A kexec kernel bootup hang is observed on Intel Atom cpu due to unmapped
EFI config table.
Currently EFI system table is identity-mapped for the kexec kernel, but EFI
config table is not mapped explicitly:
commit 6bbeb276b71f ("x86/kexec: Add the EFI system tables and ACPI
tables to the ident map")
Later in the following 2 commits, EFI config table will be accessed when
enabling sev at kernel startup. This may result in a page fault due to EFI
config table's unmapped address. Since the page fault occurs at an early
stage, it is unrecoverable and kernel hangs.
commit ec1c66af3a30 ("x86/compressed/64: Detect/setup SEV/SME features
earlier during boot")
commit c01fce9cef84 ("x86/compressed: Add SEV-SNP feature
detection/setup")
In addition, the issue doesn't appear on all systems, because the kexec
kernel uses Page Size Extension (PSE) for identity mapping. In most cases,
EFI config table can end up to be mapped into due to 1 GB page size.
However if nogbpages is set, or cpu doesn't support pdpe1gb feature
(e.g Intel Atom x6425RE cpu), EFI config table may not be mapped into
due to 2 MB page size, thus a page fault hang is more likely to happen.
In this patch, we will make sure the EFI config table is always mapped.
Signed-off-by: Tao Liu <[email protected]>
---
arch/x86/kernel/machine_kexec_64.c | 35 ++++++++++++++++++++++++++----
1 file changed, 31 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 1a3e2c05a8a5..755aa12f583f 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -28,6 +28,7 @@
#include <asm/setup.h>
#include <asm/set_memory.h>
#include <asm/cpu.h>
+#include <asm/efi.h>
#ifdef CONFIG_ACPI
/*
@@ -86,10 +87,12 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
#endif
static int
-map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p)
+map_efi_sys_cfg_tab(struct x86_mapping_info *info, pgd_t *level4p)
{
#ifdef CONFIG_EFI
unsigned long mstart, mend;
+ void *kaddr;
+ int ret;
if (!efi_enabled(EFI_BOOT))
return 0;
@@ -105,6 +108,30 @@ map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p)
if (!mstart)
return 0;
+ ret = kernel_ident_mapping_init(info, level4p, mstart, mend);
+ if (ret)
+ return ret;
+
+ kaddr = memremap(mstart, mend - mstart, MEMREMAP_WB);
+ if (!kaddr) {
+ pr_err("Could not map UEFI system table\n");
+ return -ENOMEM;
+ }
+
+ mstart = efi_config_table;
+
+ if (efi_enabled(EFI_64BIT)) {
+ efi_system_table_64_t *stbl = (efi_system_table_64_t *)kaddr;
+
+ mend = mstart + sizeof(efi_config_table_64_t) * stbl->nr_tables;
+ } else {
+ efi_system_table_32_t *stbl = (efi_system_table_32_t *)kaddr;
+
+ mend = mstart + sizeof(efi_config_table_32_t) * stbl->nr_tables;
+ }
+
+ memunmap(kaddr);
+
return kernel_ident_mapping_init(info, level4p, mstart, mend);
#endif
return 0;
@@ -244,10 +271,10 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
}
/*
- * Prepare EFI systab and ACPI tables for kexec kernel since they are
- * not covered by pfn_mapped.
+ * Prepare EFI systab, config table and ACPI tables for kexec kernel
+ * since they are not covered by pfn_mapped.
*/
- result = map_efi_systab(&info, level4p);
+ result = map_efi_sys_cfg_tab(&info, level4p);
if (result)
return result;
--
2.33.1
Hi Tao,
On 05/25/23 at 05:49pm, Tao Liu wrote:
> A kexec kernel bootup hang is observed on Intel Atom cpu due to unmapped
> EFI config table.
>
> Currently EFI system table is identity-mapped for the kexec kernel, but EFI
> config table is not mapped explicitly:
>
> commit 6bbeb276b71f ("x86/kexec: Add the EFI system tables and ACPI
> tables to the ident map")
>
> Later in the following 2 commits, EFI config table will be accessed when
> enabling sev at kernel startup. This may result in a page fault due to EFI
> config table's unmapped address. Since the page fault occurs at an early
> stage, it is unrecoverable and kernel hangs.
>
> commit ec1c66af3a30 ("x86/compressed/64: Detect/setup SEV/SME features
> earlier during boot")
> commit c01fce9cef84 ("x86/compressed: Add SEV-SNP feature
> detection/setup")
>
> In addition, the issue doesn't appear on all systems, because the kexec
> kernel uses Page Size Extension (PSE) for identity mapping. In most cases,
> EFI config table can end up to be mapped into due to 1 GB page size.
> However if nogbpages is set, or cpu doesn't support pdpe1gb feature
> (e.g Intel Atom x6425RE cpu), EFI config table may not be mapped into
> due to 2 MB page size, thus a page fault hang is more likely to happen.
>
> In this patch, we will make sure the EFI config table is always mapped.
Nice work. While you may need to rephrase above sentence, x86
maintainers don't like log with the 'this patch,' or 'we'. Please refer
to 'Changelog' part of Documentation/process/maintainer-tip.rst and
improve it.
>
> Signed-off-by: Tao Liu <[email protected]>
> ---
> arch/x86/kernel/machine_kexec_64.c | 35 ++++++++++++++++++++++++++----
> 1 file changed, 31 insertions(+), 4 deletions(-)
>
> diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
> index 1a3e2c05a8a5..755aa12f583f 100644
> --- a/arch/x86/kernel/machine_kexec_64.c
> +++ b/arch/x86/kernel/machine_kexec_64.c
> @@ -28,6 +28,7 @@
> #include <asm/setup.h>
> #include <asm/set_memory.h>
> #include <asm/cpu.h>
> +#include <asm/efi.h>
>
> #ifdef CONFIG_ACPI
> /*
> @@ -86,10 +87,12 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
> #endif
>
> static int
> -map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p)
> +map_efi_sys_cfg_tab(struct x86_mapping_info *info, pgd_t *level4p)
Can we call the function map_efi_tables() since we will map efi system
table, system config table. If you need add another table mapping here,
what would you call it, map_efi_sys_cfg_xxx_tab()?
Anyway, not very strong opinion as long as x86 maintainer likes it.
> {
> #ifdef CONFIG_EFI
> unsigned long mstart, mend;
> + void *kaddr;
> + int ret;
>
> if (!efi_enabled(EFI_BOOT))
> return 0;
> @@ -105,6 +108,30 @@ map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p)
> if (!mstart)
> return 0;
>
> + ret = kernel_ident_mapping_init(info, level4p, mstart, mend);
> + if (ret)
> + return ret;
> +
> + kaddr = memremap(mstart, mend - mstart, MEMREMAP_WB);
> + if (!kaddr) {
> + pr_err("Could not map UEFI system table\n");
> + return -ENOMEM;
> + }
> +
> + mstart = efi_config_table;
> +
> + if (efi_enabled(EFI_64BIT)) {
> + efi_system_table_64_t *stbl = (efi_system_table_64_t *)kaddr;
> +
> + mend = mstart + sizeof(efi_config_table_64_t) * stbl->nr_tables;
> + } else {
> + efi_system_table_32_t *stbl = (efi_system_table_32_t *)kaddr;
> +
> + mend = mstart + sizeof(efi_config_table_32_t) * stbl->nr_tables;
> + }
> +
> + memunmap(kaddr);
> +
> return kernel_ident_mapping_init(info, level4p, mstart, mend);
> #endif
> return 0;
> @@ -244,10 +271,10 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
> }
>
> /*
> - * Prepare EFI systab and ACPI tables for kexec kernel since they are
> - * not covered by pfn_mapped.
> + * Prepare EFI systab, config table and ACPI tables for kexec kernel
> + * since they are not covered by pfn_mapped.
> */
> - result = map_efi_systab(&info, level4p);
> + result = map_efi_sys_cfg_tab(&info, level4p);
> if (result)
> return result;
>
> --
> 2.33.1
>
Add Ard to CC.
On 05/25/23 at 05:49pm, Tao Liu wrote:
> A kexec kernel bootup hang is observed on Intel Atom cpu due to unmapped
> EFI config table.
>
> Currently EFI system table is identity-mapped for the kexec kernel, but EFI
> config table is not mapped explicitly:
>
> commit 6bbeb276b71f ("x86/kexec: Add the EFI system tables and ACPI
> tables to the ident map")
>
> Later in the following 2 commits, EFI config table will be accessed when
> enabling sev at kernel startup. This may result in a page fault due to EFI
> config table's unmapped address. Since the page fault occurs at an early
> stage, it is unrecoverable and kernel hangs.
>
> commit ec1c66af3a30 ("x86/compressed/64: Detect/setup SEV/SME features
> earlier during boot")
> commit c01fce9cef84 ("x86/compressed: Add SEV-SNP feature
> detection/setup")
>
> In addition, the issue doesn't appear on all systems, because the kexec
> kernel uses Page Size Extension (PSE) for identity mapping. In most cases,
> EFI config table can end up to be mapped into due to 1 GB page size.
> However if nogbpages is set, or cpu doesn't support pdpe1gb feature
> (e.g Intel Atom x6425RE cpu), EFI config table may not be mapped into
> due to 2 MB page size, thus a page fault hang is more likely to happen.
>
> In this patch, we will make sure the EFI config table is always mapped.
>
> Signed-off-by: Tao Liu <[email protected]>
> ---
> arch/x86/kernel/machine_kexec_64.c | 35 ++++++++++++++++++++++++++----
> 1 file changed, 31 insertions(+), 4 deletions(-)
>
> diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
> index 1a3e2c05a8a5..755aa12f583f 100644
> --- a/arch/x86/kernel/machine_kexec_64.c
> +++ b/arch/x86/kernel/machine_kexec_64.c
> @@ -28,6 +28,7 @@
> #include <asm/setup.h>
> #include <asm/set_memory.h>
> #include <asm/cpu.h>
> +#include <asm/efi.h>
>
> #ifdef CONFIG_ACPI
> /*
> @@ -86,10 +87,12 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
> #endif
>
> static int
> -map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p)
> +map_efi_sys_cfg_tab(struct x86_mapping_info *info, pgd_t *level4p)
> {
> #ifdef CONFIG_EFI
> unsigned long mstart, mend;
> + void *kaddr;
> + int ret;
>
> if (!efi_enabled(EFI_BOOT))
> return 0;
> @@ -105,6 +108,30 @@ map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p)
> if (!mstart)
> return 0;
>
> + ret = kernel_ident_mapping_init(info, level4p, mstart, mend);
> + if (ret)
> + return ret;
> +
> + kaddr = memremap(mstart, mend - mstart, MEMREMAP_WB);
> + if (!kaddr) {
> + pr_err("Could not map UEFI system table\n");
> + return -ENOMEM;
> + }
> +
> + mstart = efi_config_table;
> +
> + if (efi_enabled(EFI_64BIT)) {
> + efi_system_table_64_t *stbl = (efi_system_table_64_t *)kaddr;
> +
> + mend = mstart + sizeof(efi_config_table_64_t) * stbl->nr_tables;
> + } else {
> + efi_system_table_32_t *stbl = (efi_system_table_32_t *)kaddr;
> +
> + mend = mstart + sizeof(efi_config_table_32_t) * stbl->nr_tables;
> + }
> +
> + memunmap(kaddr);
> +
> return kernel_ident_mapping_init(info, level4p, mstart, mend);
> #endif
> return 0;
> @@ -244,10 +271,10 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
> }
>
> /*
> - * Prepare EFI systab and ACPI tables for kexec kernel since they are
> - * not covered by pfn_mapped.
> + * Prepare EFI systab, config table and ACPI tables for kexec kernel
> + * since they are not covered by pfn_mapped.
> */
> - result = map_efi_systab(&info, level4p);
> + result = map_efi_sys_cfg_tab(&info, level4p);
> if (result)
> return result;
>
> --
> 2.33.1
>
Hi Baoquan,
On Fri, May 26, 2023 at 12:08 PM Baoquan He <[email protected]> wrote:
>
> Hi Tao,
>
> On 05/25/23 at 05:49pm, Tao Liu wrote:
> > A kexec kernel bootup hang is observed on Intel Atom cpu due to unmapped
> > EFI config table.
> >
> > Currently EFI system table is identity-mapped for the kexec kernel, but EFI
> > config table is not mapped explicitly:
> >
> > commit 6bbeb276b71f ("x86/kexec: Add the EFI system tables and ACPI
> > tables to the ident map")
> >
> > Later in the following 2 commits, EFI config table will be accessed when
> > enabling sev at kernel startup. This may result in a page fault due to EFI
> > config table's unmapped address. Since the page fault occurs at an early
> > stage, it is unrecoverable and kernel hangs.
> >
> > commit ec1c66af3a30 ("x86/compressed/64: Detect/setup SEV/SME features
> > earlier during boot")
> > commit c01fce9cef84 ("x86/compressed: Add SEV-SNP feature
> > detection/setup")
> >
> > In addition, the issue doesn't appear on all systems, because the kexec
> > kernel uses Page Size Extension (PSE) for identity mapping. In most cases,
> > EFI config table can end up to be mapped into due to 1 GB page size.
> > However if nogbpages is set, or cpu doesn't support pdpe1gb feature
> > (e.g Intel Atom x6425RE cpu), EFI config table may not be mapped into
> > due to 2 MB page size, thus a page fault hang is more likely to happen.
> >
> > In this patch, we will make sure the EFI config table is always mapped.
>
> Nice work. While you may need to rephrase above sentence, x86
> maintainers don't like log with the 'this patch,' or 'we'. Please refer
> to 'Changelog' part of Documentation/process/maintainer-tip.rst and
> improve it.
OK, Thanks for the suggestion! I will get the sentence rephrased in v2.
>
> >
> > Signed-off-by: Tao Liu <[email protected]>
> > ---
> > arch/x86/kernel/machine_kexec_64.c | 35 ++++++++++++++++++++++++++----
> > 1 file changed, 31 insertions(+), 4 deletions(-)
> >
> > diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
> > index 1a3e2c05a8a5..755aa12f583f 100644
> > --- a/arch/x86/kernel/machine_kexec_64.c
> > +++ b/arch/x86/kernel/machine_kexec_64.c
> > @@ -28,6 +28,7 @@
> > #include <asm/setup.h>
> > #include <asm/set_memory.h>
> > #include <asm/cpu.h>
> > +#include <asm/efi.h>
> >
> > #ifdef CONFIG_ACPI
> > /*
> > @@ -86,10 +87,12 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
> > #endif
> >
> > static int
> > -map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p)
> > +map_efi_sys_cfg_tab(struct x86_mapping_info *info, pgd_t *level4p)
>
> Can we call the function map_efi_tables() since we will map efi system
> table, system config table. If you need add another table mapping here,
> what would you call it, map_efi_sys_cfg_xxx_tab()?
>
Yeah, map_efi_sys_cfg_xxx_tab() is surely a bad name. I agree with the
map_efi_tables() name.
Thanks,
Tao Liu
> Anyway, not very strong opinion as long as x86 maintainer likes it.
>
> > {
> > #ifdef CONFIG_EFI
> > unsigned long mstart, mend;
> > + void *kaddr;
> > + int ret;
> >
> > if (!efi_enabled(EFI_BOOT))
> > return 0;
> > @@ -105,6 +108,30 @@ map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p)
> > if (!mstart)
> > return 0;
> >
> > + ret = kernel_ident_mapping_init(info, level4p, mstart, mend);
> > + if (ret)
> > + return ret;
> > +
> > + kaddr = memremap(mstart, mend - mstart, MEMREMAP_WB);
> > + if (!kaddr) {
> > + pr_err("Could not map UEFI system table\n");
> > + return -ENOMEM;
> > + }
> > +
> > + mstart = efi_config_table;
> > +
> > + if (efi_enabled(EFI_64BIT)) {
> > + efi_system_table_64_t *stbl = (efi_system_table_64_t *)kaddr;
> > +
> > + mend = mstart + sizeof(efi_config_table_64_t) * stbl->nr_tables;
> > + } else {
> > + efi_system_table_32_t *stbl = (efi_system_table_32_t *)kaddr;
> > +
> > + mend = mstart + sizeof(efi_config_table_32_t) * stbl->nr_tables;
> > + }
> > +
> > + memunmap(kaddr);
> > +
> > return kernel_ident_mapping_init(info, level4p, mstart, mend);
> > #endif
> > return 0;
> > @@ -244,10 +271,10 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
> > }
> >
> > /*
> > - * Prepare EFI systab and ACPI tables for kexec kernel since they are
> > - * not covered by pfn_mapped.
> > + * Prepare EFI systab, config table and ACPI tables for kexec kernel
> > + * since they are not covered by pfn_mapped.
> > */
> > - result = map_efi_systab(&info, level4p);
> > + result = map_efi_sys_cfg_tab(&info, level4p);
> > if (result)
> > return result;
> >
> > --
> > 2.33.1
> >
>