memparse(cp + 4, &cp);
} else if (memcmp(cp, "max_addr=", 9) == 0) {
max_addr = GRANULEROUNDDOWN(memparse(cp + 9, &cp));
+ } else if (memcmp(cp, "min_addr=", 9) == 0) {
+ min_addr = GRANULEROUNDDOWN(memparse(cp + 9, &cp));
} else {
while (*cp != ' ' && *cp)
++cp;
@@ -429,6 +432,8 @@ efi_init (void)
++cp;
}
}
+ if (min_addr != 0UL)
+ printk(KERN_INFO "Ignoring memory below %luMB\n", min_addr >> 20);
if (max_addr != ~0UL)
printk(KERN_INFO "Ignoring memory above %luMB\n", max_addr >> 20);
@@ -895,7 +900,8 @@ find_memmap_space (void)
as = max(contig_low, md->phys_addr);
ae = min(contig_high, efi_md_end(md));
- /* keep within max_addr= command line arg */
+ /* keep within max_addr= and min_addr= command line arg */
+ as = max(as, min_addr);
ae = min(ae, max_addr);
if (ae <= as)
continue;
@@ -1005,7 +1011,8 @@ efi_memmap_init(unsigned long *s, unsign
} else
ae = efi_md_end(md);
- /* keep within max_addr= command line arg */
+ /* keep within max_addr= and min_addr= command line arg */
+ as = max(as, min_addr);
ae = min(ae, max_addr);
if (ae <= as)
continue;
@@ -1117,6 +1124,10 @@ efi_initialize_iomem_resources(struct re
*/
insert_resource(res, code_resource);
insert_resource(res, data_resource);
+#ifdef CONFIG_KEXEC
+ if (crashk_res.end > crashk_res.start)
+ insert_resource(res, &crashk_res);
+#endif
}
}
}
diff --git a/arch/ia64/kernel/machine_kexec.c b/arch/ia64/kernel/machine_kexec.c
index 3b46143..73fbb26 100644
--- a/arch/ia64/kernel/machine_kexec.c
+++ b/arch/ia64/kernel/machine_kexec.c
@@ -1,5 +1,5 @@
/*
- * arch/ia64/kernel/machine_kexec.c
+ * arch/ia64/kernel/machine_kexec.c
*
* Handle transition of Linux booting another kernel
* Copyright (C) 2005 Hewlett-Packard Development Comapny, L.P.
@@ -25,9 +25,7 @@ #include <asm/tlbflush.h>
#include <asm/delay.h>
#include <asm/meminit.h>
-extern unsigned long ia64_iobase;
-
-typedef void (*relocate_new_kernel_t)( unsigned long, unsigned long,
+typedef void (*relocate_new_kernel_t)(unsigned long, unsigned long,
struct ia64_boot_param *, unsigned long);
/*
@@ -43,9 +41,9 @@ int machine_kexec_prepare(struct kimage
func = (unsigned long *)&relocate_new_kernel;
/* Pre-load control code buffer to minimize work in kexec path */
control_code_buffer = page_address(image->control_code_page);
- memcpy((void *)control_code_buffer, (const void *)func[0],
+ memcpy((void *)control_code_buffer, (const void *)func[0],
relocate_new_kernel_size);
- flush_icache_range((unsigned long)control_code_buffer,
+ flush_icache_range((unsigned long)control_code_buffer,
(unsigned long)control_code_buffer + relocate_new_kernel_size);
return 0;
@@ -61,7 +59,6 @@ #ifdef CONFIG_PCI
struct pci_dev *dev = NULL;
irq_desc_t *idesc;
cpumask_t mask = CPU_MASK_NONE;
-
/* Disable all PCI devices */
while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
if (!(dev->is_enabled))
@@ -91,7 +88,6 @@ #elif defined(CONFIG_SMP)
smp_call_function(kexec_stop_this_cpu, (void *)image->start, 0, 0);
#endif
- ia64_set_itv(1<<16);
#ifdef CONFIG_IA64_HP_ZX1
ioc_iova_disable();
@@ -100,41 +96,20 @@ #endif
/*
* Do not allocate memory (or fail in any way) in machine_kexec().
- * We are past the point of no return, committed to rebooting now.
+ * We are past the point of no return, committed to rebooting now.
*/
+extern void *efi_get_pal_addr(void);
void machine_kexec(struct kimage *image)
{
- unsigned long indirection_page;
relocate_new_kernel_t rnk;
- unsigned long pta, impl_va_bits;
void *pal_addr = efi_get_pal_addr();
unsigned long code_addr = (unsigned long)page_address(image->control_code_page);
-
/* Interrupts aren't acceptable while we reboot */
+ ia64_set_itv(1<<16);
local_irq_disable();
-
- /* Disable VHPT */
- impl_va_bits = ffz(~(local_cpu_data->unimpl_va_mask | (7UL << 61)));
- pta = POW2(61) - POW2(vmlpt_bits);
- ia64_set_pta(pta | (0 << 8) | (vmlpt_bits << 2) | 0);
-
- /* now execute the control code.
- * We will start by executing the control code linked into the
- * kernel as opposed to the code we copied in control code buffer * page. When this code switches to physical mode, we will start
- * executing the code in control code buffer page. Reason for
- * doing this is we start code execution in virtual address space.
- * If we were to try to execute the newly copied code in virtual
- * address space, we will need to make an ITLB entry to avoid ITLB
- * miss. By executing the code linked into kernel, we take advantage
- * of the ITLB entry already in place for kernel and avoid making
- * a new entry.
- */
- indirection_page = image->head & PAGE_MASK;
-
rnk = (relocate_new_kernel_t)&code_addr;
- (*rnk)(indirection_page, image->start, ia64_boot_param,
+ (*rnk)(image->head, image->start, ia64_boot_param,
GRANULEROUNDDOWN((unsigned long) pal_addr));
BUG();
- for (;;)
- ;
+ for (;;);
}
diff --git a/arch/ia64/kernel/relocate_kernel.S b/arch/ia64/kernel/relocate_kernel.S
index d3e20ad..09bd041 100644
--- a/arch/ia64/kernel/relocate_kernel.S
+++ b/arch/ia64/kernel/relocate_kernel.S
@@ -1,5 +1,5 @@
/*
- * arch/ia64/kernel/relocate_kernel.S
+ * arch/ia64/kernel/relocate_kernel.S
*
* Relocate kexec'able kernel and start it
*
@@ -17,9 +17,7 @@ #include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/mca_asm.h>
- /* Must be relocatable PIC code callable as a C function, that once
- * it starts can not use the previous processes stack.
- *
+ /* Must be relocatable PIC code callable as a C function
*/
GLOBAL_ENTRY(relocate_new_kernel)
.prologue
@@ -36,22 +34,16 @@ GLOBAL_ENTRY(relocate_new_kernel)
srlz.i
}
;;
-
+ dep r2=0,r2,61,3 //to physical address
+ ;;
//first switch to physical mode
add r3=1f-.reloc_entry, r2
- movl r16 = IA64_PSR_AC|IA64_PSR_BN|IA64_PSR_IC|IA64_PSR_MFL
+ movl r16 = IA64_PSR_AC|IA64_PSR_BN|IA64_PSR_IC
mov ar.rsc=0 // put RSE in enforced lazy mode
;;
- add r2=(memory_stack-.reloc_entry), r2
- ;;
- add sp=(memory_stack_end - .reloc_entry),r2
+ add sp=(memory_stack_end - 16 - .reloc_entry),r2
add r8=(register_stack - .reloc_entry),r2
;;
- tpa sp=sp
- tpa r3=r3
- ;;
- loadrs
- ;;
mov r18=ar.rnat
mov ar.bspstore=r8
;;
@@ -66,7 +58,7 @@ GLOBAL_ENTRY(relocate_new_kernel)
1:
//physical mode code begin
mov b6=in1
- tpa r28=in2 // tpa must before TLB purge
+ dep r28=0,in2,61,3 //to physical address
// purge all TC entries
#define O(member) IA64_CPUINFO_##member##_OFFSET
@@ -145,10 +137,10 @@ (p7) br.cond.dpnt.few 4f
srlz.i
;;
- // copy kexec kernel segments
+ //copy segments
movl r16=PAGE_MASK
- ld8 r30=[in0],8;; // in0 is page_list
- br.sptk.few .dest_page
+ mov r30=in0 // in0 is page_list
+ br.sptk.few .dest_page
;;
.loop:
ld8 r30=[in0], 8;;
@@ -188,6 +180,8 @@ (p6) br.cond.sptk.few .loop
srlz.d
;;
br.call.sptk.many b0=b6;;
+
+.align 32
memory_stack:
.fill 8192, 1, 0
memory_stack_end:
@@ -310,7 +304,7 @@ check_irr0:
cmp.eq p6,p0=0,r8
(p6) br.cond.sptk.few check_irr0
br.few call_start
-
+
check_irr1:
mov r8=cr.irr1
;;
@@ -319,7 +313,7 @@ check_irr1:
cmp.eq p6,p0=0,r8
(p6) br.cond.sptk.few check_irr1
br.few call_start
-
+
check_irr2:
mov r8=cr.irr2
;;
@@ -328,7 +322,7 @@ check_irr2:
cmp.eq p6,p0=0,r8
(p6) br.cond.sptk.few check_irr2
br.few call_start
-
+
check_irr3:
mov r8=cr.irr3
;;
@@ -337,7 +331,7 @@ check_irr3:
cmp.eq p6,p0=0,r8
(p6) br.cond.sptk.few check_irr3
br.few call_start
-
+
call_start:
mov cr.eoi=r0
;;
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index e4dfda1..7665d4d 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -44,6 +44,8 @@ #include <linux/efi.h>
#include <linux/initrd.h>
#include <linux/pm.h>
#include <linux/cpufreq.h>
+#include <linux/kexec.h>
+#include <linux/crash_dump.h>
#include <asm/ia32.h>
#include <asm/machvec.h>
@@ -251,6 +253,32 @@ #ifdef CONFIG_BLK_DEV_INITRD
}
#endif
+#ifdef CONFIG_KEXEC
+ /* crashkernel=size@addr specifies the location to reserve for
+ * a crash kernel. By reserving this memory we guarantee
+ * that linux never set's it up as a DMA target.
+ * Useful for holding code to do something appropriate
+ * after a kernel panic.
+ */
+ {
+ char *from = strstr(saved_command_line, "crashkernel=");
+ if (from) {
+ unsigned long size, base;
+ size = memparse(from + 12, &from);
+ if (*from == '@') {
+ base = memparse(from + 1, &from);
+ rsvd_region[n].start =
+ (unsigned long)__va(base);
+ rsvd_region[n].end =
+ (unsigned long)__va(base + size);
+ crashk_res.start = base;
+ crashk_res.end = base + size - 1;
+ n++;
+ }
+ }
+ }
+#endif
+
efi_memmap_init(&rsvd_region[n].start, &rsvd_region[n].end);
n++;
@@ -484,6 +512,16 @@ #endif
if (!nomca)
ia64_mca_init();
+#ifdef CONFIG_CRASH_DUMP
+ {
+ char *from = strstr(saved_command_line, "elfcorehdr=");
+
+ if (from)
+ elfcorehdr_addr = memparse(from+11, &from);
+ saved_max_pfn = (unsigned long) -1;
+ }
+#endif
+
platform_setup(cmdline_p);
paging_init();
}
diff --git a/include/asm-ia64/kexec.h b/include/asm-ia64/kexec.h
index e9f0b7a..d45c03f 100644
--- a/include/asm-ia64/kexec.h
+++ b/include/asm-ia64/kexec.h
@@ -21,14 +21,12 @@ #define vmlpt_bits (impl_va_bits - PAGE_
#define POW2(n) (1ULL << (n))
DECLARE_PER_CPU(u64, ia64_mca_pal_base);
-
const extern unsigned int relocate_new_kernel_size;
volatile extern long kexec_rendez;
-extern void relocate_new_kernel(unsigned long, unsigned long,
+extern void relocate_new_kernel(unsigned long, unsigned long,
struct ia64_boot_param *, unsigned long);
extern void kexec_fake_sal_rendez(void *start, unsigned long wake_up,
unsigned long pal_base);
-
static inline void
crash_setup_regs(struct pt_regs *newregs, struct pt_regs *oldregs)
{
diff --git a/include/asm-ia64/meminit.h b/include/asm-ia64/meminit.h
index 46501b0..7a0e216 100644
--- a/include/asm-ia64/meminit.h
+++ b/include/asm-ia64/meminit.h
@@ -16,11 +16,12 @@ #include <linux/config.h>
* - initrd (optional)
* - command line string
* - kernel code & data
+ * - crash dumping code reserved region
* - Kernel memory map built from EFI memory map
*
* More could be added if necessary
*/
-#define IA64_MAX_RSVD_REGIONS 6
+#define IA64_MAX_RSVD_REGIONS 7
struct rsvd_region {
unsigned long start; /* virtual address of beginning of element */
diff --git a/include/linux/irq.h b/include/linux/irq.h
index ee2a82a..a4e89f4 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -94,6 +94,7 @@ irq_descp (int irq)
#include <asm/hw_irq.h> /* the arch dependent stuff */
extern int setup_irq(unsigned int irq, struct irqaction * new);
+extern void terminate_irqs(void);
#ifdef CONFIG_GENERIC_HARDIRQS
extern cpumask_t irq_affinity[NR_IRQS];
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 1279e34..7d855d2 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -393,3 +393,22 @@ int request_irq(unsigned int irq,
EXPORT_SYMBOL(request_irq);
+/*
+ * Terminate any outstanding interrupts
+ */
+void terminate_irqs(void)
+{
+ struct irqaction * action;
+ irq_desc_t *idesc;
+ int i;
+
+ for (i=0; i < NR_IRQS; i++) {
+ idesc = irq_descp(i);
+ action = idesc->action;
+ if (!action)
+ continue;
+ if (idesc->handler->end)
+ idesc->handler->end(i);
+ }
+}
+
-
: send the line "unsubscribe linux-ia64" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
|