Re: [RFC PATCH v4 14/28] Add support to access boot related data in the clear

[Tom Lendacky]

On 3/8/2017 12:55 AM, Dave Young wrote:

On 02/16/17 at 09:45am, Tom Lendacky wrote:
[snip]

+ * This function determines if an address should be mapped encrypted.
+ * Boot setup data, EFI data and E820 areas are checked in making this
+ * determination.
+ */
+static bool memremap_should_map_encrypted(resource_size_t phys_addr,
+ unsigned long size)
+{
+   /*
+* SME is not active, return true:
+*   - For early_memremap_pgprot_adjust(), returning true or false
+* results in the same protection value
+*   - For arch_memremap_do_ram_remap(), returning true will allow
+* the RAM remap to occur instead of falling back to ioremap()
+*/
+   if (!sme_active())
+   return true;


From the function name shouldn't above be return false?


I've re-worked this so that the check is in a different location and
doesn't cause confusion.




+
+   /* Check if the address is part of the setup data */
+   if (memremap_is_setup_data(phys_addr, size))
+   return false;
+
+   /* Check if the address is part of EFI boot/runtime data */
+   switch (efi_mem_type(phys_addr)) {
+   case EFI_BOOT_SERVICES_DATA:
+   case EFI_RUNTIME_SERVICES_DATA:


Only these two types needed? I'm not sure about this, just bring up the
question.


I've re-worked this code so that there is a single EFI routine that
checks boot_params.efi_info.efi_memmap/efi_systab, EFI tables and the
EFI memtype.  As for the EFI memtypes, I believe those are the only
ones required.  Some of the other types will be picked up by the e820
checks (ACPI, NVS, etc.).

Thanks,
Tom




+   return false;
+   default:
+   break;
+   }
+
+   /* Check if the address is outside kernel usable area */
+   switch (e820__get_entry_type(phys_addr, phys_addr + size - 1)) {
+   case E820_TYPE_RESERVED:
+   case E820_TYPE_ACPI:
+   case E820_TYPE_NVS:
+   case E820_TYPE_UNUSABLE:
+   return false;
+   default:
+   break;
+   }
+
+   return true;
+}
+


Thanks
Dave


___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [RFC PATCH v4 14/28] Add support to access boot related data in the clear

[Dave Young]

On 02/16/17 at 09:45am, Tom Lendacky wrote:
[snip]
> + * This function determines if an address should be mapped encrypted.
> + * Boot setup data, EFI data and E820 areas are checked in making this
> + * determination.
> + */
> +static bool memremap_should_map_encrypted(resource_size_t phys_addr,
> +   unsigned long size)
> +{
> + /*
> +  * SME is not active, return true:
> +  *   - For early_memremap_pgprot_adjust(), returning true or false
> +  * results in the same protection value
> +  *   - For arch_memremap_do_ram_remap(), returning true will allow
> +  * the RAM remap to occur instead of falling back to ioremap()
> +  */
> + if (!sme_active())
> + return true;

>From the function name shouldn't above be return false? 

> +
> + /* Check if the address is part of the setup data */
> + if (memremap_is_setup_data(phys_addr, size))
> + return false;
> +
> + /* Check if the address is part of EFI boot/runtime data */
> + switch (efi_mem_type(phys_addr)) {
> + case EFI_BOOT_SERVICES_DATA:
> + case EFI_RUNTIME_SERVICES_DATA:

Only these two types needed? I'm not sure about this, just bring up the
question.

> + return false;
> + default:
> + break;
> + }
> +
> + /* Check if the address is outside kernel usable area */
> + switch (e820__get_entry_type(phys_addr, phys_addr + size - 1)) {
> + case E820_TYPE_RESERVED:
> + case E820_TYPE_ACPI:
> + case E820_TYPE_NVS:
> + case E820_TYPE_UNUSABLE:
> + return false;
> + default:
> + break;
> + }
> +
> + return true;
> +}
> +

Thanks
Dave
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [RFC PATCH v4 14/28] Add support to access boot related data in the clear

[Borislav Petkov]

On Fri, Feb 24, 2017 at 09:04:21AM -0600, Tom Lendacky wrote:
> I looked at doing that but you get into this cyclical situation unless
> you specifically map each setup data elemement as decrypted. This is ok
> for early_memremap since we have early_memremap_decrypted() but a new
> memremap_decrypted() would have to be added. But I was trying to avoid
> having to do multiple mapping calls inside the current mapping call.
> 
> I can always look at converting the setup_data_list from an array
> into a list to eliminate the 32 entry limit, too.
> 
> Let me look at adding the early_memremap_decrypted() type support to
> memremap() and see how that looks.

Yes, so this sounds better than the cyclic thing you explained
where you have to add and update since early_memremap() calls into
memremap_should_map_encrypted() which touches the list we're updating at
the same time.

So in the case where you absolutely know that those ranges should
be mapped decrypted, we should have special helpers which do that
explicitly and they are called when we access those special regions.
Well, special for SME. I'm thinking that should simplify the handling
but you'll know better once you write it. :)

Thanks.

-- 
Regards/Gruss,
Boris.

Good mailing practices for 400: avoid top-posting and trim the reply.
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [RFC PATCH v4 14/28] Add support to access boot related data in the clear

[Tom Lendacky]

On 2/24/2017 4:21 AM, Borislav Petkov wrote:

On Thu, Feb 23, 2017 at 03:34:30PM -0600, Tom Lendacky wrote:

Hmm... maybe I'm missing something here.  This doesn't have anything to
do with kexec or efi_reuse_config.  This has to do with the fact that


I said kexec because kexec uses the setup_data mechanism to pass config
tables to the second kernel, for example.


when a system boots the setup data and the EFI data are not encrypted.
Since it's not encrypted we need to be sure that any early_memremap()
and memremap() calls remove the encryption mask from the resulting
pagetable entry that is created so the data can be accessed properly.


Anyway, I'd prefer not to do this ad-hoc caching if it can be
helped. You're imposing an arbitrary limit of 32 there which the
setup_data linked list doesn't have. So if you really want to go
inspect those elements, you could iterate over them starting from
boot_params.hdr.setup_data, just like parse_setup_data() does. Most of
the time that list should be non-existent and if it is, it will be short
anyway.



I looked at doing that but you get into this cyclical situation unless
you specifically map each setup data elemement as decrypted. This is ok
for early_memremap since we have early_memremap_decrypted() but a new
memremap_decrypted() would have to be added. But I was trying to avoid
having to do multiple mapping calls inside the current mapping call.

I can always look at converting the setup_data_list from an array
into a list to eliminate the 32 entry limit, too.

Let me look at adding the early_memremap_decrypted() type support to
memremap() and see how that looks.


And if we really decide that we need to cache it for later inspection
due to speed considerations, as you do in memremap_is_setup_data(), you
could do that in the default: branch of parse_setup_data() and do it
just once: I don't see why you need to do add_to_setup_data_list() *and*
update_setup_data_list() when you could add both pointer and updated
size once.


I do the add followed by the update because we can't determine the true
size of the setup data until it is first mapped so that the data->len
field can be accessed. In order to map it properly the physical
address range needs to be added to the list before it is mapped. After
it's mapped, the true physical address range can be calculated and
updated.

Thanks,
Tom




___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [RFC PATCH v4 14/28] Add support to access boot related data in the clear

[Borislav Petkov]

On Thu, Feb 23, 2017 at 03:34:30PM -0600, Tom Lendacky wrote:
> Hmm... maybe I'm missing something here.  This doesn't have anything to
> do with kexec or efi_reuse_config.  This has to do with the fact that

I said kexec because kexec uses the setup_data mechanism to pass config
tables to the second kernel, for example.

> when a system boots the setup data and the EFI data are not encrypted.
> Since it's not encrypted we need to be sure that any early_memremap()
> and memremap() calls remove the encryption mask from the resulting
> pagetable entry that is created so the data can be accessed properly.

Anyway, I'd prefer not to do this ad-hoc caching if it can be
helped. You're imposing an arbitrary limit of 32 there which the
setup_data linked list doesn't have. So if you really want to go
inspect those elements, you could iterate over them starting from
boot_params.hdr.setup_data, just like parse_setup_data() does. Most of
the time that list should be non-existent and if it is, it will be short
anyway.

And if we really decide that we need to cache it for later inspection
due to speed considerations, as you do in memremap_is_setup_data(), you
could do that in the default: branch of parse_setup_data() and do it
just once: I don't see why you need to do add_to_setup_data_list() *and*
update_setup_data_list() when you could add both pointer and updated
size once.

-- 
Regards/Gruss,
Boris.

Good mailing practices for 400: avoid top-posting and trim the reply.
___
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [RFC PATCH v4 14/28] Add support to access boot related data in the clear

[Tom Lendacky]

On 2/21/2017 9:06 AM, Borislav Petkov wrote:

On Thu, Feb 16, 2017 at 09:45:09AM -0600, Tom Lendacky wrote:

Boot data (such as EFI related data) is not encrypted when the system is
booted and needs to be mapped decrypted.  Add support to apply the proper
attributes to the EFI page tables and to the early_memremap and memremap
APIs to identify the type of data being accessed so that the proper
encryption attribute can be applied.


So this doesn't even begin to explain *why* we need this. The emphasis
being on *why*.

Lemme guess? kexec? And because of efi_reuse_config?


Hmm... maybe I'm missing something here.  This doesn't have anything to
do with kexec or efi_reuse_config.  This has to do with the fact that
when a system boots the setup data and the EFI data are not encrypted.
Since it's not encrypted we need to be sure that any early_memremap()
and memremap() calls remove the encryption mask from the resulting
pagetable entry that is created so the data can be accessed properly.



If so, then that whole ad-hoc caching in parse_setup_data() needs to go.
Especially if efi_reuse_config() already sees those addresses so while
we're there, we could save them somewhere or whatnot. But not doing the
whole thing again in parse_setup_data().


Signed-off-by: Tom Lendacky 
---
 arch/x86/include/asm/io.h  |3 +
 arch/x86/include/asm/setup.h   |8 +++
 arch/x86/kernel/setup.c|   33 
 arch/x86/mm/ioremap.c  |  111 
 arch/x86/platform/efi/efi_64.c |   16 --
 kernel/memremap.c  |   11 
 mm/early_ioremap.c |   18 +-
 7 files changed, 192 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 7afb0e2..833f7cc 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -381,4 +381,7 @@ extern int __must_check arch_phys_wc_add(unsigned long base,
 #define arch_io_reserve_memtype_wc arch_io_reserve_memtype_wc
 #endif

+extern bool arch_memremap_do_ram_remap(resource_size_t offset, size_t size);
+#define arch_memremap_do_ram_remap arch_memremap_do_ram_remap
+
 #endif /* _ASM_X86_IO_H */
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index ac1d5da..8d9 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -63,6 +63,14 @@ static inline void x86_ce4100_early_setup(void) { }
 #include 
 #include 

+struct setup_data_attrs {
+   u64 paddr;
+   unsigned long size;
+};
+
+extern struct setup_data_attrs setup_data_list[];
+extern unsigned int setup_data_list_count;
+
 /*
  * This is set up by the setup-routine at boot-time
  */
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index bd5b9a7..d2234bf 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -148,6 +148,9 @@ int default_check_phys_apicid_present(int phys_apicid)

 struct boot_params boot_params;

+struct setup_data_attrs setup_data_list[32];
+unsigned int setup_data_list_count;
+
 /*
  * Machine setup..
  */
@@ -419,6 +422,32 @@ static void __init reserve_initrd(void)
 }
 #endif /* CONFIG_BLK_DEV_INITRD */

+static void __init update_setup_data_list(u64 pa_data, unsigned long size)
+{
+   unsigned int i;
+
+   for (i = 0; i < setup_data_list_count; i++) {
+   if (setup_data_list[i].paddr != pa_data)
+   continue;
+
+   setup_data_list[i].size = size;
+   break;
+   }
+}
+
+static void __init add_to_setup_data_list(u64 pa_data, unsigned long size)
+{
+   if (!sme_active())
+   return;
+
+   if (!WARN(setup_data_list_count == ARRAY_SIZE(setup_data_list),
+ "exceeded maximum setup data list slots")) {
+   setup_data_list[setup_data_list_count].paddr = pa_data;
+   setup_data_list[setup_data_list_count].size = size;
+   setup_data_list_count++;
+   }
+}
+
 static void __init parse_setup_data(void)
 {
struct setup_data *data;
@@ -428,12 +457,16 @@ static void __init parse_setup_data(void)
while (pa_data) {
u32 data_len, data_type;

+   add_to_setup_data_list(pa_data, sizeof(*data));
+
data = early_memremap(pa_data, sizeof(*data));
data_len = data->len + sizeof(struct setup_data);
data_type = data->type;
pa_next = data->next;
early_memunmap(data, sizeof(*data));

+   update_setup_data_list(pa_data, data_len);
+
switch (data_type) {
case SETUP_E820_EXT:
e820__memory_setup_extended(pa_data, data_len);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 2385e70..b0ff6bc 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -13,6 +13,7 @@
 #include 
 #include 
 #include 
+#include 

 #include 
 #include 
@@ -21,6 +22,7 @@
 #include