min_low_pfn and max_low_pfn calcultion fix
PATCH 1/1 min_low_pfn and max_low_pfn calcultion fix
Hi,
We have seen bad_pte_print when testing crashdump on an SN machine in
recent 2.6.20 kernel.
There are tons of bad pte print (pfn < max_low_pfn) reports when the
crash kernel boots up, all those reported bad pages are inside initmem range;
That is because if the crash kernel code and data happens to be at the
beginning of the 1st node. build_node_maps in discontig.c will bypass reserved regions with filter_rsvd_memory. Since min_low_pfn is calculated in build_node_map, so in this case, min_low_pfn will be greater than kernel code and data.
Because pages inside initmem are freed and reused later, we sawpfn_valid check fail on those pages.
I think this theoretically happen on a normal kernel. When I checkmin_low_pfn and max_low_pfn calculation in contig.c and discontig.c. I found more issues than this.
1. min_low_pfn and max_low_pfn calculation is inconsistent betweencontig.c and discontig.c,
min_low_pfn is calculated as the first page number of boot memmap incontig.c (Why? Though this may work at the most of the time, I don't think it is the right logic). It is calculated as the lowest physical memory page number bypass reserved regions in discontig.c.
max_low_pfn is calculated include reserved regions in contig.c. It is
calculated exclude reserved regions in discontig.c.
2. If kernel code and data region is happen to be at the begin or the
end of physical memory, when min_low_pfn and max_low_pfn calculation is bypassed kernel code and data, pages in initmem will report bad.
3. initrd is also in reserved regions, if it is at the begin or at the
end of physical memory, kernel will refuse to reuse the memory. Because the virt_addr_valid check in free_initrd_mem.
So it is better to fix and clean up those issues.
Calculate min_low_pfn and max_low_pfn in a consistent way.
Below is the patch, please review and comments
arch/ia64/mm/contig.c +6 -24
@@ -75,26 +75,6 @@ show_mem (void)unsigned long bootmap_start;/** -* find_max_pfn - adjust the maximum page number callback -* @start: start of range -* @end: end of range -* @arg: address of pointer to global max_pfn variable -* -* Passed as a callback function to efi_memmap_walk() to determine the highest -* available page frame number in the system. -*/ -int -find_max_pfn (unsigned long start,unsigned long end,void *arg) -{ -unsigned long *max_pfnp = arg, pfn; - - pfn = (PAGE_ALIGN (end -1 ) -PAGE_OFFSET ) >>PAGE_SHIFT ; -if (pfn > *max_pfnp) - *max_pfnp = pfn; -return 0 ; -} - -/** * find_bootmap_location - callback to find a memory area for the bootmap * @start: start of region * @end: end of region
@@ -155,9 +135,10 @@ find_memory (void)reserve_memory ();/* first find highest page frame number */ - max_pfn =0 ; -efi_memmap_walk (find_max_pfn, &max_pfn); - + min_low_pfn =-1 ; + max_low_pfn =0 ; +efi_memmap_walk (find_max_min_low_pfn,NULL ); + max_pfn = max_low_pfn;/* how many bytes to cover all the pages */ bootmap_size =bootmem_bootmap_pages (max_pfn) <<PAGE_SHIFT ;
@@ -167,7 +148,8 @@ find_memory (void)if (bootmap_start = ~0UL )panic ("Cannot find %ld bytes for bootmap\n" , bootmap_size); - bootmap_size =init_bootmem (bootmap_start >>PAGE_SHIFT , max_pfn); + bootmap_size =init_bootmem_node (NODE_DATA (0 ), + (bootmap_start >>PAGE_SHIFT ),0 , max_pfn);/* Free all available memory, then mark bootmem-map as being in use. */ efi_memmap_walk (filter_rsvd_memory, free_bootmem);
arch/ia64/mm/discontig.c +1 -3
@@ -86,9 +86,6 @@ static int __init build_node_maps(unsign bdp->node_low_pfn =max (epfn, bdp->node_low_pfn); } - min_low_pfn =min (min_low_pfn, bdp->node_boot_start>>PAGE_SHIFT ); - max_low_pfn =max (max_low_pfn, bdp->node_low_pfn); -return 0 ; }
@@ -467,6 +464,7 @@ void __init find_memory(void)/* These actually end up getting called by call_pernode_memory() */ efi_memmap_walk (filter_rsvd_memory, build_node_maps);efi_memmap_walk (filter_rsvd_memory, find_pernode_space); +efi_memmap_walk (find_max_min_low_pfn,NULL );for_each_online_node (node)if (mem_data[node].bootmem_data.node_low_pfn) {
arch/ia64/mm/init.c +16 -0
@@ -616,6 +616,22 @@ count_reserved_pages (u64 start, u64 endreturn 0 ; } +int +find_max_min_low_pfn (unsigned long start,unsigned long end,void *arg) +{ +unsigned long pfn_start, pfn_end; +#if CONFIG_FLATMEM + pfn_start = (PAGE_ALIGN (__pa (start))) >>PAGE_SHIFT ; + pfn_end = (PAGE_ALIGN (__pa (end -1 ))) >>PAGE_SHIFT ; +#else + pfn_start =GRANULEROUNDDOWN (__pa (start)) >>PAGE_SHIFT ; + pfn_end =GRANULEROUNDUP (__pa (end -1 )) >>PAGE_SHIFT ; +#endif + min_low_pfn =min (min_low_pfn, pfn_start); + max_low_pfn =max (max_low_pfn, pfn_end); +return 0 ; +} +/* * Boot command-line option "nolwsys" can be used to disable the use of any light-weight * system call handler. When this option is in effect, all fsyscalls will end up bubbling
include/asm-ia64/meminit.h +1 -0
@@ -35,6 +35,7 @@ extern void reserve_memory (void);extern void find_initrd (void );extern int filter_rsvd_memory (unsigned long start,unsigned long end,void *arg);extern void efi_memmap_init (unsigned long *,unsigned long *); +extern int find_max_min_low_pfn (unsigned long ,unsigned long ,void *);/* * For rounding an address to the next IA64_GRANULE_SIZE or order
This fixed my problem on SN.
Quoted 166 lines · Zou Nan hai
Hi,
We have seenbad_pte_printwhen testing crashdump on an SN machine in
recent 2.6.20 kernel.
There are tons of bad pte print (pfn <max_low_pfn) reports when the
crash kernel boots up, all those reported bad pages are inside initmem range;
That is because if the crash kernel code and data happens to be at the
beginning of the 1st node.build_node_mapsindiscontig.cwill bypass reserved regions withfilter_rsvd_memory. Sincemin_low_pfnis calculated inbuild_node_map, so in this case,min_low_pfnwill be greater than kernel code and data.Because pages inside initmem are freed and reused later, we saw
pfn_validcheck fail on those pages.I think this theoretically happen on a normal kernel. When I check
min_low_pfnandmax_low_pfncalculation incontig.canddiscontig.c. I found more issues than this.1.
min_low_pfnandmax_low_pfncalculation is inconsistent betweencontig.canddiscontig.c,
min_low_pfnis calculated as the first page number of boot memmap incontig.c(Why? Though this may work at the most of the time, I don't think it is the right logic). It is calculated as the lowest physical memory page number bypass reserved regions indiscontig.c.
max_low_pfnis calculated include reserved regions incontig.c. It is
calculated exclude reserved regions indiscontig.c.2. If kernel code and data region is happen to be at the begin or the
end of physical memory, whenmin_low_pfnandmax_low_pfncalculation is bypassed kernel code and data, pages in initmem will report bad.3. initrd is also in reserved regions, if it is at the begin or at the
end of physical memory, kernel will refuse to reuse the memory. Because thevirt_addr_validcheck infree_initrd_mem.So it is better to fix and clean up those issues.
Calculatemin_low_pfnandmax_low_pfnin a consistent way.Below is the patch, please review and comments
Signed-off-by Zou Nan hai <[email protected]>diff -Nraup
a/arch/ia64/mm/contig.cb/arch/ia64/mm/contig.carch/ia64/mm/contig.c +6
-24@@ -75,26 +75,6 @@ show_mem (void)unsigned long bootmap_start;/** -* find_max_pfn - adjust the maximum page number callback -* @start: start of range -* @end: end of range -* @arg: address of pointer to global max_pfn variable -* -* Passed as a callback function to efi_memmap_walk() to determine the highest -* available page frame number in the system. -*/ -int -find_max_pfn (unsigned long start,unsigned long end,void *arg) -{ -unsigned long *max_pfnp = arg, pfn; - - pfn = (PAGE_ALIGN (end -1 ) -PAGE_OFFSET ) >>PAGE_SHIFT ; -if (pfn > *max_pfnp) - *max_pfnp = pfn; -return 0 ; -} - -/** * find_bootmap_location - callback to find a memory area for the bootmap * @start: start of region * @end: end of region @@ -155,9 +135,10 @@ find_memory (void)reserve_memory ();/* first find highest page frame number */ - max_pfn =0 ; -efi_memmap_walk (find_max_pfn, &max_pfn); - + min_low_pfn =-1 ; + max_low_pfn =0 ; +efi_memmap_walk (find_max_min_low_pfn,NULL ); + max_pfn = max_low_pfn;/* how many bytes to cover all the pages */ bootmap_size =bootmem_bootmap_pages (max_pfn) <<PAGE_SHIFT ;@@ -167,7 +148,8 @@ find_memory (void)if (bootmap_start = ~0UL )panic ("Cannot find %ld bytes for bootmap\n" , bootmap_size); - bootmap_size =init_bootmem (bootmap_start >>PAGE_SHIFT , max_pfn); + bootmap_size =init_bootmem_node (NODE_DATA (0 ), + (bootmap_start >>PAGE_SHIFT ),0 , max_pfn);/* Free all available memory, then mark bootmem-map as being in use. */ efi_memmap_walk (filter_rsvd_memory, free_bootmem);diff -Nraup
a/arch/ia64/mm/discontig.cb/arch/ia64/mm/discontig.carch/ia64/mm/discontig.c +1
-3@@ -86,9 +86,6 @@ static int __init build_node_maps(unsign bdp->node_low_pfn =max (epfn, bdp->node_low_pfn); } - min_low_pfn =min (min_low_pfn, bdp->node_boot_start>>PAGE_SHIFT ); - max_low_pfn =max (max_low_pfn, bdp->node_low_pfn); -return 0 ; }@@ -467,6 +464,7 @@ void __init find_memory(void)/* These actually end up getting called by call_pernode_memory() */ efi_memmap_walk (filter_rsvd_memory, build_node_maps);efi_memmap_walk (filter_rsvd_memory, find_pernode_space); +efi_memmap_walk (find_max_min_low_pfn,NULL );for_each_online_node (node)if (mem_data[node].bootmem_data.node_low_pfn) {diff -Nraup
a/arch/ia64/mm/init.cb/arch/ia64/mm/init.carch/ia64/mm/init.c +16
-0@@ -616,6 +616,22 @@ count_reserved_pages (u64 start, u64 endreturn 0 ; } +int +find_max_min_low_pfn (unsigned long start,unsigned long end,void *arg) +{ +unsigned long pfn_start, pfn_end; +#if CONFIG_FLATMEM + pfn_start = (PAGE_ALIGN (__pa (start))) >>PAGE_SHIFT ; + pfn_end = (PAGE_ALIGN (__pa (end -1 ))) >>PAGE_SHIFT ; +#else + pfn_start =GRANULEROUNDDOWN (__pa (start)) >>PAGE_SHIFT ; + pfn_end =GRANULEROUNDUP (__pa (end -1 )) >>PAGE_SHIFT ; +#endif + min_low_pfn =min (min_low_pfn, pfn_start); + max_low_pfn =max (max_low_pfn, pfn_end); +return 0 ; +} +/* * Boot command-line option "nolwsys" can be used to disable the use of any light-weight * system call handler. When this option is in effect, all fsyscalls will end up bubbling diff -Nraup
a/include/asm-ia64/meminit.hb/include/asm-ia64/meminit.hinclude/asm-ia64/meminit.h +1
-1@@ -35,6 +35,7 @@ extern void reserve_memory (void);extern void find_initrd (void );extern int filter_rsvd_memory (unsigned long start,unsigned long end,void *arg);extern void efi_memmap_init (unsigned long *,unsigned long *); +extern int find_max_min_low_pfn (unsigned long ,unsigned long ,void *);/* * For rounding an address to the next IA64_GRANULE_SIZE or order -To unsubscribe from this list: send the line "unsubscribe linux-ia64" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Quoted 37 lines · Zou Nan hai
Hi,
We have seenbad_pte_printwhen testing crashdump on an SN machine in
recent 2.6.20 kernel.
There are tons of bad pte print (pfn <max_low_pfn) reports when the
crash kernel boots up, all those reported bad pages are inside initmem range;
That is because if the crash kernel code and data happens to be at the
beginning of the 1st node.build_node_mapsindiscontig.cwill bypass reserved regions withfilter_rsvd_memory. Sincemin_low_pfnis calculated inbuild_node_map, so in this case,min_low_pfnwill be greater than kernel code and data.Because pages inside initmem are freed and reused later, we saw
pfn_validcheck fail on those pages.I think this theoretically happen on a normal kernel. When I check
min_low_pfnandmax_low_pfncalculation incontig.canddiscontig.c. I found more issues than this.1.
min_low_pfnandmax_low_pfncalculation is inconsistent betweencontig.canddiscontig.c,
min_low_pfnis calculated as the first page number of boot memmap incontig.c(Why? Though this may work at the most of the time, I don't think it is the right logic). It is calculated as the lowest physical memory page number bypass reserved regions indiscontig.c.
max_low_pfnis calculated include reserved regions incontig.c. It is
calculated exclude reserved regions indiscontig.c.2. If kernel code and data region is happen to be at the begin or the
end of physical memory, whenmin_low_pfnandmax_low_pfncalculation is bypassed kernel code and data, pages in initmem will report bad.3. initrd is also in reserved regions, if it is at the begin or at the
end of physical memory, kernel will refuse to reuse the memory. Because thevirt_addr_validcheck infree_initrd_mem.
Quoted 6 lines
So it is better to fix and clean up those issues.
Calculatemin_low_pfnandmax_low_pfnin a consistent way.Below is the patch, please review and comments
Signed-off-by Zou Nan hai <[email protected]>
I've seen similar problems on a HP rx2620 box using 2.6.20. I managed to resolve that problem with a patch similar to this one, but then I realized that the issue I was seeing had been solved already by some mm-related patch by Bob Picco that got included in 2.6.21-rc1.
So, I suspect that 2.6.21-rc1 and rc2 should work just fine without this patch.
/ magnus
PS. Any comments on the EFI_LOADER_DATA for ELF core header would be greatly appreciated, I think it is sort of related to this issue as well.
Quoted 2 lines · Magnus Damm
Quoted 1 line · Zou Nan hai
[excessive text deleted]
Quoted 11 lines
Quoted 6 lines
So it is better to fix and clean up those issues.
Calculatemin_low_pfnandmax_low_pfnin a consistent way.Below is the patch, please review and comments
Signed-off-by Zou Nan hai <[email protected]>I've seen similar problems on a HP rx2620 box using 2.6.20. I managed to resolve that problem with a patch similar to this one, but then I realized that the issue I was seeing had been solved already by some mm-related patch by Bob Picco that got included in 2.6.21-rc1.
I tested on 2.6.21-rc3 with DEBUG_VM turned on. The vanilla 2.6.21-rc3 without Nan-hai's patch, panicked on bugcheck on free_initmem->free_page as predicted. We still need this patch.
However, the zero-size vmcore problem is back on SN. But that is a dfiffernet problem.
Regards,
- jay
Quoted 13 lines
So, I suspect that 2.6.21-rc1 and rc2 should work just fine without this patch.
/ magnus
PS. Any comments on the
EFI_LOADER_DATAfor ELF core header would be greatly appreciated, I think it is sort of related to this issue as well.
-
To unsubscribe from this list: send the line "unsubscribe linux-ia64" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Quoted 3 lines
I tested on 2.6.21-rc3 with
DEBUG_VMturned on. The vanilla 2.6.21-rc3 without Nan-hai's patch, panicked on bugcheck onfree_initmem->free_pageas predicted. We still need this patch.
I've applied Nan hai's patch ... will push upstream in a little while.
Quoted 2 lines
However, the zero-size vmcore problem is back on SN. But that is a differnet problem.
I applied a fix that was supposed to fix this after -rc3. It is in Linus' tree now. Let me know if it really is still broken.
-Tony
Quoted 5 lines · Tony
Quoted 3 lines
I tested on 2.6.21-rc3 with
DEBUG_VMturned on. The vanilla 2.6.21-rc3 without Nan-hai's patch, panicked on bugcheck onfree_initmem->free_pageas predicted. We still need this patch.I've applied Nan hai's patch ... will push upstream in a little while.
Thanks!
Quoted 6 lines
Quoted 3 lines
However, the zero-size vmcore problem is back on SN. But that is a differnet problem.
I applied a fix that was supposed to fix this after -rc3. It is in Linus' tree now. Let me know if it really is still broken.
I git pull from Linus' tree yesterday afternoon, and i still have the zero sized vmcore problem on SN. I will look into this.
Regards,
- jay
Quoted 6 lines
(quoted diff) +0
-2-Tony -To unsubscribe from this list: send the line "unsubscribe linux-ia64" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Quoted 12 lines · Jay Lan
Quoted 2 lines · Magnus Damm
Quoted 1 line · Zou Nan hai
[excessive text deleted]
Quoted 7 lines
Quoted 6 lines
So it is better to fix and clean up those issues.
Calculatemin_low_pfnandmax_low_pfnin a consistent way.Below is the patch, please review and comments
Signed-off-by Zou Nan hai <[email protected]>
Quoted 8 lines
Quoted 4 lines
I've seen similar problems on a HP rx2620 box using 2.6.20. I managed to resolve that problem with a patch similar to this one, but then I realized that the issue I was seeing had been solved already by some mm-related patch by Bob Picco that got included in 2.6.21-rc1.
I tested on 2.6.21-rc3 with
DEBUG_VMturned on. The vanilla 2.6.21-rc3 without Nan-hai's patch, panicked on bugcheck onfree_initmem->free_pageas predicted. We still need this patch.
Ok, thanks for testing. =)
Quoted 2 lines
However, the zero-size vmcore problem is back on SN. But that is a dfiffernet problem.
Argh, more problems...
/ magnus
Magnus Damm wrote:
[snip]
Quoted 11 lines
Quoted 4 lines
I tested on 2.6.21-rc3 with
DEBUG_VMturned on. The vanilla 2.6.21-rc3 without Nan-hai's patch, panicked on bugcheck onfree_initmem->free_pageas predicted. We still need this patch.Ok, thanks for testing. =)
Quoted 2 lines
However, the zero-size vmcore problem is back on SN. But that is a dfiffernet problem.
Argh, more problems...
I found the problem. It was the "elfcorehdr" introduced in 2.6.21-rc1. Without specifying it, the elfcorehdr_addr is initialized to ELFCORE_ADDR_MAX. Later, a check in reserve_elfcorehdr will fail:
if (elfcorehdr_addr >= ELFCORE_ADDR_MAX)
return -EINVAL;
Is it supposed to be a physical address to store elf core header? If so, it is not possible for SN to provide a physical address at boot time, just like in the case of crashkernel=X@Y where Y is not used.
Thanks,
- jay
Quoted 6 lines
/ magnus
-
To unsubscribe from this list: send the line "unsubscribe linux-ia64" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Quoted 17 lines · Jay Lan
Magnus Damm wrote:
[snip]Quoted 8 lines
Quoted 3 lines
I tested on 2.6.21-rc3 with
DEBUG_VMturned on. The vanilla 2.6.21-rc3 without Nan-hai's patch, panicked on bugcheck onfree_initmem->free_pageas predicted. We still need this patch.Ok, thanks for testing. =)
Quoted 2 lines
However, the zero-size vmcore problem is back on SN. But that is a dfiffernet problem.
Argh, more problems...
I found the problem. It was the "elfcorehdr" introduced in 2.6.21-rc1. Without specifying it, the
elfcorehdr_addris initialized toELFCORE_ADDR_MAX. Later, a check inreserve_elfcorehdrwill fail:
if (elfcorehdr_addr>=ELFCORE_ADDR_MAX)
return-EINVAL;
Quoted 3 lines
Is it supposed to be a physical address to store elf core header? If so, it is not possible for SN to provide a physical address at boot time, just like in the case of crashkernel=X@Y where Y is not used.
Sorry, the elfcorehdr parameter is provided to the kdump kernel by kexec. The problem is in the reserve_elfcorehdr logic introduced in 2.6.21-rc1.
When booting up the kdump kernel, i observed a failure in reserve_elfcorehdr. The below are my debugging messages:
elfcorehdr_addr027fe4000, ELFCORE_ADDR_MAXÿffffffffffffff Cannot locate EFI vmcore descriptorreserve_elfcorehdr: vmcore descriptor size = 0reserve_memory: FAIL to reserve reserve_elfcorehdr
- jay
Quoted 11 lines
Thanks,
- jayQuoted 5 lines
/ magnus
-
To unsubscribe from this list: send the line "unsubscribe linux-ia64" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Quoted 25 lines · Jay Lan
Quoted 16 lines · Jay Lan
Magnus Damm wrote:
[snip]Quoted 8 lines
Quoted 3 lines
I tested on 2.6.21-rc3 with
DEBUG_VMturned on. The vanilla 2.6.21-rc3 without Nan-hai's patch, panicked on bugcheck onfree_initmem->free_pageas predicted. We still need this patch.Ok, thanks for testing. =)
Quoted 2 lines
However, the zero-size vmcore problem is back on SN. But that is a dfiffernet problem.
Argh, more problems...
I found the problem. It was the "elfcorehdr" introduced in 2.6.21-rc1. Without specifying it, the
elfcorehdr_addris initialized toELFCORE_ADDR_MAX. Later, a check inreserve_elfcorehdrwill fail:
if (elfcorehdr_addr>=ELFCORE_ADDR_MAX)
return-EINVAL;Quoted 3 lines
Is it supposed to be a physical address to store elf core header? If so, it is not possible for SN to provide a physical address at boot time, just like in the case of crashkernel=X@Y where Y is not used.
Sorry, the elfcorehdr parameter is provided to the kdump kernel by kexec. The problem is in the
reserve_elfcorehdrlogic introduced in 2.6.21-rc1.
Quoted 7 lines
When booting up the kdump kernel, i observed a failure in
reserve_elfcorehdr. The below are my debugging messages:
elfcorehdr_addr027fe4000, ELFCORE_ADDR_MAXÿffffffffffffff Cannot locate EFI vmcore descriptorreserve_elfcorehdr: vmcore descriptor size = 0reserve_memory: FAIL to reservereserve_elfcorehdr
Hi Tony,
The kernel code 2.6.21-rc3+ is fine wrt zero-size-vmcore issue.
I have been testing on a rhel5 environment. The /sbin/kexec worked for me up to 2.6.20.
I then built a new kexec from tot kexec-tools-testing git tree and i no longer see the zero-size-vmcore problem.
Regards,
- jay
Quoted 36 lines · Jay Lan
Quoted 25 lines · Jay Lan
Quoted 16 lines · Jay Lan
Magnus Damm wrote:
[snip]Quoted 8 lines
Quoted 3 lines
I tested on 2.6.21-rc3 with
DEBUG_VMturned on. The vanilla 2.6.21-rc3 without Nan-hai's patch, panicked on bugcheck onfree_initmem->free_pageas predicted. We still need this patch.Ok, thanks for testing. =)
Quoted 2 lines
However, the zero-size vmcore problem is back on SN. But that is a dfiffernet problem.
Argh, more problems...
I found the problem. It was the "elfcorehdr" introduced in 2.6.21-rc1. Without specifying it, the
elfcorehdr_addris initialized toELFCORE_ADDR_MAX. Later, a check inreserve_elfcorehdrwill fail:
if (elfcorehdr_addr>=ELFCORE_ADDR_MAX)
return-EINVAL;Quoted 3 lines
Is it supposed to be a physical address to store elf core header? If so, it is not possible for SN to provide a physical address at boot time, just like in the case of crashkernel=X@Y where Y is not used.
Sorry, the elfcorehdr parameter is provided to the kdump kernel by kexec. The problem is in the
reserve_elfcorehdrlogic introduced in 2.6.21-rc1.Quoted 7 lines
When booting up the kdump kernel, i observed a failure in
reserve_elfcorehdr. The below are my debugging messages:
elfcorehdr_addr027fe4000, ELFCORE_ADDR_MAXÿffffffffffffff Cannot locate EFI vmcore descriptorreserve_elfcorehdr: vmcore descriptor size = 0reserve_memory: FAIL to reservereserve_elfcorehdrHi Tony,
Quoted 7 lines
The kernel code 2.6.21-rc3+ is fine wrt zero-size-vmcore issue.
I have been testing on a rhel5 environment. The
/sbin/kexecworked for me up to 2.6.20.I then built a new kexec from tot kexec-tools-testing git tree and i no longer see the zero-size-vmcore problem.
I take it that elfcorehdr is also correct in this environment?
The latest (ia64) kernels need a fairly recent kexec-tools-testing because of the change "kexec: Use EFI_LOADER_DATA for ELF core header". A recent kexec-tools-testing is probably needed for other reasons, though I can't think of them off-hand.
Signature · 3 lines
Horms H: http://www.vergenet.net/~horms/ W: http://www.valinux.co.jp/en/
Quoted 37 lines · Horms
Quoted 36 lines · Jay Lan
Quoted 24 lines · Jay Lan
Quoted 16 lines · Jay Lan
Magnus Damm wrote:
[snip]Quoted 8 lines
Quoted 3 lines
I tested on 2.6.21-rc3 with
DEBUG_VMturned on. The vanilla 2.6.21-rc3 without Nan-hai's patch, panicked on bugcheck onfree_initmem->free_pageas predicted. We still need this patch.Ok, thanks for testing. =)
Quoted 2 lines
However, the zero-size vmcore problem is back on SN. But that is a dfiffernet problem.
Argh, more problems...
I found the problem. It was the "elfcorehdr" introduced in 2.6.21-rc1. Without specifying it, the
elfcorehdr_addris initialized toELFCORE_ADDR_MAX. Later, a check inreserve_elfcorehdrwill fail:
if (elfcorehdr_addr>=ELFCORE_ADDR_MAX)
return-EINVAL;Quoted 3 lines
Is it supposed to be a physical address to store elf core header? If so, it is not possible for SN to provide a physical address at boot time, just like in the case of crashkernel=X@Y where Y is not used.
Sorry, the elfcorehdr parameter is provided to the kdump kernel by kexec. The problem is in the
reserve_elfcorehdrlogic introduced in 2.6.21-rc1.Quoted 7 lines
When booting up the kdump kernel, i observed a failure in
reserve_elfcorehdr. The below are my debugging messages:
elfcorehdr_addr027fe4000, ELFCORE_ADDR_MAXÿffffffffffffff Cannot locate EFI vmcore descriptorreserve_elfcorehdr: vmcore descriptor size = 0reserve_memory: FAIL to reservereserve_elfcorehdrHi Tony,
The kernel code 2.6.21-rc3+ is fine wrt zero-size-vmcore issue.
Quoted 7 lines
Quoted 5 lines
I have been testing on a rhel5 environment. The
/sbin/kexecworked for me up to 2.6.20.I then built a new kexec from tot kexec-tools-testing git tree and i no longer see the zero-size-vmcore problem.
I take it that elfcorehdr is also correct in this environment?
Yes. I got a good vmcore.
Regards,
- jay
Quoted 6 lines
The latest (ia64) kernels need a fairly recent kexec-tools-testing because of the change "kexec: Use
EFI_LOADER_DATAfor ELF core header". A recent kexec-tools-testing is probably needed for other reasons, though I can't think of them off-hand.
Quoted 37 lines · Zou Nan hai
Hi,
We have seenbad_pte_printwhen testing crashdump on an SN machine in
recent 2.6.20 kernel.
There are tons of bad pte print (pfn <max_low_pfn) reports when the
crash kernel boots up, all those reported bad pages are inside initmem range;
That is because if the crash kernel code and data happens to be at the
beginning of the 1st node.build_node_mapsindiscontig.cwill bypass reserved regions withfilter_rsvd_memory. Sincemin_low_pfnis calculated inbuild_node_map, so in this case,min_low_pfnwill be greater than kernel code and data.Because pages inside initmem are freed and reused later, we saw
pfn_validcheck fail on those pages.I think this theoretically happen on a normal kernel. When I check
min_low_pfnandmax_low_pfncalculation incontig.canddiscontig.c. I found more issues than this.1.
min_low_pfnandmax_low_pfncalculation is inconsistent betweencontig.canddiscontig.c,
min_low_pfnis calculated as the first page number of boot memmap incontig.c(Why? Though this may work at the most of the time, I don't think it is the right logic). It is calculated as the lowest physical memory page number bypass reserved regions indiscontig.c.
max_low_pfnis calculated include reserved regions incontig.c. It is
calculated exclude reserved regions indiscontig.c.2. If kernel code and data region is happen to be at the begin or the
end of physical memory, whenmin_low_pfnandmax_low_pfncalculation is bypassed kernel code and data, pages in initmem will report bad.3. initrd is also in reserved regions, if it is at the begin or at the
end of physical memory, kernel will refuse to reuse the memory. Because thevirt_addr_validcheck infree_initrd_mem.
Quoted 6 lines
So it is better to fix and clean up those issues.
Calculatemin_low_pfnandmax_low_pfnin a consistent way.Below is the patch, please review and comments
Signed-off-by Zou Nan hai <[email protected]>
Hi Nanhai,
this patch seems generaly ok to me. I've put it in my working tree to see if it helps or breaks anything. I've also made a few minor comments inline.
Quoted 32 lines
diff -Nraup
a/arch/ia64/mm/contig.cb/arch/ia64/mm/contig.carch/ia64/mm/contig.c +0
-20@@ -75,26 +75,6 @@ show_mem (void)unsigned long bootmap_start;/** -* find_max_pfn - adjust the maximum page number callback -* @start: start of range -* @end: end of range -* @arg: address of pointer to global max_pfn variable -* -* Passed as a callback function to efi_memmap_walk() to determine the highest -* available page frame number in the system. -*/ -int -find_max_pfn (unsigned long start,unsigned long end,void *arg) -{ -unsigned long *max_pfnp = arg, pfn; - - pfn = (PAGE_ALIGN (end -1 ) -PAGE_OFFSET ) >>PAGE_SHIFT ; -if (pfn > *max_pfnp) - *max_pfnp = pfn; -return 0 ; -} - -/** * find_bootmap_location - callback to find a memory area for the bootmap * @start: start of region * @end: end of region
arch/ia64/mm/contig.c find_memory (void) · line 138
Quoted 7 lines
arch/ia64/mm/contig.c +1
-3@@ -155,9 +135,10 @@ find_memory (void)reserve_memory ();/* first find highest page frame number */ - max_pfn =0 ; -efi_memmap_walk (find_max_pfn, &max_pfn); - + min_low_pfn =-1 ;
I think that this should be ~0UL rather than -1
as min_low_pfn is an unsigned long.
arch/ia64/mm/contig.c find_memory (void) · line 152
Quoted 13 lines
arch/ia64/mm/contig.c +5
-1+ max_low_pfn =0 ; +efi_memmap_walk (find_max_min_low_pfn,NULL ); + max_pfn = max_low_pfn;/* how many bytes to cover all the pages */ bootmap_size =bootmem_bootmap_pages (max_pfn) <<PAGE_SHIFT ;@@ -167,7 +148,8 @@ find_memory (void)if (bootmap_start = ~0UL )panic ("Cannot find %ld bytes for bootmap\n" , bootmap_size); - bootmap_size =init_bootmem (bootmap_start >>PAGE_SHIFT , max_pfn); + bootmap_size =init_bootmem_node (NODE_DATA (0 ), + (bootmap_start >>PAGE_SHIFT ),0 , max_pfn);
This seems like an akward way to get around the architecture-idependant behaviour of init_bootmem() which sets min_low_pfn and max_low_pfn. Though I guess its ok.
Quoted 27 lines
arch/ia64/mm/contig.c +0
-0/* Free all available memory, then mark bootmem-map as being in use. */ efi_memmap_walk (filter_rsvd_memory, free_bootmem);diff -Nraup
a/arch/ia64/mm/discontig.cb/arch/ia64/mm/discontig.carch/ia64/mm/discontig.c +1
-3@@ -86,9 +86,6 @@ static int __init build_node_maps(unsign bdp->node_low_pfn =max (epfn, bdp->node_low_pfn); } - min_low_pfn =min (min_low_pfn, bdp->node_boot_start>>PAGE_SHIFT ); - max_low_pfn =max (max_low_pfn, bdp->node_low_pfn); -return 0 ; }@@ -467,6 +464,7 @@ void __init find_memory(void)/* These actually end up getting called by call_pernode_memory() */ efi_memmap_walk (filter_rsvd_memory, build_node_maps);efi_memmap_walk (filter_rsvd_memory, find_pernode_space); +efi_memmap_walk (find_max_min_low_pfn,NULL );for_each_online_node (node)if (mem_data[node].bootmem_data.node_low_pfn) {diff -Nraup
a/arch/ia64/mm/init.cb/arch/ia64/mm/init.c
arch/ia64/mm/init.c count_reserved_pages (u64 start, u64 end · line 623
Quoted 8 lines
arch/ia64/mm/init.c +5
-0@@ -616,6 +616,22 @@ count_reserved_pages (u64 start, u64 endreturn 0 ; } +int +find_max_min_low_pfn (unsigned long start,unsigned long end,void *arg) +{ +unsigned long pfn_start, pfn_end; +#if CONFIG_FLATMEM
I think this should be #ifdef not #if, I currently see the following compiler warning:
arch/ia64/mm/init.c:655:5: warning: "CONFIG_FLATMEM" is not defined arch/ia64/mm/init.c:655:5: warning: "CONFIG_FLATMEM" is not defined
Quoted 36 lines
arch/ia64/mm/init.c +11
-0+ pfn_start = (PAGE_ALIGN (__pa (start))) >>PAGE_SHIFT ; + pfn_end = (PAGE_ALIGN (__pa (end -1 ))) >>PAGE_SHIFT ; +#else + pfn_start =GRANULEROUNDDOWN (__pa (start)) >>PAGE_SHIFT ; + pfn_end =GRANULEROUNDUP (__pa (end -1 )) >>PAGE_SHIFT ; +#endif + min_low_pfn =min (min_low_pfn, pfn_start); + max_low_pfn =max (max_low_pfn, pfn_end); +return 0 ; +} +/* * Boot command-line option "nolwsys" can be used to disable the use of any light-weight * system call handler. When this option is in effect, all fsyscalls will end up bubbling diff -Nraup
a/include/asm-ia64/meminit.hb/include/asm-ia64/meminit.hinclude/asm-ia64/meminit.h +1
-1@@ -35,6 +35,7 @@ extern void reserve_memory (void);extern void find_initrd (void );extern int filter_rsvd_memory (unsigned long start,unsigned long end,void *arg);extern void efi_memmap_init (unsigned long *,unsigned long *); +extern int find_max_min_low_pfn (unsigned long ,unsigned long ,void *);/* * For rounding an address to the next IA64_GRANULE_SIZE or order -To unsubscribe from this list: send the line "unsubscribe linux-ia64" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Signature · 3 lines
Horms H: http://www.vergenet.net/~horms/ W: http://www.valinux.co.jp/en/
Simon had one comment and two changes to Nan-hai's patches. Both changes make sense to me. I tested on SN with the both changes integrated.
I need this patch for SN to work. Simon, please comment if you need more testing on this patch. Thanks!
Quoted 189 lines · Horms
Quoted 36 lines · Zou Nan hai
Hi,
We have seenbad_pte_printwhen testing crashdump on an SN machine in
recent 2.6.20 kernel.
There are tons of bad pte print (pfn <max_low_pfn) reports when the
crash kernel boots up, all those reported bad pages are inside initmem range;
That is because if the crash kernel code and data happens to be at the
beginning of the 1st node.build_node_mapsindiscontig.cwill bypass reserved regions withfilter_rsvd_memory. Sincemin_low_pfnis calculated inbuild_node_map, so in this case,min_low_pfnwill be greater than kernel code and data.Because pages inside initmem are freed and reused later, we saw
pfn_validcheck fail on those pages.I think this theoretically happen on a normal kernel. When I check
min_low_pfnandmax_low_pfncalculation incontig.canddiscontig.c. I found more issues than this.1.
min_low_pfnandmax_low_pfncalculation is inconsistent betweencontig.canddiscontig.c,
min_low_pfnis calculated as the first page number of boot memmap incontig.c(Why? Though this may work at the most of the time, I don't think it is the right logic). It is calculated as the lowest physical memory page number bypass reserved regions indiscontig.c.
max_low_pfnis calculated include reserved regions incontig.c. It is
calculated exclude reserved regions indiscontig.c.2. If kernel code and data region is happen to be at the begin or the
end of physical memory, whenmin_low_pfnandmax_low_pfncalculation is bypassed kernel code and data, pages in initmem will report bad.3. initrd is also in reserved regions, if it is at the begin or at the
end of physical memory, kernel will refuse to reuse the memory. Because thevirt_addr_validcheck infree_initrd_mem.Quoted 6 lines
So it is better to fix and clean up those issues.
Calculatemin_low_pfnandmax_low_pfnin a consistent way.Below is the patch, please review and comments
Signed-off-by Zou Nan hai <[email protected]>Hi Nanhai,
this patch seems generaly ok to me. I've put it in my working tree to see if it helps or breaks anything. I've also made a few minor comments inline.
Quoted 31 lines
diff -Nraup
a/arch/ia64/mm/contig.cb/arch/ia64/mm/contig.carch/ia64/mm/contig.c +0
-20@@ -75,26 +75,6 @@ show_mem (void)unsigned long bootmap_start;/** -* find_max_pfn - adjust the maximum page number callback -* @start: start of range -* @end: end of range -* @arg: address of pointer to global max_pfn variable -* -* Passed as a callback function to efi_memmap_walk() to determine the highest -* available page frame number in the system. -*/ -int -find_max_pfn (unsigned long start,unsigned long end,void *arg) -{ -unsigned long *max_pfnp = arg, pfn; - - pfn = (PAGE_ALIGN (end -1 ) -PAGE_OFFSET ) >>PAGE_SHIFT ; -if (pfn > *max_pfnp) - *max_pfnp = pfn; -return 0 ; -} - -/** * find_bootmap_location - callback to find a memory area for the bootmap * @start: start of region * @end: end of region arch/ia64/mm/contig.c find_memory (void) · line 138
Quoted 7 lines
arch/ia64/mm/contig.c +1
-3@@ -155,9 +135,10 @@ find_memory (void)reserve_memory ();/* first find highest page frame number */ - max_pfn =0 ; -efi_memmap_walk (find_max_pfn, &max_pfn); - + min_low_pfn =-1 ;I think that this should be ~0UL rather than -1
asmin_low_pfnis an unsigned long.arch/ia64/mm/contig.c find_memory (void) · line 152
Quoted 13 lines
arch/ia64/mm/contig.c +5
-1+ max_low_pfn =0 ; +efi_memmap_walk (find_max_min_low_pfn,NULL ); + max_pfn = max_low_pfn;/* how many bytes to cover all the pages */ bootmap_size =bootmem_bootmap_pages (max_pfn) <<PAGE_SHIFT ;@@ -167,7 +148,8 @@ find_memory (void)if (bootmap_start = ~0UL )panic ("Cannot find %ld bytes for bootmap\n" , bootmap_size); - bootmap_size =init_bootmem (bootmap_start >>PAGE_SHIFT , max_pfn); + bootmap_size =init_bootmem_node (NODE_DATA (0 ), + (bootmap_start >>PAGE_SHIFT ),0 , max_pfn);This seems like an akward way to get around the architecture-idependant behaviour of
init_bootmem()which setsmin_low_pfnandmax_low_pfn. Though I guess its ok.Quoted 27 lines
arch/ia64/mm/contig.c +0
-0/* Free all available memory, then mark bootmem-map as being in use. */ efi_memmap_walk (filter_rsvd_memory, free_bootmem);diff -Nraup
a/arch/ia64/mm/discontig.cb/arch/ia64/mm/discontig.carch/ia64/mm/discontig.c +1
-3@@ -86,9 +86,6 @@ static int __init build_node_maps(unsign bdp->node_low_pfn =max (epfn, bdp->node_low_pfn); } - min_low_pfn =min (min_low_pfn, bdp->node_boot_start>>PAGE_SHIFT ); - max_low_pfn =max (max_low_pfn, bdp->node_low_pfn); -return 0 ; }@@ -467,6 +464,7 @@ void __init find_memory(void)/* These actually end up getting called by call_pernode_memory() */ efi_memmap_walk (filter_rsvd_memory, build_node_maps);efi_memmap_walk (filter_rsvd_memory, find_pernode_space); +efi_memmap_walk (find_max_min_low_pfn,NULL );for_each_online_node (node)if (mem_data[node].bootmem_data.node_low_pfn) {diff -Nraup
a/arch/ia64/mm/init.cb/arch/ia64/mm/init.carch/ia64/mm/init.c count_reserved_pages (u64 start, u64 end · line 623
Quoted 8 lines
arch/ia64/mm/init.c +5
-0@@ -616,6 +616,22 @@ count_reserved_pages (u64 start, u64 endreturn 0 ; } +int +find_max_min_low_pfn (unsigned long start,unsigned long end,void *arg) +{ +unsigned long pfn_start, pfn_end; +#if CONFIG_FLATMEM I think this should be #ifdef not #if, I currently see the following compiler warning:
arch/ia64/mm/init.c:655:5: warning: "CONFIG_FLATMEM" is not definedarch/ia64/mm/init.c:655:5: warning: "CONFIG_FLATMEM" is not definedQuoted 36 lines
arch/ia64/mm/init.c +11
-0+ pfn_start = (PAGE_ALIGN (__pa (start))) >>PAGE_SHIFT ; + pfn_end = (PAGE_ALIGN (__pa (end -1 ))) >>PAGE_SHIFT ; +#else + pfn_start =GRANULEROUNDDOWN (__pa (start)) >>PAGE_SHIFT ; + pfn_end =GRANULEROUNDUP (__pa (end -1 )) >>PAGE_SHIFT ; +#endif + min_low_pfn =min (min_low_pfn, pfn_start); + max_low_pfn =max (max_low_pfn, pfn_end); +return 0 ; +} +/* * Boot command-line option "nolwsys" can be used to disable the use of any light-weight * system call handler. When this option is in effect, all fsyscalls will end up bubbling diff -Nraup
a/include/asm-ia64/meminit.hb/include/asm-ia64/meminit.hinclude/asm-ia64/meminit.h +1
-1@@ -35,6 +35,7 @@ extern void reserve_memory (void);extern void find_initrd (void );extern int filter_rsvd_memory (unsigned long start,unsigned long end,void *arg);extern void efi_memmap_init (unsigned long *,unsigned long *); +extern int find_max_min_low_pfn (unsigned long ,unsigned long ,void *);/* * For rounding an address to the next IA64_GRANULE_SIZE or order -To unsubscribe from this list: send the line "unsubscribe linux-ia64" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html