Patchwork [2/4] efi/arm: defer persistent reservations until after paging_init()

login
register
mail settings
Submitter Ard Biesheuvel
Date Nov. 6, 2018, 11:37 a.m.
Message ID <20181106113732.16351-3-ard.biesheuvel@linaro.org>
Download mbox | patch
Permalink /patch/650351/
State New
Headers show

Comments

Ard Biesheuvel - Nov. 6, 2018, 11:37 a.m.
The new memory EFI reservation feature we introduced to allow memory
reservations to persist across kexec may trigger an unbounded number
of calls to memblock_reserve(). The memblock subsystem can deal with
this fine, but not before memblock resizing is enabled, which we can
only do after paging_init(), when the memory we reallocate the array
into is actually mapped.

So break out the memreserve table processing into a separate function
and call if after paging_init() on both arm64 and ARM.

Cc: Russell King <linux@armlinux.org.uk>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm/kernel/setup.c    | 1 +
 arch/arm64/kernel/setup.c  | 1 +
 drivers/firmware/efi/efi.c | 8 ++++++--
 include/linux/efi.h        | 7 +++++++
 4 files changed, 15 insertions(+), 2 deletions(-)
Ard Biesheuvel - Nov. 6, 2018, 7:02 p.m.
On 6 November 2018 at 12:37, Ard Biesheuvel <ard.biesheuvel@linaro.org> wrote:
> The new memory EFI reservation feature we introduced to allow memory
> reservations to persist across kexec may trigger an unbounded number
> of calls to memblock_reserve(). The memblock subsystem can deal with
> this fine, but not before memblock resizing is enabled, which we can
> only do after paging_init(), when the memory we reallocate the array
> into is actually mapped.
>
> So break out the memreserve table processing into a separate function
> and call if after paging_init() on both arm64 and ARM.
>
> Cc: Russell King <linux@armlinux.org.uk>
> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>

Russell,

If you are ok with this patch, may I have your ack please? I would
like to send it out before the end of the week.

Thanks,

> ---
>  arch/arm/kernel/setup.c    | 1 +
>  arch/arm64/kernel/setup.c  | 1 +
>  drivers/firmware/efi/efi.c | 8 ++++++--
>  include/linux/efi.h        | 7 +++++++
>  4 files changed, 15 insertions(+), 2 deletions(-)
>
> diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
> index ac7e08886863..e99f12eaf390 100644
> --- a/arch/arm/kernel/setup.c
> +++ b/arch/arm/kernel/setup.c
> @@ -1117,6 +1117,7 @@ void __init setup_arch(char **cmdline_p)
>         early_ioremap_reset();
>
>         paging_init(mdesc);
> +       efi_apply_persistent_mem_reservations();
>         request_standard_resources(mdesc);
>
>         if (mdesc->restart)
> diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
> index 953e316521fc..f4fc1e0544b7 100644
> --- a/arch/arm64/kernel/setup.c
> +++ b/arch/arm64/kernel/setup.c
> @@ -313,6 +313,7 @@ void __init setup_arch(char **cmdline_p)
>         arm64_memblock_init();
>
>         paging_init();
> +       efi_apply_persistent_mem_reservations();
>
>         acpi_table_upgrade();
>
> diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
> index 249eb70691b0..55e4ea20bdc3 100644
> --- a/drivers/firmware/efi/efi.c
> +++ b/drivers/firmware/efi/efi.c
> @@ -592,7 +592,11 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz,
>
>                 early_memunmap(tbl, sizeof(*tbl));
>         }
> +       return 0;
> +}
>
> +int __init efi_apply_persistent_mem_reservations(void)
> +{
>         if (efi.mem_reserve != EFI_INVALID_TABLE_ADDR) {
>                 unsigned long prsv = efi.mem_reserve;
>
> @@ -602,7 +606,7 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz,
>                         /* reserve the entry itself */
>                         memblock_reserve(prsv, sizeof(*rsv));
>
> -                       rsv = early_memremap(prsv, sizeof(*rsv));
> +                       rsv = memremap(prsv, sizeof(*rsv), MEMREMAP_WB);
>                         if (rsv == NULL) {
>                                 pr_err("Could not map UEFI memreserve entry!\n");
>                                 return -ENOMEM;
> @@ -612,7 +616,7 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz,
>                                 memblock_reserve(rsv->base, rsv->size);
>
>                         prsv = rsv->next;
> -                       early_memunmap(rsv, sizeof(*rsv));
> +                       memunmap(rsv);
>                 }
>         }
>
> diff --git a/include/linux/efi.h b/include/linux/efi.h
> index 845174e113ce..100ce4a4aff6 100644
> --- a/include/linux/efi.h
> +++ b/include/linux/efi.h
> @@ -1167,6 +1167,8 @@ static inline bool efi_enabled(int feature)
>  extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused);
>
>  extern bool efi_is_table_address(unsigned long phys_addr);
> +
> +extern int efi_apply_persistent_mem_reservations(void);
>  #else
>  static inline bool efi_enabled(int feature)
>  {
> @@ -1185,6 +1187,11 @@ static inline bool efi_is_table_address(unsigned long phys_addr)
>  {
>         return false;
>  }
> +
> +static inline int efi_apply_persistent_mem_reservations(void)
> +{
> +       return 0;
> +}
>  #endif
>
>  extern int efi_status_to_err(efi_status_t status);
> --
> 2.19.1
>
Russell King - ARM Linux - Nov. 6, 2018, 7:08 p.m.
On Tue, Nov 06, 2018 at 08:02:58PM +0100, Ard Biesheuvel wrote:
> On 6 November 2018 at 12:37, Ard Biesheuvel <ard.biesheuvel@linaro.org> wrote:
> > The new memory EFI reservation feature we introduced to allow memory
> > reservations to persist across kexec may trigger an unbounded number
> > of calls to memblock_reserve(). The memblock subsystem can deal with
> > this fine, but not before memblock resizing is enabled, which we can
> > only do after paging_init(), when the memory we reallocate the array
> > into is actually mapped.
> >
> > So break out the memreserve table processing into a separate function
> > and call if after paging_init() on both arm64 and ARM.
> >
> > Cc: Russell King <linux@armlinux.org.uk>
> > Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> 
> Russell,
> 
> If you are ok with this patch, may I have your ack please? I would
> like to send it out before the end of the week.

You're not going to get a quick answer to this, because it needs me to
investigate what the effect of this change actually is by code review.
I can't guarantee when I'll get around to that.
Ard Biesheuvel - Nov. 6, 2018, 8:06 p.m.
On 6 November 2018 at 20:08, Russell King - ARM Linux
<linux@armlinux.org.uk> wrote:
> On Tue, Nov 06, 2018 at 08:02:58PM +0100, Ard Biesheuvel wrote:
>> On 6 November 2018 at 12:37, Ard Biesheuvel <ard.biesheuvel@linaro.org> wrote:
>> > The new memory EFI reservation feature we introduced to allow memory
>> > reservations to persist across kexec may trigger an unbounded number
>> > of calls to memblock_reserve(). The memblock subsystem can deal with
>> > this fine, but not before memblock resizing is enabled, which we can
>> > only do after paging_init(), when the memory we reallocate the array
>> > into is actually mapped.
>> >
>> > So break out the memreserve table processing into a separate function
>> > and call if after paging_init() on both arm64 and ARM.
>> >
>> > Cc: Russell King <linux@armlinux.org.uk>
>> > Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
>>
>> Russell,
>>
>> If you are ok with this patch, may I have your ack please? I would
>> like to send it out before the end of the week.
>
> You're not going to get a quick answer to this, because it needs me to
> investigate what the effect of this change actually is by code review.
> I can't guarantee when I'll get around to that.
>

Fair enough.

I will drop the ARM hunk for now then, and we'll fix ARM when you have
more time.

Thanks,
Russell King - ARM Linux - Nov. 6, 2018, 11:49 p.m.
On Tue, Nov 06, 2018 at 09:06:56PM +0100, Ard Biesheuvel wrote:
> On 6 November 2018 at 20:08, Russell King - ARM Linux
> <linux@armlinux.org.uk> wrote:
> > On Tue, Nov 06, 2018 at 08:02:58PM +0100, Ard Biesheuvel wrote:
> >> On 6 November 2018 at 12:37, Ard Biesheuvel <ard.biesheuvel@linaro.org> wrote:
> >> > The new memory EFI reservation feature we introduced to allow memory
> >> > reservations to persist across kexec may trigger an unbounded number
> >> > of calls to memblock_reserve(). The memblock subsystem can deal with
> >> > this fine, but not before memblock resizing is enabled, which we can
> >> > only do after paging_init(), when the memory we reallocate the array
> >> > into is actually mapped.
> >> >
> >> > So break out the memreserve table processing into a separate function
> >> > and call if after paging_init() on both arm64 and ARM.
> >> >
> >> > Cc: Russell King <linux@armlinux.org.uk>
> >> > Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> >>
> >> Russell,
> >>
> >> If you are ok with this patch, may I have your ack please? I would
> >> like to send it out before the end of the week.
> >
> > You're not going to get a quick answer to this, because it needs me to
> > investigate what the effect of this change actually is by code review.
> > I can't guarantee when I'll get around to that.
> >
> 
> Fair enough.
> 
> I will drop the ARM hunk for now then, and we'll fix ARM when you have
> more time.

I don't see how you can do that - you're dropping the processing of
reserved areas out of the efi_config_parse_tables() path, so that
won't happen any more on ARM if you don't apply the ARM hunk.

So what I see at the moment is that efi_config_parse_tables() is
called prior to paging_init() - and prior to our memblock
initialisation, and you're proposing to move the processing that
marks blocks as reserved immediately after paging_init(), and
to use the normal memremap() interface to map stuff.

I'm not convinced this will work - the memory allocators have not
been setup at this point, so using memremap() will try to allocate
page tables and potentially fail.  If the normal allocators are
setup, it's way too late to be calling memblock_reserve() - the
memory will have been passed over to the page allocator according
to which memblocks are available but not reserved.

The normal page allocator is setup by mem_init(), which happens
way after setup_arch() has returned.

So, I don't see how your patch can be correct at the moment.

Patch

diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index ac7e08886863..e99f12eaf390 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -1117,6 +1117,7 @@  void __init setup_arch(char **cmdline_p)
 	early_ioremap_reset();
 
 	paging_init(mdesc);
+	efi_apply_persistent_mem_reservations();
 	request_standard_resources(mdesc);
 
 	if (mdesc->restart)
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 953e316521fc..f4fc1e0544b7 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -313,6 +313,7 @@  void __init setup_arch(char **cmdline_p)
 	arm64_memblock_init();
 
 	paging_init();
+	efi_apply_persistent_mem_reservations();
 
 	acpi_table_upgrade();
 
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 249eb70691b0..55e4ea20bdc3 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -592,7 +592,11 @@  int __init efi_config_parse_tables(void *config_tables, int count, int sz,
 
 		early_memunmap(tbl, sizeof(*tbl));
 	}
+	return 0;
+}
 
+int __init efi_apply_persistent_mem_reservations(void)
+{
 	if (efi.mem_reserve != EFI_INVALID_TABLE_ADDR) {
 		unsigned long prsv = efi.mem_reserve;
 
@@ -602,7 +606,7 @@  int __init efi_config_parse_tables(void *config_tables, int count, int sz,
 			/* reserve the entry itself */
 			memblock_reserve(prsv, sizeof(*rsv));
 
-			rsv = early_memremap(prsv, sizeof(*rsv));
+			rsv = memremap(prsv, sizeof(*rsv), MEMREMAP_WB);
 			if (rsv == NULL) {
 				pr_err("Could not map UEFI memreserve entry!\n");
 				return -ENOMEM;
@@ -612,7 +616,7 @@  int __init efi_config_parse_tables(void *config_tables, int count, int sz,
 				memblock_reserve(rsv->base, rsv->size);
 
 			prsv = rsv->next;
-			early_memunmap(rsv, sizeof(*rsv));
+			memunmap(rsv);
 		}
 	}
 
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 845174e113ce..100ce4a4aff6 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1167,6 +1167,8 @@  static inline bool efi_enabled(int feature)
 extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused);
 
 extern bool efi_is_table_address(unsigned long phys_addr);
+
+extern int efi_apply_persistent_mem_reservations(void);
 #else
 static inline bool efi_enabled(int feature)
 {
@@ -1185,6 +1187,11 @@  static inline bool efi_is_table_address(unsigned long phys_addr)
 {
 	return false;
 }
+
+static inline int efi_apply_persistent_mem_reservations(void)
+{
+	return 0;
+}
 #endif
 
 extern int efi_status_to_err(efi_status_t status);