[PATCH 2/2 v8] x86/kdump: clean up all the code related to the backup region
When the crashkernel kernel command line option is specified, the
low 1M memory will always be reserved, which makes that the memory
allocated later won't fall into the low 1M area, thereby, it's not
necessary to create a backup region and also no need to copy the
first 640k content to a backup region.
Currently, the code related to the backup region can be safely
removed, so lets clean up.
Signed-off-by: Lianbo Jiang
---
arch/x86/include/asm/kexec.h | 10
arch/x86/include/asm/purgatory.h | 10
arch/x86/kernel/crash.c| 87 --
arch/x86/kernel/machine_kexec_64.c | 47
arch/x86/purgatory/purgatory.c | 19 ---
5 files changed, 11 insertions(+), 162 deletions(-)
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 5e7d6b46de97..6802c59e8252 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -66,10 +66,6 @@ struct kimage;
# define KEXEC_ARCH KEXEC_ARCH_X86_64
#endif
-/* Memory to backup during crash kdump */
-#define KEXEC_BACKUP_SRC_START (0UL)
-#define KEXEC_BACKUP_SRC_END (640 * 1024UL - 1) /* 640K */
-
/*
* This function is responsible for capturing register states if coming
* via panic otherwise just fix up the ss and sp if coming via kernel
@@ -154,12 +150,6 @@ struct kimage_arch {
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
- /* Details of backup region */
- unsigned long backup_src_start;
- unsigned long backup_src_sz;
-
- /* Physical address of backup segment */
- unsigned long backup_load_addr;
/* Core ELF header buffer */
void *elf_headers;
diff --git a/arch/x86/include/asm/purgatory.h b/arch/x86/include/asm/purgatory.h
index 92c34e517da1..5528e9325049 100644
--- a/arch/x86/include/asm/purgatory.h
+++ b/arch/x86/include/asm/purgatory.h
@@ -6,16 +6,6 @@
#include
extern void purgatory(void);
-/*
- * These forward declarations serve two purposes:
- *
- * 1) Make sparse happy when checking arch/purgatory
- * 2) Document that these are required to be global so the symbol
- *lookup in kexec works
- */
-extern unsigned long purgatory_backup_dest;
-extern unsigned long purgatory_backup_src;
-extern unsigned long purgatory_backup_sz;
#endif /* __ASSEMBLY__ */
#endif /* _ASM_PURGATORY_H */
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index db2301afade5..40b04b6eb675 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -188,8 +188,6 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
#ifdef CONFIG_KEXEC_FILE
-static unsigned long crash_zero_bytes;
-
static int get_nr_ram_ranges_callback(struct resource *res, void *arg)
{
unsigned int *nr_ranges = arg;
@@ -232,6 +230,11 @@ static int elf_header_exclude_ranges(struct crash_mem
*cmem)
{
int ret = 0;
+ /* Exclude the low 1M because it is always reserved */
+ ret = crash_exclude_mem_range(cmem, 0, 1<<20);
+ if (ret)
+ return ret;
+
/* Exclude crashkernel region */
ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end);
if (ret)
@@ -261,9 +264,7 @@ static int prepare_elf_headers(struct kimage *image, void
**addr,
unsigned long *sz)
{
struct crash_mem *cmem;
- Elf64_Ehdr *ehdr;
- Elf64_Phdr *phdr;
- int ret, i;
+ int ret;
cmem = fill_up_crash_elf_data();
if (!cmem)
@@ -282,22 +283,7 @@ static int prepare_elf_headers(struct kimage *image, void
**addr,
/* By default prepare 64bit headers */
ret = crash_prepare_elf64_headers(cmem,
IS_ENABLED(CONFIG_X86_64), addr, sz);
- if (ret)
- goto out;
- /*
-* If a range matches backup region, adjust offset to backup
-* segment.
-*/
- ehdr = (Elf64_Ehdr *)*addr;
- phdr = (Elf64_Phdr *)(ehdr + 1);
- for (i = 0; i < ehdr->e_phnum; phdr++, i++)
- if (phdr->p_type == PT_LOAD &&
- phdr->p_paddr == image->arch.backup_src_start &&
- phdr->p_memsz == image->arch.backup_src_sz) {
- phdr->p_offset = image->arch.backup_load_addr;
- break;
- }
out:
vfree(cmem);
return ret;
@@ -336,19 +322,11 @@ static int memmap_exclude_ranges(struct kimage *image,
struct crash_mem *cmem,
unsigned long long mend)
{
unsigned long start, end;
- int ret = 0;
cmem->ranges[0].start = mstart;
cmem->ranges[0].end = mend;
cmem->nr_ranges = 1;
- /* Exclude Backup region */
- start = image->arch.backup_load_addr;
- end = start + image->arch.backup_src_sz - 1;
- ret = crash_exclude_mem_range(cmem, start, end);
- if (ret)
- return
[PATCH 0/2 v8] x86/kdump: Fix 'kmem -s' reported an invalid freepointer when SME was active
In purgatory(), the main things are as below: [1] verify sha256 hashes for various segments. Lets keep these codes, and do not touch the logic. [2] copy the first 640k content to a backup region. Lets safely remove it and clean all code related to backup region. This patch series will remove the backup region, because the current handling of copying the first 640k runs into problems when SME is active(https://bugzilla.kernel.org/show_bug.cgi?id=204793). The low 1M region will always be reserved when the crashkernel kernel command line option is specified. And this way makes it unnecessary to do anything with the low 1M region, because the memory allocated later won't fall into the low 1M area. This series includes two patches: [1] x86/kdump: always reserve the low 1M when the crashkernel option is specified The low 1M region will always be reserved when the crashkernel kernel command line option is specified, which ensures that the memory allocated later won't fall into the low 1M area. [2] x86/kdump: clean up all the code related to the backup region Remove the backup region and clean up. Changes since v1: [1] Add extra checking condition: when the crashkernel option is specified, reserve the low 640k area. Changes since v2: [1] Reserve the low 1M region when the crashkernel option is only specified.(Suggested by Eric) [2] Remove the unused crash_copy_backup_region() [3] Remove the backup region and clean up [4] Split them into three patches Changes since v3: [1] Improve the first patch's log [2] Improve the third patch based on Eric's suggestions Changes since v4: [1] Correct some typos, and also improve the first patch's log [2] Add a new function kexec_reserve_low_1MiB() in kernel/kexec_core.c and which is called by reserve_real_mode(). (Suggested by Boris) Changes since v5: [1] Call the cmdline_find_option() instead of strstr() to check the crashkernel option. (Suggested by Hatayama) [2] Add a weak function kexec_reserve_low_1MiB() in kernel/kexec_core.c, and implement the kexec_reserve_low_1MiB() in arch/x86/kernel/ machine_kexec_64.c so that it does not cause the compile error on non-x86 kernel, and also ensures that it can work well on x86 kernel. Changes since v6: [1] Move the kexec_reserve_low_1MiB() to arch/x86/kernel/crash.c and also move its declaration function to arch/x86/include/asm/crash.h (Suggested by Dave Young) [2] Adjust the corresponding header files. Changes since v7: [1] Change the function name from kexec_reserve_low_1MiB() to crash_reserve_low_1M(). Lianbo Jiang (2): x86/kdump: always reserve the low 1M when the crashkernel option is specified x86/kdump: clean up all the code related to the backup region arch/x86/include/asm/crash.h | 6 ++ arch/x86/include/asm/kexec.h | 10 --- arch/x86/include/asm/purgatory.h | 10 --- arch/x86/kernel/crash.c| 102 - arch/x86/kernel/machine_kexec_64.c | 47 - arch/x86/purgatory/purgatory.c | 19 -- arch/x86/realmode/init.c | 2 + 7 files changed, 34 insertions(+), 162 deletions(-) -- 2.17.1 ___ kexec mailing list kexec@lists.infradead.org http://lists.infradead.org/mailman/listinfo/kexec
[PATCH 1/2 v8] x86/kdump: always reserve the low 1M when the crashkernel option is specified
Kdump kernel will reuse the first 640k region because the real mode
trampoline has to work in this area. When the vmcore is dumped, the
old memory in this area may be accessed, therefore, kernel has to
copy the contents of the first 640k area to a backup region so that
kdump kernel can read the old memory from the backup area of the
first 640k area, which is done in the purgatory().
But, the current handling of copying the first 640k area runs into
problems when SME is enabled, kernel does not properly copy these
old memory to the backup area in the purgatory(), thereby, kdump
kernel reads out the encrypted contents, because the kdump kernel
must access the first kernel's memory with the encryption bit set
when SME is enabled in the first kernel. Please refer to this link:
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=204793
Finally, it causes the following errors, and the crash tool gets
invalid pointers when parsing the vmcore.
crash> kmem -s|grep -i invalid
kmem: dma-kmalloc-512: slab:d77680001c00 invalid
freepointer:a6086ac099f0c5a4
kmem: dma-kmalloc-512: slab:d77680001c00 invalid
freepointer:a6086ac099f0c5a4
crash>
To avoid the above errors, when the crashkernel option is specified,
lets reserve the remaining low 1M memory(after reserving real mode
memory) so that the allocated memory does not fall into the low 1M
area, which makes us not to copy the first 640k content to a backup
region in purgatory(). This indicates that it does not need to be
included in crash dumps or used for anything except the processor
trampolines that must live in the low 1M.
Signed-off-by: Lianbo Jiang
---
arch/x86/include/asm/crash.h | 6 ++
arch/x86/kernel/crash.c | 15 +++
arch/x86/realmode/init.c | 2 ++
3 files changed, 23 insertions(+)
diff --git a/arch/x86/include/asm/crash.h b/arch/x86/include/asm/crash.h
index 0acf5ee45a21..3dff55f4ed9d 100644
--- a/arch/x86/include/asm/crash.h
+++ b/arch/x86/include/asm/crash.h
@@ -8,4 +8,10 @@ int crash_setup_memmap_entries(struct kimage *image,
struct boot_params *params);
void crash_smp_send_stop(void);
+#ifdef CONFIG_KEXEC_CORE
+void __init crash_reserve_low_1M(void);
+#else
+static inline void __init crash_reserve_low_1M(void) { }
+#endif
+
#endif /* _ASM_X86_CRASH_H */
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index eb651fbde92a..db2301afade5 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -24,6 +24,7 @@
#include
#include
#include
+#include
#include
#include
@@ -39,6 +40,7 @@
#include
#include
#include
+#include
/* Used while preparing memory map entries for second kernel */
struct crash_memmap_data {
@@ -68,6 +70,19 @@ static inline void cpu_crash_vmclear_loaded_vmcss(void)
rcu_read_unlock();
}
+/*
+ * When the crashkernel option is specified, only use the low
+ * 1M for the real mode trampoline.
+ */
+void __init crash_reserve_low_1M(void)
+{
+ if (cmdline_find_option(boot_command_line, "crashkernel",
+ NULL, 0) > 0) {
+ memblock_reserve(0, 1<<20);
+ pr_info("Reserving the low 1M of memory for crashkernel\n");
+ }
+}
+
#if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index 7dce39c8c034..262f83cad355 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -8,6 +8,7 @@
#include
#include
#include
+#include
struct real_mode_header *real_mode_header;
u32 *trampoline_cr4_features;
@@ -34,6 +35,7 @@ void __init reserve_real_mode(void)
memblock_reserve(mem, size);
set_real_mode_mem(mem);
+ crash_reserve_low_1M();
}
static void __init setup_real_mode(void)
--
2.17.1
___
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec
Re: Makedumpfile help for 5.4.0.rc3 : Arm
Hi Kazu,
Sorry for top posting, but I am on leave for Diwali Holidays and will
return to the office in a couple of days.
I have the solution/patchset ready and I just need to finish the
commit messages to make sure they are self-explanatory for upstream
acceptance.
I will try to post them and also answer your email in detail when I
return back from holidays.
Thanks for your patience.
Regards,
Bhupesh
(Sent from my Android Phone)
On Tue, Oct 29, 2019 at 2:23 AM Kazuhito Hagio wrote:
>
> Hi Bhupesh,
>
> > -Original Message-
> > > > I am working on the changes in the vmcoreinfo after the 52-bit VA
> > > > changes from Steve were accepted in Linux 5.4-rc1 ("Support for 52-bit
> > > > virtual addressing in kernel space”).
> > >
> > >
> > >I don’t see a commit with this title in linux-stable ; Could you be
> > > a little more specific what
> > file that was applied to ?
> >
> > You can have a look at the following commit (and dependencies) in
> > Linus's tree
> > (git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git)
> > which introduced 52-bit kernel VAs for arm64 architecture:
> >
> > commit b6d00d47e81a49f6cf462518c10408f37a3e6785
> > Author: Steve Capper
> > Date: Wed Aug 7 16:55:22 2019 +0100
> >
> > arm64: mm: Introduce 52-bit Kernel VAs
>
> Thank you for working on this.
>
> I've also had a look at them, and my understanding is that we need
> in vmcoreinfo at least:
>
> - TCR_EL1.T1SZ (almost equals to vabits_actual) to determine:
> o PAGE_OFFSET
> o whether the kernel has the "flipped" linear map and the others.
> We need a fix to __pa() with it. (see the patch below)
>
> - PA_BITS or MAX_PHYSMEM_BITS to determine:
> o whether SPARSEMEM_EXTREME or not, in is_sparsemem_extreme()
> o whether the kernel has 48-bit or 52-bit PA to switch
> the calculation of pte-to-paddr. (this might be unnecessary?)
>
> Is this right?
>
> And wrote a very draft patch, which works on a 5.4-rc4 kernel that
> I modified to have NUMBER(vabits_actual) and NUMBER(MAX_PHYSMEM_BITS),
> with VA_BITS=48 config or VA_BITS=52 config running in 48-bit mode.
> https://github.com/k-hagio/makedumpfile/commit/fd9d86ea05b38e9edbb8c0ac3ebd612d5d485df3
>
> (I don't intend to export them as they are, it's just for an experiment.
> And no support for --mem-usage option, "real" 52-bit PA, and so on.)
>
> As for MAX_PHYSMEM_BITS, I don't stick to export it for all architectures,
> although I told you that it would be better to do so in the past.
> If it's hard to do so, it's fine with me to export it or something similar
> only for arm64 for now..
>
> Your thoughts?
>
> Thanks,
> Kazu
>
___
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec
Re: [PATCH 1/2 v7] x86/kdump: always reserve the low 1MiB when the crashkernel option is specified
On 10/29/19 at 02:06pm, lijiang wrote:
> >> struct crash_memmap_data {
> >> @@ -68,6 +70,19 @@ static inline void cpu_crash_vmclear_loaded_vmcss(void)
> >>rcu_read_unlock();
> >> }
> >>
> >> +/*
> >> + * When the crashkernel option is specified, only use the low
> >> + * 1MiB for the real mode trampoline.
> >> + */
> >> +void __init kexec_reserve_low_1MiB(void)
> >
> > Thanks for the effort, Lianbo. I believe everyone is confident with this
> > solution and fix.
> >
> > I have a tiny concern, why the function name is
> > kexec_reserve_low_1MiB(), but not kexec_reserve_low_1M()?
>
> Thanks for your comment, Baoquan.
>
> It means that kernel will reserve 1M 'Byte' memory, the function name does not
> have special meaning.
>
> Would you mind if i change it to the crash_reserve_low_1M()?
Yes, crash_xx looks better since it's only related to crash dumping. As
for 1M, not very sure, see if other people have comment about it. Anyway,
crash_reserve_low_1M() looks good to me. Thanks.
>
> void __init crash_reserve_low_1M(void)
>
> Thanks.
> Lianbo
>
> > I searched in kernel code with below filter, didn't see MiB appearing in
> > a function name. I am not sure about it either, just ask.
> >
> > git grep "_[1-9]*M " arch/ kernel/ mm include/ drivers/ net/ init fs
> > crypto/ certs/ ipc lib
> >
> > Thanks
> > Baoquan
> >
> >> +{
> >> + if (cmdline_find_option(boot_command_line, "crashkernel",
> >> + NULL, 0) > 0) {
> >> + memblock_reserve(0, 1<<20);
> >> + pr_info("Reserving the low 1MiB of memory for crashkernel\n");
> >> + }
> >> +}
> >> +
> >> #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
> >>
> >> static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
> >> diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
> >> index 7dce39c8c034..b8bbd0017ca8 100644
> >> --- a/arch/x86/realmode/init.c
> >> +++ b/arch/x86/realmode/init.c
> >> @@ -8,6 +8,7 @@
> >> #include
> >> #include
> >> #include
> >> +#include
> >>
> >> struct real_mode_header *real_mode_header;
> >> u32 *trampoline_cr4_features;
> >> @@ -34,6 +35,7 @@ void __init reserve_real_mode(void)
> >>
> >>memblock_reserve(mem, size);
> >>set_real_mode_mem(mem);
> >> + kexec_reserve_low_1MiB();
> >> }
> >>
> >> static void __init setup_real_mode(void)
> >> --
> >> 2.17.1
> >>
___
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec
Re: [PATCH 1/2 v7] x86/kdump: always reserve the low 1MiB when the crashkernel option is specified
在 2019年10月29日 13:28, Baoquan He 写道:
> On 10/29/19 at 10:10am, Lianbo Jiang wrote:
>> Kdump kernel will reuse the first 640k region because the real mode
>> trampoline has to work in this area. When the vmcore is dumped, the
>> old memory in this area may be accessed, therefore, kernel has to
>> copy the contents of the first 640k area to a backup region so that
>> kdump kernel can read the old memory from the backup area of the
>> first 640k area, which is done in the purgatory().
>>
>> But, the current handling of copying the first 640k area runs into
>> problems when SME is enabled, kernel does not properly copy these
>> old memory to the backup area in the purgatory(), thereby, kdump
>> kernel reads out the encrypted contents, because the kdump kernel
>> must access the first kernel's memory with the encryption bit set
>> when SME is enabled in the first kernel. Please refer to this link:
>>
>> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=204793
>>
>> Finally, it causes the following errors, and the crash tool gets
>> invalid pointers when parsing the vmcore.
>>
>> crash> kmem -s|grep -i invalid
>> kmem: dma-kmalloc-512: slab:d77680001c00 invalid
>> freepointer:a6086ac099f0c5a4
>> kmem: dma-kmalloc-512: slab:d77680001c00 invalid
>> freepointer:a6086ac099f0c5a4
>> crash>
>>
>> To avoid the above errors, when the crashkernel option is specified,
>> lets reserve the remaining low 1MiB memory(after reserving real mode
>> memory) so that the allocated memory does not fall into the low 1MiB
>> area, which makes us not to copy the first 640k content to a backup
>> region in purgatory(). This indicates that it does not need to be
>> included in crash dumps or used for anything except the processor
>> trampolines that must live in the low 1MiB.
>>
>> Signed-off-by: Lianbo Jiang
>> ---
>> arch/x86/include/asm/crash.h | 6 ++
>> arch/x86/kernel/crash.c | 15 +++
>> arch/x86/realmode/init.c | 2 ++
>> 3 files changed, 23 insertions(+)
>>
>> diff --git a/arch/x86/include/asm/crash.h b/arch/x86/include/asm/crash.h
>> index 0acf5ee45a21..3e966a3dc823 100644
>> --- a/arch/x86/include/asm/crash.h
>> +++ b/arch/x86/include/asm/crash.h
>> @@ -8,4 +8,10 @@ int crash_setup_memmap_entries(struct kimage *image,
>> struct boot_params *params);
>> void crash_smp_send_stop(void);
>>
>> +#ifdef CONFIG_KEXEC_CORE
>> +void __init kexec_reserve_low_1MiB(void);
>> +#else
>> +static inline void __init kexec_reserve_low_1MiB(void) { }
>> +#endif
>> +
>> #endif /* _ASM_X86_CRASH_H */
>> diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
>> index eb651fbde92a..144f519aef29 100644
>> --- a/arch/x86/kernel/crash.c
>> +++ b/arch/x86/kernel/crash.c
>> @@ -24,6 +24,7 @@
>> #include
>> #include
>> #include
>> +#include
>>
>> #include
>> #include
>> @@ -39,6 +40,7 @@
>> #include
>> #include
>> #include
>> +#include
>>
>> /* Used while preparing memory map entries for second kernel */
>> struct crash_memmap_data {
>> @@ -68,6 +70,19 @@ static inline void cpu_crash_vmclear_loaded_vmcss(void)
>> rcu_read_unlock();
>> }
>>
>> +/*
>> + * When the crashkernel option is specified, only use the low
>> + * 1MiB for the real mode trampoline.
>> + */
>> +void __init kexec_reserve_low_1MiB(void)
>
> Thanks for the effort, Lianbo. I believe everyone is confident with this
> solution and fix.
>
> I have a tiny concern, why the function name is
> kexec_reserve_low_1MiB(), but not kexec_reserve_low_1M()?
Thanks for your comment, Baoquan.
It means that kernel will reserve 1M 'Byte' memory, the function name does not
have special meaning.
Would you mind if i change it to the crash_reserve_low_1M()?
void __init crash_reserve_low_1M(void)
Thanks.
Lianbo
> I searched in kernel code with below filter, didn't see MiB appearing in
> a function name. I am not sure about it either, just ask.
>
> git grep "_[1-9]*M " arch/ kernel/ mm include/ drivers/ net/ init fs crypto/
> certs/ ipc lib
>
> Thanks
> Baoquan
>
>> +{
>> +if (cmdline_find_option(boot_command_line, "crashkernel",
>> +NULL, 0) > 0) {
>> +memblock_reserve(0, 1<<20);
>> +pr_info("Reserving the low 1MiB of memory for crashkernel\n");
>> +}
>> +}
>> +
>> #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
>>
>> static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
>> diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
>> index 7dce39c8c034..b8bbd0017ca8 100644
>> --- a/arch/x86/realmode/init.c
>> +++ b/arch/x86/realmode/init.c
>> @@ -8,6 +8,7 @@
>> #include
>> #include
>> #include
>> +#include
>>
>> struct real_mode_header *real_mode_header;
>> u32 *trampoline_cr4_features;
>> @@ -34,6 +35,7 @@ void __init reserve_real_mode(void)
>>
>> memblock_reserve(mem, size);
>> set_real_mode_mem(mem);
>> +kexec_reserve_low_1MiB();
>> }
>>
>> static void __init setup_real_mode(void)
